Merge branch 'for-next/core' into for-kernelci
diff --git a/.mailmap b/.mailmap
index 8284692..9f41b39 100644
--- a/.mailmap
+++ b/.mailmap
@@ -38,6 +38,16 @@
Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
Alexey Makhalov <alexey.amakhalov@broadcom.com> <amakhalov@vmware.com>
+Alex Elder <elder@kernel.org>
+Alex Elder <elder@kernel.org> <aelder@sgi.com>
+Alex Elder <elder@kernel.org> <alex.elder@linaro.org>
+Alex Elder <elder@kernel.org> <alex.elder@linary.org>
+Alex Elder <elder@kernel.org> <elder@dreamhost.com>
+Alex Elder <elder@kernel.org> <elder@dreawmhost.com>
+Alex Elder <elder@kernel.org> <elder@ieee.org>
+Alex Elder <elder@kernel.org> <elder@inktank.com>
+Alex Elder <elder@kernel.org> <elder@linaro.org>
+Alex Elder <elder@kernel.org> <elder@newdream.net>
Alex Hung <alexhung@gmail.com> <alex.hung@canonical.com>
Alex Shi <alexs@kernel.org> <alex.shi@intel.com>
Alex Shi <alexs@kernel.org> <alex.shi@linaro.org>
@@ -98,6 +108,8 @@
Ben Widawsky <bwidawsk@kernel.org> <ben.widawsky@intel.com>
Ben Widawsky <bwidawsk@kernel.org> <benjamin.widawsky@intel.com>
Benjamin Poirier <benjamin.poirier@gmail.com> <bpoirier@suse.de>
+Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@gmail.com>
+Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@redhat.com>
Bjorn Andersson <andersson@kernel.org> <bjorn@kryo.se>
Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@linaro.org>
Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@sonymobile.com>
@@ -446,7 +458,8 @@
Nadav Amit <nadav.amit@gmail.com> <namit@vmware.com>
Nadav Amit <nadav.amit@gmail.com> <namit@cs.technion.ac.il>
Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com>
-Naoya Horiguchi <naoya.horiguchi@nec.com> <n-horiguchi@ah.jp.nec.com>
+Naoya Horiguchi <nao.horiguchi@gmail.com> <n-horiguchi@ah.jp.nec.com>
+Naoya Horiguchi <nao.horiguchi@gmail.com> <naoya.horiguchi@nec.com>
Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
Neeraj Upadhyay <quic_neeraju@quicinc.com> <neeraju@codeaurora.org>
Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com>
@@ -499,6 +512,7 @@
Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com> <pradeepc@codeaurora.org>
Prasad Sodagudi <quic_psodagud@quicinc.com> <psodagud@codeaurora.org>
Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com>
+Puranjay Mohan <puranjay@kernel.org> <puranjay12@gmail.com>
Qais Yousef <qyousef@layalina.io> <qais.yousef@imgtec.com>
Qais Yousef <qyousef@layalina.io> <qais.yousef@arm.com>
Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com>
@@ -524,6 +538,7 @@
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>
+Richard Genoud <richard.genoud@bootlin.com> <richard.genoud@gmail.com>
Richard Leitner <richard.leitner@linux.dev> <dev@g0hl1n.net>
Richard Leitner <richard.leitner@linux.dev> <me@g0hl1n.net>
Richard Leitner <richard.leitner@linux.dev> <richard.leitner@skidata.com>
diff --git a/CREDITS b/CREDITS
index c55c5a0..0107047 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3146,6 +3146,10 @@
S: 13353 Berlin
S: Germany
+N: Gustavo Pimental
+E: gustavo.pimentel@synopsys.com
+D: PCI driver for Synopsys DesignWare
+
N: Emanuel Pirker
E: epirker@edu.uni-klu.ac.at
D: AIC5800 IEEE 1394, RAW I/O on 1394
diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index cce768a..25a04cd 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -138,11 +138,10 @@
the BHB might be shared across privilege levels even in the presence of
Enhanced IBRS.
-Currently the only known real-world BHB attack vector is via
-unprivileged eBPF. Therefore, it's highly recommended to not enable
-unprivileged eBPF, especially when eIBRS is used (without retpolines).
-For a full mitigation against BHB attacks, it's recommended to use
-retpolines (or eIBRS combined with retpolines).
+Previously the only known real-world BHB attack vector was via unprivileged
+eBPF. Further research has found attacks that don't require unprivileged eBPF.
+For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or
+use the BHB clearing sequence.
Attack scenarios
----------------
@@ -430,6 +429,23 @@
'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB
=========================== =======================================================
+ - Branch History Injection (BHI) protection status:
+
+.. list-table::
+
+ * - BHI: Not affected
+ - System is not affected
+ * - BHI: Retpoline
+ - System is protected by retpoline
+ * - BHI: BHI_DIS_S
+ - System is protected by BHI_DIS_S
+ * - BHI: SW loop, KVM SW loop
+ - System is protected by software clearing sequence
+ * - BHI: Vulnerable
+ - System is vulnerable to BHI
+ * - BHI: Vulnerable, KVM: SW loop
+ - System is vulnerable; KVM is protected by software clearing sequence
+
Full mitigation might require a microcode update from the CPU
vendor. When the necessary microcode is not available, the kernel will
report vulnerability.
@@ -484,7 +500,11 @@
Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at
boot, by setting the IBRS bit, and they're automatically protected against
- Spectre v2 variant attacks.
+ some Spectre v2 variant attacks. The BHB can still influence the choice of
+ indirect branch predictor entry, and although branch predictor entries are
+ isolated between modes when eIBRS is enabled, the BHB itself is not isolated
+ between modes. Systems which support BHI_DIS_S will set it to protect against
+ BHI attacks.
On Intel's enhanced IBRS systems, this includes cross-thread branch target
injections on SMT systems (STIBP). In other words, Intel eIBRS enables
@@ -638,6 +658,18 @@
spectre_v2=off. Spectre variant 1 mitigations
cannot be disabled.
+ spectre_bhi=
+
+ [X86] Control mitigation of Branch History Injection
+ (BHI) vulnerability. This setting affects the deployment
+ of the HW BHI control and the SW BHB clearing sequence.
+
+ on
+ (default) Enable the HW or SW mitigation as
+ needed.
+ off
+ Disable the mitigation.
+
For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt
Mitigation selection guide
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index afd6fcc..8e3e33c 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3426,6 +3426,9 @@
arch-independent options, each of which is an
aggregation of existing arch-specific options.
+ Note, "mitigations" is supported if and only if the
+ kernel was built with CPU_MITIGATIONS=y.
+
off
Disable all optional CPU mitigations. This
improves system performance, but it may also
@@ -3447,6 +3450,7 @@
retbleed=off [X86]
spec_rstack_overflow=off [X86]
spec_store_bypass_disable=off [X86,PPC]
+ spectre_bhi=off [X86]
spectre_v2_user=off [X86]
srbds=off [X86,INTEL]
ssbd=force-off [ARM64]
@@ -6066,6 +6070,15 @@
sonypi.*= [HW] Sony Programmable I/O Control Device driver
See Documentation/admin-guide/laptops/sonypi.rst
+ spectre_bhi= [X86] Control mitigation of Branch History Injection
+ (BHI) vulnerability. This setting affects the
+ deployment of the HW BHI control and the SW BHB
+ clearing sequence.
+
+ on - (default) Enable the HW or SW mitigation
+ as needed.
+ off - Disable the mitigation.
+
spectre_v2= [X86,EARLY] Control mitigation of Spectre variant 2
(indirect branch speculation) vulnerability.
The default operation protects the kernel from
diff --git a/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst b/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst
index d350482..c389d4f 100644
--- a/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst
+++ b/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst
@@ -29,7 +29,7 @@
========================================
*[If you are new to building or bisecting Linux, ignore this section and head
-over to the* ":ref:`step-by-step guide<introguide_bissbs>`" *below. It utilizes
+over to the* ':ref:`step-by-step guide <introguide_bissbs>`' *below. It utilizes
the same commands as this section while describing them in brief fashion. The
steps are nevertheless easy to follow and together with accompanying entries
in a reference section mention many alternatives, pitfalls, and additional
@@ -38,8 +38,8 @@
**In case you want to check if a bug is present in code currently supported by
developers**, execute just the *preparations* and *segment 1*; while doing so,
consider the newest Linux kernel you regularly use to be the 'working' kernel.
-In the following example that's assumed to be 6.0.13, which is why the sources
-of 6.0 will be used to prepare the .config file.
+In the following example that's assumed to be 6.0, which is why its sources
+will be used to prepare the .config file.
**In case you face a regression**, follow the steps at least till the end of
*segment 2*. Then you can submit a preliminary report -- or continue with
@@ -61,7 +61,7 @@
cd ~/linux/
git remote add -t master stable \
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
- git checkout --detach v6.0
+ git switch --detach v6.0
# * Hint: if you used an existing clone, ensure no stale .config is around.
make olddefconfig
# * Ensure the former command picked the .config of the 'working' kernel.
@@ -87,7 +87,7 @@
a) Checking out latest mainline code::
cd ~/linux/
- git checkout --force --detach mainline/master
+ git switch --discard-changes --detach mainline/master
b) Build, install, and boot a kernel::
@@ -125,7 +125,7 @@
a) Start by checking out the sources of the 'good' version::
cd ~/linux/
- git checkout --force --detach v6.0
+ git switch --discard-changes --detach v6.0
b) Build, install, and boot a kernel as described earlier in *segment 1,
section b* -- just feel free to skip the 'du' commands, as you have a rough
@@ -136,8 +136,7 @@
* **Segment 3**: perform and validate the bisection.
- a) In case your 'broken' version is a stable/longterm release, add the Git
- branch holding it::
+ a) Retrieve the sources for your 'bad' version::
git remote set-branches --add stable linux-6.1.y
git fetch stable
@@ -157,11 +156,12 @@
works with the newly built kernel. If it does, tell Git by executing
``git bisect good``; if it does not, run ``git bisect bad`` instead.
- All three commands will make Git checkout another commit; then re-execute
+ All three commands will make Git check out another commit; then re-execute
this step (e.g. build, install, boot, and test a kernel to then tell Git
the outcome). Do so again and again until Git shows which commit broke
things. If you run short of disk space during this process, check the
- "Supplementary tasks" section below.
+ section 'Complementary tasks: cleanup during and after the process'
+ below.
d) Once your finished the bisection, put a few things away::
@@ -172,14 +172,17 @@
e) Try to verify the bisection result::
- git checkout --force --detach mainline/master
+ git switch --discard-changes --detach mainline/master
git revert --no-edit cafec0cacaca0
+ cp ~/kernel-config-working .config
+ ./scripts/config --set-str CONFIG_LOCALVERSION '-local-cafec0cacaca0-reverted'
This is optional, as some commits are impossible to revert. But if the
second command worked flawlessly, build, install, and boot one more kernel
- kernel, which should not show the regression.
+ kernel; just this time skip the first command copying the base .config file
+ over, as that already has been taken care off.
-* **Supplementary tasks**: cleanup during and after the process.
+* **Complementary tasks**: cleanup during and after the process.
a) To avoid running out of disk space during a bisection, you might need to
remove some kernels you built earlier. You most likely want to keep those
@@ -202,13 +205,25 @@
the kernels you built earlier and later you might want to keep around for
a week or two.
+* **Optional task**: test a debug patch or a proposed fix later::
+
+ git fetch mainline
+ git switch --discard-changes --detach mainline/master
+ git apply /tmp/foobars-proposed-fix-v1.patch
+ cp ~/kernel-config-working .config
+ ./scripts/config --set-str CONFIG_LOCALVERSION '-local-foobars-fix-v1'
+
+ Build, install, and boot a kernel as described in *segment 1, section b* --
+ but this time omit the first command copying the build configuration over,
+ as that has been taken care of already.
+
.. _introguide_bissbs:
Step-by-step guide on how to verify bugs and bisect regressions
===============================================================
This guide describes how to set up your own Linux kernels for investigating bugs
-or regressions you intent to report. How far you want to follow the instructions
+or regressions you intend to report. How far you want to follow the instructions
depends on your issue:
Execute all steps till the end of *segment 1* to **verify if your kernel problem
@@ -221,15 +236,17 @@
*segment 3* to **perform a bisection** for a full-fledged regression report
developers are obliged to act upon.
- :ref:`Preparations: set up everything to build your own kernels.<introprep_bissbs>`
+ :ref:`Preparations: set up everything to build your own kernels <introprep_bissbs>`.
- :ref:`Segment 1: try to reproduce the problem with the latest codebase.<introlatestcheck_bissbs>`
+ :ref:`Segment 1: try to reproduce the problem with the latest codebase <introlatestcheck_bissbs>`.
- :ref:`Segment 2: check if the kernels you build work fine.<introworkingcheck_bissbs>`
+ :ref:`Segment 2: check if the kernels you build work fine <introworkingcheck_bissbs>`.
- :ref:`Segment 3: perform a bisection and validate the result.<introbisect_bissbs>`
+ :ref:`Segment 3: perform a bisection and validate the result <introbisect_bissbs>`.
- :ref:`Supplementary tasks: cleanup during and after following this guide.<introclosure_bissbs>`
+ :ref:`Complementary tasks: cleanup during and after following this guide <introclosure_bissbs>`.
+
+ :ref:`Optional tasks: test reverts, patches, or later versions <introoptional_bissbs>`.
The steps in each segment illustrate the important aspects of the process, while
a comprehensive reference section holds additional details for almost all of the
@@ -240,24 +257,35 @@
For further details on how to report Linux kernel issues or regressions check
out Documentation/admin-guide/reporting-issues.rst, which works in conjunction
with this document. It among others explains why you need to verify bugs with
-the latest 'mainline' kernel, even if you face a problem with a kernel from a
-'stable/longterm' series; for users facing a regression it also explains that
-sending a preliminary report after finishing segment 2 might be wise, as the
-regression and its culprit might be known already. For further details on
-what actually qualifies as a regression check out
-Documentation/admin-guide/reporting-regressions.rst.
+the latest 'mainline' kernel (e.g. versions like 6.0, 6.1-rc1, or 6.1-rc6),
+even if you face a problem with a kernel from a 'stable/longterm' series
+(say 6.0.13).
+
+For users facing a regression that document also explains why sending a
+preliminary report after segment 2 might be wise, as the regression and its
+culprit might be known already. For further details on what actually qualifies
+as a regression check out Documentation/admin-guide/reporting-regressions.rst.
+
+If you run into any problems while following this guide or have ideas how to
+improve it, :ref:`please let the kernel developers know <submit_improvements>`.
.. _introprep_bissbs:
Preparations: set up everything to build your own kernels
---------------------------------------------------------
+The following steps lay the groundwork for all further tasks.
+
+Note: the instructions assume you are building and testing on the same
+machine; if you want to compile the kernel on another system, check
+:ref:`Build kernels on a different machine <buildhost_bis>` below.
+
.. _backup_bissbs:
* Create a fresh backup and put system repair and restore tools at hand, just
to be prepared for the unlikely case of something going sideways.
- [:ref:`details<backup_bisref>`]
+ [:ref:`details <backup_bisref>`]
.. _vanilla_bissbs:
@@ -265,7 +293,7 @@
builds them automatically. That includes but is not limited to DKMS, openZFS,
VirtualBox, and Nvidia's graphics drivers (including the GPLed kernel module).
- [:ref:`details<vanilla_bisref>`]
+ [:ref:`details <vanilla_bisref>`]
.. _secureboot_bissbs:
@@ -276,48 +304,49 @@
their restrictions through a process initiated by
``mokutil --disable-validation``.
- [:ref:`details<secureboot_bisref>`]
+ [:ref:`details <secureboot_bisref>`]
.. _rangecheck_bissbs:
* Determine the kernel versions considered 'good' and 'bad' throughout this
- guide.
+ guide:
- Do you follow this guide to verify if a bug is present in the code developers
- care for? Then consider the mainline release your 'working' kernel (the newest
- one you regularly use) is based on to be the 'good' version; if your 'working'
- kernel for example is 6.0.11, then your 'good' kernel is 6.0.
+ * Do you follow this guide to verify if a bug is present in the code the
+ primary developers care for? Then consider the version of the newest kernel
+ you regularly use currently as 'good' (e.g. 6.0, 6.0.13, or 6.1-rc2).
- In case you face a regression, it depends on the version range where the
- regression was introduced:
+ * Do you face a regression, e.g. something broke or works worse after
+ switching to a newer kernel version? In that case it depends on the version
+ range during which the problem appeared:
- * Something which used to work in Linux 6.0 broke when switching to Linux
- 6.1-rc1? Then henceforth regard 6.0 as the last known 'good' version
- and 6.1-rc1 as the first 'bad' one.
+ * Something regressed when updating from a stable/longterm release
+ (say 6.0.13) to a newer mainline series (like 6.1-rc7 or 6.1) or a
+ stable/longterm version based on one (say 6.1.5)? Then consider the
+ mainline release your working kernel is based on to be the 'good'
+ version (e.g. 6.0) and the first version to be broken as the 'bad' one
+ (e.g. 6.1-rc7, 6.1, or 6.1.5). Note, at this point it is merely assumed
+ that 6.0 is fine; this hypothesis will be checked in segment 2.
- * Some function stopped working when updating from 6.0.11 to 6.1.4? Then for
- the time being consider 6.0 as the last 'good' version and 6.1.4 as
- the 'bad' one. Note, at this point it is merely assumed that 6.0 is fine;
- this assumption will be checked in segment 2.
+ * Something regressed when switching from one mainline version (say 6.0) to
+ a later one (like 6.1-rc1) or a stable/longterm release based on it
+ (say 6.1.5)? Then regard the last working version (e.g. 6.0) as 'good' and
+ the first broken (e.g. 6.1-rc1 or 6.1.5) as 'bad'.
- * A feature you used in 6.0.11 does not work at all or worse in 6.1.13? In
- that case you want to bisect within a stable/longterm series: consider
- 6.0.11 as the last known 'good' version and 6.0.13 as the first 'bad'
- one. Note, in this case you still want to compile and test a mainline kernel
- as explained in segment 1: the outcome will determine if you need to report
- your issue to the regular developers or the stable team.
+ * Something regressed when updating within a stable/longterm series (say
+ from 6.0.13 to 6.0.15)? Then consider those versions as 'good' and 'bad'
+ (e.g. 6.0.13 and 6.0.15), as you need to bisect within that series.
*Note, do not confuse 'good' version with 'working' kernel; the latter term
throughout this guide will refer to the last kernel that has been working
fine.*
- [:ref:`details<rangecheck_bisref>`]
+ [:ref:`details <rangecheck_bisref>`]
.. _bootworking_bissbs:
* Boot into the 'working' kernel and briefly use the apparently broken feature.
- [:ref:`details<bootworking_bisref>`]
+ [:ref:`details <bootworking_bisref>`]
.. _diskspace_bissbs:
@@ -327,7 +356,7 @@
debug symbols: both explain approaches reducing the amount of space, which
should allow you to master these tasks with about 4 Gigabytes free space.
- [:ref:`details<diskspace_bisref>`]
+ [:ref:`details <diskspace_bisref>`]
.. _buildrequires_bissbs:
@@ -337,7 +366,7 @@
reference section shows how to quickly install those on various popular Linux
distributions.
- [:ref:`details<buildrequires_bisref>`]
+ [:ref:`details <buildrequires_bisref>`]
.. _sources_bissbs:
@@ -360,14 +389,23 @@
git remote add -t master stable \
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
- [:ref:`details<sources_bisref>`]
+ [:ref:`details <sources_bisref>`]
+
+.. _stablesources_bissbs:
+
+* Is one of the versions you earlier established as 'good' or 'bad' a stable or
+ longterm release (say 6.1.5)? Then download the code for the series it belongs
+ to ('linux-6.1.y' in this example)::
+
+ git remote set-branches --add stable linux-6.1.y
+ git fetch stable
.. _oldconfig_bissbs:
* Start preparing a kernel build configuration (the '.config' file).
Before doing so, ensure you are still running the 'working' kernel an earlier
- step told you to boot; if you are unsure, check the current kernel release
+ step told you to boot; if you are unsure, check the current kernelrelease
identifier using ``uname -r``.
Afterwards check out the source code for the version earlier established as
@@ -375,7 +413,7 @@
the version number in this and all later Git commands needs to be prefixed
with a 'v'::
- git checkout --detach v6.0
+ git switch --discard-changes --detach v6.0
Now create a build configuration file::
@@ -398,7 +436,7 @@
'make olddefconfig' again and check if it now picked up the right config file
as base.
- [:ref:`details<oldconfig_bisref>`]
+ [:ref:`details <oldconfig_bisref>`]
.. _localmodconfig_bissbs:
@@ -432,7 +470,7 @@
spending much effort on, as long as it boots and allows to properly test the
feature that causes trouble.
- [:ref:`details<localmodconfig_bisref>`]
+ [:ref:`details <localmodconfig_bisref>`]
.. _tagging_bissbs:
@@ -442,7 +480,7 @@
./scripts/config --set-str CONFIG_LOCALVERSION '-local'
./scripts/config -e CONFIG_LOCALVERSION_AUTO
- [:ref:`details<tagging_bisref>`]
+ [:ref:`details <tagging_bisref>`]
.. _debugsymbols_bissbs:
@@ -461,7 +499,7 @@
./scripts/config -d DEBUG_INFO -d DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT \
-d DEBUG_INFO_DWARF4 -d DEBUG_INFO_DWARF5 -e CONFIG_DEBUG_INFO_NONE
- [:ref:`details<debugsymbols_bisref>`]
+ [:ref:`details <debugsymbols_bisref>`]
.. _configmods_bissbs:
@@ -471,14 +509,14 @@
* Are you running Debian? Then you want to avoid known problems by performing
additional adjustments explained in the reference section.
- [:ref:`details<configmods_distros_bisref>`].
+ [:ref:`details <configmods_distros_bisref>`].
* If you want to influence other aspects of the configuration, do so now using
your preferred tool. Note, to use make targets like 'menuconfig' or
'nconfig', you will need to install the development files of ncurses; for
'xconfig' you likewise need the Qt5 or Qt6 headers.
- [:ref:`details<configmods_individual_bisref>`].
+ [:ref:`details <configmods_individual_bisref>`].
.. _saveconfig_bissbs:
@@ -488,7 +526,7 @@
make olddefconfig
cp .config ~/kernel-config-working
- [:ref:`details<saveconfig_bisref>`]
+ [:ref:`details <saveconfig_bisref>`]
.. _introlatestcheck_bissbs:
@@ -498,16 +536,30 @@
The following steps verify if the problem occurs with the code currently
supported by developers. In case you face a regression, it also checks that the
problem is not caused by some .config change, as reporting the issue then would
-be a waste of time. [:ref:`details<introlatestcheck_bisref>`]
+be a waste of time. [:ref:`details <introlatestcheck_bisref>`]
.. _checkoutmaster_bissbs:
-* Check out the latest Linux codebase::
+* Check out the latest Linux codebase.
- cd ~/linux/
- git checkout --force --detach mainline/master
+ * Are your 'good' and 'bad' versions from the same stable or longterm series?
+ Then check the `front page of kernel.org <https://kernel.org/>`_: if it
+ lists a release from that series without an '[EOL]' tag, checkout the series
+ latest version ('linux-6.1.y' in the following example)::
- [:ref:`details<checkoutmaster_bisref>`]
+ cd ~/linux/
+ git switch --discard-changes --detach stable/linux-6.1.y
+
+ Your series is unsupported, if is not listed or carrying a 'end of life'
+ tag. In that case you might want to check if a successor series (say
+ linux-6.2.y) or mainline (see next point) fix the bug.
+
+ * In all other cases, run::
+
+ cd ~/linux/
+ git switch --discard-changes --detach mainline/master
+
+ [:ref:`details <checkoutmaster_bisref>`]
.. _build_bissbs:
@@ -522,7 +574,7 @@
reference section for alternatives, which obviously will require other
steps to install as well.
- [:ref:`details<build_bisref>`]
+ [:ref:`details <build_bisref>`]
.. _install_bissbs:
@@ -555,7 +607,7 @@
down: if you will build more kernels as described in segment 2 and 3, you will
have to perform those again after executing ``command -v installkernel [...]``.
- [:ref:`details<install_bisref>`]
+ [:ref:`details <install_bisref>`]
.. _storagespace_bissbs:
@@ -568,7 +620,7 @@
Write down or remember those two values for later: they enable you to prevent
running out of disk space accidentally during a bisection.
- [:ref:`details<storagespace_bisref>`]
+ [:ref:`details <storagespace_bisref>`]
.. _kernelrelease_bissbs:
@@ -595,7 +647,7 @@
If that command does not return '0', check the reference section, as the cause
for this might interfere with your testing.
- [:ref:`details<tainted_bisref>`]
+ [:ref:`details <tainted_bisref>`]
.. _recheckbroken_bissbs:
@@ -603,21 +655,19 @@
out the instructions in the reference section to ensure nothing went sideways
during your tests.
- [:ref:`details<recheckbroken_bisref>`]
+ [:ref:`details <recheckbroken_bisref>`]
.. _recheckstablebroken_bissbs:
-* Are you facing a problem within a stable/longterm series, but failed to
- reproduce it with the mainline kernel you just built? One that according to
- the `front page of kernel.org <https://kernel.org/>`_ is still supported? Then
- check if the latest codebase for the particular series might already fix the
- problem. To do so, add the stable series Git branch for your 'good' kernel
- (again, this here is assumed to be 6.0) and check out the latest version::
+* Did you just built a stable or longterm kernel? And were you able to reproduce
+ the regression with it? Then you should test the latest mainline codebase as
+ well, because the result determines which developers the bug must be submitted
+ to.
+
+ To prepare that test, check out current mainline::
cd ~/linux/
- git remote set-branches --add stable linux-6.0.y
- git fetch stable
- git checkout --force --detach linux-6.0.y
+ git switch --discard-changes --detach mainline/master
Now use the checked out code to build and install another kernel using the
commands the earlier steps already described in more detail::
@@ -639,14 +689,16 @@
uname -r
cat /proc/sys/kernel/tainted
- Now verify if this kernel is showing the problem.
+ Now verify if this kernel is showing the problem. If it does, then you need
+ to report the bug to the primary developers; if it does not, report it to the
+ stable team. See Documentation/admin-guide/reporting-issues.rst for details.
- [:ref:`details<recheckstablebroken_bisref>`]
+ [:ref:`details <recheckstablebroken_bisref>`]
Do you follow this guide to verify if a problem is present in the code
currently supported by Linux kernel developers? Then you are done at this
point. If you later want to remove the kernel you just built, check out
-:ref:`Supplementary tasks: cleanup during and after following this guide<introclosure_bissbs>`.
+:ref:`Complementary tasks: cleanup during and after following this guide <introclosure_bissbs>`.
In case you face a regression, move on and execute at least the next segment
as well.
@@ -658,7 +710,7 @@
In case of a regression, you now want to ensure the trimmed configuration file
you created earlier works as expected; a bisection with the .config file
-otherwise would be a waste of time. [:ref:`details<introworkingcheck_bisref>`]
+otherwise would be a waste of time. [:ref:`details <introworkingcheck_bisref>`]
.. _recheckworking_bissbs:
@@ -669,7 +721,7 @@
'good' (once again assumed to be 6.0 here)::
cd ~/linux/
- git checkout --detach v6.0
+ git switch --discard-changes --detach v6.0
Now use the checked out code to configure, build, and install another kernel
using the commands the previous subsection explained in more detail::
@@ -693,7 +745,7 @@
Now check if this kernel works as expected; if not, consult the reference
section for further instructions.
- [:ref:`details<recheckworking_bisref>`]
+ [:ref:`details <recheckworking_bisref>`]
.. _introbisect_bissbs:
@@ -703,18 +755,11 @@
With all the preparations and precaution builds taken care of, you are now ready
to begin the bisection. This will make you build quite a few kernels -- usually
about 15 in case you encountered a regression when updating to a newer series
-(say from 6.0.11 to 6.1.3). But do not worry, due to the trimmed build
+(say from 6.0.13 to 6.1.5). But do not worry, due to the trimmed build
configuration created earlier this works a lot faster than many people assume:
overall on average it will often just take about 10 to 15 minutes to compile
each kernel on commodity x86 machines.
-* In case your 'bad' version is a stable/longterm release (say 6.1.5), add its
- stable branch, unless you already did so earlier::
-
- cd ~/linux/
- git remote set-branches --add stable linux-6.1.y
- git fetch stable
-
.. _bisectstart_bissbs:
* Start the bisection and tell Git about the versions earlier established as
@@ -725,7 +770,7 @@
git bisect good v6.0
git bisect bad v6.1.5
- [:ref:`details<bisectstart_bisref>`]
+ [:ref:`details <bisectstart_bisref>`]
.. _bisectbuild_bissbs:
@@ -745,7 +790,7 @@
If compilation fails for some reason, run ``git bisect skip`` and restart
executing the stack of commands from the beginning.
- In case you skipped the "test latest codebase" step in the guide, check its
+ In case you skipped the 'test latest codebase' step in the guide, check its
description as for why the 'df [...]' and 'make -s kernelrelease [...]'
commands are here.
@@ -754,7 +799,7 @@
totally normal to see release identifiers like '6.0-rc1-local-gcafec0cacaca0'
if you bisect between versions 6.1 and 6.2 for example.
- [:ref:`details<bisectbuild_bisref>`]
+ [:ref:`details <bisectbuild_bisref>`]
.. _bisecttest_bissbs:
@@ -794,7 +839,7 @@
might need to scroll up to see the message mentioning the culprit;
alternatively, run ``git bisect log > ~/bisection-log``.
- [:ref:`details<bisecttest_bisref>`]
+ [:ref:`details <bisecttest_bisref>`]
.. _bisectlog_bissbs:
@@ -806,7 +851,7 @@
cp .config ~/bisection-config-culprit
git bisect reset
- [:ref:`details<bisectlog_bisref>`]
+ [:ref:`details <bisectlog_bisref>`]
.. _revert_bissbs:
@@ -823,16 +868,16 @@
Begin by checking out the latest codebase depending on the range you bisected:
* Did you face a regression within a stable/longterm series (say between
- 6.0.11 and 6.0.13) that does not happen in mainline? Then check out the
+ 6.0.13 and 6.0.15) that does not happen in mainline? Then check out the
latest codebase for the affected series like this::
git fetch stable
- git checkout --force --detach linux-6.0.y
+ git switch --discard-changes --detach linux-6.0.y
* In all other cases check out latest mainline::
git fetch mainline
- git checkout --force --detach mainline/master
+ git switch --discard-changes --detach mainline/master
If you bisected a regression within a stable/longterm series that also
happens in mainline, there is one more thing to do: look up the mainline
@@ -846,27 +891,33 @@
git revert --no-edit cafec0cacaca0
- If that fails, give up trying and move on to the next step. But if it works,
- build a kernel again using the familiar command sequence::
+ If that fails, give up trying and move on to the next step; if it works,
+ adjust the tag to facilitate the identification and prevent accidentally
+ overwriting another kernel::
cp ~/kernel-config-working .config
+ ./scripts/config --set-str CONFIG_LOCALVERSION '-local-cafec0cacaca0-reverted'
+
+ Build a kernel using the familiar command sequence, just without copying the
+ the base .config over::
+
make olddefconfig &&
- make -j $(nproc --all) &&
+ make -j $(nproc --all)
# * Check if the free space suffices holding another kernel:
df -h /boot/ /lib/modules/
sudo make modules_install
command -v installkernel && sudo make install
- Make -s kernelrelease | tee -a ~/kernels-built
+ make -s kernelrelease | tee -a ~/kernels-built
reboot
- Now check one last time if the feature that made you perform a bisection work
- with that kernel.
+ Now check one last time if the feature that made you perform a bisection works
+ with that kernel: if everything went well, it should not show the regression.
- [:ref:`details<revert_bisref>`]
+ [:ref:`details <revert_bisref>`]
.. _introclosure_bissbs:
-Supplementary tasks: cleanup during and after the bisection
+Complementary tasks: cleanup during and after the bisection
-----------------------------------------------------------
During and after following this guide you might want or need to remove some of
@@ -903,7 +954,7 @@
kernel image and related files behind; in that case remove them as described
in the reference section.
- [:ref:`details<makeroom_bisref>`]
+ [:ref:`details <makeroom_bisref>`]
.. _finishingtouch_bissbs:
@@ -926,18 +977,99 @@
the version considered 'good', and the last three or four you compiled
during the actual bisection process.
- [:ref:`details<finishingtouch_bisref>`]
+ [:ref:`details <finishingtouch_bisref>`]
+
+.. _introoptional_bissbs:
+
+Optional: test reverts, patches, or later versions
+--------------------------------------------------
+
+While or after reporting a bug, you might want or potentially will be asked to
+test reverts, debug patches, proposed fixes, or other versions. In that case
+follow these instructions.
+
+* Update your Git clone and check out the latest code.
+
+ * In case you want to test mainline, fetch its latest changes before checking
+ its code out::
+
+ git fetch mainline
+ git switch --discard-changes --detach mainline/master
+
+ * In case you want to test a stable or longterm kernel, first add the branch
+ holding the series you are interested in (6.2 in the example), unless you
+ already did so earlier::
+
+ git remote set-branches --add stable linux-6.2.y
+
+ Then fetch the latest changes and check out the latest version from the
+ series::
+
+ git fetch stable
+ git switch --discard-changes --detach stable/linux-6.2.y
+
+* Copy your kernel build configuration over::
+
+ cp ~/kernel-config-working .config
+
+* Your next step depends on what you want to do:
+
+ * In case you just want to test the latest codebase, head to the next step,
+ you are already all set.
+
+ * In case you want to test if a revert fixes an issue, revert one or multiple
+ changes by specifying their commit ids::
+
+ git revert --no-edit cafec0cacaca0
+
+ Now give that kernel a special tag to facilitates its identification and
+ prevent accidentally overwriting another kernel::
+
+ ./scripts/config --set-str CONFIG_LOCALVERSION '-local-cafec0cacaca0-reverted'
+
+ * In case you want to test a patch, store the patch in a file like
+ '/tmp/foobars-proposed-fix-v1.patch' and apply it like this::
+
+ git apply /tmp/foobars-proposed-fix-v1.patch
+
+ In case of multiple patches, repeat this step with the others.
+
+ Now give that kernel a special tag to facilitates its identification and
+ prevent accidentally overwriting another kernel::
+
+ ./scripts/config --set-str CONFIG_LOCALVERSION '-local-foobars-fix-v1'
+
+* Build a kernel using the familiar commands, just without copying the kernel
+ build configuration over, as that has been taken care of already::
+
+ make olddefconfig &&
+ make -j $(nproc --all)
+ # * Check if the free space suffices holding another kernel:
+ df -h /boot/ /lib/modules/
+ sudo make modules_install
+ command -v installkernel && sudo make install
+ make -s kernelrelease | tee -a ~/kernels-built
+ reboot
+
+* Now verify you booted the newly built kernel and check it.
+
+[:ref:`details <introoptional_bisref>`]
.. _submit_improvements:
-This concludes the step-by-step guide.
+Conclusion
+----------
+
+You have reached the end of the step-by-step guide.
Did you run into trouble following any of the above steps not cleared up by the
reference section below? Did you spot errors? Or do you have ideas how to
-improve the guide? Then please take a moment and let the maintainer of this
+improve the guide?
+
+If any of that applies, please take a moment and let the maintainer of this
document know by email (Thorsten Leemhuis <linux@leemhuis.info>), ideally while
CCing the Linux docs mailing list (linux-doc@vger.kernel.org). Such feedback is
-vital to improve this document further, which is in everybody's interest, as it
+vital to improve this text further, which is in everybody's interest, as it
will enable more people to master the task described here -- and hopefully also
improve similar guides inspired by this one.
@@ -948,10 +1080,20 @@
This section holds additional information for almost all the items in the above
step-by-step guide.
+Preparations for building your own kernels
+------------------------------------------
+
+ *The steps in this section lay the groundwork for all further tests.*
+ [:ref:`... <introprep_bissbs>`]
+
+The steps in all later sections of this guide depend on those described here.
+
+[:ref:`back to step-by-step guide <introprep_bissbs>`].
+
.. _backup_bisref:
Prepare for emergencies
------------------------
+~~~~~~~~~~~~~~~~~~~~~~~
*Create a fresh backup and put system repair and restore tools at hand.*
[:ref:`... <backup_bissbs>`]
@@ -966,7 +1108,7 @@
.. _vanilla_bisref:
Remove anything related to externally maintained kernel modules
----------------------------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Remove all software that depends on externally developed kernel drivers or
builds them automatically.* [:ref:`...<vanilla_bissbs>`]
@@ -984,7 +1126,7 @@
.. _secureboot_bisref:
Deal with techniques like Secure Boot
--------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*On platforms with 'Secure Boot' or similar techniques, prepare everything to
ensure the system will permit your self-compiled kernel to boot later.*
@@ -1021,7 +1163,7 @@
.. _bootworking_bisref:
Boot the last kernel that was working
--------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Boot into the last working kernel and briefly recheck if the feature that
regressed really works.* [:ref:`...<bootworking_bissbs>`]
@@ -1034,7 +1176,7 @@
.. _diskspace_bisref:
Space requirements
-------------------
+~~~~~~~~~~~~~~~~~~
*Ensure to have enough free space for building Linux.*
[:ref:`... <diskspace_bissbs>`]
@@ -1052,32 +1194,32 @@
.. _rangecheck_bisref:
Bisection range
----------------
+~~~~~~~~~~~~~~~
*Determine the kernel versions considered 'good' and 'bad' throughout this
guide.* [:ref:`...<rangecheck_bissbs>`]
Establishing the range of commits to be checked is mostly straightforward,
except when a regression occurred when switching from a release of one stable
-series to a release of a later series (e.g. from 6.0.11 to 6.1.4). In that case
+series to a release of a later series (e.g. from 6.0.13 to 6.1.5). In that case
Git will need some hand holding, as there is no straight line of descent.
That's because with the release of 6.0 mainline carried on to 6.1 while the
stable series 6.0.y branched to the side. It's therefore theoretically possible
-that the issue you face with 6.1.4 only worked in 6.0.11, as it was fixed by a
+that the issue you face with 6.1.5 only worked in 6.0.13, as it was fixed by a
commit that went into one of the 6.0.y releases, but never hit mainline or the
6.1.y series. Thankfully that normally should not happen due to the way the
stable/longterm maintainers maintain the code. It's thus pretty safe to assume
6.0 as a 'good' kernel. That assumption will be tested anyway, as that kernel
will be built and tested in the segment '2' of this guide; Git would force you
-to do this as well, if you tried bisecting between 6.0.11 and 6.1.13.
+to do this as well, if you tried bisecting between 6.0.13 and 6.1.15.
[:ref:`back to step-by-step guide <rangecheck_bissbs>`]
.. _buildrequires_bisref:
Install build requirements
---------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~
*Install all software required to build a Linux kernel.*
[:ref:`...<buildrequires_bissbs>`]
@@ -1117,7 +1259,7 @@
for example might want to skip installing the development headers for ncurses,
which you will only need in case you later might want to adjust the kernel build
configuration using make the targets 'menuconfig' or 'nconfig'; likewise omit
-the headers of Qt6 is you do not plan to adjust the .config using 'xconfig'.
+the headers of Qt6 if you do not plan to adjust the .config using 'xconfig'.
You furthermore might need additional libraries and their development headers
for tasks not covered in this guide -- for example when building utilities from
@@ -1128,7 +1270,7 @@
.. _sources_bisref:
Download the sources using Git
-------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Retrieve the Linux mainline sources.*
[:ref:`...<sources_bissbs>`]
@@ -1148,7 +1290,7 @@
.. _sources_bundle_bisref:
Downloading Linux mainline sources using a bundle
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+"""""""""""""""""""""""""""""""""""""""""""""""""
Use the following commands to retrieve the Linux mainline sources using a
bundle::
@@ -1184,7 +1326,7 @@
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
Now deepen your clone's history to the second predecessor of the mainline
-release of your 'good' version. In case the latter are 6.0 or 6.0.11, 5.19 would
+release of your 'good' version. In case the latter are 6.0 or 6.0.13, 5.19 would
be the first predecessor and 5.18 the second -- hence deepen the history up to
that version::
@@ -1219,7 +1361,7 @@
.. _oldconfig_bisref:
Start defining the build configuration for your kernel
-------------------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Start preparing a kernel build configuration (the '.config' file).*
[:ref:`... <oldconfig_bissbs>`]
@@ -1279,7 +1421,7 @@
.. _localmodconfig_bisref:
Trim the build configuration for your kernel
---------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Disable any kernel modules apparently superfluous for your setup.*
[:ref:`... <localmodconfig_bissbs>`]
@@ -1328,7 +1470,7 @@
.. _tagging_bisref:
Tag the kernels about to be build
----------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Ensure all the kernels you will build are clearly identifiable using a
special tag and a unique version identifier.* [:ref:`... <tagging_bissbs>`]
@@ -1344,7 +1486,7 @@
.. _debugsymbols_bisref:
Decide to enable or disable debug symbols
------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Decide how to handle debug symbols.* [:ref:`... <debugsymbols_bissbs>`]
@@ -1373,7 +1515,7 @@
.. _configmods_bisref:
Adjust build configuration
---------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~
*Check if you may want or need to adjust some other kernel configuration
options:*
@@ -1384,7 +1526,7 @@
.. _configmods_distros_bisref:
Distro specific adjustments
-~~~~~~~~~~~~~~~~~~~~~~~~~~~
+"""""""""""""""""""""""""""
*Are you running* [:ref:`... <configmods_bissbs>`]
@@ -1409,7 +1551,7 @@
.. _configmods_individual_bisref:
Individual adjustments
-~~~~~~~~~~~~~~~~~~~~~~
+""""""""""""""""""""""
*If you want to influence the other aspects of the configuration, do so
now.* [:ref:`... <configmods_bissbs>`]
@@ -1426,13 +1568,13 @@
.. _saveconfig_bisref:
Put the .config file aside
---------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~
*Reprocess the .config after the latest changes and store it in a safe place.*
[:ref:`... <saveconfig_bissbs>`]
Put the .config you prepared aside, as you want to copy it back to the build
-directory every time during this guide before you start building another
+directory every time during this guide before you start building another
kernel. That's because going back and forth between different versions can alter
.config files in odd ways; those occasionally cause side effects that could
confuse testing or in some cases render the result of your bisection
@@ -1442,8 +1584,8 @@
.. _introlatestcheck_bisref:
-Try to reproduce the regression
------------------------------------------
+Try to reproduce the problem with the latest codebase
+-----------------------------------------------------
*Verify the regression is not caused by some .config change and check if it
still occurs with the latest codebase.* [:ref:`... <introlatestcheck_bissbs>`]
@@ -1490,28 +1632,28 @@
Your report might be ignored if you send it to the wrong party -- and even
when you get a reply there is a decent chance that developers tell you to
- evaluate which of the two cases it is before they take a closer look.
+ evaluate which of the two cases it is before they take a closer look.
[:ref:`back to step-by-step guide <introlatestcheck_bissbs>`]
.. _checkoutmaster_bisref:
Check out the latest Linux codebase
------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Check out the latest Linux codebase.*
- [:ref:`... <introlatestcheck_bissbs>`]
+ [:ref:`... <checkoutmaster_bissbs>`]
In case you later want to recheck if an ever newer codebase might fix the
problem, remember to run that ``git fetch --shallow-exclude [...]`` command
again mentioned earlier to update your local Git repository.
-[:ref:`back to step-by-step guide <introlatestcheck_bissbs>`]
+[:ref:`back to step-by-step guide <checkoutmaster_bissbs>`]
.. _build_bisref:
Build your kernel
------------------
+~~~~~~~~~~~~~~~~~
*Build the image and the modules of your first kernel using the config file
you prepared.* [:ref:`... <build_bissbs>`]
@@ -1521,7 +1663,7 @@
deb, rpm or tar file.
Dealing with build errors
-~~~~~~~~~~~~~~~~~~~~~~~~~
+"""""""""""""""""""""""""
When a build error occurs, it might be caused by some aspect of your machine's
setup that often can be fixed quickly; other times though the problem lies in
@@ -1552,11 +1694,11 @@
In the end, most issues you run into have likely been encountered and
reported by others already. That includes issues where the cause is not your
-system, but lies in the code. If you run into one of those, you might thus find a
-solution (e.g. a patch) or workaround for your issue, too.
+system, but lies in the code. If you run into one of those, you might thus find
+a solution (e.g. a patch) or workaround for your issue, too.
Package your kernel up
-~~~~~~~~~~~~~~~~~~~~~~
+""""""""""""""""""""""
The step-by-step guide uses the default make targets (e.g. 'bzImage' and
'modules' on x86) to build the image and the modules of your kernel, which later
@@ -1587,7 +1729,7 @@
.. _install_bisref:
Put the kernel in place
------------------------
+~~~~~~~~~~~~~~~~~~~~~~~
*Install the kernel you just built.* [:ref:`... <install_bissbs>`]
@@ -1630,7 +1772,7 @@
.. _storagespace_bisref:
Storage requirements per kernel
--------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Check how much storage space the kernel, its modules, and other related files
like the initramfs consume.* [:ref:`... <storagespace_bissbs>`]
@@ -1651,7 +1793,7 @@
.. _tainted_bisref:
Check if your newly built kernel considers itself 'tainted'
------------------------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Check if the kernel marked itself as 'tainted'.*
[:ref:`... <tainted_bissbs>`]
@@ -1670,7 +1812,7 @@
.. _recheckbroken_bisref:
Check the kernel built from a recent mainline codebase
-------------------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Verify if your bug occurs with the newly built kernel.*
[:ref:`... <recheckbroken_bissbs>`]
@@ -1696,7 +1838,7 @@
.. _recheckstablebroken_bisref:
Check the kernel built from the latest stable/longterm codebase
----------------------------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Are you facing a regression within a stable/longterm release, but failed to
reproduce it with the kernel you just built using the latest mainline sources?
@@ -1741,7 +1883,7 @@
.. _recheckworking_bisref:
Build your own version of the 'good' kernel
--------------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Build your own variant of the working kernel and check if the feature that
regressed works as expected with it.* [:ref:`... <recheckworking_bissbs>`]
@@ -1767,15 +1909,25 @@
Note, if you found and fixed problems with the .config file, you want to use it
to build another kernel from the latest codebase, as your earlier tests with
-mainline and the latest version from an affected stable/longterm series were most
-likely flawed.
+mainline and the latest version from an affected stable/longterm series were
+most likely flawed.
[:ref:`back to step-by-step guide <recheckworking_bissbs>`]
+Perform a bisection and validate the result
+-------------------------------------------
+
+ *With all the preparations and precaution builds taken care of, you are now
+ ready to begin the bisection.* [:ref:`... <introbisect_bissbs>`]
+
+The steps in this segment perform and validate the bisection.
+
+[:ref:`back to step-by-step guide <introbisect_bissbs>`].
+
.. _bisectstart_bisref:
Start the bisection
--------------------
+~~~~~~~~~~~~~~~~~~~
*Start the bisection and tell Git about the versions earlier established as
'good' and 'bad'.* [:ref:`... <bisectstart_bissbs>`]
@@ -1789,7 +1941,7 @@
.. _bisectbuild_bisref:
Build a kernel from the bisection point
----------------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*Build, install, and boot a kernel from the code Git checked out using the
same commands you used earlier.* [:ref:`... <bisectbuild_bissbs>`]
@@ -1817,7 +1969,7 @@
.. _bisecttest_bisref:
Bisection checkpoint
---------------------
+~~~~~~~~~~~~~~~~~~~~
*Check if the feature that regressed works in the kernel you just built.*
[:ref:`... <bisecttest_bissbs>`]
@@ -1831,7 +1983,7 @@
.. _bisectlog_bisref:
Put the bisection log away
---------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~
*Store Git's bisection log and the current .config file in a safe place.*
[:ref:`... <bisectlog_bissbs>`]
@@ -1851,7 +2003,7 @@
.. _revert_bisref:
Try reverting the culprit
--------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~
*Try reverting the culprit on top of the latest codebase to see if this fixes
your regression.* [:ref:`... <revert_bissbs>`]
@@ -1869,14 +2021,20 @@
[:ref:`back to step-by-step guide <revert_bissbs>`]
+Cleanup steps during and after following this guide
+---------------------------------------------------
-Supplementary tasks: cleanup during and after the bisection
------------------------------------------------------------
+ *During and after following this guide you might want or need to remove some
+ of the kernels you installed.* [:ref:`... <introclosure_bissbs>`]
+
+The steps in this section describe clean-up procedures.
+
+[:ref:`back to step-by-step guide <introclosure_bissbs>`].
.. _makeroom_bisref:
Cleaning up during the bisection
---------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*To remove one of the kernels you installed, look up its 'kernelrelease'
identifier.* [:ref:`... <makeroom_bissbs>`]
@@ -1911,13 +2069,13 @@
the steps to do that vary quite a bit between Linux distributions.
Note, be careful with wildcards like '*' when deleting files or directories
-for kernels manually: you might accidentally remove files of a 6.0.11 kernel
+for kernels manually: you might accidentally remove files of a 6.0.13 kernel
when all you want is to remove 6.0 or 6.0.1.
[:ref:`back to step-by-step guide <makeroom_bissbs>`]
Cleaning up after the bisection
--------------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. _finishingtouch_bisref:
@@ -1932,26 +2090,105 @@
(~/linux/.git/) behind -- a simple ``git reset --hard`` thus will bring the
sources back.
-Removing the repository as well would likely be unwise at this point: there is a
-decent chance developers will ask you to build another kernel to perform
-additional tests. This is often required to debug an issue or check proposed
-fixes. Before doing so you want to run the ``git fetch mainline`` command again
-followed by ``git checkout mainline/master`` to bring your clone up to date and
-checkout the latest codebase. Then apply the patch using ``git apply
-<filename>`` or ``git am <filename>`` and build yet another kernel using the
-familiar commands.
+Removing the repository as well would likely be unwise at this point: there
+is a decent chance developers will ask you to build another kernel to
+perform additional tests -- like testing a debug patch or a proposed fix.
+Details on how to perform those can be found in the section :ref:`Optional
+tasks: test reverts, patches, or later versions <introoptional_bissbs>`.
Additional tests are also the reason why you want to keep the
~/kernel-config-working file around for a few weeks.
[:ref:`back to step-by-step guide <finishingtouch_bissbs>`]
+.. _introoptional_bisref:
+
+Test reverts, patches, or later versions
+----------------------------------------
+
+ *While or after reporting a bug, you might want or potentially will be asked
+ to test reverts, patches, proposed fixes, or other versions.*
+ [:ref:`... <introoptional_bissbs>`]
+
+All the commands used in this section should be pretty straight forward, so
+there is not much to add except one thing: when setting a kernel tag as
+instructed, ensure it is not much longer than the one used in the example, as
+problems will arise if the kernelrelease identifier exceeds 63 characters.
+
+[:ref:`back to step-by-step guide <introoptional_bissbs>`].
+
+
+Additional information
+======================
+
+.. _buildhost_bis:
+
+Build kernels on a different machine
+------------------------------------
+
+To compile kernels on another system, slightly alter the step-by-step guide's
+instructions:
+
+* Start following the guide on the machine where you want to install and test
+ the kernels later.
+
+* After executing ':ref:`Boot into the working kernel and briefly use the
+ apparently broken feature <bootworking_bissbs>`', save the list of loaded
+ modules to a file using ``lsmod > ~/test-machine-lsmod``. Then locate the
+ build configuration for the running kernel (see ':ref:`Start defining the
+ build configuration for your kernel <oldconfig_bisref>`' for hints on where
+ to find it) and store it as '~/test-machine-config-working'. Transfer both
+ files to the home directory of your build host.
+
+* Continue the guide on the build host (e.g. with ':ref:`Ensure to have enough
+ free space for building [...] <diskspace_bissbs>`').
+
+* When you reach ':ref:`Start preparing a kernel build configuration[...]
+ <oldconfig_bissbs>`': before running ``make olddefconfig`` for the first time,
+ execute the following command to base your configuration on the one from the
+ test machine's 'working' kernel::
+
+ cp ~/test-machine-config-working ~/linux/.config
+
+* During the next step to ':ref:`disable any apparently superfluous kernel
+ modules <localmodconfig_bissbs>`' use the following command instead::
+
+ yes '' | make localmodconfig LSMOD=~/lsmod_foo-machine localmodconfig
+
+* Continue the guide, but ignore the instructions outlining how to compile,
+ install, and reboot into a kernel every time they come up. Instead build
+ like this::
+
+ cp ~/kernel-config-working .config
+ make olddefconfig &&
+ make -j $(nproc --all) targz-pkg
+
+ This will generate a gzipped tar file whose name is printed in the last
+ line shown; for example, a kernel with the kernelrelease identifier
+ '6.0.0-rc1-local-g928a87efa423' built for x86 machines usually will
+ be stored as '~/linux/linux-6.0.0-rc1-local-g928a87efa423-x86.tar.gz'.
+
+ Copy that file to your test machine's home directory.
+
+* Switch to the test machine to check if you have enough space to hold another
+ kernel. Then extract the file you transferred::
+
+ sudo tar -xvzf ~/linux-6.0.0-rc1-local-g928a87efa423-x86.tar.gz -C /
+
+ Afterwards :ref:`generate the initramfs and add the kernel to your boot
+ loader's configuration <install_bisref>`; on some distributions the following
+ command will take care of both these tasks::
+
+ sudo /sbin/installkernel 6.0.0-rc1-local-g928a87efa423 /boot/vmlinuz-6.0.0-rc1-local-g928a87efa423
+
+ Now reboot and ensure you started the intended kernel.
+
+This approach even works when building for another architecture: just install
+cross-compilers and add the appropriate parameters to every invocation of make
+(e.g. ``make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- [...]``).
Additional reading material
-===========================
-
-Further sources
----------------
+---------------------------
* The `man page for 'git bisect' <https://git-scm.com/docs/git-bisect>`_ and
`fighting regressions with 'git bisect' <https://git-scm.com/docs/git-bisect-lk2009.html>`_
diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index ed73c61..bcc370c 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -671,7 +671,7 @@
events_unbound unbound 9 9 10 10 8
events_freezable percpu 0 2 4 6
events_power_efficient percpu 0 2 4 6
- events_freezable_power_ percpu 0 2 4 6
+ events_freezable_pwr_ef percpu 0 2 4 6
rcu_gp percpu 0 2 4 6
rcu_par_gp percpu 0 2 4 6
slub_flushwq percpu 0 2 4 6
@@ -694,7 +694,7 @@
events_unbound 38306 0 0.1 - 7 - -
events_freezable 0 0 0.0 0 0 - -
events_power_efficient 29598 0 0.2 0 0 - -
- events_freezable_power_ 10 0 0.0 0 0 - -
+ events_freezable_pwr_ef 10 0 0.0 0 0 - -
sock_diag_events 0 0 0.0 0 0 - -
total infl CPUtime CPUhog CMW/RPR mayday rescued
@@ -704,7 +704,7 @@
events_unbound 38322 0 0.1 - 7 - -
events_freezable 0 0 0.0 0 0 - -
events_power_efficient 29603 0 0.2 0 0 - -
- events_freezable_power_ 10 0 0.0 0 0 - -
+ events_freezable_pwr_ef 10 0 0.0 0 0 - -
sock_diag_events 0 0 0.0 0 0 - -
...
diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml
index c0d6a4f..e6dc549 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml
@@ -53,6 +53,15 @@
compatible:
const: qcom,sm8150-dpu
+ "^displayport-controller@[0-9a-f]+$":
+ type: object
+ additionalProperties: true
+
+ properties:
+ compatible:
+ contains:
+ const: qcom,sm8150-dp
+
"^dsi@[0-9a-f]+$":
type: object
additionalProperties: true
diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml
index 1812ef3..3c36cd0 100644
--- a/Documentation/devicetree/bindings/eeprom/at24.yaml
+++ b/Documentation/devicetree/bindings/eeprom/at24.yaml
@@ -69,14 +69,10 @@
- items:
pattern: c32$
- items:
- pattern: c32d-wl$
- - items:
pattern: cs32$
- items:
pattern: c64$
- items:
- pattern: c64d-wl$
- - items:
pattern: cs64$
- items:
pattern: c128$
@@ -136,6 +132,7 @@
- renesas,r1ex24128
- samsung,s524ad0xd1
- const: atmel,24c128
+ - pattern: '^atmel,24c(32|64)d-wl$' # Actual vendor is st
label:
description: Descriptive name of the EEPROM.
diff --git a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml
index c13c10c..eed0df9 100644
--- a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml
+++ b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml
@@ -42,7 +42,7 @@
properties:
compatible:
contains:
- const: maxim,max30100
+ const: maxim,max30102
then:
properties:
maxim,green-led-current-microamp: false
diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
index d476de8..4d5a957 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
@@ -120,7 +120,9 @@
slew-rate: true
gpio-hog: true
gpios: true
+ input: true
input-enable: true
+ output-enable: true
output-high: true
output-low: true
line-name: true
diff --git a/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml b/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml
index afcdeed..bc813fe 100644
--- a/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml
+++ b/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml
@@ -52,6 +52,9 @@
- const: main
- const: mm
+ power-domains:
+ maxItems: 1
+
required:
- compatible
- reg
diff --git a/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml b/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml
index 65cb2e5..eb2992a 100644
--- a/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml
+++ b/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml
@@ -8,7 +8,7 @@
title: Atmel Universal Synchronous Asynchronous Receiver/Transmitter (USART)
maintainers:
- - Richard Genoud <richard.genoud@gmail.com>
+ - Richard Genoud <richard.genoud@bootlin.com>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
index 0b87c26..79798c7 100644
--- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
+++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml
@@ -171,6 +171,7 @@
unevaluatedProperties: false
pcie-phy:
+ type: object
description:
Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt
diff --git a/Documentation/devicetree/bindings/sound/rt5645.txt b/Documentation/devicetree/bindings/sound/rt5645.txt
index 41a62fd..c1fa379 100644
--- a/Documentation/devicetree/bindings/sound/rt5645.txt
+++ b/Documentation/devicetree/bindings/sound/rt5645.txt
@@ -20,6 +20,11 @@
a GPIO spec for the external headphone detect pin. If jd-mode = 0,
we will get the JD status by getting the value of hp-detect-gpios.
+- cbj-sleeve-gpios:
+ a GPIO spec to control the external combo jack circuit to tie the sleeve/ring2
+ contacts to the ground or floating. It could avoid some electric noise from the
+ active speaker jacks.
+
- realtek,in2-differential
Boolean. Indicate MIC2 input are differential, rather than single-ended.
@@ -68,6 +73,7 @@
compatible = "realtek,rt5650";
reg = <0x1a>;
hp-detect-gpios = <&gpio 19 0>;
+ cbj-sleeve-gpios = <&gpio 20 0>;
interrupt-parent = <&gpio>;
interrupts = <7 IRQ_TYPE_EDGE_FALLING>;
realtek,dmic-en = "true";
diff --git a/Documentation/driver-api/virtio/writing_virtio_drivers.rst b/Documentation/driver-api/virtio/writing_virtio_drivers.rst
index e14c5879..e5de6f5 100644
--- a/Documentation/driver-api/virtio/writing_virtio_drivers.rst
+++ b/Documentation/driver-api/virtio/writing_virtio_drivers.rst
@@ -97,7 +97,6 @@
static struct virtio_driver virtio_dummy_driver = {
.driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
.id_table = id_table,
.probe = virtio_dummy_probe,
.remove = virtio_dummy_remove,
diff --git a/Documentation/filesystems/bcachefs/index.rst b/Documentation/filesystems/bcachefs/index.rst
new file mode 100644
index 0000000..e2bd61c
--- /dev/null
+++ b/Documentation/filesystems/bcachefs/index.rst
@@ -0,0 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================
+bcachefs Documentation
+======================
+
+.. toctree::
+ :maxdepth: 2
+ :numbered:
+
+ errorcodes
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 0ea1e44..1f9b4c9 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -69,6 +69,7 @@
afs
autofs
autofs-mount-control
+ bcachefs/index
befs
bfs
btrfs
diff --git a/Documentation/mm/page_owner.rst b/Documentation/mm/page_owner.rst
index 0d0334c..3a45a20 100644
--- a/Documentation/mm/page_owner.rst
+++ b/Documentation/mm/page_owner.rst
@@ -24,10 +24,10 @@
each page. It is already implemented and activated if page owner is
enabled. Other usages are more than welcome.
-It can also be used to show all the stacks and their outstanding
-allocations, which gives us a quick overview of where the memory is going
-without the need to screen through all the pages and match the allocation
-and free operation.
+It can also be used to show all the stacks and their current number of
+allocated base pages, which gives us a quick overview of where the memory
+is going without the need to screen through all the pages and match the
+allocation and free operation.
page owner is disabled by default. So, if you'd like to use it, you need
to add "page_owner=on" to your boot cmdline. If the kernel is built
@@ -75,42 +75,45 @@
cat /sys/kernel/debug/page_owner_stacks/show_stacks > stacks.txt
cat stacks.txt
- prep_new_page+0xa9/0x120
- get_page_from_freelist+0x7e6/0x2140
- __alloc_pages+0x18a/0x370
- new_slab+0xc8/0x580
- ___slab_alloc+0x1f2/0xaf0
- __slab_alloc.isra.86+0x22/0x40
- kmem_cache_alloc+0x31b/0x350
- __khugepaged_enter+0x39/0x100
- dup_mmap+0x1c7/0x5ce
- copy_process+0x1afe/0x1c90
- kernel_clone+0x9a/0x3c0
- __do_sys_clone+0x66/0x90
- do_syscall_64+0x7f/0x160
- entry_SYSCALL_64_after_hwframe+0x6c/0x74
- stack_count: 234
+ post_alloc_hook+0x177/0x1a0
+ get_page_from_freelist+0xd01/0xd80
+ __alloc_pages+0x39e/0x7e0
+ allocate_slab+0xbc/0x3f0
+ ___slab_alloc+0x528/0x8a0
+ kmem_cache_alloc+0x224/0x3b0
+ sk_prot_alloc+0x58/0x1a0
+ sk_alloc+0x32/0x4f0
+ inet_create+0x427/0xb50
+ __sock_create+0x2e4/0x650
+ inet_ctl_sock_create+0x30/0x180
+ igmp_net_init+0xc1/0x130
+ ops_init+0x167/0x410
+ setup_net+0x304/0xa60
+ copy_net_ns+0x29b/0x4a0
+ create_new_namespaces+0x4a1/0x820
+ nr_base_pages: 16
...
...
echo 7000 > /sys/kernel/debug/page_owner_stacks/count_threshold
cat /sys/kernel/debug/page_owner_stacks/show_stacks> stacks_7000.txt
cat stacks_7000.txt
- prep_new_page+0xa9/0x120
- get_page_from_freelist+0x7e6/0x2140
- __alloc_pages+0x18a/0x370
- alloc_pages_mpol+0xdf/0x1e0
- folio_alloc+0x14/0x50
- filemap_alloc_folio+0xb0/0x100
- page_cache_ra_unbounded+0x97/0x180
- filemap_fault+0x4b4/0x1200
- __do_fault+0x2d/0x110
- do_pte_missing+0x4b0/0xa30
- __handle_mm_fault+0x7fa/0xb70
- handle_mm_fault+0x125/0x300
- do_user_addr_fault+0x3c9/0x840
- exc_page_fault+0x68/0x150
- asm_exc_page_fault+0x22/0x30
- stack_count: 8248
+ post_alloc_hook+0x177/0x1a0
+ get_page_from_freelist+0xd01/0xd80
+ __alloc_pages+0x39e/0x7e0
+ alloc_pages_mpol+0x22e/0x490
+ folio_alloc+0xd5/0x110
+ filemap_alloc_folio+0x78/0x230
+ page_cache_ra_order+0x287/0x6f0
+ filemap_get_pages+0x517/0x1160
+ filemap_read+0x304/0x9f0
+ xfs_file_buffered_read+0xe6/0x1d0 [xfs]
+ xfs_file_read_iter+0x1f0/0x380 [xfs]
+ __kernel_read+0x3b9/0x730
+ kernel_read_file+0x309/0x4d0
+ __do_sys_finit_module+0x381/0x730
+ do_syscall_64+0x8d/0x150
+ entry_SYSCALL_64_after_hwframe+0x62/0x6a
+ nr_base_pages: 20824
...
cat /sys/kernel/debug/page_owner > page_owner_full.txt
diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst
index bb21002..6e9a459 100644
--- a/Documentation/process/embargoed-hardware-issues.rst
+++ b/Documentation/process/embargoed-hardware-issues.rst
@@ -252,7 +252,7 @@
AMD Tom Lendacky <thomas.lendacky@amd.com>
Ampere Darren Hart <darren@os.amperecomputing.com>
ARM Catalin Marinas <catalin.marinas@arm.com>
- IBM Power Anton Blanchard <anton@linux.ibm.com>
+ IBM Power Michael Ellerman <ellerman@au.ibm.com>
IBM Z Christian Borntraeger <borntraeger@de.ibm.com>
Intel Tony Luck <tony.luck@intel.com>
Qualcomm Trilok Soni <quic_tsoni@quicinc.com>
diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst
index 5c4fa9f..c913771 100644
--- a/Documentation/rust/arch-support.rst
+++ b/Documentation/rust/arch-support.rst
@@ -16,7 +16,7 @@
Architecture Level of support Constraints
============= ================ ==============================================
``arm64`` Maintained Little Endian only.
-``loongarch`` Maintained -
+``loongarch`` Maintained \-
``um`` Maintained ``x86_64`` only.
``x86`` Maintained ``x86_64`` only.
============= ================ ==============================================
diff --git a/Documentation/timers/no_hz.rst b/Documentation/timers/no_hz.rst
index f8786be..7fe8ef9 100644
--- a/Documentation/timers/no_hz.rst
+++ b/Documentation/timers/no_hz.rst
@@ -129,11 +129,8 @@
online to handle timekeeping tasks in order to ensure that system
calls like gettimeofday() returns accurate values on adaptive-tick CPUs.
(This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no running
-user processes to observe slight drifts in clock rate.) Therefore, the
-boot CPU is prohibited from entering adaptive-ticks mode. Specifying a
-"nohz_full=" mask that includes the boot CPU will result in a boot-time
-error message, and the boot CPU will be removed from the mask. Note that
-this means that your system must have at least two CPUs in order for
+user processes to observe slight drifts in clock rate.) Note that this
+means that your system must have at least two CPUs in order for
CONFIG_NO_HZ_FULL=y to do anything for you.
Finally, adaptive-ticks CPUs must have their RCU callbacks offloaded.
diff --git a/Documentation/translations/zh_CN/core-api/workqueue.rst b/Documentation/translations/zh_CN/core-api/workqueue.rst
index 7fac6f7..fe0ff5a 100644
--- a/Documentation/translations/zh_CN/core-api/workqueue.rst
+++ b/Documentation/translations/zh_CN/core-api/workqueue.rst
@@ -7,12 +7,13 @@
司延腾 Yanteng Si <siyanteng@loongson.cn>
周彬彬 Binbin Zhou <zhoubinbin@loongson.cn>
+ 陈兴友 Xingyou Chen <rockrush@rockwork.org>
.. _cn_workqueue.rst:
-=========================
-并发管理的工作队列 (cmwq)
-=========================
+========
+工作队列
+========
:日期: September, 2010
:作者: Tejun Heo <tj@kernel.org>
@@ -22,7 +23,7 @@
简介
====
-在很多情况下，需要一个异步进程的执行环境，工作队列（wq）API是这种情况下
+在很多情况下，需要一个异步的程序执行环境，工作队列（wq）API是这种情况下
最常用的机制。
当需要这样一个异步执行上下文时，一个描述将要执行的函数的工作项（work，
@@ -34,8 +35,8 @@
队列时，工作者又开始执行。
-为什么要cmwq?
-=============
+为什么要有并发管理工作队列?
+===========================
在最初的wq实现中，多线程（MT）wq在每个CPU上有一个工作者线程，而单线程
（ST）wq在全系统有一个工作者线程。一个MT wq需要保持与CPU数量相同的工
@@ -73,9 +74,11 @@
向该函数的工作项，并在工作队列中排队等待该工作项。（就是挂到workqueue
队列里面去）
-特定目的线程，称为工作线程（工作者），一个接一个地执行队列中的功能。
-如果没有工作项排队，工作者线程就会闲置。这些工作者线程被管理在所谓
-的工作者池中。
+工作项可以在线程或BH(软中断)上下文中执行。
+
+对于由线程执行的工作队列，被称为（内核）工作者（[k]worker）的特殊
+线程会依次执行其中的函数。如果没有工作项排队，工作者线程就会闲置。
+这些工作者线程被管理在所谓的工作者池中。
cmwq设计区分了面向用户的工作队列，子系统和驱动程序在上面排队工作，
以及管理工作者池和处理排队工作项的后端机制。
@@ -84,6 +87,10 @@
优先级的工作项，还有一些额外的工作者池，用于服务未绑定工作队列的工
作项目——这些后备池的数量是动态的。
+BH工作队列使用相同的结构。然而，由于同一时间只可能有一个执行上下文，
+不需要担心并发问题。每个CPU上的BH工作者池只包含一个用于表示BH执行
+上下文的虚拟工作者。BH工作队列可以被看作软中断的便捷接口。
+
当他们认为合适的时候，子系统和驱动程序可以通过特殊的
``workqueue API`` 函数创建和排队工作项。他们可以通过在工作队列上
设置标志来影响工作项执行方式的某些方面，他们把工作项放在那里。这些
@@ -95,9 +102,9 @@
否则一个绑定的工作队列的工作项将被排在与发起线程运行的CPU相关的普
通或高级工作工作者池的工作项列表中。
-对于任何工作者池的实施，管理并发水平（有多少执行上下文处于活动状
-态）是一个重要问题。最低水平是为了节省资源，而饱和水平是指系统被
-充分使用。
+对于任何线程池的实施，管理并发水平（有多少执行上下文处于活动状
+态）是一个重要问题。cmwq试图将并发保持在一个尽可能低且充足的
+水平。最低水平是为了节省资源，而充足是为了使系统能被充分使用。
每个与实际CPU绑定的worker-pool通过钩住调度器来实现并发管理。每当
一个活动的工作者被唤醒或睡眠时，工作者池就会得到通知，并跟踪当前可
@@ -140,6 +147,17 @@
``flags``
---------
+``WQ_BH``
+ BH工作队列可以被看作软中断的便捷接口。它总是每个CPU一份，
+ 其中的各个工作项也会按在队列中的顺序，被所属CPU在软中断
+ 上下文中执行。
+
+ BH工作队列的 ``max_active`` 值必须为0，且只能单独或和
+ ``WQ_HIGHPRI`` 标志组合使用。
+
+ BH工作项不可以睡眠。像延迟排队、冲洗、取消等所有其他特性
+ 都是支持的。
+
``WQ_UNBOUND``
排队到非绑定wq的工作项由特殊的工作者池提供服务，这些工作者不
绑定在任何特定的CPU上。这使得wq表现得像一个简单的执行环境提
@@ -184,25 +202,21 @@
--------------
``@max_active`` 决定了每个CPU可以分配给wq的工作项的最大执行上
-下文数量。例如，如果 ``@max_active为16`` ，每个CPU最多可以同
-时执行16个wq的工作项。
+下文数量。例如，如果 ``@max_active`` 为16 ，每个CPU最多可以同
+时执行16个wq的工作项。它总是每CPU属性，即便对于未绑定 wq。
-目前，对于一个绑定的wq， ``@max_active`` 的最大限制是512，当指
-定为0时使用的默认值是256。对于非绑定的wq，其限制是512和
-4 * ``num_possible_cpus()`` 中的较高值。这些值被选得足够高，所
-以它们不是限制性因素，同时会在失控情况下提供保护。
+``@max_active`` 的最大限制是512，当指定为0时使用的默认值是256。
+这些值被选得足够高，所以它们不是限制性因素，同时会在失控情况下提供
+保护。
一个wq的活动工作项的数量通常由wq的用户来调节，更具体地说，是由用
户在同一时间可以排列多少个工作项来调节。除非有特定的需求来控制活动
工作项的数量，否则建议指定 为"0"。
-一些用户依赖于ST wq的严格执行顺序。 ``@max_active`` 为1和 ``WQ_UNBOUND``
-的组合用来实现这种行为。这种wq上的工作项目总是被排到未绑定的工作池
-中，并且在任何时候都只有一个工作项目处于活动状态，从而实现与ST wq相
-同的排序属性。
-
-在目前的实现中，上述配置只保证了特定NUMA节点内的ST行为。相反，
-``alloc_ordered_workqueue()`` 应该被用来实现全系统的ST行为。
+一些用户依赖于任意时刻最多只有一个工作项被执行，且各工作项被按队列中
+顺序处理带来的严格执行顺序。``@max_active`` 为1和 ``WQ_UNBOUND``
+的组合曾被用来实现这种行为，现在不用了。请使用
+``alloc_ordered_workqueue()`` 。
执行场景示例
@@ -285,7 +299,7 @@
* 除非有特殊需要，建议使用0作为@max_active。在大多数使用情
况下，并发水平通常保持在默认限制之下。
-* 一个wq作为前进进度保证（WQ_MEM_RECLAIM，冲洗（flush）和工
+* 一个wq作为前进进度保证，``WQ_MEM_RECLAIM`` ，冲洗（flush）和工
作项属性的域。不涉及内存回收的工作项，不需要作为工作项组的一
部分被刷新，也不需要任何特殊属性，可以使用系统中的一个wq。使
用专用wq和系统wq在执行特性上没有区别。
@@ -294,6 +308,337 @@
益的，因为wq操作和工作项执行中的定位水平提高了。
+亲和性作用域
+============
+
+一个非绑定工作队列根据其亲和性作用域来对CPU进行分组以提高缓存
+局部性。比如如果一个工作队列使用默认的“cache”亲和性作用域，
+它将根据最后一级缓存的边界来分组处理器。这个工作队列上的工作项
+将被分配给一个与发起CPU共用最后级缓存的处理器上的工作者。根据
+``affinity_strict`` 的设置，工作者在启动后可能被允许移出
+所在作用域，也可能不被允许。
+
+工作队列目前支持以下亲和性作用域。
+
+``default``
+ 使用模块参数 ``workqueue.default_affinity_scope`` 指定
+ 的作用域，该参数总是会被设为以下作用域中的一个。
+
+``cpu``
+ CPU不被分组。一个CPU上发起的工作项会被同一CPU上的工作者执行。
+ 这使非绑定工作队列表现得像是不含并发管理的每CPU工作队列。
+
+``smt``
+ CPU被按SMT边界分组。这通常意味着每个物理CPU核上的各逻辑CPU会
+ 被分进同一组。
+
+``cache``
+ CPU被按缓存边界分组。采用哪个缓存边界由架构代码决定。很多情况
+ 下会使用L3。这是默认的亲和性作用域。
+
+``numa``
+ CPU被按NUMA边界分组。
+
+``system``
+ 所有CPU被放在同一组。工作队列不尝试在临近发起CPU的CPU上运行
+ 工作项。
+
+默认的亲和性作用域可以被模块参数 ``workqueue.default_affinity_scope``
+修改，特定工作队列的亲和性作用域可以通过 ``apply_workqueue_attrs()``
+被更改。
+
+如果设置了 ``WQ_SYSFS`` ，工作队列会在它的 ``/sys/devices/virtual/workqueue/WQ_NAME/``
+目录中有以下亲和性作用域相关的接口文件。
+
+``affinity_scope``
+ 读操作以查看当前的亲和性作用域。写操作用于更改设置。
+
+ 当前作用域是默认值时，当前生效的作用域也可以被从这个文件中
+ 读到（小括号内），例如 ``default (cache)`` 。
+
+``affinity_strict``
+ 默认值0表明亲和性作用域不是严格的。当一个工作项开始执行时，
+ 工作队列尽量尝试使工作者处于亲和性作用域内，称为遣返。启动后，
+ 调度器可以自由地将工作者调度到系统中任意它认为合适的地方去。
+ 这使得在保留使用其他CPU（如果必需且有可用）能力的同时，
+ 还能从作用域局部性上获益。
+
+ 如果设置为1，作用域内的所有工作者将被保证总是处于作用域内。
+ 这在跨亲和性作用域会导致如功耗、负载隔离等方面的潜在影响时
+ 会有用。严格的NUMA作用域也可用于和旧版内核中工作队列的行为
+ 保持一致。
+
+
+亲和性作用域与性能
+==================
+
+如果非绑定工作队列的行为对绝大多数使用场景来说都是最优的，
+不需要更多调节，就完美了。很不幸，在当前内核中，重度使用
+工作队列时，需要在局部性和利用率间显式地作一个明显的权衡。
+
+更高的局部性带来更高效率，也就是相同数量的CPU周期内可以做
+更多工作。然而，如果发起者没能将工作项充分地分散在亲和性
+作用域间，更高的局部性也可能带来更低的整体系统利用率。以下
+dm-crypt 的性能测试清楚地阐明了这一取舍。
+
+测试运行在一个12核24线程、4个L3缓存的处理器（AMD Ryzen
+9 3900x）上。为保持一致性，关闭CPU超频。 ``/dev/dm-0``
+是NVME SSD（三星 990 PRO）上创建，用 ``cryptsetup``
+以默认配置打开的一个 dm-crypt 设备。
+
+
+场景 1: 机器上遍布着有充足的发起者和工作量
+------------------------------------------
+
+使用命令：::
+
+ $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k --ioengine=libaio \
+ --iodepth=64 --runtime=60 --numjobs=24 --time_based --group_reporting \
+ --name=iops-test-job --verify=sha512
+
+这里有24个发起者，每个同时发起64个IO。 ``--verify=sha512``
+使得 ``fio`` 每次生成和读回内容受发起者和 ``kcryptd``
+间的执行局部性影响。下面是基于不同 ``kcryptd`` 的亲和性
+作用域设置，各经过五次测试得到的读取带宽和CPU利用率数据。
+
+.. list-table::
+ :widths: 16 20 20
+ :header-rows: 1
+
+ * - 亲和性
+ - 带宽 (MiBps)
+ - CPU利用率（%）
+
+ * - system
+ - 1159.40 ±1.34
+ - 99.31 ±0.02
+
+ * - cache
+ - 1166.40 ±0.89
+ - 99.34 ±0.01
+
+ * - cache (strict)
+ - 1166.00 ±0.71
+ - 99.35 ±0.01
+
+在系统中分布着足够多发起者的情况下，不论严格与否，“cache”
+没有表现得更差。三种配置均使整个机器达到饱和，但由于提高了
+局部性，缓存相关的两种有0.6%的（带宽）提升。
+
+
+场景 2: 更少发起者，足以达到饱和的工作量
+----------------------------------------
+
+使用命令：::
+
+ $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k \
+ --ioengine=libaio --iodepth=64 --runtime=60 --numjobs=8 \
+ --time_based --group_reporting --name=iops-test-job --verify=sha512
+
+与上一个场景唯一的区别是 ``--numjobs=8``。 发起者数量
+减少为三分之一，但仍然有足以使系统达到饱和的工作总量。
+
+.. list-table::
+ :widths: 16 20 20
+ :header-rows: 1
+
+ * - 亲和性
+ - 带宽 (MiBps)
+ - CPU利用率（%）
+
+ * - system
+ - 1155.40 ±0.89
+ - 97.41 ±0.05
+
+ * - cache
+ - 1154.40 ±1.14
+ - 96.15 ±0.09
+
+ * - cache (strict)
+ - 1112.00 ±4.64
+ - 93.26 ±0.35
+
+这里有超过使系统达到饱和所需的工作量。“system”和“cache”
+都接近但并未使机器完全饱和。“cache”消耗更少的CPU但更高的
+效率使其得到和“system”相同的带宽。
+
+八个发起者盘桓在四个L3缓存作用域间仍然允许“cache (strict)”
+几乎使机器饱和，但缺少对工作的保持（不移到空闲处理器上）
+开始带来3.7%的带宽损失。
+
+
+场景 3: 更少发起者，不充足的工作量
+----------------------------------
+
+使用命令：::
+
+ $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k \
+ --ioengine=libaio --iodepth=64 --runtime=60 --numjobs=4 \
+ --time_based --group_reporting --name=iops-test-job --verify=sha512
+
+再次，唯一的区别是 ``--numjobs=4``。由于发起者减少到四个，
+现在没有足以使系统饱和的工作量，带宽变得依赖于完成时延。
+
+.. list-table::
+ :widths: 16 20 20
+ :header-rows: 1
+
+ * - 亲和性
+ - 带宽 (MiBps)
+ - CPU利用率（%）
+
+ * - system
+ - 993.60 ±1.82
+ - 75.49 ±0.06
+
+ * - cache
+ - 973.40 ±1.52
+ - 74.90 ±0.07
+
+ * - cache (strict)
+ - 828.20 ±4.49
+ - 66.84 ±0.29
+
+现在，局部性和利用率间的权衡更清晰了。“cache”展示出相比
+“system”2%的带宽损失，而“cache (strict)”跌到20%。
+
+
+结论和建议
+----------
+
+在以上试验中，虽然一致并且也明显，但“cache”亲和性作用域
+相比“system”的性能优势并不大。然而，这影响是依赖于作用域
+间距离的，在更复杂的处理器拓扑下可能有更明显的影响。
+
+虽然这些情形下缺少工作保持是有坏处的，但比“cache (strict)”
+好多了，而且最大化工作队列利用率的需求也并不常见。因此，
+“cache”是非绑定池的默认亲和性作用域。
+
+* 由于不存在一个适用于大多数场景的选择，对于可能需要消耗
+ 大量CPU的工作队列，建议通过 ``apply_workqueue_attrs()``
+ 进行（专门）配置，并考虑是否启用 ``WQ_SYSFS``。
+
+* 设置了严格“cpu”亲和性作用域的非绑定工作队列，它的行为与
+ ``WQ_CPU_INTENSIVE`` 每CPU工作队列一样。后者没有真正
+ 优势，而前者提供了大幅度的灵活性。
+
+* 亲和性作用域是从Linux v6.5起引入的。为了模拟旧版行为，
+ 可以使用严格的“numa”亲和性作用域。
+
+* 不严格的亲和性作用域中，缺少工作保持大概缘于调度器。内核
+ 为什么没能维护好大多数场景下的工作保持，把事情作对，还没有
+ 理论上的解释。因此，未来调度器的改进可能会使我们不再需要
+ 这些调节项。
+
+
+检查配置
+========
+
+使用 tools/workqueue/wq_dump.py（drgn脚本） 来检查未
+绑定CPU的亲和性配置，工作者池，以及工作队列如何映射到池上: ::
+
+ $ tools/workqueue/wq_dump.py
+ Affinity Scopes
+ ===============
+ wq_unbound_cpumask=0000000f
+
+ CPU
+ nr_pods 4
+ pod_cpus [0]=00000001 [1]=00000002 [2]=00000004 [3]=00000008
+ pod_node [0]=0 [1]=0 [2]=1 [3]=1
+ cpu_pod [0]=0 [1]=1 [2]=2 [3]=3
+
+ SMT
+ nr_pods 4
+ pod_cpus [0]=00000001 [1]=00000002 [2]=00000004 [3]=00000008
+ pod_node [0]=0 [1]=0 [2]=1 [3]=1
+ cpu_pod [0]=0 [1]=1 [2]=2 [3]=3
+
+ CACHE (default)
+ nr_pods 2
+ pod_cpus [0]=00000003 [1]=0000000c
+ pod_node [0]=0 [1]=1
+ cpu_pod [0]=0 [1]=0 [2]=1 [3]=1
+
+ NUMA
+ nr_pods 2
+ pod_cpus [0]=00000003 [1]=0000000c
+ pod_node [0]=0 [1]=1
+ cpu_pod [0]=0 [1]=0 [2]=1 [3]=1
+
+ SYSTEM
+ nr_pods 1
+ pod_cpus [0]=0000000f
+ pod_node [0]=-1
+ cpu_pod [0]=0 [1]=0 [2]=0 [3]=0
+
+ Worker Pools
+ ============
+ pool[00] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 0
+ pool[01] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 0
+ pool[02] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 1
+ pool[03] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 1
+ pool[04] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 2
+ pool[05] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 2
+ pool[06] ref= 1 nice= 0 idle/workers= 3/ 3 cpu= 3
+ pool[07] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 3
+ pool[08] ref=42 nice= 0 idle/workers= 6/ 6 cpus=0000000f
+ pool[09] ref=28 nice= 0 idle/workers= 3/ 3 cpus=00000003
+ pool[10] ref=28 nice= 0 idle/workers= 17/ 17 cpus=0000000c
+ pool[11] ref= 1 nice=-20 idle/workers= 1/ 1 cpus=0000000f
+ pool[12] ref= 2 nice=-20 idle/workers= 1/ 1 cpus=00000003
+ pool[13] ref= 2 nice=-20 idle/workers= 1/ 1 cpus=0000000c
+
+ Workqueue CPU -> pool
+ =====================
+ [ workqueue \ CPU 0 1 2 3 dfl]
+ events percpu 0 2 4 6
+ events_highpri percpu 1 3 5 7
+ events_long percpu 0 2 4 6
+ events_unbound unbound 9 9 10 10 8
+ events_freezable percpu 0 2 4 6
+ events_power_efficient percpu 0 2 4 6
+ events_freezable_power_ percpu 0 2 4 6
+ rcu_gp percpu 0 2 4 6
+ rcu_par_gp percpu 0 2 4 6
+ slub_flushwq percpu 0 2 4 6
+ netns ordered 8 8 8 8 8
+ ...
+
+参见命令的帮助消息以获取更多信息。
+
+
+监视
+====
+
+使用 tools/workqueue/wq_monitor.py 来监视工作队列的运行： ::
+
+ $ tools/workqueue/wq_monitor.py events
+ total infl CPUtime CPUhog CMW/RPR mayday rescued
+ events 18545 0 6.1 0 5 - -
+ events_highpri 8 0 0.0 0 0 - -
+ events_long 3 0 0.0 0 0 - -
+ events_unbound 38306 0 0.1 - 7 - -
+ events_freezable 0 0 0.0 0 0 - -
+ events_power_efficient 29598 0 0.2 0 0 - -
+ events_freezable_power_ 10 0 0.0 0 0 - -
+ sock_diag_events 0 0 0.0 0 0 - -
+
+ total infl CPUtime CPUhog CMW/RPR mayday rescued
+ events 18548 0 6.1 0 5 - -
+ events_highpri 8 0 0.0 0 0 - -
+ events_long 3 0 0.0 0 0 - -
+ events_unbound 38322 0 0.1 - 7 - -
+ events_freezable 0 0 0.0 0 0 - -
+ events_power_efficient 29603 0 0.2 0 0 - -
+ events_freezable_power_ 10 0 0.0 0 0 - -
+ sock_diag_events 0 0 0.0 0 0 - -
+
+ ...
+
+参见命令的帮助消息以获取更多信息。
+
+
调试
====
@@ -330,7 +675,6 @@
工作队列保证，如果在工作项排队后满足以下条件，则工作项不能重入：
-
1. 工作函数没有被改变。
2. 没有人将该工作项排到另一个工作队列中。
3. 该工作项尚未被重新启动。
diff --git a/MAINTAINERS b/MAINTAINERS
index 9db17a2..0d7c8205 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -553,7 +553,7 @@
F: drivers/input/misc/adxl34x.c
ADXL355 THREE-AXIS DIGITAL ACCELEROMETER DRIVER
-M: Puranjay Mohan <puranjay12@gmail.com>
+M: Puranjay Mohan <puranjay@kernel.org>
L: linux-iio@vger.kernel.org
S: Supported
F: Documentation/devicetree/bindings/iio/accel/adi,adxl355.yaml
@@ -2191,7 +2191,6 @@
ARM/FREESCALE LAYERSCAPE ARM ARCHITECTURE
M: Shawn Guo <shawnguo@kernel.org>
-M: Li Yang <leoyang.li@nxp.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
@@ -2708,7 +2707,7 @@
N: rockchip
ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
R: Alim Akhtar <alim.akhtar@samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org
@@ -3580,6 +3579,7 @@
C: irc://irc.oftc.net/bcache
T: git https://evilpiepirate.org/git/bcachefs.git
F: fs/bcachefs/
+F: Documentation/filesystems/bcachefs/
BDISP ST MEDIA DRIVER
M: Fabien Dessenne <fabien.dessenne@foss.st.com>
@@ -3721,7 +3721,7 @@
BPF JIT for ARM
M: Russell King <linux@armlinux.org.uk>
-M: Puranjay Mohan <puranjay12@gmail.com>
+M: Puranjay Mohan <puranjay@kernel.org>
L: bpf@vger.kernel.org
S: Maintained
F: arch/arm/net/
@@ -3771,6 +3771,8 @@
BPF JIT for RISC-V (64-bit)
M: Björn Töpel <bjorn@kernel.org>
+R: Pu Lehui <pulehui@huawei.com>
+R: Puranjay Mohan <puranjay@kernel.org>
L: bpf@vger.kernel.org
S: Maintained
F: arch/riscv/net/
@@ -4198,7 +4200,6 @@
F: drivers/scsi/bnx2i/
BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M: Ariel Elior <aelior@marvell.com>
M: Sudarsana Kalluru <skalluru@marvell.com>
M: Manish Chopra <manishc@marvell.com>
L: netdev@vger.kernel.org
@@ -4876,7 +4877,6 @@
CEPH COMMON CODE (LIBCEPH)
M: Ilya Dryomov <idryomov@gmail.com>
M: Xiubo Li <xiubli@redhat.com>
-R: Jeff Layton <jlayton@kernel.org>
L: ceph-devel@vger.kernel.org
S: Supported
W: http://ceph.com/
@@ -4888,7 +4888,6 @@
CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH)
M: Xiubo Li <xiubli@redhat.com>
M: Ilya Dryomov <idryomov@gmail.com>
-R: Jeff Layton <jlayton@kernel.org>
L: ceph-devel@vger.kernel.org
S: Supported
W: http://ceph.com/
@@ -5564,7 +5563,7 @@
CPUIDLE DRIVER - ARM EXYNOS
M: Daniel Lezcano <daniel.lezcano@linaro.org>
M: Kukjin Kim <kgene@kernel.org>
-R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+R: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-pm@vger.kernel.org
L: linux-samsung-soc@vger.kernel.org
S: Maintained
@@ -7838,9 +7837,8 @@
F: fs/efs/
EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER
-M: Douglas Miller <dougmill@linux.ibm.com>
L: netdev@vger.kernel.org
-S: Maintained
+S: Orphan
F: drivers/net/ethernet/ibm/ehea/
ELM327 CAN NETWORK DRIVER
@@ -8530,7 +8528,6 @@
F: drivers/video/fbdev/fsl-diu-fb.*
FREESCALE DMA DRIVER
-M: Li Yang <leoyang.li@nxp.com>
M: Zhang Wei <zw@zh-kernel.org>
L: linuxppc-dev@lists.ozlabs.org
S: Maintained
@@ -8695,10 +8692,9 @@
F: include/dt-bindings/soc/cpm1-fsl,tsa.h
FREESCALE QUICC ENGINE UCC ETHERNET DRIVER
-M: Li Yang <leoyang.li@nxp.com>
L: netdev@vger.kernel.org
L: linuxppc-dev@lists.ozlabs.org
-S: Maintained
+S: Orphan
F: drivers/net/ethernet/freescale/ucc_geth*
FREESCALE QUICC ENGINE UCC HDLC DRIVER
@@ -8715,10 +8711,9 @@
F: drivers/tty/serial/ucc_uart.c
FREESCALE SOC DRIVERS
-M: Li Yang <leoyang.li@nxp.com>
L: linuxppc-dev@lists.ozlabs.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S: Maintained
+S: Orphan
F: Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml
F: Documentation/devicetree/bindings/soc/fsl/
F: drivers/soc/fsl/
@@ -8752,17 +8747,15 @@
F: sound/soc/fsl/fsl_qmc_audio.c
FREESCALE USB PERIPHERAL DRIVERS
-M: Li Yang <leoyang.li@nxp.com>
L: linux-usb@vger.kernel.org
L: linuxppc-dev@lists.ozlabs.org
-S: Maintained
+S: Orphan
F: drivers/usb/gadget/udc/fsl*
FREESCALE USB PHY DRIVER
-M: Ran Wang <ran.wang_1@nxp.com>
L: linux-usb@vger.kernel.org
L: linuxppc-dev@lists.ozlabs.org
-S: Maintained
+S: Orphan
F: drivers/usb/phy/phy-fsl-usb*
FREEVXFS FILESYSTEM
@@ -9007,7 +9000,7 @@
F: include/linux/platform_data/i2c-mux-gpio.h
GENERIC GPIO RESET DRIVER
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
S: Maintained
F: drivers/reset/reset-gpio.c
@@ -9590,7 +9583,7 @@
HID CORE LAYER
M: Jiri Kosina <jikos@kernel.org>
-M: Benjamin Tissoires <benjamin.tissoires@redhat.com>
+M: Benjamin Tissoires <bentiss@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
@@ -10037,7 +10030,7 @@
HWPOISON MEMORY FAILURE HANDLING
M: Miaohe Lin <linmiaohe@huawei.com>
-R: Naoya Horiguchi <naoya.horiguchi@nec.com>
+R: Naoya Horiguchi <nao.horiguchi@gmail.com>
L: linux-mm@kvack.org
S: Maintained
F: mm/hwpoison-inject.c
@@ -12008,7 +12001,7 @@
F: security/keys/encrypted-keys/
KEYS-TRUSTED
-M: James Bottomley <jejb@linux.ibm.com>
+M: James Bottomley <James.Bottomley@HansenPartnership.com>
M: Jarkko Sakkinen <jarkko@kernel.org>
M: Mimi Zohar <zohar@linux.ibm.com>
L: linux-integrity@vger.kernel.org
@@ -13302,7 +13295,7 @@
MAXIM MAX17040 FAMILY FUEL GAUGE DRIVERS
R: Iskren Chernev <iskren.chernev@gmail.com>
-R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+R: Krzysztof Kozlowski <krzk@kernel.org>
R: Marek Szyprowski <m.szyprowski@samsung.com>
R: Matheus Castello <matheus@castello.eng.br>
L: linux-pm@vger.kernel.org
@@ -13312,7 +13305,7 @@
MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS
R: Hans de Goede <hdegoede@redhat.com>
-R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+R: Krzysztof Kozlowski <krzk@kernel.org>
R: Marek Szyprowski <m.szyprowski@samsung.com>
R: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
R: Purism Kernel Team <kernel@puri.sm>
@@ -13370,7 +13363,7 @@
F: drivers/power/supply/max77976_charger.c
MAXIM MUIC CHARGER DRIVERS FOR EXYNOS BASED BOARDS
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-pm@vger.kernel.org
S: Maintained
B: mailto:linux-samsung-soc@vger.kernel.org
@@ -13381,7 +13374,7 @@
MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS
M: Chanwoo Choi <cw00.choi@samsung.com>
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-kernel@vger.kernel.org
S: Maintained
B: mailto:linux-samsung-soc@vger.kernel.org
@@ -14165,7 +14158,7 @@
F: tools/testing/memblock/
MEMORY CONTROLLER DRIVERS
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-kernel@vger.kernel.org
S: Maintained
B: mailto:krzysztof.kozlowski@linaro.org
@@ -14370,7 +14363,7 @@
F: include/dt-bindings/dma/at91.h
MICROCHIP AT91 SERIAL DRIVER
-M: Richard Genoud <richard.genoud@gmail.com>
+M: Richard Genoud <richard.genoud@bootlin.com>
S: Maintained
F: Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml
F: drivers/tty/serial/atmel_serial.c
@@ -15175,9 +15168,8 @@
F: drivers/scsi/myrs.*
MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE)
-M: Chris Lee <christopher.lee@cspi.com>
L: netdev@vger.kernel.org
-S: Supported
+S: Orphan
W: https://www.cspi.com/ethernet-products/support/downloads/
F: drivers/net/ethernet/myricom/myri10ge/
@@ -15546,7 +15538,7 @@
F: net/ipv4/nexthop.c
NFC SUBSYSTEM
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/nfc/
@@ -15923,7 +15915,7 @@
F: drivers/regulator/pf8x00-regulator.c
NXP PTN5150A CC LOGIC AND EXTCON DRIVER
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-kernel@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/extcon/extcon-ptn5150.yaml
@@ -16534,7 +16526,7 @@
OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS
M: Rob Herring <robh@kernel.org>
-M: Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org>
+M: Krzysztof Kozlowski <krzk+dt@kernel.org>
M: Conor Dooley <conor+dt@kernel.org>
L: devicetree@vger.kernel.org
S: Maintained
@@ -16813,12 +16805,6 @@
F: drivers/leds/leds-pca9532.c
F: include/linux/leds-pca9532.h
-PCA9541 I2C BUS MASTER SELECTOR DRIVER
-M: Guenter Roeck <linux@roeck-us.net>
-L: linux-i2c@vger.kernel.org
-S: Maintained
-F: drivers/i2c/muxes/i2c-mux-pca9541.c
-
PCI DRIVER FOR AARDVARK (Marvell Armada 3700)
M: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
M: Pali Rohár <pali@kernel.org>
@@ -16981,7 +16967,6 @@
PCI DRIVER FOR SYNOPSYS DESIGNWARE
M: Jingoo Han <jingoohan1@gmail.com>
-M: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
L: linux-pci@vger.kernel.org
S: Maintained
@@ -17492,7 +17477,7 @@
F: drivers/pinctrl/renesas/
PIN CONTROLLER - SAMSUNG
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
R: Alim Akhtar <alim.akhtar@samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -17888,7 +17873,7 @@
F: drivers/media/rc/pwm-ir-tx.c
PWM SUBSYSTEM
-M: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
+M: Uwe Kleine-König <ukleinek@kernel.org>
L: linux-pwm@vger.kernel.org
S: Maintained
Q: https://patchwork.ozlabs.org/project/linux-pwm/list/
@@ -18012,7 +17997,6 @@
F: drivers/scsi/qedi/
QLOGIC QL4xxx ETHERNET DRIVER
-M: Ariel Elior <aelior@marvell.com>
M: Manish Chopra <manishc@marvell.com>
L: netdev@vger.kernel.org
S: Supported
@@ -18022,7 +18006,6 @@
QLOGIC QL4xxx RDMA DRIVER
M: Michal Kalderon <mkalderon@marvell.com>
-M: Ariel Elior <aelior@marvell.com>
L: linux-rdma@vger.kernel.org
S: Supported
F: drivers/infiniband/hw/qedr/
@@ -19460,7 +19443,7 @@
F: sound/soc/samsung/
SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-crypto@vger.kernel.org
L: linux-samsung-soc@vger.kernel.org
S: Maintained
@@ -19495,7 +19478,7 @@
F: drivers/platform/x86/samsung-laptop.c
SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-kernel@vger.kernel.org
L: linux-samsung-soc@vger.kernel.org
S: Maintained
@@ -19521,7 +19504,7 @@
F: include/media/drv-intf/s3c_camif.h
SAMSUNG S3FWRN5 NFC DRIVER
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
S: Maintained
F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml
F: drivers/nfc/s3fwrn5
@@ -19542,7 +19525,7 @@
F: drivers/media/i2c/s5k5baf.c
SAMSUNG S5P Security SubSystem (SSS) DRIVER
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
M: Vladimir Zapolskiy <vz@mleia.com>
L: linux-crypto@vger.kernel.org
L: linux-samsung-soc@vger.kernel.org
@@ -19564,7 +19547,7 @@
F: drivers/media/platform/samsung/exynos4-is/
SAMSUNG SOC CLOCK DRIVERS
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
M: Chanwoo Choi <cw00.choi@samsung.com>
R: Alim Akhtar <alim.akhtar@samsung.com>
@@ -19596,7 +19579,7 @@
SAMSUNG THERMAL DRIVER
M: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
L: linux-pm@vger.kernel.org
L: linux-samsung-soc@vger.kernel.org
S: Maintained
@@ -19683,7 +19666,7 @@
F: include/scsi/sg.h
SCSI SUBSYSTEM
-M: "James E.J. Bottomley" <jejb@linux.ibm.com>
+M: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
M: "Martin K. Petersen" <martin.petersen@oracle.com>
L: linux-scsi@vger.kernel.org
S: Maintained
@@ -20192,7 +20175,6 @@
SIOX
M: Thorsten Scherer <t.scherer@eckelmann.de>
-M: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
R: Pengutronix Kernel Team <kernel@pengutronix.de>
S: Supported
F: drivers/gpio/gpio-siox.c
@@ -21941,7 +21923,7 @@
F: include/linux/soc/ti/ti_sci_protocol.h
TEXAS INSTRUMENTS' TMP117 TEMPERATURE SENSOR DRIVER
-M: Puranjay Mohan <puranjay12@gmail.com>
+M: Puranjay Mohan <puranjay@kernel.org>
L: linux-iio@vger.kernel.org
S: Supported
F: Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml
@@ -22584,6 +22566,7 @@
B: https://bugzilla.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat
F: tools/power/x86/turbostat/
+F: tools/testing/selftests/turbostat/
TW5864 VIDEO4LINUX DRIVER
M: Bluecherry Maintainers <maintainers@bluecherrydvr.com>
@@ -22853,7 +22836,7 @@
USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...)
M: Jiri Kosina <jikos@kernel.org>
-M: Benjamin Tissoires <benjamin.tissoires@redhat.com>
+M: Benjamin Tissoires <bentiss@kernel.org>
L: linux-usb@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
@@ -23792,7 +23775,7 @@
F: drivers/mmc/host/vub300.c
W1 DALLAS'S 1-WIRE BUS
-M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
S: Maintained
F: Documentation/devicetree/bindings/w1/
F: Documentation/w1/
@@ -24481,6 +24464,14 @@
F: Documentation/admin-guide/LSM/Yama.rst
F: security/yama/
+YAML NETLINK (YNL)
+M: Donald Hunter <donald.hunter@gmail.com>
+M: Jakub Kicinski <kuba@kernel.org>
+F: Documentation/netlink/
+F: Documentation/userspace-api/netlink/intro-specs.rst
+F: Documentation/userspace-api/netlink/specs.rst
+F: tools/net/ynl/
+
YEALINK PHONE DRIVER
M: Henk Vergonet <Henk.Vergonet@gmail.com>
L: usbb2k-api-dev@nongnu.org
diff --git a/Makefile b/Makefile
index e1bf128..d51d411 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 9
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc7
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
diff --git a/arch/Kconfig b/arch/Kconfig
index 9f06678..30f7930 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -9,6 +9,14 @@
#
source "arch/$(SRCARCH)/Kconfig"
+config ARCH_CONFIGURES_CPU_MITIGATIONS
+ bool
+
+if !ARCH_CONFIGURES_CPU_MITIGATIONS
+config CPU_MITIGATIONS
+ def_bool y
+endif
+
menu "General architecture-dependent options"
config ARCH_HAS_SUBPAGE_FAULTS
@@ -1172,12 +1180,12 @@
config PAGE_SHIFT
int
- default 12 if PAGE_SIZE_4KB
- default 13 if PAGE_SIZE_8KB
- default 14 if PAGE_SIZE_16KB
- default 15 if PAGE_SIZE_32KB
- default 16 if PAGE_SIZE_64KB
- default 18 if PAGE_SIZE_256KB
+ default 12 if PAGE_SIZE_4KB
+ default 13 if PAGE_SIZE_8KB
+ default 14 if PAGE_SIZE_16KB
+ default 15 if PAGE_SIZE_32KB
+ default 16 if PAGE_SIZE_64KB
+ default 18 if PAGE_SIZE_256KB
# This allows to use a set of generic functions to determine mmap base
# address by giving priority to top-down scheme only if the process
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 99d2845..4092bec 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -6,7 +6,6 @@
config ARC
def_bool y
select ARC_TIMERS
- select ARCH_HAS_CPU_CACHE_ALIASING
select ARCH_HAS_CACHE_LINE_SIZE
select ARCH_HAS_DEBUG_VM_PGTABLE
select ARCH_HAS_DMA_PREP_COHERENT
diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile
index 5648748..5a85501 100644
--- a/arch/arc/boot/Makefile
+++ b/arch/arc/boot/Makefile
@@ -1,8 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
-# uImage build relies on mkimage being availble on your host for ARC target
+# uImage build relies on mkimage being available on your host for ARC target
# You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage
-# and make sure it's reacable from your PATH
+# and make sure it's reachable from your PATH
OBJCOPYFLAGS= -O binary -R .note -R .note.gnu.build-id -R .comment -S
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 3434c81..c0a8126 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -119,9 +119,9 @@
/*
* The DW APB ICTL intc on MB is connected to CPU intc via a
* DT "invisible" DW APB GPIO block, configured to simply pass thru
- * interrupts - setup accordinly in platform init (plat-axs10x/ax10x.c)
+ * interrupts - setup accordingly in platform init (plat-axs10x/ax10x.c)
*
- * So here we mimic a direct connection betwen them, ignoring the
+ * So here we mimic a direct connection between them, ignoring the
* ABPG GPIO. Thus set "interrupts = <24>" (DW APB GPIO to core)
* instead of "interrupts = <12>" (DW APB ICTL to DW APB GPIO)
*
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 6691f42..41b980d 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -205,7 +205,6 @@
};
gmac: ethernet@8000 {
- #interrupt-cells = <1>;
compatible = "snps,dwmac";
reg = <0x8000 0x2000>;
interrupts = <10>;
diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
index 90a4120..0e0e2d3 100644
--- a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
@@ -113,7 +113,7 @@
/*
* Embedded Vision subsystem UIO mappings; only relevant for EV VDK
*
- * This node is intentionally put outside of MB above becase
+ * This node is intentionally put outside of MB above because
* it maps areas outside of MB's 0xez-0xfz.
*/
uio_ev: uio@d0000000 {
diff --git a/arch/arc/include/asm/cachetype.h b/arch/arc/include/asm/cachetype.h
deleted file mode 100644
index 05fc7ed..0000000
--- a/arch/arc/include/asm/cachetype.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_ARC_CACHETYPE_H
-#define __ASM_ARC_CACHETYPE_H
-
-#include <linux/types.h>
-
-#define cpu_dcache_is_aliasing() true
-
-#endif
diff --git a/arch/arc/include/asm/dsp.h b/arch/arc/include/asm/dsp.h
index 202c78e..f496dbc 100644
--- a/arch/arc/include/asm/dsp.h
+++ b/arch/arc/include/asm/dsp.h
@@ -12,7 +12,7 @@
/*
* DSP-related saved registers - need to be saved only when you are
* scheduled out.
- * structure fields name must correspond to aux register defenitions for
+ * structure fields name must correspond to aux register definitions for
* automatic offset calculation in DSP_AUX_SAVE_RESTORE macros
*/
struct dsp_callee_regs {
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index 92c3e9f..00946fe 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -7,7 +7,7 @@
* Stack switching code can no longer reliably rely on the fact that
* if we are NOT in user mode, stack is switched to kernel mode.
* e.g. L2 IRQ interrupted a L1 ISR which had not yet completed
- * it's prologue including stack switching from user mode
+ * its prologue including stack switching from user mode
*
* Vineetg: Aug 28th 2008: Bug #94984
* -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap
@@ -143,7 +143,7 @@
* 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode)
* 3. But before it could switch SP from USER to KERNEL stack
* a L2 IRQ "Interrupts" L1
- * Thay way although L2 IRQ happened in Kernel mode, stack is still
+ * That way although L2 IRQ happened in Kernel mode, stack is still
* not switched.
* To handle this, we may need to switch stack even if in kernel mode
* provided SP has values in range of USER mode stack ( < 0x7000_0000 )
@@ -173,7 +173,7 @@
GET_CURR_TASK_ON_CPU r9
- /* With current tsk in r9, get it's kernel mode stack base */
+ /* With current tsk in r9, get its kernel mode stack base */
GET_TSK_STACK_BASE r9, r9
/* save U mode SP @ pt_regs->sp */
@@ -282,7 +282,7 @@
* NOTE:
*
* It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
- * for memory load operations. If used in that way interrupts are deffered
+ * for memory load operations. If used in that way interrupts are deferred
* by hardware and that is not good.
*-------------------------------------------------------------*/
.macro EXCEPTION_EPILOGUE
@@ -350,7 +350,7 @@
* NOTE:
*
* It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg
- * for memory load operations. If used in that way interrupts are deffered
+ * for memory load operations. If used in that way interrupts are deferred
* by hardware and that is not good.
*-------------------------------------------------------------*/
.macro INTERRUPT_EPILOGUE LVL
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index cf1ba37..38c3572 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -7,7 +7,7 @@
#ifndef __ASM_ARC_ENTRY_H
#define __ASM_ARC_ENTRY_H
-#include <asm/unistd.h> /* For NR_syscalls defination */
+#include <asm/unistd.h> /* For NR_syscalls definition */
#include <asm/arcregs.h>
#include <asm/ptrace.h>
#include <asm/processor.h> /* For VMALLOC_START */
@@ -56,7 +56,7 @@
.endm
/*-------------------------------------------------------------
- * given a tsk struct, get to the base of it's kernel mode stack
+ * given a tsk struct, get to the base of its kernel mode stack
* tsk->thread_info is really a PAGE, whose bottom hoists stack
* which grows upwards towards thread_info
*------------------------------------------------------------*/
diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h
index c574712..9cd7926 100644
--- a/arch/arc/include/asm/irq.h
+++ b/arch/arc/include/asm/irq.h
@@ -10,7 +10,7 @@
* ARCv2 can support 240 interrupts in the core interrupts controllers and
* 128 interrupts in IDU. Thus 512 virtual IRQs must be enough for most
* configurations of boards.
- * This doesnt affect ARCompact, but we change it to same value
+ * This doesn't affect ARCompact, but we change it to same value
*/
#define NR_IRQS 512
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index 0d63e56..936a2f2 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -46,7 +46,7 @@
* IRQ Control Macros
*
* All of them have "memory" clobber (compiler barrier) which is needed to
- * ensure that LD/ST requiring irq safetly (R-M-W when LLSC is not available)
+ * ensure that LD/ST requiring irq safety (R-M-W when LLSC is not available)
* are redone after IRQs are re-enabled (and gcc doesn't reuse stale register)
*
* Noted at the time of Abilis Timer List corruption
diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h
index dda471f..9963bb1 100644
--- a/arch/arc/include/asm/mmu_context.h
+++ b/arch/arc/include/asm/mmu_context.h
@@ -165,7 +165,7 @@
* for retiring-mm. However destroy_context( ) still needs to do that because
* between mm_release( ) = >deactive_mm( ) and
* mmput => .. => __mmdrop( ) => destroy_context( )
- * there is a good chance that task gets sched-out/in, making it's ASID valid
+ * there is a good chance that task gets sched-out/in, making its ASID valid
* again (this teased me for a whole day).
*/
diff --git a/arch/arc/include/asm/pgtable-bits-arcv2.h b/arch/arc/include/asm/pgtable-bits-arcv2.h
index f3eea3f..8ebec1b 100644
--- a/arch/arc/include/asm/pgtable-bits-arcv2.h
+++ b/arch/arc/include/asm/pgtable-bits-arcv2.h
@@ -66,7 +66,7 @@
* Other rules which cause the divergence from 1:1 mapping
*
* 1. Although ARC700 can do exclusive execute/write protection (meaning R
- * can be tracked independet of X/W unlike some other CPUs), still to
+ * can be tracked independently of X/W unlike some other CPUs), still to
* keep things consistent with other archs:
* -Write implies Read: W => R
* -Execute implies Read: X => R
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 00b9318..cf79df0 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -169,7 +169,7 @@
return *(unsigned long *)((unsigned long)regs + offset);
}
-extern int syscall_trace_entry(struct pt_regs *);
+extern int syscall_trace_enter(struct pt_regs *);
extern void syscall_trace_exit(struct pt_regs *);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/shmparam.h b/arch/arc/include/asm/shmparam.h
index 8b02514..719112a 100644
--- a/arch/arc/include/asm/shmparam.h
+++ b/arch/arc/include/asm/shmparam.h
@@ -6,7 +6,7 @@
#ifndef __ARC_ASM_SHMPARAM_H
#define __ARC_ASM_SHMPARAM_H
-/* Handle upto 2 cache bins */
+/* Handle up to 2 cache bins */
#define SHMLBA (2 * PAGE_SIZE)
/* Enforce SHMLBA in shmat */
diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h
index e0913f5..990f834 100644
--- a/arch/arc/include/asm/smp.h
+++ b/arch/arc/include/asm/smp.h
@@ -77,7 +77,7 @@
/*
* ARC700 doesn't support atomic Read-Modify-Write ops.
- * Originally Interrupts had to be disabled around code to gaurantee atomicity.
+ * Originally Interrupts had to be disabled around code to guarantee atomicity.
* The LLOCK/SCOND insns allow writing interrupt-hassle-free based atomic ops
* based on retry-if-irq-in-atomic (with hardware assist).
* However despite these, we provide the IRQ disabling variant
@@ -86,7 +86,7 @@
* support needed.
*
* (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be
- * gaurantted by the platform (not something which core handles).
+ * guaranteed by the platform (not something which core handles).
* Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ
* disabling for atomicity.
*
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 4c530cf..12daaf3 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -38,7 +38,7 @@
struct thread_info {
unsigned long flags; /* low level flags */
unsigned long ksp; /* kernel mode stack top in __switch_to */
- int preempt_count; /* 0 => preemptable, <0 => BUG */
+ int preempt_count; /* 0 => preemptible, <0 => BUG */
int cpu; /* current CPU */
unsigned long thr_ptr; /* TLS ptr */
struct task_struct *task; /* main task structure */
diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h
index 02109cd..8d1f1ef 100644
--- a/arch/arc/include/uapi/asm/swab.h
+++ b/arch/arc/include/uapi/asm/swab.h
@@ -62,7 +62,7 @@
* 8051fdc4: st r2,[r1,20] ; Mem op : save result back to mem
*
* Joern suggested a better "C" algorithm which is great since
- * (1) It is portable to any architecure
+ * (1) It is portable to any architecture
* (2) At the same time it takes advantage of ARC ISA (rotate intrns)
*/
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index 2e49c81..e238b5f 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -5,7 +5,7 @@
* Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com)
*/
-#include <linux/linkage.h> /* ARC_{EXTRY,EXIT} */
+#include <linux/linkage.h> /* ARC_{ENTRY,EXIT} */
#include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,TRAP...} */
#include <asm/errno.h>
#include <asm/arcregs.h>
@@ -31,7 +31,7 @@
VECTOR mem_service ; Mem exception
VECTOR instr_service ; Instrn Error
VECTOR EV_MachineCheck ; Fatal Machine check
-VECTOR EV_TLBMissI ; Intruction TLB miss
+VECTOR EV_TLBMissI ; Instruction TLB miss
VECTOR EV_TLBMissD ; Data TLB miss
VECTOR EV_TLBProtV ; Protection Violation
VECTOR EV_PrivilegeV ; Privilege Violation
@@ -76,11 +76,11 @@
# query in hard ISR path would return false (since .IE is set) which would
# trips genirq interrupt handling asserts.
#
- # So do a "soft" disable of interrutps here.
+ # So do a "soft" disable of interrupts here.
#
# Note this disable is only for consistent book-keeping as further interrupts
# will be disabled anyways even w/o this. Hardware tracks active interrupts
- # seperately in AUX_IRQ_ACT.active and will not take new interrupts
+ # separately in AUX_IRQ_ACT.active and will not take new interrupts
# unless this one returns (or higher prio becomes pending in 2-prio scheme)
IRQ_DISABLE
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 089f668..3c7e74a 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -95,7 +95,7 @@
lr r0, [efa]
mov r1, sp
- ; MC excpetions disable MMU
+ ; MC exceptions disable MMU
ARC_MMU_REENABLE r3
lsr r3, r10, 8
@@ -209,7 +209,7 @@
; ---------------------------------------------
; syscall TRAP
-; ABI: (r0-r7) upto 8 args, (r8) syscall number
+; ABI: (r0-r7) up to 8 args, (r8) syscall number
; ---------------------------------------------
ENTRY(EV_Trap)
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 9152782..8d541f5 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -165,7 +165,7 @@
; setup stack (fp, sp)
mov fp, 0
- ; set it's stack base to tsk->thread_info bottom
+ ; set its stack base to tsk->thread_info bottom
GET_TSK_STACK_BASE r0, sp
j start_kernel_secondary
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 6788987..f324f0e 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -56,7 +56,7 @@
WRITE_AUX(AUX_IRQ_CTRL, ictrl);
/*
- * ARCv2 core intc provides multiple interrupt priorities (upto 16).
+ * ARCv2 core intc provides multiple interrupt priorities (up to 16).
* Typical builds though have only two levels (0-high, 1-low)
* Linux by default uses lower prio 1 for most irqs, reserving 0 for
* NMI style interrupts in future (say perf)
diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index e71d641..f8e2960 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -190,7 +190,8 @@
}
}
-int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
+static int
+__kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
{
struct kprobe *p;
struct kprobe_ctlblk *kcb;
@@ -241,8 +242,8 @@
return 0;
}
-static int __kprobes arc_post_kprobe_handler(unsigned long addr,
- struct pt_regs *regs)
+static int
+__kprobes arc_post_kprobe_handler(unsigned long addr, struct pt_regs *regs)
{
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index adff957..6e5a651c 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -38,7 +38,7 @@
* (based on a specific RTL build)
* Below is the static map between perf generic/arc specific event_id and
* h/w condition names.
- * At the time of probe, we loop thru each index and find it's name to
+ * At the time of probe, we loop thru each index and find its name to
* complete the mapping of perf event_id to h/w index as latter is needed
* to program the counter really
*/
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index d08a509..7b6a9be 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -390,7 +390,7 @@
#ifdef CONFIG_ARC_HAS_DCCM
/*
* DCCM can be arbit placed in hardware.
- * Make sure it's placement/sz matches what Linux is built with
+ * Make sure its placement/sz matches what Linux is built with
*/
if ((unsigned int)__arc_dccm_base != info->dccm.base)
panic("Linux built with incorrect DCCM Base address\n");
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index 8f6f4a5..fefa705 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -8,15 +8,16 @@
*
* vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK)
* -do_signal() supports TIF_RESTORE_SIGMASK
- * -do_signal() no loner needs oldset, required by OLD sys_sigsuspend
- * -sys_rt_sigsuspend() now comes from generic code, so discard arch implemen
+ * -do_signal() no longer needs oldset, required by OLD sys_sigsuspend
+ * -sys_rt_sigsuspend() now comes from generic code, so discard arch
+ * implementation
* -sys_sigsuspend() no longer needs to fudge ptregs, hence that arg removed
* -sys_sigsuspend() no longer loops for do_signal(), sets TIF_xxx and leaves
* the job to do_signal()
*
* vineetg: July 2009
* -Modified Code to support the uClibc provided userland sigreturn stub
- * to avoid kernel synthesing it on user stack at runtime, costing TLB
+ * to avoid kernel synthesizing it on user stack at runtime, costing TLB
* probes and Cache line flushes.
*
* vineetg: July 2009
diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c
index 9b9570b..a19751e 100644
--- a/arch/arc/kernel/traps.c
+++ b/arch/arc/kernel/traps.c
@@ -89,7 +89,7 @@
/*
* Entry point for miscll errors such as Nested Exceptions
- * -Duplicate TLB entry is handled seperately though
+ * -Duplicate TLB entry is handled separately though
*/
void do_machine_check_fault(unsigned long address, struct pt_regs *regs)
{
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 549c3f4..61a1b2b 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -41,8 +41,8 @@
#endif
/*
- * The reason for having a seperate subsection .init.ramfs is to
- * prevent objump from including it in kernel dumps
+ * The reason for having a separate subsection .init.ramfs is to
+ * prevent objdump from including it in kernel dumps
*
* Reason for having .init.ramfs above .init is to make sure that the
* binary blob is tucked away to one side, reducing the displacement
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index ad702b4..cae4a7a 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -212,7 +212,7 @@
unsigned long flags;
/* If range @start to @end is more than 32 TLB entries deep,
- * its better to move to a new ASID rather than searching for
+ * it's better to move to a new ASID rather than searching for
* individual entries and then shooting them down
*
* The calc above is rough, doesn't account for unaligned parts,
@@ -408,7 +408,7 @@
* -More importantly it makes this handler inconsistent with fast-path
* TLB Refill handler which always deals with "current"
*
- * Lets see the use cases when current->mm != vma->mm and we land here
+ * Let's see the use cases when current->mm != vma->mm and we land here
* 1. execve->copy_strings()->__get_user_pages->handle_mm_fault
* Here VM wants to pre-install a TLB entry for user stack while
* current->mm still points to pre-execve mm (hence the condition).
diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S
index e054780..dc65e87 100644
--- a/arch/arc/mm/tlbex.S
+++ b/arch/arc/mm/tlbex.S
@@ -5,19 +5,19 @@
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
*
* Vineetg: April 2011 :
- * -MMU v1: moved out legacy code into a seperate file
+ * -MMU v1: moved out legacy code into a separate file
* -MMU v3: PD{0,1} bits layout changed: They don't overlap anymore,
* helps avoid a shift when preparing PD0 from PTE
*
* Vineetg: July 2009
- * -For MMU V2, we need not do heuristics at the time of commiting a D-TLB
- * entry, so that it doesn't knock out it's I-TLB entry
+ * -For MMU V2, we need not do heuristics at the time of committing a D-TLB
+ * entry, so that it doesn't knock out its I-TLB entry
* -Some more fine tuning:
* bmsk instead of add, asl.cc instead of branch, delay slot utilise etc
*
* Vineetg: July 2009
* -Practically rewrote the I/D TLB Miss handlers
- * Now 40 and 135 instructions a peice as compared to 131 and 449 resp.
+ * Now 40 and 135 instructions apiece as compared to 131 and 449 resp.
* Hence Leaner by 1.5 K
* Used Conditional arithmetic to replace excessive branching
* Also used short instructions wherever possible
diff --git a/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts
index 4f609e9..009d2c8 100644
--- a/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts
@@ -242,7 +242,7 @@
regulator-state-standby {
regulator-on-in-suspend;
- regulator-suspend-voltage = <1150000>;
+ regulator-suspend-microvolt = <1150000>;
regulator-mode = <4>;
};
@@ -263,7 +263,7 @@
regulator-state-standby {
regulator-on-in-suspend;
- regulator-suspend-voltage = <1050000>;
+ regulator-suspend-microvolt = <1050000>;
regulator-mode = <4>;
};
@@ -280,7 +280,7 @@
regulator-always-on;
regulator-state-standby {
- regulator-suspend-voltage = <1800000>;
+ regulator-suspend-microvolt = <1800000>;
regulator-on-in-suspend;
};
@@ -296,7 +296,7 @@
regulator-always-on;
regulator-state-standby {
- regulator-suspend-voltage = <3300000>;
+ regulator-suspend-microvolt = <3300000>;
regulator-on-in-suspend;
};
diff --git a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts
index 217e9b9..20b2497 100644
--- a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts
@@ -293,7 +293,7 @@
regulator-state-standby {
regulator-on-in-suspend;
- regulator-suspend-voltage = <1150000>;
+ regulator-suspend-microvolt = <1150000>;
regulator-mode = <4>;
};
@@ -314,7 +314,7 @@
regulator-state-standby {
regulator-on-in-suspend;
- regulator-suspend-voltage = <1050000>;
+ regulator-suspend-microvolt = <1050000>;
regulator-mode = <4>;
};
@@ -331,7 +331,7 @@
regulator-always-on;
regulator-state-standby {
- regulator-suspend-voltage = <1800000>;
+ regulator-suspend-microvolt = <1800000>;
regulator-on-in-suspend;
};
@@ -346,7 +346,7 @@
regulator-max-microvolt = <3700000>;
regulator-state-standby {
- regulator-suspend-voltage = <1800000>;
+ regulator-suspend-microvolt = <1800000>;
regulator-on-in-suspend;
};
diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi
index 3fdece5..5248a05 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi
@@ -805,6 +805,7 @@
&pinctrl_usb_pwr>;
dr_mode = "host";
power-active-high;
+ over-current-active-low;
disable-over-current;
status = "okay";
};
diff --git a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
index 1235a71..52869e6 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi
@@ -666,7 +666,7 @@
bus-width = <4>;
no-1-8-v;
no-sdio;
- no-emmc;
+ no-mmc;
status = "okay";
};
diff --git a/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts b/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts
index ba7231b..7bab113 100644
--- a/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts
+++ b/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts
@@ -210,6 +210,7 @@
remote-endpoint = <&mipi_from_sensor>;
clock-lanes = <0>;
data-lanes = <1>;
+ link-frequencies = /bits/ 64 <330000000>;
};
};
};
diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c
index 31755a3..ff2a4a4 100644
--- a/arch/arm/mach-omap2/board-n8x0.c
+++ b/arch/arm/mach-omap2/board-n8x0.c
@@ -79,10 +79,8 @@
static struct gpiod_lookup_table tusb_gpio_table = {
.dev_id = "musb-tusb",
.table = {
- GPIO_LOOKUP("gpio-0-15", 0, "enable",
- GPIO_ACTIVE_HIGH),
- GPIO_LOOKUP("gpio-48-63", 10, "int",
- GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP("gpio-0-31", 0, "enable", GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP("gpio-32-63", 26, "int", GPIO_ACTIVE_HIGH),
{ }
},
};
@@ -140,12 +138,11 @@
static int slot2_cover_open;
static struct device *mmc_device;
-static struct gpiod_lookup_table nokia8xx_mmc_gpio_table = {
+static struct gpiod_lookup_table nokia800_mmc_gpio_table = {
.dev_id = "mmci-omap.0",
.table = {
/* Slot switch, GPIO 96 */
- GPIO_LOOKUP("gpio-80-111", 16,
- "switch", GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP("gpio-96-127", 0, "switch", GPIO_ACTIVE_HIGH),
{ }
},
};
@@ -153,12 +150,12 @@
static struct gpiod_lookup_table nokia810_mmc_gpio_table = {
.dev_id = "mmci-omap.0",
.table = {
+ /* Slot switch, GPIO 96 */
+ GPIO_LOOKUP("gpio-96-127", 0, "switch", GPIO_ACTIVE_HIGH),
/* Slot index 1, VSD power, GPIO 23 */
- GPIO_LOOKUP_IDX("gpio-16-31", 7,
- "vsd", 1, GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP_IDX("gpio-0-31", 23, "vsd", 1, GPIO_ACTIVE_HIGH),
/* Slot index 1, VIO power, GPIO 9 */
- GPIO_LOOKUP_IDX("gpio-0-15", 9,
- "vio", 1, GPIO_ACTIVE_HIGH),
+ GPIO_LOOKUP_IDX("gpio-0-31", 9, "vio", 1, GPIO_ACTIVE_HIGH),
{ }
},
};
@@ -415,8 +412,6 @@
static void __init n8x0_mmc_init(void)
{
- gpiod_add_lookup_table(&nokia8xx_mmc_gpio_table);
-
if (board_is_n810()) {
mmc1_data.slots[0].name = "external";
@@ -429,6 +424,8 @@
mmc1_data.slots[1].name = "internal";
mmc1_data.slots[1].ban_openended = 1;
gpiod_add_lookup_table(&nokia810_mmc_gpio_table);
+ } else {
+ gpiod_add_lookup_table(&nokia800_mmc_gpio_table);
}
mmc1_data.nr_slots = 2;
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 1d67245..72b5cd6 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -871,16 +871,11 @@
}
/* dst = src (4 bytes)*/
-static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off,
- struct jit_ctx *ctx) {
+static inline void emit_a32_mov_r(const s8 dst, const s8 src, struct jit_ctx *ctx) {
const s8 *tmp = bpf2a32[TMP_REG_1];
s8 rt;
rt = arm_bpf_get_reg32(src, tmp[0], ctx);
- if (off && off != 32) {
- emit(ARM_LSL_I(rt, rt, 32 - off), ctx);
- emit(ARM_ASR_I(rt, rt, 32 - off), ctx);
- }
arm_bpf_put_reg32(dst, rt, ctx);
}
@@ -889,15 +884,15 @@
const s8 src[],
struct jit_ctx *ctx) {
if (!is64) {
- emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
+ emit_a32_mov_r(dst_lo, src_lo, ctx);
if (!ctx->prog->aux->verifier_zext)
/* Zero out high 4 bytes */
emit_a32_mov_i(dst_hi, 0, ctx);
} else if (__LINUX_ARM_ARCH__ < 6 &&
ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
/* complete 8 byte move */
- emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
- emit_a32_mov_r(dst_hi, src_hi, 0, ctx);
+ emit_a32_mov_r(dst_lo, src_lo, ctx);
+ emit_a32_mov_r(dst_hi, src_hi, ctx);
} else if (is_stacked(src_lo) && is_stacked(dst_lo)) {
const u8 *tmp = bpf2a32[TMP_REG_1];
@@ -917,17 +912,52 @@
static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[],
struct jit_ctx *ctx) {
const s8 *tmp = bpf2a32[TMP_REG_1];
- const s8 *rt;
+ s8 rs;
+ s8 rd;
- rt = arm_bpf_get_reg64(dst, tmp, ctx);
+ if (is_stacked(dst_lo))
+ rd = tmp[1];
+ else
+ rd = dst_lo;
+ rs = arm_bpf_get_reg32(src_lo, rd, ctx);
+ /* rs may be one of src[1], dst[1], or tmp[1] */
- emit_a32_mov_r(dst_lo, src_lo, off, ctx);
+ /* Sign extend rs if needed. If off == 32, lower 32-bits of src are moved to dst and sign
+ * extension only happens in the upper 64 bits.
+ */
+ if (off != 32) {
+ /* Sign extend rs into rd */
+ emit(ARM_LSL_I(rd, rs, 32 - off), ctx);
+ emit(ARM_ASR_I(rd, rd, 32 - off), ctx);
+ } else {
+ rd = rs;
+ }
+
+ /* Write rd to dst_lo
+ *
+ * Optimization:
+ * Assume:
+ * 1. dst == src and stacked.
+ * 2. off == 32
+ *
+ * In this case src_lo was loaded into rd(tmp[1]) but rd was not sign extended as off==32.
+ * So, we don't need to write rd back to dst_lo as they have the same value.
+ * This saves us one str instruction.
+ */
+ if (dst_lo != src_lo || off != 32)
+ arm_bpf_put_reg32(dst_lo, rd, ctx);
+
if (!is64) {
if (!ctx->prog->aux->verifier_zext)
/* Zero out high 4 bytes */
emit_a32_mov_i(dst_hi, 0, ctx);
} else {
- emit(ARM_ASR_I(rt[0], rt[1], 31), ctx);
+ if (is_stacked(dst_hi)) {
+ emit(ARM_ASR_I(tmp[0], rd, 31), ctx);
+ arm_bpf_put_reg32(dst_hi, tmp[0], ctx);
+ } else {
+ emit(ARM_ASR_I(dst_hi, rd, 31), ctx);
+ }
}
}
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi
index 3c42240..4aaf5a0 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi
@@ -41,7 +41,7 @@
interrupts = <GIC_SPI 267 IRQ_TYPE_LEVEL_HIGH>;
fsl,usbphy = <&usbphy1>;
fsl,usbmisc = <&usbmisc1 0>;
- clocks = <&usb2_lpcg 0>;
+ clocks = <&usb2_lpcg IMX_LPCG_CLK_6>;
ahb-burst-config = <0x0>;
tx-burst-size-dword = <0x10>;
rx-burst-size-dword = <0x10>;
@@ -58,7 +58,7 @@
usbphy1: usbphy@5b100000 {
compatible = "fsl,imx7ulp-usbphy";
reg = <0x5b100000 0x1000>;
- clocks = <&usb2_lpcg 1>;
+ clocks = <&usb2_lpcg IMX_LPCG_CLK_7>;
power-domains = <&pd IMX_SC_R_USB_0_PHY>;
status = "disabled";
};
@@ -67,8 +67,8 @@
interrupts = <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>;
reg = <0x5b010000 0x10000>;
clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>,
- <&sdhc0_lpcg IMX_LPCG_CLK_0>,
- <&sdhc0_lpcg IMX_LPCG_CLK_5>;
+ <&sdhc0_lpcg IMX_LPCG_CLK_5>,
+ <&sdhc0_lpcg IMX_LPCG_CLK_0>;
clock-names = "ipg", "ahb", "per";
power-domains = <&pd IMX_SC_R_SDHC_0>;
status = "disabled";
@@ -78,8 +78,8 @@
interrupts = <GIC_SPI 233 IRQ_TYPE_LEVEL_HIGH>;
reg = <0x5b020000 0x10000>;
clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>,
- <&sdhc1_lpcg IMX_LPCG_CLK_0>,
- <&sdhc1_lpcg IMX_LPCG_CLK_5>;
+ <&sdhc1_lpcg IMX_LPCG_CLK_5>,
+ <&sdhc1_lpcg IMX_LPCG_CLK_0>;
clock-names = "ipg", "ahb", "per";
power-domains = <&pd IMX_SC_R_SDHC_1>;
fsl,tuning-start-tap = <20>;
@@ -91,8 +91,8 @@
interrupts = <GIC_SPI 234 IRQ_TYPE_LEVEL_HIGH>;
reg = <0x5b030000 0x10000>;
clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>,
- <&sdhc2_lpcg IMX_LPCG_CLK_0>,
- <&sdhc2_lpcg IMX_LPCG_CLK_5>;
+ <&sdhc2_lpcg IMX_LPCG_CLK_5>,
+ <&sdhc2_lpcg IMX_LPCG_CLK_0>;
clock-names = "ipg", "ahb", "per";
power-domains = <&pd IMX_SC_R_SDHC_2>;
status = "disabled";
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
index cab3468..f7a91d4 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi
@@ -28,8 +28,8 @@
#size-cells = <0>;
interrupts = <GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
- clocks = <&spi0_lpcg 0>,
- <&spi0_lpcg 1>;
+ clocks = <&spi0_lpcg IMX_LPCG_CLK_0>,
+ <&spi0_lpcg IMX_LPCG_CLK_4>;
clock-names = "per", "ipg";
assigned-clocks = <&clk IMX_SC_R_SPI_0 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <60000000>;
@@ -44,8 +44,8 @@
#size-cells = <0>;
interrupts = <GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
- clocks = <&spi1_lpcg 0>,
- <&spi1_lpcg 1>;
+ clocks = <&spi1_lpcg IMX_LPCG_CLK_0>,
+ <&spi1_lpcg IMX_LPCG_CLK_4>;
clock-names = "per", "ipg";
assigned-clocks = <&clk IMX_SC_R_SPI_1 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <60000000>;
@@ -60,8 +60,8 @@
#size-cells = <0>;
interrupts = <GIC_SPI 338 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
- clocks = <&spi2_lpcg 0>,
- <&spi2_lpcg 1>;
+ clocks = <&spi2_lpcg IMX_LPCG_CLK_0>,
+ <&spi2_lpcg IMX_LPCG_CLK_4>;
clock-names = "per", "ipg";
assigned-clocks = <&clk IMX_SC_R_SPI_2 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <60000000>;
@@ -76,8 +76,8 @@
#size-cells = <0>;
interrupts = <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
- clocks = <&spi3_lpcg 0>,
- <&spi3_lpcg 1>;
+ clocks = <&spi3_lpcg IMX_LPCG_CLK_0>,
+ <&spi3_lpcg IMX_LPCG_CLK_4>;
clock-names = "per", "ipg";
assigned-clocks = <&clk IMX_SC_R_SPI_3 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <60000000>;
@@ -145,8 +145,8 @@
compatible = "fsl,imx8qxp-pwm", "fsl,imx27-pwm";
reg = <0x5a190000 0x1000>;
interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&adma_pwm_lpcg 1>,
- <&adma_pwm_lpcg 0>;
+ clocks = <&adma_pwm_lpcg IMX_LPCG_CLK_4>,
+ <&adma_pwm_lpcg IMX_LPCG_CLK_0>;
clock-names = "ipg", "per";
assigned-clocks = <&clk IMX_SC_R_LCD_0_PWM_0 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <24000000>;
@@ -355,8 +355,8 @@
reg = <0x5a880000 0x10000>;
interrupts = <GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
- clocks = <&adc0_lpcg 0>,
- <&adc0_lpcg 1>;
+ clocks = <&adc0_lpcg IMX_LPCG_CLK_0>,
+ <&adc0_lpcg IMX_LPCG_CLK_4>;
clock-names = "per", "ipg";
assigned-clocks = <&clk IMX_SC_R_ADC_0 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <24000000>;
@@ -370,8 +370,8 @@
reg = <0x5a890000 0x10000>;
interrupts = <GIC_SPI 241 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
- clocks = <&adc1_lpcg 0>,
- <&adc1_lpcg 1>;
+ clocks = <&adc1_lpcg IMX_LPCG_CLK_0>,
+ <&adc1_lpcg IMX_LPCG_CLK_4>;
clock-names = "per", "ipg";
assigned-clocks = <&clk IMX_SC_R_ADC_1 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <24000000>;
@@ -384,8 +384,8 @@
reg = <0x5a8d0000 0x10000>;
interrupts = <GIC_SPI 235 IRQ_TYPE_LEVEL_HIGH>;
interrupt-parent = <&gic>;
- clocks = <&can0_lpcg 1>,
- <&can0_lpcg 0>;
+ clocks = <&can0_lpcg IMX_LPCG_CLK_4>,
+ <&can0_lpcg IMX_LPCG_CLK_0>;
clock-names = "ipg", "per";
assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <40000000>;
@@ -405,8 +405,8 @@
* CAN1 shares CAN0's clock and to enable CAN0's clock it
* has to be powered on.
*/
- clocks = <&can0_lpcg 1>,
- <&can0_lpcg 0>;
+ clocks = <&can0_lpcg IMX_LPCG_CLK_4>,
+ <&can0_lpcg IMX_LPCG_CLK_0>;
clock-names = "ipg", "per";
assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <40000000>;
@@ -426,8 +426,8 @@
* CAN2 shares CAN0's clock and to enable CAN0's clock it
* has to be powered on.
*/
- clocks = <&can0_lpcg 1>,
- <&can0_lpcg 0>;
+ clocks = <&can0_lpcg IMX_LPCG_CLK_4>,
+ <&can0_lpcg IMX_LPCG_CLK_0>;
clock-names = "ipg", "per";
assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <40000000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
index 7e510b2..764c1a0 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi
@@ -25,8 +25,8 @@
compatible = "fsl,imx27-pwm";
reg = <0x5d000000 0x10000>;
clock-names = "ipg", "per";
- clocks = <&pwm0_lpcg 4>,
- <&pwm0_lpcg 1>;
+ clocks = <&pwm0_lpcg IMX_LPCG_CLK_6>,
+ <&pwm0_lpcg IMX_LPCG_CLK_1>;
assigned-clocks = <&clk IMX_SC_R_PWM_0 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <24000000>;
#pwm-cells = <3>;
@@ -38,8 +38,8 @@
compatible = "fsl,imx27-pwm";
reg = <0x5d010000 0x10000>;
clock-names = "ipg", "per";
- clocks = <&pwm1_lpcg 4>,
- <&pwm1_lpcg 1>;
+ clocks = <&pwm1_lpcg IMX_LPCG_CLK_6>,
+ <&pwm1_lpcg IMX_LPCG_CLK_1>;
assigned-clocks = <&clk IMX_SC_R_PWM_1 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <24000000>;
#pwm-cells = <3>;
@@ -51,8 +51,8 @@
compatible = "fsl,imx27-pwm";
reg = <0x5d020000 0x10000>;
clock-names = "ipg", "per";
- clocks = <&pwm2_lpcg 4>,
- <&pwm2_lpcg 1>;
+ clocks = <&pwm2_lpcg IMX_LPCG_CLK_6>,
+ <&pwm2_lpcg IMX_LPCG_CLK_1>;
assigned-clocks = <&clk IMX_SC_R_PWM_2 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <24000000>;
#pwm-cells = <3>;
@@ -64,8 +64,8 @@
compatible = "fsl,imx27-pwm";
reg = <0x5d030000 0x10000>;
clock-names = "ipg", "per";
- clocks = <&pwm3_lpcg 4>,
- <&pwm3_lpcg 1>;
+ clocks = <&pwm3_lpcg IMX_LPCG_CLK_6>,
+ <&pwm3_lpcg IMX_LPCG_CLK_1>;
assigned-clocks = <&clk IMX_SC_R_PWM_3 IMX_SC_PM_CLK_PER>;
assigned-clock-rates = <24000000>;
#pwm-cells = <3>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
index 41c79d2..f24b147 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi
@@ -14,6 +14,7 @@
pinctrl-0 = <&pinctrl_usbcon1>;
type = "micro";
label = "otg";
+ vbus-supply = <®_usb1_vbus>;
id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
port {
@@ -183,7 +184,6 @@
};
&usb3_phy0 {
- vbus-supply = <®_usb1_vbus>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
index d5c400b..f5491a6 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi
@@ -14,6 +14,7 @@
pinctrl-0 = <&pinctrl_usbcon1>;
type = "micro";
label = "otg";
+ vbus-supply = <®_usb1_vbus>;
id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
port {
@@ -202,7 +203,6 @@
};
&usb3_phy0 {
- vbus-supply = <®_usb1_vbus>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index bfc5c81..8141926 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -1672,7 +1672,7 @@
<&clk IMX8MP_CLK_MEDIA_MIPI_PHY1_REF_ROOT>,
<&clk IMX8MP_CLK_MEDIA_AXI_ROOT>;
clock-names = "pclk", "wrap", "phy", "axi";
- assigned-clocks = <&clk IMX8MP_CLK_MEDIA_CAM1_PIX>,
+ assigned-clocks = <&clk IMX8MP_CLK_MEDIA_CAM2_PIX>,
<&clk IMX8MP_CLK_MEDIA_MIPI_PHY1_REF>;
assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>,
<&clk IMX8MP_CLK_24M>;
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
index 11626fa..aa9f28c 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi
@@ -153,15 +153,15 @@
};
&flexcan2 {
- clocks = <&can1_lpcg 1>,
- <&can1_lpcg 0>;
+ clocks = <&can1_lpcg IMX_LPCG_CLK_4>,
+ <&can1_lpcg IMX_LPCG_CLK_0>;
assigned-clocks = <&clk IMX_SC_R_CAN_1 IMX_SC_PM_CLK_PER>;
fsl,clk-source = /bits/ 8 <1>;
};
&flexcan3 {
- clocks = <&can2_lpcg 1>,
- <&can2_lpcg 0>;
+ clocks = <&can2_lpcg IMX_LPCG_CLK_4>,
+ <&can2_lpcg IMX_LPCG_CLK_0>;
assigned-clocks = <&clk IMX_SC_R_CAN_2 IMX_SC_PM_CLK_PER>;
fsl,clk-source = /bits/ 8 <1>;
};
diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
index 0c38f7b..234e3b2 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
+++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts
@@ -129,7 +129,7 @@
};
&pio {
- eth_default: eth_default {
+ eth_default: eth-default-pins {
tx_pins {
pinmux = <MT2712_PIN_71_GBE_TXD3__FUNC_GBE_TXD3>,
<MT2712_PIN_72_GBE_TXD2__FUNC_GBE_TXD2>,
@@ -156,7 +156,7 @@
};
};
- eth_sleep: eth_sleep {
+ eth_sleep: eth-sleep-pins {
tx_pins {
pinmux = <MT2712_PIN_71_GBE_TXD3__FUNC_GPIO71>,
<MT2712_PIN_72_GBE_TXD2__FUNC_GPIO72>,
@@ -182,14 +182,14 @@
};
};
- usb0_id_pins_float: usb0_iddig {
+ usb0_id_pins_float: usb0-iddig-pins {
pins_iddig {
pinmux = <MT2712_PIN_12_IDDIG_P0__FUNC_IDDIG_A>;
bias-pull-up;
};
};
- usb1_id_pins_float: usb1_iddig {
+ usb1_id_pins_float: usb1-iddig-pins {
pins_iddig {
pinmux = <MT2712_PIN_14_IDDIG_P1__FUNC_IDDIG_B>;
bias-pull-up;
diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
index 6d218ca..082672e 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi
@@ -249,10 +249,11 @@
#clock-cells = <1>;
};
- infracfg: syscon@10001000 {
+ infracfg: clock-controller@10001000 {
compatible = "mediatek,mt2712-infracfg", "syscon";
reg = <0 0x10001000 0 0x1000>;
#clock-cells = <1>;
+ #reset-cells = <1>;
};
pericfg: syscon@10003000 {
diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
index 3ee9266..917fa39 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
@@ -252,7 +252,7 @@
clock-names = "hif_sel";
};
- cir: cir@10009000 {
+ cir: ir-receiver@10009000 {
compatible = "mediatek,mt7622-cir";
reg = <0 0x10009000 0 0x1000>;
interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_LOW>;
@@ -283,16 +283,14 @@
};
};
- apmixedsys: apmixedsys@10209000 {
- compatible = "mediatek,mt7622-apmixedsys",
- "syscon";
+ apmixedsys: clock-controller@10209000 {
+ compatible = "mediatek,mt7622-apmixedsys";
reg = <0 0x10209000 0 0x1000>;
#clock-cells = <1>;
};
- topckgen: topckgen@10210000 {
- compatible = "mediatek,mt7622-topckgen",
- "syscon";
+ topckgen: clock-controller@10210000 {
+ compatible = "mediatek,mt7622-topckgen";
reg = <0 0x10210000 0 0x1000>;
#clock-cells = <1>;
};
@@ -515,7 +513,6 @@
<&pericfg CLK_PERI_AUXADC_PD>;
clock-names = "therm", "auxadc";
resets = <&pericfg MT7622_PERI_THERM_SW_RST>;
- reset-names = "therm";
mediatek,auxadc = <&auxadc>;
mediatek,apmixedsys = <&apmixedsys>;
nvmem-cells = <&thermal_calibration>;
@@ -734,9 +731,8 @@
power-domains = <&scpsys MT7622_POWER_DOMAIN_WB>;
};
- ssusbsys: ssusbsys@1a000000 {
- compatible = "mediatek,mt7622-ssusbsys",
- "syscon";
+ ssusbsys: clock-controller@1a000000 {
+ compatible = "mediatek,mt7622-ssusbsys";
reg = <0 0x1a000000 0 0x1000>;
#clock-cells = <1>;
#reset-cells = <1>;
@@ -793,9 +789,8 @@
};
};
- pciesys: pciesys@1a100800 {
- compatible = "mediatek,mt7622-pciesys",
- "syscon";
+ pciesys: clock-controller@1a100800 {
+ compatible = "mediatek,mt7622-pciesys";
reg = <0 0x1a100800 0 0x1000>;
#clock-cells = <1>;
#reset-cells = <1>;
@@ -921,12 +916,13 @@
};
};
- hifsys: syscon@1af00000 {
- compatible = "mediatek,mt7622-hifsys", "syscon";
+ hifsys: clock-controller@1af00000 {
+ compatible = "mediatek,mt7622-hifsys";
reg = <0 0x1af00000 0 0x70>;
+ #clock-cells = <1>;
};
- ethsys: syscon@1b000000 {
+ ethsys: clock-controller@1b000000 {
compatible = "mediatek,mt7622-ethsys",
"syscon";
reg = <0 0x1b000000 0 0x1000>;
@@ -966,9 +962,7 @@
};
eth: ethernet@1b100000 {
- compatible = "mediatek,mt7622-eth",
- "mediatek,mt2701-eth",
- "syscon";
+ compatible = "mediatek,mt7622-eth";
reg = <0 0x1b100000 0 0x20000>;
interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_LOW>,
<GIC_SPI 224 IRQ_TYPE_LEVEL_LOW>,
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
index e04b1c0..ed79ad1a 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
+++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts
@@ -146,19 +146,19 @@
&cpu_thermal {
cooling-maps {
- cpu-active-high {
+ map-cpu-active-high {
/* active: set fan to cooling level 2 */
cooling-device = <&fan 2 2>;
trip = <&cpu_trip_active_high>;
};
- cpu-active-med {
+ map-cpu-active-med {
/* active: set fan to cooling level 1 */
cooling-device = <&fan 1 1>;
trip = <&cpu_trip_active_med>;
};
- cpu-active-low {
+ map-cpu-active-low {
/* active: set fan to cooling level 0 */
cooling-device = <&fan 0 0>;
trip = <&cpu_trip_active_low>;
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
index b3f416b..559990d 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
@@ -332,9 +332,8 @@
reg = <0 0x1100c800 0 0x800>;
interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&infracfg CLK_INFRA_THERM_CK>,
- <&infracfg CLK_INFRA_ADC_26M_CK>,
- <&infracfg CLK_INFRA_ADC_FRC_CK>;
- clock-names = "therm", "auxadc", "adc_32k";
+ <&infracfg CLK_INFRA_ADC_26M_CK>;
+ clock-names = "therm", "auxadc";
nvmem-cells = <&thermal_calibration>;
nvmem-cell-names = "calibration-data";
#thermal-sensor-cells = <1>;
@@ -492,8 +491,6 @@
compatible = "mediatek,mt7986-ethsys",
"syscon";
reg = <0 0x15000000 0 0x1000>;
- #address-cells = <1>;
- #size-cells = <1>;
#clock-cells = <1>;
#reset-cells = <1>;
};
@@ -556,7 +553,6 @@
<&topckgen CLK_TOP_SGM_325M_SEL>;
assigned-clock-parents = <&apmixedsys CLK_APMIXED_NET2PLL>,
<&apmixedsys CLK_APMIXED_SGMPLL>;
- #reset-cells = <1>;
#address-cells = <1>;
#size-cells = <0>;
mediatek,ethsys = <ðsys>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
index 6bd7424..100191c 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
@@ -433,7 +433,6 @@
};
&mt6358_vgpu_reg {
- regulator-min-microvolt = <625000>;
regulator-max-microvolt = <900000>;
regulator-coupled-with = <&mt6358_vsram_gpu_reg>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
index 93dfbf1..774ae5d 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
@@ -1637,6 +1637,7 @@
compatible = "mediatek,mt8183-mfgcfg", "syscon";
reg = <0 0x13000000 0 0x1000>;
#clock-cells = <1>;
+ power-domains = <&spm MT8183_POWER_DOMAIN_MFG_ASYNC>;
};
gpu: gpu@13040000 {
diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi
index 3dea28f..1807e9d 100644
--- a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi
@@ -1296,7 +1296,7 @@
* regulator coupling requirements.
*/
regulator-name = "ppvar_dvdd_vgpu";
- regulator-min-microvolt = <600000>;
+ regulator-min-microvolt = <500000>;
regulator-max-microvolt = <950000>;
regulator-ramp-delay = <6250>;
regulator-enable-ramp-delay = <200>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
index 9b738f6..7a70424 100644
--- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
@@ -1421,7 +1421,7 @@
mt6315_6_vbuck1: vbuck1 {
regulator-compatible = "vbuck1";
regulator-name = "Vbcpu";
- regulator-min-microvolt = <300000>;
+ regulator-min-microvolt = <400000>;
regulator-max-microvolt = <1193750>;
regulator-enable-ramp-delay = <256>;
regulator-allowed-modes = <0 1 2>;
@@ -1431,7 +1431,7 @@
mt6315_6_vbuck3: vbuck3 {
regulator-compatible = "vbuck3";
regulator-name = "Vlcpu";
- regulator-min-microvolt = <300000>;
+ regulator-min-microvolt = <400000>;
regulator-max-microvolt = <1193750>;
regulator-enable-ramp-delay = <256>;
regulator-allowed-modes = <0 1 2>;
@@ -1448,7 +1448,7 @@
mt6315_7_vbuck1: vbuck1 {
regulator-compatible = "vbuck1";
regulator-name = "Vgpu";
- regulator-min-microvolt = <606250>;
+ regulator-min-microvolt = <400000>;
regulator-max-microvolt = <800000>;
regulator-enable-ramp-delay = <256>;
regulator-allowed-modes = <0 1 2>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
index 05e4016..84cbdf6 100644
--- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
@@ -1464,6 +1464,7 @@
reg = <0 0x14001000 0 0x1000>;
interrupts = <GIC_SPI 252 IRQ_TYPE_LEVEL_HIGH 0>;
clocks = <&mmsys CLK_MM_DISP_MUTEX0>;
+ mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>;
mediatek,gce-events = <CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_0>,
<CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_1>;
power-domains = <&spm MT8192_POWER_DOMAIN_DISP>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
index f94c07f..4a11918 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
@@ -264,6 +264,38 @@
status = "okay";
};
+&cpu0 {
+ cpu-supply = <&mt6359_vcore_buck_reg>;
+};
+
+&cpu1 {
+ cpu-supply = <&mt6359_vcore_buck_reg>;
+};
+
+&cpu2 {
+ cpu-supply = <&mt6359_vcore_buck_reg>;
+};
+
+&cpu3 {
+ cpu-supply = <&mt6359_vcore_buck_reg>;
+};
+
+&cpu4 {
+ cpu-supply = <&mt6315_6_vbuck1>;
+};
+
+&cpu5 {
+ cpu-supply = <&mt6315_6_vbuck1>;
+};
+
+&cpu6 {
+ cpu-supply = <&mt6315_6_vbuck1>;
+};
+
+&cpu7 {
+ cpu-supply = <&mt6315_6_vbuck1>;
+};
+
&dp_intf0 {
status = "okay";
@@ -1214,7 +1246,7 @@
mt6315_6_vbuck1: vbuck1 {
regulator-compatible = "vbuck1";
regulator-name = "Vbcpu";
- regulator-min-microvolt = <300000>;
+ regulator-min-microvolt = <400000>;
regulator-max-microvolt = <1193750>;
regulator-enable-ramp-delay = <256>;
regulator-ramp-delay = <6250>;
@@ -1232,7 +1264,7 @@
mt6315_7_vbuck1: vbuck1 {
regulator-compatible = "vbuck1";
regulator-name = "Vgpu";
- regulator-min-microvolt = <625000>;
+ regulator-min-microvolt = <400000>;
regulator-max-microvolt = <1193750>;
regulator-enable-ramp-delay = <256>;
regulator-ramp-delay = <6250>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
index ea6dc22..5d8b68f 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
@@ -2028,6 +2028,7 @@
compatible = "mediatek,mt8195-vppsys0", "syscon";
reg = <0 0x14000000 0 0x1000>;
#clock-cells = <1>;
+ mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0 0x1000>;
};
dma-controller@14001000 {
@@ -2251,6 +2252,7 @@
compatible = "mediatek,mt8195-vppsys1", "syscon";
reg = <0 0x14f00000 0 0x1000>;
#clock-cells = <1>;
+ mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0 0x1000>;
};
mutex@14f01000 {
@@ -3080,6 +3082,7 @@
reg = <0 0x1c01a000 0 0x1000>;
mboxes = <&gce0 0 CMDQ_THR_PRIO_4>;
#clock-cells = <1>;
+ mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0xa000 0x1000>;
};
@@ -3261,6 +3264,7 @@
interrupts = <GIC_SPI 658 IRQ_TYPE_LEVEL_HIGH 0>;
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>;
clocks = <&vdosys0 CLK_VDO0_DISP_MUTEX0>;
+ mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0x6000 0x1000>;
mediatek,gce-events = <CMDQ_EVENT_VDO0_DISP_STREAM_DONE_0>;
};
@@ -3331,6 +3335,7 @@
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
clocks = <&vdosys1 CLK_VDO1_DISP_MUTEX>;
clock-names = "vdo1_mutex";
+ mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x1000 0x1000>;
mediatek,gce-events = <CMDQ_EVENT_VDO1_STREAM_DONE_ENG_0>;
};
diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi
index 7e7f0f0..41f51d3 100644
--- a/arch/arm64/boot/dts/qcom/sc7280.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi
@@ -3707,7 +3707,7 @@
compatible = "qcom,sc7280-adsp-pas";
reg = <0 0x03700000 0 0x100>;
- interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>,
<&adsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
<&adsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>,
<&adsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -3944,7 +3944,7 @@
compatible = "qcom,sc7280-cdsp-pas";
reg = <0 0x0a300000 0 0x10000>;
- interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>,
<&cdsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>,
<&cdsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>,
<&cdsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>,
diff --git a/arch/arm64/boot/dts/qcom/sc8180x.dtsi b/arch/arm64/boot/dts/qcom/sc8180x.dtsi
index 32afc78..053f786 100644
--- a/arch/arm64/boot/dts/qcom/sc8180x.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8180x.dtsi
@@ -2701,7 +2701,7 @@
resets = <&gcc GCC_USB30_SEC_BCR>;
power-domains = <&gcc USB30_SEC_GDSC>;
interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
- <&pdc 7 IRQ_TYPE_LEVEL_HIGH>,
+ <&pdc 40 IRQ_TYPE_LEVEL_HIGH>,
<&pdc 10 IRQ_TYPE_EDGE_BOTH>,
<&pdc 11 IRQ_TYPE_EDGE_BOTH>;
interrupt-names = "hs_phy_irq", "ss_phy_irq",
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
index a5b1948..d0f82e1 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
@@ -1774,6 +1774,7 @@
reset-names = "pci";
power-domains = <&gcc PCIE_4_GDSC>;
+ required-opps = <&rpmhpd_opp_nom>;
phys = <&pcie4_phy>;
phy-names = "pciephy";
@@ -1872,6 +1873,7 @@
reset-names = "pci";
power-domains = <&gcc PCIE_3B_GDSC>;
+ required-opps = <&rpmhpd_opp_nom>;
phys = <&pcie3b_phy>;
phy-names = "pciephy";
@@ -1970,6 +1972,7 @@
reset-names = "pci";
power-domains = <&gcc PCIE_3A_GDSC>;
+ required-opps = <&rpmhpd_opp_nom>;
phys = <&pcie3a_phy>;
phy-names = "pciephy";
@@ -2071,6 +2074,7 @@
reset-names = "pci";
power-domains = <&gcc PCIE_2B_GDSC>;
+ required-opps = <&rpmhpd_opp_nom>;
phys = <&pcie2b_phy>;
phy-names = "pciephy";
@@ -2169,6 +2173,7 @@
reset-names = "pci";
power-domains = <&gcc PCIE_2A_GDSC>;
+ required-opps = <&rpmhpd_opp_nom>;
phys = <&pcie2a_phy>;
phy-names = "pciephy";
@@ -2641,7 +2646,7 @@
compatible = "qcom,sc8280xp-adsp-pas";
reg = <0 0x03000000 0 0x100>;
- interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -4977,7 +4982,7 @@
compatible = "qcom,sc8280xp-nsp0-pas";
reg = <0 0x1b300000 0 0x100>;
- interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>,
<&smp2p_nsp0_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_nsp0_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_nsp0_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -5108,7 +5113,7 @@
compatible = "qcom,sc8280xp-nsp1-pas";
reg = <0 0x21300000 0 0x100>;
- interrupts-extended = <&intc GIC_SPI 887 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&intc GIC_SPI 887 IRQ_TYPE_EDGE_RISING>,
<&smp2p_nsp1_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_nsp1_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_nsp1_in 2 IRQ_TYPE_EDGE_RISING>,
diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi
index 24bcec3..0be0535 100644
--- a/arch/arm64/boot/dts/qcom/sm6350.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi
@@ -1252,7 +1252,7 @@
compatible = "qcom,sm6350-adsp-pas";
reg = <0 0x03000000 0 0x100>;
- interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -1511,7 +1511,7 @@
compatible = "qcom,sm6350-cdsp-pas";
reg = <0 0x08300000 0 0x10000>;
- interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>,
<&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>,
diff --git a/arch/arm64/boot/dts/qcom/sm6375.dtsi b/arch/arm64/boot/dts/qcom/sm6375.dtsi
index 4386f8a..f40509d 100644
--- a/arch/arm64/boot/dts/qcom/sm6375.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm6375.dtsi
@@ -1561,7 +1561,7 @@
compatible = "qcom,sm6375-adsp-pas";
reg = <0 0x0a400000 0 0x100>;
- interrupts-extended = <&intc GIC_SPI 282 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&intc GIC_SPI 282 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>,
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index 39bd8f0..7f2333c 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -3062,7 +3062,7 @@
compatible = "qcom,sm8250-slpi-pas";
reg = <0 0x05c00000 0 0x4000>;
- interrupts-extended = <&pdc 9 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&pdc 9 IRQ_TYPE_EDGE_RISING>,
<&smp2p_slpi_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_slpi_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_slpi_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -3766,7 +3766,7 @@
compatible = "qcom,sm8250-cdsp-pas";
reg = <0 0x08300000 0 0x10000>;
- interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>,
<&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>,
@@ -5928,7 +5928,7 @@
compatible = "qcom,sm8250-adsp-pas";
reg = <0 0x17300000 0 0x100>;
- interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>,
+ interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>,
<&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>,
diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi
index b86be34..024d265 100644
--- a/arch/arm64/boot/dts/qcom/sm8450.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi
@@ -1777,12 +1777,8 @@
ranges = <0x01000000 0x0 0x00000000 0x0 0x60200000 0x0 0x100000>,
<0x02000000 0x0 0x60300000 0x0 0x60300000 0x0 0x3d00000>;
- /*
- * MSIs for BDF (1:0.0) only works with Device ID 0x5980.
- * Hence, the IDs are swapped.
- */
- msi-map = <0x0 &gic_its 0x5981 0x1>,
- <0x100 &gic_its 0x5980 0x1>;
+ msi-map = <0x0 &gic_its 0x5980 0x1>,
+ <0x100 &gic_its 0x5981 0x1>;
msi-map-mask = <0xff00>;
interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,
@@ -1900,12 +1896,8 @@
ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>,
<0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>;
- /*
- * MSIs for BDF (1:0.0) only works with Device ID 0x5a00.
- * Hence, the IDs are swapped.
- */
- msi-map = <0x0 &gic_its 0x5a01 0x1>,
- <0x100 &gic_its 0x5a00 0x1>;
+ msi-map = <0x0 &gic_its 0x5a00 0x1>,
+ <0x100 &gic_its 0x5a01 0x1>;
msi-map-mask = <0xff00>;
interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi
index 3904348..3348bc0 100644
--- a/arch/arm64/boot/dts/qcom/sm8550.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi
@@ -1755,9 +1755,8 @@
<&gem_noc MASTER_APPSS_PROC 0 &cnoc_main SLAVE_PCIE_0 0>;
interconnect-names = "pcie-mem", "cpu-pcie";
- /* Entries are reversed due to the unusual ITS DeviceID encoding */
- msi-map = <0x0 &gic_its 0x1401 0x1>,
- <0x100 &gic_its 0x1400 0x1>;
+ msi-map = <0x0 &gic_its 0x1400 0x1>,
+ <0x100 &gic_its 0x1401 0x1>;
iommu-map = <0x0 &apps_smmu 0x1400 0x1>,
<0x100 &apps_smmu 0x1401 0x1>;
@@ -1867,9 +1866,8 @@
<&gem_noc MASTER_APPSS_PROC 0 &cnoc_main SLAVE_PCIE_1 0>;
interconnect-names = "pcie-mem", "cpu-pcie";
- /* Entries are reversed due to the unusual ITS DeviceID encoding */
- msi-map = <0x0 &gic_its 0x1481 0x1>,
- <0x100 &gic_its 0x1480 0x1>;
+ msi-map = <0x0 &gic_its 0x1480 0x1>,
+ <0x100 &gic_its 0x1481 0x1>;
iommu-map = <0x0 &apps_smmu 0x1480 0x1>,
<0x100 &apps_smmu 0x1481 0x1>;
diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi
index ba72d8f..eb11786 100644
--- a/arch/arm64/boot/dts/qcom/sm8650.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi
@@ -2274,9 +2274,8 @@
interrupt-map-mask = <0 0 0 0x7>;
#interrupt-cells = <1>;
- /* Entries are reversed due to the unusual ITS DeviceID encoding */
- msi-map = <0x0 &gic_its 0x1401 0x1>,
- <0x100 &gic_its 0x1400 0x1>;
+ msi-map = <0x0 &gic_its 0x1400 0x1>,
+ <0x100 &gic_its 0x1401 0x1>;
msi-map-mask = <0xff00>;
linux,pci-domain = <0>;
@@ -2402,9 +2401,8 @@
interrupt-map-mask = <0 0 0 0x7>;
#interrupt-cells = <1>;
- /* Entries are reversed due to the unusual ITS DeviceID encoding */
- msi-map = <0x0 &gic_its 0x1481 0x1>,
- <0x100 &gic_its 0x1480 0x1>;
+ msi-map = <0x0 &gic_its 0x1480 0x1>,
+ <0x100 &gic_its 0x1481 0x1>;
msi-map-mask = <0xff00>;
linux,pci-domain = <1>;
diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
index 8e517f7..6b40082 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
@@ -284,7 +284,7 @@
domain-idle-states {
CLUSTER_CL4: cluster-sleep-0 {
- compatible = "arm,idle-state";
+ compatible = "domain-idle-state";
idle-state-name = "l2-ret";
arm,psci-suspend-param = <0x01000044>;
entry-latency-us = <350>;
@@ -293,7 +293,7 @@
};
CLUSTER_CL5: cluster-sleep-1 {
- compatible = "arm,idle-state";
+ compatible = "domain-idle-state";
idle-state-name = "ret-pll-off";
arm,psci-suspend-param = <0x01000054>;
entry-latency-us = <2200>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
index 5846a11..d5e0358 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
@@ -663,7 +663,7 @@
port@1 {
reg = <1>;
- mipi1_in_panel: endpoint@1 {
+ mipi1_in_panel: endpoint {
remote-endpoint = <&mipi1_out_panel>;
};
};
@@ -689,7 +689,6 @@
ep-gpios = <&gpio0 3 GPIO_ACTIVE_HIGH>;
/* PERST# asserted in S3 */
- pcie-reset-suspend = <1>;
vpcie3v3-supply = <&wlan_3v3>;
vpcie1v8-supply = <&pp1800_pcie>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
index dfb2a0b..9586bb1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
@@ -611,7 +611,7 @@
#size-cells = <0>;
interface@0 { /* interface 0 of configuration 1 */
- compatible = "usbbda,8156.config1.0";
+ compatible = "usbifbda,8156.config1.0";
reg = <0 1>;
};
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
index 054c6a4..294eb2d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
@@ -779,7 +779,6 @@
};
&pcie0 {
- bus-scan-delay-ms = <1000>;
ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>;
num-lanes = <4>;
pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
index 2c3984a..f6f1594 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts
@@ -194,6 +194,8 @@
num-lanes = <4>;
pinctrl-names = "default";
pinctrl-0 = <&pcie_clkreqn_cpm>;
+ vpcie3v3-supply = <&vcc3v3_baseboard>;
+ vpcie12v-supply = <&dc_12v>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
index c08e693..ccbe3a7 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
@@ -79,6 +79,26 @@
regulator-max-microvolt = <5000000>;
};
+ vcca_0v9: vcca-0v9-regulator {
+ compatible = "regulator-fixed";
+ regulator-name = "vcca_0v9";
+ regulator-always-on;
+ regulator-boot-on;
+ regulator-min-microvolt = <900000>;
+ regulator-max-microvolt = <900000>;
+ vin-supply = <&vcc_1v8>;
+ };
+
+ vcca_1v8: vcca-1v8-regulator {
+ compatible = "regulator-fixed";
+ regulator-name = "vcca_1v8";
+ regulator-always-on;
+ regulator-boot-on;
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ vin-supply = <&vcc3v3_sys>;
+ };
+
vdd_log: vdd-log {
compatible = "pwm-regulator";
pwms = <&pwm2 0 25000 1>;
@@ -416,16 +436,28 @@
gpio1830-supply = <&vcc_1v8>;
};
-&pmu_io_domains {
- status = "okay";
- pmu1830-supply = <&vcc_1v8>;
+&pcie0 {
+ /* PCIe PHY supplies */
+ vpcie0v9-supply = <&vcca_0v9>;
+ vpcie1v8-supply = <&vcca_1v8>;
};
-&pwm2 {
- status = "okay";
+&pcie_clkreqn_cpm {
+ rockchip,pins =
+ <2 RK_PD2 RK_FUNC_GPIO &pcfg_pull_up>;
};
&pinctrl {
+ pinctrl-names = "default";
+ pinctrl-0 = <&q7_thermal_pin>;
+
+ gpios {
+ q7_thermal_pin: q7-thermal-pin {
+ rockchip,pins =
+ <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>;
+ };
+ };
+
i2c8 {
i2c8_xfer_a: i2c8-xfer {
rockchip,pins =
@@ -458,11 +490,20 @@
usb3 {
usb3_id: usb3-id {
rockchip,pins =
- <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>;
+ <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_up>;
};
};
};
+&pmu_io_domains {
+ status = "okay";
+ pmu1830-supply = <&vcc_1v8>;
+};
+
+&pwm2 {
+ status = "okay";
+};
+
&sdhci {
/*
* Signal integrity isn't great at 200MHz but 100MHz has proven stable
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
index 6ecdf5d..c1194d1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
@@ -447,7 +447,6 @@
&pcie2x1 {
reset-gpios = <&gpio0 RK_PB6 GPIO_ACTIVE_HIGH>;
- disable-gpios = <&gpio0 RK_PA6 GPIO_ACTIVE_HIGH>;
vpcie3v3-supply = <&vcc3v3_pcie>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
index 7b5f390..c87fad2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts
@@ -416,6 +416,8 @@
vccio_sd: LDO_REG5 {
regulator-name = "vccio_sd";
+ regulator-always-on;
+ regulator-boot-on;
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <3300000>;
@@ -525,9 +527,9 @@
#address-cells = <1>;
#size-cells = <0>;
- switch@0 {
+ switch@1f {
compatible = "mediatek,mt7531";
- reg = <0>;
+ reg = <0x1f>;
ports {
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts b/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts
index a8a4cc1..a3112d5 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts
@@ -523,7 +523,6 @@
&pcie2x1 {
reset-gpios = <&gpio3 RK_PC1 GPIO_ACTIVE_HIGH>;
- disable-gpios = <&gpio3 RK_PC2 GPIO_ACTIVE_HIGH>;
vpcie3v3-supply = <&vcc3v3_mini_pcie>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
index cce1c8e..94ecb9b 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi
@@ -216,9 +216,9 @@
pinctrl-0 = <&i2c7m0_xfer>;
status = "okay";
- es8316: audio-codec@11 {
+ es8316: audio-codec@10 {
compatible = "everest,es8316";
- reg = <0x11>;
+ reg = <0x10>;
assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
assigned-clock-rates = <12288000>;
clocks = <&cru I2S0_8CH_MCLKOUT>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
index 1b606ea..1a60442 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
@@ -485,6 +485,7 @@
pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
<&rk806_dvs2_null>, <&rk806_dvs3_null>;
spi-max-frequency = <1000000>;
+ system-power-controller;
vcc1-supply = <&vcc5v0_sys>;
vcc2-supply = <&vcc5v0_sys>;
@@ -506,7 +507,7 @@
#gpio-cells = <2>;
rk806_dvs1_null: dvs1-null-pins {
- pins = "gpio_pwrctrl2";
+ pins = "gpio_pwrctrl1";
function = "pin_fun0";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
index 67414d7..22bbfbe 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
@@ -456,6 +456,7 @@
<&rk806_dvs2_null>, <&rk806_dvs3_null>;
pinctrl-names = "default";
spi-max-frequency = <1000000>;
+ system-power-controller;
vcc1-supply = <&vcc4v0_sys>;
vcc2-supply = <&vcc4v0_sys>;
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 06234c3..cb68adc 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -289,6 +289,11 @@
adr_l x1, __hyp_text_end
adr_l x2, dcache_clean_poc
blr x2
+
+ mov_q x0, INIT_SCTLR_EL2_MMU_OFF
+ pre_disable_mmu_workaround
+ msr sctlr_el2, x0
+ isb
0:
mov_q x0, HCR_HOST_NVHE_FLAGS
@@ -323,13 +328,11 @@
cbz x0, 2f
/* Set a sane SCTLR_EL1, the VHE way */
- pre_disable_mmu_workaround
msr_s SYS_SCTLR_EL12, x1
mov x2, #BOOT_CPU_FLAG_E2H
b 3f
2:
- pre_disable_mmu_workaround
msr sctlr_el1, x1
mov x2, xzr
3:
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index f48b8da..1d26bb5 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -338,12 +338,12 @@
int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
struct vgic_reg_attr *reg_attr)
{
- int cpuid;
+ int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr);
- cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr);
-
- reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid);
reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+ reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid);
+ if (!reg_attr->vcpu)
+ return -EINVAL;
return 0;
}
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 0f0e10b..b872b00 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -276,7 +276,10 @@
pte_t *ptep = NULL;
pgdp = pgd_offset(mm, addr);
- p4dp = p4d_offset(pgdp, addr);
+ p4dp = p4d_alloc(mm, pgdp, addr);
+ if (!p4dp)
+ return NULL;
+
pudp = pud_alloc(mm, p4dp, addr);
if (!pudp)
return NULL;
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 0c4e3ec..0e270a1 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -219,9 +219,6 @@
pte_t *ptep;
unsigned long addr = (unsigned long)page_address(page);
- if (!can_set_direct_map())
- return true;
-
pgdp = pgd_offset_k(addr);
if (pgd_none(READ_ONCE(*pgdp)))
return false;
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 122021f..13eac43 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1844,15 +1844,15 @@
emit_call(enter_prog, ctx);
+ /* save return value to callee saved register x20 */
+ emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx);
+
/* if (__bpf_prog_enter(prog) == 0)
* goto skip_exec_of_prog;
*/
branch = ctx->image + ctx->idx;
emit(A64_NOP, ctx);
- /* save return value to callee saved register x20 */
- emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx);
-
emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx);
if (!p->jited)
emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx);
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index a5f300e..54ad04d 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -595,7 +595,7 @@
select RELOCATABLE
config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
- def_bool CRASH_CORE
+ def_bool CRASH_RESERVE
config RELOCATABLE
bool "Relocatable kernel"
diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
index 49a70f8..b6aeb1f 100644
--- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
@@ -100,6 +100,13 @@
#size-cells = <2>;
dma-coherent;
+ isa@18000000 {
+ compatible = "isa";
+ #size-cells = <1>;
+ #address-cells = <2>;
+ ranges = <1 0x0 0x0 0x18000000 0x4000>;
+ };
+
liointc0: interrupt-controller@1fe01400 {
compatible = "loongson,liointc-2.0";
reg = <0x0 0x1fe01400 0x0 0x40>,
diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
index dca91ca..74b99bd 100644
--- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
@@ -61,12 +61,45 @@
&gmac0 {
status = "okay";
+
+ phy-mode = "gmii";
+ phy-handle = <&phy0>;
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy0: ethernet-phy@0 {
+ reg = <2>;
+ };
+ };
};
&gmac1 {
status = "okay";
+
+ phy-mode = "gmii";
+ phy-handle = <&phy1>;
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy1: ethernet-phy@1 {
+ reg = <2>;
+ };
+ };
};
&gmac2 {
status = "okay";
+
+ phy-mode = "rgmii";
+ phy-handle = <&phy2>;
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy2: ethernet-phy@2 {
+ reg = <0>;
+ };
+ };
};
diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
index a231949..9eab2d0 100644
--- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
@@ -51,6 +51,13 @@
#address-cells = <2>;
#size-cells = <2>;
+ isa@18400000 {
+ compatible = "isa";
+ #size-cells = <1>;
+ #address-cells = <2>;
+ ranges = <1 0x0 0x0 0x18400000 0x4000>;
+ };
+
pmc: power-management@100d0000 {
compatible = "loongson,ls2k2000-pmc", "loongson,ls2k0500-pmc", "syscon";
reg = <0x0 0x100d0000 0x0 0x58>;
@@ -109,6 +116,8 @@
msi: msi-controller@1fe01140 {
compatible = "loongson,pch-msi-1.0";
reg = <0x0 0x1fe01140 0x0 0x8>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
msi-controller;
loongson,msi-base-vec = <64>;
loongson,msi-num-vecs = <192>;
@@ -140,27 +149,34 @@
#address-cells = <3>;
#size-cells = <2>;
device_type = "pci";
+ msi-parent = <&msi>;
bus-range = <0x0 0xff>;
- ranges = <0x01000000 0x0 0x00008000 0x0 0x18400000 0x0 0x00008000>,
+ ranges = <0x01000000 0x0 0x00008000 0x0 0x18408000 0x0 0x00008000>,
<0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>;
gmac0: ethernet@3,0 {
reg = <0x1800 0x0 0x0 0x0 0x0>;
- interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
+ <13 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
interrupt-parent = <&pic>;
status = "disabled";
};
gmac1: ethernet@3,1 {
reg = <0x1900 0x0 0x0 0x0 0x0>;
- interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
+ <15 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
interrupt-parent = <&pic>;
status = "disabled";
};
gmac2: ethernet@3,2 {
reg = <0x1a00 0x0 0x0 0x0 0x0>;
- interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <17 IRQ_TYPE_LEVEL_HIGH>,
+ <18 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
interrupt-parent = <&pic>;
status = "disabled";
};
diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h
index b24437e..7bd47d6 100644
--- a/arch/loongarch/include/asm/addrspace.h
+++ b/arch/loongarch/include/asm/addrspace.h
@@ -11,6 +11,7 @@
#define _ASM_ADDRSPACE_H
#include <linux/const.h>
+#include <linux/sizes.h>
#include <asm/loongarch.h>
diff --git a/arch/loongarch/include/asm/crash_core.h b/arch/loongarch/include/asm/crash_reserve.h
similarity index 75%
rename from arch/loongarch/include/asm/crash_core.h
rename to arch/loongarch/include/asm/crash_reserve.h
index 218bdbf..a1d9b84 100644
--- a/arch/loongarch/include/asm/crash_core.h
+++ b/arch/loongarch/include/asm/crash_reserve.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0-only */
-#ifndef _LOONGARCH_CRASH_CORE_H
-#define _LOONGARCH_CRASH_CORE_H
+#ifndef _LOONGARCH_CRASH_RESERVE_H
+#define _LOONGARCH_CRASH_RESERVE_H
#define CRASH_ALIGN SZ_2M
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index 4a8adcc..c2f9979 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -14,11 +14,6 @@
#include <asm/pgtable-bits.h>
#include <asm/string.h>
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page) ((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size);
extern void __init early_iounmap(void __iomem *addr, unsigned long size);
@@ -73,6 +68,21 @@
#define __io_aw() mmiowb()
+#ifdef CONFIG_KFENCE
+#define virt_to_phys(kaddr) \
+({ \
+ (likely((unsigned long)kaddr < vm_map_base)) ? __pa((unsigned long)kaddr) : \
+ page_to_phys(tlb_virt_to_page((unsigned long)kaddr)) + offset_in_page((unsigned long)kaddr);\
+})
+
+#define phys_to_virt(paddr) \
+({ \
+ extern char *__kfence_pool; \
+ (unlikely(__kfence_pool == NULL)) ? __va((unsigned long)paddr) : \
+ page_address(phys_to_page((unsigned long)paddr)) + offset_in_page((unsigned long)paddr);\
+})
+#endif
+
#include <asm-generic/io.h>
#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h
index 6c82aea..a6a5760 100644
--- a/arch/loongarch/include/asm/kfence.h
+++ b/arch/loongarch/include/asm/kfence.h
@@ -16,6 +16,7 @@
static inline bool arch_kfence_init_pool(void)
{
int err;
+ char *kaddr, *vaddr;
char *kfence_pool = __kfence_pool;
struct vm_struct *area;
@@ -35,6 +36,14 @@
return false;
}
+ kaddr = kfence_pool;
+ vaddr = __kfence_pool;
+ while (kaddr < kfence_pool + KFENCE_POOL_SIZE) {
+ set_page_address(virt_to_page(kaddr), vaddr);
+ kaddr += PAGE_SIZE;
+ vaddr += PAGE_SIZE;
+ }
+
return true;
}
diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index 4402706..e85df33 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -78,7 +78,26 @@
struct page *dmw_virt_to_page(unsigned long kaddr);
struct page *tlb_virt_to_page(unsigned long kaddr);
-#define virt_to_pfn(kaddr) PFN_DOWN(PHYSADDR(kaddr))
+#define pfn_to_phys(pfn) __pfn_to_phys(pfn)
+#define phys_to_pfn(paddr) __phys_to_pfn(paddr)
+
+#define page_to_phys(page) pfn_to_phys(page_to_pfn(page))
+#define phys_to_page(paddr) pfn_to_page(phys_to_pfn(paddr))
+
+#ifndef CONFIG_KFENCE
+
+#define page_to_virt(page) __va(page_to_phys(page))
+#define virt_to_page(kaddr) phys_to_page(__pa(kaddr))
+
+#else
+
+#define WANT_PAGE_VIRTUAL
+
+#define page_to_virt(page) \
+({ \
+ extern char *__kfence_pool; \
+ (__kfence_pool == NULL) ? __va(page_to_phys(page)) : page_address(page); \
+})
#define virt_to_page(kaddr) \
({ \
@@ -86,6 +105,11 @@
dmw_virt_to_page((unsigned long)kaddr) : tlb_virt_to_page((unsigned long)kaddr);\
})
+#endif
+
+#define pfn_to_virt(pfn) page_to_virt(pfn_to_page(pfn))
+#define virt_to_pfn(kaddr) page_to_pfn(virt_to_page(kaddr))
+
extern int __virt_addr_valid(volatile void *kaddr);
#define virt_addr_valid(kaddr) __virt_addr_valid((volatile void *)(kaddr))
diff --git a/arch/loongarch/include/asm/perf_event.h b/arch/loongarch/include/asm/perf_event.h
index 2a35a0b..52b6380 100644
--- a/arch/loongarch/include/asm/perf_event.h
+++ b/arch/loongarch/include/asm/perf_event.h
@@ -7,6 +7,14 @@
#ifndef __LOONGARCH_PERF_EVENT_H__
#define __LOONGARCH_PERF_EVENT_H__
+#include <asm/ptrace.h>
+
#define perf_arch_bpf_user_pt_regs(regs) (struct user_pt_regs *)regs
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+ (regs)->csr_era = (__ip); \
+ (regs)->regs[3] = current_stack_pointer; \
+ (regs)->regs[22] = (unsigned long) __builtin_frame_address(0); \
+}
+
#endif /* __LOONGARCH_PERF_EVENT_H__ */
diff --git a/arch/loongarch/include/asm/tlb.h b/arch/loongarch/include/asm/tlb.h
index da7a3b5..e071f5e 100644
--- a/arch/loongarch/include/asm/tlb.h
+++ b/arch/loongarch/include/asm/tlb.h
@@ -132,8 +132,6 @@
);
}
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-
static void tlb_flush(struct mmu_gather *tlb);
#define tlb_flush tlb_flush
diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c
index 0491bf4..cac7cba 100644
--- a/arch/loongarch/kernel/perf_event.c
+++ b/arch/loongarch/kernel/perf_event.c
@@ -884,4 +884,4 @@
return 0;
}
-early_initcall(init_hw_perf_events);
+pure_initcall(init_hw_perf_events);
diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c
index 1fc2f681..97b40de 100644
--- a/arch/loongarch/mm/fault.c
+++ b/arch/loongarch/mm/fault.c
@@ -202,10 +202,10 @@
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
} else {
- if (!(vma->vm_flags & VM_READ) && address != exception_era(regs))
- goto bad_area;
if (!(vma->vm_flags & VM_EXEC) && address == exception_era(regs))
goto bad_area;
+ if (!(vma->vm_flags & (VM_READ | VM_WRITE)) && address != exception_era(regs))
+ goto bad_area;
}
/*
diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c
index a9630a8..89af7c1 100644
--- a/arch/loongarch/mm/mmap.c
+++ b/arch/loongarch/mm/mmap.c
@@ -4,6 +4,7 @@
*/
#include <linux/export.h>
#include <linux/io.h>
+#include <linux/kfence.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/mman.h>
@@ -111,6 +112,9 @@
{
unsigned long vaddr = (unsigned long)kaddr;
+ if (is_kfence_address((void *)kaddr))
+ return 1;
+
if ((vaddr < PAGE_OFFSET) || (vaddr >= vm_map_base))
return 0;
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index 2aae72e..bda0181 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -11,13 +11,13 @@
struct page *dmw_virt_to_page(unsigned long kaddr)
{
- return pfn_to_page(virt_to_pfn(kaddr));
+ return phys_to_page(__pa(kaddr));
}
EXPORT_SYMBOL(dmw_virt_to_page);
struct page *tlb_virt_to_page(unsigned long kaddr)
{
- return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr)));
+ return phys_to_page(pfn_to_phys(pte_pfn(*virt_to_kpte(kaddr))));
}
EXPORT_SYMBOL(tlb_virt_to_page);
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index d14d0e3..4a2b40c 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -159,7 +159,7 @@
#define exception_ip(regs) exception_ip(regs)
#define profile_pc(regs) instruction_pointer(regs)
-extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall);
+extern asmlinkage long syscall_trace_enter(struct pt_regs *regs);
extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
extern void die(const char *, struct pt_regs *) __noreturn;
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index d1b11f6..cb1045e 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -101,6 +101,7 @@
OFFSET(TI_CPU, thread_info, cpu);
OFFSET(TI_PRE_COUNT, thread_info, preempt_count);
OFFSET(TI_REGS, thread_info, regs);
+ OFFSET(TI_SYSCALL, thread_info, syscall);
DEFINE(_THREAD_SIZE, THREAD_SIZE);
DEFINE(_THREAD_MASK, THREAD_MASK);
DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 59288c1..61503a3 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1317,16 +1317,13 @@
* Notification of system call entry/exit
* - triggered by current->work.syscall_trace
*/
-asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
+asmlinkage long syscall_trace_enter(struct pt_regs *regs)
{
user_exit();
- current_thread_info()->syscall = syscall;
-
if (test_thread_flag(TIF_SYSCALL_TRACE)) {
if (ptrace_report_syscall_entry(regs))
return -1;
- syscall = current_thread_info()->syscall;
}
#ifdef CONFIG_SECCOMP
@@ -1335,7 +1332,7 @@
struct seccomp_data sd;
unsigned long args[6];
- sd.nr = syscall;
+ sd.nr = current_thread_info()->syscall;
sd.arch = syscall_get_arch(current);
syscall_get_arguments(current, regs, args);
for (i = 0; i < 6; i++)
@@ -1345,23 +1342,23 @@
ret = __secure_computing(&sd);
if (ret == -1)
return ret;
- syscall = current_thread_info()->syscall;
}
#endif
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
trace_sys_enter(regs, regs->regs[2]);
- audit_syscall_entry(syscall, regs->regs[4], regs->regs[5],
+ audit_syscall_entry(current_thread_info()->syscall,
+ regs->regs[4], regs->regs[5],
regs->regs[6], regs->regs[7]);
/*
* Negative syscall numbers are mistaken for rejected syscalls, but
* won't have had the return value set appropriately, so we do so now.
*/
- if (syscall < 0)
+ if (current_thread_info()->syscall < 0)
syscall_set_return_value(current, regs, -ENOSYS, 0);
- return syscall;
+ return current_thread_info()->syscall;
}
/*
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 18dc9b3..2c60471 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -77,6 +77,18 @@
PTR_WD load_a7, bad_stack_a7
.previous
+ /*
+ * syscall number is in v0 unless we called syscall(__NR_###)
+ * where the real syscall number is in a0
+ */
+ subu t2, v0, __NR_O32_Linux
+ bnez t2, 1f /* __NR_syscall at offset 0 */
+ LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number
+ b 2f
+1:
+ LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number
+2:
+
lw t0, TI_FLAGS($28) # syscall tracing enabled?
li t1, _TIF_WORK_SYSCALL_ENTRY
and t0, t1
@@ -114,16 +126,7 @@
SAVE_STATIC
move a0, sp
- /*
- * syscall number is in v0 unless we called syscall(__NR_###)
- * where the real syscall number is in a0
- */
- move a1, v0
- subu t2, v0, __NR_O32_Linux
- bnez t2, 1f /* __NR_syscall at offset 0 */
- lw a1, PT_R4(sp)
-
-1: jal syscall_trace_enter
+ jal syscall_trace_enter
bltz v0, 1f # seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 97456b2c..9778885 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -44,6 +44,8 @@
sd a3, PT_R26(sp) # save a3 for syscall restarting
+ LONG_S v0, TI_SYSCALL($28) # Store syscall number
+
li t1, _TIF_WORK_SYSCALL_ENTRY
LONG_L t0, TI_FLAGS($28) # syscall tracing enabled?
and t0, t1, t0
@@ -72,7 +74,6 @@
n32_syscall_trace_entry:
SAVE_STATIC
move a0, sp
- move a1, v0
jal syscall_trace_enter
bltz v0, 1f # seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S
index e6264aa..be11ea5 100644
--- a/arch/mips/kernel/scall64-n64.S
+++ b/arch/mips/kernel/scall64-n64.S
@@ -46,6 +46,8 @@
sd a3, PT_R26(sp) # save a3 for syscall restarting
+ LONG_S v0, TI_SYSCALL($28) # Store syscall number
+
li t1, _TIF_WORK_SYSCALL_ENTRY
LONG_L t0, TI_FLAGS($28) # syscall tracing enabled?
and t0, t1, t0
@@ -82,7 +84,6 @@
syscall_trace_entry:
SAVE_STATIC
move a0, sp
- move a1, v0
jal syscall_trace_enter
bltz v0, 1f # seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index d3c2616..7a5abb7 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -79,6 +79,22 @@
PTR_WD load_a7, bad_stack_a7
.previous
+ /*
+ * absolute syscall number is in v0 unless we called syscall(__NR_###)
+ * where the real syscall number is in a0
+ * note: NR_syscall is the first O32 syscall but the macro is
+ * only defined when compiling with -mabi=32 (CONFIG_32BIT)
+ * therefore __NR_O32_Linux is used (4000)
+ */
+
+ subu t2, v0, __NR_O32_Linux
+ bnez t2, 1f /* __NR_syscall at offset 0 */
+ LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number
+ b 2f
+1:
+ LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number
+2:
+
li t1, _TIF_WORK_SYSCALL_ENTRY
LONG_L t0, TI_FLAGS($28) # syscall tracing enabled?
and t0, t1, t0
@@ -113,22 +129,7 @@
sd a7, PT_R11(sp) # For indirect syscalls
move a0, sp
- /*
- * absolute syscall number is in v0 unless we called syscall(__NR_###)
- * where the real syscall number is in a0
- * note: NR_syscall is the first O32 syscall but the macro is
- * only defined when compiling with -mabi=32 (CONFIG_32BIT)
- * therefore __NR_O32_Linux is used (4000)
- */
- .set push
- .set reorder
- subu t1, v0, __NR_O32_Linux
- move a1, v0
- bnez t1, 1f /* __NR_syscall at offset 0 */
- ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
- .set pop
-
-1: jal syscall_trace_enter
+ jal syscall_trace_enter
bltz v0, 1f # seccomp failed? Skip syscall
diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c
index 74fb86b..7c72875 100644
--- a/arch/powerpc/crypto/chacha-p10-glue.c
+++ b/arch/powerpc/crypto/chacha-p10-glue.c
@@ -197,6 +197,9 @@
static int __init chacha_p10_init(void)
{
+ if (!cpu_has_feature(CPU_FTR_ARCH_31))
+ return 0;
+
static_branch_enable(&have_p10);
return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
@@ -204,10 +207,13 @@
static void __exit chacha_p10_exit(void)
{
+ if (!static_branch_likely(&have_p10))
+ return;
+
crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
}
-module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init);
+module_init(chacha_p10_init);
module_exit(chacha_p10_exit);
MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)");
diff --git a/arch/powerpc/include/asm/plpks.h b/arch/powerpc/include/asm/plpks.h
index 23b7702..7a84069 100644
--- a/arch/powerpc/include/asm/plpks.h
+++ b/arch/powerpc/include/asm/plpks.h
@@ -44,9 +44,8 @@
#define PLPKS_MAX_DATA_SIZE 4000
// Timeouts for PLPKS operations
-#define PLPKS_MAX_TIMEOUT 5000 // msec
-#define PLPKS_FLUSH_SLEEP 10 // msec
-#define PLPKS_FLUSH_SLEEP_RANGE 400
+#define PLPKS_MAX_TIMEOUT (5 * USEC_PER_SEC)
+#define PLPKS_FLUSH_SLEEP 10000 // usec
struct plpks_var {
char *component;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 1185efe..29a8c8e 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1285,15 +1285,14 @@
struct device *dev)
{
struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
- struct iommu_group *grp = iommu_group_get(dev);
struct iommu_table_group *table_group;
+ struct iommu_group *grp;
/* At first attach the ownership is already set */
- if (!domain) {
- iommu_group_put(grp);
+ if (!domain)
return 0;
- }
+ grp = iommu_group_get(dev);
table_group = iommu_group_get_iommudata(grp);
/*
* The domain being set to PLATFORM from earlier
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index e8c4129..b1e6d27 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -786,8 +786,16 @@
* parent bus. During reboot, there will be ibm,dma-window property to
* define DMA window. For kdump, there will at least be default window or DDW
* or both.
+ * There is an exception to the above. In case the PE goes into frozen
+ * state, firmware may not provide ibm,dma-window property at the time
+ * of LPAR boot up.
*/
+ if (!pdn) {
+ pr_debug(" no ibm,dma-window property !\n");
+ return;
+ }
+
ppci = PCI_DN(pdn);
pr_debug(" parent is %pOF, iommu_table: 0x%p\n",
diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c
index febe18f..4a59549 100644
--- a/arch/powerpc/platforms/pseries/plpks.c
+++ b/arch/powerpc/platforms/pseries/plpks.c
@@ -415,8 +415,7 @@
break;
}
- usleep_range(PLPKS_FLUSH_SLEEP,
- PLPKS_FLUSH_SLEEP + PLPKS_FLUSH_SLEEP_RANGE);
+ fsleep(PLPKS_FLUSH_SLEEP);
timeout = timeout + PLPKS_FLUSH_SLEEP;
} while (timeout < PLPKS_MAX_TIMEOUT);
@@ -464,9 +463,10 @@
continuetoken = retbuf[0];
if (pseries_status_to_err(rc) == -EBUSY) {
- int delay_ms = get_longbusy_msecs(rc);
- mdelay(delay_ms);
- timeout += delay_ms;
+ int delay_us = get_longbusy_msecs(rc) * 1000;
+
+ fsleep(delay_us);
+ timeout += delay_us;
}
rc = pseries_status_to_err(rc);
} while (rc == -EBUSY && timeout < PLPKS_MAX_TIMEOUT);
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 910ba88..2acc7d8 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -82,14 +82,14 @@
Otherwise, please say "N" here to avoid unnecessary overhead.
-config ERRATA_THEAD_PBMT
- bool "Apply T-Head memory type errata"
+config ERRATA_THEAD_MAE
+ bool "Apply T-Head's memory attribute extension (XTheadMae) errata"
depends on ERRATA_THEAD && 64BIT && MMU
select RISCV_ALTERNATIVE_EARLY
default y
help
- This will apply the memory type errata to handle the non-standard
- memory type bits in page-table-entries on T-Head SoCs.
+ This will apply the memory attribute extension errata to handle the
+ non-standard PTE utilization on T-Head SoCs (XTheadMae).
If you don't know what to do here, say "Y".
diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
index b1c410b..bf6a0a6 100644
--- a/arch/riscv/errata/thead/errata.c
+++ b/arch/riscv/errata/thead/errata.c
@@ -19,20 +19,26 @@
#include <asm/patch.h>
#include <asm/vendorid_list.h>
-static bool errata_probe_pbmt(unsigned int stage,
- unsigned long arch_id, unsigned long impid)
+#define CSR_TH_SXSTATUS 0x5c0
+#define SXSTATUS_MAEE _AC(0x200000, UL)
+
+static bool errata_probe_mae(unsigned int stage,
+ unsigned long arch_id, unsigned long impid)
{
- if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PBMT))
+ if (!IS_ENABLED(CONFIG_ERRATA_THEAD_MAE))
return false;
if (arch_id != 0 || impid != 0)
return false;
- if (stage == RISCV_ALTERNATIVES_EARLY_BOOT ||
- stage == RISCV_ALTERNATIVES_MODULE)
- return true;
+ if (stage != RISCV_ALTERNATIVES_EARLY_BOOT &&
+ stage != RISCV_ALTERNATIVES_MODULE)
+ return false;
- return false;
+ if (!(csr_read(CSR_TH_SXSTATUS) & SXSTATUS_MAEE))
+ return false;
+
+ return true;
}
/*
@@ -140,8 +146,8 @@
{
u32 cpu_req_errata = 0;
- if (errata_probe_pbmt(stage, archid, impid))
- cpu_req_errata |= BIT(ERRATA_THEAD_PBMT);
+ if (errata_probe_mae(stage, archid, impid))
+ cpu_req_errata |= BIT(ERRATA_THEAD_MAE);
errata_probe_cmo(stage, archid, impid);
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index 1f2dbfb..efd851e 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -23,7 +23,7 @@
#endif
#ifdef CONFIG_ERRATA_THEAD
-#define ERRATA_THEAD_PBMT 0
+#define ERRATA_THEAD_MAE 0
#define ERRATA_THEAD_PMU 1
#define ERRATA_THEAD_NUMBER 2
#endif
@@ -53,20 +53,20 @@
* in the default case.
*/
#define ALT_SVPBMT_SHIFT 61
-#define ALT_THEAD_PBMT_SHIFT 59
+#define ALT_THEAD_MAE_SHIFT 59
#define ALT_SVPBMT(_val, prot) \
asm(ALTERNATIVE_2("li %0, 0\t\nnop", \
"li %0, %1\t\nslli %0,%0,%3", 0, \
RISCV_ISA_EXT_SVPBMT, CONFIG_RISCV_ISA_SVPBMT, \
"li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID, \
- ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \
+ ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \
: "=r"(_val) \
: "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT), \
- "I"(prot##_THEAD >> ALT_THEAD_PBMT_SHIFT), \
+ "I"(prot##_THEAD >> ALT_THEAD_MAE_SHIFT), \
"I"(ALT_SVPBMT_SHIFT), \
- "I"(ALT_THEAD_PBMT_SHIFT))
+ "I"(ALT_THEAD_MAE_SHIFT))
-#ifdef CONFIG_ERRATA_THEAD_PBMT
+#ifdef CONFIG_ERRATA_THEAD_MAE
/*
* IO/NOCACHE memory types are handled together with svpbmt,
* so on T-Head chips, check if no other memory type is set,
@@ -83,11 +83,11 @@
"slli t3, t3, %3\n\t" \
"or %0, %0, t3\n\t" \
"2:", THEAD_VENDOR_ID, \
- ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \
+ ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \
: "+r"(_val) \
- : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT), \
- "I"(_PAGE_PMA_THEAD >> ALT_THEAD_PBMT_SHIFT), \
- "I"(ALT_THEAD_PBMT_SHIFT) \
+ : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_MAE_SHIFT), \
+ "I"(_PAGE_PMA_THEAD >> ALT_THEAD_MAE_SHIFT), \
+ "I"(ALT_THEAD_MAE_SHIFT) \
: "t3")
#else
#define ALT_THEAD_PMA(_val)
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 2947423..115ac98 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -89,7 +89,7 @@
#define PTE_FMT "%08lx"
#endif
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_64BIT) && defined(CONFIG_MMU)
/*
* We override this value as its generic definition uses __pa too early in
* the boot process (before kernel_map.va_pa_offset is set).
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 9f8ea0e..6afd6bb 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -896,7 +896,7 @@
#define PAGE_SHARED __pgprot(0)
#define PAGE_KERNEL __pgprot(0)
#define swapper_pg_dir NULL
-#define TASK_SIZE 0xffffffffUL
+#define TASK_SIZE _AC(-1, UL)
#define VMALLOC_START _AC(0, UL)
#define VMALLOC_END TASK_SIZE
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index 9f2a8e3..2902f68 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -54,7 +54,7 @@
#define RISCV_HWPROBE_EXT_ZFHMIN (1 << 28)
#define RISCV_HWPROBE_EXT_ZIHINTNTL (1 << 29)
#define RISCV_HWPROBE_EXT_ZVFH (1 << 30)
-#define RISCV_HWPROBE_EXT_ZVFHMIN (1 << 31)
+#define RISCV_HWPROBE_EXT_ZVFHMIN (1ULL << 31)
#define RISCV_HWPROBE_EXT_ZFA (1ULL << 32)
#define RISCV_HWPROBE_EXT_ZTSO (1ULL << 33)
#define RISCV_HWPROBE_EXT_ZACAS (1ULL << 34)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index fe8e159..9687618 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -231,7 +231,7 @@
* In 64-bit, any use of __va/__pa before this point is wrong as we
* did not know the start of DRAM before.
*/
- if (IS_ENABLED(CONFIG_64BIT))
+ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU))
kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;
/*
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 1adf2f3..ec9d692 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -722,6 +722,9 @@
if (ret)
return ret;
+ /* store prog start time */
+ emit_mv(RV_REG_S1, RV_REG_A0, ctx);
+
/* if (__bpf_prog_enter(prog) == 0)
* goto skip_exec_of_prog;
*/
@@ -729,9 +732,6 @@
/* nop reserved for conditional jump */
emit(rv_nop(), ctx);
- /* store prog start time */
- emit_mv(RV_REG_S1, RV_REG_A0, ctx);
-
/* arg1: &args_off */
emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx);
if (!p->jited)
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index 99f7e1f..99ea3f1 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -125,8 +125,19 @@
static inline int __paes_keyblob2pkey(struct key_blob *kb,
struct pkey_protkey *pk)
{
- return pkey_keyblob2pkey(kb->key, kb->keylen,
- pk->protkey, &pk->len, &pk->type);
+ int i, ret = -EIO;
+
+ /* try three times in case of busy card */
+ for (i = 0; ret && i < 3; i++) {
+ if (ret == -EBUSY && in_task()) {
+ if (msleep_interruptible(1000))
+ return -EINTR;
+ }
+ ret = pkey_keyblob2pkey(kb->key, kb->keylen,
+ pk->protkey, &pk->len, &pk->type);
+ }
+
+ return ret;
}
static inline int __paes_convert_key(struct s390_paes_ctx *ctx)
diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h
index 4f21ae5..390906b 100644
--- a/arch/s390/include/asm/dwarf.h
+++ b/arch/s390/include/asm/dwarf.h
@@ -9,6 +9,7 @@
#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
#define CFI_RESTORE .cfi_restore
+#define CFI_REL_OFFSET .cfi_rel_offset
#ifdef CONFIG_AS_CFI_VAL_OFFSET
#define CFI_VAL_OFFSET .cfi_val_offset
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 3dc8563..6a1e0fb 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -340,7 +340,8 @@
mvc __PT_LAST_BREAK(8,%r11),__LC_PGM_LAST_BREAK
stctg %c1,%c1,__PT_CR1(%r11)
#if IS_ENABLED(CONFIG_KVM)
- lg %r12,__LC_GMAP
+ ltg %r12,__LC_GMAP
+ jz 5f
clc __GMAP_ASCE(8,%r12), __PT_CR1(%r11)
jne 5f
BPENTER __SF_SIE_FLAGS(%r10),_TIF_ISOLATE_BP_GUEST
diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
index 57f6259..85247ef 100644
--- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S
+++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
@@ -24,8 +24,10 @@
CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE)
CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD
stg %r14,STACK_FRAME_OVERHEAD(%r15)
+ CFI_REL_OFFSET 14, STACK_FRAME_OVERHEAD
brasl %r14,__s390_vdso_\func
lg %r14,STACK_FRAME_OVERHEAD(%r15)
+ CFI_RESTORE 14
aghi %r15,WRAPPER_FRAME_SIZE
CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD
CFI_RESTORE 15
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 094b43b..12d22a7 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2661,7 +2661,7 @@
return 0;
start = pmd_val(*pmd) & HPAGE_MASK;
- end = start + HPAGE_SIZE - 1;
+ end = start + HPAGE_SIZE;
__storage_key_init_range(start, end);
set_bit(PG_arch_1, &page->flags);
cond_resched();
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index c2e8242..dc3db86 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -139,7 +139,7 @@
}
if (!test_and_set_bit(PG_arch_1, &page->flags))
- __storage_key_init_range(paddr, paddr + size - 1);
+ __storage_key_init_range(paddr, paddr + size);
}
void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4fff6ed..928820e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -62,6 +62,7 @@
select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU
select ARCH_32BIT_OFF_T if X86_32
select ARCH_CLOCKSOURCE_INIT
+ select ARCH_CONFIGURES_CPU_MITIGATIONS
select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION
select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64
@@ -2488,17 +2489,21 @@
def_bool y
depends on CALL_PADDING && !CFI_CLANG
-menuconfig SPECULATION_MITIGATIONS
- bool "Mitigations for speculative execution vulnerabilities"
+menuconfig CPU_MITIGATIONS
+ bool "Mitigations for CPU vulnerabilities"
default y
help
- Say Y here to enable options which enable mitigations for
- speculative execution hardware vulnerabilities.
+ Say Y here to enable options which enable mitigations for hardware
+ vulnerabilities (usually related to speculative execution).
+ Mitigations can be disabled or restricted to SMT systems at runtime
+ via the "mitigations" kernel parameter.
- If you say N, all mitigations will be disabled. You really
- should know what you are doing to say so.
+ If you say N, all mitigations will be disabled. This CANNOT be
+ overridden at runtime.
-if SPECULATION_MITIGATIONS
+ Say 'Y', unless you really know what you are doing.
+
+if CPU_MITIGATIONS
config MITIGATION_PAGE_TABLE_ISOLATION
bool "Remove the kernel mapping in user mode"
@@ -2633,6 +2638,16 @@
stored in floating point, vector and integer registers.
See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst>
+config MITIGATION_SPECTRE_BHI
+ bool "Mitigate Spectre-BHB (Branch History Injection)"
+ depends on CPU_SUP_INTEL
+ default y
+ help
+ Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks
+ where the branch history buffer is poisoned to speculatively steer
+ indirect branches.
+ See <file:Documentation/admin-guide/hw-vuln/spectre.rst>
+
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 6356060..51cc9c7 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -49,7 +49,7 @@
if (likely(unr < NR_syscalls)) {
unr = array_index_nospec(unr, NR_syscalls);
- regs->ax = sys_call_table[unr](regs);
+ regs->ax = x64_sys_call(regs, unr);
return true;
}
return false;
@@ -66,7 +66,7 @@
if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
xnr = array_index_nospec(xnr, X32_NR_syscalls);
- regs->ax = x32_sys_call_table[xnr](regs);
+ regs->ax = x32_sys_call(regs, xnr);
return true;
}
return false;
@@ -162,7 +162,7 @@
if (likely(unr < IA32_NR_syscalls)) {
unr = array_index_nospec(unr, IA32_NR_syscalls);
- regs->ax = ia32_sys_call_table[unr](regs);
+ regs->ax = ia32_sys_call(regs, unr);
} else if (nr != -1) {
regs->ax = __ia32_sys_ni_syscall(regs);
}
@@ -189,7 +189,7 @@
}
/**
- * int80_emulation - 32-bit legacy syscall entry
+ * do_int80_emulation - 32-bit legacy syscall C entry from asm
*
* This entry point can be used by 32-bit and 64-bit programs to perform
* 32-bit system calls. Instances of INT $0x80 can be found inline in
@@ -207,7 +207,7 @@
* eax: system call number
* ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6
*/
-DEFINE_IDTENTRY_RAW(int80_emulation)
+__visible noinstr void do_int80_emulation(struct pt_regs *regs)
{
int nr;
@@ -255,6 +255,71 @@
instrumentation_end();
syscall_exit_to_user_mode(regs);
}
+
+#ifdef CONFIG_X86_FRED
+/*
+ * A FRED-specific INT80 handler is warranted for the follwing reasons:
+ *
+ * 1) As INT instructions and hardware interrupts are separate event
+ * types, FRED does not preclude the use of vector 0x80 for external
+ * interrupts. As a result, the FRED setup code does not reserve
+ * vector 0x80 and calling int80_is_external() is not merely
+ * suboptimal but actively incorrect: it could cause a system call
+ * to be incorrectly ignored.
+ *
+ * 2) It is called only for handling vector 0x80 of event type
+ * EVENT_TYPE_SWINT and will never be called to handle any external
+ * interrupt (event type EVENT_TYPE_EXTINT).
+ *
+ * 3) FRED has separate entry flows depending on if the event came from
+ * user space or kernel space, and because the kernel does not use
+ * INT insns, the FRED kernel entry handler fred_entry_from_kernel()
+ * falls through to fred_bad_type() if the event type is
+ * EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling
+ * an INT insn, it can only be from a user level.
+ *
+ * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will
+ * likely take a different approach if it is ever needed: it
+ * probably belongs in either fred_intx()/ fred_other() or
+ * asm_fred_entrypoint_user(), depending on if this ought to be done
+ * for all entries from userspace or only system
+ * calls.
+ *
+ * 5) INT $0x80 is the fast path for 32-bit system calls under FRED.
+ */
+DEFINE_FREDENTRY_RAW(int80_emulation)
+{
+ int nr;
+
+ enter_from_user_mode(regs);
+
+ instrumentation_begin();
+ add_random_kstack_offset();
+
+ /*
+ * FRED pushed 0 into regs::orig_ax and regs::ax contains the
+ * syscall number.
+ *
+ * User tracing code (ptrace or signal handlers) might assume
+ * that the regs::orig_ax contains a 32-bit number on invoking
+ * a 32-bit syscall.
+ *
+ * Establish the syscall convention by saving the 32bit truncated
+ * syscall number in regs::orig_ax and by invalidating regs::ax.
+ */
+ regs->orig_ax = regs->ax & GENMASK(31, 0);
+ regs->ax = -ENOSYS;
+
+ nr = syscall_32_enter(regs);
+
+ local_irq_enable();
+ nr = syscall_enter_from_user_mode_work(regs, nr);
+ do_syscall_32_irqs_on(regs, nr);
+
+ instrumentation_end();
+ syscall_exit_to_user_mode(regs);
+}
+#endif
#else /* CONFIG_IA32_EMULATION */
/* Handles int $0x80 on a 32bit kernel */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8af2a26..1b5be07 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -116,6 +116,7 @@
/* clobbers %rax, make sure it is after saving the syscall nr */
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
call do_syscall_64 /* returns with IRQs disabled */
@@ -1491,3 +1492,63 @@
call make_task_dead
SYM_CODE_END(rewind_stack_and_make_dead)
.popsection
+
+/*
+ * This sequence executes branches in order to remove user branch information
+ * from the branch history tracker in the Branch Predictor, therefore removing
+ * user influence on subsequent BTB lookups.
+ *
+ * It should be used on parts prior to Alder Lake. Newer parts should use the
+ * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being
+ * virtualized on newer hardware the VMM should protect against BHI attacks by
+ * setting BHI_DIS_S for the guests.
+ *
+ * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging
+ * and not clearing the branch history. The call tree looks like:
+ *
+ * call 1
+ * call 2
+ * call 2
+ * call 2
+ * call 2
+ * call 2
+ * ret
+ * ret
+ * ret
+ * ret
+ * ret
+ * ret
+ *
+ * This means that the stack is non-constant and ORC can't unwind it with %rsp
+ * alone. Therefore we unconditionally set up the frame pointer, which allows
+ * ORC to unwind properly.
+ *
+ * The alignment is for performance and not for safety, and may be safely
+ * refactored in the future if needed.
+ */
+SYM_FUNC_START(clear_bhb_loop)
+ push %rbp
+ mov %rsp, %rbp
+ movl $5, %ecx
+ ANNOTATE_INTRA_FUNCTION_CALL
+ call 1f
+ jmp 5f
+ .align 64, 0xcc
+ ANNOTATE_INTRA_FUNCTION_CALL
+1: call 2f
+ RET
+ .align 64, 0xcc
+2: movl $5, %eax
+3: jmp 4f
+ nop
+4: sub $1, %eax
+ jnz 3b
+ sub $1, %ecx
+ jnz 1b
+ RET
+5: lfence
+ pop %rbp
+ RET
+SYM_FUNC_END(clear_bhb_loop)
+EXPORT_SYMBOL_GPL(clear_bhb_loop)
+STACK_FRAME_NON_STANDARD(clear_bhb_loop)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index eabf48c..c779046 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -92,6 +92,7 @@
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
/*
* SYSENTER doesn't filter flags, so we need to clear NT and AC
@@ -206,6 +207,7 @@
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
movq %rsp, %rdi
call do_fast_syscall_32
@@ -276,3 +278,17 @@
ANNOTATE_NOENDBR
int3
SYM_CODE_END(entry_SYSCALL_compat)
+
+/*
+ * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries
+ * point to C routines, however since this is a system call interface the branch
+ * history needs to be scrubbed to protect against BHI attacks, and that
+ * scrubbing needs to take place in assembly code prior to entering any C
+ * routines.
+ */
+SYM_CODE_START(int80_emulation)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ CLEAR_BRANCH_HISTORY
+ jmp do_int80_emulation
+SYM_CODE_END(int80_emulation)
diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c
index ac120cb..89c1476 100644
--- a/arch/x86/entry/entry_fred.c
+++ b/arch/x86/entry/entry_fred.c
@@ -28,9 +28,9 @@
if (regs->fred_cs.sl > 0) {
pr_emerg("PANIC: invalid or fatal FRED event; event type %u "
"vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n",
- regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax,
+ regs->fred_ss.type, regs->fred_ss.vector, error_code,
fred_event_data(regs), regs->cs, regs->ip);
- die("invalid or fatal FRED event", regs, regs->orig_ax);
+ die("invalid or fatal FRED event", regs, error_code);
panic("invalid or fatal FRED event");
} else {
unsigned long flags = oops_begin();
@@ -38,10 +38,10 @@
pr_alert("BUG: invalid or fatal FRED event; event type %u "
"vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n",
- regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax,
+ regs->fred_ss.type, regs->fred_ss.vector, error_code,
fred_event_data(regs), regs->cs, regs->ip);
- if (__die("Invalid or fatal FRED event", regs, regs->orig_ax))
+ if (__die("Invalid or fatal FRED event", regs, error_code))
sig = 0;
oops_end(flags, regs, sig);
@@ -66,7 +66,7 @@
/* INT80 */
case IA32_SYSCALL_VECTOR:
if (ia32_enabled())
- return int80_emulation(regs);
+ return fred_int80_emulation(regs);
fallthrough;
#endif
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 8cfc9bc..c2235ba 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -18,8 +18,25 @@
#include <asm/syscalls_32.h>
#undef __SYSCALL
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
+#ifdef CONFIG_X86_32
#define __SYSCALL(nr, sym) __ia32_##sym,
-
-__visible const sys_call_ptr_t ia32_sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_32.h>
};
+#undef __SYSCALL
+#endif
+
+#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
+
+long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_32.h>
+ default: return __ia32_sys_ni_syscall(regs);
+ }
+};
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index be120ee..33b3f09 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -11,8 +11,23 @@
#include <asm/syscalls_64.h>
#undef __SYSCALL
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
#define __SYSCALL(nr, sym) __x64_##sym,
-
-asmlinkage const sys_call_ptr_t sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_64.h>
};
+#undef __SYSCALL
+
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+
+long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_64.h>
+ default: return __x64_sys_ni_syscall(regs);
+ }
+};
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index bdd0e03..03de4a9 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -11,8 +11,12 @@
#include <asm/syscalls_x32.h>
#undef __SYSCALL
-#define __SYSCALL(nr, sym) __x64_##sym,
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-asmlinkage const sys_call_ptr_t x32_sys_call_table[] = {
-#include <asm/syscalls_x32.h>
+long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_x32.h>
+ default: return __x64_sys_ni_syscall(regs);
+ }
};
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index a3c0df1..2fb7d53c 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -98,11 +98,6 @@
static bool write_ok_or_segv(unsigned long ptr, size_t size)
{
- /*
- * XXX: if access_ok, get_user, and put_user handled
- * sig_on_uaccess_err, this could go away.
- */
-
if (!access_ok((void __user *)ptr, size)) {
struct thread_struct *thread = ¤t->thread;
@@ -120,10 +115,8 @@
bool emulate_vsyscall(unsigned long error_code,
struct pt_regs *regs, unsigned long address)
{
- struct task_struct *tsk;
unsigned long caller;
int vsyscall_nr, syscall_nr, tmp;
- int prev_sig_on_uaccess_err;
long ret;
unsigned long orig_dx;
@@ -172,8 +165,6 @@
goto sigsegv;
}
- tsk = current;
-
/*
* Check for access_ok violations and find the syscall nr.
*
@@ -234,12 +225,8 @@
goto do_ret; /* skip requested */
/*
- * With a real vsyscall, page faults cause SIGSEGV. We want to
- * preserve that behavior to make writing exploits harder.
+ * With a real vsyscall, page faults cause SIGSEGV.
*/
- prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err;
- current->thread.sig_on_uaccess_err = 1;
-
ret = -EFAULT;
switch (vsyscall_nr) {
case 0:
@@ -262,23 +249,12 @@
break;
}
- current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err;
-
check_fault:
if (ret == -EFAULT) {
/* Bad news -- userspace fed a bad pointer to a vsyscall. */
warn_bad_vsyscall(KERN_INFO, regs,
"vsyscall fault (exploit attempt?)");
-
- /*
- * If we failed to generate a signal for any reason,
- * generate one here. (This should be impossible.)
- */
- if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
- !sigismember(&tsk->pending.signal, SIGSEGV)))
- goto sigsegv;
-
- return true; /* Don't emulate the ret. */
+ goto sigsegv;
}
regs->ax = ret;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 0905064..5b0dd07 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1644,6 +1644,7 @@
while (++i < cpuc->n_events) {
cpuc->event_list[i-1] = cpuc->event_list[i];
cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
+ cpuc->assign[i-1] = cpuc->assign[i];
}
cpuc->event_constraint[i-1] = NULL;
--cpuc->n_events;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 78cd508..4367aa7 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1693,6 +1693,7 @@
lbr->from = x86_pmu.lbr_from;
lbr->to = x86_pmu.lbr_to;
lbr->info = x86_pmu.lbr_info;
+ lbr->has_callstack = x86_pmu_has_lbr_callstack();
}
EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 5fc4554..0569f57 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -105,7 +105,7 @@
* IPI implementation on Hyper-V.
*/
static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
- bool exclude_self)
+ bool exclude_self)
{
struct hv_send_ipi_ex *ipi_arg;
unsigned long flags;
@@ -132,8 +132,8 @@
if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) {
ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
- nr_bank = cpumask_to_vpset_skip(&(ipi_arg->vp_set), mask,
- exclude_self ? cpu_is_self : NULL);
+ nr_bank = cpumask_to_vpset_skip(&ipi_arg->vp_set, mask,
+ exclude_self ? cpu_is_self : NULL);
/*
* 'nr_bank <= 0' means some CPUs in cpumask can't be
@@ -147,7 +147,7 @@
}
status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
- ipi_arg, NULL);
+ ipi_arg, NULL);
ipi_mask_ex_done:
local_irq_restore(flags);
@@ -155,7 +155,7 @@
}
static bool __send_ipi_mask(const struct cpumask *mask, int vector,
- bool exclude_self)
+ bool exclude_self)
{
int cur_cpu, vcpu, this_cpu = smp_processor_id();
struct hv_send_ipi ipi_arg;
@@ -181,7 +181,7 @@
return false;
}
- if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+ if (vector < HV_IPI_LOW_VECTOR || vector > HV_IPI_HIGH_VECTOR)
return false;
/*
@@ -218,7 +218,7 @@
}
status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
- ipi_arg.cpu_mask);
+ ipi_arg.cpu_mask);
return hv_result_success(status);
do_ex_hypercall:
@@ -241,7 +241,7 @@
return false;
}
- if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
+ if (vector < HV_IPI_LOW_VECTOR || vector > HV_IPI_HIGH_VECTOR)
return false;
if (vp >= 64)
diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c
index 68a0843..3fa1f2e 100644
--- a/arch/x86/hyperv/hv_proc.c
+++ b/arch/x86/hyperv/hv_proc.c
@@ -3,7 +3,6 @@
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/clockchips.h>
-#include <linux/acpi.h>
#include <linux/hyperv.h>
#include <linux/slab.h>
#include <linux/cpuhotplug.h>
@@ -116,12 +115,11 @@
int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
{
- struct hv_add_logical_processor_in *input;
- struct hv_add_logical_processor_out *output;
+ struct hv_input_add_logical_processor *input;
+ struct hv_output_add_logical_processor *output;
u64 status;
unsigned long flags;
int ret = HV_STATUS_SUCCESS;
- int pxm = node_to_pxm(node);
/*
* When adding a logical processor, the hypervisor may return
@@ -137,11 +135,7 @@
input->lp_index = lp_index;
input->apic_id = apic_id;
- input->flags = 0;
- input->proximity_domain_info.domain_id = pxm;
- input->proximity_domain_info.flags.reserved = 0;
- input->proximity_domain_info.flags.proximity_info_valid = 1;
- input->proximity_domain_info.flags.proximity_preferred = 1;
+ input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR,
input, output);
local_irq_restore(flags);
@@ -166,7 +160,6 @@
u64 status;
unsigned long irq_flags;
int ret = HV_STATUS_SUCCESS;
- int pxm = node_to_pxm(node);
/* Root VPs don't seem to need pages deposited */
if (partition_id != hv_current_partition_id) {
@@ -185,14 +178,7 @@
input->vp_index = vp_index;
input->flags = flags;
input->subnode_type = HvSubnodeAny;
- if (node != NUMA_NO_NODE) {
- input->proximity_domain_info.domain_id = pxm;
- input->proximity_domain_info.flags.reserved = 0;
- input->proximity_domain_info.flags.proximity_info_valid = 1;
- input->proximity_domain_info.flags.proximity_preferred = 1;
- } else {
- input->proximity_domain_info.as_uint64 = 0;
- }
+ input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL);
local_irq_restore(irq_flags);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 94ce0f7..e6ab0cf 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -13,6 +13,7 @@
#include <asm/mpspec.h>
#include <asm/msr.h>
#include <asm/hardirq.h>
+#include <asm/io.h>
#define ARCH_APICTIMER_STOPS_ON_C3 1
@@ -98,7 +99,7 @@
static inline u32 native_apic_mem_read(u32 reg)
{
- return *((volatile u32 *)(APIC_BASE + reg));
+ return readl((void __iomem *)(APIC_BASE + reg));
}
static inline void native_apic_mem_eoi(void)
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index fe1e7e3..63bdc6b8 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -79,6 +79,9 @@
#define __smp_mb__before_atomic() do { } while (0)
#define __smp_mb__after_atomic() do { } while (0)
+/* Writing to CR3 provides a full memory barrier in switch_mm(). */
+#define smp_mb__after_switch_mm() do { } while (0)
+
#include <asm-generic/barrier.h>
#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index c086699..aa6c8f8c 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -25,6 +25,7 @@
void cc_random_init(void);
#else
#define cc_vendor (CC_VENDOR_NONE)
+static const u64 cc_mask = 0;
static inline u64 cc_mkenc(u64 val)
{
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index a38f8f9..3c74343 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -461,11 +461,15 @@
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
- * CPUID levels like 0x80000022, etc.
+ * CPUID levels like 0x80000022, etc and Linux defined features.
*
* Reuse free bits when adding new feature flags!
*/
#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
+#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
+#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */
+#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
/*
* BUG word(s)
@@ -515,4 +519,5 @@
#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */
#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h
index e8f58dd..2e74a7f 100644
--- a/arch/x86/include/asm/e820/api.h
+++ b/arch/x86/include/asm/e820/api.h
@@ -17,6 +17,7 @@
extern void e820__range_add (u64 start, u64 size, enum e820_type type);
extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type);
+extern u64 e820__range_update_table(struct e820_table *t, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
extern void e820__print_table(char *who);
extern int e820__update_table(struct e820_table *table);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 16e07a2..6efd149 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -855,6 +855,7 @@
int cpuid_nent;
struct kvm_cpuid_entry2 *cpuid_entries;
struct kvm_hypervisor_cpuid kvm_cpuid;
+ bool is_amd_compatible;
/*
* FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 05956bd..e72c2b8 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -61,10 +61,13 @@
#define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */
#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */
#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
+#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */
+#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT)
/* A mask for bits which the kernel toggles when controlling mitigations */
#define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
- | SPEC_CTRL_RRSBA_DIS_S)
+ | SPEC_CTRL_RRSBA_DIS_S \
+ | SPEC_CTRL_BHI_DIS_S)
#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */
@@ -163,6 +166,10 @@
* are restricted to targets in
* kernel.
*/
+#define ARCH_CAP_BHI_NO BIT(20) /*
+ * CPU is not affected by Branch
+ * History Injection.
+ */
#define ARCH_CAP_PBRSB_NO BIT(24) /*
* Not susceptible to Post-Barrier
* Return Stack Buffer Predictions.
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 170c89e..ff5f1ec 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -326,6 +326,19 @@
ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
.endm
+#ifdef CONFIG_X86_64
+.macro CLEAR_BRANCH_HISTORY
+ ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
+.endm
+
+.macro CLEAR_BRANCH_HISTORY_VMEXIT
+ ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT
+.endm
+#else
+#define CLEAR_BRANCH_HISTORY
+#define CLEAR_BRANCH_HISTORY_VMEXIT
+#endif
+
#else /* __ASSEMBLY__ */
#define ANNOTATE_RETPOLINE_SAFE \
@@ -368,6 +381,10 @@
extern void entry_untrain_ret(void);
extern void entry_ibpb(void);
+#ifdef CONFIG_X86_64
+extern void clear_bhb_loop(void);
+#endif
+
extern void (*x86_return_thunk)(void);
extern void __warn_thunk(void);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 3736b8a..7f1e172 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -555,6 +555,7 @@
unsigned int from;
unsigned int to;
unsigned int info;
+ bool has_callstack;
};
extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 0b748ee..9abb8cc 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -148,7 +148,7 @@
#define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | \
_PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \
- _PAGE_DEVMAP | _PAGE_ENC | _PAGE_UFFD_WP)
+ _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP)
#define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT)
#define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE)
@@ -173,6 +173,7 @@
};
#endif
+#define _PAGE_CC (_AT(pteval_t, cc_mask))
#define _PAGE_ENC (_AT(pteval_t, sme_me_mask))
#define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 811548f..78e51b0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -472,7 +472,6 @@
unsigned long iopl_emul;
unsigned int iopl_warn:1;
- unsigned int sig_on_uaccess_err:1;
/*
* Protection Keys Register for Userspace. Loaded immediately on
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 7f57382..93ed600 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -269,6 +269,7 @@
int rmp_make_shared(u64 pfn, enum pg_level level);
void snp_leak_pages(u64 pfn, unsigned int npages);
void kdump_sev_callback(void);
+void snp_fixup_e820_tables(void);
#else
static inline bool snp_probe_rmptable_info(void) { return false; }
static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
@@ -282,6 +283,7 @@
static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
static inline void kdump_sev_callback(void) { }
+static inline void snp_fixup_e820_tables(void) {}
#endif
#endif
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index f44e2f9..2fc7bc3 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,19 +16,17 @@
#include <asm/thread_info.h> /* for TS_COMPAT */
#include <asm/unistd.h>
+/* This is used purely for kernel/trace/trace_syscalls.c */
typedef long (*sys_call_ptr_t)(const struct pt_regs *);
extern const sys_call_ptr_t sys_call_table[];
-#if defined(CONFIG_X86_32)
-#define ia32_sys_call_table sys_call_table
-#else
/*
* These may not exist, but still put the prototypes in so we
* can use IS_ENABLED().
*/
-extern const sys_call_ptr_t ia32_sys_call_table[];
-extern const sys_call_ptr_t x32_sys_call_table[];
-#endif
+extern long ia32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x64_sys_call(const struct pt_regs *, unsigned int nr);
/*
* Only the low 32 bits of orig_ax are meaningful, so we return int.
@@ -127,6 +125,7 @@
}
bool do_syscall_64(struct pt_regs *regs, int nr);
+void do_int80_emulation(struct pt_regs *regs);
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index a42d8a6..803dcfb 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1687,11 +1687,11 @@
static bool x2apic_hw_locked(void)
{
- u64 ia32_cap;
+ u64 x86_arch_cap_msr;
u64 msr;
- ia32_cap = x86_read_arch_cap_msr();
- if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) {
+ x86_arch_cap_msr = x86_read_arch_cap_msr();
+ if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) {
rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr);
return (msr & LEGACY_XAPIC_DISABLED);
}
@@ -1771,7 +1771,7 @@
__x2apic_enable();
}
-static __init void apic_set_fixmap(void);
+static __init void apic_set_fixmap(bool read_apic);
static __init void x2apic_disable(void)
{
@@ -1793,7 +1793,12 @@
}
__x2apic_disable();
- apic_set_fixmap();
+ /*
+ * Don't reread the APIC ID as it was already done from
+ * check_x2apic() and the APIC driver still is a x2APIC variant,
+ * which fails to do the read after x2APIC was disabled.
+ */
+ apic_set_fixmap(false);
}
static __init void x2apic_enable(void)
@@ -2057,13 +2062,14 @@
}
}
-static __init void apic_set_fixmap(void)
+static __init void apic_set_fixmap(bool read_apic)
{
set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr);
apic_mmio_base = APIC_BASE;
apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
apic_mmio_base, mp_lapic_addr);
- apic_read_boot_cpu_id(false);
+ if (read_apic)
+ apic_read_boot_cpu_id(false);
}
void __init register_lapic_address(unsigned long address)
@@ -2073,7 +2079,7 @@
mp_lapic_addr = address;
if (!x2apic_mode)
- apic_set_fixmap();
+ apic_set_fixmap(true);
}
/*
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9bf17c9..307302a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -459,8 +459,7 @@
case 0x1a:
switch (c->x86_model) {
- case 0x00 ... 0x0f:
- case 0x20 ... 0x2f:
+ case 0x00 ... 0x2f:
case 0x40 ... 0x4f:
case 0x70 ... 0x7f:
setup_force_cpu_cap(X86_FEATURE_ZEN5);
@@ -535,7 +534,6 @@
static void early_init_amd(struct cpuinfo_x86 *c)
{
- u64 value;
u32 dummy;
if (c->x86 >= 0xf)
@@ -603,20 +601,6 @@
early_detect_mem_encrypt(c);
- /* Re-enable TopologyExtensions if switched off by BIOS */
- if (c->x86 == 0x15 &&
- (c->x86_model >= 0x10 && c->x86_model <= 0x6f) &&
- !cpu_has(c, X86_FEATURE_TOPOEXT)) {
-
- if (msr_set_bit(0xc0011005, 54) > 0) {
- rdmsrl(0xc0011005, value);
- if (value & BIT_64(54)) {
- set_cpu_cap(c, X86_FEATURE_TOPOEXT);
- pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
- }
- }
- }
-
if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) {
if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB))
setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index e7ba936..ab18185 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -61,6 +61,8 @@
u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
EXPORT_SYMBOL_GPL(x86_pred_cmd);
+static u64 __ro_after_init x86_arch_cap_msr;
+
static DEFINE_MUTEX(spec_ctrl_mutex);
void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
@@ -144,6 +146,8 @@
x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK;
}
+ x86_arch_cap_msr = x86_read_arch_cap_msr();
+
/* Select the proper CPU mitigations before patching alternatives: */
spectre_v1_select_mitigation();
spectre_v2_select_mitigation();
@@ -301,8 +305,6 @@
static void __init taa_select_mitigation(void)
{
- u64 ia32_cap;
-
if (!boot_cpu_has_bug(X86_BUG_TAA)) {
taa_mitigation = TAA_MITIGATION_OFF;
return;
@@ -341,9 +343,8 @@
* On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
* update is required.
*/
- ia32_cap = x86_read_arch_cap_msr();
- if ( (ia32_cap & ARCH_CAP_MDS_NO) &&
- !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR))
+ if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) &&
+ !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))
taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
/*
@@ -401,8 +402,6 @@
static void __init mmio_select_mitigation(void)
{
- u64 ia32_cap;
-
if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
cpu_mitigations_off()) {
@@ -413,8 +412,6 @@
if (mmio_mitigation == MMIO_MITIGATION_OFF)
return;
- ia32_cap = x86_read_arch_cap_msr();
-
/*
* Enable CPU buffer clear mitigation for host and VMM, if also affected
* by MDS or TAA. Otherwise, enable mitigation for VMM only.
@@ -437,7 +434,7 @@
* be propagated to uncore buffers, clearing the Fill buffers on idle
* is required irrespective of SMT state.
*/
- if (!(ia32_cap & ARCH_CAP_FBSDP_NO))
+ if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO))
static_branch_enable(&mds_idle_clear);
/*
@@ -447,10 +444,10 @@
* FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
* affected systems.
*/
- if ((ia32_cap & ARCH_CAP_FB_CLEAR) ||
+ if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) ||
(boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
- !(ia32_cap & ARCH_CAP_MDS_NO)))
+ !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)))
mmio_mitigation = MMIO_MITIGATION_VERW;
else
mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
@@ -508,7 +505,7 @@
if (rfds_mitigation == RFDS_MITIGATION_OFF)
return;
- if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR)
+ if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR)
setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
else
rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED;
@@ -659,8 +656,6 @@
static void __init srbds_select_mitigation(void)
{
- u64 ia32_cap;
-
if (!boot_cpu_has_bug(X86_BUG_SRBDS))
return;
@@ -669,8 +664,7 @@
* are only exposed to SRBDS when TSX is enabled or when CPU is affected
* by Processor MMIO Stale Data vulnerability.
*/
- ia32_cap = x86_read_arch_cap_msr();
- if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) &&
+ if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) &&
!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
srbds_mitigation = SRBDS_MITIGATION_TSX_OFF;
else if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
@@ -813,7 +807,7 @@
/* Will verify below that mitigation _can_ be disabled */
/* No microcode */
- if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) {
+ if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) {
if (gds_mitigation == GDS_MITIGATION_FORCE) {
/*
* This only needs to be done on the boot CPU so do it
@@ -1544,20 +1538,25 @@
return SPECTRE_V2_RETPOLINE;
}
+static bool __ro_after_init rrsba_disabled;
+
/* Disable in-kernel use of non-RSB RET predictors */
static void __init spec_ctrl_disable_kernel_rrsba(void)
{
- u64 ia32_cap;
+ if (rrsba_disabled)
+ return;
+
+ if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) {
+ rrsba_disabled = true;
+ return;
+ }
if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL))
return;
- ia32_cap = x86_read_arch_cap_msr();
-
- if (ia32_cap & ARCH_CAP_RRSBA) {
- x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S;
- update_spec_ctrl(x86_spec_ctrl_base);
- }
+ x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S;
+ update_spec_ctrl(x86_spec_ctrl_base);
+ rrsba_disabled = true;
}
static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode)
@@ -1607,6 +1606,74 @@
dump_stack();
}
+/*
+ * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by
+ * branch history in userspace. Not needed if BHI_NO is set.
+ */
+static bool __init spec_ctrl_bhi_dis(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_BHI_CTRL))
+ return false;
+
+ x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S;
+ update_spec_ctrl(x86_spec_ctrl_base);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW);
+
+ return true;
+}
+
+enum bhi_mitigations {
+ BHI_MITIGATION_OFF,
+ BHI_MITIGATION_ON,
+};
+
+static enum bhi_mitigations bhi_mitigation __ro_after_init =
+ IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF;
+
+static int __init spectre_bhi_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ bhi_mitigation = BHI_MITIGATION_OFF;
+ else if (!strcmp(str, "on"))
+ bhi_mitigation = BHI_MITIGATION_ON;
+ else
+ pr_err("Ignoring unknown spectre_bhi option (%s)", str);
+
+ return 0;
+}
+early_param("spectre_bhi", spectre_bhi_parse_cmdline);
+
+static void __init bhi_select_mitigation(void)
+{
+ if (bhi_mitigation == BHI_MITIGATION_OFF)
+ return;
+
+ /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */
+ if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+ !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) {
+ spec_ctrl_disable_kernel_rrsba();
+ if (rrsba_disabled)
+ return;
+ }
+
+ if (spec_ctrl_bhi_dis())
+ return;
+
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ /* Mitigate KVM by default */
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+ pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n");
+
+ /* Mitigate syscalls when the mitigation is forced =on */
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
+ pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n");
+}
+
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -1718,6 +1785,9 @@
mode == SPECTRE_V2_RETPOLINE)
spec_ctrl_disable_kernel_rrsba();
+ if (boot_cpu_has(X86_BUG_BHI))
+ bhi_select_mitigation();
+
spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
@@ -1832,8 +1902,6 @@
/* Update the static key controlling the MDS CPU buffer clear in idle */
static void update_mds_branch_idle(void)
{
- u64 ia32_cap = x86_read_arch_cap_msr();
-
/*
* Enable the idle clearing if SMT is active on CPUs which are
* affected only by MSBDS and not any other MDS variant.
@@ -1848,7 +1916,7 @@
if (sched_smt_active()) {
static_branch_enable(&mds_idle_clear);
} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
- (ia32_cap & ARCH_CAP_FBSDP_NO)) {
+ (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) {
static_branch_disable(&mds_idle_clear);
}
}
@@ -2695,15 +2763,15 @@
switch (spectre_v2_user_stibp) {
case SPECTRE_V2_USER_NONE:
- return ", STIBP: disabled";
+ return "; STIBP: disabled";
case SPECTRE_V2_USER_STRICT:
- return ", STIBP: forced";
+ return "; STIBP: forced";
case SPECTRE_V2_USER_STRICT_PREFERRED:
- return ", STIBP: always-on";
+ return "; STIBP: always-on";
case SPECTRE_V2_USER_PRCTL:
case SPECTRE_V2_USER_SECCOMP:
if (static_key_enabled(&switch_to_cond_stibp))
- return ", STIBP: conditional";
+ return "; STIBP: conditional";
}
return "";
}
@@ -2712,10 +2780,10 @@
{
if (boot_cpu_has(X86_FEATURE_IBPB)) {
if (static_key_enabled(&switch_mm_always_ibpb))
- return ", IBPB: always-on";
+ return "; IBPB: always-on";
if (static_key_enabled(&switch_mm_cond_ibpb))
- return ", IBPB: conditional";
- return ", IBPB: disabled";
+ return "; IBPB: conditional";
+ return "; IBPB: disabled";
}
return "";
}
@@ -2725,14 +2793,32 @@
if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) ||
boot_cpu_has(X86_FEATURE_RSB_VMEXIT))
- return ", PBRSB-eIBRS: SW sequence";
+ return "; PBRSB-eIBRS: SW sequence";
else
- return ", PBRSB-eIBRS: Vulnerable";
+ return "; PBRSB-eIBRS: Vulnerable";
} else {
- return ", PBRSB-eIBRS: Not affected";
+ return "; PBRSB-eIBRS: Not affected";
}
}
+static const char *spectre_bhi_state(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_BHI))
+ return "; BHI: Not affected";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
+ return "; BHI: BHI_DIS_S";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
+ return "; BHI: SW loop, KVM: SW loop";
+ else if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+ !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) &&
+ rrsba_disabled)
+ return "; BHI: Retpoline";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+ return "; BHI: Vulnerable, KVM: SW loop";
+
+ return "; BHI: Vulnerable";
+}
+
static ssize_t spectre_v2_show_state(char *buf)
{
if (spectre_v2_enabled == SPECTRE_V2_LFENCE)
@@ -2745,13 +2831,15 @@
spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n");
- return sysfs_emit(buf, "%s%s%s%s%s%s%s\n",
+ return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n",
spectre_v2_strings[spectre_v2_enabled],
ibpb_state(),
- boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+ boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "",
stibp_state(),
- boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
+ boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "",
pbrsb_eibrs_state(),
+ spectre_bhi_state(),
+ /* this should always be at the end */
spectre_v2_module_string());
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5c1e6d6..605c26c0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1120,6 +1120,7 @@
#define NO_SPECTRE_V2 BIT(8)
#define NO_MMIO BIT(9)
#define NO_EIBRS_PBRSB BIT(10)
+#define NO_BHI BIT(11)
#define VULNWL(vendor, family, model, whitelist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1182,18 +1183,18 @@
VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
/* AMD Family 0xf - 0x12 */
- VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
- VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
- VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI),
+ VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI),
/* Zhaoxin Family 7 */
- VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
- VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
+ VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI),
+ VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI),
{}
};
@@ -1283,25 +1284,25 @@
u64 x86_read_arch_cap_msr(void)
{
- u64 ia32_cap = 0;
+ u64 x86_arch_cap_msr = 0;
if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
- rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
+ rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr);
- return ia32_cap;
+ return x86_arch_cap_msr;
}
-static bool arch_cap_mmio_immune(u64 ia32_cap)
+static bool arch_cap_mmio_immune(u64 x86_arch_cap_msr)
{
- return (ia32_cap & ARCH_CAP_FBSDP_NO &&
- ia32_cap & ARCH_CAP_PSDP_NO &&
- ia32_cap & ARCH_CAP_SBDR_SSDP_NO);
+ return (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO &&
+ x86_arch_cap_msr & ARCH_CAP_PSDP_NO &&
+ x86_arch_cap_msr & ARCH_CAP_SBDR_SSDP_NO);
}
-static bool __init vulnerable_to_rfds(u64 ia32_cap)
+static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr)
{
/* The "immunity" bit trumps everything else: */
- if (ia32_cap & ARCH_CAP_RFDS_NO)
+ if (x86_arch_cap_msr & ARCH_CAP_RFDS_NO)
return false;
/*
@@ -1309,7 +1310,7 @@
* indicate that mitigation is needed because guest is running on a
* vulnerable hardware or may migrate to such hardware:
*/
- if (ia32_cap & ARCH_CAP_RFDS_CLEAR)
+ if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR)
return true;
/* Only consult the blacklist when there is no enumeration: */
@@ -1318,11 +1319,11 @@
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
- u64 ia32_cap = x86_read_arch_cap_msr();
+ u64 x86_arch_cap_msr = x86_read_arch_cap_msr();
/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) &&
- !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
+ !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO))
setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION))
@@ -1334,7 +1335,7 @@
setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) &&
- !(ia32_cap & ARCH_CAP_SSB_NO) &&
+ !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) &&
!cpu_has(c, X86_FEATURE_AMD_SSB_NO))
setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
@@ -1345,17 +1346,17 @@
* Don't use AutoIBRS when SNP is enabled because it degrades host
* userspace indirect branch performance.
*/
- if ((ia32_cap & ARCH_CAP_IBRS_ALL) ||
+ if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) ||
(cpu_has(c, X86_FEATURE_AUTOIBRS) &&
!cpu_feature_enabled(X86_FEATURE_SEV_SNP))) {
setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
- !(ia32_cap & ARCH_CAP_PBRSB_NO))
+ !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO))
setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
}
if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) &&
- !(ia32_cap & ARCH_CAP_MDS_NO)) {
+ !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)) {
setup_force_cpu_bug(X86_BUG_MDS);
if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY))
setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
@@ -1374,9 +1375,9 @@
* TSX_CTRL check alone is not sufficient for cases when the microcode
* update is not present or running as guest that don't get TSX_CTRL.
*/
- if (!(ia32_cap & ARCH_CAP_TAA_NO) &&
+ if (!(x86_arch_cap_msr & ARCH_CAP_TAA_NO) &&
(cpu_has(c, X86_FEATURE_RTM) ||
- (ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
+ (x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)))
setup_force_cpu_bug(X86_BUG_TAA);
/*
@@ -1402,7 +1403,7 @@
* Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
* nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
*/
- if (!arch_cap_mmio_immune(ia32_cap)) {
+ if (!arch_cap_mmio_immune(x86_arch_cap_msr)) {
if (cpu_matches(cpu_vuln_blacklist, MMIO))
setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
@@ -1410,7 +1411,7 @@
}
if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
- if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))
+ if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (x86_arch_cap_msr & ARCH_CAP_RSBA))
setup_force_cpu_bug(X86_BUG_RETBLEED);
}
@@ -1428,18 +1429,25 @@
* disabling AVX2. The only way to do this in HW is to clear XCR0[2],
* which means that AVX will be disabled.
*/
- if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) &&
+ if (cpu_matches(cpu_vuln_blacklist, GDS) && !(x86_arch_cap_msr & ARCH_CAP_GDS_NO) &&
boot_cpu_has(X86_FEATURE_AVX))
setup_force_cpu_bug(X86_BUG_GDS);
- if (vulnerable_to_rfds(ia32_cap))
+ if (vulnerable_to_rfds(x86_arch_cap_msr))
setup_force_cpu_bug(X86_BUG_RFDS);
+ /* When virtualized, eIBRS could be hidden, assume vulnerable */
+ if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) &&
+ !cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
+ (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
+ boot_cpu_has(X86_FEATURE_HYPERVISOR)))
+ setup_force_cpu_bug(X86_BUG_BHI);
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
/* Rogue Data Cache Load? No! */
- if (ia32_cap & ARCH_CAP_RDCL_NO)
+ if (x86_arch_cap_msr & ARCH_CAP_RDCL_NO)
return;
setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index b717420..946813d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -44,7 +44,10 @@
{ X86_FEATURE_F16C, X86_FEATURE_XMM2, },
{ X86_FEATURE_AES, X86_FEATURE_XMM2 },
{ X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 },
+ { X86_FEATURE_GFNI, X86_FEATURE_XMM2 },
{ X86_FEATURE_FMA, X86_FEATURE_AVX },
+ { X86_FEATURE_VAES, X86_FEATURE_AVX },
+ { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX },
{ X86_FEATURE_AVX2, X86_FEATURE_AVX, },
{ X86_FEATURE_AVX512F, X86_FEATURE_AVX, },
{ X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F },
@@ -56,9 +59,6 @@
{ X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F },
{ X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL },
- { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL },
- { X86_FEATURE_VAES, X86_FEATURE_AVX512VL },
- { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL },
{ X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL },
{ X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL },
{ X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F },
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index a515328..af5aa2c 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -28,6 +28,7 @@
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
{ X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 },
{ X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 },
+ { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 },
{ X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
{ X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 },
{ X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index aaca8d2..d17c9b7 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -123,7 +123,6 @@
early_per_cpu(x86_cpu_to_apicid, cpu) = apic_id;
early_per_cpu(x86_cpu_to_acpiid, cpu) = acpi_id;
#endif
- set_cpu_possible(cpu, true);
set_cpu_present(cpu, true);
}
@@ -210,7 +209,11 @@
topo_info.nr_disabled_cpus++;
}
- /* Register present and possible CPUs in the domain maps */
+ /*
+ * Register present and possible CPUs in the domain
+ * maps. cpu_possible_map will be updated in
+ * topology_init_possible_cpus() after enumeration is done.
+ */
for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++)
set_bit(topo_apicid(apic_id, dom), apic_maps[dom].map);
}
diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index 1a8b3ad..a7aa6ef 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -29,11 +29,21 @@
if (!sft)
sft = get_count_order(ecx.cpu_nthreads + 1);
- topology_set_dom(tscan, TOPO_SMT_DOMAIN, sft, ecx.cpu_nthreads + 1);
+ /*
+ * cpu_nthreads describes the number of threads in the package
+ * sft is the number of APIC ID bits per package
+ *
+ * As the number of actual threads per core is not described in
+ * this leaf, just set the CORE domain shift and let the later
+ * parsers set SMT shift. Assume one thread per core by default
+ * which is correct if there are no other CPUID leafs to parse.
+ */
+ topology_update_dom(tscan, TOPO_SMT_DOMAIN, 0, 1);
+ topology_set_dom(tscan, TOPO_CORE_DOMAIN, sft, ecx.cpu_nthreads + 1);
return true;
}
-static void store_node(struct topo_scan *tscan, unsigned int nr_nodes, u16 node_id)
+static void store_node(struct topo_scan *tscan, u16 nr_nodes, u16 node_id)
{
/*
* Starting with Fam 17h the DIE domain could probably be used to
@@ -73,12 +83,14 @@
tscan->c->topo.initial_apicid = leaf.ext_apic_id;
/*
- * If leaf 0xb is available, then SMT shift is set already. If not
- * take it from ecx.threads_per_core and use topo_update_dom() -
- * topology_set_dom() would propagate and overwrite the already
- * propagated CORE level.
+ * If leaf 0xb is available, then the domain shifts are set
+ * already and nothing to do here.
*/
if (!has_0xb) {
+ /*
+ * Leaf 0x80000008 set the CORE domain shift already.
+ * Update the SMT domain, but do not propagate it.
+ */
unsigned int nthreads = leaf.core_nthreads + 1;
topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads);
@@ -109,13 +121,13 @@
static bool parse_fam10h_node_id(struct topo_scan *tscan)
{
- struct {
- union {
+ union {
+ struct {
u64 node_id : 3,
nodes_per_pkg : 3,
unused : 58;
- u64 msr;
};
+ u64 msr;
} nid;
if (!boot_cpu_has(X86_FEATURE_NODEID_MSR))
@@ -135,6 +147,26 @@
tscan->c->topo.llc_id = apicid >> tscan->dom_shifts[TOPO_CORE_DOMAIN];
}
+static void topoext_fixup(struct topo_scan *tscan)
+{
+ struct cpuinfo_x86 *c = tscan->c;
+ u64 msrval;
+
+ /* Try to re-enable TopologyExtensions if switched off by BIOS */
+ if (cpu_has(c, X86_FEATURE_TOPOEXT) || c->x86_vendor != X86_VENDOR_AMD ||
+ c->x86 != 0x15 || c->x86_model < 0x10 || c->x86_model > 0x6f)
+ return;
+
+ if (msr_set_bit(0xc0011005, 54) <= 0)
+ return;
+
+ rdmsrl(0xc0011005, msrval);
+ if (msrval & BIT_64(54)) {
+ set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+ pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+ }
+}
+
static void parse_topology_amd(struct topo_scan *tscan)
{
bool has_0xb = false;
@@ -164,6 +196,7 @@
void cpu_parse_topology_amd(struct topo_scan *tscan)
{
tscan->amd_nodes_per_pkg = 1;
+ topoext_fixup(tscan);
parse_topology_amd(tscan);
if (tscan->amd_nodes_per_pkg > 1)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 6f1b379..68b09f7 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -532,9 +532,10 @@
return __e820__range_update(e820_table, start, size, old_type, new_type);
}
-static u64 __init e820__range_update_kexec(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type)
+u64 __init e820__range_update_table(struct e820_table *t, u64 start, u64 size,
+ enum e820_type old_type, enum e820_type new_type)
{
- return __e820__range_update(e820_table_kexec, start, size, old_type, new_type);
+ return __e820__range_update(t, start, size, old_type, new_type);
}
/* Remove a range of memory from the E820 table: */
@@ -806,7 +807,7 @@
addr = memblock_phys_alloc(size, align);
if (addr) {
- e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
+ e820__range_update_table(e820_table_kexec, addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n");
e820__update_table_kexec();
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 7062b84..6d3d20e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -139,7 +139,7 @@
log_lvl, d3, d6, d7);
}
- if (cpu_feature_enabled(X86_FEATURE_OSPKE))
+ if (cr4 & X86_CR4_PKE)
printk("%sPKRU: %08x\n", log_lvl, read_pkru());
}
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 8b04958..b4f8fa0 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -1203,12 +1203,14 @@
break;
case SVM_EXIT_MONITOR:
- if (opcode == 0x010f && modrm == 0xc8)
+ /* MONITOR and MONITORX instructions generate the same error code */
+ if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa))
return ES_OK;
break;
case SVM_EXIT_MWAIT:
- if (opcode == 0x010f && modrm == 0xc9)
+ /* MWAIT and MWAITX instructions generate the same error code */
+ if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb))
return ES_OK;
break;
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index a88bb14..addc44f 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -3,11 +3,6 @@
ccflags-y += -I $(srctree)/arch/x86/kvm
ccflags-$(CONFIG_KVM_WERROR) += -Werror
-ifeq ($(CONFIG_FRAME_POINTER),y)
-OBJECT_FILES_NON_STANDARD_vmx/vmenter.o := y
-OBJECT_FILES_NON_STANDARD_svm/vmenter.o := y
-endif
-
include $(srctree)/virt/kvm/Makefile.kvm
kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index bfc0bfc..77352a4 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -376,6 +376,7 @@
kvm_update_pv_runtime(vcpu);
+ vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu);
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 856e303..23dbb9e 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -120,6 +120,16 @@
return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx);
}
+static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.is_amd_compatible;
+}
+
+static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu)
+{
+ return !guest_cpuid_is_amd_compatible(vcpu);
+}
+
static inline int guest_cpuid_family(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index cf37586..ebf4102 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2776,7 +2776,8 @@
trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL);
- if (r && lvt_type == APIC_LVTPC)
+ if (r && lvt_type == APIC_LVTPC &&
+ guest_cpuid_is_intel_compatible(apic->vcpu))
kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED);
return r;
}
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 992e651..db007a4 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4935,7 +4935,7 @@
context->cpu_role.base.level, is_efer_nx(context),
guest_can_use(vcpu, X86_FEATURE_GBPAGES),
is_cr4_pse(context),
- guest_cpuid_is_amd_or_hygon(vcpu));
+ guest_cpuid_is_amd_compatible(vcpu));
}
static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
@@ -5576,9 +5576,9 @@
* that problem is swept under the rug; KVM's CPUID API is horrific and
* it's all but impossible to solve it without introducing a new API.
*/
- vcpu->arch.root_mmu.root_role.word = 0;
- vcpu->arch.guest_mmu.root_role.word = 0;
- vcpu->arch.nested_mmu.root_role.word = 0;
+ vcpu->arch.root_mmu.root_role.invalid = 1;
+ vcpu->arch.guest_mmu.root_role.invalid = 1;
+ vcpu->arch.nested_mmu.root_role.invalid = 1;
vcpu->arch.root_mmu.cpu_role.ext.valid = 0;
vcpu->arch.guest_mmu.cpu_role.ext.valid = 0;
vcpu->arch.nested_mmu.cpu_role.ext.valid = 0;
@@ -7399,7 +7399,8 @@
* by the memslot, KVM can't use a hugepage due to the
* misaligned address regardless of memory attributes.
*/
- if (gfn >= slot->base_gfn) {
+ if (gfn >= slot->base_gfn &&
+ gfn + nr_pages <= slot->base_gfn + slot->npages) {
if (hugepage_has_attrs(kvm, slot, gfn, level, attrs))
hugepage_clear_mixed(slot, gfn, level);
else
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index d078157..04c1f09 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -1548,17 +1548,21 @@
}
}
-/*
- * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
- * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
- * If AD bits are not enabled, this will require clearing the writable bit on
- * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
- * be flushed.
- */
+static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp)
+{
+ /*
+ * All TDP MMU shadow pages share the same role as their root, aside
+ * from level, so it is valid to key off any shadow page to determine if
+ * write protection is needed for an entire tree.
+ */
+ return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled();
+}
+
static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
gfn_t start, gfn_t end)
{
- u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK;
+ const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK :
+ shadow_dirty_mask;
struct tdp_iter iter;
bool spte_set = false;
@@ -1573,7 +1577,7 @@
if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
continue;
- KVM_MMU_WARN_ON(kvm_ad_enabled() &&
+ KVM_MMU_WARN_ON(dbit == shadow_dirty_mask &&
spte_ad_need_write_protect(iter.old_spte));
if (!(iter.old_spte & dbit))
@@ -1590,11 +1594,9 @@
}
/*
- * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If
- * AD bits are enabled, this will involve clearing the dirty bit on each SPTE.
- * If AD bits are not enabled, this will require clearing the writable bit on
- * each SPTE. Returns true if an SPTE has been changed and the TLBs need to
- * be flushed.
+ * Clear the dirty status (D-bit or W-bit) of all the SPTEs mapping GFNs in the
+ * memslot. Returns true if an SPTE has been changed and the TLBs need to be
+ * flushed.
*/
bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
const struct kvm_memory_slot *slot)
@@ -1610,18 +1612,11 @@
return spte_set;
}
-/*
- * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
- * set in mask, starting at gfn. The given memslot is expected to contain all
- * the GFNs represented by set bits in the mask. If AD bits are enabled,
- * clearing the dirty status will involve clearing the dirty bit on each SPTE
- * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
- */
static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
gfn_t gfn, unsigned long mask, bool wrprot)
{
- u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK :
- shadow_dirty_mask;
+ const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK :
+ shadow_dirty_mask;
struct tdp_iter iter;
lockdep_assert_held_write(&kvm->mmu_lock);
@@ -1633,7 +1628,7 @@
if (!mask)
break;
- KVM_MMU_WARN_ON(kvm_ad_enabled() &&
+ KVM_MMU_WARN_ON(dbit == shadow_dirty_mask &&
spte_ad_need_write_protect(iter.old_spte));
if (iter.level > PG_LEVEL_4K ||
@@ -1659,11 +1654,9 @@
}
/*
- * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is
- * set in mask, starting at gfn. The given memslot is expected to contain all
- * the GFNs represented by set bits in the mask. If AD bits are enabled,
- * clearing the dirty status will involve clearing the dirty bit on each SPTE
- * or, if AD bits are not enabled, clearing the writable bit on each SPTE.
+ * Clear the dirty status (D-bit or W-bit) of all the 4k SPTEs mapping GFNs for
+ * which a bit is set in mask, starting at gfn. The given memslot is expected to
+ * contain all the GFNs represented by set bits in the mask.
*/
void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *slot,
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index c397b28..a593b03 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -775,8 +775,20 @@
pmu->pebs_data_cfg_mask = ~0ull;
bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX);
- if (vcpu->kvm->arch.enable_pmu)
- static_call(kvm_x86_pmu_refresh)(vcpu);
+ if (!vcpu->kvm->arch.enable_pmu)
+ return;
+
+ static_call(kvm_x86_pmu_refresh)(vcpu);
+
+ /*
+ * At RESET, both Intel and AMD CPUs set all enable bits for general
+ * purpose counters in IA32_PERF_GLOBAL_CTRL (so that software that
+ * was written for v1 PMUs don't unknowingly leave GP counters disabled
+ * in the global controls). Emulate that behavior when refreshing the
+ * PMU so that userspace doesn't need to manually set PERF_GLOBAL_CTRL.
+ */
+ if (kvm_pmu_has_perf_global_ctrl(pmu) && pmu->nr_arch_gp_counters)
+ pmu->global_ctrl = GENMASK_ULL(pmu->nr_arch_gp_counters - 1, 0);
}
void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index 58ac8d6..2f4e155 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -52,7 +52,7 @@
#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1)
#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2)
#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3)
-#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
+#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
/* CPUID level 0x80000007 (EDX). */
@@ -128,6 +128,7 @@
KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC);
KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
+ KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
default:
return x86_feature;
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 61a7531..759581b 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -434,7 +434,7 @@
/* Avoid using vmalloc for smaller buffers. */
size = npages * sizeof(struct page *);
if (size > PAGE_SIZE)
- pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ pages = __vmalloc(size, GFP_KERNEL_ACCOUNT);
else
pages = kmalloc(size, GFP_KERNEL_ACCOUNT);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d1a9f995..9aaf83c8 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1503,6 +1503,11 @@
__free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
}
+static struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd)
+{
+ return page_address(sd->save_area) + 0x400;
+}
+
static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1519,12 +1524,8 @@
* or subsequent vmload of host save area.
*/
vmsave(sd->save_area_pa);
- if (sev_es_guest(vcpu->kvm)) {
- struct sev_es_save_area *hostsa;
- hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
-
- sev_es_prepare_switch_to_guest(hostsa);
- }
+ if (sev_es_guest(vcpu->kvm))
+ sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd));
if (tsc_scaling)
__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
@@ -4101,6 +4102,7 @@
static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted)
{
+ struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu);
struct vcpu_svm *svm = to_svm(vcpu);
guest_state_enter_irqoff();
@@ -4108,7 +4110,8 @@
amd_clear_divider();
if (sev_es_guest(vcpu->kvm))
- __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted);
+ __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted,
+ sev_es_host_save_area(sd));
else
__svm_vcpu_run(svm, spec_ctrl_intercepted);
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 7f1fbd8..33878ef 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -698,7 +698,8 @@
/* vmenter.S */
-void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted);
+void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted,
+ struct sev_es_save_area *hostsa);
void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted);
#define DEFINE_KVM_GHCB_ACCESSORS(field) \
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 187018c..a0c8eb3 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -3,6 +3,7 @@
#include <asm/asm.h>
#include <asm/asm-offsets.h>
#include <asm/bitsperlong.h>
+#include <asm/frame.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/nospec-branch.h>
#include "kvm-asm-offsets.h"
@@ -67,7 +68,7 @@
"", X86_FEATURE_V_SPEC_CTRL
901:
.endm
-.macro RESTORE_HOST_SPEC_CTRL_BODY
+.macro RESTORE_HOST_SPEC_CTRL_BODY spec_ctrl_intercepted:req
900:
/* Same for after vmexit. */
mov $MSR_IA32_SPEC_CTRL, %ecx
@@ -76,7 +77,7 @@
* Load the value that the guest had written into MSR_IA32_SPEC_CTRL,
* if it was not intercepted during guest execution.
*/
- cmpb $0, (%_ASM_SP)
+ cmpb $0, \spec_ctrl_intercepted
jnz 998f
rdmsr
movl %eax, SVM_spec_ctrl(%_ASM_DI)
@@ -99,6 +100,7 @@
*/
SYM_FUNC_START(__svm_vcpu_run)
push %_ASM_BP
+ mov %_ASM_SP, %_ASM_BP
#ifdef CONFIG_X86_64
push %r15
push %r14
@@ -268,7 +270,7 @@
RET
RESTORE_GUEST_SPEC_CTRL_BODY
- RESTORE_HOST_SPEC_CTRL_BODY
+ RESTORE_HOST_SPEC_CTRL_BODY (%_ASM_SP)
10: cmpb $0, _ASM_RIP(kvm_rebooting)
jne 2b
@@ -290,66 +292,68 @@
SYM_FUNC_END(__svm_vcpu_run)
+#ifdef CONFIG_KVM_AMD_SEV
+
+
+#ifdef CONFIG_X86_64
+#define SEV_ES_GPRS_BASE 0x300
+#define SEV_ES_RBX (SEV_ES_GPRS_BASE + __VCPU_REGS_RBX * WORD_SIZE)
+#define SEV_ES_RBP (SEV_ES_GPRS_BASE + __VCPU_REGS_RBP * WORD_SIZE)
+#define SEV_ES_RSI (SEV_ES_GPRS_BASE + __VCPU_REGS_RSI * WORD_SIZE)
+#define SEV_ES_RDI (SEV_ES_GPRS_BASE + __VCPU_REGS_RDI * WORD_SIZE)
+#define SEV_ES_R12 (SEV_ES_GPRS_BASE + __VCPU_REGS_R12 * WORD_SIZE)
+#define SEV_ES_R13 (SEV_ES_GPRS_BASE + __VCPU_REGS_R13 * WORD_SIZE)
+#define SEV_ES_R14 (SEV_ES_GPRS_BASE + __VCPU_REGS_R14 * WORD_SIZE)
+#define SEV_ES_R15 (SEV_ES_GPRS_BASE + __VCPU_REGS_R15 * WORD_SIZE)
+#endif
+
/**
* __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode
* @svm: struct vcpu_svm *
* @spec_ctrl_intercepted: bool
*/
SYM_FUNC_START(__svm_sev_es_vcpu_run)
- push %_ASM_BP
-#ifdef CONFIG_X86_64
- push %r15
- push %r14
- push %r13
- push %r12
-#else
- push %edi
- push %esi
-#endif
- push %_ASM_BX
+ FRAME_BEGIN
/*
- * Save variables needed after vmexit on the stack, in inverse
- * order compared to when they are needed.
+ * Save non-volatile (callee-saved) registers to the host save area.
+ * Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not
+ * saved on VMRUN.
*/
+ mov %rbp, SEV_ES_RBP (%rdx)
+ mov %r15, SEV_ES_R15 (%rdx)
+ mov %r14, SEV_ES_R14 (%rdx)
+ mov %r13, SEV_ES_R13 (%rdx)
+ mov %r12, SEV_ES_R12 (%rdx)
+ mov %rbx, SEV_ES_RBX (%rdx)
- /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */
- push %_ASM_ARG2
-
- /* Save @svm. */
- push %_ASM_ARG1
-
-.ifnc _ASM_ARG1, _ASM_DI
/*
- * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX
- * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL.
+ * Save volatile registers that hold arguments that are needed after
+ * #VMEXIT (RDI=@svm and RSI=@spec_ctrl_intercepted).
*/
- mov %_ASM_ARG1, %_ASM_DI
-.endif
+ mov %rdi, SEV_ES_RDI (%rdx)
+ mov %rsi, SEV_ES_RSI (%rdx)
- /* Clobbers RAX, RCX, RDX. */
+ /* Clobbers RAX, RCX, RDX (@hostsa). */
RESTORE_GUEST_SPEC_CTRL
/* Get svm->current_vmcb->pa into RAX. */
- mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX
- mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX
+ mov SVM_current_vmcb(%rdi), %rax
+ mov KVM_VMCB_pa(%rax), %rax
/* Enter guest mode */
sti
-1: vmrun %_ASM_AX
+1: vmrun %rax
2: cli
- /* Pop @svm to RDI, guest registers have been saved already. */
- pop %_ASM_DI
-
#ifdef CONFIG_MITIGATION_RETPOLINE
/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
- FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+ FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
#endif
- /* Clobbers RAX, RCX, RDX. */
+ /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */
RESTORE_HOST_SPEC_CTRL
/*
@@ -361,30 +365,17 @@
*/
UNTRAIN_RET_VM
- /* "Pop" @spec_ctrl_intercepted. */
- pop %_ASM_BX
-
- pop %_ASM_BX
-
-#ifdef CONFIG_X86_64
- pop %r12
- pop %r13
- pop %r14
- pop %r15
-#else
- pop %esi
- pop %edi
-#endif
- pop %_ASM_BP
+ FRAME_END
RET
RESTORE_GUEST_SPEC_CTRL_BODY
- RESTORE_HOST_SPEC_CTRL_BODY
+ RESTORE_HOST_SPEC_CTRL_BODY %sil
-3: cmpb $0, _ASM_RIP(kvm_rebooting)
+3: cmpb $0, kvm_rebooting(%rip)
jne 2b
ud2
_ASM_EXTABLE(1b, 3b)
SYM_FUNC_END(__svm_sev_es_vcpu_run)
+#endif /* CONFIG_KVM_AMD_SEV */
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 12ade34..be40474 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -535,7 +535,7 @@
perf_capabilities = vcpu_get_perf_capabilities(vcpu);
if (cpuid_model_is_consistent(vcpu) &&
(perf_capabilities & PMU_CAP_LBR_FMT))
- x86_perf_get_lbr(&lbr_desc->records);
+ memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps));
else
lbr_desc->records.nr = 0;
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 2bfbf75..f6986de 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -275,6 +275,8 @@
call vmx_spec_ctrl_restore_host
+ CLEAR_BRANCH_HISTORY_VMEXIT
+
/* Put return value in AX */
mov %_ASM_BX, %_ASM_AX
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index c37a89e..22411f4 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -218,6 +218,8 @@
int __read_mostly pt_mode = PT_MODE_SYSTEM;
module_param(pt_mode, int, S_IRUGO);
+struct x86_pmu_lbr __ro_after_init vmx_lbr_caps;
+
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
static DEFINE_MUTEX(vmx_l1d_flush_mutex);
@@ -7862,10 +7864,9 @@
vmx_update_exception_bitmap(vcpu);
}
-static u64 vmx_get_perf_capabilities(void)
+static __init u64 vmx_get_perf_capabilities(void)
{
u64 perf_cap = PMU_CAP_FW_WRITES;
- struct x86_pmu_lbr lbr;
u64 host_perf_cap = 0;
if (!enable_pmu)
@@ -7875,15 +7876,43 @@
rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) {
- x86_perf_get_lbr(&lbr);
- if (lbr.nr)
+ x86_perf_get_lbr(&vmx_lbr_caps);
+
+ /*
+ * KVM requires LBR callstack support, as the overhead due to
+ * context switching LBRs without said support is too high.
+ * See intel_pmu_create_guest_lbr_event() for more info.
+ */
+ if (!vmx_lbr_caps.has_callstack)
+ memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps));
+ else if (vmx_lbr_caps.nr)
perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
}
if (vmx_pebs_supported()) {
perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
- if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
- perf_cap &= ~PERF_CAP_PEBS_BASELINE;
+
+ /*
+ * Disallow adaptive PEBS as it is functionally broken, can be
+ * used by the guest to read *host* LBRs, and can be used to
+ * bypass userspace event filters. To correctly and safely
+ * support adaptive PEBS, KVM needs to:
+ *
+ * 1. Account for the ADAPTIVE flag when (re)programming fixed
+ * counters.
+ *
+ * 2. Gain support from perf (or take direct control of counter
+ * programming) to support events without adaptive PEBS
+ * enabled for the hardware counter.
+ *
+ * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with
+ * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1.
+ *
+ * 4. Document which PMU events are effectively exposed to the
+ * guest via adaptive PEBS, and make adaptive PEBS mutually
+ * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary.
+ */
+ perf_cap &= ~PERF_CAP_PEBS_BASELINE;
}
return perf_cap;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 65786db..90f9e44 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -15,6 +15,7 @@
#include "vmx_ops.h"
#include "../cpuid.h"
#include "run_flags.h"
+#include "../mmu.h"
#define MSR_TYPE_R 1
#define MSR_TYPE_W 2
@@ -109,6 +110,8 @@
bool msr_passthrough;
};
+extern struct x86_pmu_lbr vmx_lbr_caps;
+
/*
* The nested_vmx structure is part of vcpu_vmx, and holds information we need
* for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -719,7 +722,8 @@
if (!enable_ept)
return true;
- return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
+ return allow_smaller_maxphyaddr &&
+ cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits();
}
static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 47d9f03..91478b76 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1621,7 +1621,7 @@
ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
- ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR)
+ ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
static u64 kvm_get_arch_capabilities(void)
{
@@ -3470,7 +3470,7 @@
static bool can_set_mci_status(struct kvm_vcpu *vcpu)
{
/* McStatusWrEn enabled? */
- if (guest_cpuid_is_amd_or_hygon(vcpu))
+ if (guest_cpuid_is_amd_compatible(vcpu))
return !!(vcpu->arch.msr_hwcr & BIT_ULL(18));
return false;
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index e674ccf..391059b 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -382,8 +382,15 @@
SYM_CODE_START(__x86_return_thunk)
UNWIND_HINT_FUNC
ANNOTATE_NOENDBR
+#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || \
+ defined(CONFIG_MITIGATION_SRSO) || \
+ defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)
ALTERNATIVE __stringify(ANNOTATE_UNRET_SAFE; ret), \
"jmp warn_thunk_thunk", X86_FEATURE_ALWAYS
+#else
+ ANNOTATE_UNRET_SAFE
+ ret
+#endif
int3
SYM_CODE_END(__x86_return_thunk)
EXPORT_SYMBOL(__x86_return_thunk)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 622d12e..bba4e02 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -723,39 +723,8 @@
WARN_ON_ONCE(user_mode(regs));
/* Are we prepared to handle this kernel fault? */
- if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
- /*
- * Any interrupt that takes a fault gets the fixup. This makes
- * the below recursive fault logic only apply to a faults from
- * task context.
- */
- if (in_interrupt())
- return;
-
- /*
- * Per the above we're !in_interrupt(), aka. task context.
- *
- * In this case we need to make sure we're not recursively
- * faulting through the emulate_vsyscall() logic.
- */
- if (current->thread.sig_on_uaccess_err && signal) {
- sanitize_error_code(address, &error_code);
-
- set_signal_archinfo(address, error_code);
-
- if (si_code == SEGV_PKUERR) {
- force_sig_pkuerr((void __user *)address, pkey);
- } else {
- /* XXX: hwpoison faults will set the wrong code. */
- force_sig_fault(signal, si_code, (void __user *)address);
- }
- }
-
- /*
- * Barring that, we can do the fixup and be happy.
- */
+ if (fixup_exception(regs, X86_TRAP_PF, error_code, address))
return;
- }
/*
* AMD erratum #91 manifests as a spurious page fault on a PREFETCH
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 6f3b3e0..0a120d8 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -102,6 +102,13 @@
phys_addr_t total_mem = memblock_phys_mem_size();
unsigned long size;
+ /*
+ * Do RMP table fixups after the e820 tables have been setup by
+ * e820__memory_setup().
+ */
+ if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+ snp_fixup_e820_tables();
+
if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
return;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index df5fac4..59cbc94 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1807,36 +1807,41 @@
if (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
BPF_MODE(insn->code) == BPF_PROBE_MEMSX) {
/* Conservatively check that src_reg + insn->off is a kernel address:
- * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE
- * src_reg is used as scratch for src_reg += insn->off and restored
- * after emit_ldx if necessary
+ * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE
+ * and
+ * src_reg + insn->off < VSYSCALL_ADDR
*/
- u64 limit = TASK_SIZE_MAX + PAGE_SIZE;
+ u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR;
u8 *end_of_jmp;
- /* At end of these emitted checks, insn->off will have been added
- * to src_reg, so no need to do relative load with insn->off offset
- */
- insn_off = 0;
+ /* movabsq r10, VSYSCALL_ADDR */
+ emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32,
+ (u32)(long)VSYSCALL_ADDR);
- /* movabsq r11, limit */
- EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG));
- EMIT((u32)limit, 4);
- EMIT(limit >> 32, 4);
+ /* mov src_reg, r11 */
+ EMIT_mov(AUX_REG, src_reg);
if (insn->off) {
- /* add src_reg, insn->off */
- maybe_emit_1mod(&prog, src_reg, true);
- EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off);
+ /* add r11, insn->off */
+ maybe_emit_1mod(&prog, AUX_REG, true);
+ EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off);
}
- /* cmp src_reg, r11 */
- maybe_emit_mod(&prog, src_reg, AUX_REG, true);
- EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG));
+ /* sub r11, r10 */
+ maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true);
+ EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX));
- /* if unsigned '>=', goto load */
- EMIT2(X86_JAE, 0);
+ /* movabsq r10, limit */
+ emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32,
+ (u32)(long)limit);
+
+ /* cmp r10, r11 */
+ maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true);
+ EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX));
+
+ /* if unsigned '>', goto load */
+ EMIT2(X86_JA, 0);
end_of_jmp = prog;
/* xor dst_reg, dst_reg */
@@ -1862,18 +1867,6 @@
/* populate jmp_offset for JMP above */
start_of_ldx[-1] = prog - start_of_ldx;
- if (insn->off && src_reg != dst_reg) {
- /* sub src_reg, insn->off
- * Restore src_reg after "add src_reg, insn->off" in prev
- * if statement. But if src_reg == dst_reg, emit_ldx
- * above already clobbered src_reg, so no need to restore.
- * If add src_reg, insn->off was unnecessary, no need to
- * restore either.
- */
- maybe_emit_1mod(&prog, src_reg, true);
- EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off);
- }
-
if (!bpf_prog->aux->extable)
break;
@@ -3473,3 +3466,9 @@
{
return true;
}
+
+/* x86-64 JIT emits its own code to filter user addresses so return 0 here */
+u64 bpf_arch_uaddress_limit(void)
+{
+ return 0;
+}
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index ab0e844..0ae1053 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -163,6 +163,42 @@
return true;
}
+static void __init __snp_fixup_e820_tables(u64 pa)
+{
+ if (IS_ALIGNED(pa, PMD_SIZE))
+ return;
+
+ /*
+ * Handle cases where the RMP table placement by the BIOS is not
+ * 2M aligned and the kexec kernel could try to allocate
+ * from within that chunk which then causes a fatal RMP fault.
+ *
+ * The e820_table needs to be updated as it is converted to
+ * kernel memory resources and used by KEXEC_FILE_LOAD syscall
+ * to load kexec segments.
+ *
+ * The e820_table_firmware needs to be updated as it is exposed
+ * to sysfs and used by the KEXEC_LOAD syscall to load kexec
+ * segments.
+ *
+ * The e820_table_kexec needs to be updated as it passed to
+ * the kexec-ed kernel.
+ */
+ pa = ALIGN_DOWN(pa, PMD_SIZE);
+ if (e820__mapped_any(pa, pa + PMD_SIZE, E820_TYPE_RAM)) {
+ pr_info("Reserving start/end of RMP table on a 2MB boundary [0x%016llx]\n", pa);
+ e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+ e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+ e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+ }
+}
+
+void __init snp_fixup_e820_tables(void)
+{
+ __snp_fixup_e820_tables(probed_rmp_base);
+ __snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size);
+}
+
/*
* Do the necessary preparations which are verified by the firmware as
* described in the SNP_INIT_EX firmware command description in the SNP
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index ace2eb0..9ba5381 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -219,13 +219,21 @@
static void xen_cpuid(unsigned int *ax, unsigned int *bx,
unsigned int *cx, unsigned int *dx)
{
- unsigned maskebx = ~0;
+ unsigned int maskebx = ~0;
+ unsigned int or_ebx = 0;
/*
* Mask out inconvenient features, to try and disable as many
* unsupported kernel subsystems as possible.
*/
switch (*ax) {
+ case 0x1:
+ /* Replace initial APIC ID in bits 24-31 of EBX. */
+ /* See xen_pv_smp_config() for related topology preparations. */
+ maskebx = 0x00ffffff;
+ or_ebx = smp_processor_id() << 24;
+ break;
+
case CPUID_MWAIT_LEAF:
/* Synthesize the values.. */
*ax = 0;
@@ -248,6 +256,7 @@
: "0" (*ax), "2" (*cx));
*bx &= maskebx;
+ *bx |= or_ebx;
}
static bool __init xen_check_mwait(void)
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 27d1a5b..ac41d83 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -154,9 +154,9 @@
u32 apicid = 0;
int i;
- topology_register_boot_apic(apicid++);
+ topology_register_boot_apic(apicid);
- for (i = 1; i < nr_cpu_ids; i++)
+ for (i = 0; i < nr_cpu_ids; i++)
topology_register_apic(apicid++, CPU_ACPIID_INVALID, true);
/* Pretend to be a proper enumerated system */
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index 38bcecb..a2b6bb5 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -100,6 +100,10 @@
void flush_icache_range(unsigned long start, unsigned long end);
void flush_cache_page(struct vm_area_struct*,
unsigned long, unsigned long);
+#define flush_cache_all flush_cache_all
+#define flush_cache_range flush_cache_range
+#define flush_icache_range flush_icache_range
+#define flush_cache_page flush_cache_page
#else
#define flush_cache_all local_flush_cache_all
#define flush_cache_range local_flush_cache_range
@@ -136,20 +140,7 @@
#else
-#define flush_cache_all() do { } while (0)
-#define flush_cache_mm(mm) do { } while (0)
-#define flush_cache_dup_mm(mm) do { } while (0)
-
-#define flush_cache_vmap(start,end) do { } while (0)
-#define flush_cache_vmap_early(start,end) do { } while (0)
-#define flush_cache_vunmap(start,end) do { } while (0)
-
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page) do { } while (0)
-
#define flush_icache_range local_flush_icache_range
-#define flush_cache_page(vma, addr, pfn) do { } while (0)
-#define flush_cache_range(vma, start, end) do { } while (0)
#endif
@@ -162,15 +153,14 @@
__invalidate_icache_range(start,(end) - (start)); \
} while (0)
-#define flush_dcache_mmap_lock(mapping) do { } while (0)
-#define flush_dcache_mmap_unlock(mapping) do { } while (0)
-
#if defined(CONFIG_MMU) && (DCACHE_WAY_SIZE > PAGE_SIZE)
extern void copy_to_user_page(struct vm_area_struct*, struct page*,
unsigned long, void*, const void*, unsigned long);
extern void copy_from_user_page(struct vm_area_struct*, struct page*,
unsigned long, void*, const void*, unsigned long);
+#define copy_to_user_page copy_to_user_page
+#define copy_from_user_page copy_from_user_page
#else
@@ -186,4 +176,6 @@
#endif
+#include <asm-generic/cacheflush.h>
+
#endif /* _XTENSA_CACHEFLUSH_H */
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index d008a15..7ed1a20 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -115,9 +115,9 @@
#define MAKE_RA_FOR_CALL(ra,ws) (((ra) & 0x3fffffff) | (ws) << 30)
/* Convert return address to a valid pc
- * Note: We assume that the stack pointer is in the same 1GB ranges as the ra
+ * Note: 'text' is the address within the same 1GB range as the ra
*/
-#define MAKE_PC_FROM_RA(ra,sp) (((ra) & 0x3fffffff) | ((sp) & 0xc0000000))
+#define MAKE_PC_FROM_RA(ra, text) (((ra) & 0x3fffffff) | ((unsigned long)(text) & 0xc0000000))
#elif defined(__XTENSA_CALL0_ABI__)
@@ -127,9 +127,9 @@
#define MAKE_RA_FOR_CALL(ra, ws) (ra)
/* Convert return address to a valid pc
- * Note: We assume that the stack pointer is in the same 1GB ranges as the ra
+ * Note: 'text' is not used as 'ra' is always the full address
*/
-#define MAKE_PC_FROM_RA(ra, sp) (ra)
+#define MAKE_PC_FROM_RA(ra, text) (ra)
#else
#error Unsupported Xtensa ABI
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index a270467..86c7011 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -87,7 +87,7 @@
# define user_mode(regs) (((regs)->ps & 0x00000020)!=0)
# define instruction_pointer(regs) ((regs)->pc)
# define return_pointer(regs) (MAKE_PC_FROM_RA((regs)->areg[0], \
- (regs)->areg[1]))
+ (regs)->pc))
# ifndef CONFIG_SMP
# define profile_pc(regs) instruction_pointer(regs)
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index a815577..7bd6667 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -47,6 +47,7 @@
#include <asm/asm-offsets.h>
#include <asm/regs.h>
#include <asm/hw_breakpoint.h>
+#include <asm/sections.h>
#include <asm/traps.h>
extern void ret_from_fork(void);
@@ -380,7 +381,7 @@
int count = 0;
sp = p->thread.sp;
- pc = MAKE_PC_FROM_RA(p->thread.ra, p->thread.sp);
+ pc = MAKE_PC_FROM_RA(p->thread.ra, _text);
do {
if (sp < stack_page + sizeof(struct task_struct) ||
@@ -392,7 +393,7 @@
/* Stack layout: sp-4: ra, sp-3: sp' */
- pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), sp);
+ pc = MAKE_PC_FROM_RA(SPILL_SLOT(sp, 0), _text);
sp = SPILL_SLOT(sp, 1);
} while (count++ < 16);
return 0;
diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c
index 831ffb6..ed324fd 100644
--- a/arch/xtensa/kernel/stacktrace.c
+++ b/arch/xtensa/kernel/stacktrace.c
@@ -13,6 +13,7 @@
#include <linux/stacktrace.h>
#include <asm/ftrace.h>
+#include <asm/sections.h>
#include <asm/stacktrace.h>
#include <asm/traps.h>
#include <linux/uaccess.h>
@@ -189,7 +190,7 @@
if (a1 <= (unsigned long)sp)
break;
- frame.pc = MAKE_PC_FROM_RA(a0, a1);
+ frame.pc = MAKE_PC_FROM_RA(a0, _text);
frame.sp = a1;
if (fn(&frame, data))
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 8896e69..abec44b6 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -166,10 +166,8 @@
static void iss_console_write(struct console *co, const char *s, unsigned count)
{
- if (s && *s != 0) {
- int len = strlen(s);
- simc_write(1, s, count < len ? count : len);
- }
+ if (s && *s != 0)
+ simc_write(1, s, min(count, strlen(s)));
}
static struct tty_driver* iss_console_device(struct console *c, int *index)
diff --git a/block/bdev.c b/block/bdev.c
index b8e32d9..da2a167 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -645,6 +645,14 @@
bdev_write_inode(bdev);
}
+static void blkdev_put_whole(struct block_device *bdev)
+{
+ if (atomic_dec_and_test(&bdev->bd_openers))
+ blkdev_flush_mapping(bdev);
+ if (bdev->bd_disk->fops->release)
+ bdev->bd_disk->fops->release(bdev->bd_disk);
+}
+
static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode)
{
struct gendisk *disk = bdev->bd_disk;
@@ -663,20 +671,21 @@
if (!atomic_read(&bdev->bd_openers))
set_init_blocksize(bdev);
- if (test_bit(GD_NEED_PART_SCAN, &disk->state))
- bdev_disk_changed(disk, false);
atomic_inc(&bdev->bd_openers);
+ if (test_bit(GD_NEED_PART_SCAN, &disk->state)) {
+ /*
+ * Only return scanning errors if we are called from contexts
+ * that explicitly want them, e.g. the BLKRRPART ioctl.
+ */
+ ret = bdev_disk_changed(disk, false);
+ if (ret && (mode & BLK_OPEN_STRICT_SCAN)) {
+ blkdev_put_whole(bdev);
+ return ret;
+ }
+ }
return 0;
}
-static void blkdev_put_whole(struct block_device *bdev)
-{
- if (atomic_dec_and_test(&bdev->bd_openers))
- blkdev_flush_mapping(bdev);
- if (bdev->bd_disk->fops->release)
- bdev->bd_disk->fops->release(bdev->bd_disk);
-}
-
static int blkdev_get_part(struct block_device *part, blk_mode_t mode)
{
struct gendisk *disk = part->bd_disk;
@@ -873,7 +882,7 @@
goto abort_claiming;
ret = -EBUSY;
if (!bdev_may_open(bdev, mode))
- goto abort_claiming;
+ goto put_module;
if (bdev_is_partition(bdev))
ret = blkdev_get_part(bdev, mode);
else
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index bdbb557..0594670 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1409,6 +1409,12 @@
return 0;
}
+void blkg_init_queue(struct request_queue *q)
+{
+ INIT_LIST_HEAD(&q->blkg_list);
+ mutex_init(&q->blkcg_mutex);
+}
+
int blkcg_init_disk(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
@@ -1416,9 +1422,6 @@
bool preloaded;
int ret;
- INIT_LIST_HEAD(&q->blkg_list);
- mutex_init(&q->blkcg_mutex);
-
new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
if (!new_blkg)
return -ENOMEM;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 78b7410..90b3959 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -189,6 +189,7 @@
extern struct blkcg blkcg_root;
extern bool blkcg_debug_stats;
+void blkg_init_queue(struct request_queue *q);
int blkcg_init_disk(struct gendisk *disk);
void blkcg_exit_disk(struct gendisk *disk);
@@ -482,6 +483,7 @@
};
static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline void blkg_init_queue(struct request_queue *q) { }
static inline int blkcg_init_disk(struct gendisk *disk) { return 0; }
static inline void blkcg_exit_disk(struct gendisk *disk) { }
static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
diff --git a/block/blk-core.c b/block/blk-core.c
index a16b5ab..b795ac1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -442,6 +442,8 @@
init_waitqueue_head(&q->mq_freeze_wq);
mutex_init(&q->mq_freeze_lock);
+ blkg_init_queue(q);
+
/*
* Init percpu_ref in atomic mode so that it's faster to shutdown.
* See blk_register_queue() for details.
@@ -1195,6 +1197,7 @@
if (unlikely(!rq_list_empty(plug->cached_rq)))
blk_mq_free_plug_rqs(plug);
+ plug->cur_ktime = 0;
current->flags &= ~PF_BLOCK_TS;
}
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 9a85bfb..690ca99 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1347,7 +1347,7 @@
{
struct ioc *ioc = iocg->ioc;
struct blkcg_gq *blkg = iocg_to_blkg(iocg);
- u64 tdelta, delay, new_delay;
+ u64 tdelta, delay, new_delay, shift;
s64 vover, vover_pct;
u32 hwa;
@@ -1362,8 +1362,9 @@
/* calculate the current delay in effect - 1/2 every second */
tdelta = now->now - iocg->delay_at;
- if (iocg->delay)
- delay = iocg->delay >> div64_u64(tdelta, USEC_PER_SEC);
+ shift = div64_u64(tdelta, USEC_PER_SEC);
+ if (iocg->delay && shift < BITS_PER_LONG)
+ delay = iocg->delay >> shift;
else
delay = 0;
@@ -1438,8 +1439,11 @@
lockdep_assert_held(&iocg->ioc->lock);
lockdep_assert_held(&iocg->waitq.lock);
- /* make sure that nobody messed with @iocg */
- WARN_ON_ONCE(list_empty(&iocg->active_list));
+ /*
+ * make sure that nobody messed with @iocg. Check iocg->pd.online
+ * to avoid warn when removing blkcg or disk.
+ */
+ WARN_ON_ONCE(list_empty(&iocg->active_list) && iocg->pd.online);
WARN_ON_ONCE(iocg->inuse > 1);
iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index cdbaef1..d273184 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -182,17 +182,13 @@
return -EINVAL;
/*
- * Devices that require a virtual boundary do not support scatter/gather
- * I/O natively, but instead require a descriptor list entry for each
- * page (which might not be identical to the Linux PAGE_SIZE). Because
- * of that they are not limited by our notion of "segment size".
+ * Stacking device may have both virtual boundary and max segment
+ * size limit, so allow this setting now, and long-term the two
+ * might need to move out of stacking limits since we have immutable
+ * bvec and lower layer bio splitting is supposed to handle the two
+ * correctly.
*/
- if (lim->virt_boundary_mask) {
- if (WARN_ON_ONCE(lim->max_segment_size &&
- lim->max_segment_size != UINT_MAX))
- return -EINVAL;
- lim->max_segment_size = UINT_MAX;
- } else {
+ if (!lim->virt_boundary_mask) {
/*
* The maximum segment size has an odd historic 64k default that
* drivers probably should override. Just like the I/O size we
diff --git a/block/ioctl.c b/block/ioctl.c
index a9028a2..f505f9c 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -563,7 +563,8 @@
return -EACCES;
if (bdev_is_partition(bdev))
return -EINVAL;
- return disk_scan_partitions(bdev->bd_disk, mode);
+ return disk_scan_partitions(bdev->bd_disk,
+ mode | BLK_OPEN_STRICT_SCAN);
case BLKTRACESTART:
case BLKTRACESTOP:
case BLKTRACETEARDOWN:
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 39f6d1b..51d3f1a 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
*/
#include <linux/firmware.h>
@@ -131,22 +131,6 @@
return 0;
}
-static int ivpu_get_core_clock_rate(struct ivpu_device *vdev, u64 *clk_rate)
-{
- int ret;
-
- ret = ivpu_rpm_get_if_active(vdev);
- if (ret < 0)
- return ret;
-
- *clk_rate = ret ? ivpu_hw_reg_pll_freq_get(vdev) : 0;
-
- if (ret)
- ivpu_rpm_put(vdev);
-
- return 0;
-}
-
static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
{
struct ivpu_file_priv *file_priv = file->driver_priv;
@@ -170,7 +154,7 @@
args->value = vdev->platform;
break;
case DRM_IVPU_PARAM_CORE_CLOCK_RATE:
- ret = ivpu_get_core_clock_rate(vdev, &args->value);
+ args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio);
break;
case DRM_IVPU_PARAM_NUM_CONTEXTS:
args->value = ivpu_get_context_count(vdev);
@@ -387,12 +371,15 @@
{
int ret;
- ivpu_prepare_for_reset(vdev);
+ /* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
+ pci_save_state(to_pci_dev(vdev->drm.dev));
ret = ivpu_hw_power_down(vdev);
if (ret)
ivpu_warn(vdev, "Failed to power down HW: %d\n", ret);
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+
return ret;
}
@@ -530,7 +517,7 @@
vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID;
vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID;
atomic64_set(&vdev->unique_id_counter, 0);
- xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC);
+ xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1);
lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
@@ -560,11 +547,11 @@
/* Power up early so the rest of init code can access VPU registers */
ret = ivpu_hw_power_up(vdev);
if (ret)
- goto err_power_down;
+ goto err_shutdown;
ret = ivpu_mmu_global_context_init(vdev);
if (ret)
- goto err_power_down;
+ goto err_shutdown;
ret = ivpu_mmu_init(vdev);
if (ret)
@@ -601,10 +588,8 @@
ivpu_mmu_reserved_context_fini(vdev);
err_mmu_gctx_fini:
ivpu_mmu_global_context_fini(vdev);
-err_power_down:
- ivpu_hw_power_down(vdev);
- if (IVPU_WA(d3hot_after_power_off))
- pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+err_shutdown:
+ ivpu_shutdown(vdev);
err_xa_destroy:
xa_destroy(&vdev->db_xa);
xa_destroy(&vdev->submitted_jobs_xa);
@@ -628,9 +613,8 @@
static void ivpu_dev_fini(struct ivpu_device *vdev)
{
ivpu_pm_disable(vdev);
+ ivpu_prepare_for_reset(vdev);
ivpu_shutdown(vdev);
- if (IVPU_WA(d3hot_after_power_off))
- pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
ivpu_jobs_abort_all(vdev);
ivpu_job_done_consumer_fini(vdev);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 7be0500..bb4374d 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
*/
#ifndef __IVPU_DRV_H__
@@ -90,7 +90,6 @@
struct ivpu_wa_table {
bool punit_disabled;
bool clear_runtime_mem;
- bool d3hot_after_power_off;
bool interrupt_clear_with_0;
bool disable_clock_relinquish;
bool disable_d0i3_msg;
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index b290916..094c659 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -21,6 +21,7 @@
u32 (*profiling_freq_get)(struct ivpu_device *vdev);
void (*profiling_freq_drive)(struct ivpu_device *vdev, bool enable);
u32 (*reg_pll_freq_get)(struct ivpu_device *vdev);
+ u32 (*ratio_to_freq)(struct ivpu_device *vdev, u32 ratio);
u32 (*reg_telemetry_offset_get)(struct ivpu_device *vdev);
u32 (*reg_telemetry_size_get)(struct ivpu_device *vdev);
u32 (*reg_telemetry_enable_get)(struct ivpu_device *vdev);
@@ -130,6 +131,11 @@
return vdev->hw->ops->reg_pll_freq_get(vdev);
};
+static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
+{
+ return vdev->hw->ops->ratio_to_freq(vdev, ratio);
+}
+
static inline u32 ivpu_hw_reg_telemetry_offset_get(struct ivpu_device *vdev)
{
return vdev->hw->ops->reg_telemetry_offset_get(vdev);
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 9a0c949..bd25e2d 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
*/
#include "ivpu_drv.h"
@@ -75,7 +75,6 @@
{
vdev->wa.punit_disabled = false;
vdev->wa.clear_runtime_mem = false;
- vdev->wa.d3hot_after_power_off = true;
REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK);
if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) {
@@ -86,7 +85,6 @@
IVPU_PRINT_WA(punit_disabled);
IVPU_PRINT_WA(clear_runtime_mem);
- IVPU_PRINT_WA(d3hot_after_power_off);
IVPU_PRINT_WA(interrupt_clear_with_0);
}
@@ -805,12 +803,12 @@
/* Profiling freq - is a debug feature. Unavailable on VPU 37XX. */
}
-static u32 ivpu_hw_37xx_pll_to_freq(u32 ratio, u32 config)
+static u32 ivpu_hw_37xx_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
{
u32 pll_clock = PLL_REF_CLK_FREQ * ratio;
u32 cpu_clock;
- if ((config & 0xff) == PLL_RATIO_4_3)
+ if ((vdev->hw->config & 0xff) == PLL_RATIO_4_3)
cpu_clock = pll_clock * 2 / 4;
else
cpu_clock = pll_clock * 2 / 5;
@@ -829,7 +827,7 @@
if (!ivpu_is_silicon(vdev))
return PLL_SIMULATION_FREQ;
- return ivpu_hw_37xx_pll_to_freq(pll_curr_ratio, vdev->hw->config);
+ return ivpu_hw_37xx_ratio_to_freq(vdev, pll_curr_ratio);
}
static u32 ivpu_hw_37xx_reg_telemetry_offset_get(struct ivpu_device *vdev)
@@ -1052,6 +1050,7 @@
.profiling_freq_get = ivpu_hw_37xx_profiling_freq_get,
.profiling_freq_drive = ivpu_hw_37xx_profiling_freq_drive,
.reg_pll_freq_get = ivpu_hw_37xx_reg_pll_freq_get,
+ .ratio_to_freq = ivpu_hw_37xx_ratio_to_freq,
.reg_telemetry_offset_get = ivpu_hw_37xx_reg_telemetry_offset_get,
.reg_telemetry_size_get = ivpu_hw_37xx_reg_telemetry_size_get,
.reg_telemetry_enable_get = ivpu_hw_37xx_reg_telemetry_enable_get,
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index e4eddbf..b0b88d4 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -980,6 +980,11 @@
return PLL_RATIO_TO_FREQ(pll_curr_ratio);
}
+static u32 ivpu_hw_40xx_ratio_to_freq(struct ivpu_device *vdev, u32 ratio)
+{
+ return PLL_RATIO_TO_FREQ(ratio);
+}
+
static u32 ivpu_hw_40xx_reg_telemetry_offset_get(struct ivpu_device *vdev)
{
return REGB_RD32(VPU_40XX_BUTTRESS_VPU_TELEMETRY_OFFSET);
@@ -1230,6 +1235,7 @@
.profiling_freq_get = ivpu_hw_40xx_profiling_freq_get,
.profiling_freq_drive = ivpu_hw_40xx_profiling_freq_drive,
.reg_pll_freq_get = ivpu_hw_40xx_reg_pll_freq_get,
+ .ratio_to_freq = ivpu_hw_40xx_ratio_to_freq,
.reg_telemetry_offset_get = ivpu_hw_40xx_reg_telemetry_offset_get,
.reg_telemetry_size_get = ivpu_hw_40xx_reg_telemetry_size_get,
.reg_telemetry_enable_get = ivpu_hw_40xx_reg_telemetry_enable_get,
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 04ac4b9..56ff067 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
*/
#include <linux/genalloc.h>
@@ -501,7 +501,11 @@
spin_lock_init(&ipc->cons_lock);
INIT_LIST_HEAD(&ipc->cons_list);
INIT_LIST_HEAD(&ipc->cb_msg_list);
- drmm_mutex_init(&vdev->drm, &ipc->lock);
+ ret = drmm_mutex_init(&vdev->drm, &ipc->lock);
+ if (ret) {
+ ivpu_err(vdev, "Failed to initialize ipc->lock, ret %d\n", ret);
+ goto err_free_rx;
+ }
ivpu_ipc_reset(vdev);
return 0;
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 91bd640..2e46b32 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -278,7 +278,7 @@
case IVPU_MMU_EVT_F_VMS_FETCH:
return "Fetch of VMS caused external abort";
default:
- return "Unknown CMDQ command";
+ return "Unknown event";
}
}
@@ -286,15 +286,15 @@
{
switch (err) {
case IVPU_MMU_CERROR_NONE:
- return "No CMDQ Error";
+ return "No error";
case IVPU_MMU_CERROR_ILL:
return "Illegal command";
case IVPU_MMU_CERROR_ABT:
- return "External abort on CMDQ read";
+ return "External abort on command queue read";
case IVPU_MMU_CERROR_ATC_INV_SYNC:
return "Sync failed to complete ATS invalidation";
default:
- return "Unknown CMDQ Error";
+ return "Unknown error";
}
}
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 7cce1c9..4f5ea46 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright (C) 2020-2023 Intel Corporation
+ * Copyright (C) 2020-2024 Intel Corporation
*/
#include <linux/highmem.h>
@@ -58,14 +58,11 @@
{
int ret;
- /* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */
- pci_save_state(to_pci_dev(vdev->drm.dev));
+ ivpu_prepare_for_reset(vdev);
ret = ivpu_shutdown(vdev);
if (ret)
- ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret);
-
- pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
+ ivpu_err(vdev, "Failed to shutdown NPU: %d\n", ret);
return ret;
}
@@ -74,10 +71,10 @@
{
int ret;
- pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
- pci_restore_state(to_pci_dev(vdev->drm.dev));
-
retry:
+ pci_restore_state(to_pci_dev(vdev->drm.dev));
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0);
+
ret = ivpu_hw_power_up(vdev);
if (ret) {
ivpu_err(vdev, "Failed to power up HW: %d\n", ret);
@@ -100,6 +97,7 @@
ivpu_mmu_disable(vdev);
err_power_down:
ivpu_hw_power_down(vdev);
+ pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
if (!ivpu_fw_is_cold_boot(vdev)) {
ivpu_pm_prepare_cold_boot(vdev);
diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c
index 1fbc9b9..736c2eb 100644
--- a/drivers/accessibility/speakup/main.c
+++ b/drivers/accessibility/speakup/main.c
@@ -574,7 +574,7 @@
}
attr_ch = get_char(vc, (u_short *)tmp_pos, &spk_attr);
buf[cnt++] = attr_ch;
- while (tmpx < vc->vc_cols - 1) {
+ while (tmpx < vc->vc_cols - 1 && cnt < sizeof(buf) - 1) {
tmp_pos += 2;
tmpx++;
ch = get_char(vc, (u_short *)tmp_pos, &temp);
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 4bfbe55..a40b6f3 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -170,8 +170,8 @@
#define GET_BIT_WIDTH(reg) ((reg)->access_width ? (8 << ((reg)->access_width - 1)) : (reg)->bit_width)
/* Shift and apply the mask for CPC reads/writes */
-#define MASK_VAL(reg, val) ((val) >> ((reg)->bit_offset & \
- GENMASK(((reg)->bit_width), 0)))
+#define MASK_VAL(reg, val) (((val) >> (reg)->bit_offset) & \
+ GENMASK(((reg)->bit_width) - 1, 0))
static ssize_t show_feedback_ctrs(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
@@ -1002,14 +1002,14 @@
}
*val = 0;
+ size = GET_BIT_WIDTH(reg);
if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
- u32 width = GET_BIT_WIDTH(reg);
u32 val_u32;
acpi_status status;
status = acpi_os_read_port((acpi_io_address)reg->address,
- &val_u32, width);
+ &val_u32, size);
if (ACPI_FAILURE(status)) {
pr_debug("Error: Failed to read SystemIO port %llx\n",
reg->address);
@@ -1018,17 +1018,22 @@
*val = val_u32;
return 0;
- } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
+ } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) {
+ /*
+ * For registers in PCC space, the register size is determined
+ * by the bit width field; the access size is used to indicate
+ * the PCC subspace id.
+ */
+ size = reg->bit_width;
vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
+ }
else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
vaddr = reg_res->sys_mem_vaddr;
else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE)
return cpc_read_ffh(cpu, reg, val);
else
return acpi_os_read_memory((acpi_physical_address)reg->address,
- val, reg->bit_width);
-
- size = GET_BIT_WIDTH(reg);
+ val, size);
switch (size) {
case 8:
@@ -1044,8 +1049,13 @@
*val = readq_relaxed(vaddr);
break;
default:
- pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n",
- reg->bit_width, pcc_ss_id);
+ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+ pr_debug("Error: Cannot read %u bit width from system memory: 0x%llx\n",
+ size, reg->address);
+ } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
+ pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n",
+ size, pcc_ss_id);
+ }
return -EFAULT;
}
@@ -1063,12 +1073,13 @@
int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
struct cpc_reg *reg = ®_res->cpc_entry.reg;
+ size = GET_BIT_WIDTH(reg);
+
if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
- u32 width = GET_BIT_WIDTH(reg);
acpi_status status;
status = acpi_os_write_port((acpi_io_address)reg->address,
- (u32)val, width);
+ (u32)val, size);
if (ACPI_FAILURE(status)) {
pr_debug("Error: Failed to write SystemIO port %llx\n",
reg->address);
@@ -1076,17 +1087,22 @@
}
return 0;
- } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0)
+ } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) {
+ /*
+ * For registers in PCC space, the register size is determined
+ * by the bit width field; the access size is used to indicate
+ * the PCC subspace id.
+ */
+ size = reg->bit_width;
vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id);
+ }
else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
vaddr = reg_res->sys_mem_vaddr;
else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE)
return cpc_write_ffh(cpu, reg, val);
else
return acpi_os_write_memory((acpi_physical_address)reg->address,
- val, reg->bit_width);
-
- size = GET_BIT_WIDTH(reg);
+ val, size);
if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
val = MASK_VAL(reg, val);
@@ -1105,8 +1121,13 @@
writeq_relaxed(val, vaddr);
break;
default:
- pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n",
- reg->bit_width, pcc_ss_id);
+ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+ pr_debug("Error: Cannot write %u bit width to system memory: 0x%llx\n",
+ size, reg->address);
+ } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
+ pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n",
+ size, pcc_ss_id);
+ }
ret_val = -EFAULT;
break;
}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 7c157bf..d146432 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1843,7 +1843,8 @@
if (dep->honor_dep)
adev->flags.honor_deps = 1;
- adev->dep_unmet++;
+ if (!dep->met)
+ adev->dep_unmet++;
}
}
}
diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c
index cd84af2..dd0b40b 100644
--- a/drivers/acpi/x86/s2idle.c
+++ b/drivers/acpi/x86/s2idle.c
@@ -492,16 +492,14 @@
unsigned int func_mask;
/*
- * Avoid evaluating the same _DSM function for two
- * different UUIDs and prioritize the MSFT one.
+ * Log a message if the _DSM function sets for two
+ * different UUIDs overlap.
*/
func_mask = lps0_dsm_func_mask & lps0_dsm_func_mask_microsoft;
- if (func_mask) {
+ if (func_mask)
acpi_handle_info(adev->handle,
"Duplicate LPS0 _DSM functions (mask: 0x%x)\n",
func_mask);
- lps0_dsm_func_mask &= ~func_mask;
- }
}
}
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index bad28cf..dd6923d 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -1708,8 +1708,10 @@
size_t object_size = 0;
read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset);
- if (offset > buffer->data_size || read_size < sizeof(*hdr))
+ if (offset > buffer->data_size || read_size < sizeof(*hdr) ||
+ !IS_ALIGNED(offset, sizeof(u32)))
return 0;
+
if (u) {
if (copy_from_user(object, u + offset, read_size))
return 0;
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 562302e..6548f10 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -666,6 +666,87 @@
module_param(mobile_lpm_policy, int, 0644);
MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets");
+static char *ahci_mask_port_map;
+module_param_named(mask_port_map, ahci_mask_port_map, charp, 0444);
+MODULE_PARM_DESC(mask_port_map,
+ "32-bits port map masks to ignore controllers ports. "
+ "Valid values are: "
+ "\"<mask>\" to apply the same mask to all AHCI controller "
+ "devices, and \"<pci_dev>=<mask>,<pci_dev>=<mask>,...\" to "
+ "specify different masks for the controllers specified, "
+ "where <pci_dev> is the PCI ID of an AHCI controller in the "
+ "form \"domain:bus:dev.func\"");
+
+static void ahci_apply_port_map_mask(struct device *dev,
+ struct ahci_host_priv *hpriv, char *mask_s)
+{
+ unsigned int mask;
+
+ if (kstrtouint(mask_s, 0, &mask)) {
+ dev_err(dev, "Invalid port map mask\n");
+ return;
+ }
+
+ hpriv->mask_port_map = mask;
+}
+
+static void ahci_get_port_map_mask(struct device *dev,
+ struct ahci_host_priv *hpriv)
+{
+ char *param, *end, *str, *mask_s;
+ char *name;
+
+ if (!strlen(ahci_mask_port_map))
+ return;
+
+ str = kstrdup(ahci_mask_port_map, GFP_KERNEL);
+ if (!str)
+ return;
+
+ /* Handle single mask case */
+ if (!strchr(str, '=')) {
+ ahci_apply_port_map_mask(dev, hpriv, str);
+ goto free;
+ }
+
+ /*
+ * Mask list case: parse the parameter to apply the mask only if
+ * the device name matches.
+ */
+ param = str;
+ end = param + strlen(param);
+ while (param && param < end && *param) {
+ name = param;
+ param = strchr(name, '=');
+ if (!param)
+ break;
+
+ *param = '\0';
+ param++;
+ if (param >= end)
+ break;
+
+ if (strcmp(dev_name(dev), name) != 0) {
+ param = strchr(param, ',');
+ if (param)
+ param++;
+ continue;
+ }
+
+ mask_s = param;
+ param = strchr(mask_s, ',');
+ if (param) {
+ *param = '\0';
+ param++;
+ }
+
+ ahci_apply_port_map_mask(dev, hpriv, mask_s);
+ }
+
+free:
+ kfree(str);
+}
+
static void ahci_pci_save_initial_config(struct pci_dev *pdev,
struct ahci_host_priv *hpriv)
{
@@ -688,6 +769,10 @@
"Disabling your PATA port. Use the boot option 'ahci.marvell_enable=0' to avoid this.\n");
}
+ /* Handle port map masks passed as module parameter. */
+ if (ahci_mask_port_map)
+ ahci_get_port_map_mask(&pdev->dev, hpriv);
+
ahci_save_initial_config(&pdev->dev, hpriv);
}
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index be3412c..c449d60 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2539,7 +2539,7 @@
bool cdl_enabled;
u64 val;
- if (ata_id_major_version(dev->id) < 12)
+ if (ata_id_major_version(dev->id) < 11)
goto not_supported;
if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE) ||
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 2f4c588..e954976 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -4745,7 +4745,7 @@
* bail out.
*/
if (ap->pflags & ATA_PFLAG_SUSPENDED)
- goto unlock;
+ goto unlock_ap;
if (!sdev)
continue;
@@ -4758,7 +4758,7 @@
if (do_resume) {
ret = scsi_resume_device(sdev);
if (ret == -EWOULDBLOCK)
- goto unlock;
+ goto unlock_scan;
dev->flags &= ~ATA_DFLAG_RESUMING;
}
ret = scsi_rescan_device(sdev);
@@ -4766,12 +4766,13 @@
spin_lock_irqsave(ap->lock, flags);
if (ret)
- goto unlock;
+ goto unlock_ap;
}
}
-unlock:
+unlock_ap:
spin_unlock_irqrestore(ap->lock, flags);
+unlock_scan:
mutex_unlock(&ap->scsi_scan_mutex);
/* Reschedule with a delay if scsi_rescan_device() returned an error */
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 5cb425f..0a34dd3 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -2839,6 +2839,43 @@
EXPORT_SYMBOL_GPL(regmap_read);
/**
+ * regmap_read_bypassed() - Read a value from a single register direct
+ * from the device, bypassing the cache
+ *
+ * @map: Register map to read from
+ * @reg: Register to be read from
+ * @val: Pointer to store read value
+ *
+ * A value of zero will be returned on success, a negative errno will
+ * be returned in error cases.
+ */
+int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val)
+{
+ int ret;
+ bool bypass, cache_only;
+
+ if (!IS_ALIGNED(reg, map->reg_stride))
+ return -EINVAL;
+
+ map->lock(map->lock_arg);
+
+ bypass = map->cache_bypass;
+ cache_only = map->cache_only;
+ map->cache_bypass = true;
+ map->cache_only = false;
+
+ ret = _regmap_read(map, reg, val);
+
+ map->cache_bypass = bypass;
+ map->cache_only = cache_only;
+
+ map->unlock(map->lock_arg);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(regmap_read_bypassed);
+
+/**
* regmap_raw_read() - Read raw data from the device
*
* @map: Register map to read from
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index bea3d5c..374e4ef 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2177,7 +2177,8 @@
.max_hw_sectors = p->max_sectors,
.chunk_sectors = p->chunk_sectors,
.virt_boundary_mask = p->virt_boundary_mask,
-
+ .max_segments = USHRT_MAX,
+ .max_segment_size = UINT_MAX,
};
struct gendisk *disk;
int ret = -EINVAL;
diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index ac8ebcc..812fd2a 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -380,8 +380,10 @@
switch (data->cd_info.state) {
case HCI_DEVCOREDUMP_IDLE:
err = hci_devcd_init(hdev, MTK_COREDUMP_SIZE);
- if (err < 0)
+ if (err < 0) {
+ kfree_skb(skb);
break;
+ }
data->cd_info.cnt = 0;
/* It is supposed coredump can be done within 5 seconds */
@@ -407,9 +409,6 @@
break;
}
- if (err < 0)
- kfree_skb(skb);
-
return err;
}
EXPORT_SYMBOL_GPL(btmtk_process_coredump);
diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 19cfc34..216826c 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -15,6 +15,8 @@
#define VERSION "0.1"
+#define QCA_BDADDR_DEFAULT (&(bdaddr_t) {{ 0xad, 0x5a, 0x00, 0x00, 0x00, 0x00 }})
+
int qca_read_soc_version(struct hci_dev *hdev, struct qca_btsoc_version *ver,
enum qca_btsoc_type soc_type)
{
@@ -612,6 +614,38 @@
}
EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome);
+static int qca_check_bdaddr(struct hci_dev *hdev)
+{
+ struct hci_rp_read_bd_addr *bda;
+ struct sk_buff *skb;
+ int err;
+
+ if (bacmp(&hdev->public_addr, BDADDR_ANY))
+ return 0;
+
+ skb = __hci_cmd_sync(hdev, HCI_OP_READ_BD_ADDR, 0, NULL,
+ HCI_INIT_TIMEOUT);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
+ bt_dev_err(hdev, "Failed to read device address (%d)", err);
+ return err;
+ }
+
+ if (skb->len != sizeof(*bda)) {
+ bt_dev_err(hdev, "Device address length mismatch");
+ kfree_skb(skb);
+ return -EIO;
+ }
+
+ bda = (struct hci_rp_read_bd_addr *)skb->data;
+ if (!bacmp(&bda->bdaddr, QCA_BDADDR_DEFAULT))
+ set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+
+ kfree_skb(skb);
+
+ return 0;
+}
+
static void qca_generate_hsp_nvm_name(char *fwname, size_t max_size,
struct qca_btsoc_version ver, u8 rom_ver, u16 bid)
{
@@ -818,6 +852,10 @@
break;
}
+ err = qca_check_bdaddr(hdev);
+ if (err)
+ return err;
+
bt_dev_info(hdev, "QCA setup on UART is completed");
return 0;
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 06e915b..e3946f7 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -542,6 +542,8 @@
/* Realtek 8852BE Bluetooth devices */
{ USB_DEVICE(0x0cb8, 0xc559), .driver_info = BTUSB_REALTEK |
BTUSB_WIDEBAND_SPEECH },
+ { USB_DEVICE(0x0bda, 0x4853), .driver_info = BTUSB_REALTEK |
+ BTUSB_WIDEBAND_SPEECH },
{ USB_DEVICE(0x0bda, 0x887b), .driver_info = BTUSB_REALTEK |
BTUSB_WIDEBAND_SPEECH },
{ USB_DEVICE(0x0bda, 0xb85b), .driver_info = BTUSB_REALTEK |
@@ -3480,13 +3482,12 @@
static void btusb_coredump_qca(struct hci_dev *hdev)
{
+ int err;
static const u8 param[] = { 0x26 };
- struct sk_buff *skb;
- skb = __hci_cmd_sync(hdev, 0xfc0c, 1, param, HCI_CMD_TIMEOUT);
- if (IS_ERR(skb))
- bt_dev_err(hdev, "%s: triggle crash failed (%ld)", __func__, PTR_ERR(skb));
- kfree_skb(skb);
+ err = __hci_cmd_send(hdev, 0xfc0c, 1, param);
+ if (err < 0)
+ bt_dev_err(hdev, "%s: triggle crash failed (%d)", __func__, err);
}
/*
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index ecbc52e..0c9c9ee 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -1672,6 +1672,9 @@
struct hci_uart *hu = hci_get_drvdata(hdev);
bool wakeup;
+ if (!hu->serdev)
+ return true;
+
/* BT SoC attached through the serial bus is handled by the serdev driver.
* So we need to use the device handle of the serdev driver to get the
* status of device may wakeup.
@@ -1905,8 +1908,6 @@
case QCA_WCN6750:
case QCA_WCN6855:
case QCA_WCN7850:
- set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
-
qcadev = serdev_device_get_drvdata(hu->serdev);
if (qcadev->bdaddr_property_broken)
set_bit(HCI_QUIRK_BDADDR_PROPERTY_BROKEN, &hdev->quirks);
@@ -1957,8 +1958,10 @@
qca_debugfs_init(hdev);
hu->hdev->hw_error = qca_hw_error;
hu->hdev->cmd_timeout = qca_cmd_timeout;
- if (device_can_wakeup(hu->serdev->ctrl->dev.parent))
- hu->hdev->wakeup = qca_wakeup;
+ if (hu->serdev) {
+ if (device_can_wakeup(hu->serdev->ctrl->dev.parent))
+ hu->hdev->wakeup = qca_wakeup;
+ }
} else if (ret == -ENOENT) {
/* No patch/nvm-config found, run with original fw/config */
set_bit(QCA_ROM_FW, &qca->flags);
@@ -2329,16 +2332,21 @@
(data->soc_type == QCA_WCN6750 ||
data->soc_type == QCA_WCN6855)) {
dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n");
- power_ctrl_enabled = false;
+ return PTR_ERR(qcadev->bt_en);
}
+ if (!qcadev->bt_en)
+ power_ctrl_enabled = false;
+
qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl",
GPIOD_IN);
if (IS_ERR(qcadev->sw_ctrl) &&
(data->soc_type == QCA_WCN6750 ||
data->soc_type == QCA_WCN6855 ||
- data->soc_type == QCA_WCN7850))
- dev_warn(&serdev->dev, "failed to acquire SW_CTRL gpio\n");
+ data->soc_type == QCA_WCN7850)) {
+ dev_err(&serdev->dev, "failed to acquire SW_CTRL gpio\n");
+ return PTR_ERR(qcadev->sw_ctrl);
+ }
qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL);
if (IS_ERR(qcadev->susclk)) {
@@ -2357,10 +2365,13 @@
qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable",
GPIOD_OUT_LOW);
if (IS_ERR(qcadev->bt_en)) {
- dev_warn(&serdev->dev, "failed to acquire enable gpio\n");
- power_ctrl_enabled = false;
+ dev_err(&serdev->dev, "failed to acquire enable gpio\n");
+ return PTR_ERR(qcadev->bt_en);
}
+ if (!qcadev->bt_en)
+ power_ctrl_enabled = false;
+
qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL);
if (IS_ERR(qcadev->susclk)) {
dev_warn(&serdev->dev, "failed to acquire clk\n");
diff --git a/drivers/cache/sifive_ccache.c b/drivers/cache/sifive_ccache.c
index 89ed6cd6..e9cc8b4 100644
--- a/drivers/cache/sifive_ccache.c
+++ b/drivers/cache/sifive_ccache.c
@@ -15,6 +15,8 @@
#include <linux/of_address.h>
#include <linux/device.h>
#include <linux/bitfield.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
#include <asm/cacheflush.h>
#include <asm/cacheinfo.h>
#include <asm/dma-noncoherent.h>
@@ -247,13 +249,49 @@
return IRQ_HANDLED;
}
+static int sifive_ccache_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ unsigned long quirks;
+ int intr_num, rc;
+
+ quirks = (unsigned long)device_get_match_data(dev);
+
+ intr_num = platform_irq_count(pdev);
+ if (!intr_num)
+ return dev_err_probe(dev, -ENODEV, "No interrupts property\n");
+
+ for (int i = 0; i < intr_num; i++) {
+ if (i == DATA_UNCORR && (quirks & QUIRK_BROKEN_DATA_UNCORR))
+ continue;
+
+ g_irq[i] = platform_get_irq(pdev, i);
+ if (g_irq[i] < 0)
+ return g_irq[i];
+
+ rc = devm_request_irq(dev, g_irq[i], ccache_int_handler, 0, "ccache_ecc", NULL);
+ if (rc)
+ return dev_err_probe(dev, rc, "Could not request IRQ %d\n", g_irq[i]);
+ }
+
+ return 0;
+}
+
+static struct platform_driver sifive_ccache_driver = {
+ .probe = sifive_ccache_probe,
+ .driver = {
+ .name = "sifive_ccache",
+ .of_match_table = sifive_ccache_ids,
+ },
+};
+
static int __init sifive_ccache_init(void)
{
struct device_node *np;
struct resource res;
- int i, rc, intr_num;
const struct of_device_id *match;
unsigned long quirks;
+ int rc;
np = of_find_matching_node_and_match(NULL, sifive_ccache_ids, &match);
if (!np)
@@ -277,28 +315,6 @@
goto err_unmap;
}
- intr_num = of_property_count_u32_elems(np, "interrupts");
- if (!intr_num) {
- pr_err("No interrupts property\n");
- rc = -ENODEV;
- goto err_unmap;
- }
-
- for (i = 0; i < intr_num; i++) {
- g_irq[i] = irq_of_parse_and_map(np, i);
-
- if (i == DATA_UNCORR && (quirks & QUIRK_BROKEN_DATA_UNCORR))
- continue;
-
- rc = request_irq(g_irq[i], ccache_int_handler, 0, "ccache_ecc",
- NULL);
- if (rc) {
- pr_err("Could not request IRQ %d\n", g_irq[i]);
- goto err_free_irq;
- }
- }
- of_node_put(np);
-
#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
if (quirks & QUIRK_NONSTANDARD_CACHE_OPS) {
riscv_cbom_block_size = SIFIVE_CCACHE_LINE_SIZE;
@@ -315,11 +331,15 @@
#ifdef CONFIG_DEBUG_FS
setup_sifive_debug();
#endif
+
+ rc = platform_driver_register(&sifive_ccache_driver);
+ if (rc)
+ goto err_unmap;
+
+ of_node_put(np);
+
return 0;
-err_free_irq:
- while (--i >= 0)
- free_irq(g_irq[i], NULL);
err_unmap:
iounmap(ccache_base);
err_node_put:
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 456be28..2597cb4 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -702,7 +702,7 @@
static void __cold _credit_init_bits(size_t bits)
{
- static struct execute_work set_ready;
+ static DECLARE_WORK(set_ready, crng_set_ready);
unsigned int new, orig, add;
unsigned long flags;
@@ -718,8 +718,8 @@
if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) {
crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */
- if (static_key_initialized)
- execute_in_process_context(crng_set_ready, &set_ready);
+ if (static_key_initialized && system_unbound_wq)
+ queue_work(system_unbound_wq, &set_ready);
atomic_notifier_call_chain(&random_ready_notifier, 0, NULL);
wake_up_interruptible(&crng_init_wait);
kill_fasync(&fasync, SIGIO, POLL_IN);
@@ -890,8 +890,8 @@
/*
* If we were initialized by the cpu or bootloader before jump labels
- * are initialized, then we should enable the static branch here, where
- * it's guaranteed that jump labels have been initialized.
+ * or workqueues are initialized, then we should enable the static
+ * branch here, where it's guaranteed that these have been initialized.
*/
if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY)
crng_set_ready(NULL);
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 25371c9..8cca52b 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -37,6 +37,10 @@
static HLIST_HEAD(clk_orphan_list);
static LIST_HEAD(clk_notifier_list);
+/* List of registered clks that use runtime PM */
+static HLIST_HEAD(clk_rpm_list);
+static DEFINE_MUTEX(clk_rpm_list_lock);
+
static const struct hlist_head *all_lists[] = {
&clk_root_list,
&clk_orphan_list,
@@ -59,6 +63,7 @@
struct clk_hw *hw;
struct module *owner;
struct device *dev;
+ struct hlist_node rpm_node;
struct device_node *of_node;
struct clk_core *parent;
struct clk_parent_map *parents;
@@ -122,6 +127,89 @@
pm_runtime_put_sync(core->dev);
}
+/**
+ * clk_pm_runtime_get_all() - Runtime "get" all clk provider devices
+ *
+ * Call clk_pm_runtime_get() on all runtime PM enabled clks in the clk tree so
+ * that disabling unused clks avoids a deadlock where a device is runtime PM
+ * resuming/suspending and the runtime PM callback is trying to grab the
+ * prepare_lock for something like clk_prepare_enable() while
+ * clk_disable_unused_subtree() holds the prepare_lock and is trying to runtime
+ * PM resume/suspend the device as well.
+ *
+ * Context: Acquires the 'clk_rpm_list_lock' and returns with the lock held on
+ * success. Otherwise the lock is released on failure.
+ *
+ * Return: 0 on success, negative errno otherwise.
+ */
+static int clk_pm_runtime_get_all(void)
+{
+ int ret;
+ struct clk_core *core, *failed;
+
+ /*
+ * Grab the list lock to prevent any new clks from being registered
+ * or unregistered until clk_pm_runtime_put_all().
+ */
+ mutex_lock(&clk_rpm_list_lock);
+
+ /*
+ * Runtime PM "get" all the devices that are needed for the clks
+ * currently registered. Do this without holding the prepare_lock, to
+ * avoid the deadlock.
+ */
+ hlist_for_each_entry(core, &clk_rpm_list, rpm_node) {
+ ret = clk_pm_runtime_get(core);
+ if (ret) {
+ failed = core;
+ pr_err("clk: Failed to runtime PM get '%s' for clk '%s'\n",
+ dev_name(failed->dev), failed->name);
+ goto err;
+ }
+ }
+
+ return 0;
+
+err:
+ hlist_for_each_entry(core, &clk_rpm_list, rpm_node) {
+ if (core == failed)
+ break;
+
+ clk_pm_runtime_put(core);
+ }
+ mutex_unlock(&clk_rpm_list_lock);
+
+ return ret;
+}
+
+/**
+ * clk_pm_runtime_put_all() - Runtime "put" all clk provider devices
+ *
+ * Put the runtime PM references taken in clk_pm_runtime_get_all() and release
+ * the 'clk_rpm_list_lock'.
+ */
+static void clk_pm_runtime_put_all(void)
+{
+ struct clk_core *core;
+
+ hlist_for_each_entry(core, &clk_rpm_list, rpm_node)
+ clk_pm_runtime_put(core);
+ mutex_unlock(&clk_rpm_list_lock);
+}
+
+static void clk_pm_runtime_init(struct clk_core *core)
+{
+ struct device *dev = core->dev;
+
+ if (dev && pm_runtime_enabled(dev)) {
+ core->rpm_enabled = true;
+
+ mutex_lock(&clk_rpm_list_lock);
+ hlist_add_head(&core->rpm_node, &clk_rpm_list);
+ mutex_unlock(&clk_rpm_list_lock);
+ }
+}
+
/*** locking ***/
static void clk_prepare_lock(void)
{
@@ -1381,9 +1469,6 @@
if (core->flags & CLK_IGNORE_UNUSED)
return;
- if (clk_pm_runtime_get(core))
- return;
-
if (clk_core_is_prepared(core)) {
trace_clk_unprepare(core);
if (core->ops->unprepare_unused)
@@ -1392,8 +1477,6 @@
core->ops->unprepare(core->hw);
trace_clk_unprepare_complete(core);
}
-
- clk_pm_runtime_put(core);
}
static void __init clk_disable_unused_subtree(struct clk_core *core)
@@ -1409,9 +1492,6 @@
if (core->flags & CLK_OPS_PARENT_ENABLE)
clk_core_prepare_enable(core->parent);
- if (clk_pm_runtime_get(core))
- goto unprepare_out;
-
flags = clk_enable_lock();
if (core->enable_count)
@@ -1436,8 +1516,6 @@
unlock_out:
clk_enable_unlock(flags);
- clk_pm_runtime_put(core);
-unprepare_out:
if (core->flags & CLK_OPS_PARENT_ENABLE)
clk_core_disable_unprepare(core->parent);
}
@@ -1453,6 +1531,7 @@
static int __init clk_disable_unused(void)
{
struct clk_core *core;
+ int ret;
if (clk_ignore_unused) {
pr_warn("clk: Not disabling unused clocks\n");
@@ -1461,6 +1540,13 @@
pr_info("clk: Disabling unused clocks\n");
+ ret = clk_pm_runtime_get_all();
+ if (ret)
+ return ret;
+ /*
+ * Grab the prepare lock to keep the clk topology stable while iterating
+ * over clks.
+ */
clk_prepare_lock();
hlist_for_each_entry(core, &clk_root_list, child_node)
@@ -1477,6 +1563,8 @@
clk_prepare_unlock();
+ clk_pm_runtime_put_all();
+
return 0;
}
late_initcall_sync(clk_disable_unused);
@@ -3252,9 +3340,7 @@
{
struct clk_core *child;
- clk_pm_runtime_get(c);
clk_summary_show_one(s, c, level);
- clk_pm_runtime_put(c);
hlist_for_each_entry(child, &c->children, child_node)
clk_summary_show_subtree(s, child, level + 1);
@@ -3264,11 +3350,15 @@
{
struct clk_core *c;
struct hlist_head **lists = s->private;
+ int ret;
seq_puts(s, " enable prepare protect duty hardware connection\n");
seq_puts(s, " clock count count count rate accuracy phase cycle enable consumer id\n");
seq_puts(s, "---------------------------------------------------------------------------------------------------------------------------------------------\n");
+ ret = clk_pm_runtime_get_all();
+ if (ret)
+ return ret;
clk_prepare_lock();
@@ -3277,6 +3367,7 @@
clk_summary_show_subtree(s, c, 0);
clk_prepare_unlock();
+ clk_pm_runtime_put_all();
return 0;
}
@@ -3324,8 +3415,14 @@
struct clk_core *c;
bool first_node = true;
struct hlist_head **lists = s->private;
+ int ret;
+
+ ret = clk_pm_runtime_get_all();
+ if (ret)
+ return ret;
seq_putc(s, '{');
+
clk_prepare_lock();
for (; *lists; lists++) {
@@ -3338,6 +3435,7 @@
}
clk_prepare_unlock();
+ clk_pm_runtime_put_all();
seq_puts(s, "}\n");
return 0;
@@ -3981,8 +4079,6 @@
}
clk_core_reparent_orphans_nolock();
-
- kref_init(&core->ref);
out:
clk_pm_runtime_put(core);
unlock:
@@ -4211,6 +4307,22 @@
kfree(core->parents);
}
+/* Free memory allocated for a struct clk_core */
+static void __clk_release(struct kref *ref)
+{
+ struct clk_core *core = container_of(ref, struct clk_core, ref);
+
+ if (core->rpm_enabled) {
+ mutex_lock(&clk_rpm_list_lock);
+ hlist_del(&core->rpm_node);
+ mutex_unlock(&clk_rpm_list_lock);
+ }
+
+ clk_core_free_parent_map(core);
+ kfree_const(core->name);
+ kfree(core);
+}
+
static struct clk *
__clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw)
{
@@ -4231,6 +4343,8 @@
goto fail_out;
}
+ kref_init(&core->ref);
+
core->name = kstrdup_const(init->name, GFP_KERNEL);
if (!core->name) {
ret = -ENOMEM;
@@ -4243,9 +4357,8 @@
}
core->ops = init->ops;
- if (dev && pm_runtime_enabled(dev))
- core->rpm_enabled = true;
core->dev = dev;
+ clk_pm_runtime_init(core);
core->of_node = np;
if (dev && dev->driver)
core->owner = dev->driver->owner;
@@ -4285,12 +4398,10 @@
hw->clk = NULL;
fail_create_clk:
- clk_core_free_parent_map(core);
fail_parents:
fail_ops:
- kfree_const(core->name);
fail_name:
- kfree(core);
+ kref_put(&core->ref, __clk_release);
fail_out:
return ERR_PTR(ret);
}
@@ -4370,18 +4481,6 @@
}
EXPORT_SYMBOL_GPL(of_clk_hw_register);
-/* Free memory allocated for a clock. */
-static void __clk_release(struct kref *ref)
-{
- struct clk_core *core = container_of(ref, struct clk_core, ref);
-
- lockdep_assert_held(&prepare_lock);
-
- clk_core_free_parent_map(core);
- kfree_const(core->name);
- kfree(core);
-}
-
/*
* Empty clk_ops for unregistered clocks. These are used temporarily
* after clk_unregister() was called on a clock and until last clock
@@ -4472,7 +4571,8 @@
if (ops == &clk_nodrv_ops) {
pr_err("%s: unregistered clock: %s\n", __func__,
clk->core->name);
- goto unlock;
+ clk_prepare_unlock();
+ return;
}
/*
* Assign empty clock ops for consumers that might still hold
@@ -4506,11 +4606,10 @@
if (clk->core->protect_count)
pr_warn("%s: unregistering protected clock: %s\n",
__func__, clk->core->name);
+ clk_prepare_unlock();
kref_put(&clk->core->ref, __clk_release);
free_clk(clk);
-unlock:
- clk_prepare_unlock();
}
EXPORT_SYMBOL_GPL(clk_unregister);
@@ -4669,13 +4768,11 @@
if (clk->min_rate > 0 || clk->max_rate < ULONG_MAX)
clk_set_rate_range_nolock(clk, 0, ULONG_MAX);
- owner = clk->core->owner;
- kref_put(&clk->core->ref, __clk_release);
-
clk_prepare_unlock();
+ owner = clk->core->owner;
+ kref_put(&clk->core->ref, __clk_release);
module_put(owner);
-
free_clk(clk);
}
diff --git a/drivers/clk/mediatek/clk-mt7988-infracfg.c b/drivers/clk/mediatek/clk-mt7988-infracfg.c
index 449041f..c8c023a 100644
--- a/drivers/clk/mediatek/clk-mt7988-infracfg.c
+++ b/drivers/clk/mediatek/clk-mt7988-infracfg.c
@@ -156,7 +156,7 @@
GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P1, "infra_pcie_peri_ck_26m_ck_p1",
"csw_infra_f26m_sel", 8),
GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P2, "infra_pcie_peri_ck_26m_ck_p2",
- "csw_infra_f26m_sel", 9),
+ "infra_pcie_peri_ck_26m_ck_p3", 9),
GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P3, "infra_pcie_peri_ck_26m_ck_p3",
"csw_infra_f26m_sel", 10),
/* INFRA1 */
diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c
index 2e55368..bd37ab4 100644
--- a/drivers/clk/mediatek/clk-mtk.c
+++ b/drivers/clk/mediatek/clk-mtk.c
@@ -13,6 +13,7 @@
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include "clk-mtk.h"
@@ -494,6 +495,16 @@
return IS_ERR(base) ? PTR_ERR(base) : -ENOMEM;
}
+
+ devm_pm_runtime_enable(&pdev->dev);
+ /*
+ * Do a pm_runtime_resume_and_get() to workaround a possible
+ * deadlock between clk_register() and the genpd framework.
+ */
+ r = pm_runtime_resume_and_get(&pdev->dev);
+ if (r)
+ return r;
+
/* Calculate how many clk_hw_onecell_data entries to allocate */
num_clks = mcd->num_clks + mcd->num_composite_clks;
num_clks += mcd->num_fixed_clks + mcd->num_factor_clks;
@@ -574,6 +585,8 @@
goto unregister_clks;
}
+ pm_runtime_put(&pdev->dev);
+
return r;
unregister_clks:
@@ -604,6 +617,8 @@
free_base:
if (mcd->shared_io && base)
iounmap(base);
+
+ pm_runtime_put(&pdev->dev);
return r;
}
diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c
index 8602c02..45c5255 100644
--- a/drivers/clk/qcom/clk-smd-rpm.c
+++ b/drivers/clk/qcom/clk-smd-rpm.c
@@ -768,6 +768,7 @@
static const struct rpm_smd_clk_desc rpm_clk_msm8976 = {
.clks = msm8976_clks,
+ .num_clks = ARRAY_SIZE(msm8976_clks),
.icc_clks = bimc_pcnoc_snoc_smmnoc_icc_clks,
.num_icc_clks = ARRAY_SIZE(bimc_pcnoc_snoc_smmnoc_icc_clks),
};
diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c
index e7a4068..df9618a 100644
--- a/drivers/clk/qcom/gdsc.c
+++ b/drivers/clk/qcom/gdsc.c
@@ -487,9 +487,14 @@
if (!scs[i] || !scs[i]->supply)
continue;
- scs[i]->rsupply = devm_regulator_get(dev, scs[i]->supply);
- if (IS_ERR(scs[i]->rsupply))
- return PTR_ERR(scs[i]->rsupply);
+ scs[i]->rsupply = devm_regulator_get_optional(dev, scs[i]->supply);
+ if (IS_ERR(scs[i]->rsupply)) {
+ ret = PTR_ERR(scs[i]->rsupply);
+ if (ret != -ENODEV)
+ return ret;
+
+ scs[i]->rsupply = NULL;
+ }
}
data->num_domains = num;
diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c
index 3484e6c..503c6f5 100644
--- a/drivers/clk/samsung/clk-exynos-clkout.c
+++ b/drivers/clk/samsung/clk-exynos-clkout.c
@@ -13,9 +13,9 @@
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/pm.h>
-#include <linux/property.h>
#define EXYNOS_CLKOUT_NR_CLKS 1
#define EXYNOS_CLKOUT_PARENTS 32
@@ -84,17 +84,24 @@
static int exynos_clkout_match_parent_dev(struct device *dev, u32 *mux_mask)
{
const struct exynos_clkout_variant *variant;
+ const struct of_device_id *match;
if (!dev->parent) {
dev_err(dev, "not instantiated from MFD\n");
return -EINVAL;
}
- variant = device_get_match_data(dev->parent);
- if (!variant) {
+ /*
+ * 'exynos_clkout_ids' arrays is not the ids array matched by
+ * the dev->parent driver, so of_device_get_match_data() or
+ * device_get_match_data() cannot be used here.
+ */
+ match = of_match_device(exynos_clkout_ids, dev->parent);
+ if (!match) {
dev_err(dev, "cannot match parent device\n");
return -EINVAL;
}
+ variant = match->data;
*mux_mask = variant->mux_mask;
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
index 8951ffc..6a4b2b9 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
@@ -182,6 +182,8 @@
&ccu_nkm_ops,
CLK_SET_RATE_UNGATE | CLK_SET_RATE_PARENT),
.features = CCU_FEATURE_CLOSEST_RATE,
+ .min_rate = 500000000,
+ .max_rate = 1400000000,
},
};
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c
index 42568c6..892df80 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c
@@ -1181,11 +1181,18 @@
SUN50I_H6_USB3_CLK_REG,
};
+static struct ccu_mux_nb sun50i_h6_cpu_nb = {
+ .common = &cpux_clk.common,
+ .cm = &cpux_clk.mux,
+ .delay_us = 1,
+ .bypass_index = 0, /* index of 24 MHz oscillator */
+};
+
static int sun50i_h6_ccu_probe(struct platform_device *pdev)
{
void __iomem *reg;
+ int i, ret;
u32 val;
- int i;
reg = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(reg))
@@ -1252,7 +1259,15 @@
val |= BIT(24);
writel(val, reg + SUN50I_H6_HDMI_CEC_CLK_REG);
- return devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc);
+ ret = devm_sunxi_ccu_probe(&pdev->dev, reg, &sun50i_h6_ccu_desc);
+ if (ret)
+ return ret;
+
+ /* Reparent CPU during PLL CPUX rate changes */
+ ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk,
+ &sun50i_h6_cpu_nb);
+
+ return 0;
}
static const struct of_device_id sun50i_h6_ccu_ids[] = {
diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c
index 8babce5..ac0091b 100644
--- a/drivers/clk/sunxi-ng/ccu_common.c
+++ b/drivers/clk/sunxi-ng/ccu_common.c
@@ -44,6 +44,16 @@
unsigned long current_rate,
unsigned long best_rate)
{
+ unsigned long min_rate, max_rate;
+
+ clk_hw_get_rate_range(&common->hw, &min_rate, &max_rate);
+
+ if (current_rate > max_rate)
+ return false;
+
+ if (current_rate < min_rate)
+ return false;
+
if (common->features & CCU_FEATURE_CLOSEST_RATE)
return abs(current_rate - target_rate) < abs(best_rate - target_rate);
@@ -122,6 +132,7 @@
for (i = 0; i < desc->hw_clks->num ; i++) {
struct clk_hw *hw = desc->hw_clks->hws[i];
+ struct ccu_common *common = hw_to_ccu_common(hw);
const char *name;
if (!hw)
@@ -136,6 +147,14 @@
pr_err("Couldn't register clock %d - %s\n", i, name);
goto err_clk_unreg;
}
+
+ if (common->max_rate)
+ clk_hw_set_rate_range(hw, common->min_rate,
+ common->max_rate);
+ else
+ WARN(common->min_rate,
+ "No max_rate, ignoring min_rate of clock %d - %s\n",
+ i, name);
}
ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get,
diff --git a/drivers/clk/sunxi-ng/ccu_common.h b/drivers/clk/sunxi-ng/ccu_common.h
index 942a72c..329734f 100644
--- a/drivers/clk/sunxi-ng/ccu_common.h
+++ b/drivers/clk/sunxi-ng/ccu_common.h
@@ -31,6 +31,9 @@
u16 lock_reg;
u32 prediv;
+ unsigned long min_rate;
+ unsigned long max_rate;
+
unsigned long features;
spinlock_t *lock;
struct clk_hw hw;
diff --git a/drivers/comedi/drivers/vmk80xx.c b/drivers/comedi/drivers/vmk80xx.c
index 4536ed4..84dce51 100644
--- a/drivers/comedi/drivers/vmk80xx.c
+++ b/drivers/comedi/drivers/vmk80xx.c
@@ -641,32 +641,21 @@
struct vmk80xx_private *devpriv = dev->private;
struct usb_interface *intf = comedi_to_usb_interface(dev);
struct usb_host_interface *iface_desc = intf->cur_altsetting;
- struct usb_endpoint_descriptor *ep_desc;
- int i;
+ struct usb_endpoint_descriptor *ep_rx_desc, *ep_tx_desc;
+ int ret;
- if (iface_desc->desc.bNumEndpoints != 2)
+ if (devpriv->model == VMK8061_MODEL)
+ ret = usb_find_common_endpoints(iface_desc, &ep_rx_desc,
+ &ep_tx_desc, NULL, NULL);
+ else
+ ret = usb_find_common_endpoints(iface_desc, NULL, NULL,
+ &ep_rx_desc, &ep_tx_desc);
+
+ if (ret)
return -ENODEV;
- for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) {
- ep_desc = &iface_desc->endpoint[i].desc;
-
- if (usb_endpoint_is_int_in(ep_desc) ||
- usb_endpoint_is_bulk_in(ep_desc)) {
- if (!devpriv->ep_rx)
- devpriv->ep_rx = ep_desc;
- continue;
- }
-
- if (usb_endpoint_is_int_out(ep_desc) ||
- usb_endpoint_is_bulk_out(ep_desc)) {
- if (!devpriv->ep_tx)
- devpriv->ep_tx = ep_desc;
- continue;
- }
- }
-
- if (!devpriv->ep_rx || !devpriv->ep_tx)
- return -ENODEV;
+ devpriv->ep_rx = ep_rx_desc;
+ devpriv->ep_tx = ep_tx_desc;
if (!usb_endpoint_maxp(devpriv->ep_rx) || !usb_endpoint_maxp(devpriv->ep_tx))
return -EINVAL;
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index af5cb81..cb8c155 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -525,22 +525,11 @@
{
struct acpi_device *hb = to_cxl_host_bridge(NULL, dev);
u32 uid;
- int rc;
if (kstrtou32(acpi_device_uid(hb), 0, &uid))
return -EINVAL;
- rc = acpi_get_genport_coordinates(uid, dport->hb_coord);
- if (rc < 0)
- return rc;
-
- /* Adjust back to picoseconds from nanoseconds */
- for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
- dport->hb_coord[i].read_latency *= 1000;
- dport->hb_coord[i].write_latency *= 1000;
- }
-
- return 0;
+ return acpi_get_genport_coordinates(uid, dport->coord);
}
static int add_host_bridge_dport(struct device *match, void *arg)
diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index eddbbe2..bb83867 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -14,12 +14,42 @@
struct dsmas_entry {
struct range dpa_range;
u8 handle;
- struct access_coordinate coord;
+ struct access_coordinate coord[ACCESS_COORDINATE_MAX];
int entries;
int qos_class;
};
+static u32 cdat_normalize(u16 entry, u64 base, u8 type)
+{
+ u32 value;
+
+ /*
+ * Check for invalid and overflow values
+ */
+ if (entry == 0xffff || !entry)
+ return 0;
+ else if (base > (UINT_MAX / (entry)))
+ return 0;
+
+ /*
+ * CDAT fields follow the format of HMAT fields. See table 5 Device
+ * Scoped Latency and Bandwidth Information Structure in Coherent Device
+ * Attribute Table (CDAT) Specification v1.01.
+ */
+ value = entry * base;
+ switch (type) {
+ case ACPI_HMAT_ACCESS_LATENCY:
+ case ACPI_HMAT_READ_LATENCY:
+ case ACPI_HMAT_WRITE_LATENCY:
+ value = DIV_ROUND_UP(value, 1000);
+ break;
+ default:
+ break;
+ }
+ return value;
+}
+
static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg,
const unsigned long end)
{
@@ -58,8 +88,8 @@
return 0;
}
-static void cxl_access_coordinate_set(struct access_coordinate *coord,
- int access, unsigned int val)
+static void __cxl_access_coordinate_set(struct access_coordinate *coord,
+ int access, unsigned int val)
{
switch (access) {
case ACPI_HMAT_ACCESS_LATENCY:
@@ -85,6 +115,13 @@
}
}
+static void cxl_access_coordinate_set(struct access_coordinate *coord,
+ int access, unsigned int val)
+{
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+ __cxl_access_coordinate_set(&coord[i], access, val);
+}
+
static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg,
const unsigned long end)
{
@@ -97,7 +134,6 @@
__le16 le_val;
u64 val;
u16 len;
- int rc;
len = le16_to_cpu((__force __le16)hdr->length);
if (len != size || (unsigned long)hdr + len > end) {
@@ -124,12 +160,10 @@
le_base = (__force __le64)dslbis->entry_base_unit;
le_val = (__force __le16)dslbis->entry[0];
- rc = check_mul_overflow(le64_to_cpu(le_base),
- le16_to_cpu(le_val), &val);
- if (rc)
- pr_warn("DSLBIS value overflowed.\n");
+ val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base),
+ dslbis->data_type);
- cxl_access_coordinate_set(&dent->coord, dslbis->data_type, val);
+ cxl_access_coordinate_set(dent->coord, dslbis->data_type, val);
return 0;
}
@@ -163,25 +197,18 @@
static int cxl_port_perf_data_calculate(struct cxl_port *port,
struct xarray *dsmas_xa)
{
- struct access_coordinate ep_c;
- struct access_coordinate coord[ACCESS_COORDINATE_MAX];
+ struct access_coordinate ep_c[ACCESS_COORDINATE_MAX];
struct dsmas_entry *dent;
int valid_entries = 0;
unsigned long index;
int rc;
- rc = cxl_endpoint_get_perf_coordinates(port, &ep_c);
+ rc = cxl_endpoint_get_perf_coordinates(port, ep_c);
if (rc) {
dev_dbg(&port->dev, "Failed to retrieve ep perf coordinates.\n");
return rc;
}
- rc = cxl_hb_get_perf_coordinates(port, coord);
- if (rc) {
- dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n");
- return rc;
- }
-
struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port);
if (!cxl_root)
@@ -193,18 +220,10 @@
xa_for_each(dsmas_xa, index, dent) {
int qos_class;
- cxl_coordinates_combine(&dent->coord, &dent->coord, &ep_c);
- /*
- * Keeping the host bridge coordinates separate from the dsmas
- * coordinates in order to allow calculation of access class
- * 0 and 1 for region later.
- */
- cxl_coordinates_combine(&coord[ACCESS_COORDINATE_CPU],
- &coord[ACCESS_COORDINATE_CPU],
- &dent->coord);
+ cxl_coordinates_combine(dent->coord, dent->coord, ep_c);
dent->entries = 1;
rc = cxl_root->ops->qos_class(cxl_root,
- &coord[ACCESS_COORDINATE_CPU],
+ &dent->coord[ACCESS_COORDINATE_CPU],
1, &qos_class);
if (rc != 1)
continue;
@@ -222,14 +241,17 @@
static void update_perf_entry(struct device *dev, struct dsmas_entry *dent,
struct cxl_dpa_perf *dpa_perf)
{
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+ dpa_perf->coord[i] = dent->coord[i];
dpa_perf->dpa_range = dent->dpa_range;
- dpa_perf->coord = dent->coord;
dpa_perf->qos_class = dent->qos_class;
dev_dbg(dev,
"DSMAS: dpa: %#llx qos: %d read_bw: %d write_bw %d read_lat: %d write_lat: %d\n",
dent->dpa_range.start, dpa_perf->qos_class,
- dent->coord.read_bandwidth, dent->coord.write_bandwidth,
- dent->coord.read_latency, dent->coord.write_latency);
+ dent->coord[ACCESS_COORDINATE_CPU].read_bandwidth,
+ dent->coord[ACCESS_COORDINATE_CPU].write_bandwidth,
+ dent->coord[ACCESS_COORDINATE_CPU].read_latency,
+ dent->coord[ACCESS_COORDINATE_CPU].write_latency);
}
static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds,
@@ -461,17 +483,16 @@
le_base = (__force __le64)tbl->sslbis_header.entry_base_unit;
le_val = (__force __le16)tbl->entries[i].latency_or_bandwidth;
-
- if (check_mul_overflow(le64_to_cpu(le_base),
- le16_to_cpu(le_val), &val))
- dev_warn(dev, "SSLBIS value overflowed!\n");
+ val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base),
+ sslbis->data_type);
xa_for_each(&port->dports, index, dport) {
if (dsp_id == ACPI_CDAT_SSLBIS_ANY_PORT ||
- dsp_id == dport->port_id)
- cxl_access_coordinate_set(&dport->sw_coord,
+ dsp_id == dport->port_id) {
+ cxl_access_coordinate_set(dport->coord,
sslbis->data_type,
val);
+ }
}
}
@@ -493,16 +514,9 @@
}
EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL);
-/**
- * cxl_coordinates_combine - Combine the two input coordinates
- *
- * @out: Output coordinate of c1 and c2 combined
- * @c1: input coordinates
- * @c2: input coordinates
- */
-void cxl_coordinates_combine(struct access_coordinate *out,
- struct access_coordinate *c1,
- struct access_coordinate *c2)
+static void __cxl_coordinates_combine(struct access_coordinate *out,
+ struct access_coordinate *c1,
+ struct access_coordinate *c2)
{
if (c1->write_bandwidth && c2->write_bandwidth)
out->write_bandwidth = min(c1->write_bandwidth,
@@ -515,23 +529,34 @@
out->read_latency = c1->read_latency + c2->read_latency;
}
+/**
+ * cxl_coordinates_combine - Combine the two input coordinates
+ *
+ * @out: Output coordinate of c1 and c2 combined
+ * @c1: input coordinates
+ * @c2: input coordinates
+ */
+void cxl_coordinates_combine(struct access_coordinate *out,
+ struct access_coordinate *c1,
+ struct access_coordinate *c2)
+{
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+ __cxl_coordinates_combine(&out[i], &c1[i], &c2[i]);
+}
+
MODULE_IMPORT_NS(CXL);
void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
struct cxl_endpoint_decoder *cxled)
{
struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
- struct cxl_port *port = cxlmd->endpoint;
struct cxl_dev_state *cxlds = cxlmd->cxlds;
struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
- struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX];
- struct access_coordinate coord;
struct range dpa = {
.start = cxled->dpa_res->start,
.end = cxled->dpa_res->end,
};
struct cxl_dpa_perf *perf;
- int rc;
switch (cxlr->mode) {
case CXL_DECODER_RAM:
@@ -549,35 +574,16 @@
if (!range_contains(&perf->dpa_range, &dpa))
return;
- rc = cxl_hb_get_perf_coordinates(port, hb_coord);
- if (rc) {
- dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n");
- return;
- }
-
for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
- /* Pickup the host bridge coords */
- cxl_coordinates_combine(&coord, &hb_coord[i], &perf->coord);
-
/* Get total bandwidth and the worst latency for the cxl region */
cxlr->coord[i].read_latency = max_t(unsigned int,
cxlr->coord[i].read_latency,
- coord.read_latency);
+ perf->coord[i].read_latency);
cxlr->coord[i].write_latency = max_t(unsigned int,
cxlr->coord[i].write_latency,
- coord.write_latency);
- cxlr->coord[i].read_bandwidth += coord.read_bandwidth;
- cxlr->coord[i].write_bandwidth += coord.write_bandwidth;
-
- /*
- * Convert latency to nanosec from picosec to be consistent
- * with the resulting latency coordinates computed by the
- * HMAT_REPORTING code.
- */
- cxlr->coord[i].read_latency =
- DIV_ROUND_UP(cxlr->coord[i].read_latency, 1000);
- cxlr->coord[i].write_latency =
- DIV_ROUND_UP(cxlr->coord[i].write_latency, 1000);
+ perf->coord[i].write_latency);
+ cxlr->coord[i].read_bandwidth += perf->coord[i].read_bandwidth;
+ cxlr->coord[i].write_bandwidth += perf->coord[i].write_bandwidth;
}
}
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 9adda47..65185c9 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -915,7 +915,7 @@
payload->handles[i++] = gen->hdr.handle;
dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log,
- le16_to_cpu(payload->handles[i]));
+ le16_to_cpu(payload->handles[i - 1]));
if (i == max_handles) {
payload->nr_recs = i;
@@ -946,24 +946,22 @@
struct cxl_memdev *cxlmd = mds->cxlds.cxlmd;
struct device *dev = mds->cxlds.dev;
struct cxl_get_event_payload *payload;
- struct cxl_mbox_cmd mbox_cmd;
u8 log_type = type;
u16 nr_rec;
mutex_lock(&mds->event.log_lock);
payload = mds->event.buf;
- mbox_cmd = (struct cxl_mbox_cmd) {
- .opcode = CXL_MBOX_OP_GET_EVENT_RECORD,
- .payload_in = &log_type,
- .size_in = sizeof(log_type),
- .payload_out = payload,
- .size_out = mds->payload_size,
- .min_out = struct_size(payload, records, 0),
- };
-
do {
int rc, i;
+ struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) {
+ .opcode = CXL_MBOX_OP_GET_EVENT_RECORD,
+ .payload_in = &log_type,
+ .size_in = sizeof(log_type),
+ .payload_out = payload,
+ .size_out = mds->payload_size,
+ .min_out = struct_size(payload, records, 0),
+ };
rc = cxl_internal_send_cmd(mds, &mbox_cmd);
if (rc) {
@@ -1296,7 +1294,6 @@
struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds);
struct cxl_mbox_poison_out *po;
struct cxl_mbox_poison_in pi;
- struct cxl_mbox_cmd mbox_cmd;
int nr_records = 0;
int rc;
@@ -1308,16 +1305,16 @@
pi.offset = cpu_to_le64(offset);
pi.length = cpu_to_le64(len / CXL_POISON_LEN_MULT);
- mbox_cmd = (struct cxl_mbox_cmd) {
- .opcode = CXL_MBOX_OP_GET_POISON,
- .size_in = sizeof(pi),
- .payload_in = &pi,
- .size_out = mds->payload_size,
- .payload_out = po,
- .min_out = struct_size(po, record, 0),
- };
-
do {
+ struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd){
+ .opcode = CXL_MBOX_OP_GET_POISON,
+ .size_in = sizeof(pi),
+ .payload_in = &pi,
+ .size_out = mds->payload_size,
+ .payload_out = po,
+ .min_out = struct_size(po, record, 0),
+ };
+
rc = cxl_internal_send_cmd(mds, &mbox_cmd);
if (rc)
break;
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 2b0cab5..887ed6e3 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -2133,36 +2133,44 @@
}
EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL);
-/**
- * cxl_hb_get_perf_coordinates - Retrieve performance numbers between initiator
- * and host bridge
- *
- * @port: endpoint cxl_port
- * @coord: output access coordinates
- *
- * Return: errno on failure, 0 on success.
- */
-int cxl_hb_get_perf_coordinates(struct cxl_port *port,
- struct access_coordinate *coord)
+static void add_latency(struct access_coordinate *c, long latency)
{
- struct cxl_port *iter = port;
- struct cxl_dport *dport;
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+ c[i].write_latency += latency;
+ c[i].read_latency += latency;
+ }
+}
- if (!is_cxl_endpoint(port))
- return -EINVAL;
-
- dport = iter->parent_dport;
- while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
- iter = to_cxl_port(iter->dev.parent);
- dport = iter->parent_dport;
+static bool coordinates_valid(struct access_coordinate *c)
+{
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+ if (c[i].read_bandwidth && c[i].write_bandwidth &&
+ c[i].read_latency && c[i].write_latency)
+ continue;
+ return false;
}
- coord[ACCESS_COORDINATE_LOCAL] =
- dport->hb_coord[ACCESS_COORDINATE_LOCAL];
- coord[ACCESS_COORDINATE_CPU] =
- dport->hb_coord[ACCESS_COORDINATE_CPU];
+ return true;
+}
- return 0;
+static void set_min_bandwidth(struct access_coordinate *c, unsigned int bw)
+{
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+ c[i].write_bandwidth = min(c[i].write_bandwidth, bw);
+ c[i].read_bandwidth = min(c[i].read_bandwidth, bw);
+ }
+}
+
+static void set_access_coordinates(struct access_coordinate *out,
+ struct access_coordinate *in)
+{
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++)
+ out[i] = in[i];
+}
+
+static bool parent_port_is_cxl_root(struct cxl_port *port)
+{
+ return is_cxl_root(to_cxl_port(port->dev.parent));
}
/**
@@ -2176,47 +2184,76 @@
int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
struct access_coordinate *coord)
{
- struct access_coordinate c = {
- .read_bandwidth = UINT_MAX,
- .write_bandwidth = UINT_MAX,
+ struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
+ struct access_coordinate c[] = {
+ {
+ .read_bandwidth = UINT_MAX,
+ .write_bandwidth = UINT_MAX,
+ },
+ {
+ .read_bandwidth = UINT_MAX,
+ .write_bandwidth = UINT_MAX,
+ },
};
struct cxl_port *iter = port;
struct cxl_dport *dport;
struct pci_dev *pdev;
+ struct device *dev;
unsigned int bw;
+ bool is_cxl_root;
if (!is_cxl_endpoint(port))
return -EINVAL;
- dport = iter->parent_dport;
+ /*
+ * Skip calculation for RCD. Expectation is HMAT already covers RCD case
+ * since RCH does not support hotplug.
+ */
+ if (cxlmd->cxlds->rcd)
+ return 0;
/*
- * Exit the loop when the parent port of the current port is cxl root.
- * The iterative loop starts at the endpoint and gathers the
- * latency of the CXL link from the current iter to the next downstream
- * port each iteration. If the parent is cxl root then there is
- * nothing to gather.
+ * Exit the loop when the parent port of the current iter port is cxl
+ * root. The iterative loop starts at the endpoint and gathers the
+ * latency of the CXL link from the current device/port to the connected
+ * downstream port each iteration.
*/
- while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) {
- cxl_coordinates_combine(&c, &c, &dport->sw_coord);
- c.write_latency += dport->link_latency;
- c.read_latency += dport->link_latency;
-
- iter = to_cxl_port(iter->dev.parent);
+ do {
dport = iter->parent_dport;
- }
+ iter = to_cxl_port(iter->dev.parent);
+ is_cxl_root = parent_port_is_cxl_root(iter);
+
+ /*
+ * There's no valid access_coordinate for a root port since RPs do not
+ * have CDAT and therefore needs to be skipped.
+ */
+ if (!is_cxl_root) {
+ if (!coordinates_valid(dport->coord))
+ return -EINVAL;
+ cxl_coordinates_combine(c, c, dport->coord);
+ }
+ add_latency(c, dport->link_latency);
+ } while (!is_cxl_root);
+
+ dport = iter->parent_dport;
+ /* Retrieve HB coords */
+ if (!coordinates_valid(dport->coord))
+ return -EINVAL;
+ cxl_coordinates_combine(c, c, dport->coord);
+
+ dev = port->uport_dev->parent;
+ if (!dev_is_pci(dev))
+ return -ENODEV;
/* Get the calculated PCI paths bandwidth */
- pdev = to_pci_dev(port->uport_dev->parent);
+ pdev = to_pci_dev(dev);
bw = pcie_bandwidth_available(pdev, NULL, NULL, NULL);
if (bw == 0)
return -ENXIO;
bw /= BITS_PER_BYTE;
- c.write_bandwidth = min(c.write_bandwidth, bw);
- c.read_bandwidth = min(c.read_bandwidth, bw);
-
- *coord = c;
+ set_min_bandwidth(c, bw);
+ set_access_coordinates(coord, c);
return 0;
}
diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
index 372786f..3c42f98 100644
--- a/drivers/cxl/core/regs.c
+++ b/drivers/cxl/core/regs.c
@@ -271,6 +271,7 @@
static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi,
struct cxl_register_map *map)
{
+ u8 reg_type = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK, reg_lo);
int bar = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BIR_MASK, reg_lo);
u64 offset = ((u64)reg_hi << 32) |
(reg_lo & CXL_DVSEC_REG_LOCATOR_BLOCK_OFF_LOW_MASK);
@@ -278,11 +279,11 @@
if (offset > pci_resource_len(pdev, bar)) {
dev_warn(&pdev->dev,
"BAR%d: %pr: too small (offset: %pa, type: %d)\n", bar,
- &pdev->resource[bar], &offset, map->reg_type);
+ &pdev->resource[bar], &offset, reg_type);
return false;
}
- map->reg_type = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK, reg_lo);
+ map->reg_type = reg_type;
map->resource = pci_resource_start(pdev, bar) + offset;
map->max_size = pci_resource_len(pdev, bar) - offset;
return true;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 534e25e..036d17d 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -663,8 +663,7 @@
* @rch: Indicate whether this dport was enumerated in RCH or VH mode
* @port: reference to cxl_port that contains this downstream port
* @regs: Dport parsed register blocks
- * @sw_coord: access coordinates (performance) for switch from CDAT
- * @hb_coord: access coordinates (performance) from ACPI generic port (host bridge)
+ * @coord: access coordinates (bandwidth and latency performance attributes)
* @link_latency: calculated PCIe downstream latency
*/
struct cxl_dport {
@@ -675,8 +674,7 @@
bool rch;
struct cxl_port *port;
struct cxl_regs regs;
- struct access_coordinate sw_coord;
- struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX];
+ struct access_coordinate coord[ACCESS_COORDINATE_MAX];
long link_latency;
};
@@ -884,8 +882,6 @@
int cxl_endpoint_get_perf_coordinates(struct cxl_port *port,
struct access_coordinate *coord);
-int cxl_hb_get_perf_coordinates(struct cxl_port *port,
- struct access_coordinate *coord);
void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
struct cxl_endpoint_decoder *cxled);
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 20fb3b3..36cee9c 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -401,7 +401,7 @@
*/
struct cxl_dpa_perf {
struct range dpa_range;
- struct access_coordinate coord;
+ struct access_coordinate coord[ACCESS_COORDINATE_MAX];
int qos_class;
};
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index 78a9389..1398814 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -171,6 +171,10 @@
u32 status_err;
unsigned short i;
+ /* Since IRQ may be shared, check if DMA controller is powered on */
+ if (status == GENMASK(31, 0))
+ return IRQ_NONE;
+
dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status);
/* Check if we have any interrupt from the DMA controller */
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index 8078ab9..c095a2c 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -342,7 +342,7 @@
if (!evl)
return;
- spin_lock(&evl->lock);
+ mutex_lock(&evl->lock);
status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
t = status.tail;
h = status.head;
@@ -354,9 +354,8 @@
set_bit(h, evl->bmap);
h = (h + 1) % size;
}
- spin_unlock(&evl->lock);
-
drain_workqueue(wq->wq);
+ mutex_unlock(&evl->lock);
}
static int idxd_cdev_release(struct inode *node, struct file *filep)
diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c
index f3f25ee..ad4245c 100644
--- a/drivers/dma/idxd/debugfs.c
+++ b/drivers/dma/idxd/debugfs.c
@@ -66,7 +66,7 @@
if (!evl || !evl->log)
return 0;
- spin_lock(&evl->lock);
+ mutex_lock(&evl->lock);
evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
t = evl_status.tail;
@@ -87,7 +87,7 @@
dump_event_entry(idxd, s, i, &count, processed);
}
- spin_unlock(&evl->lock);
+ mutex_unlock(&evl->lock);
return 0;
}
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index ecfdf4a..c41ef19 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -775,7 +775,7 @@
goto err_alloc;
}
- spin_lock(&evl->lock);
+ mutex_lock(&evl->lock);
evl->log = addr;
evl->dma = dma_addr;
evl->log_size = size;
@@ -796,7 +796,7 @@
gencfg.evl_en = 1;
iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
- spin_unlock(&evl->lock);
+ mutex_unlock(&evl->lock);
return 0;
err_alloc:
@@ -819,7 +819,7 @@
if (!gencfg.evl_en)
return;
- spin_lock(&evl->lock);
+ mutex_lock(&evl->lock);
gencfg.evl_en = 0;
iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
@@ -836,7 +836,7 @@
evl_dma = evl->dma;
evl->log = NULL;
evl->size = IDXD_EVL_SIZE_MIN;
- spin_unlock(&evl->lock);
+ mutex_unlock(&evl->lock);
dma_free_coherent(dev, evl_log_size, evl_log, evl_dma);
}
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index a4099a1..7b98944 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -293,7 +293,7 @@
struct idxd_evl {
/* Lock to protect event log access. */
- spinlock_t lock;
+ struct mutex lock;
void *log;
dma_addr_t dma;
/* Total size of event log = number of entries * entry size. */
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 4954adc..264c4e4 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -354,7 +354,7 @@
if (!evl)
return -ENOMEM;
- spin_lock_init(&evl->lock);
+ mutex_init(&evl->lock);
evl->size = IDXD_EVL_SIZE_MIN;
idxd_name = dev_name(idxd_confdev(idxd));
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 348aa21..8dc029c 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -363,7 +363,7 @@
evl_status.bits = 0;
evl_status.int_pending = 1;
- spin_lock(&evl->lock);
+ mutex_lock(&evl->lock);
/* Clear interrupt pending bit */
iowrite32(evl_status.bits_upper32,
idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32));
@@ -380,7 +380,7 @@
evl_status.head = h;
iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
- spin_unlock(&evl->lock);
+ mutex_unlock(&evl->lock);
}
irqreturn_t idxd_misc_thread(int vec, void *data)
diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c
index fdda6d6..5e94247 100644
--- a/drivers/dma/idxd/perfmon.c
+++ b/drivers/dma/idxd/perfmon.c
@@ -528,14 +528,11 @@
return 0;
target = cpumask_any_but(cpu_online_mask, cpu);
-
/* migrate events if there is a valid target */
- if (target < nr_cpu_ids)
+ if (target < nr_cpu_ids) {
cpumask_set_cpu(target, &perfmon_dsa_cpu_mask);
- else
- target = -1;
-
- perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target);
+ perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target);
+ }
return 0;
}
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
index 4e76c4e..e001f4f 100644
--- a/drivers/dma/owl-dma.c
+++ b/drivers/dma/owl-dma.c
@@ -250,7 +250,7 @@
else
regval &= ~val;
- writel(val, pchan->base + reg);
+ writel(regval, pchan->base + reg);
}
static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data)
@@ -274,7 +274,7 @@
else
regval &= ~val;
- writel(val, od->base + reg);
+ writel(regval, od->base + reg);
}
static void dma_writel(struct owl_dma *od, u32 reg, u32 data)
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 5f6d7f1..ad8e3da 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1053,9 +1053,6 @@
thrd->req_running = idx;
- if (desc->rqtype == DMA_MEM_TO_DEV || desc->rqtype == DMA_DEV_TO_MEM)
- UNTIL(thrd, PL330_STATE_WFP);
-
return true;
}
diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c
index 88547a2..3642508 100644
--- a/drivers/dma/tegra186-gpc-dma.c
+++ b/drivers/dma/tegra186-gpc-dma.c
@@ -746,6 +746,9 @@
bytes_xfer = dma_desc->bytes_xfer +
sg_req[dma_desc->sg_idx].len - (wcount * 4);
+ if (dma_desc->bytes_req == bytes_xfer)
+ return 0;
+
residual = dma_desc->bytes_req - (bytes_xfer % dma_desc->bytes_req);
return residual;
diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h
index 98f5f6f..6ad0887 100644
--- a/drivers/dma/xilinx/xdma-regs.h
+++ b/drivers/dma/xilinx/xdma-regs.h
@@ -117,6 +117,9 @@
CHAN_CTRL_IE_WRITE_ERROR | \
CHAN_CTRL_IE_DESC_ERROR)
+/* bits of the channel status register */
+#define XDMA_CHAN_STATUS_BUSY BIT(0)
+
#define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START
#define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH | \
diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c
index 170017f..313b217 100644
--- a/drivers/dma/xilinx/xdma.c
+++ b/drivers/dma/xilinx/xdma.c
@@ -71,6 +71,8 @@
enum dma_transfer_direction dir;
struct dma_slave_config cfg;
u32 irq;
+ struct completion last_interrupt;
+ bool stop_requested;
};
/**
@@ -376,6 +378,8 @@
return ret;
xchan->busy = true;
+ xchan->stop_requested = false;
+ reinit_completion(&xchan->last_interrupt);
return 0;
}
@@ -387,7 +391,6 @@
static int xdma_xfer_stop(struct xdma_chan *xchan)
{
int ret;
- u32 val;
struct xdma_device *xdev = xchan->xdev_hdl;
/* clear run stop bit to prevent any further auto-triggering */
@@ -395,13 +398,7 @@
CHAN_CTRL_RUN_STOP);
if (ret)
return ret;
-
- /* Clear the channel status register */
- ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &val);
- if (ret)
- return ret;
-
- return 0;
+ return ret;
}
/**
@@ -474,6 +471,8 @@
xchan->xdev_hdl = xdev;
xchan->base = base + i * XDMA_CHAN_STRIDE;
xchan->dir = dir;
+ xchan->stop_requested = false;
+ init_completion(&xchan->last_interrupt);
ret = xdma_channel_init(xchan);
if (ret)
@@ -521,6 +520,7 @@
spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
xdma_chan->busy = false;
+ xdma_chan->stop_requested = true;
vd = vchan_next_desc(&xdma_chan->vchan);
if (vd) {
list_del(&vd->node);
@@ -542,17 +542,26 @@
static void xdma_synchronize(struct dma_chan *chan)
{
struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+ struct xdma_device *xdev = xdma_chan->xdev_hdl;
+ int st = 0;
+
+ /* If the engine continues running, wait for the last interrupt */
+ regmap_read(xdev->rmap, xdma_chan->base + XDMA_CHAN_STATUS, &st);
+ if (st & XDMA_CHAN_STATUS_BUSY)
+ wait_for_completion_timeout(&xdma_chan->last_interrupt, msecs_to_jiffies(1000));
vchan_synchronize(&xdma_chan->vchan);
}
/**
- * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses
- * @sw_desc: tx descriptor state container
- * @src_addr: Value for a ->src_addr field of a first descriptor
- * @dst_addr: Value for a ->dst_addr field of a first descriptor
- * @size: Total size of a contiguous memory block
- * @filled_descs_num: Number of filled hardware descriptors for corresponding sw_desc
+ * xdma_fill_descs() - Fill hardware descriptors for one contiguous memory chunk.
+ * More than one descriptor will be used if the size is bigger
+ * than XDMA_DESC_BLEN_MAX.
+ * @sw_desc: Descriptor container
+ * @src_addr: First value for the ->src_addr field
+ * @dst_addr: First value for the ->dst_addr field
+ * @size: Size of the contiguous memory block
+ * @filled_descs_num: Index of the first descriptor to take care of in @sw_desc
*/
static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr,
u64 dst_addr, u32 size, u32 filled_descs_num)
@@ -704,7 +713,7 @@
desc_num = 0;
for (i = 0; i < periods; i++) {
desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num);
- addr += i * period_size;
+ addr += period_size;
}
tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -876,6 +885,9 @@
u32 st;
bool repeat_tx;
+ if (xchan->stop_requested)
+ complete(&xchan->last_interrupt);
+
spin_lock(&xchan->vchan.lock);
/* get submitted request */
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index b82815e..eb0637d 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -214,7 +214,8 @@
* @running: true if the channel is running
* @first_frame: flag for the first frame of stream
* @video_group: flag if multi-channel operation is needed for video channels
- * @lock: lock to access struct xilinx_dpdma_chan
+ * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before
+ * @vchan.lock, if both are to be held.
* @desc_pool: descriptor allocation pool
* @err_task: error IRQ bottom half handler
* @desc: References to descriptors being processed
@@ -1097,12 +1098,14 @@
* Complete the active descriptor, if any, promote the pending
* descriptor to active, and queue the next transfer, if any.
*/
+ spin_lock(&chan->vchan.lock);
if (chan->desc.active)
vchan_cookie_complete(&chan->desc.active->vdesc);
chan->desc.active = pending;
chan->desc.pending = NULL;
xilinx_dpdma_chan_queue_transfer(chan);
+ spin_unlock(&chan->vchan.lock);
out:
spin_unlock_irqrestore(&chan->lock, flags);
@@ -1264,10 +1267,12 @@
struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
unsigned long flags;
- spin_lock_irqsave(&chan->vchan.lock, flags);
+ spin_lock_irqsave(&chan->lock, flags);
+ spin_lock(&chan->vchan.lock);
if (vchan_issue_pending(&chan->vchan))
xilinx_dpdma_chan_queue_transfer(chan);
- spin_unlock_irqrestore(&chan->vchan.lock, flags);
+ spin_unlock(&chan->vchan.lock);
+ spin_unlock_irqrestore(&chan->lock, flags);
}
static int xilinx_dpdma_config(struct dma_chan *dchan,
@@ -1495,7 +1500,9 @@
XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id);
spin_lock_irqsave(&chan->lock, flags);
+ spin_lock(&chan->vchan.lock);
xilinx_dpdma_chan_queue_transfer(chan);
+ spin_unlock(&chan->vchan.lock);
spin_unlock_irqrestore(&chan->lock, flags);
}
diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 64eaca8..d0f6693 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -42,6 +42,7 @@
struct list_head list;
const struct dpll_pin_ops *ops;
void *priv;
+ void *cookie;
};
struct dpll_device *dpll_device_get_by_id(int id)
@@ -54,12 +55,14 @@
static struct dpll_pin_registration *
dpll_pin_registration_find(struct dpll_pin_ref *ref,
- const struct dpll_pin_ops *ops, void *priv)
+ const struct dpll_pin_ops *ops, void *priv,
+ void *cookie)
{
struct dpll_pin_registration *reg;
list_for_each_entry(reg, &ref->registration_list, list) {
- if (reg->ops == ops && reg->priv == priv)
+ if (reg->ops == ops && reg->priv == priv &&
+ reg->cookie == cookie)
return reg;
}
return NULL;
@@ -67,7 +70,8 @@
static int
dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin,
- const struct dpll_pin_ops *ops, void *priv)
+ const struct dpll_pin_ops *ops, void *priv,
+ void *cookie)
{
struct dpll_pin_registration *reg;
struct dpll_pin_ref *ref;
@@ -78,7 +82,7 @@
xa_for_each(xa_pins, i, ref) {
if (ref->pin != pin)
continue;
- reg = dpll_pin_registration_find(ref, ops, priv);
+ reg = dpll_pin_registration_find(ref, ops, priv, cookie);
if (reg) {
refcount_inc(&ref->refcount);
return 0;
@@ -111,6 +115,7 @@
}
reg->ops = ops;
reg->priv = priv;
+ reg->cookie = cookie;
if (ref_exists)
refcount_inc(&ref->refcount);
list_add_tail(®->list, &ref->registration_list);
@@ -119,7 +124,8 @@
}
static int dpll_xa_ref_pin_del(struct xarray *xa_pins, struct dpll_pin *pin,
- const struct dpll_pin_ops *ops, void *priv)
+ const struct dpll_pin_ops *ops, void *priv,
+ void *cookie)
{
struct dpll_pin_registration *reg;
struct dpll_pin_ref *ref;
@@ -128,7 +134,7 @@
xa_for_each(xa_pins, i, ref) {
if (ref->pin != pin)
continue;
- reg = dpll_pin_registration_find(ref, ops, priv);
+ reg = dpll_pin_registration_find(ref, ops, priv, cookie);
if (WARN_ON(!reg))
return -EINVAL;
list_del(®->list);
@@ -146,7 +152,7 @@
static int
dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll,
- const struct dpll_pin_ops *ops, void *priv)
+ const struct dpll_pin_ops *ops, void *priv, void *cookie)
{
struct dpll_pin_registration *reg;
struct dpll_pin_ref *ref;
@@ -157,7 +163,7 @@
xa_for_each(xa_dplls, i, ref) {
if (ref->dpll != dpll)
continue;
- reg = dpll_pin_registration_find(ref, ops, priv);
+ reg = dpll_pin_registration_find(ref, ops, priv, cookie);
if (reg) {
refcount_inc(&ref->refcount);
return 0;
@@ -190,6 +196,7 @@
}
reg->ops = ops;
reg->priv = priv;
+ reg->cookie = cookie;
if (ref_exists)
refcount_inc(&ref->refcount);
list_add_tail(®->list, &ref->registration_list);
@@ -199,7 +206,7 @@
static void
dpll_xa_ref_dpll_del(struct xarray *xa_dplls, struct dpll_device *dpll,
- const struct dpll_pin_ops *ops, void *priv)
+ const struct dpll_pin_ops *ops, void *priv, void *cookie)
{
struct dpll_pin_registration *reg;
struct dpll_pin_ref *ref;
@@ -208,7 +215,7 @@
xa_for_each(xa_dplls, i, ref) {
if (ref->dpll != dpll)
continue;
- reg = dpll_pin_registration_find(ref, ops, priv);
+ reg = dpll_pin_registration_find(ref, ops, priv, cookie);
if (WARN_ON(!reg))
return;
list_del(®->list);
@@ -594,14 +601,14 @@
static int
__dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin,
- const struct dpll_pin_ops *ops, void *priv)
+ const struct dpll_pin_ops *ops, void *priv, void *cookie)
{
int ret;
- ret = dpll_xa_ref_pin_add(&dpll->pin_refs, pin, ops, priv);
+ ret = dpll_xa_ref_pin_add(&dpll->pin_refs, pin, ops, priv, cookie);
if (ret)
return ret;
- ret = dpll_xa_ref_dpll_add(&pin->dpll_refs, dpll, ops, priv);
+ ret = dpll_xa_ref_dpll_add(&pin->dpll_refs, dpll, ops, priv, cookie);
if (ret)
goto ref_pin_del;
xa_set_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED);
@@ -610,7 +617,7 @@
return ret;
ref_pin_del:
- dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv);
+ dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv, cookie);
return ret;
}
@@ -642,7 +649,7 @@
dpll->clock_id == pin->clock_id)))
ret = -EINVAL;
else
- ret = __dpll_pin_register(dpll, pin, ops, priv);
+ ret = __dpll_pin_register(dpll, pin, ops, priv, NULL);
mutex_unlock(&dpll_lock);
return ret;
@@ -651,11 +658,11 @@
static void
__dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin,
- const struct dpll_pin_ops *ops, void *priv)
+ const struct dpll_pin_ops *ops, void *priv, void *cookie)
{
ASSERT_DPLL_PIN_REGISTERED(pin);
- dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv);
- dpll_xa_ref_dpll_del(&pin->dpll_refs, dpll, ops, priv);
+ dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv, cookie);
+ dpll_xa_ref_dpll_del(&pin->dpll_refs, dpll, ops, priv, cookie);
if (xa_empty(&pin->dpll_refs))
xa_clear_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED);
}
@@ -680,7 +687,7 @@
mutex_lock(&dpll_lock);
dpll_pin_delete_ntf(pin);
- __dpll_pin_unregister(dpll, pin, ops, priv);
+ __dpll_pin_unregister(dpll, pin, ops, priv, NULL);
mutex_unlock(&dpll_lock);
}
EXPORT_SYMBOL_GPL(dpll_pin_unregister);
@@ -716,12 +723,12 @@
return -EINVAL;
mutex_lock(&dpll_lock);
- ret = dpll_xa_ref_pin_add(&pin->parent_refs, parent, ops, priv);
+ ret = dpll_xa_ref_pin_add(&pin->parent_refs, parent, ops, priv, pin);
if (ret)
goto unlock;
refcount_inc(&pin->refcount);
xa_for_each(&parent->dpll_refs, i, ref) {
- ret = __dpll_pin_register(ref->dpll, pin, ops, priv);
+ ret = __dpll_pin_register(ref->dpll, pin, ops, priv, parent);
if (ret) {
stop = i;
goto dpll_unregister;
@@ -735,11 +742,12 @@
dpll_unregister:
xa_for_each(&parent->dpll_refs, i, ref)
if (i < stop) {
- __dpll_pin_unregister(ref->dpll, pin, ops, priv);
+ __dpll_pin_unregister(ref->dpll, pin, ops, priv,
+ parent);
dpll_pin_delete_ntf(pin);
}
refcount_dec(&pin->refcount);
- dpll_xa_ref_pin_del(&pin->parent_refs, parent, ops, priv);
+ dpll_xa_ref_pin_del(&pin->parent_refs, parent, ops, priv, pin);
unlock:
mutex_unlock(&dpll_lock);
return ret;
@@ -764,10 +772,10 @@
mutex_lock(&dpll_lock);
dpll_pin_delete_ntf(pin);
- dpll_xa_ref_pin_del(&pin->parent_refs, parent, ops, priv);
+ dpll_xa_ref_pin_del(&pin->parent_refs, parent, ops, priv, pin);
refcount_dec(&pin->refcount);
xa_for_each(&pin->dpll_refs, i, ref)
- __dpll_pin_unregister(ref->dpll, pin, ops, priv);
+ __dpll_pin_unregister(ref->dpll, pin, ops, priv, parent);
mutex_unlock(&dpll_lock);
}
EXPORT_SYMBOL_GPL(dpll_pin_on_pin_unregister);
diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c
index 1688a50..a556d23 100644
--- a/drivers/edac/versal_edac.c
+++ b/drivers/edac/versal_edac.c
@@ -425,7 +425,7 @@
convert_to_physical(priv, pinf), pinf.burstpos);
edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
- priv->ce_cnt, 0, 0, 0, 0, 0, -1,
+ 1, 0, 0, 0, 0, 0, -1,
priv->message, "");
}
@@ -438,7 +438,7 @@
convert_to_physical(priv, pinf), pinf.burstpos);
edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
- priv->ue_cnt, 0, 0, 0, 0, 0, -1,
+ 1, 0, 0, 0, 0, 0, -1,
priv->message, "");
}
@@ -865,6 +865,9 @@
for (i = 0; i < NUM_UE_BITPOS; i++)
token[i] = strsep(&pbuf, ",");
+ if (!token[0] || !token[1])
+ return -EFAULT;
+
ret = kstrtou8(token[0], 0, &ue0);
if (ret)
return ret;
@@ -1135,8 +1138,7 @@
}
rc = xlnx_register_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1,
- XPM_EVENT_ERROR_MASK_DDRMC_CR | XPM_EVENT_ERROR_MASK_DDRMC_NCR |
- XPM_EVENT_ERROR_MASK_NOC_CR | XPM_EVENT_ERROR_MASK_NOC_NCR,
+ XPM_EVENT_ERROR_MASK_DDRMC_CR | XPM_EVENT_ERROR_MASK_DDRMC_NCR,
false, err_callback, mci);
if (rc) {
if (rc == -EACCES)
@@ -1173,8 +1175,6 @@
xlnx_unregister_event(PM_NOTIFY_CB, VERSAL_EVENT_ERROR_PMC_ERR1,
XPM_EVENT_ERROR_MASK_DDRMC_CR |
- XPM_EVENT_ERROR_MASK_NOC_CR |
- XPM_EVENT_ERROR_MASK_NOC_NCR |
XPM_EVENT_ERROR_MASK_DDRMC_NCR, err_callback, mci);
edac_mc_del_mc(&pdev->dev);
edac_mc_free(mci);
diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c
index b0d671d..ea31ac7 100644
--- a/drivers/firewire/nosy.c
+++ b/drivers/firewire/nosy.c
@@ -148,10 +148,12 @@
if (atomic_read(&buffer->size) == 0)
return -ENODEV;
- /* FIXME: Check length <= user_length. */
+ length = buffer->head->length;
+
+ if (length > user_length)
+ return 0;
end = buffer->data + buffer->capacity;
- length = buffer->head->length;
if (&buffer->head->data[length] < end) {
if (copy_to_user(data, buffer->head->data, length))
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 38d1941..b9ae034 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -1556,6 +1556,8 @@
#define HEADER_GET_DATA_LENGTH(q) (((q) >> 16) & 0xffff)
#define HEADER_GET_EXTENDED_TCODE(q) (((q) >> 0) & 0xffff)
+static u32 get_cycle_time(struct fw_ohci *ohci);
+
static void handle_local_rom(struct fw_ohci *ohci,
struct fw_packet *packet, u32 csr)
{
@@ -1580,6 +1582,8 @@
(void *) ohci->config_rom + i, length);
}
+ // Timestamping on behalf of the hardware.
+ response.timestamp = cycle_time_to_ohci_tstamp(get_cycle_time(ohci));
fw_core_handle_response(&ohci->card, &response);
}
@@ -1628,6 +1632,8 @@
fw_fill_response(&response, packet->header, RCODE_BUSY, NULL, 0);
out:
+ // Timestamping on behalf of the hardware.
+ response.timestamp = cycle_time_to_ohci_tstamp(get_cycle_time(ohci));
fw_core_handle_response(&ohci->card, &response);
}
@@ -1670,8 +1676,6 @@
}
}
-static u32 get_cycle_time(struct fw_ohci *ohci);
-
static void at_context_transmit(struct context *ctx, struct fw_packet *packet)
{
unsigned long flags;
diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index f2556a8..9bc2e10 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -790,7 +790,7 @@
part_id = packed_id_list[ids_processed++];
- if (!ids_count[list]) { /* Global Notification */
+ if (ids_count[list] == 1) { /* Global Notification */
__do_sched_recv_cb(part_id, 0, false);
continue;
}
diff --git a/drivers/firmware/arm_scmi/powercap.c b/drivers/firmware/arm_scmi/powercap.c
index ea9201e..1fa79bb 100644
--- a/drivers/firmware/arm_scmi/powercap.c
+++ b/drivers/firmware/arm_scmi/powercap.c
@@ -736,7 +736,7 @@
ph->hops->fastchannel_init(ph, POWERCAP_DESCRIBE_FASTCHANNEL,
POWERCAP_PAI_GET, 4, domain,
&fc[POWERCAP_FC_PAI].get_addr, NULL,
- &fc[POWERCAP_PAI_GET].rate_limit);
+ &fc[POWERCAP_FC_PAI].rate_limit);
*p_fc = fc;
}
diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c
index 3505735..130d13e 100644
--- a/drivers/firmware/arm_scmi/raw_mode.c
+++ b/drivers/firmware/arm_scmi/raw_mode.c
@@ -921,7 +921,7 @@
rd->raw = raw;
filp->private_data = rd;
- return 0;
+ return nonseekable_open(inode, filp);
}
static int scmi_dbg_raw_mode_release(struct inode *inode, struct file *filp)
@@ -950,6 +950,7 @@
.open = scmi_dbg_raw_mode_open,
.release = scmi_dbg_raw_mode_release,
.write = scmi_dbg_raw_mode_reset_write,
+ .llseek = no_llseek,
.owner = THIS_MODULE,
};
@@ -959,6 +960,7 @@
.read = scmi_dbg_raw_mode_message_read,
.write = scmi_dbg_raw_mode_message_write,
.poll = scmi_dbg_raw_mode_message_poll,
+ .llseek = no_llseek,
.owner = THIS_MODULE,
};
@@ -975,6 +977,7 @@
.read = scmi_dbg_raw_mode_message_read,
.write = scmi_dbg_raw_mode_message_async_write,
.poll = scmi_dbg_raw_mode_message_poll,
+ .llseek = no_llseek,
.owner = THIS_MODULE,
};
@@ -998,6 +1001,7 @@
.release = scmi_dbg_raw_mode_release,
.read = scmi_test_dbg_raw_mode_notif_read,
.poll = scmi_test_dbg_raw_mode_notif_poll,
+ .llseek = no_llseek,
.owner = THIS_MODULE,
};
@@ -1021,6 +1025,7 @@
.release = scmi_dbg_raw_mode_release,
.read = scmi_test_dbg_raw_mode_errors_read,
.poll = scmi_test_dbg_raw_mode_errors_poll,
+ .llseek = no_llseek,
.owner = THIS_MODULE,
};
diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c
index 5b439d0..50f6503 100644
--- a/drivers/firmware/efi/unaccepted_memory.c
+++ b/drivers/firmware/efi/unaccepted_memory.c
@@ -4,6 +4,7 @@
#include <linux/memblock.h>
#include <linux/spinlock.h>
#include <linux/crash_dump.h>
+#include <linux/nmi.h>
#include <asm/unaccepted_memory.h>
/* Protects unaccepted memory bitmap and accepting_list */
@@ -149,6 +150,9 @@
}
list_del(&range.list);
+
+ touch_softlockup_watchdog();
+
spin_unlock_irqrestore(&unaccepted_memory_lock, flags);
}
diff --git a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
index 32188f0..bc550ad 100644
--- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
+++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
@@ -221,6 +221,19 @@
* alignment of 8 bytes (64 bits) for GUIDs. Our definition of efi_guid_t,
* however, has an alignment of 4 byte (32 bits). So far, this seems to work
* fine here. See also the comment on the typedef of efi_guid_t.
+ *
+ * Note: It looks like uefisecapp is quite picky about how the memory passed to
+ * it is structured and aligned. In particular the request/response setup used
+ * for QSEE_CMD_UEFI_GET_VARIABLE. While qcom_qseecom_app_send(), in theory,
+ * accepts separate buffers/addresses for the request and response parts, in
+ * practice, however, it seems to expect them to be both part of a larger
+ * contiguous block. We initially allocated separate buffers for the request
+ * and response but this caused the QSEE_CMD_UEFI_GET_VARIABLE command to
+ * either not write any response to the response buffer or outright crash the
+ * device. Therefore, we now allocate a single contiguous block of DMA memory
+ * for both and properly align the data using the macros below. In particular,
+ * request and response structs are aligned at 8 byte (via __reqdata_offs()),
+ * following the driver that this has been reverse-engineered from.
*/
#define qcuefi_buf_align_fields(fields...) \
({ \
@@ -244,6 +257,12 @@
#define __array_offs(type, count, offset) \
__field_impl(sizeof(type) * (count), __alignof__(type), offset)
+#define __array_offs_aligned(type, count, align, offset) \
+ __field_impl(sizeof(type) * (count), align, offset)
+
+#define __reqdata_offs(size, offset) \
+ __array_offs_aligned(u8, size, 8, offset)
+
#define __array(type, count) __array_offs(type, count, NULL)
#define __field_offs(type, offset) __array_offs(type, 1, offset)
#define __field(type) __array_offs(type, 1, NULL)
@@ -277,10 +296,15 @@
unsigned long buffer_size = *data_size;
efi_status_t efi_status = EFI_SUCCESS;
unsigned long name_length;
+ dma_addr_t cmd_buf_dma;
+ size_t cmd_buf_size;
+ void *cmd_buf;
size_t guid_offs;
size_t name_offs;
size_t req_size;
size_t rsp_size;
+ size_t req_offs;
+ size_t rsp_offs;
ssize_t status;
if (!name || !guid)
@@ -304,17 +328,19 @@
__array(u8, buffer_size)
);
- req_data = kzalloc(req_size, GFP_KERNEL);
- if (!req_data) {
+ cmd_buf_size = qcuefi_buf_align_fields(
+ __reqdata_offs(req_size, &req_offs)
+ __reqdata_offs(rsp_size, &rsp_offs)
+ );
+
+ cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL);
+ if (!cmd_buf) {
efi_status = EFI_OUT_OF_RESOURCES;
goto out;
}
- rsp_data = kzalloc(rsp_size, GFP_KERNEL);
- if (!rsp_data) {
- efi_status = EFI_OUT_OF_RESOURCES;
- goto out_free_req;
- }
+ req_data = cmd_buf + req_offs;
+ rsp_data = cmd_buf + rsp_offs;
req_data->command_id = QSEE_CMD_UEFI_GET_VARIABLE;
req_data->data_size = buffer_size;
@@ -332,7 +358,9 @@
memcpy(((void *)req_data) + req_data->guid_offset, guid, req_data->guid_size);
- status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size);
+ status = qcom_qseecom_app_send(qcuefi->client,
+ cmd_buf_dma + req_offs, req_size,
+ cmd_buf_dma + rsp_offs, rsp_size);
if (status) {
efi_status = EFI_DEVICE_ERROR;
goto out_free;
@@ -407,9 +435,7 @@
memcpy(data, ((void *)rsp_data) + rsp_data->data_offset, rsp_data->data_size);
out_free:
- kfree(rsp_data);
-out_free_req:
- kfree(req_data);
+ qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma);
out:
return efi_status;
}
@@ -422,10 +448,15 @@
struct qsee_rsp_uefi_set_variable *rsp_data;
efi_status_t efi_status = EFI_SUCCESS;
unsigned long name_length;
+ dma_addr_t cmd_buf_dma;
+ size_t cmd_buf_size;
+ void *cmd_buf;
size_t name_offs;
size_t guid_offs;
size_t data_offs;
size_t req_size;
+ size_t req_offs;
+ size_t rsp_offs;
ssize_t status;
if (!name || !guid)
@@ -450,17 +481,19 @@
__array_offs(u8, data_size, &data_offs)
);
- req_data = kzalloc(req_size, GFP_KERNEL);
- if (!req_data) {
+ cmd_buf_size = qcuefi_buf_align_fields(
+ __reqdata_offs(req_size, &req_offs)
+ __reqdata_offs(sizeof(*rsp_data), &rsp_offs)
+ );
+
+ cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL);
+ if (!cmd_buf) {
efi_status = EFI_OUT_OF_RESOURCES;
goto out;
}
- rsp_data = kzalloc(sizeof(*rsp_data), GFP_KERNEL);
- if (!rsp_data) {
- efi_status = EFI_OUT_OF_RESOURCES;
- goto out_free_req;
- }
+ req_data = cmd_buf + req_offs;
+ rsp_data = cmd_buf + rsp_offs;
req_data->command_id = QSEE_CMD_UEFI_SET_VARIABLE;
req_data->attributes = attributes;
@@ -483,8 +516,9 @@
if (data_size)
memcpy(((void *)req_data) + req_data->data_offset, data, req_data->data_size);
- status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data,
- sizeof(*rsp_data));
+ status = qcom_qseecom_app_send(qcuefi->client,
+ cmd_buf_dma + req_offs, req_size,
+ cmd_buf_dma + rsp_offs, sizeof(*rsp_data));
if (status) {
efi_status = EFI_DEVICE_ERROR;
goto out_free;
@@ -507,9 +541,7 @@
}
out_free:
- kfree(rsp_data);
-out_free_req:
- kfree(req_data);
+ qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma);
out:
return efi_status;
}
@@ -521,10 +553,15 @@
struct qsee_req_uefi_get_next_variable *req_data;
struct qsee_rsp_uefi_get_next_variable *rsp_data;
efi_status_t efi_status = EFI_SUCCESS;
+ dma_addr_t cmd_buf_dma;
+ size_t cmd_buf_size;
+ void *cmd_buf;
size_t guid_offs;
size_t name_offs;
size_t req_size;
size_t rsp_size;
+ size_t req_offs;
+ size_t rsp_offs;
ssize_t status;
if (!name_size || !name || !guid)
@@ -545,17 +582,19 @@
__array(*name, *name_size / sizeof(*name))
);
- req_data = kzalloc(req_size, GFP_KERNEL);
- if (!req_data) {
+ cmd_buf_size = qcuefi_buf_align_fields(
+ __reqdata_offs(req_size, &req_offs)
+ __reqdata_offs(rsp_size, &rsp_offs)
+ );
+
+ cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL);
+ if (!cmd_buf) {
efi_status = EFI_OUT_OF_RESOURCES;
goto out;
}
- rsp_data = kzalloc(rsp_size, GFP_KERNEL);
- if (!rsp_data) {
- efi_status = EFI_OUT_OF_RESOURCES;
- goto out_free_req;
- }
+ req_data = cmd_buf + req_offs;
+ rsp_data = cmd_buf + rsp_offs;
req_data->command_id = QSEE_CMD_UEFI_GET_NEXT_VARIABLE;
req_data->guid_offset = guid_offs;
@@ -572,7 +611,9 @@
goto out_free;
}
- status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size);
+ status = qcom_qseecom_app_send(qcuefi->client,
+ cmd_buf_dma + req_offs, req_size,
+ cmd_buf_dma + rsp_offs, rsp_size);
if (status) {
efi_status = EFI_DEVICE_ERROR;
goto out_free;
@@ -645,9 +686,7 @@
}
out_free:
- kfree(rsp_data);
-out_free_req:
- kfree(req_data);
+ qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma);
out:
return efi_status;
}
@@ -659,26 +698,34 @@
struct qsee_req_uefi_query_variable_info *req_data;
struct qsee_rsp_uefi_query_variable_info *rsp_data;
efi_status_t efi_status = EFI_SUCCESS;
+ dma_addr_t cmd_buf_dma;
+ size_t cmd_buf_size;
+ void *cmd_buf;
+ size_t req_offs;
+ size_t rsp_offs;
int status;
- req_data = kzalloc(sizeof(*req_data), GFP_KERNEL);
- if (!req_data) {
+ cmd_buf_size = qcuefi_buf_align_fields(
+ __reqdata_offs(sizeof(*req_data), &req_offs)
+ __reqdata_offs(sizeof(*rsp_data), &rsp_offs)
+ );
+
+ cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL);
+ if (!cmd_buf) {
efi_status = EFI_OUT_OF_RESOURCES;
goto out;
}
- rsp_data = kzalloc(sizeof(*rsp_data), GFP_KERNEL);
- if (!rsp_data) {
- efi_status = EFI_OUT_OF_RESOURCES;
- goto out_free_req;
- }
+ req_data = cmd_buf + req_offs;
+ rsp_data = cmd_buf + rsp_offs;
req_data->command_id = QSEE_CMD_UEFI_QUERY_VARIABLE_INFO;
req_data->attributes = attr;
req_data->length = sizeof(*req_data);
- status = qcom_qseecom_app_send(qcuefi->client, req_data, sizeof(*req_data), rsp_data,
- sizeof(*rsp_data));
+ status = qcom_qseecom_app_send(qcuefi->client,
+ cmd_buf_dma + req_offs, sizeof(*req_data),
+ cmd_buf_dma + rsp_offs, sizeof(*rsp_data));
if (status) {
efi_status = EFI_DEVICE_ERROR;
goto out_free;
@@ -711,9 +758,7 @@
*max_variable_size = rsp_data->max_variable_size;
out_free:
- kfree(rsp_data);
-out_free_req:
- kfree(req_data);
+ qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma);
out:
return efi_status;
}
diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c
index 520de9b..90283f1 100644
--- a/drivers/firmware/qcom/qcom_scm.c
+++ b/drivers/firmware/qcom/qcom_scm.c
@@ -1576,9 +1576,9 @@
/**
* qcom_scm_qseecom_app_send() - Send to and receive data from a given QSEE app.
* @app_id: The ID of the target app.
- * @req: Request buffer sent to the app (must be DMA-mappable).
+ * @req: DMA address of the request buffer sent to the app.
* @req_size: Size of the request buffer.
- * @rsp: Response buffer, written to by the app (must be DMA-mappable).
+ * @rsp: DMA address of the response buffer, written to by the app.
* @rsp_size: Size of the response buffer.
*
* Sends a request to the QSEE app associated with the given ID and read back
@@ -1589,33 +1589,13 @@
*
* Return: Zero on success, nonzero on failure.
*/
-int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp,
- size_t rsp_size)
+int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size,
+ dma_addr_t rsp, size_t rsp_size)
{
struct qcom_scm_qseecom_resp res = {};
struct qcom_scm_desc desc = {};
- dma_addr_t req_phys;
- dma_addr_t rsp_phys;
int status;
- /* Map request buffer */
- req_phys = dma_map_single(__scm->dev, req, req_size, DMA_TO_DEVICE);
- status = dma_mapping_error(__scm->dev, req_phys);
- if (status) {
- dev_err(__scm->dev, "qseecom: failed to map request buffer\n");
- return status;
- }
-
- /* Map response buffer */
- rsp_phys = dma_map_single(__scm->dev, rsp, rsp_size, DMA_FROM_DEVICE);
- status = dma_mapping_error(__scm->dev, rsp_phys);
- if (status) {
- dma_unmap_single(__scm->dev, req_phys, req_size, DMA_TO_DEVICE);
- dev_err(__scm->dev, "qseecom: failed to map response buffer\n");
- return status;
- }
-
- /* Set up SCM call data */
desc.owner = QSEECOM_TZ_OWNER_TZ_APPS;
desc.svc = QSEECOM_TZ_SVC_APP_ID_PLACEHOLDER;
desc.cmd = QSEECOM_TZ_CMD_APP_SEND;
@@ -1623,18 +1603,13 @@
QCOM_SCM_RW, QCOM_SCM_VAL,
QCOM_SCM_RW, QCOM_SCM_VAL);
desc.args[0] = app_id;
- desc.args[1] = req_phys;
+ desc.args[1] = req;
desc.args[2] = req_size;
- desc.args[3] = rsp_phys;
+ desc.args[3] = rsp;
desc.args[4] = rsp_size;
- /* Perform call */
status = qcom_scm_qseecom_call(&desc, &res);
- /* Unmap buffers */
- dma_unmap_single(__scm->dev, rsp_phys, rsp_size, DMA_FROM_DEVICE);
- dma_unmap_single(__scm->dev, req_phys, req_size, DMA_TO_DEVICE);
-
if (status)
return status;
diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c
index 98b8fd1..80cac3a 100644
--- a/drivers/fpga/dfl-pci.c
+++ b/drivers/fpga/dfl-pci.c
@@ -78,6 +78,7 @@
#define PCIE_DEVICE_ID_SILICOM_PAC_N5011 0x1001
#define PCIE_DEVICE_ID_INTEL_DFL 0xbcce
/* PCI Subdevice ID for PCIE_DEVICE_ID_INTEL_DFL */
+#define PCIE_SUBDEVICE_ID_INTEL_D5005 0x138d
#define PCIE_SUBDEVICE_ID_INTEL_N6000 0x1770
#define PCIE_SUBDEVICE_ID_INTEL_N6001 0x1771
#define PCIE_SUBDEVICE_ID_INTEL_C6100 0x17d4
@@ -102,6 +103,8 @@
{PCI_DEVICE(PCI_VENDOR_ID_SILICOM_DENMARK, PCIE_DEVICE_ID_SILICOM_PAC_N5010),},
{PCI_DEVICE(PCI_VENDOR_ID_SILICOM_DENMARK, PCIE_DEVICE_ID_SILICOM_PAC_N5011),},
{PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL,
+ PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_D5005),},
+ {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL,
PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_N6000),},
{PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL_VF,
PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_N6000),},
diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c
index 1ee62cd..25db014 100644
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@@ -92,7 +92,7 @@
case 0x5e:
return GPIOPANELCTL;
default:
- return -EOPNOTSUPP;
+ return -ENOTSUPP;
}
}
diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c
index 5ef8af8..c097e31 100644
--- a/drivers/gpio/gpio-lpc32xx.c
+++ b/drivers/gpio/gpio-lpc32xx.c
@@ -529,6 +529,7 @@
{ .compatible = "nxp,lpc3220-gpio", },
{ },
};
+MODULE_DEVICE_TABLE(of, lpc32xx_gpio_of_match);
static struct platform_driver lpc32xx_gpio_driver = {
.driver = {
diff --git a/drivers/gpio/gpio-tangier.c b/drivers/gpio/gpio-tangier.c
index b75e0b1..4b29aba 100644
--- a/drivers/gpio/gpio-tangier.c
+++ b/drivers/gpio/gpio-tangier.c
@@ -195,7 +195,8 @@
static void tng_irq_ack(struct irq_data *d)
{
- struct tng_gpio *priv = irq_data_get_irq_chip_data(d);
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct tng_gpio *priv = gpiochip_get_data(gc);
irq_hw_number_t gpio = irqd_to_hwirq(d);
void __iomem *gisr;
u8 shift;
@@ -227,7 +228,8 @@
static void tng_irq_mask(struct irq_data *d)
{
- struct tng_gpio *priv = irq_data_get_irq_chip_data(d);
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct tng_gpio *priv = gpiochip_get_data(gc);
irq_hw_number_t gpio = irqd_to_hwirq(d);
tng_irq_unmask_mask(priv, gpio, false);
@@ -236,7 +238,8 @@
static void tng_irq_unmask(struct irq_data *d)
{
- struct tng_gpio *priv = irq_data_get_irq_chip_data(d);
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+ struct tng_gpio *priv = gpiochip_get_data(gc);
irq_hw_number_t gpio = irqd_to_hwirq(d);
gpiochip_enable_irq(&priv->chip, gpio);
diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c
index d87dd06..9130c69 100644
--- a/drivers/gpio/gpio-tegra186.c
+++ b/drivers/gpio/gpio-tegra186.c
@@ -36,12 +36,6 @@
#define TEGRA186_GPIO_SCR_SEC_REN BIT(27)
#define TEGRA186_GPIO_SCR_SEC_G1W BIT(9)
#define TEGRA186_GPIO_SCR_SEC_G1R BIT(1)
-#define TEGRA186_GPIO_FULL_ACCESS (TEGRA186_GPIO_SCR_SEC_WEN | \
- TEGRA186_GPIO_SCR_SEC_REN | \
- TEGRA186_GPIO_SCR_SEC_G1R | \
- TEGRA186_GPIO_SCR_SEC_G1W)
-#define TEGRA186_GPIO_SCR_SEC_ENABLE (TEGRA186_GPIO_SCR_SEC_WEN | \
- TEGRA186_GPIO_SCR_SEC_REN)
/* control registers */
#define TEGRA186_GPIO_ENABLE_CONFIG 0x00
@@ -177,10 +171,18 @@
value = __raw_readl(secure + TEGRA186_GPIO_SCR);
- if ((value & TEGRA186_GPIO_SCR_SEC_ENABLE) == 0)
- return true;
+ /*
+ * When SCR_SEC_[R|W]EN is unset, then we have full read/write access to all the
+ * registers for given GPIO pin.
+ * When SCR_SEC[R|W]EN is set, then there is need to further check the accompanying
+ * SCR_SEC_G1[R|W] bit to determine read/write access to all the registers for given
+ * GPIO pin.
+ */
- if ((value & TEGRA186_GPIO_FULL_ACCESS) == TEGRA186_GPIO_FULL_ACCESS)
+ if (((value & TEGRA186_GPIO_SCR_SEC_REN) == 0 ||
+ ((value & TEGRA186_GPIO_SCR_SEC_REN) && (value & TEGRA186_GPIO_SCR_SEC_G1R))) &&
+ ((value & TEGRA186_GPIO_SCR_SEC_WEN) == 0 ||
+ ((value & TEGRA186_GPIO_SCR_SEC_WEN) && (value & TEGRA186_GPIO_SCR_SEC_G1W))))
return true;
return false;
diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c
index c18b6b4..94ca9d0 100644
--- a/drivers/gpio/gpio-wcove.c
+++ b/drivers/gpio/gpio-wcove.c
@@ -104,7 +104,7 @@
unsigned int reg = type == CTRL_IN ? GPIO_IN_CTRL_BASE : GPIO_OUT_CTRL_BASE;
if (gpio >= WCOVE_GPIO_NUM)
- return -EOPNOTSUPP;
+ return -ENOTSUPP;
return reg + gpio;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9c62552..b3b8464 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -210,6 +210,7 @@
extern int amdgpu_mcbp;
extern int amdgpu_discovery;
extern int amdgpu_mes;
+extern int amdgpu_mes_log_enable;
extern int amdgpu_mes_kiq;
extern int amdgpu_noretry;
extern int amdgpu_force_asic_type;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index df58a6a..e4d4e55 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -220,7 +220,7 @@
(kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
kfd_mem_limit.max_ttm_mem_limit) ||
(adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed >
- vram_size - reserved_for_pt)) {
+ vram_size - reserved_for_pt - atomic64_read(&adev->vram_pin_size))) {
ret = -ENOMEM;
goto release;
}
@@ -1854,6 +1854,7 @@
err_bo_create:
amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags, xcp_id);
err_reserve_limit:
+ amdgpu_sync_free(&(*mem)->sync);
mutex_destroy(&(*mem)->lock);
if (gobj)
drm_gem_object_put(gobj);
@@ -2900,13 +2901,12 @@
amdgpu_sync_create(&sync_obj);
- /* Validate BOs and map them to GPUVM (update VM page tables). */
+ /* Validate BOs managed by KFD */
list_for_each_entry(mem, &process_info->kfd_bo_list,
validate_list) {
struct amdgpu_bo *bo = mem->bo;
uint32_t domain = mem->domain;
- struct kfd_mem_attachment *attachment;
struct dma_resv_iter cursor;
struct dma_fence *fence;
@@ -2931,6 +2931,25 @@
goto validate_map_fail;
}
}
+ }
+
+ if (failed_size)
+ pr_debug("0x%lx/0x%lx in system\n", failed_size, total_size);
+
+ /* Validate PDs, PTs and evicted DMABuf imports last. Otherwise BO
+ * validations above would invalidate DMABuf imports again.
+ */
+ ret = process_validate_vms(process_info, &exec.ticket);
+ if (ret) {
+ pr_debug("Validating VMs failed, ret: %d\n", ret);
+ goto validate_map_fail;
+ }
+
+ /* Update mappings managed by KFD. */
+ list_for_each_entry(mem, &process_info->kfd_bo_list,
+ validate_list) {
+ struct kfd_mem_attachment *attachment;
+
list_for_each_entry(attachment, &mem->attachments, list) {
if (!attachment->is_mapped)
continue;
@@ -2947,18 +2966,6 @@
}
}
- if (failed_size)
- pr_debug("0x%lx/0x%lx in system\n", failed_size, total_size);
-
- /* Validate PDs, PTs and evicted DMABuf imports last. Otherwise BO
- * validations above would invalidate DMABuf imports again.
- */
- ret = process_validate_vms(process_info, &exec.ticket);
- if (ret) {
- pr_debug("Validating VMs failed, ret: %d\n", ret);
- goto validate_map_fail;
- }
-
/* Update mappings not managed by KFD */
list_for_each_entry(peer_vm, &process_info->vm_list_head,
vm_list_node) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 0a4b097..ec888fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -819,7 +819,7 @@
p->bytes_moved += ctx.bytes_moved;
if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
- amdgpu_bo_in_cpu_visible_vram(bo))
+ amdgpu_res_cpu_visible(adev, bo->tbo.resource))
p->bytes_moved_vis += ctx.bytes_moved;
if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index aa16d51..7753a2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4135,18 +4135,22 @@
adev->ip_blocks[i].status.hw = true;
}
}
+ } else if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) &&
+ !amdgpu_device_has_display_hardware(adev)) {
+ r = psp_gpu_reset(adev);
} else {
- tmp = amdgpu_reset_method;
- /* It should do a default reset when loading or reloading the driver,
- * regardless of the module parameter reset_method.
- */
- amdgpu_reset_method = AMD_RESET_METHOD_NONE;
- r = amdgpu_asic_reset(adev);
- amdgpu_reset_method = tmp;
- if (r) {
- dev_err(adev->dev, "asic reset on init failed\n");
- goto failed;
- }
+ tmp = amdgpu_reset_method;
+ /* It should do a default reset when loading or reloading the driver,
+ * regardless of the module parameter reset_method.
+ */
+ amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+ r = amdgpu_asic_reset(adev);
+ amdgpu_reset_method = tmp;
+ }
+
+ if (r) {
+ dev_err(adev->dev, "asic reset on init failed\n");
+ goto failed;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index fdd36fb..ac5bf01 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -1896,6 +1896,7 @@
amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
break;
case IP_VERSION(14, 0, 0):
+ case IP_VERSION(14, 0, 1):
amdgpu_device_ip_block_add(adev, &smu_v14_0_ip_block);
break;
default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 80b9642..e427729 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -195,6 +195,7 @@
int amdgpu_mcbp = -1;
int amdgpu_discovery = -1;
int amdgpu_mes;
+int amdgpu_mes_log_enable = 0;
int amdgpu_mes_kiq;
int amdgpu_noretry = -1;
int amdgpu_force_asic_type = -1;
@@ -668,6 +669,15 @@
module_param_named(mes, amdgpu_mes, int, 0444);
/**
+ * DOC: mes_log_enable (int)
+ * Enable Micro Engine Scheduler log. This is used to enable/disable MES internal log.
+ * (0 = disabled (default), 1 = enabled)
+ */
+MODULE_PARM_DESC(mes_log_enable,
+ "Enable Micro Engine Scheduler log (0 = disabled (default), 1 = enabled)");
+module_param_named(mes_log_enable, amdgpu_mes_log_enable, int, 0444);
+
+/**
* DOC: mes_kiq (int)
* Enable Micro Engine Scheduler KIQ. This is a new engine pipe for kiq.
* (0 = disabled (default), 1 = enabled)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4b3000c..e4742b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -304,12 +304,15 @@
dma_fence_set_error(finished, -ECANCELED);
if (finished->error < 0) {
- DRM_INFO("Skip scheduling IBs!\n");
+ dev_dbg(adev->dev, "Skip scheduling IBs in ring(%s)",
+ ring->name);
} else {
r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job,
&fence);
if (r)
- DRM_ERROR("Error scheduling IBs (%d)\n", r);
+ dev_err(adev->dev,
+ "Error scheduling IBs (%d) in ring(%s)", r,
+ ring->name);
}
job->job_run_counter++;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index a98e03e..1569bef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -102,7 +102,10 @@
{
int r;
- r = amdgpu_bo_create_kernel(adev, PAGE_SIZE, PAGE_SIZE,
+ if (!amdgpu_mes_log_enable)
+ return 0;
+
+ r = amdgpu_bo_create_kernel(adev, AMDGPU_MES_LOG_BUFFER_SIZE, PAGE_SIZE,
AMDGPU_GEM_DOMAIN_GTT,
&adev->mes.event_log_gpu_obj,
&adev->mes.event_log_gpu_addr,
@@ -1129,6 +1132,7 @@
return;
amdgpu_mes_remove_hw_queue(adev, ring->hw_queue_id);
+ del_timer_sync(&ring->fence_drv.fallback_timer);
amdgpu_ring_fini(ring);
kfree(ring);
}
@@ -1549,12 +1553,11 @@
uint32_t *mem = (uint32_t *)(adev->mes.event_log_cpu_addr);
seq_hex_dump(m, "", DUMP_PREFIX_OFFSET, 32, 4,
- mem, PAGE_SIZE, false);
+ mem, AMDGPU_MES_LOG_BUFFER_SIZE, false);
return 0;
}
-
DEFINE_SHOW_ATTRIBUTE(amdgpu_debugfs_mes_event_log);
#endif
@@ -1565,7 +1568,7 @@
#if defined(CONFIG_DEBUG_FS)
struct drm_minor *minor = adev_to_drm(adev)->primary;
struct dentry *root = minor->debugfs_root;
- if (adev->enable_mes)
+ if (adev->enable_mes && amdgpu_mes_log_enable)
debugfs_create_file("amdgpu_mes_event_log", 0444, root,
adev, &amdgpu_debugfs_mes_event_log_fops);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 7d4f93f..4c8fc31 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -52,6 +52,7 @@
#define AMDGPU_MES_PROC_CTX_SIZE 0x1000 /* one page area */
#define AMDGPU_MES_GANG_CTX_SIZE 0x1000 /* one page area */
+#define AMDGPU_MES_LOG_BUFFER_SIZE 0x4000 /* Maximu log buffer size for MES */
struct amdgpu_mes_funcs;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 010b0cb..f6d5034 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -605,6 +605,8 @@
else
amdgpu_bo_placement_from_domain(bo, bp->domain);
if (bp->type == ttm_bo_type_kernel)
+ bo->tbo.priority = 2;
+ else if (!(bp->flags & AMDGPU_GEM_CREATE_DISCARDABLE))
bo->tbo.priority = 1;
if (!bp->destroy)
@@ -617,8 +619,7 @@
return r;
if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
- bo->tbo.resource->mem_type == TTM_PL_VRAM &&
- amdgpu_bo_in_cpu_visible_vram(bo))
+ amdgpu_res_cpu_visible(adev, bo->tbo.resource))
amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
ctx.bytes_moved);
else
@@ -1242,14 +1243,18 @@
* amdgpu_bo_move_notify - notification about a memory move
* @bo: pointer to a buffer object
* @evict: if this move is evicting the buffer from the graphics address space
+ * @new_mem: new resource for backing the BO
*
* Marks the corresponding &amdgpu_bo buffer object as invalid, also performs
* bookkeeping.
* TTM driver callback which is called when ttm moves a buffer.
*/
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict)
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+ bool evict,
+ struct ttm_resource *new_mem)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
+ struct ttm_resource *old_mem = bo->resource;
struct amdgpu_bo *abo;
if (!amdgpu_bo_is_amdgpu_bo(bo))
@@ -1261,34 +1266,36 @@
amdgpu_bo_kunmap(abo);
if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach &&
- bo->resource->mem_type != TTM_PL_SYSTEM)
+ old_mem && old_mem->mem_type != TTM_PL_SYSTEM)
dma_buf_move_notify(abo->tbo.base.dma_buf);
- /* remember the eviction */
- if (evict)
- atomic64_inc(&adev->num_evictions);
+ /* move_notify is called before move happens */
+ trace_amdgpu_bo_move(abo, new_mem ? new_mem->mem_type : -1,
+ old_mem ? old_mem->mem_type : -1);
}
void amdgpu_bo_get_memory(struct amdgpu_bo *bo,
struct amdgpu_mem_stats *stats)
{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+ struct ttm_resource *res = bo->tbo.resource;
uint64_t size = amdgpu_bo_size(bo);
struct drm_gem_object *obj;
unsigned int domain;
bool shared;
/* Abort if the BO doesn't currently have a backing store */
- if (!bo->tbo.resource)
+ if (!res)
return;
obj = &bo->tbo.base;
shared = drm_gem_object_is_shared_for_memory_stats(obj);
- domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type);
+ domain = amdgpu_mem_type_to_domain(res->mem_type);
switch (domain) {
case AMDGPU_GEM_DOMAIN_VRAM:
stats->vram += size;
- if (amdgpu_bo_in_cpu_visible_vram(bo))
+ if (amdgpu_res_cpu_visible(adev, bo->tbo.resource))
stats->visible_vram += size;
if (shared)
stats->vram_shared += size;
@@ -1389,10 +1396,7 @@
/* Remember that this BO was accessed by the CPU */
abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
- if (bo->resource->mem_type != TTM_PL_VRAM)
- return 0;
-
- if (amdgpu_bo_in_cpu_visible_vram(abo))
+ if (amdgpu_res_cpu_visible(adev, bo->resource))
return 0;
/* Can't move a pinned BO to visible VRAM */
@@ -1415,7 +1419,7 @@
/* this should never happen */
if (bo->resource->mem_type == TTM_PL_VRAM &&
- !amdgpu_bo_in_cpu_visible_vram(abo))
+ !amdgpu_res_cpu_visible(adev, bo->resource))
return VM_FAULT_SIGBUS;
ttm_bo_move_to_lru_tail_unlocked(bo);
@@ -1579,6 +1583,7 @@
*/
u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m)
{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
struct dma_buf_attachment *attachment;
struct dma_buf *dma_buf;
const char *placement;
@@ -1587,10 +1592,11 @@
if (dma_resv_trylock(bo->tbo.base.resv)) {
unsigned int domain;
+
domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type);
switch (domain) {
case AMDGPU_GEM_DOMAIN_VRAM:
- if (amdgpu_bo_in_cpu_visible_vram(bo))
+ if (amdgpu_res_cpu_visible(adev, bo->tbo.resource))
placement = "VRAM VISIBLE";
else
placement = "VRAM";
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index be679c4..bc42ccb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -251,28 +251,6 @@
}
/**
- * amdgpu_bo_in_cpu_visible_vram - check if BO is (partly) in visible VRAM
- */
-static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo)
-{
- struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
- struct amdgpu_res_cursor cursor;
-
- if (!bo->tbo.resource || bo->tbo.resource->mem_type != TTM_PL_VRAM)
- return false;
-
- amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor);
- while (cursor.remaining) {
- if (cursor.start < adev->gmc.visible_vram_size)
- return true;
-
- amdgpu_res_next(&cursor, cursor.size);
- }
-
- return false;
-}
-
-/**
* amdgpu_bo_explicit_sync - return whether the bo is explicitly synced
*/
static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
@@ -350,7 +328,9 @@
int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
size_t buffer_size, uint32_t *metadata_size,
uint64_t *flags);
-void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict);
+void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+ bool evict,
+ struct ttm_resource *new_mem);
void amdgpu_bo_release_notify(struct ttm_buffer_object *bo);
vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo);
void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index fc418e6..109fe55 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -133,7 +133,7 @@
} else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
!(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) &&
- amdgpu_bo_in_cpu_visible_vram(abo)) {
+ amdgpu_res_cpu_visible(adev, bo->resource)) {
/* Try evicting to the CPU inaccessible part of VRAM
* first, but only set GTT as busy placement, so this
@@ -403,40 +403,55 @@
return r;
}
+/**
+ * amdgpu_res_cpu_visible - Check that resource can be accessed by CPU
+ * @adev: amdgpu device
+ * @res: the resource to check
+ *
+ * Returns: true if the full resource is CPU visible, false otherwise.
+ */
+bool amdgpu_res_cpu_visible(struct amdgpu_device *adev,
+ struct ttm_resource *res)
+{
+ struct amdgpu_res_cursor cursor;
+
+ if (!res)
+ return false;
+
+ if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT ||
+ res->mem_type == AMDGPU_PL_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL)
+ return true;
+
+ if (res->mem_type != TTM_PL_VRAM)
+ return false;
+
+ amdgpu_res_first(res, 0, res->size, &cursor);
+ while (cursor.remaining) {
+ if ((cursor.start + cursor.size) >= adev->gmc.visible_vram_size)
+ return false;
+ amdgpu_res_next(&cursor, cursor.size);
+ }
+
+ return true;
+}
+
/*
- * amdgpu_mem_visible - Check that memory can be accessed by ttm_bo_move_memcpy
+ * amdgpu_res_copyable - Check that memory can be accessed by ttm_bo_move_memcpy
*
* Called by amdgpu_bo_move()
*/
-static bool amdgpu_mem_visible(struct amdgpu_device *adev,
- struct ttm_resource *mem)
+static bool amdgpu_res_copyable(struct amdgpu_device *adev,
+ struct ttm_resource *mem)
{
- u64 mem_size = (u64)mem->size;
- struct amdgpu_res_cursor cursor;
- u64 end;
-
- if (mem->mem_type == TTM_PL_SYSTEM ||
- mem->mem_type == TTM_PL_TT)
- return true;
- if (mem->mem_type != TTM_PL_VRAM)
+ if (!amdgpu_res_cpu_visible(adev, mem))
return false;
- amdgpu_res_first(mem, 0, mem_size, &cursor);
- end = cursor.start + cursor.size;
- while (cursor.remaining) {
- amdgpu_res_next(&cursor, cursor.size);
+ /* ttm_resource_ioremap only supports contiguous memory */
+ if (mem->mem_type == TTM_PL_VRAM &&
+ !(mem->placement & TTM_PL_FLAG_CONTIGUOUS))
+ return false;
- if (!cursor.remaining)
- break;
-
- /* ttm_resource_ioremap only supports contiguous memory */
- if (end != cursor.start)
- return false;
-
- end = cursor.start + cursor.size;
- }
-
- return end <= adev->gmc.visible_vram_size;
+ return true;
}
/*
@@ -466,14 +481,16 @@
if (!old_mem || (old_mem->mem_type == TTM_PL_SYSTEM &&
bo->ttm == NULL)) {
+ amdgpu_bo_move_notify(bo, evict, new_mem);
ttm_bo_move_null(bo, new_mem);
- goto out;
+ return 0;
}
if (old_mem->mem_type == TTM_PL_SYSTEM &&
(new_mem->mem_type == TTM_PL_TT ||
new_mem->mem_type == AMDGPU_PL_PREEMPT)) {
+ amdgpu_bo_move_notify(bo, evict, new_mem);
ttm_bo_move_null(bo, new_mem);
- goto out;
+ return 0;
}
if ((old_mem->mem_type == TTM_PL_TT ||
old_mem->mem_type == AMDGPU_PL_PREEMPT) &&
@@ -483,9 +500,10 @@
return r;
amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm);
+ amdgpu_bo_move_notify(bo, evict, new_mem);
ttm_resource_free(bo, &bo->resource);
ttm_bo_assign_mem(bo, new_mem);
- goto out;
+ return 0;
}
if (old_mem->mem_type == AMDGPU_PL_GDS ||
@@ -497,8 +515,9 @@
new_mem->mem_type == AMDGPU_PL_OA ||
new_mem->mem_type == AMDGPU_PL_DOORBELL) {
/* Nothing to save here */
+ amdgpu_bo_move_notify(bo, evict, new_mem);
ttm_bo_move_null(bo, new_mem);
- goto out;
+ return 0;
}
if (bo->type == ttm_bo_type_device &&
@@ -510,27 +529,28 @@
abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
}
- if (adev->mman.buffer_funcs_enabled) {
- if (((old_mem->mem_type == TTM_PL_SYSTEM &&
- new_mem->mem_type == TTM_PL_VRAM) ||
- (old_mem->mem_type == TTM_PL_VRAM &&
- new_mem->mem_type == TTM_PL_SYSTEM))) {
- hop->fpfn = 0;
- hop->lpfn = 0;
- hop->mem_type = TTM_PL_TT;
- hop->flags = TTM_PL_FLAG_TEMPORARY;
- return -EMULTIHOP;
- }
-
- r = amdgpu_move_blit(bo, evict, new_mem, old_mem);
- } else {
- r = -ENODEV;
+ if (adev->mman.buffer_funcs_enabled &&
+ ((old_mem->mem_type == TTM_PL_SYSTEM &&
+ new_mem->mem_type == TTM_PL_VRAM) ||
+ (old_mem->mem_type == TTM_PL_VRAM &&
+ new_mem->mem_type == TTM_PL_SYSTEM))) {
+ hop->fpfn = 0;
+ hop->lpfn = 0;
+ hop->mem_type = TTM_PL_TT;
+ hop->flags = TTM_PL_FLAG_TEMPORARY;
+ return -EMULTIHOP;
}
+ amdgpu_bo_move_notify(bo, evict, new_mem);
+ if (adev->mman.buffer_funcs_enabled)
+ r = amdgpu_move_blit(bo, evict, new_mem, old_mem);
+ else
+ r = -ENODEV;
+
if (r) {
/* Check that all memory is CPU accessible */
- if (!amdgpu_mem_visible(adev, old_mem) ||
- !amdgpu_mem_visible(adev, new_mem)) {
+ if (!amdgpu_res_copyable(adev, old_mem) ||
+ !amdgpu_res_copyable(adev, new_mem)) {
pr_err("Move buffer fallback to memcpy unavailable\n");
return r;
}
@@ -540,11 +560,10 @@
return r;
}
- trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
-out:
- /* update statistics */
+ /* update statistics after the move */
+ if (evict)
+ atomic64_inc(&adev->num_evictions);
atomic64_add(bo->base.size, &adev->num_bytes_moved);
- amdgpu_bo_move_notify(bo, evict);
return 0;
}
@@ -557,7 +576,6 @@
struct ttm_resource *mem)
{
struct amdgpu_device *adev = amdgpu_ttm_adev(bdev);
- size_t bus_size = (size_t)mem->size;
switch (mem->mem_type) {
case TTM_PL_SYSTEM:
@@ -568,9 +586,6 @@
break;
case TTM_PL_VRAM:
mem->bus.offset = mem->start << PAGE_SHIFT;
- /* check if it's visible */
- if ((mem->bus.offset + bus_size) > adev->gmc.visible_vram_size)
- return -EINVAL;
if (adev->mman.aper_base_kaddr &&
mem->placement & TTM_PL_FLAG_CONTIGUOUS)
@@ -1548,7 +1563,7 @@
static void
amdgpu_bo_delete_mem_notify(struct ttm_buffer_object *bo)
{
- amdgpu_bo_move_notify(bo, false);
+ amdgpu_bo_move_notify(bo, false, NULL);
}
static struct ttm_device_funcs amdgpu_bo_driver = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 65ec821..32cf6b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -139,6 +139,9 @@
int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr,
uint64_t start);
+bool amdgpu_res_cpu_visible(struct amdgpu_device *adev,
+ struct ttm_resource *res);
+
int amdgpu_ttm_init(struct amdgpu_device *adev);
void amdgpu_ttm_fini(struct amdgpu_device *adev);
void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
index 0df97c3..f7c7353 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c
@@ -774,6 +774,9 @@
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ if (amdgpu_in_reset(adev) || adev->in_s0ix || adev->in_suspend)
+ return 0;
+
return umsch_mm_test(adev);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 4299ce3..9408906 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1613,6 +1613,37 @@
trace_amdgpu_vm_bo_map(bo_va, mapping);
}
+/* Validate operation parameters to prevent potential abuse */
+static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev,
+ struct amdgpu_bo *bo,
+ uint64_t saddr,
+ uint64_t offset,
+ uint64_t size)
+{
+ uint64_t tmp, lpfn;
+
+ if (saddr & AMDGPU_GPU_PAGE_MASK
+ || offset & AMDGPU_GPU_PAGE_MASK
+ || size & AMDGPU_GPU_PAGE_MASK)
+ return -EINVAL;
+
+ if (check_add_overflow(saddr, size, &tmp)
+ || check_add_overflow(offset, size, &tmp)
+ || size == 0 /* which also leads to end < begin */)
+ return -EINVAL;
+
+ /* make sure object fit at this offset */
+ if (bo && offset + size > amdgpu_bo_size(bo))
+ return -EINVAL;
+
+ /* Ensure last pfn not exceed max_pfn */
+ lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT;
+ if (lpfn >= adev->vm_manager.max_pfn)
+ return -EINVAL;
+
+ return 0;
+}
+
/**
* amdgpu_vm_bo_map - map bo inside a vm
*
@@ -1639,21 +1670,14 @@
struct amdgpu_bo *bo = bo_va->base.bo;
struct amdgpu_vm *vm = bo_va->base.vm;
uint64_t eaddr;
+ int r;
- /* validate the parameters */
- if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK)
- return -EINVAL;
- if (saddr + size <= saddr || offset + size <= offset)
- return -EINVAL;
-
- /* make sure object fit at this offset */
- eaddr = saddr + size - 1;
- if ((bo && offset + size > amdgpu_bo_size(bo)) ||
- (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT))
- return -EINVAL;
+ r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size);
+ if (r)
+ return r;
saddr /= AMDGPU_GPU_PAGE_SIZE;
- eaddr /= AMDGPU_GPU_PAGE_SIZE;
+ eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;
tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr);
if (tmp) {
@@ -1706,17 +1730,9 @@
uint64_t eaddr;
int r;
- /* validate the parameters */
- if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK)
- return -EINVAL;
- if (saddr + size <= saddr || offset + size <= offset)
- return -EINVAL;
-
- /* make sure object fit at this offset */
- eaddr = saddr + size - 1;
- if ((bo && offset + size > amdgpu_bo_size(bo)) ||
- (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT))
- return -EINVAL;
+ r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size);
+ if (r)
+ return r;
/* Allocate all the needed memory */
mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
@@ -1730,7 +1746,7 @@
}
saddr /= AMDGPU_GPU_PAGE_SIZE;
- eaddr /= AMDGPU_GPU_PAGE_SIZE;
+ eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;
mapping->start = saddr;
mapping->last = eaddr;
@@ -1817,10 +1833,14 @@
struct amdgpu_bo_va_mapping *before, *after, *tmp, *next;
LIST_HEAD(removed);
uint64_t eaddr;
+ int r;
- eaddr = saddr + size - 1;
+ r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size);
+ if (r)
+ return r;
+
saddr /= AMDGPU_GPU_PAGE_SIZE;
- eaddr /= AMDGPU_GPU_PAGE_SIZE;
+ eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE;
/* Allocate all the needed memory */
before = kzalloc(sizeof(*before), GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 6695481..c23d97d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -205,7 +205,7 @@
dpm_ctl &= 0xfffffffe; /* Disable DPM */
WREG32(vpe_get_reg_offset(vpe, 0, vpe->regs.dpm_enable), dpm_ctl);
dev_dbg(adev->dev, "%s: disable vpe dpm\n", __func__);
- return 0;
+ return -EINVAL;
}
int amdgpu_vpe_psp_update_sram(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index d6f808a..fbb43ae 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -62,6 +62,11 @@
adev->doorbell_index.max_assignment = AMDGPU_DOORBELL_LAYOUT1_MAX_ASSIGNMENT << 1;
}
+static bool aqua_vanjaram_xcp_vcn_shared(struct amdgpu_device *adev)
+{
+ return (adev->xcp_mgr->num_xcps > adev->vcn.num_vcn_inst);
+}
+
static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev,
uint32_t inst_idx, struct amdgpu_ring *ring)
{
@@ -87,7 +92,7 @@
case AMDGPU_RING_TYPE_VCN_ENC:
case AMDGPU_RING_TYPE_VCN_JPEG:
ip_blk = AMDGPU_XCP_VCN;
- if (adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE)
+ if (aqua_vanjaram_xcp_vcn_shared(adev))
inst_mask = 1 << (inst_idx * 2);
break;
default:
@@ -140,10 +145,12 @@
aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id);
- /* VCN is shared by two partitions under CPX MODE */
+ /* VCN may be shared by two partitions under CPX MODE in certain
+ * configs.
+ */
if ((ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC ||
- ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) &&
- adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE)
+ ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) &&
+ aqua_vanjaram_xcp_vcn_shared(adev))
aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id + 1);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index f90905e..701146d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -9186,7 +9186,7 @@
7 + /* PIPELINE_SYNC */
SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
- 2 + /* VM_FLUSH */
+ 4 + /* VM_FLUSH */
8 + /* FENCE for VM_FLUSH */
20 + /* GDS switch */
4 + /* double SWITCH_BUFFER,
@@ -9276,7 +9276,6 @@
7 + /* gfx_v10_0_ring_emit_pipeline_sync */
SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
- 2 + /* gfx_v10_0_ring_emit_vm_flush */
8 + 8 + 8, /* gfx_v10_0_ring_emit_fence_kiq x3 for user fence, vm fence */
.emit_ib_size = 7, /* gfx_v10_0_ring_emit_ib_compute */
.emit_ib = gfx_v10_0_ring_emit_ib_compute,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 1770e49..f00e05a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1635,7 +1635,7 @@
active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa));
}
- active_rb_bitmap |= global_active_rb_bitmap;
+ active_rb_bitmap &= global_active_rb_bitmap;
adev->gfx.config.backend_enable_mask = active_rb_bitmap;
adev->gfx.config.num_rbs = hweight32(active_rb_bitmap);
}
@@ -5465,6 +5465,7 @@
/* Make sure that we can't skip the SET_Q_MODE packets when the VM
* changed in any way.
*/
+ ring->set_q_mode_offs = 0;
ring->set_q_mode_ptr = NULL;
}
@@ -6191,7 +6192,7 @@
7 + /* PIPELINE_SYNC */
SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
- 2 + /* VM_FLUSH */
+ 4 + /* VM_FLUSH */
8 + /* FENCE for VM_FLUSH */
20 + /* GDS switch */
5 + /* COND_EXEC */
@@ -6277,7 +6278,6 @@
7 + /* gfx_v11_0_ring_emit_pipeline_sync */
SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
- 2 + /* gfx_v11_0_ring_emit_vm_flush */
8 + 8 + 8, /* gfx_v11_0_ring_emit_fence_kiq x3 for user fence, vm fence */
.emit_ib_size = 7, /* gfx_v11_0_ring_emit_ib_compute */
.emit_ib = gfx_v11_0_ring_emit_ib_compute,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 6f97a6d..99dbd23 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -6981,7 +6981,6 @@
7 + /* gfx_v9_0_ring_emit_pipeline_sync */
SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
- 2 + /* gfx_v9_0_ring_emit_vm_flush */
8 + 8 + 8 + /* gfx_v9_0_ring_emit_fence x3 for user fence, vm fence */
7 + /* gfx_v9_0_emit_mem_sync */
5 + /* gfx_v9_0_emit_wave_limit for updating mmSPI_WCL_PIPE_PERCENT_GFX register */
@@ -7019,7 +7018,6 @@
7 + /* gfx_v9_0_ring_emit_pipeline_sync */
SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 +
SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 +
- 2 + /* gfx_v9_0_ring_emit_vm_flush */
8 + 8 + 8, /* gfx_v9_0_ring_emit_fence_kiq x3 for user fence, vm fence */
.emit_ib_size = 7, /* gfx_v9_0_ring_emit_ib_compute */
.emit_fence = gfx_v9_0_ring_emit_fence_kiq,
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 072c478..63f281a9 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -411,8 +411,11 @@
mes_set_hw_res_pkt.enable_reg_active_poll = 1;
mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
mes_set_hw_res_pkt.oversubscription_timer = 50;
- mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
- mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr;
+ if (amdgpu_mes_log_enable) {
+ mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
+ mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr =
+ mes->event_log_gpu_addr;
+ }
return mes_v11_0_submit_pkt_and_poll_completion(mes,
&mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt),
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 34237a1..e708468 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -368,7 +368,8 @@
u32 ref_and_mask = 0;
const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg;
- ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me;
+ ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0
+ << (ring->me % adev->sdma.num_inst_per_aid);
sdma_v4_4_2_wait_reg_mem(ring, 0, 1,
adev->nbio.funcs->get_hdp_flush_done_offset(adev),
@@ -1602,19 +1603,9 @@
u32 sdma_cntl;
sdma_cntl = RREG32_SDMA(type, regSDMA_CNTL);
- switch (state) {
- case AMDGPU_IRQ_STATE_DISABLE:
- sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL,
- DRAM_ECC_INT_ENABLE, 0);
- WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl);
- break;
- /* sdma ecc interrupt is enabled by default
- * driver doesn't need to do anything to
- * enable the interrupt */
- case AMDGPU_IRQ_STATE_ENABLE:
- default:
- break;
- }
+ sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, DRAM_ECC_INT_ENABLE,
+ state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0);
+ WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 42f4bd2..da01b52 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -280,17 +280,21 @@
u32 ref_and_mask = 0;
const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg;
- ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me;
+ if (ring->me > 1) {
+ amdgpu_asic_flush_hdp(adev, ring);
+ } else {
+ ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me;
- amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
- SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) |
- SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */
- amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2);
- amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2);
- amdgpu_ring_write(ring, ref_and_mask); /* reference */
- amdgpu_ring_write(ring, ref_and_mask); /* mask */
- amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
- SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */
+ amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
+ SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) |
+ SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */
+ amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2);
+ amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2);
+ amdgpu_ring_write(ring, ref_and_mask); /* reference */
+ amdgpu_ring_write(ring, ref_and_mask); /* mask */
+ amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
+ SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */
+ }
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 581a3bd..43ca63f 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -457,10 +457,8 @@
{
switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
case IP_VERSION(11, 0, 0):
- return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC);
case IP_VERSION(11, 0, 2):
case IP_VERSION(11, 0, 3):
- return false;
default:
return true;
}
@@ -722,7 +720,10 @@
AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_JPEG |
AMD_PG_SUPPORT_GFX_PG;
- adev->external_rev_id = adev->rev_id + 0x1;
+ if (adev->rev_id == 0)
+ adev->external_rev_id = 0x1;
+ else
+ adev->external_rev_id = adev->rev_id + 0x10;
break;
case IP_VERSION(11, 5, 1):
adev->cg_flags =
@@ -869,10 +870,35 @@
return soc21_common_hw_fini(adev);
}
+static bool soc21_need_reset_on_resume(struct amdgpu_device *adev)
+{
+ u32 sol_reg1, sol_reg2;
+
+ /* Will reset for the following suspend abort cases.
+ * 1) Only reset dGPU side.
+ * 2) S3 suspend got aborted and TOS is active.
+ */
+ if (!(adev->flags & AMD_IS_APU) && adev->in_s3 &&
+ !adev->suspend_complete) {
+ sol_reg1 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81);
+ msleep(100);
+ sol_reg2 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81);
+
+ return (sol_reg1 != sol_reg2);
+ }
+
+ return false;
+}
+
static int soc21_common_resume(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ if (soc21_need_reset_on_resume(adev)) {
+ dev_info(adev->dev, "S3 suspend aborted, resetting...");
+ soc21_asic_reset(adev);
+ }
+
return soc21_common_hw_init(adev);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
index 84368cf..bd57896 100644
--- a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c
@@ -225,6 +225,8 @@
WREG32_SOC15(VCN, 0, regVCN_UMSCH_RB_SIZE, ring->ring_size);
+ ring->wptr = 0;
+
data = RREG32_SOC15(VCN, 0, regVCN_RB_ENABLE);
data &= ~(VCN_RB_ENABLE__AUDIO_RB_EN_MASK);
WREG32_SOC15(VCN, 0, regVCN_RB_ENABLE, data);
diff --git a/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c b/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c
index 769eb8f..09315dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c
@@ -144,6 +144,12 @@
WREG32(vpe_get_reg_offset(vpe, j, regVPEC_CNTL), ret);
}
+ /* setup collaborate mode */
+ vpe_v6_1_set_collaborate_mode(vpe, true);
+ /* setup DPM */
+ if (amdgpu_vpe_configure_dpm(vpe))
+ dev_warn(adev->dev, "VPE failed to enable DPM\n");
+
/*
* For VPE 6.1.1, still only need to add master's offset, and psp will apply it to slave as well.
* Here use instance 0 as master.
@@ -159,11 +165,7 @@
adev->vpe.cmdbuf_cpu_addr[0] = f32_offset;
adev->vpe.cmdbuf_cpu_addr[1] = f32_cntl;
- amdgpu_vpe_psp_update_sram(adev);
- vpe_v6_1_set_collaborate_mode(vpe, true);
- amdgpu_vpe_configure_dpm(vpe);
-
- return 0;
+ return amdgpu_vpe_psp_update_sram(adev);
}
vpe_hdr = (const struct vpe_firmware_header_v1_0 *)adev->vpe.fw->data;
@@ -196,8 +198,6 @@
}
vpe_v6_1_halt(vpe, false);
- vpe_v6_1_set_collaborate_mode(vpe, true);
- amdgpu_vpe_configure_dpm(vpe);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index f9631f4..55aa74c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -779,8 +779,8 @@
* nodes, but not more than args->num_of_nodes as that is
* the amount of memory allocated by user
*/
- pa = kzalloc((sizeof(struct kfd_process_device_apertures) *
- args->num_of_nodes), GFP_KERNEL);
+ pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures),
+ GFP_KERNEL);
if (!pa)
return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 041ec3d..719d6d3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -960,7 +960,6 @@
{
struct kfd_node *node;
int i;
- int count;
if (!kfd->init_complete)
return;
@@ -968,12 +967,10 @@
/* for runtime suspend, skip locking kfd */
if (!run_pm) {
mutex_lock(&kfd_processes_mutex);
- count = ++kfd_locked;
- mutex_unlock(&kfd_processes_mutex);
-
/* For first KFD device suspend all the KFD processes */
- if (count == 1)
+ if (++kfd_locked == 1)
kfd_suspend_all_processes();
+ mutex_unlock(&kfd_processes_mutex);
}
for (i = 0; i < kfd->num_nodes; i++) {
@@ -984,7 +981,7 @@
int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
{
- int ret, count, i;
+ int ret, i;
if (!kfd->init_complete)
return 0;
@@ -998,12 +995,10 @@
/* for runtime resume, skip unlocking kfd */
if (!run_pm) {
mutex_lock(&kfd_processes_mutex);
- count = --kfd_locked;
- mutex_unlock(&kfd_processes_mutex);
-
- WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
- if (count == 0)
+ if (--kfd_locked == 0)
ret = kfd_resume_all_processes();
+ WARN_ONCE(kfd_locked < 0, "KFD suspend / resume ref. error");
+ mutex_unlock(&kfd_processes_mutex);
}
return ret;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index f4d395e..0b65555 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2001,6 +2001,7 @@
dev_err(dev, "HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n");
while (halt_if_hws_hang)
schedule();
+ kfd_hws_hang(dqm);
return -ETIME;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index bdc01ca..5c8d81b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -509,10 +509,19 @@
start = start_mgr << PAGE_SHIFT;
end = (last_mgr + 1) << PAGE_SHIFT;
+ r = amdgpu_amdkfd_reserve_mem_limit(node->adev,
+ prange->npages * PAGE_SIZE,
+ KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+ node->xcp ? node->xcp->id : 0);
+ if (r) {
+ dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r);
+ return -ENOSPC;
+ }
+
r = svm_range_vram_node_new(node, prange, true);
if (r) {
dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r);
- return r;
+ goto out;
}
ttm_res_offset = (start_mgr - prange->start + prange->offset) << PAGE_SHIFT;
@@ -545,6 +554,11 @@
svm_range_vram_node_free(prange);
}
+out:
+ amdgpu_amdkfd_unreserve_mem_limit(node->adev,
+ prange->npages * PAGE_SIZE,
+ KFD_IOC_ALLOC_MEM_FLAGS_VRAM,
+ node->xcp ? node->xcp->id : 0);
return r < 0 ? r : 0;
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 717a60d..451bb05 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -819,9 +819,9 @@
mutex_lock(&kfd_processes_mutex);
if (kfd_is_locked()) {
- mutex_unlock(&kfd_processes_mutex);
pr_debug("KFD is locked! Cannot create process");
- return ERR_PTR(-EINVAL);
+ process = ERR_PTR(-EINVAL);
+ goto out;
}
/* A prior open of /dev/kfd could have already created the process. */
@@ -829,6 +829,14 @@
if (process) {
pr_debug("Process already found\n");
} else {
+ /* If the process just called exec(3), it is possible that the
+ * cleanup of the kfd_process (following the release of the mm
+ * of the old process image) is still in the cleanup work queue.
+ * Make sure to drain any job before trying to recreate any
+ * resource for this process.
+ */
+ flush_workqueue(kfd_process_wq);
+
process = create_process(thread);
if (IS_ERR(process))
goto out;
@@ -1922,6 +1930,8 @@
rcu_read_lock();
ef = dma_fence_get_rcu_safe(&p->ef);
rcu_read_unlock();
+ if (!ef)
+ return -EINVAL;
ret = dma_fence_signal(ef);
dma_fence_put(ef);
@@ -1949,10 +1959,9 @@
* they are responsible stopping the queues and scheduling
* the restore work.
*/
- if (!signal_eviction_fence(p))
- queue_delayed_work(kfd_restore_wq, &p->restore_work,
- msecs_to_jiffies(PROCESS_RESTORE_TIME_MS));
- else
+ if (signal_eviction_fence(p) ||
+ mod_delayed_work(kfd_restore_wq, &p->restore_work,
+ msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
kfd_process_restore_queues(p);
pr_debug("Finished evicting pasid 0x%x\n", p->pasid);
@@ -2011,9 +2020,9 @@
if (ret) {
pr_debug("Failed to restore BOs of pasid 0x%x, retry after %d ms\n",
p->pasid, PROCESS_BACK_OFF_TIME_MS);
- ret = queue_delayed_work(kfd_restore_wq, &p->restore_work,
- msecs_to_jiffies(PROCESS_BACK_OFF_TIME_MS));
- WARN(!ret, "reschedule restore work failed\n");
+ if (mod_delayed_work(kfd_restore_wq, &p->restore_work,
+ msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)))
+ kfd_process_restore_queues(p);
}
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f0f7f48..386875e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3426,7 +3426,7 @@
mm, KFD_MIGRATE_TRIGGER_PREFETCH);
*migrated = !r;
- return r;
+ return 0;
}
int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 71d2d44..d6e71aa 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -148,6 +148,9 @@
#define FIRMWARE_DCN_35_DMUB "amdgpu/dcn_3_5_dmcub.bin"
MODULE_FIRMWARE(FIRMWARE_DCN_35_DMUB);
+#define FIRMWARE_DCN_351_DMUB "amdgpu/dcn_3_5_1_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_DCN_351_DMUB);
+
/* Number of bytes in PSP header for firmware. */
#define PSP_HEADER_BYTES 0x100
@@ -3026,6 +3029,7 @@
dc_stream_release(dm_new_crtc_state->stream);
dm_new_crtc_state->stream = NULL;
}
+ dm_new_crtc_state->base.color_mgmt_changed = true;
}
for_each_new_plane_in_state(dm->cached_state, plane, new_plane_state, i) {
@@ -3044,6 +3048,10 @@
/* Do mst topology probing after resuming cached state*/
drm_connector_list_iter_begin(ddev, &iter);
drm_for_each_connector_iter(connector, &iter) {
+
+ if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
+ continue;
+
aconnector = to_amdgpu_dm_connector(connector);
if (aconnector->dc_link->type != dc_connection_mst_branch ||
aconnector->mst_root)
@@ -4529,15 +4537,18 @@
/* Determine whether to enable Replay support by default. */
if (!(amdgpu_dc_debug_mask & DC_DISABLE_REPLAY)) {
switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
- case IP_VERSION(3, 1, 4):
- case IP_VERSION(3, 1, 5):
- case IP_VERSION(3, 1, 6):
- case IP_VERSION(3, 2, 0):
- case IP_VERSION(3, 2, 1):
- case IP_VERSION(3, 5, 0):
- case IP_VERSION(3, 5, 1):
- replay_feature_enabled = true;
- break;
+/*
+ * Disabled by default due to https://gitlab.freedesktop.org/drm/amd/-/issues/3344
+ * case IP_VERSION(3, 1, 4):
+ * case IP_VERSION(3, 1, 5):
+ * case IP_VERSION(3, 1, 6):
+ * case IP_VERSION(3, 2, 0):
+ * case IP_VERSION(3, 2, 1):
+ * case IP_VERSION(3, 5, 0):
+ * case IP_VERSION(3, 5, 1):
+ * replay_feature_enabled = true;
+ * break;
+ */
default:
replay_feature_enabled = amdgpu_dc_feature_mask & DC_REPLAY_MASK;
break;
@@ -4820,9 +4831,11 @@
fw_name_dmub = FIRMWARE_DCN_V3_2_1_DMCUB;
break;
case IP_VERSION(3, 5, 0):
- case IP_VERSION(3, 5, 1):
fw_name_dmub = FIRMWARE_DCN_35_DMUB;
break;
+ case IP_VERSION(3, 5, 1):
+ fw_name_dmub = FIRMWARE_DCN_351_DMUB;
+ break;
default:
/* ASIC doesn't support DMUB. */
return 0;
@@ -5921,6 +5934,9 @@
&aconnector->base.probed_modes :
&aconnector->base.modes;
+ if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
+ return NULL;
+
if (aconnector->freesync_vid_base.clock != 0)
return &aconnector->freesync_vid_base;
@@ -6306,19 +6322,16 @@
if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket);
- if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) {
+ if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
+ stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
+ stream->signal == SIGNAL_TYPE_EDP) {
//
// should decide stream support vsc sdp colorimetry capability
// before building vsc info packet
//
- stream->use_vsc_sdp_for_colorimetry = false;
- if (aconnector->dc_sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
- stream->use_vsc_sdp_for_colorimetry =
- aconnector->dc_sink->is_vsc_sdp_colorimetry_supported;
- } else {
- if (stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED)
- stream->use_vsc_sdp_for_colorimetry = true;
- }
+ stream->use_vsc_sdp_for_colorimetry = stream->link->dpcd_caps.dpcd_rev.raw >= 0x14 &&
+ stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED;
+
if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22)
tf = TRANSFER_FUNC_GAMMA_22;
mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
@@ -8762,10 +8775,10 @@
if (!drm_atomic_crtc_needs_modeset(new_crtc_state))
continue;
+notify:
if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
continue;
-notify:
aconnector = to_amdgpu_dm_connector(connector);
mutex_lock(&adev->dm.audio_lock);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index eee4945..c7715a1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1495,7 +1495,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -1596,7 +1598,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -1681,7 +1685,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -1780,7 +1786,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -1865,7 +1873,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -1964,7 +1974,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -2045,7 +2057,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -2141,7 +2155,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -2220,7 +2236,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -2276,7 +2294,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -2347,7 +2367,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
@@ -2418,7 +2440,9 @@
for (i = 0; i < MAX_PIPES; i++) {
pipe_ctx = &aconnector->dc_link->dc->current_state->res_ctx.pipe_ctx[i];
if (pipe_ctx->stream &&
- pipe_ctx->stream->link == aconnector->dc_link)
+ pipe_ctx->stream->link == aconnector->dc_link &&
+ pipe_ctx->stream->sink &&
+ pipe_ctx->stream->sink == aconnector->dc_sink)
break;
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
index 16e72d6..08c494a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c
@@ -76,10 +76,8 @@
static int amdgpu_dm_wb_connector_get_modes(struct drm_connector *connector)
{
- struct drm_device *dev = connector->dev;
-
- return drm_add_modes_noedid(connector, dev->mode_config.max_width,
- dev->mode_config.max_height);
+ /* Maximum resolution supported by DWB */
+ return drm_add_modes_noedid(connector, 3840, 2160);
}
static int amdgpu_dm_wb_prepare_job(struct drm_writeback_connector *wb_connector,
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 05f3925..ab31643 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -2948,6 +2948,7 @@
result = get_integrated_info_v2_1(bp, info);
break;
case 2:
+ case 3:
result = get_integrated_info_v2_2(bp, info);
break;
default:
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index 644da46..5506cf9 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -145,6 +145,10 @@
*/
clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
if (safe_to_lower) {
+ if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) {
+ dcn315_smu_set_dtbclk(clk_mgr, false);
+ clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+ }
/* check that we're not already in lower */
if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) {
display_count = dcn315_get_active_display_cnt_wa(dc, context);
@@ -160,6 +164,10 @@
}
}
} else {
+ if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
+ dcn315_smu_set_dtbclk(clk_mgr, true);
+ clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+ }
/* check that we're not already in D0 */
if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_MISSION_MODE) {
union display_idle_optimization_u idle_info = { 0 };
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
index 12f3e8a..6ad4f4e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c
@@ -99,20 +99,25 @@
return display_count;
}
-static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable)
+static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context,
+ bool safe_to_lower, bool disable)
{
struct dc *dc = clk_mgr_base->ctx->dc;
int i;
for (i = 0; i < dc->res_pool->pipe_count; ++i) {
- struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+ struct pipe_ctx *pipe = safe_to_lower
+ ? &context->res_ctx.pipe_ctx[i]
+ : &dc->current_state->res_ctx.pipe_ctx[i];
if (pipe->top_pipe || pipe->prev_odm_pipe)
continue;
- if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL ||
- dc_is_virtual_signal(pipe->stream->signal))) {
+ if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) ||
+ !pipe->stream->link_enc)) {
if (disable) {
- pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
+ if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc)
+ pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg);
+
reset_sync_context_for_pipe(dc, context, i);
} else
pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
@@ -207,11 +212,11 @@
}
if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
- dcn316_disable_otg_wa(clk_mgr_base, context, true);
+ dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
- dcn316_disable_otg_wa(clk_mgr_base, context, false);
+ dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
update_dispclk = true;
}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index bec252e..e506e4f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -712,8 +712,12 @@
* since we calculate mode support based on softmax being the max UCLK
* frequency.
*/
- dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
- dc->clk_mgr->bw_params->dc_mode_softmax_memclk);
+ if (dc->debug.disable_dc_mode_overwrite) {
+ dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
+ dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
+ } else
+ dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
+ dc->clk_mgr->bw_params->dc_mode_softmax_memclk);
} else {
dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
}
@@ -746,8 +750,13 @@
/* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */
if (clk_mgr_base->clks.p_state_change_support &&
(update_uclk || !clk_mgr_base->clks.prev_p_state_change_support) &&
- !dc->work_arounds.clock_update_disable_mask.uclk)
+ !dc->work_arounds.clock_update_disable_mask.uclk) {
+ if (dc->clk_mgr->dc_mode_softmax_enabled && dc->debug.disable_dc_mode_overwrite)
+ dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK,
+ max((int)dc->clk_mgr->bw_params->dc_mode_softmax_memclk, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)));
+
dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz));
+ }
if (clk_mgr_base->clks.num_ways != new_clocks->num_ways &&
clk_mgr_base->clks.num_ways > new_clocks->num_ways) {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 101fe96..d9c5692 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -73,6 +73,12 @@
#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK 0x00000007L
#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK 0x000F0000L
+#define regCLK5_0_CLK5_spll_field_8 0x464b
+#define regCLK5_0_CLK5_spll_field_8_BASE_IDX 0
+
+#define CLK5_0_CLK5_spll_field_8__spll_ssc_en__SHIFT 0xd
+#define CLK5_0_CLK5_spll_field_8__spll_ssc_en_MASK 0x00002000L
+
#define SMU_VER_THRESHOLD 0x5D4A00 //93.74.0
#define REG(reg_name) \
@@ -411,6 +417,17 @@
{
}
+static bool dcn35_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base)
+{
+ struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+ struct dc_context *ctx = clk_mgr->base.ctx;
+ uint32_t ssc_enable;
+
+ REG_GET(CLK5_0_CLK5_spll_field_8, spll_ssc_en, &ssc_enable);
+
+ return ssc_enable == 1;
+}
+
static void init_clk_states(struct clk_mgr *clk_mgr)
{
struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
@@ -428,7 +445,16 @@
void dcn35_init_clocks(struct clk_mgr *clk_mgr)
{
+ struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
init_clk_states(clk_mgr);
+
+ // to adjust dp_dto reference clock if ssc is enable otherwise to apply dprefclk
+ if (dcn35_is_spll_ssc_enabled(clk_mgr))
+ clk_mgr->dp_dto_source_clock_in_khz =
+ dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz);
+ else
+ clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
+
}
static struct clk_bw_params dcn35_bw_params = {
.vram_type = Ddr4MemType,
@@ -517,6 +543,28 @@
static struct dcn35_watermarks dummy_wms = { 0 };
+static struct dcn35_ss_info_table ss_info_table = {
+ .ss_divider = 1000,
+ .ss_percentage = {0, 0, 375, 375, 375}
+};
+
+static void dcn35_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
+{
+ struct dc_context *ctx = clk_mgr->base.ctx;
+ uint32_t clock_source;
+
+ REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
+ // If it's DFS mode, clock_source is 0.
+ if (dcn35_is_spll_ssc_enabled(&clk_mgr->base) && (clock_source < ARRAY_SIZE(ss_info_table.ss_percentage))) {
+ clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
+
+ if (clk_mgr->dprefclk_ss_percentage != 0) {
+ clk_mgr->ss_on_dprefclk = true;
+ clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
+ }
+ }
+}
+
static void dcn35_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn35_watermarks *table)
{
int i, num_valid_sets;
@@ -1061,6 +1109,8 @@
dce_clock_read_ss_info(&clk_mgr->base);
/*when clk src is from FCH, it could have ss, same clock src as DPREF clk*/
+ dcn35_read_ss_info_from_lut(&clk_mgr->base);
+
clk_mgr->base.base.bw_params = &dcn35_bw_params;
if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 03b554e..d68c83e 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1801,6 +1801,9 @@
return false;
}
+ if (link->dpcd_caps.channel_coding_cap.bits.DP_128b_132b_SUPPORTED)
+ return false;
+
if (dc->link_srv->edp_is_ilr_optimization_required(link, crtc_timing)) {
DC_LOG_EVENT_LINK_TRAINING("Seamless boot disabled to optimize eDP link rate\n");
return false;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 5cc7f8d..61986e5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -436,6 +436,15 @@
goto out;
}
+ if (stream_status->plane_count == 0 && dc->config.enable_windowed_mpo_odm)
+ /* ODM combine could prevent us from supporting more planes
+ * we will reset ODM slice count back to 1 when all planes have
+ * been removed to maximize the amount of planes supported when
+ * new planes are added.
+ */
+ resource_update_pipes_for_stream_with_slice_count(
+ state, dc->current_state, dc->res_pool, stream, 1);
+
otg_master_pipe = resource_get_otg_master_for_stream(
&state->res_ctx, stream);
if (otg_master_pipe)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 970644b..b5e0289 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -976,7 +976,10 @@
struct bp_pixel_clock_parameters bp_pc_params = {0};
enum transmitter_color_depth bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24;
- if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
+ // Apply ssed(spread spectrum) dpref clock for edp only.
+ if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0
+ && pix_clk_params->signal_type == SIGNAL_TYPE_EDP
+ && encoding == DP_8b_10b_ENCODING)
dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
// For these signal types Driver to program DP_DTO without calling VBIOS Command table
if (dc_is_dp_signal(pix_clk_params->signal_type) || dc_is_virtual_signal(pix_clk_params->signal_type)) {
@@ -1093,9 +1096,6 @@
unsigned int modulo_hz = 0;
unsigned int dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dprefclk_khz;
- if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0)
- dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz;
-
if (clock_source->id == CLOCK_SOURCE_ID_DP_DTO) {
clock_hz = REG_READ(PHASE[inst]);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c
index 5b7ad38..65e45a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c
@@ -395,6 +395,12 @@
x),
25));
+ // If y rounds up to integer, carry it over to x.
+ if (y >> 25) {
+ x += 1;
+ y = 0;
+ }
+
switch (stream_encoder_inst) {
case 0:
REG_SET_2(DP_DPHY_SYM32_VC_RATE_CNTL0, 0,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
index e224a02..8a0460e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c
@@ -248,14 +248,12 @@
enc10->base.hpd_source = init_data->hpd_source;
enc10->base.connector = init_data->connector;
+ if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+ enc10->base.features.flags.bits.DP_IS_USB_C = 1;
+
enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
enc10->base.features = *enc_features;
- if (enc10->base.connector.id == CONNECTOR_ID_USBC)
- enc10->base.features.flags.bits.DP_IS_USB_C = 1;
-
- if (enc10->base.connector.id == CONNECTOR_ID_USBC)
- enc10->base.features.flags.bits.DP_IS_USB_C = 1;
enc10->base.transmitter = init_data->transmitter;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
index 81e349d..da94e53 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c
@@ -184,6 +184,8 @@
enc10->base.hpd_source = init_data->hpd_source;
enc10->base.connector = init_data->connector;
+ if (enc10->base.connector.id == CONNECTOR_ID_USBC)
+ enc10->base.features.flags.bits.DP_IS_USB_C = 1;
enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
@@ -238,8 +240,6 @@
}
enc10->base.features.flags.bits.HDMI_6GB_EN = 1;
- if (enc10->base.connector.id == CONNECTOR_ID_USBC)
- enc10->base.features.flags.bits.DP_IS_USB_C = 1;
if (bp_funcs->get_connector_speed_cap_info)
result = bp_funcs->get_connector_speed_cap_info(enc10->base.ctx->dc_bios,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
index deb6d16..7307b7b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
@@ -291,6 +291,7 @@
.do_urgent_latency_adjustment = false,
.urgent_latency_adjustment_fabric_clock_component_us = 0,
.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+ .dispclk_dppclk_vco_speed_mhz = 2400.0,
.num_chans = 4,
.dummy_pstate_latency_us = 10.0
};
@@ -438,6 +439,7 @@
.do_urgent_latency_adjustment = false,
.urgent_latency_adjustment_fabric_clock_component_us = 0,
.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
+ .dispclk_dppclk_vco_speed_mhz = 2500.0,
};
void dcn31_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index 5491b70..5a965c2 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -270,7 +270,7 @@
/* Error check whether requested and allocated are equal */
req_bw = requested_bw * (Kbps_TO_Gbps / link->dpia_bw_alloc_config.bw_granularity);
- if (req_bw == link->dpia_bw_alloc_config.allocated_bw) {
+ if (req_bw && (req_bw == link->dpia_bw_alloc_config.allocated_bw)) {
DC_LOG_ERROR("%s: Request bw equals to allocated bw for link(%d)\n",
__func__, link->link_index);
}
@@ -341,6 +341,14 @@
ret = true;
init_usb4_bw_struct(link);
link->dpia_bw_alloc_config.bw_alloc_enabled = true;
+
+ /*
+ * During DP tunnel creation, CM preallocates BW and reduces estimated BW of other
+ * DPIA. CM release preallocation only when allocation is complete. Do zero alloc
+ * to make the CM to release preallocation and update estimated BW correctly for
+ * all DPIAs per host router
+ */
+ link_dp_dpia_allocate_usb4_bandwidth_for_stream(link, 0);
}
}
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
index f07a4c7..52eab8f 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c
@@ -267,9 +267,6 @@
OTG_V_TOTAL_MAX_SEL, 1,
OTG_FORCE_LOCK_ON_EVENT, 0,
OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */
-
- // Setup manual flow control for EOF via TRIG_A
- optc->funcs->setup_manual_trigger(optc);
}
}
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
index a2387ce..622214b 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
@@ -2449,6 +2449,7 @@
dc->caps.post_blend_color_processing = true;
dc->caps.force_dp_tps4_for_cp2520 = true;
dc->caps.extended_aux_timeout_support = true;
+ dc->caps.dmcub_support = true;
/* Color pipeline capabilities */
dc->caps.color.dpp.dcn_arch = 1;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index f09b9d4..bbd0169 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -4261,6 +4261,13 @@
}
}
+ /*
+ * If gpu_od is the only member in the list, that means gpu_od is an
+ * empty directory, so remove it.
+ */
+ if (list_is_singular(&adev->pm.od_kobj_list))
+ goto err_out;
+
return 0;
err_out:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 246b211..6533314 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -735,7 +735,7 @@
smu->adev = adev;
smu->pm_enabled = !!amdgpu_dpm;
smu->is_apu = false;
- smu->smu_baco.state = SMU_BACO_STATE_EXIT;
+ smu->smu_baco.state = SMU_BACO_STATE_NONE;
smu->smu_baco.platform_support = false;
smu->user_dpm_profile.fan_mode = -1;
@@ -1966,10 +1966,25 @@
return 0;
}
+static int smu_reset_mp1_state(struct smu_context *smu)
+{
+ struct amdgpu_device *adev = smu->adev;
+ int ret = 0;
+
+ if ((!adev->in_runpm) && (!adev->in_suspend) &&
+ (!amdgpu_in_reset(adev)) && amdgpu_ip_version(adev, MP1_HWIP, 0) ==
+ IP_VERSION(13, 0, 10) &&
+ !amdgpu_device_has_display_hardware(adev))
+ ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD);
+
+ return ret;
+}
+
static int smu_hw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
struct smu_context *smu = adev->powerplay.pp_handle;
+ int ret;
if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
return 0;
@@ -1987,7 +2002,15 @@
adev->pm.dpm_enabled = false;
- return smu_smc_hw_cleanup(smu);
+ ret = smu_smc_hw_cleanup(smu);
+ if (ret)
+ return ret;
+
+ ret = smu_reset_mp1_state(smu);
+ if (ret)
+ return ret;
+
+ return 0;
}
static void smu_late_fini(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index a870bdd4..1fa8157 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -424,6 +424,7 @@
enum smu_baco_state {
SMU_BACO_STATE_ENTER = 0,
SMU_BACO_STATE_EXIT,
+ SMU_BACO_STATE_NONE,
};
struct smu_baco_context {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
index 5bb7a63..97522c0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h
@@ -144,6 +144,37 @@
uint32_t MaxGfxClk;
} DpmClocks_t;
+//Freq in MHz
+//Voltage in milli volts with 2 fractional bits
+typedef struct {
+ uint32_t DcfClocks[NUM_DCFCLK_DPM_LEVELS];
+ uint32_t DispClocks[NUM_DISPCLK_DPM_LEVELS];
+ uint32_t DppClocks[NUM_DPPCLK_DPM_LEVELS];
+ uint32_t SocClocks[NUM_SOCCLK_DPM_LEVELS];
+ uint32_t VClocks0[NUM_VCN_DPM_LEVELS];
+ uint32_t VClocks1[NUM_VCN_DPM_LEVELS];
+ uint32_t DClocks0[NUM_VCN_DPM_LEVELS];
+ uint32_t DClocks1[NUM_VCN_DPM_LEVELS];
+ uint32_t VPEClocks[NUM_VPE_DPM_LEVELS];
+ uint32_t FclkClocks_Freq[NUM_FCLK_DPM_LEVELS];
+ uint32_t FclkClocks_Voltage[NUM_FCLK_DPM_LEVELS];
+ uint32_t SocVoltage[NUM_SOC_VOLTAGE_LEVELS];
+ MemPstateTable_t MemPstateTable[NUM_MEM_PSTATE_LEVELS];
+
+ uint8_t NumDcfClkLevelsEnabled;
+ uint8_t NumDispClkLevelsEnabled; //Applies to both Dispclk and Dppclk
+ uint8_t NumSocClkLevelsEnabled;
+ uint8_t Vcn0ClkLevelsEnabled; //Applies to both Vclk0 and Dclk0
+ uint8_t Vcn1ClkLevelsEnabled; //Applies to both Vclk1 and Dclk1
+ uint8_t VpeClkLevelsEnabled;
+ uint8_t NumMemPstatesEnabled;
+ uint8_t NumFclkLevelsEnabled;
+ uint8_t spare;
+
+ uint32_t MinGfxClk;
+ uint32_t MaxGfxClk;
+} DpmClocks_t_v14_0_1;
+
typedef struct {
uint16_t CoreFrequency[16]; //Target core frequency [MHz]
uint16_t CorePower[16]; //CAC calculated core power [mW]
@@ -224,7 +255,7 @@
#define TABLE_CUSTOM_DPM 2 // Called by Driver
#define TABLE_BIOS_GPIO_CONFIG 3 // Called by BIOS
#define TABLE_DPMCLOCKS 4 // Called by Driver and VBIOS
-#define TABLE_SPARE0 5 // Unused
+#define TABLE_MOMENTARY_PM 5 // Called by Tools
#define TABLE_MODERN_STDBY 6 // Called by Tools for Modern Standby Log
#define TABLE_SMU_METRICS 7 // Called by Driver and SMF/PMF
#define TABLE_COUNT 8
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h
index 356e0f5..ddb6258 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h
@@ -42,7 +42,7 @@
#define FEATURE_EDC_BIT 7
#define FEATURE_PLL_POWER_DOWN_BIT 8
#define FEATURE_VDDOFF_BIT 9
-#define FEATURE_VCN_DPM_BIT 10
+#define FEATURE_VCN_DPM_BIT 10 /* this is for both VCN0 and VCN1 */
#define FEATURE_DS_MPM_BIT 11
#define FEATURE_FCLK_DPM_BIT 12
#define FEATURE_SOCCLK_DPM_BIT 13
@@ -56,9 +56,9 @@
#define FEATURE_DS_GFXCLK_BIT 21
#define FEATURE_DS_SOCCLK_BIT 22
#define FEATURE_DS_LCLK_BIT 23
-#define FEATURE_LOW_POWER_DCNCLKS_BIT 24 // for all DISP clks
+#define FEATURE_LOW_POWER_DCNCLKS_BIT 24
#define FEATURE_DS_SHUBCLK_BIT 25
-#define FEATURE_SPARE0_BIT 26 //SPARE
+#define FEATURE_RESERVED0_BIT 26
#define FEATURE_ZSTATES_BIT 27
#define FEATURE_IOMMUL2_PG_BIT 28
#define FEATURE_DS_FCLK_BIT 29
@@ -66,8 +66,8 @@
#define FEATURE_DS_MP1CLK_BIT 31
#define FEATURE_WHISPER_MODE_BIT 32
#define FEATURE_SMU_LOW_POWER_BIT 33
-#define FEATURE_SMART_L3_RINSER_BIT 34
-#define FEATURE_SPARE1_BIT 35 //SPARE
+#define FEATURE_RESERVED1_BIT 34 /* v14_0_0 SMART_L3_RINSER; v14_0_1 RESERVED1 */
+#define FEATURE_GFX_DEM_BIT 35 /* v14_0_0 SPARE; v14_0_1 GFX_DEM */
#define FEATURE_PSI_BIT 36
#define FEATURE_PROCHOT_BIT 37
#define FEATURE_CPUOFF_BIT 38
@@ -77,11 +77,11 @@
#define FEATURE_PERF_LIMIT_BIT 42
#define FEATURE_CORE_DLDO_BIT 43
#define FEATURE_DVO_BIT 44
-#define FEATURE_DS_VCN_BIT 45
+#define FEATURE_DS_VCN_BIT 45 /* v14_0_1 this is for both VCN0 and VCN1 */
#define FEATURE_CPPC_BIT 46
#define FEATURE_CPPC_PREFERRED_CORES 47
#define FEATURE_DF_CSTATES_BIT 48
-#define FEATURE_SPARE2_BIT 49 //SPARE
+#define FEATURE_FAST_PSTATE_CLDO_BIT 49 /* v14_0_0 SPARE */
#define FEATURE_ATHUB_PG_BIT 50
#define FEATURE_VDDOFF_ECO_BIT 51
#define FEATURE_ZSTATES_ECO_BIT 52
@@ -93,8 +93,8 @@
#define FEATURE_DS_IPUCLK_BIT 58
#define FEATURE_DS_VPECLK_BIT 59
#define FEATURE_VPE_DPM_BIT 60
-#define FEATURE_SPARE_61 61
-#define FEATURE_FP_DIDT 62
+#define FEATURE_SMART_L3_RINSER_BIT 61 /* v14_0_0 SPARE*/
+#define FEATURE_PCC_BIT 62 /* v14_0_0 FP_DIDT v14_0_1 PCC_BIT */
#define NUM_FEATURES 63
// Firmware Header/Footer
@@ -151,6 +151,43 @@
// MP1_EXT_SCRATCH7 = RTOS Current Job
} FwStatus_t;
+typedef struct {
+ // MP1_EXT_SCRATCH0
+ uint32_t DpmHandlerID : 8;
+ uint32_t ActivityMonitorID : 8;
+ uint32_t DpmTimerID : 8;
+ uint32_t DpmHubID : 4;
+ uint32_t DpmHubTask : 4;
+ // MP1_EXT_SCRATCH1
+ uint32_t CclkSyncStatus : 8;
+ uint32_t ZstateStatus : 4;
+ uint32_t Cpu1VddOff : 4;
+ uint32_t DstateFun : 4;
+ uint32_t DstateDev : 4;
+ uint32_t GfxOffStatus : 2;
+ uint32_t Cpu0Off : 2;
+ uint32_t Cpu1Off : 2;
+ uint32_t Cpu0VddOff : 2;
+ // MP1_EXT_SCRATCH2
+ uint32_t P2JobHandler :32;
+ // MP1_EXT_SCRATCH3
+ uint32_t PostCode :32;
+ // MP1_EXT_SCRATCH4
+ uint32_t MsgPortBusy :15;
+ uint32_t RsmuPmiP1Pending : 1;
+ uint32_t RsmuPmiP2PendingCnt : 8;
+ uint32_t DfCstateExitPending : 1;
+ uint32_t Pc6EntryPending : 1;
+ uint32_t Pc6ExitPending : 1;
+ uint32_t WarmResetPending : 1;
+ uint32_t Mp0ClkPending : 1;
+ uint32_t InWhisperMode : 1;
+ uint32_t spare2 : 2;
+ // MP1_EXT_SCRATCH5
+ uint32_t IdleMask :32;
+ // MP1_EXT_SCRATCH6 = RTOS threads' status
+ // MP1_EXT_SCRATCH7 = RTOS Current Job
+} FwStatus_t_v14_0_1;
#pragma pack(pop)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
index ca7ce42..c4dc588 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
@@ -72,23 +72,19 @@
#define PPSMC_MSG_SetHardMinSocclkByFreq 0x13 ///< Set hard min for SOC CLK
#define PPSMC_MSG_SetSoftMinFclk 0x14 ///< Set hard min for FCLK
#define PPSMC_MSG_SetSoftMinVcn0 0x15 ///< Set soft min for VCN0 clocks (VCLK0 and DCLK0)
-
#define PPSMC_MSG_EnableGfxImu 0x16 ///< Enable GFX IMU
-
-#define PPSMC_MSG_spare_0x17 0x17
-#define PPSMC_MSG_spare_0x18 0x18
+#define PPSMC_MSG_spare_0x17 0x17 ///< Get GFX clock frequency
+#define PPSMC_MSG_spare_0x18 0x18 ///< Get FCLK frequency
#define PPSMC_MSG_AllowGfxOff 0x19 ///< Inform PMFW of allowing GFXOFF entry
#define PPSMC_MSG_DisallowGfxOff 0x1A ///< Inform PMFW of disallowing GFXOFF entry
#define PPSMC_MSG_SetSoftMaxGfxClk 0x1B ///< Set soft max for GFX CLK
#define PPSMC_MSG_SetHardMinGfxClk 0x1C ///< Set hard min for GFX CLK
-
#define PPSMC_MSG_SetSoftMaxSocclkByFreq 0x1D ///< Set soft max for SOC CLK
#define PPSMC_MSG_SetSoftMaxFclkByFreq 0x1E ///< Set soft max for FCLK
#define PPSMC_MSG_SetSoftMaxVcn0 0x1F ///< Set soft max for VCN0 clocks (VCLK0 and DCLK0)
-#define PPSMC_MSG_spare_0x20 0x20
+#define PPSMC_MSG_spare_0x20 0x20 ///< Set power limit percentage
#define PPSMC_MSG_PowerDownJpeg0 0x21 ///< Power down Jpeg of VCN0
#define PPSMC_MSG_PowerUpJpeg0 0x22 ///< Power up Jpeg of VCN0; VCN0 is power gated by default
-
#define PPSMC_MSG_SetHardMinFclkByFreq 0x23 ///< Set hard min for FCLK
#define PPSMC_MSG_SetSoftMinSocclkByFreq 0x24 ///< Set soft min for SOC CLK
#define PPSMC_MSG_AllowZstates 0x25 ///< Inform PMFM of allowing Zstate entry, i.e. no Miracast activity
@@ -99,8 +95,8 @@
#define PPSMC_MSG_PowerUpIspByTile 0x2A ///< This message is used to power up ISP tiles and enable the ISP DPM
#define PPSMC_MSG_SetHardMinIspiclkByFreq 0x2B ///< Set HardMin by frequency for ISPICLK
#define PPSMC_MSG_SetHardMinIspxclkByFreq 0x2C ///< Set HardMin by frequency for ISPXCLK
-#define PPSMC_MSG_PowerDownUmsch 0x2D ///< Power down VCN.UMSCH (aka VSCH) scheduler
-#define PPSMC_MSG_PowerUpUmsch 0x2E ///< Power up VCN.UMSCH (aka VSCH) scheduler
+#define PPSMC_MSG_PowerDownUmsch 0x2D ///< Power down VCN0.UMSCH (aka VSCH) scheduler
+#define PPSMC_MSG_PowerUpUmsch 0x2E ///< Power up VCN0.UMSCH (aka VSCH) scheduler
#define PPSMC_Message_IspStutterOn_MmhubPgDis 0x2F ///< ISP StutterOn mmHub PgDis
#define PPSMC_Message_IspStutterOff_MmhubPgEn 0x30 ///< ISP StufferOff mmHub PgEn
#define PPSMC_MSG_PowerUpVpe 0x31 ///< Power up VPE
@@ -110,7 +106,9 @@
#define PPSMC_MSG_DisableLSdma 0x35 ///< Disable LSDMA
#define PPSMC_MSG_SetSoftMaxVpe 0x36 ///<
#define PPSMC_MSG_SetSoftMinVpe 0x37 ///<
-#define PPSMC_Message_Count 0x38 ///< Total number of PPSMC messages
+#define PPSMC_MSG_AllocMALLCache 0x38 ///< Allocating MALL Cache
+#define PPSMC_MSG_ReleaseMALLCache 0x39 ///< Releasing MALL Cache
+#define PPSMC_Message_Count 0x3A ///< Total number of PPSMC messages
/** @}*/
/**
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
index 3f7463c..4af1985 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
@@ -27,6 +27,7 @@
#define SMU14_DRIVER_IF_VERSION_INV 0xFFFFFFFF
#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_0 0x7
+#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_1 0x6
#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x1
#define FEATURE_MASK(feature) (1ULL << feature)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 9c03296..67117ce 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2751,7 +2751,13 @@
switch (mp1_state) {
case PP_MP1_STATE_UNLOAD:
- ret = smu_cmn_set_mp1_state(smu, mp1_state);
+ ret = smu_cmn_send_smc_msg_with_param(smu,
+ SMU_MSG_PrepareMp1ForUnload,
+ 0x55, NULL);
+
+ if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT)
+ ret = smu_v13_0_disable_pmfw_state(smu);
+
break;
default:
/* Ignore others */
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
index bb98156..949131b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
@@ -226,8 +226,18 @@
struct amdgpu_device *adev = smu->adev;
int ret = 0;
- if (!en && !adev->in_s0ix)
+ if (!en && !adev->in_s0ix) {
+ /* Adds a GFX reset as workaround just before sending the
+ * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering
+ * an invalid state.
+ */
+ ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset,
+ SMU_RESET_MODE_2, NULL);
+ if (ret)
+ return ret;
+
ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL);
+ }
return ret;
}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 3957af0..c977ebe 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -2294,6 +2294,17 @@
return sizeof(*gpu_metrics);
}
+static void smu_v13_0_6_restore_pci_config(struct smu_context *smu)
+{
+ struct amdgpu_device *adev = smu->adev;
+ int i;
+
+ for (i = 0; i < 16; i++)
+ pci_write_config_dword(adev->pdev, i * 4,
+ adev->pdev->saved_config_space[i]);
+ pci_restore_msi_state(adev->pdev);
+}
+
static int smu_v13_0_6_mode2_reset(struct smu_context *smu)
{
int ret = 0, index;
@@ -2315,6 +2326,20 @@
/* Restore the config space saved during init */
amdgpu_device_load_pci_state(adev->pdev);
+ /* Certain platforms have switches which assign virtual BAR values to
+ * devices. OS uses the virtual BAR values and device behind the switch
+ * is assgined another BAR value. When device's config space registers
+ * are queried, switch returns the virtual BAR values. When mode-2 reset
+ * is performed, switch is unaware of it, and will continue to return
+ * the same virtual values to the OS.This affects
+ * pci_restore_config_space() API as it doesn't write the value saved if
+ * the current value read from config space is the same as what is
+ * saved. As a workaround, make sure the config space is restored
+ * always.
+ */
+ if (!(adev->flags & AMD_IS_APU))
+ smu_v13_0_6_restore_pci_config(smu);
+
dev_dbg(smu->adev->dev, "wait for reset ack\n");
do {
ret = smu_cmn_wait_for_response(smu);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 9e39f99..07a65e0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -234,7 +234,7 @@
smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
break;
case IP_VERSION(14, 0, 1):
- smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0;
+ smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_1;
break;
default:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index d6de6d9..63399c0 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -161,7 +161,7 @@
SMU_TABLE_INIT(tables, SMU_TABLE_WATERMARKS, sizeof(Watermarks_t),
PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
- SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, sizeof(DpmClocks_t),
+ SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, max(sizeof(DpmClocks_t), sizeof(DpmClocks_t_v14_0_1)),
PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t),
PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
@@ -171,7 +171,7 @@
goto err0_out;
smu_table->metrics_time = 0;
- smu_table->clocks_table = kzalloc(sizeof(DpmClocks_t), GFP_KERNEL);
+ smu_table->clocks_table = kzalloc(max(sizeof(DpmClocks_t), sizeof(DpmClocks_t_v14_0_1)), GFP_KERNEL);
if (!smu_table->clocks_table)
goto err1_out;
@@ -593,6 +593,60 @@
return ret;
}
+static int smu_v14_0_1_get_dpm_freq_by_index(struct smu_context *smu,
+ enum smu_clk_type clk_type,
+ uint32_t dpm_level,
+ uint32_t *freq)
+{
+ DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+
+ if (!clk_table || clk_type >= SMU_CLK_COUNT)
+ return -EINVAL;
+
+ switch (clk_type) {
+ case SMU_SOCCLK:
+ if (dpm_level >= clk_table->NumSocClkLevelsEnabled)
+ return -EINVAL;
+ *freq = clk_table->SocClocks[dpm_level];
+ break;
+ case SMU_VCLK:
+ if (dpm_level >= clk_table->Vcn0ClkLevelsEnabled)
+ return -EINVAL;
+ *freq = clk_table->VClocks0[dpm_level];
+ break;
+ case SMU_DCLK:
+ if (dpm_level >= clk_table->Vcn0ClkLevelsEnabled)
+ return -EINVAL;
+ *freq = clk_table->DClocks0[dpm_level];
+ break;
+ case SMU_VCLK1:
+ if (dpm_level >= clk_table->Vcn1ClkLevelsEnabled)
+ return -EINVAL;
+ *freq = clk_table->VClocks1[dpm_level];
+ break;
+ case SMU_DCLK1:
+ if (dpm_level >= clk_table->Vcn1ClkLevelsEnabled)
+ return -EINVAL;
+ *freq = clk_table->DClocks1[dpm_level];
+ break;
+ case SMU_UCLK:
+ case SMU_MCLK:
+ if (dpm_level >= clk_table->NumMemPstatesEnabled)
+ return -EINVAL;
+ *freq = clk_table->MemPstateTable[dpm_level].MemClk;
+ break;
+ case SMU_FCLK:
+ if (dpm_level >= clk_table->NumFclkLevelsEnabled)
+ return -EINVAL;
+ *freq = clk_table->FclkClocks_Freq[dpm_level];
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int smu_v14_0_0_get_dpm_freq_by_index(struct smu_context *smu,
enum smu_clk_type clk_type,
uint32_t dpm_level,
@@ -637,6 +691,19 @@
return 0;
}
+static int smu_v14_0_common_get_dpm_freq_by_index(struct smu_context *smu,
+ enum smu_clk_type clk_type,
+ uint32_t dpm_level,
+ uint32_t *freq)
+{
+ if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+ smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, dpm_level, freq);
+ else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+ smu_v14_0_1_get_dpm_freq_by_index(smu, clk_type, dpm_level, freq);
+
+ return 0;
+}
+
static bool smu_v14_0_0_clk_dpm_is_enabled(struct smu_context *smu,
enum smu_clk_type clk_type)
{
@@ -657,6 +724,8 @@
break;
case SMU_VCLK:
case SMU_DCLK:
+ case SMU_VCLK1:
+ case SMU_DCLK1:
feature_id = SMU_FEATURE_VCN_DPM_BIT;
break;
default:
@@ -666,6 +735,126 @@
return smu_cmn_feature_is_enabled(smu, feature_id);
}
+static int smu_v14_0_1_get_dpm_ultimate_freq(struct smu_context *smu,
+ enum smu_clk_type clk_type,
+ uint32_t *min,
+ uint32_t *max)
+{
+ DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+ uint32_t clock_limit;
+ uint32_t max_dpm_level, min_dpm_level;
+ int ret = 0;
+
+ if (!smu_v14_0_0_clk_dpm_is_enabled(smu, clk_type)) {
+ switch (clk_type) {
+ case SMU_MCLK:
+ case SMU_UCLK:
+ clock_limit = smu->smu_table.boot_values.uclk;
+ break;
+ case SMU_FCLK:
+ clock_limit = smu->smu_table.boot_values.fclk;
+ break;
+ case SMU_GFXCLK:
+ case SMU_SCLK:
+ clock_limit = smu->smu_table.boot_values.gfxclk;
+ break;
+ case SMU_SOCCLK:
+ clock_limit = smu->smu_table.boot_values.socclk;
+ break;
+ case SMU_VCLK:
+ case SMU_VCLK1:
+ clock_limit = smu->smu_table.boot_values.vclk;
+ break;
+ case SMU_DCLK:
+ case SMU_DCLK1:
+ clock_limit = smu->smu_table.boot_values.dclk;
+ break;
+ default:
+ clock_limit = 0;
+ break;
+ }
+
+ /* clock in Mhz unit */
+ if (min)
+ *min = clock_limit / 100;
+ if (max)
+ *max = clock_limit / 100;
+
+ return 0;
+ }
+
+ if (max) {
+ switch (clk_type) {
+ case SMU_GFXCLK:
+ case SMU_SCLK:
+ *max = clk_table->MaxGfxClk;
+ break;
+ case SMU_MCLK:
+ case SMU_UCLK:
+ case SMU_FCLK:
+ max_dpm_level = 0;
+ break;
+ case SMU_SOCCLK:
+ max_dpm_level = clk_table->NumSocClkLevelsEnabled - 1;
+ break;
+ case SMU_VCLK:
+ case SMU_DCLK:
+ max_dpm_level = clk_table->Vcn0ClkLevelsEnabled - 1;
+ break;
+ case SMU_VCLK1:
+ case SMU_DCLK1:
+ max_dpm_level = clk_table->Vcn1ClkLevelsEnabled - 1;
+ break;
+ default:
+ ret = -EINVAL;
+ goto failed;
+ }
+
+ if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) {
+ ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max);
+ if (ret)
+ goto failed;
+ }
+ }
+
+ if (min) {
+ switch (clk_type) {
+ case SMU_GFXCLK:
+ case SMU_SCLK:
+ *min = clk_table->MinGfxClk;
+ break;
+ case SMU_MCLK:
+ case SMU_UCLK:
+ min_dpm_level = clk_table->NumMemPstatesEnabled - 1;
+ break;
+ case SMU_FCLK:
+ min_dpm_level = clk_table->NumFclkLevelsEnabled - 1;
+ break;
+ case SMU_SOCCLK:
+ min_dpm_level = 0;
+ break;
+ case SMU_VCLK:
+ case SMU_DCLK:
+ case SMU_VCLK1:
+ case SMU_DCLK1:
+ min_dpm_level = 0;
+ break;
+ default:
+ ret = -EINVAL;
+ goto failed;
+ }
+
+ if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) {
+ ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min);
+ if (ret)
+ goto failed;
+ }
+ }
+
+failed:
+ return ret;
+}
+
static int smu_v14_0_0_get_dpm_ultimate_freq(struct smu_context *smu,
enum smu_clk_type clk_type,
uint32_t *min,
@@ -736,7 +925,7 @@
}
if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) {
- ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max);
+ ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max);
if (ret)
goto failed;
}
@@ -768,7 +957,7 @@
}
if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) {
- ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min);
+ ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min);
if (ret)
goto failed;
}
@@ -778,6 +967,19 @@
return ret;
}
+static int smu_v14_0_common_get_dpm_ultimate_freq(struct smu_context *smu,
+ enum smu_clk_type clk_type,
+ uint32_t *min,
+ uint32_t *max)
+{
+ if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+ smu_v14_0_0_get_dpm_ultimate_freq(smu, clk_type, min, max);
+ else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+ smu_v14_0_1_get_dpm_ultimate_freq(smu, clk_type, min, max);
+
+ return 0;
+}
+
static int smu_v14_0_0_get_current_clk_freq(struct smu_context *smu,
enum smu_clk_type clk_type,
uint32_t *value)
@@ -811,6 +1013,37 @@
return smu_v14_0_0_get_smu_metrics_data(smu, member_type, value);
}
+static int smu_v14_0_1_get_dpm_level_count(struct smu_context *smu,
+ enum smu_clk_type clk_type,
+ uint32_t *count)
+{
+ DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+
+ switch (clk_type) {
+ case SMU_SOCCLK:
+ *count = clk_table->NumSocClkLevelsEnabled;
+ break;
+ case SMU_VCLK:
+ case SMU_DCLK:
+ *count = clk_table->Vcn0ClkLevelsEnabled;
+ break;
+ case SMU_VCLK1:
+ case SMU_DCLK1:
+ *count = clk_table->Vcn1ClkLevelsEnabled;
+ break;
+ case SMU_MCLK:
+ *count = clk_table->NumMemPstatesEnabled;
+ break;
+ case SMU_FCLK:
+ *count = clk_table->NumFclkLevelsEnabled;
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
static int smu_v14_0_0_get_dpm_level_count(struct smu_context *smu,
enum smu_clk_type clk_type,
uint32_t *count)
@@ -840,6 +1073,18 @@
return 0;
}
+static int smu_v14_0_common_get_dpm_level_count(struct smu_context *smu,
+ enum smu_clk_type clk_type,
+ uint32_t *count)
+{
+ if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+ smu_v14_0_0_get_dpm_level_count(smu, clk_type, count);
+ else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+ smu_v14_0_1_get_dpm_level_count(smu, clk_type, count);
+
+ return 0;
+}
+
static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
enum smu_clk_type clk_type, char *buf)
{
@@ -866,18 +1111,20 @@
case SMU_SOCCLK:
case SMU_VCLK:
case SMU_DCLK:
+ case SMU_VCLK1:
+ case SMU_DCLK1:
case SMU_MCLK:
case SMU_FCLK:
ret = smu_v14_0_0_get_current_clk_freq(smu, clk_type, &cur_value);
if (ret)
break;
- ret = smu_v14_0_0_get_dpm_level_count(smu, clk_type, &count);
+ ret = smu_v14_0_common_get_dpm_level_count(smu, clk_type, &count);
if (ret)
break;
for (i = 0; i < count; i++) {
- ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, i, &value);
+ ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, i, &value);
if (ret)
break;
@@ -940,8 +1187,13 @@
break;
case SMU_VCLK:
case SMU_DCLK:
- msg_set_min = SMU_MSG_SetHardMinVcn;
- msg_set_max = SMU_MSG_SetSoftMaxVcn;
+ msg_set_min = SMU_MSG_SetHardMinVcn0;
+ msg_set_max = SMU_MSG_SetSoftMaxVcn0;
+ break;
+ case SMU_VCLK1:
+ case SMU_DCLK1:
+ msg_set_min = SMU_MSG_SetHardMinVcn1;
+ msg_set_max = SMU_MSG_SetSoftMaxVcn1;
break;
default:
return -EINVAL;
@@ -971,11 +1223,11 @@
case SMU_FCLK:
case SMU_VCLK:
case SMU_DCLK:
- ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
+ ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
if (ret)
break;
- ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq);
+ ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq);
if (ret)
break;
@@ -1000,25 +1252,25 @@
switch (level) {
case AMD_DPM_FORCED_LEVEL_HIGH:
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, NULL, &sclk_max);
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &fclk_max);
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &socclk_max);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, NULL, &sclk_max);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &fclk_max);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &socclk_max);
sclk_min = sclk_max;
fclk_min = fclk_max;
socclk_min = socclk_max;
break;
case AMD_DPM_FORCED_LEVEL_LOW:
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, NULL);
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, NULL);
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, NULL);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, NULL);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, NULL);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, NULL);
sclk_max = sclk_min;
fclk_max = fclk_min;
socclk_max = socclk_min;
break;
case AMD_DPM_FORCED_LEVEL_AUTO:
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, &sclk_max);
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, &fclk_max);
- smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, &socclk_max);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, &sclk_max);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, &fclk_max);
+ smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, &socclk_max);
break;
case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
@@ -1067,6 +1319,18 @@
return ret;
}
+static int smu_v14_0_1_set_fine_grain_gfx_freq_parameters(struct smu_context *smu)
+{
+ DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+
+ smu->gfx_default_hard_min_freq = clk_table->MinGfxClk;
+ smu->gfx_default_soft_max_freq = clk_table->MaxGfxClk;
+ smu->gfx_actual_hard_min_freq = 0;
+ smu->gfx_actual_soft_max_freq = 0;
+
+ return 0;
+}
+
static int smu_v14_0_0_set_fine_grain_gfx_freq_parameters(struct smu_context *smu)
{
DpmClocks_t *clk_table = smu->smu_table.clocks_table;
@@ -1079,6 +1343,16 @@
return 0;
}
+static int smu_v14_0_common_set_fine_grain_gfx_freq_parameters(struct smu_context *smu)
+{
+ if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+ smu_v14_0_0_set_fine_grain_gfx_freq_parameters(smu);
+ else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+ smu_v14_0_1_set_fine_grain_gfx_freq_parameters(smu);
+
+ return 0;
+}
+
static int smu_v14_0_0_set_vpe_enable(struct smu_context *smu,
bool enable)
{
@@ -1095,6 +1369,25 @@
0, NULL);
}
+static int smu_14_0_1_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table)
+{
+ DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table;
+ uint8_t idx;
+
+ /* Only the Clock information of SOC and VPE is copied to provide VPE DPM settings for use. */
+ for (idx = 0; idx < NUM_SOCCLK_DPM_LEVELS; idx++) {
+ clock_table->SocClocks[idx].Freq = (idx < clk_table->NumSocClkLevelsEnabled) ? clk_table->SocClocks[idx]:0;
+ clock_table->SocClocks[idx].Vol = 0;
+ }
+
+ for (idx = 0; idx < NUM_VPE_DPM_LEVELS; idx++) {
+ clock_table->VPEClocks[idx].Freq = (idx < clk_table->VpeClkLevelsEnabled) ? clk_table->VPEClocks[idx]:0;
+ clock_table->VPEClocks[idx].Vol = 0;
+ }
+
+ return 0;
+}
+
static int smu_14_0_0_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table)
{
DpmClocks_t *clk_table = smu->smu_table.clocks_table;
@@ -1114,6 +1407,16 @@
return 0;
}
+static int smu_v14_0_common_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table)
+{
+ if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0))
+ smu_14_0_0_get_dpm_table(smu, clock_table);
+ else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+ smu_14_0_1_get_dpm_table(smu, clock_table);
+
+ return 0;
+}
+
static const struct pptable_funcs smu_v14_0_0_ppt_funcs = {
.check_fw_status = smu_v14_0_check_fw_status,
.check_fw_version = smu_v14_0_check_fw_version,
@@ -1135,16 +1438,16 @@
.set_driver_table_location = smu_v14_0_set_driver_table_location,
.gfx_off_control = smu_v14_0_gfx_off_control,
.mode2_reset = smu_v14_0_0_mode2_reset,
- .get_dpm_ultimate_freq = smu_v14_0_0_get_dpm_ultimate_freq,
+ .get_dpm_ultimate_freq = smu_v14_0_common_get_dpm_ultimate_freq,
.od_edit_dpm_table = smu_v14_0_od_edit_dpm_table,
.print_clk_levels = smu_v14_0_0_print_clk_levels,
.force_clk_levels = smu_v14_0_0_force_clk_levels,
.set_performance_level = smu_v14_0_0_set_performance_level,
- .set_fine_grain_gfx_freq_parameters = smu_v14_0_0_set_fine_grain_gfx_freq_parameters,
+ .set_fine_grain_gfx_freq_parameters = smu_v14_0_common_set_fine_grain_gfx_freq_parameters,
.set_gfx_power_up_by_imu = smu_v14_0_set_gfx_power_up_by_imu,
.dpm_set_vpe_enable = smu_v14_0_0_set_vpe_enable,
.dpm_set_umsch_mm_enable = smu_v14_0_0_set_umsch_mm_enable,
- .get_dpm_clock_table = smu_14_0_0_get_dpm_table,
+ .get_dpm_clock_table = smu_v14_0_common_get_dpm_table,
};
static void smu_v14_0_0_set_smu_mailbox_registers(struct smu_context *smu)
diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c
index ebb6d8e..1e92594 100644
--- a/drivers/gpu/drm/ast/ast_dp.c
+++ b/drivers/gpu/drm/ast/ast_dp.c
@@ -180,6 +180,7 @@
{
struct ast_device *ast = to_ast_device(dev);
u8 video_on_off = on;
+ u32 i = 0;
// Video On/Off
ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xE3, (u8) ~AST_DP_VIDEO_ENABLE, on);
@@ -192,6 +193,8 @@
ASTDP_MIRROR_VIDEO_ENABLE) != video_on_off) {
// wait 1 ms
mdelay(1);
+ if (++i > 200)
+ break;
}
}
}
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 871e4e2..0683a12 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -777,6 +777,7 @@
unsigned int total_modes_count = 0;
struct drm_client_offset *offsets;
unsigned int connector_count = 0;
+ /* points to modes protected by mode_config.mutex */
struct drm_display_mode **modes;
struct drm_crtc **crtcs;
int i, ret = 0;
@@ -845,7 +846,6 @@
drm_client_pick_crtcs(client, connectors, connector_count,
crtcs, modes, 0, width, height);
}
- mutex_unlock(&dev->mode_config.mutex);
drm_client_modeset_release(client);
@@ -875,6 +875,7 @@
modeset->y = offset->y;
}
}
+ mutex_unlock(&dev->mode_config.mutex);
mutex_unlock(&client->modeset_mutex);
out:
diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c
index e440f45..9333754 100644
--- a/drivers/gpu/drm/drm_gem_atomic_helper.c
+++ b/drivers/gpu/drm/drm_gem_atomic_helper.c
@@ -224,8 +224,8 @@
__drm_atomic_helper_plane_duplicate_state(plane, &new_shadow_plane_state->base);
- drm_format_conv_state_copy(&shadow_plane_state->fmtcnv_state,
- &new_shadow_plane_state->fmtcnv_state);
+ drm_format_conv_state_copy(&new_shadow_plane_state->fmtcnv_state,
+ &shadow_plane_state->fmtcnv_state);
}
EXPORT_SYMBOL(__drm_gem_duplicate_shadow_plane_state);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 734412a..a9bf426 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -164,26 +164,6 @@
*value = gpu->identity.eco_id;
break;
- case ETNAVIV_PARAM_GPU_NN_CORE_COUNT:
- *value = gpu->identity.nn_core_count;
- break;
-
- case ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE:
- *value = gpu->identity.nn_mad_per_core;
- break;
-
- case ETNAVIV_PARAM_GPU_TP_CORE_COUNT:
- *value = gpu->identity.tp_core_count;
- break;
-
- case ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE:
- *value = gpu->identity.on_chip_sram_size;
- break;
-
- case ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE:
- *value = gpu->identity.axi_sram_size;
- break;
-
default:
DBG("%s: invalid param: %u", dev_name(gpu->dev), param);
return -EINVAL;
@@ -663,8 +643,8 @@
/* Disable TX clock gating on affected core revisions. */
if (etnaviv_is_model_rev(gpu, GC4000, 0x5222) ||
etnaviv_is_model_rev(gpu, GC2000, 0x5108) ||
- etnaviv_is_model_rev(gpu, GC2000, 0x6202) ||
- etnaviv_is_model_rev(gpu, GC2000, 0x6203))
+ etnaviv_is_model_rev(gpu, GC7000, 0x6202) ||
+ etnaviv_is_model_rev(gpu, GC7000, 0x6203))
pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX;
/* Disable SE and RA clock gating on affected core revisions. */
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 7d5e915..197e003 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -54,18 +54,6 @@
/* Number of Neural Network cores. */
u32 nn_core_count;
- /* Number of MAD units per Neural Network core. */
- u32 nn_mad_per_core;
-
- /* Number of Tensor Processing cores. */
- u32 tp_core_count;
-
- /* Size in bytes of the SRAM inside the NPU. */
- u32 on_chip_sram_size;
-
- /* Size in bytes of the SRAM across the AXI bus. */
- u32 axi_sram_size;
-
/* Size of the vertex cache. */
u32 vertex_cache_size;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
index d8e7334..8665f26 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c
@@ -17,10 +17,6 @@
.thread_count = 128,
.shader_core_count = 1,
.nn_core_count = 0,
- .nn_mad_per_core = 0,
- .tp_core_count = 0,
- .on_chip_sram_size = 0,
- .axi_sram_size = 0,
.vertex_cache_size = 8,
.vertex_output_buffer_size = 1024,
.pixel_pipes = 1,
@@ -52,11 +48,6 @@
.register_max = 64,
.thread_count = 256,
.shader_core_count = 1,
- .nn_core_count = 0,
- .nn_mad_per_core = 0,
- .tp_core_count = 0,
- .on_chip_sram_size = 0,
- .axi_sram_size = 0,
.vertex_cache_size = 8,
.vertex_output_buffer_size = 512,
.pixel_pipes = 1,
@@ -89,10 +80,6 @@
.thread_count = 512,
.shader_core_count = 2,
.nn_core_count = 0,
- .nn_mad_per_core = 0,
- .tp_core_count = 0,
- .on_chip_sram_size = 0,
- .axi_sram_size = 0,
.vertex_cache_size = 16,
.vertex_output_buffer_size = 1024,
.pixel_pipes = 1,
@@ -125,10 +112,6 @@
.thread_count = 512,
.shader_core_count = 2,
.nn_core_count = 0,
- .nn_mad_per_core = 0,
- .tp_core_count = 0,
- .on_chip_sram_size = 0,
- .axi_sram_size = 0,
.vertex_cache_size = 16,
.vertex_output_buffer_size = 1024,
.pixel_pipes = 1,
@@ -160,11 +143,6 @@
.register_max = 64,
.thread_count = 512,
.shader_core_count = 2,
- .nn_core_count = 0,
- .nn_mad_per_core = 0,
- .tp_core_count = 0,
- .on_chip_sram_size = 0,
- .axi_sram_size = 0,
.vertex_cache_size = 16,
.vertex_output_buffer_size = 1024,
.pixel_pipes = 1,
@@ -197,10 +175,6 @@
.thread_count = 1024,
.shader_core_count = 4,
.nn_core_count = 0,
- .nn_mad_per_core = 0,
- .tp_core_count = 0,
- .on_chip_sram_size = 0,
- .axi_sram_size = 0,
.vertex_cache_size = 16,
.vertex_output_buffer_size = 1024,
.pixel_pipes = 2,
@@ -233,10 +207,6 @@
.thread_count = 256,
.shader_core_count = 1,
.nn_core_count = 8,
- .nn_mad_per_core = 64,
- .tp_core_count = 4,
- .on_chip_sram_size = 524288,
- .axi_sram_size = 1048576,
.vertex_cache_size = 16,
.vertex_output_buffer_size = 1024,
.pixel_pipes = 1,
@@ -269,10 +239,6 @@
.thread_count = 256,
.shader_core_count = 1,
.nn_core_count = 6,
- .nn_mad_per_core = 64,
- .tp_core_count = 3,
- .on_chip_sram_size = 262144,
- .axi_sram_size = 0,
.vertex_cache_size = 16,
.vertex_output_buffer_size = 1024,
.pixel_pipes = 1,
diff --git a/drivers/gpu/drm/gma500/Makefile b/drivers/gpu/drm/gma500/Makefile
index 4f302cd..58fed80 100644
--- a/drivers/gpu/drm/gma500/Makefile
+++ b/drivers/gpu/drm/gma500/Makefile
@@ -34,7 +34,6 @@
psb_intel_lvds.o \
psb_intel_modes.o \
psb_intel_sdvo.o \
- psb_lid.o \
psb_irq.o
gma500_gfx-$(CONFIG_ACPI) += opregion.o
diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c
index dcfcd7b..6dece8f 100644
--- a/drivers/gpu/drm/gma500/psb_device.c
+++ b/drivers/gpu/drm/gma500/psb_device.c
@@ -73,8 +73,7 @@
}
psb_intel_lvds_set_brightness(dev, PSB_MAX_BRIGHTNESS);
- /* This must occur after the backlight is properly initialised */
- psb_lid_timer_init(dev_priv);
+
return 0;
}
@@ -259,8 +258,6 @@
static void psb_chip_teardown(struct drm_device *dev)
{
- struct drm_psb_private *dev_priv = to_drm_psb_private(dev);
- psb_lid_timer_takedown(dev_priv);
gma_intel_teardown_gmbus(dev);
}
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index c5edfa4..83c1768 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -162,7 +162,6 @@
#define PSB_NUM_VBLANKS 2
#define PSB_WATCHDOG_DELAY (HZ * 2)
-#define PSB_LID_DELAY (HZ / 10)
#define PSB_MAX_BRIGHTNESS 100
@@ -491,11 +490,7 @@
/* Hotplug handling */
struct work_struct hotplug_work;
- /* LID-Switch */
- spinlock_t lid_lock;
- struct timer_list lid_timer;
struct psb_intel_opregion opregion;
- u32 lid_last_state;
/* Watchdog */
uint32_t apm_reg;
@@ -591,10 +586,6 @@
int i2c_bus; /* I2C bus identifier for Moorestown */
};
-/* psb_lid.c */
-extern void psb_lid_timer_init(struct drm_psb_private *dev_priv);
-extern void psb_lid_timer_takedown(struct drm_psb_private *dev_priv);
-
/* modesetting */
extern void psb_modeset_init(struct drm_device *dev);
extern void psb_modeset_cleanup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/gma500/psb_lid.c b/drivers/gpu/drm/gma500/psb_lid.c
deleted file mode 100644
index 58a7fe3..0000000
--- a/drivers/gpu/drm/gma500/psb_lid.c
+++ /dev/null
@@ -1,80 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/**************************************************************************
- * Copyright (c) 2007, Intel Corporation.
- *
- * Authors: Thomas Hellstrom <thomas-at-tungstengraphics-dot-com>
- **************************************************************************/
-
-#include <linux/spinlock.h>
-
-#include "psb_drv.h"
-#include "psb_intel_reg.h"
-#include "psb_reg.h"
-
-static void psb_lid_timer_func(struct timer_list *t)
-{
- struct drm_psb_private *dev_priv = from_timer(dev_priv, t, lid_timer);
- struct drm_device *dev = (struct drm_device *)&dev_priv->dev;
- struct timer_list *lid_timer = &dev_priv->lid_timer;
- unsigned long irq_flags;
- u32 __iomem *lid_state = dev_priv->opregion.lid_state;
- u32 pp_status;
-
- if (readl(lid_state) == dev_priv->lid_last_state)
- goto lid_timer_schedule;
-
- if ((readl(lid_state)) & 0x01) {
- /*lid state is open*/
- REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) | POWER_TARGET_ON);
- do {
- pp_status = REG_READ(PP_STATUS);
- } while ((pp_status & PP_ON) == 0 &&
- (pp_status & PP_SEQUENCE_MASK) != 0);
-
- if (REG_READ(PP_STATUS) & PP_ON) {
- /*FIXME: should be backlight level before*/
- psb_intel_lvds_set_brightness(dev, 100);
- } else {
- DRM_DEBUG("LVDS panel never powered up");
- return;
- }
- } else {
- psb_intel_lvds_set_brightness(dev, 0);
-
- REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) & ~POWER_TARGET_ON);
- do {
- pp_status = REG_READ(PP_STATUS);
- } while ((pp_status & PP_ON) == 0);
- }
- dev_priv->lid_last_state = readl(lid_state);
-
-lid_timer_schedule:
- spin_lock_irqsave(&dev_priv->lid_lock, irq_flags);
- if (!timer_pending(lid_timer)) {
- lid_timer->expires = jiffies + PSB_LID_DELAY;
- add_timer(lid_timer);
- }
- spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags);
-}
-
-void psb_lid_timer_init(struct drm_psb_private *dev_priv)
-{
- struct timer_list *lid_timer = &dev_priv->lid_timer;
- unsigned long irq_flags;
-
- spin_lock_init(&dev_priv->lid_lock);
- spin_lock_irqsave(&dev_priv->lid_lock, irq_flags);
-
- timer_setup(lid_timer, psb_lid_timer_func, 0);
-
- lid_timer->expires = jiffies + PSB_LID_DELAY;
-
- add_timer(lid_timer);
- spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags);
-}
-
-void psb_lid_timer_takedown(struct drm_psb_private *dev_priv)
-{
- del_timer_sync(&dev_priv->lid_timer);
-}
-
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index ed89b86..f672bfd 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2534,7 +2534,8 @@
intel_atomic_get_old_cdclk_state(state);
const struct intel_cdclk_state *new_cdclk_state =
intel_atomic_get_new_cdclk_state(state);
- enum pipe pipe = new_cdclk_state->pipe;
+ struct intel_cdclk_config cdclk_config;
+ enum pipe pipe;
if (!intel_cdclk_changed(&old_cdclk_state->actual,
&new_cdclk_state->actual))
@@ -2543,12 +2544,25 @@
if (IS_DG2(i915))
intel_cdclk_pcode_pre_notify(state);
- if (pipe == INVALID_PIPE ||
- old_cdclk_state->actual.cdclk <= new_cdclk_state->actual.cdclk) {
- drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed);
+ if (new_cdclk_state->disable_pipes) {
+ cdclk_config = new_cdclk_state->actual;
+ pipe = INVALID_PIPE;
+ } else {
+ if (new_cdclk_state->actual.cdclk >= old_cdclk_state->actual.cdclk) {
+ cdclk_config = new_cdclk_state->actual;
+ pipe = new_cdclk_state->pipe;
+ } else {
+ cdclk_config = old_cdclk_state->actual;
+ pipe = INVALID_PIPE;
+ }
- intel_set_cdclk(i915, &new_cdclk_state->actual, pipe);
+ cdclk_config.voltage_level = max(new_cdclk_state->actual.voltage_level,
+ old_cdclk_state->actual.voltage_level);
}
+
+ drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed);
+
+ intel_set_cdclk(i915, &cdclk_config, pipe);
}
/**
@@ -2566,7 +2580,7 @@
intel_atomic_get_old_cdclk_state(state);
const struct intel_cdclk_state *new_cdclk_state =
intel_atomic_get_new_cdclk_state(state);
- enum pipe pipe = new_cdclk_state->pipe;
+ enum pipe pipe;
if (!intel_cdclk_changed(&old_cdclk_state->actual,
&new_cdclk_state->actual))
@@ -2575,12 +2589,15 @@
if (IS_DG2(i915))
intel_cdclk_pcode_post_notify(state);
- if (pipe != INVALID_PIPE &&
- old_cdclk_state->actual.cdclk > new_cdclk_state->actual.cdclk) {
- drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed);
+ if (!new_cdclk_state->disable_pipes &&
+ new_cdclk_state->actual.cdclk < old_cdclk_state->actual.cdclk)
+ pipe = new_cdclk_state->pipe;
+ else
+ pipe = INVALID_PIPE;
- intel_set_cdclk(i915, &new_cdclk_state->actual, pipe);
- }
+ drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed);
+
+ intel_set_cdclk(i915, &new_cdclk_state->actual, pipe);
}
static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state)
@@ -3058,6 +3075,7 @@
return NULL;
cdclk_state->pipe = INVALID_PIPE;
+ cdclk_state->disable_pipes = false;
return &cdclk_state->base;
}
@@ -3236,6 +3254,8 @@
if (ret)
return ret;
+ new_cdclk_state->disable_pipes = true;
+
drm_dbg_kms(&dev_priv->drm,
"Modeset required for cdclk change\n");
}
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h
index 48fd7d3..71bc032 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.h
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.h
@@ -51,6 +51,9 @@
/* bitmask of active pipes */
u8 active_pipes;
+
+ /* update cdclk with pipes disabled */
+ bool disable_pipes;
};
int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index c587a8e..c17462b 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -4256,7 +4256,12 @@
static bool crtcs_port_sync_compatible(const struct intel_crtc_state *crtc_state1,
const struct intel_crtc_state *crtc_state2)
{
+ /*
+ * FIXME the modeset sequence is currently wrong and
+ * can't deal with bigjoiner + port sync at the same time.
+ */
return crtc_state1->hw.active && crtc_state2->hw.active &&
+ !crtc_state1->bigjoiner_pipes && !crtc_state2->bigjoiner_pipes &&
crtc_state1->output_types == crtc_state2->output_types &&
crtc_state1->output_format == crtc_state2->output_format &&
crtc_state1->lane_count == crtc_state2->lane_count &&
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index abd62be..e583515 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2725,7 +2725,11 @@
intel_panel_downclock_mode(connector, &pipe_config->hw.adjusted_mode);
int pixel_clock;
- if (has_seamless_m_n(connector))
+ /*
+ * FIXME all joined pipes share the same transcoder.
+ * Need to account for that when updating M/N live.
+ */
+ if (has_seamless_m_n(connector) && !pipe_config->bigjoiner_pipes)
pipe_config->update_m_n = true;
if (!can_enable_drrs(connector, pipe_config, downclock_mode)) {
diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
index b98a878..9db43bd 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
@@ -691,12 +691,15 @@
u8 bcaps;
int ret;
+ *hdcp_capable = false;
+ *hdcp2_capable = false;
if (!intel_encoder_is_mst(connector->encoder))
return -EINVAL;
ret = _intel_dp_hdcp2_get_capability(aux, hdcp2_capable);
if (ret)
- return ret;
+ drm_dbg_kms(&i915->drm,
+ "HDCP2 DPCD capability read failed err: %d\n", ret);
ret = intel_dp_hdcp_read_bcaps(aux, i915, &bcaps);
if (ret)
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index b6e539f..aabd018 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1422,6 +1422,17 @@
return;
}
+ /*
+ * FIXME figure out what is wrong with PSR+bigjoiner and
+ * fix it. Presumably something related to the fact that
+ * PSR is a transcoder level feature.
+ */
+ if (crtc_state->bigjoiner_pipes) {
+ drm_dbg_kms(&dev_priv->drm,
+ "PSR disabled due to bigjoiner\n");
+ return;
+ }
+
if (CAN_PANEL_REPLAY(intel_dp))
crtc_state->has_panel_replay = true;
else
diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c
index eb5bd07..f542ee1 100644
--- a/drivers/gpu/drm/i915/display/intel_vrr.c
+++ b/drivers/gpu/drm/i915/display/intel_vrr.c
@@ -117,6 +117,13 @@
const struct drm_display_info *info = &connector->base.display_info;
int vmin, vmax;
+ /*
+ * FIXME all joined pipes share the same transcoder.
+ * Need to account for that during VRR toggle/push/etc.
+ */
+ if (crtc_state->bigjoiner_pipes)
+ return;
+
if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
return;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index f3dcae4..0f83c6d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1403,14 +1403,17 @@
* Trying to pass a 'need_sync' or 'in_reset' flag all the way down through
* every possible call stack is unfeasible. It would be too intrusive to many
* areas that really don't care about the GuC backend. However, there is the
- * 'reset_in_progress' flag available, so just use that.
+ * I915_RESET_BACKOFF flag and the gt->reset.mutex can be tested for is_locked.
+ * So just use those. Note that testing both is required due to the hideously
+ * complex nature of the i915 driver's reset code paths.
*
* And note that in the case of a reset occurring during driver unload
- * (wedge_on_fini), skipping the cancel in _prepare (when the reset flag is set
- * is fine because there is another cancel in _finish (when the reset flag is
- * not).
+ * (wedged_on_fini), skipping the cancel in reset_prepare/reset_fini (when the
+ * reset flag/mutex are set) is fine because there is another explicit cancel in
+ * intel_guc_submission_fini (when the reset flag/mutex are not).
*/
- if (guc_to_gt(guc)->uc.reset_in_progress)
+ if (mutex_is_locked(&guc_to_gt(guc)->reset.mutex) ||
+ test_bit(I915_RESET_BACKOFF, &guc_to_gt(guc)->reset.flags))
cancel_delayed_work(&guc->timestamp.work);
else
cancel_delayed_work_sync(&guc->timestamp.work);
@@ -1424,8 +1427,6 @@
unsigned long flags;
ktime_t unused;
- guc_cancel_busyness_worker(guc);
-
spin_lock_irqsave(&guc->timestamp.lock, flags);
guc_update_pm_timestamp(guc, &unused);
@@ -2004,13 +2005,6 @@
void intel_guc_submission_reset_finish(struct intel_guc *guc)
{
- /*
- * Ensure the busyness worker gets cancelled even on a fatal wedge.
- * Note that reset_prepare is not allowed to because it confuses lockdep.
- */
- if (guc_submission_initialized(guc))
- guc_cancel_busyness_worker(guc);
-
/* Reset called during driver load or during wedge? */
if (unlikely(!guc_submission_initialized(guc) ||
!intel_guc_is_fw_running(guc) ||
@@ -2136,6 +2130,7 @@
if (!guc->submission_initialized)
return;
+ guc_fini_engine_stats(guc);
guc_flush_destroyed_contexts(guc);
guc_lrc_desc_pool_destroy_v69(guc);
i915_sched_engine_put(guc->sched_engine);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 6dfe5d9..399bc31 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -637,6 +637,10 @@
{
struct intel_guc *guc = &uc->guc;
+ /*
+ * NB: The wedge code path results in prepare -> prepare -> finish -> finish.
+ * So this function is sometimes called with the in-progress flag not set.
+ */
uc->reset_in_progress = false;
/* Firmware expected to be running when this function is called */
diff --git a/drivers/gpu/drm/imagination/pvr_fw_mips.h b/drivers/gpu/drm/imagination/pvr_fw_mips.h
index 408dbe6..a0c5c41 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_mips.h
+++ b/drivers/gpu/drm/imagination/pvr_fw_mips.h
@@ -7,13 +7,14 @@
#include "pvr_rogue_mips.h"
#include <asm/page.h>
+#include <linux/math.h>
#include <linux/types.h>
/* Forward declaration from pvr_gem.h. */
struct pvr_gem_object;
-#define PVR_MIPS_PT_PAGE_COUNT ((ROGUE_MIPSFW_MAX_NUM_PAGETABLE_PAGES * ROGUE_MIPSFW_PAGE_SIZE_4K) \
- >> PAGE_SHIFT)
+#define PVR_MIPS_PT_PAGE_COUNT DIV_ROUND_UP(ROGUE_MIPSFW_MAX_NUM_PAGETABLE_PAGES * ROGUE_MIPSFW_PAGE_SIZE_4K, PAGE_SIZE)
+
/**
* struct pvr_fw_mips_data - MIPS-specific data
*/
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 0674aca..cf0b1de 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1377,6 +1377,10 @@
if (adreno_is_a618(gpu))
gpu->ubwc_config.highest_bank_bit = 14;
+ if (adreno_is_a619(gpu))
+ /* TODO: Should be 14 but causes corruption at e.g. 1920x1200 on DP */
+ gpu->ubwc_config.highest_bank_bit = 13;
+
if (adreno_is_a619_holi(gpu))
gpu->ubwc_config.highest_bank_bit = 13;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 1f5245f..a847a0f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -852,7 +852,7 @@
(block->type << 8) | i);
in += CRASHDUMP_READ(in, REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE,
- block->size, dumper->iova + A6XX_CD_DATA_OFFSET);
+ block->size, out);
out += block->size * sizeof(u32);
}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
index 9a9f709..a3e60ac 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h
@@ -324,6 +324,7 @@
},
};
+/* TODO: INTF 3, 8 and 7 are used for MST, marked as INTF_NONE for now */
static const struct dpu_intf_cfg x1e80100_intf[] = {
{
.name = "intf_0", .id = INTF_0,
@@ -358,8 +359,8 @@
.name = "intf_3", .id = INTF_3,
.base = 0x37000, .len = 0x280,
.features = INTF_SC7280_MASK,
- .type = INTF_DP,
- .controller_id = MSM_DP_CONTROLLER_1,
+ .type = INTF_NONE,
+ .controller_id = MSM_DP_CONTROLLER_0, /* pair with intf_0 for DP MST */
.prog_fetch_lines_worst_case = 24,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31),
@@ -368,7 +369,7 @@
.base = 0x38000, .len = 0x280,
.features = INTF_SC7280_MASK,
.type = INTF_DP,
- .controller_id = MSM_DP_CONTROLLER_2,
+ .controller_id = MSM_DP_CONTROLLER_1,
.prog_fetch_lines_worst_case = 24,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 20),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 21),
@@ -381,6 +382,33 @@
.prog_fetch_lines_worst_case = 24,
.intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 22),
.intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 23),
+ }, {
+ .name = "intf_6", .id = INTF_6,
+ .base = 0x3A000, .len = 0x280,
+ .features = INTF_SC7280_MASK,
+ .type = INTF_DP,
+ .controller_id = MSM_DP_CONTROLLER_2,
+ .prog_fetch_lines_worst_case = 24,
+ .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17),
+ .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16),
+ }, {
+ .name = "intf_7", .id = INTF_7,
+ .base = 0x3b000, .len = 0x280,
+ .features = INTF_SC7280_MASK,
+ .type = INTF_NONE,
+ .controller_id = MSM_DP_CONTROLLER_2, /* pair with intf_6 for DP MST */
+ .prog_fetch_lines_worst_case = 24,
+ .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 18),
+ .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 19),
+ }, {
+ .name = "intf_8", .id = INTF_8,
+ .base = 0x3c000, .len = 0x280,
+ .features = INTF_SC7280_MASK,
+ .type = INTF_NONE,
+ .controller_id = MSM_DP_CONTROLLER_1, /* pair with intf_4 for DP MST */
+ .prog_fetch_lines_worst_case = 24,
+ .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12),
+ .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13),
},
};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index ef87123..68fae04 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -459,15 +459,15 @@
&perf->core_clk_rate);
debugfs_create_u32("enable_bw_release", 0600, entry,
(u32 *)&perf->enable_bw_release);
- debugfs_create_u32("threshold_low", 0600, entry,
+ debugfs_create_u32("threshold_low", 0400, entry,
(u32 *)&perf->perf_cfg->max_bw_low);
- debugfs_create_u32("threshold_high", 0600, entry,
+ debugfs_create_u32("threshold_high", 0400, entry,
(u32 *)&perf->perf_cfg->max_bw_high);
- debugfs_create_u32("min_core_ib", 0600, entry,
+ debugfs_create_u32("min_core_ib", 0400, entry,
(u32 *)&perf->perf_cfg->min_core_ib);
- debugfs_create_u32("min_llcc_ib", 0600, entry,
+ debugfs_create_u32("min_llcc_ib", 0400, entry,
(u32 *)&perf->perf_cfg->min_llcc_ib);
- debugfs_create_u32("min_dram_ib", 0600, entry,
+ debugfs_create_u32("min_dram_ib", 0400, entry,
(u32 *)&perf->perf_cfg->min_dram_ib);
debugfs_create_file("perf_mode", 0600, entry,
(u32 *)perf, &dpu_core_perf_mode_fops);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
index 946dd01..6a0a748 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -525,14 +525,14 @@
int ret;
if (!irq_cb) {
- DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n",
- DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb);
+ DPU_ERROR("IRQ=[%d, %d] NULL callback\n",
+ DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
return -EINVAL;
}
if (!dpu_core_irq_is_valid(irq_idx)) {
- DPU_ERROR("invalid IRQ=[%d, %d]\n",
- DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx));
+ DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n",
+ DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb);
return -EINVAL;
}
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index c4cb82a..ffbfde9 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -484,7 +484,7 @@
}
}
-static int dp_display_handle_port_ststus_changed(struct dp_display_private *dp)
+static int dp_display_handle_port_status_changed(struct dp_display_private *dp)
{
int rc = 0;
@@ -541,7 +541,7 @@
drm_dbg_dp(dp->drm_dev, "hpd_state=%d sink_request=%d\n",
dp->hpd_state, sink_request);
if (sink_request & DS_PORT_STATUS_CHANGED)
- rc = dp_display_handle_port_ststus_changed(dp);
+ rc = dp_display_handle_port_status_changed(dp);
else
rc = dp_display_handle_irq_hpd(dp);
}
@@ -588,6 +588,7 @@
ret = dp_display_usbpd_configure_cb(&pdev->dev);
if (ret) { /* link train failed */
dp->hpd_state = ST_DISCONNECTED;
+ pm_runtime_put_sync(&pdev->dev);
} else {
dp->hpd_state = ST_MAINLINK_READY;
}
@@ -645,6 +646,7 @@
dp_display_host_phy_exit(dp);
dp->hpd_state = ST_DISCONNECTED;
dp_display_notify_disconnect(&dp->dp_display.pdev->dev);
+ pm_runtime_put_sync(&pdev->dev);
mutex_unlock(&dp->event_mutex);
return 0;
}
diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index e3f61c3..80166f7 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -89,7 +89,7 @@
for (i = 0; i < n; i++) {
ret = msm_gem_get_and_pin_iova(fb->obj[i], aspace, &msm_fb->iova[i]);
- drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)",
+ drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)\n",
fb->base.id, i, msm_fb->iova[i], ret);
if (ret)
return ret;
@@ -176,7 +176,7 @@
const struct msm_format *format;
int ret, i, n;
- drm_dbg_state(dev, "create framebuffer: mode_cmd=%p (%dx%d@%4.4s)",
+ drm_dbg_state(dev, "create framebuffer: mode_cmd=%p (%dx%d@%4.4s)\n",
mode_cmd, mode_cmd->width, mode_cmd->height,
(char *)&mode_cmd->pixel_format);
@@ -232,7 +232,7 @@
refcount_set(&msm_fb->dirtyfb, 1);
- drm_dbg_state(dev, "create: FB ID: %d (%p)", fb->base.id, fb);
+ drm_dbg_state(dev, "create: FB ID: %d (%p)\n", fb->base.id, fb);
return fb;
diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c
index 84c21ec..af6a6fc 100644
--- a/drivers/gpu/drm/msm/msm_kms.c
+++ b/drivers/gpu/drm/msm/msm_kms.c
@@ -149,7 +149,7 @@
struct msm_kms *kms = priv->kms;
if (!kms)
return -ENXIO;
- drm_dbg_vbl(dev, "crtc=%u", crtc->base.id);
+ drm_dbg_vbl(dev, "crtc=%u\n", crtc->base.id);
return vblank_ctrl_queue_work(priv, crtc, true);
}
@@ -160,7 +160,7 @@
struct msm_kms *kms = priv->kms;
if (!kms)
return;
- drm_dbg_vbl(dev, "crtc=%u", crtc->base.id);
+ drm_dbg_vbl(dev, "crtc=%u\n", crtc->base.id);
vblank_ctrl_queue_work(priv, crtc, false);
}
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 6f5d376..a11d16a 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -15,7 +15,9 @@
};
struct nvkm_gsp_radix3 {
- struct nvkm_gsp_mem mem[3];
+ struct nvkm_gsp_mem lvl0;
+ struct nvkm_gsp_mem lvl1;
+ struct sg_table lvl2;
};
int nvkm_gsp_sg(struct nvkm_device *, u64 size, struct sg_table *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 479effcf..79cfab5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -23,6 +23,7 @@
*/
#include "nouveau_drv.h"
+#include "nouveau_bios.h"
#include "nouveau_reg.h"
#include "dispnv04/hw.h"
#include "nouveau_encoder.h"
@@ -1677,7 +1678,7 @@
*/
if (nv_match_device(dev, 0x0201, 0x1462, 0x8851)) {
if (*conn == 0xf2005014 && *conf == 0xffffffff) {
- fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, 1);
+ fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, DCB_OUTPUT_B);
return false;
}
}
@@ -1763,26 +1764,26 @@
#ifdef __powerpc__
/* Apple iMac G4 NV17 */
if (of_machine_is_compatible("PowerMac4,5")) {
- fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, 1);
- fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, 2);
+ fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, DCB_OUTPUT_B);
+ fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, DCB_OUTPUT_C);
return;
}
#endif
/* Make up some sane defaults */
fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG,
- bios->legacy.i2c_indices.crt, 1, 1);
+ bios->legacy.i2c_indices.crt, 1, DCB_OUTPUT_B);
if (nv04_tv_identify(dev, bios->legacy.i2c_indices.tv) >= 0)
fabricate_dcb_output(dcb, DCB_OUTPUT_TV,
bios->legacy.i2c_indices.tv,
- all_heads, 0);
+ all_heads, DCB_OUTPUT_A);
else if (bios->tmds.output0_script_ptr ||
bios->tmds.output1_script_ptr)
fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS,
bios->legacy.i2c_indices.panel,
- all_heads, 1);
+ all_heads, DCB_OUTPUT_B);
}
static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c
index 7de7707e..a72c458 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dp.c
@@ -225,12 +225,18 @@
u8 *dpcd = nv_encoder->dp.dpcd;
int ret = NOUVEAU_DP_NONE, hpd;
- /* If we've already read the DPCD on an eDP device, we don't need to
- * reread it as it won't change
+ /* eDP ports don't support hotplugging - so there's no point in probing eDP ports unless we
+ * haven't probed them once before.
*/
- if (connector->connector_type == DRM_MODE_CONNECTOR_eDP &&
- dpcd[DP_DPCD_REV] != 0)
- return NOUVEAU_DP_SST;
+ if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+ if (connector->status == connector_status_connected)
+ return NOUVEAU_DP_SST;
+ else if (connector->status == connector_status_disconnected)
+ return NOUVEAU_DP_NONE;
+ }
+
+ // Ensure that the aux bus is enabled for probing
+ drm_dp_dpcd_set_powered(&nv_connector->aux, true);
mutex_lock(&nv_encoder->dp.hpd_irq_lock);
if (mstm) {
@@ -293,6 +299,13 @@
if (mstm && !mstm->suspended && ret != NOUVEAU_DP_MST)
nv50_mstm_remove(mstm);
+ /* GSP doesn't like when we try to do aux transactions on a port it considers disconnected,
+ * and since we don't really have a usecase for that anyway - just disable the aux bus here
+ * if we've decided the connector is disconnected
+ */
+ if (ret == NOUVEAU_DP_NONE)
+ drm_dp_dpcd_set_powered(&nv_connector->aux, false);
+
mutex_unlock(&nv_encoder->dp.hpd_irq_lock);
return ret;
}
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
index adc60b2..141b0a5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
@@ -205,7 +205,9 @@
break;
case NVKM_FIRMWARE_IMG_DMA:
nvkm_memory_unref(&memory);
- dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys);
+ dma_unmap_single(fw->device->dev, fw->phys, sg_dma_len(&fw->mem.sgl),
+ DMA_TO_DEVICE);
+ kfree(fw->img);
break;
case NVKM_FIRMWARE_IMG_SGT:
nvkm_memory_unref(&memory);
@@ -235,14 +237,17 @@
fw->img = kmemdup(src, fw->len, GFP_KERNEL);
break;
case NVKM_FIRMWARE_IMG_DMA: {
- dma_addr_t addr;
-
len = ALIGN(fw->len, PAGE_SIZE);
- fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL);
- if (fw->img) {
- memcpy(fw->img, src, fw->len);
- fw->phys = addr;
+ fw->img = kmalloc(len, GFP_KERNEL);
+ if (!fw->img)
+ return -ENOMEM;
+
+ memcpy(fw->img, src, fw->len);
+ fw->phys = dma_map_single(fw->device->dev, fw->img, len, DMA_TO_DEVICE);
+ if (dma_mapping_error(fw->device->dev, fw->phys)) {
+ kfree(fw->img);
+ return -EFAULT;
}
sg_init_one(&fw->mem.sgl, fw->img, len);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c
index 4bf486b..cb05f7f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c
@@ -66,11 +66,16 @@
return ERR_PTR(-EINVAL);
}
+static void of_fini(void *p)
+{
+ kfree(p);
+}
+
const struct nvbios_source
nvbios_of = {
.name = "OpenFirmware",
.init = of_init,
- .fini = (void(*)(void *))kfree,
+ .fini = of_fini,
.read = of_read,
.size = of_size,
.rw = false,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
index 7bcbc48..271bfa0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
@@ -25,6 +25,7 @@
#include <subdev/bios.h>
#include <subdev/bios/init.h>
+#include <subdev/gsp.h>
void
gm107_devinit_disable(struct nvkm_devinit *init)
@@ -33,10 +34,13 @@
u32 r021c00 = nvkm_rd32(device, 0x021c00);
u32 r021c04 = nvkm_rd32(device, 0x021c04);
- if (r021c00 & 0x00000001)
- nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0);
- if (r021c00 & 0x00000004)
- nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2);
+ /* gsp only wants to enable/disable display */
+ if (!nvkm_gsp_rm(device->gsp)) {
+ if (r021c00 & 0x00000001)
+ nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0);
+ if (r021c00 & 0x00000004)
+ nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2);
+ }
if (r021c04 & 0x00000001)
nvkm_subdev_disable(device, NVKM_ENGINE_DISP, 0);
}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
index 11b4c9c..666eb93 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
@@ -41,6 +41,7 @@
rm->dtor = r535_devinit_dtor;
rm->post = hw->post;
+ rm->disable = hw->disable;
ret = nv50_devinit_new_(rm, device, type, inst, pdevinit);
if (ret)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index 9994cbd..abe41f7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -1112,7 +1112,7 @@
rpc->numEntries = NV_GSP_REG_NUM_ENTRIES;
str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]);
- strings = (char *)&rpc->entries[NV_GSP_REG_NUM_ENTRIES];
+ strings = (char *)rpc + str_offset;
for (i = 0; i < NV_GSP_REG_NUM_ENTRIES; i++) {
int name_len = strlen(r535_registry_entries[i].name) + 1;
@@ -1624,7 +1624,7 @@
meta->magic = GSP_FW_WPR_META_MAGIC;
meta->revision = GSP_FW_WPR_META_REVISION;
- meta->sysmemAddrOfRadix3Elf = gsp->radix3.mem[0].addr;
+ meta->sysmemAddrOfRadix3Elf = gsp->radix3.lvl0.addr;
meta->sizeOfRadix3Elf = gsp->fb.wpr2.elf.size;
meta->sysmemAddrOfBootloader = gsp->boot.fw.addr;
@@ -1919,8 +1919,9 @@
static void
nvkm_gsp_radix3_dtor(struct nvkm_gsp *gsp, struct nvkm_gsp_radix3 *rx3)
{
- for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--)
- nvkm_gsp_mem_dtor(gsp, &rx3->mem[i]);
+ nvkm_gsp_sg_free(gsp->subdev.device, &rx3->lvl2);
+ nvkm_gsp_mem_dtor(gsp, &rx3->lvl1);
+ nvkm_gsp_mem_dtor(gsp, &rx3->lvl0);
}
/**
@@ -1960,36 +1961,60 @@
nvkm_gsp_radix3_sg(struct nvkm_gsp *gsp, struct sg_table *sgt, u64 size,
struct nvkm_gsp_radix3 *rx3)
{
- u64 addr;
+ struct sg_dma_page_iter sg_dma_iter;
+ struct scatterlist *sg;
+ size_t bufsize;
+ u64 *pte;
+ int ret, i, page_idx = 0;
- for (int i = ARRAY_SIZE(rx3->mem) - 1; i >= 0; i--) {
- u64 *ptes;
- size_t bufsize;
- int ret, idx;
+ ret = nvkm_gsp_mem_ctor(gsp, GSP_PAGE_SIZE, &rx3->lvl0);
+ if (ret)
+ return ret;
- bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
- ret = nvkm_gsp_mem_ctor(gsp, bufsize, &rx3->mem[i]);
- if (ret)
- return ret;
+ ret = nvkm_gsp_mem_ctor(gsp, GSP_PAGE_SIZE, &rx3->lvl1);
+ if (ret)
+ goto lvl1_fail;
- ptes = rx3->mem[i].data;
- if (i == 2) {
- struct scatterlist *sgl;
+ // Allocate level 2
+ bufsize = ALIGN((size / GSP_PAGE_SIZE) * sizeof(u64), GSP_PAGE_SIZE);
+ ret = nvkm_gsp_sg(gsp->subdev.device, bufsize, &rx3->lvl2);
+ if (ret)
+ goto lvl2_fail;
- for_each_sgtable_dma_sg(sgt, sgl, idx) {
- for (int j = 0; j < sg_dma_len(sgl) / GSP_PAGE_SIZE; j++)
- *ptes++ = sg_dma_address(sgl) + (GSP_PAGE_SIZE * j);
- }
- } else {
- for (int j = 0; j < size / GSP_PAGE_SIZE; j++)
- *ptes++ = addr + GSP_PAGE_SIZE * j;
+ // Write the bus address of level 1 to level 0
+ pte = rx3->lvl0.data;
+ *pte = rx3->lvl1.addr;
+
+ // Write the bus address of each page in level 2 to level 1
+ pte = rx3->lvl1.data;
+ for_each_sgtable_dma_page(&rx3->lvl2, &sg_dma_iter, 0)
+ *pte++ = sg_page_iter_dma_address(&sg_dma_iter);
+
+ // Finally, write the bus address of each page in sgt to level 2
+ for_each_sgtable_sg(&rx3->lvl2, sg, i) {
+ void *sgl_end;
+
+ pte = sg_virt(sg);
+ sgl_end = (void *)pte + sg->length;
+
+ for_each_sgtable_dma_page(sgt, &sg_dma_iter, page_idx) {
+ *pte++ = sg_page_iter_dma_address(&sg_dma_iter);
+ page_idx++;
+
+ // Go to the next scatterlist for level 2 if we've reached the end
+ if ((void *)pte >= sgl_end)
+ break;
}
-
- size = rx3->mem[i].size;
- addr = rx3->mem[i].addr;
}
- return 0;
+ if (ret) {
+lvl2_fail:
+ nvkm_gsp_mem_dtor(gsp, &rx3->lvl1);
+lvl1_fail:
+ nvkm_gsp_mem_dtor(gsp, &rx3->lvl0);
+ }
+
+ return ret;
}
int
@@ -2021,7 +2046,7 @@
sr = gsp->sr.meta.data;
sr->magic = GSP_FW_SR_META_MAGIC;
sr->revision = GSP_FW_SR_META_REVISION;
- sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.mem[0].addr;
+ sr->sysmemAddrOfSuspendResumeData = gsp->sr.radix3.lvl0.addr;
sr->sizeOfSuspendResumeData = len;
mbox0 = lower_32_bits(gsp->sr.meta.addr);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
index a7f3fc3..dd5b5a1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c
@@ -222,8 +222,11 @@
void __iomem *map = NULL;
/* Already mapped? */
- if (refcount_inc_not_zero(&iobj->maps))
+ if (refcount_inc_not_zero(&iobj->maps)) {
+ /* read barrier match the wmb on refcount set */
+ smp_rmb();
return iobj->map;
+ }
/* Take the lock, and re-check that another thread hasn't
* already mapped the object in the meantime.
@@ -250,6 +253,8 @@
iobj->base.memory.ptrs = &nv50_instobj_fast;
else
iobj->base.memory.ptrs = &nv50_instobj_slow;
+ /* barrier to ensure the ptrs are written before refcount is set */
+ smp_wmb();
refcount_set(&iobj->maps, 1);
}
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index d037b3b..5b15d02 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -177,7 +177,7 @@
config DRM_PANEL_ILITEK_ILI9341
tristate "Ilitek ILI9341 240x320 QVGA panels"
- depends on OF && SPI
+ depends on SPI
select DRM_KMS_HELPER
select DRM_GEM_DMA_HELPER
depends on BACKLIGHT_CLASS_DEVICE
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
index 3574681..b933380 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
@@ -22,8 +22,9 @@
#include <linux/bitops.h>
#include <linux/delay.h>
#include <linux/gpio/consumer.h>
+#include <linux/mod_devicetable.h>
#include <linux/module.h>
-#include <linux/of.h>
+#include <linux/property.h>
#include <linux/regulator/consumer.h>
#include <linux/spi/spi.h>
@@ -421,7 +422,7 @@
ili9341_dpi_init(ili);
- return ret;
+ return 0;
}
static int ili9341_dpi_enable(struct drm_panel *panel)
@@ -691,7 +692,7 @@
* Every new incarnation of this display must have a unique
* data entry for the system in this driver.
*/
- ili->conf = of_device_get_match_data(dev);
+ ili->conf = device_get_match_data(dev);
if (!ili->conf) {
dev_err(dev, "missing device configuration\n");
return -ENODEV;
@@ -714,18 +715,18 @@
reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
if (IS_ERR(reset))
- dev_err(dev, "Failed to get gpio 'reset'\n");
+ return dev_err_probe(dev, PTR_ERR(reset), "Failed to get gpio 'reset'\n");
dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW);
if (IS_ERR(dc))
- dev_err(dev, "Failed to get gpio 'dc'\n");
+ return dev_err_probe(dev, PTR_ERR(dc), "Failed to get gpio 'dc'\n");
if (!strcmp(id->name, "sf-tc240t-9370-t"))
return ili9341_dpi_probe(spi, dc, reset);
else if (!strcmp(id->name, "yx240qv29"))
return ili9341_dbi_probe(spi, dc, reset);
- return -1;
+ return -ENODEV;
}
static void ili9341_remove(struct spi_device *spi)
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt36672e.c b/drivers/gpu/drm/panel/panel-novatek-nt36672e.c
index cb7406d..c39fe0f 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt36672e.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt36672e.c
@@ -614,8 +614,6 @@
struct nt36672e_panel *ctx = mipi_dsi_get_drvdata(dsi);
mipi_dsi_detach(ctx->dsi);
- mipi_dsi_device_unregister(ctx->dsi);
-
drm_panel_remove(&ctx->panel);
}
diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c
index 7751446..b15ca56 100644
--- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c
+++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c
@@ -253,8 +253,6 @@
struct visionox_rm69299 *ctx = mipi_dsi_get_drvdata(dsi);
mipi_dsi_detach(ctx->dsi);
- mipi_dsi_device_unregister(ctx->dsi);
-
drm_panel_remove(&ctx->panel);
}
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index f38385f..b91019c 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -502,11 +502,18 @@
mapping_set_unevictable(mapping);
for (i = page_offset; i < page_offset + NUM_FAULT_PAGES; i++) {
+ /* Can happen if the last fault only partially filled this
+ * section of the pages array before failing. In that case
+ * we skip already filled pages.
+ */
+ if (pages[i])
+ continue;
+
pages[i] = shmem_read_mapping_page(mapping, i);
if (IS_ERR(pages[i])) {
ret = PTR_ERR(pages[i]);
pages[i] = NULL;
- goto err_pages;
+ goto err_unlock;
}
}
@@ -514,7 +521,7 @@
ret = sg_alloc_table_from_pages(sgt, pages + page_offset,
NUM_FAULT_PAGES, 0, SZ_2M, GFP_KERNEL);
if (ret)
- goto err_pages;
+ goto err_unlock;
ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0);
if (ret)
@@ -537,8 +544,6 @@
err_map:
sg_free_table(sgt);
-err_pages:
- drm_gem_shmem_put_pages(&bo->base);
err_unlock:
dma_resv_unlock(obj->resv);
err_bo:
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 368d26d..9febc8b 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -58,16 +58,56 @@
signed long timeout)
{
struct qxl_device *qdev;
+ struct qxl_release *release;
+ int count = 0, sc = 0;
+ bool have_drawable_releases;
unsigned long cur, end = jiffies + timeout;
qdev = container_of(fence->lock, struct qxl_device, release_lock);
+ release = container_of(fence, struct qxl_release, base);
+ have_drawable_releases = release->type == QXL_RELEASE_DRAWABLE;
- if (!wait_event_timeout(qdev->release_event,
- (dma_fence_is_signaled(fence) ||
- (qxl_io_notify_oom(qdev), 0)),
- timeout))
- return 0;
+retry:
+ sc++;
+ if (dma_fence_is_signaled(fence))
+ goto signaled;
+
+ qxl_io_notify_oom(qdev);
+
+ for (count = 0; count < 11; count++) {
+ if (!qxl_queue_garbage_collect(qdev, true))
+ break;
+
+ if (dma_fence_is_signaled(fence))
+ goto signaled;
+ }
+
+ if (dma_fence_is_signaled(fence))
+ goto signaled;
+
+ if (have_drawable_releases || sc < 4) {
+ if (sc > 2)
+ /* back off */
+ usleep_range(500, 1000);
+
+ if (time_after(jiffies, end))
+ return 0;
+
+ if (have_drawable_releases && sc > 300) {
+ DMA_FENCE_WARN(fence,
+ "failed to wait on release %llu after spincount %d\n",
+ fence->context & ~0xf0000000, sc);
+ goto signaled;
+ }
+ goto retry;
+ }
+ /*
+ * yeah, original sync_obj_wait gave up after 3 spins when
+ * have_drawable_releases is not set.
+ */
+
+signaled:
cur = jiffies;
if (time_after(cur, end))
return 0;
diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h
index 9494722..b7f2259 100644
--- a/drivers/gpu/drm/radeon/pptable.h
+++ b/drivers/gpu/drm/radeon/pptable.h
@@ -424,7 +424,7 @@
typedef struct _ATOM_PPLIB_STATE_V2
{
//number of valid dpm levels in this state; Driver uses it to calculate the whole
- //size of the state: sizeof(ATOM_PPLIB_STATE_V2) + (ucNumDPMLevels - 1) * sizeof(UCHAR)
+ //size of the state: struct_size(ATOM_PPLIB_STATE_V2, clockInfoIndex, ucNumDPMLevels)
UCHAR ucNumDPMLevels;
//a index to the array of nonClockInfos
@@ -432,14 +432,14 @@
/**
* Driver will read the first ucNumDPMLevels in this array
*/
- UCHAR clockInfoIndex[1];
+ UCHAR clockInfoIndex[] __counted_by(ucNumDPMLevels);
} ATOM_PPLIB_STATE_V2;
typedef struct _StateArray{
//how many states we have
UCHAR ucNumEntries;
- ATOM_PPLIB_STATE_V2 states[1];
+ ATOM_PPLIB_STATE_V2 states[] __counted_by(ucNumEntries);
}StateArray;
@@ -450,7 +450,7 @@
//sizeof(ATOM_PPLIB_CLOCK_INFO)
UCHAR ucEntrySize;
- UCHAR clockInfo[1];
+ UCHAR clockInfo[] __counted_by(ucNumEntries);
}ClockInfoArray;
typedef struct _NonClockInfoArray{
@@ -460,7 +460,7 @@
//sizeof(ATOM_PPLIB_NONCLOCK_INFO)
UCHAR ucEntrySize;
- ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[1];
+ ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries);
}NonClockInfoArray;
typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index bb1f0a3..10793a4 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -923,8 +923,12 @@
max_device = ATOM_MAX_SUPPORTED_DEVICE_INFO;
for (i = 0; i < max_device; i++) {
- ATOM_CONNECTOR_INFO_I2C ci =
- supported_devices->info.asConnInfo[i];
+ ATOM_CONNECTOR_INFO_I2C ci;
+
+ if (frev > 1)
+ ci = supported_devices->info_2d1.asConnInfo[i];
+ else
+ ci = supported_devices->info.asConnInfo[i];
bios_connectors[i].valid = false;
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 112438d..6e1fd69 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -288,17 +288,23 @@
enum ttm_caching caching,
unsigned int order)
{
- if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE)
+ if (pool->use_dma_alloc)
return &pool->caching[caching].orders[order];
#ifdef CONFIG_X86
switch (caching) {
case ttm_write_combined:
+ if (pool->nid != NUMA_NO_NODE)
+ return &pool->caching[caching].orders[order];
+
if (pool->use_dma32)
return &global_dma32_write_combined[order];
return &global_write_combined[order];
case ttm_uncached:
+ if (pool->nid != NUMA_NO_NODE)
+ return &pool->caching[caching].orders[order];
+
if (pool->use_dma32)
return &global_dma32_uncached[order];
@@ -566,11 +572,17 @@
pool->use_dma_alloc = use_dma_alloc;
pool->use_dma32 = use_dma32;
- if (use_dma_alloc || nid != NUMA_NO_NODE) {
- for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
- for (j = 0; j < NR_PAGE_ORDERS; ++j)
- ttm_pool_type_init(&pool->caching[i].orders[j],
- pool, i, j);
+ for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
+ for (j = 0; j < NR_PAGE_ORDERS; ++j) {
+ struct ttm_pool_type *pt;
+
+ /* Initialize only pool types which are actually used */
+ pt = ttm_pool_select_type(pool, i, j);
+ if (pt != &pool->caching[i].orders[j])
+ continue;
+
+ ttm_pool_type_init(pt, pool, i, j);
+ }
}
}
EXPORT_SYMBOL(ttm_pool_init);
@@ -599,10 +611,16 @@
{
unsigned int i, j;
- if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) {
- for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
- for (j = 0; j < NR_PAGE_ORDERS; ++j)
- ttm_pool_type_fini(&pool->caching[i].orders[j]);
+ for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
+ for (j = 0; j < NR_PAGE_ORDERS; ++j) {
+ struct ttm_pool_type *pt;
+
+ pt = ttm_pool_select_type(pool, i, j);
+ if (pt != &pool->caching[i].orders[j])
+ continue;
+
+ ttm_pool_type_fini(pt);
+ }
}
/* We removed the pool types from the LRU, but we need to also make sure
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 578a7c3..d776e3f 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -92,7 +92,7 @@
*/
if (bdev->pool.use_dma_alloc && cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) {
page_flags |= TTM_TT_FLAG_DECRYPTED;
- drm_info(ddev, "TT memory decryption enabled.");
+ drm_info_once(ddev, "TT memory decryption enabled.");
}
bo->ttm = bdev->funcs->ttm_tt_create(bo, page_flags);
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index 2e04f6c..ce6b2fb 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -105,7 +105,6 @@
struct v3d_file_priv *file = v3d->bin_job->base.file->driver_priv;
u64 runtime = local_clock() - file->start_ns[V3D_BIN];
- file->enabled_ns[V3D_BIN] += local_clock() - file->start_ns[V3D_BIN];
file->jobs_sent[V3D_BIN]++;
v3d->queue[V3D_BIN].jobs_sent++;
@@ -126,7 +125,6 @@
struct v3d_file_priv *file = v3d->render_job->base.file->driver_priv;
u64 runtime = local_clock() - file->start_ns[V3D_RENDER];
- file->enabled_ns[V3D_RENDER] += local_clock() - file->start_ns[V3D_RENDER];
file->jobs_sent[V3D_RENDER]++;
v3d->queue[V3D_RENDER].jobs_sent++;
@@ -147,7 +145,6 @@
struct v3d_file_priv *file = v3d->csd_job->base.file->driver_priv;
u64 runtime = local_clock() - file->start_ns[V3D_CSD];
- file->enabled_ns[V3D_CSD] += local_clock() - file->start_ns[V3D_CSD];
file->jobs_sent[V3D_CSD]++;
v3d->queue[V3D_CSD].jobs_sent++;
@@ -195,7 +192,6 @@
struct v3d_file_priv *file = v3d->tfu_job->base.file->driver_priv;
u64 runtime = local_clock() - file->start_ns[V3D_TFU];
- file->enabled_ns[V3D_TFU] += local_clock() - file->start_ns[V3D_TFU];
file->jobs_sent[V3D_TFU]++;
v3d->queue[V3D_TFU].jobs_sent++;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index c52c7bf..717d624 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -456,8 +456,10 @@
.no_wait_gpu = false
};
u32 j, initial_line = dst_offset / dst_stride;
- struct vmw_bo_blit_line_data d;
+ struct vmw_bo_blit_line_data d = {0};
int ret = 0;
+ struct page **dst_pages = NULL;
+ struct page **src_pages = NULL;
/* Buffer objects need to be either pinned or reserved: */
if (!(dst->pin_count))
@@ -477,12 +479,35 @@
return ret;
}
+ if (!src->ttm->pages && src->ttm->sg) {
+ src_pages = kvmalloc_array(src->ttm->num_pages,
+ sizeof(struct page *), GFP_KERNEL);
+ if (!src_pages)
+ return -ENOMEM;
+ ret = drm_prime_sg_to_page_array(src->ttm->sg, src_pages,
+ src->ttm->num_pages);
+ if (ret)
+ goto out;
+ }
+ if (!dst->ttm->pages && dst->ttm->sg) {
+ dst_pages = kvmalloc_array(dst->ttm->num_pages,
+ sizeof(struct page *), GFP_KERNEL);
+ if (!dst_pages) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = drm_prime_sg_to_page_array(dst->ttm->sg, dst_pages,
+ dst->ttm->num_pages);
+ if (ret)
+ goto out;
+ }
+
d.mapped_dst = 0;
d.mapped_src = 0;
d.dst_addr = NULL;
d.src_addr = NULL;
- d.dst_pages = dst->ttm->pages;
- d.src_pages = src->ttm->pages;
+ d.dst_pages = dst->ttm->pages ? dst->ttm->pages : dst_pages;
+ d.src_pages = src->ttm->pages ? src->ttm->pages : src_pages;
d.dst_num_pages = PFN_UP(dst->resource->size);
d.src_num_pages = PFN_UP(src->resource->size);
d.dst_prot = ttm_io_prot(dst, dst->resource, PAGE_KERNEL);
@@ -504,6 +529,10 @@
kunmap_atomic(d.src_addr);
if (d.dst_addr)
kunmap_atomic(d.dst_addr);
+ if (src_pages)
+ kvfree(src_pages);
+ if (dst_pages)
+ kvfree(dst_pages);
return ret;
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index bfd41ce..0014463 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -204,6 +204,7 @@
VMW_BO_DOMAIN_VRAM,
VMW_BO_DOMAIN_VRAM);
buf->places[0].lpfn = PFN_UP(bo->resource->size);
+ buf->busy_places[0].lpfn = PFN_UP(bo->resource->size);
ret = ttm_bo_validate(bo, &buf->placement, &ctx);
/* For some reason we didn't end up at the start of vram */
@@ -377,7 +378,8 @@
{
struct ttm_operation_ctx ctx = {
.interruptible = params->bo_type != ttm_bo_type_kernel,
- .no_wait_gpu = false
+ .no_wait_gpu = false,
+ .resv = params->resv,
};
struct ttm_device *bdev = &dev_priv->bdev;
struct drm_device *vdev = &dev_priv->drm;
@@ -394,8 +396,8 @@
vmw_bo_placement_set(vmw_bo, params->domain, params->busy_domain);
ret = ttm_bo_init_reserved(bdev, &vmw_bo->tbo, params->bo_type,
- &vmw_bo->placement, 0, &ctx, NULL,
- NULL, destroy);
+ &vmw_bo->placement, 0, &ctx,
+ params->sg, params->resv, destroy);
if (unlikely(ret))
return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
index 0d496dc..f349642e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
@@ -55,6 +55,8 @@
enum ttm_bo_type bo_type;
size_t size;
bool pin;
+ struct dma_resv *resv;
+ struct sg_table *sg;
};
/**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index c7d90f9..58fb40c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -666,11 +666,12 @@
[vmw_dma_map_populate] = "Caching DMA mappings.",
[vmw_dma_map_bind] = "Giving up DMA mappings early."};
- /* TTM currently doesn't fully support SEV encryption. */
- if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
- return -EINVAL;
-
- if (vmw_force_coherent)
+ /*
+ * When running with SEV we always want dma mappings, because
+ * otherwise ttm tt pool pages will bounce through swiotlb running
+ * out of available space.
+ */
+ if (vmw_force_coherent || cc_platform_has(CC_ATTR_MEM_ENCRYPT))
dev_priv->map_mode = vmw_dma_alloc_coherent;
else if (vmw_restrict_iommu)
dev_priv->map_mode = vmw_dma_map_bind;
@@ -1627,6 +1628,7 @@
.prime_fd_to_handle = vmw_prime_fd_to_handle,
.prime_handle_to_fd = vmw_prime_handle_to_fd,
+ .gem_prime_import_sg_table = vmw_prime_import_sg_table,
.fops = &vmwgfx_driver_fops,
.name = VMWGFX_DRIVER_NAME,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 12efecc..b019a1a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1130,6 +1130,9 @@
struct drm_file *file_priv,
uint32_t handle, uint32_t flags,
int *prime_fd);
+struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev,
+ struct dma_buf_attachment *attach,
+ struct sg_table *table);
/*
* MemoryOBject management - vmwgfx_mob.c
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 2a0cda3..5efc6a7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -991,7 +991,7 @@
}
event->event.base.type = DRM_VMW_EVENT_FENCE_SIGNALED;
- event->event.base.length = sizeof(*event);
+ event->event.base.length = sizeof(event->event);
event->event.user_data = user_data;
ret = drm_event_reserve_init(dev, file_priv, &event->base, &event->event.base);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c
index 12787bb..d6bcaf0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c
@@ -149,6 +149,38 @@
return ret;
}
+struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev,
+ struct dma_buf_attachment *attach,
+ struct sg_table *table)
+{
+ int ret;
+ struct vmw_private *dev_priv = vmw_priv(dev);
+ struct drm_gem_object *gem = NULL;
+ struct vmw_bo *vbo;
+ struct vmw_bo_params params = {
+ .domain = (dev_priv->has_mob) ? VMW_BO_DOMAIN_SYS : VMW_BO_DOMAIN_VRAM,
+ .busy_domain = VMW_BO_DOMAIN_SYS,
+ .bo_type = ttm_bo_type_sg,
+ .size = attach->dmabuf->size,
+ .pin = false,
+ .resv = attach->dmabuf->resv,
+ .sg = table,
+
+ };
+
+ dma_resv_lock(params.resv, NULL);
+
+ ret = vmw_bo_create(dev_priv, ¶ms, &vbo);
+ if (ret != 0)
+ goto out_no_bo;
+
+ vbo->tbo.base.funcs = &vmw_gem_object_funcs;
+
+ gem = &vbo->tbo.base;
+out_no_bo:
+ dma_resv_unlock(params.resv);
+ return gem;
+}
int vmw_gem_object_create_ioctl(struct drm_device *dev, void *data,
struct drm_file *filp)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index cd49253..84ae4e1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -933,6 +933,7 @@
int vmw_du_crtc_atomic_check(struct drm_crtc *crtc,
struct drm_atomic_state *state)
{
+ struct vmw_private *vmw = vmw_priv(crtc->dev);
struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state,
crtc);
struct vmw_display_unit *du = vmw_crtc_to_du(new_state->crtc);
@@ -940,9 +941,13 @@
bool has_primary = new_state->plane_mask &
drm_plane_mask(crtc->primary);
- /* We always want to have an active plane with an active CRTC */
- if (has_primary != new_state->enable)
- return -EINVAL;
+ /*
+ * This is fine in general, but broken userspace might expect
+ * some actual rendering so give a clue as why it's blank.
+ */
+ if (new_state->enable && !has_primary)
+ drm_dbg_driver(&vmw->drm,
+ "CRTC without a primary plane will be blank.\n");
if (new_state->connector_mask != connector_mask &&
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index a94947b..19a843da 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -243,10 +243,10 @@
static const uint32_t __maybe_unused vmw_primary_plane_formats[] = {
- DRM_FORMAT_XRGB1555,
- DRM_FORMAT_RGB565,
DRM_FORMAT_XRGB8888,
DRM_FORMAT_ARGB8888,
+ DRM_FORMAT_RGB565,
+ DRM_FORMAT_XRGB1555,
};
static const uint32_t __maybe_unused vmw_cursor_plane_formats[] = {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
index 2d72a5e..c99cad4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
@@ -75,8 +75,12 @@
int fd, u32 *handle)
{
struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+ int ret = ttm_prime_fd_to_handle(tfile, fd, handle);
- return ttm_prime_fd_to_handle(tfile, fd, handle);
+ if (ret)
+ ret = drm_gem_prime_fd_to_handle(dev, file_priv, fd, handle);
+
+ return ret;
}
int vmw_prime_handle_to_fd(struct drm_device *dev,
@@ -85,5 +89,12 @@
int *prime_fd)
{
struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
- return ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd);
+ int ret;
+
+ if (handle > VMWGFX_NUM_MOB)
+ ret = ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd);
+ else
+ ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd);
+
+ return ret;
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 4d23d0a..621d98b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -188,13 +188,18 @@
switch (dev_priv->map_mode) {
case vmw_dma_map_bind:
case vmw_dma_map_populate:
- vsgt->sgt = &vmw_tt->sgt;
- ret = sg_alloc_table_from_pages_segment(
- &vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0,
- (unsigned long)vsgt->num_pages << PAGE_SHIFT,
- dma_get_max_seg_size(dev_priv->drm.dev), GFP_KERNEL);
- if (ret)
- goto out_sg_alloc_fail;
+ if (vmw_tt->dma_ttm.page_flags & TTM_TT_FLAG_EXTERNAL) {
+ vsgt->sgt = vmw_tt->dma_ttm.sg;
+ } else {
+ vsgt->sgt = &vmw_tt->sgt;
+ ret = sg_alloc_table_from_pages_segment(&vmw_tt->sgt,
+ vsgt->pages, vsgt->num_pages, 0,
+ (unsigned long)vsgt->num_pages << PAGE_SHIFT,
+ dma_get_max_seg_size(dev_priv->drm.dev),
+ GFP_KERNEL);
+ if (ret)
+ goto out_sg_alloc_fail;
+ }
ret = vmw_ttm_map_for_dma(vmw_tt);
if (unlikely(ret != 0))
@@ -209,8 +214,9 @@
return 0;
out_map_fail:
- sg_free_table(vmw_tt->vsgt.sgt);
- vmw_tt->vsgt.sgt = NULL;
+ drm_warn(&dev_priv->drm, "VSG table map failed!");
+ sg_free_table(vsgt->sgt);
+ vsgt->sgt = NULL;
out_sg_alloc_fail:
return ret;
}
@@ -356,15 +362,17 @@
static int vmw_ttm_populate(struct ttm_device *bdev,
struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
{
- int ret;
+ bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0;
- /* TODO: maybe completely drop this ? */
if (ttm_tt_is_populated(ttm))
return 0;
- ret = ttm_pool_alloc(&bdev->pool, ttm, ctx);
+ if (external && ttm->sg)
+ return drm_prime_sg_to_dma_addr_array(ttm->sg,
+ ttm->dma_address,
+ ttm->num_pages);
- return ret;
+ return ttm_pool_alloc(&bdev->pool, ttm, ctx);
}
static void vmw_ttm_unpopulate(struct ttm_device *bdev,
@@ -372,6 +380,10 @@
{
struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt,
dma_ttm);
+ bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0;
+
+ if (external)
+ return;
vmw_ttm_unbind(bdev, ttm);
@@ -390,6 +402,7 @@
{
struct vmw_ttm_tt *vmw_be;
int ret;
+ bool external = bo->type == ttm_bo_type_sg;
vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL);
if (!vmw_be)
@@ -398,7 +411,10 @@
vmw_be->dev_priv = vmw_priv_from_ttm(bo->bdev);
vmw_be->mob = NULL;
- if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
+ if (external)
+ page_flags |= TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE;
+
+ if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent || external)
ret = ttm_sg_tt_init(&vmw_be->dma_ttm, bo, page_flags,
ttm_cached);
else
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
index 420eba0..854a7bb 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
@@ -84,7 +84,8 @@
#define IS_ROCKETLAKE(dev_priv) IS_PLATFORM(dev_priv, XE_ROCKETLAKE)
#define IS_DG1(dev_priv) IS_PLATFORM(dev_priv, XE_DG1)
#define IS_ALDERLAKE_S(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_S)
-#define IS_ALDERLAKE_P(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_P)
+#define IS_ALDERLAKE_P(dev_priv) (IS_PLATFORM(dev_priv, XE_ALDERLAKE_P) || \
+ IS_PLATFORM(dev_priv, XE_ALDERLAKE_N))
#define IS_XEHPSDV(dev_priv) (dev_priv && 0)
#define IS_DG2(dev_priv) IS_PLATFORM(dev_priv, XE_DG2)
#define IS_PONTEVECCHIO(dev_priv) IS_PLATFORM(dev_priv, XE_PVC)
diff --git a/drivers/gpu/drm/xe/display/intel_fb_bo.c b/drivers/gpu/drm/xe/display/intel_fb_bo.c
index b21da7b..a9c1f98 100644
--- a/drivers/gpu/drm/xe/display/intel_fb_bo.c
+++ b/drivers/gpu/drm/xe/display/intel_fb_bo.c
@@ -31,7 +31,7 @@
ret = ttm_bo_reserve(&bo->ttm, true, false, NULL);
if (ret)
- return ret;
+ goto err;
if (!(bo->flags & XE_BO_SCANOUT_BIT)) {
/*
@@ -42,12 +42,16 @@
*/
if (XE_IOCTL_DBG(i915, !list_empty(&bo->ttm.base.gpuva.list))) {
ttm_bo_unreserve(&bo->ttm);
- return -EINVAL;
+ ret = -EINVAL;
+ goto err;
}
bo->flags |= XE_BO_SCANOUT_BIT;
}
ttm_bo_unreserve(&bo->ttm);
+ return 0;
+err:
+ xe_bo_put(bo);
return ret;
}
diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index e4db069..6ec375c 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -108,11 +108,6 @@
xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0);
drmm_mutex_init(&xe->drm, &xe->sb_lock);
- drmm_mutex_init(&xe->drm, &xe->display.backlight.lock);
- drmm_mutex_init(&xe->drm, &xe->display.audio.mutex);
- drmm_mutex_init(&xe->drm, &xe->display.wm.wm_mutex);
- drmm_mutex_init(&xe->drm, &xe->display.pps.mutex);
- drmm_mutex_init(&xe->drm, &xe->display.hdcp.hdcp_mutex);
xe->enabled_irq_mask = ~0;
err = drmm_add_action_or_reset(&xe->drm, display_destroy, NULL);
diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index 0b1266c..deddc8b 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -125,7 +125,7 @@
#define RING_EXECLIST_STATUS_LO(base) XE_REG((base) + 0x234)
#define RING_EXECLIST_STATUS_HI(base) XE_REG((base) + 0x234 + 4)
-#define RING_CONTEXT_CONTROL(base) XE_REG((base) + 0x244)
+#define RING_CONTEXT_CONTROL(base) XE_REG((base) + 0x244, XE_REG_OPTION_MASKED)
#define CTX_CTRL_INHIBIT_SYN_CTX_SWITCH REG_BIT(3)
#define CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT REG_BIT(0)
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index a0afe1b..f9705430 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -378,7 +378,9 @@
err);
/* Initialize CCS mode sysfs after early initialization of HW engines */
- xe_gt_ccs_mode_sysfs_init(gt);
+ err = xe_gt_ccs_mode_sysfs_init(gt);
+ if (err)
+ goto err_force_wake;
/*
* Stash hardware-reported version. Since this register does not exist
diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
index 529fc28..396aeb5 100644
--- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
+++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
@@ -167,25 +167,20 @@
* and it is expected that there are no open drm clients while doing so.
* The number of available compute slices is exposed to user through a per-gt
* 'num_cslices' sysfs interface.
+ *
+ * Returns: Returns error value for failure and 0 for success.
*/
-void xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt)
+int xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt)
{
struct xe_device *xe = gt_to_xe(gt);
int err;
if (!xe_gt_ccs_mode_enabled(gt))
- return;
+ return 0;
err = sysfs_create_files(gt->sysfs, gt_ccs_mode_attrs);
- if (err) {
- drm_warn(&xe->drm, "Sysfs creation for ccs_mode failed err: %d\n", err);
- return;
- }
+ if (err)
+ return err;
- err = drmm_add_action_or_reset(&xe->drm, xe_gt_ccs_mode_sysfs_fini, gt);
- if (err) {
- sysfs_remove_files(gt->sysfs, gt_ccs_mode_attrs);
- drm_warn(&xe->drm, "%s: drmm_add_action_or_reset failed, err: %d\n",
- __func__, err);
- }
+ return drmm_add_action_or_reset(&xe->drm, xe_gt_ccs_mode_sysfs_fini, gt);
}
diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.h b/drivers/gpu/drm/xe/xe_gt_ccs_mode.h
index f39975a..f877985 100644
--- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.h
+++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.h
@@ -12,7 +12,7 @@
#include "xe_platform_types.h"
void xe_gt_apply_ccs_mode(struct xe_gt *gt);
-void xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt);
+int xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt);
static inline bool xe_gt_ccs_mode_enabled(const struct xe_gt *gt)
{
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 355edd4..7f32547 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1054,10 +1054,10 @@
adj_len);
break;
case XE_GUC_ACTION_GUC2PF_RELAY_FROM_VF:
- ret = xe_guc_relay_process_guc2pf(&guc->relay, payload, adj_len);
+ ret = xe_guc_relay_process_guc2pf(&guc->relay, hxg, hxg_len);
break;
case XE_GUC_ACTION_GUC2VF_RELAY_FROM_PF:
- ret = xe_guc_relay_process_guc2vf(&guc->relay, payload, adj_len);
+ ret = xe_guc_relay_process_guc2vf(&guc->relay, hxg, hxg_len);
break;
default:
drm_err(&xe->drm, "unexpected action 0x%04x\n", action);
diff --git a/drivers/gpu/drm/xe/xe_huc.c b/drivers/gpu/drm/xe/xe_huc.c
index b545f85..6b9b1cb 100644
--- a/drivers/gpu/drm/xe/xe_huc.c
+++ b/drivers/gpu/drm/xe/xe_huc.c
@@ -53,7 +53,6 @@
struct xe_gt *gt = huc_to_gt(huc);
struct xe_device *xe = gt_to_xe(gt);
struct xe_bo *bo;
- int err;
/* we use a single object for both input and output */
bo = xe_bo_create_pin_map(xe, gt_to_tile(gt), NULL,
@@ -66,13 +65,7 @@
huc->gsc_pkt = bo;
- err = drmm_add_action_or_reset(&xe->drm, free_gsc_pkt, huc);
- if (err) {
- free_gsc_pkt(&xe->drm, huc);
- return err;
- }
-
- return 0;
+ return drmm_add_action_or_reset(&xe->drm, free_gsc_pkt, huc);
}
int xe_huc_init(struct xe_huc *huc)
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index b82233a..9ac7fbe 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -290,7 +290,7 @@
* As y can be < 2, we compute tau4 = (4 | x) << y
* and then add 2 when doing the final right shift to account for units
*/
- tau4 = ((1 << x_w) | x) << y;
+ tau4 = (u64)((1 << x_w) | x) << y;
/* val in hwmon interface units (millisec) */
out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
@@ -330,7 +330,7 @@
r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT);
x = REG_FIELD_GET(PKG_MAX_WIN_X, r);
y = REG_FIELD_GET(PKG_MAX_WIN_Y, r);
- tau4 = ((1 << x_w) | x) << y;
+ tau4 = (u64)((1 << x_w) | x) << y;
max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w);
if (val > max_win)
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 1426feb..57066fa 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -525,9 +525,8 @@
static void set_context_control(u32 *regs, struct xe_hw_engine *hwe)
{
- regs[CTX_CONTEXT_CONTROL] = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH) |
- _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
- CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT;
+ regs[CTX_CONTEXT_CONTROL] = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH |
+ CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
/* TODO: Timestamp */
}
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index ee1bb93..2ba4fb9 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -227,7 +227,7 @@
if (vm->flags & XE_VM_FLAG_64K && level == 1)
flags = XE_PDE_64K;
- entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (level - 1) *
+ entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (u64)(level - 1) *
XE_PAGE_SIZE, pat_index);
xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE * level, u64,
entry | flags);
@@ -235,7 +235,7 @@
/* Write PDE's that point to our BO. */
for (i = 0; i < num_entries - num_level; i++) {
- entry = vm->pt_ops->pde_encode_bo(bo, i * XE_PAGE_SIZE,
+ entry = vm->pt_ops->pde_encode_bo(bo, (u64)i * XE_PAGE_SIZE,
pat_index);
xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE +
@@ -291,7 +291,7 @@
#define VM_SA_UPDATE_UNIT_SIZE (XE_PAGE_SIZE / NUM_VMUSA_UNIT_PER_PAGE)
#define NUM_VMUSA_WRITES_PER_UNIT (VM_SA_UPDATE_UNIT_SIZE / sizeof(u64))
drm_suballoc_manager_init(&m->vm_update_sa,
- (map_ofs / XE_PAGE_SIZE - NUM_KERNEL_PDE) *
+ (size_t)(map_ofs / XE_PAGE_SIZE - NUM_KERNEL_PDE) *
NUM_VMUSA_UNIT_PER_PAGE, 0);
m->pt_bo = bo;
@@ -490,7 +490,7 @@
struct xe_vm *vm = m->q->vm;
u16 pat_index;
u32 ptes;
- u64 ofs = at_pt * XE_PAGE_SIZE;
+ u64 ofs = (u64)at_pt * XE_PAGE_SIZE;
u64 cur_ofs;
/* Indirect access needs compression enabled uncached PAT index */
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 62d1ef8..32cd0c9 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1577,6 +1577,16 @@
xe->usm.num_vm_in_fault_mode--;
else if (!(vm->flags & XE_VM_FLAG_MIGRATION))
xe->usm.num_vm_in_non_fault_mode--;
+
+ if (vm->usm.asid) {
+ void *lookup;
+
+ xe_assert(xe, xe->info.has_asid);
+ xe_assert(xe, !(vm->flags & XE_VM_FLAG_MIGRATION));
+
+ lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid);
+ xe_assert(xe, lookup == vm);
+ }
mutex_unlock(&xe->usm.lock);
for_each_tile(tile, xe, id)
@@ -1592,24 +1602,18 @@
struct xe_device *xe = vm->xe;
struct xe_tile *tile;
u8 id;
- void *lookup;
/* xe_vm_close_and_put was not called? */
xe_assert(xe, !vm->size);
+ if (xe_vm_in_preempt_fence_mode(vm))
+ flush_work(&vm->preempt.rebind_work);
+
mutex_destroy(&vm->snap_mutex);
- if (!(vm->flags & XE_VM_FLAG_MIGRATION)) {
+ if (!(vm->flags & XE_VM_FLAG_MIGRATION))
xe_device_mem_access_put(xe);
- if (xe->info.has_asid && vm->usm.asid) {
- mutex_lock(&xe->usm.lock);
- lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid);
- xe_assert(xe, lookup == vm);
- mutex_unlock(&xe->usm.lock);
- }
- }
-
for_each_tile(tile, xe, id)
XE_WARN_ON(vm->pt_root[id]);
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 783975d..7c52757 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -351,11 +351,6 @@
return 0;
}
-static int host1x_dma_configure(struct device *dev)
-{
- return of_dma_configure(dev, dev->of_node, true);
-}
-
static const struct dev_pm_ops host1x_device_pm_ops = {
.suspend = pm_generic_suspend,
.resume = pm_generic_resume,
@@ -369,7 +364,6 @@
.name = "host1x",
.match = host1x_device_match,
.uevent = host1x_device_uevent,
- .dma_configure = host1x_dma_configure,
.pm = &host1x_device_pm_ops,
};
@@ -458,8 +452,6 @@
device->dev.bus = &host1x_bus_type;
device->dev.parent = host1x->dev;
- of_dma_configure(&device->dev, host1x->dev->of_node, true);
-
device->dev.dma_parms = &device->dma_parms;
dma_set_max_seg_size(&device->dev, UINT_MAX);
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index e6a8b6d..3c3c497 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -965,9 +965,7 @@
}
break;
case REPORT_TYPE_MOUSE:
- workitem->reports_supported |= STD_MOUSE | HIDPP;
- if (djrcv_dev->type == recvr_type_mouse_only)
- workitem->reports_supported |= MULTIMEDIA;
+ workitem->reports_supported |= STD_MOUSE | HIDPP | MULTIMEDIA;
break;
}
}
diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index f9cceae..da5ea5a 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -944,9 +944,11 @@
/* This is needed to be sure hid_hw_stop() isn't called twice by the subsystem */
static void mcp2221_remove(struct hid_device *hdev)
{
+#if IS_REACHABLE(CONFIG_IIO)
struct mcp2221 *mcp = hid_get_drvdata(hdev);
cancel_delayed_work_sync(&mcp->init_work);
+#endif
}
#if IS_REACHABLE(CONFIG_IIO)
diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index ab5953f..80e0f23 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -481,10 +481,10 @@
{ BTN_TR, JC_BTN_R, },
{ BTN_TR2, JC_BTN_LSTICK, }, /* ZR */
{ BTN_START, JC_BTN_PLUS, },
- { BTN_FORWARD, JC_BTN_Y, }, /* C UP */
- { BTN_BACK, JC_BTN_ZR, }, /* C DOWN */
- { BTN_LEFT, JC_BTN_X, }, /* C LEFT */
- { BTN_RIGHT, JC_BTN_MINUS, }, /* C RIGHT */
+ { BTN_SELECT, JC_BTN_Y, }, /* C UP */
+ { BTN_X, JC_BTN_ZR, }, /* C DOWN */
+ { BTN_Y, JC_BTN_X, }, /* C LEFT */
+ { BTN_C, JC_BTN_MINUS, }, /* C RIGHT */
{ BTN_MODE, JC_BTN_HOME, },
{ BTN_Z, JC_BTN_CAP, },
{ /* sentinel */ },
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 2df1ab3..d965382 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -64,7 +64,6 @@
/* flags */
#define I2C_HID_STARTED 0
#define I2C_HID_RESET_PENDING 1
-#define I2C_HID_READ_PENDING 2
#define I2C_HID_PWR_ON 0x00
#define I2C_HID_PWR_SLEEP 0x01
@@ -190,15 +189,10 @@
msgs[n].len = recv_len;
msgs[n].buf = recv_buf;
n++;
-
- set_bit(I2C_HID_READ_PENDING, &ihid->flags);
}
ret = i2c_transfer(client->adapter, msgs, n);
- if (recv_len)
- clear_bit(I2C_HID_READ_PENDING, &ihid->flags);
-
if (ret != n)
return ret < 0 ? ret : -EIO;
@@ -556,9 +550,6 @@
{
struct i2c_hid *ihid = dev_id;
- if (test_bit(I2C_HID_READ_PENDING, &ihid->flags))
- return IRQ_HANDLED;
-
i2c_hid_get_input(ihid);
return IRQ_HANDLED;
@@ -735,12 +726,15 @@
mutex_lock(&ihid->reset_lock);
do {
ret = i2c_hid_start_hwreset(ihid);
- if (ret)
+ if (ret == 0)
+ ret = i2c_hid_finish_hwreset(ihid);
+ else
msleep(1000);
} while (tries-- > 0 && ret);
+ mutex_unlock(&ihid->reset_lock);
if (ret)
- goto abort_reset;
+ return ret;
use_override = i2c_hid_get_dmi_hid_report_desc_override(client->name,
&rsize);
@@ -750,11 +744,8 @@
i2c_hid_dbg(ihid, "Using a HID report descriptor override\n");
} else {
rdesc = kzalloc(rsize, GFP_KERNEL);
-
- if (!rdesc) {
- ret = -ENOMEM;
- goto abort_reset;
- }
+ if (!rdesc)
+ return -ENOMEM;
i2c_hid_dbg(ihid, "asking HID report descriptor\n");
@@ -763,23 +754,10 @@
rdesc, rsize);
if (ret) {
hid_err(hid, "reading report descriptor failed\n");
- goto abort_reset;
+ goto out;
}
}
- /*
- * Windows directly reads the report-descriptor after sending reset
- * and then waits for resets completion afterwards. Some touchpads
- * actually wait for the report-descriptor to be read before signalling
- * reset completion.
- */
- ret = i2c_hid_finish_hwreset(ihid);
-abort_reset:
- clear_bit(I2C_HID_RESET_PENDING, &ihid->flags);
- mutex_unlock(&ihid->reset_lock);
- if (ret)
- goto out;
-
i2c_hid_dbg(ihid, "Report Descriptor: %*ph\n", rsize, rdesc);
ret = hid_parse_report(hid, rdesc, rsize);
diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c
index a49c6af..dd5fc60 100644
--- a/drivers/hid/intel-ish-hid/ipc/ipc.c
+++ b/drivers/hid/intel-ish-hid/ipc/ipc.c
@@ -948,6 +948,7 @@
if (!dev)
return NULL;
+ dev->devc = &pdev->dev;
ishtp_device_init(dev);
init_waitqueue_head(&dev->wait_hw_ready);
@@ -983,7 +984,6 @@
}
dev->ops = &ish_hw_ops;
- dev->devc = &pdev->dev;
dev->mtu = IPC_PAYLOAD_SIZE - sizeof(struct ishtp_msg_hdr);
return dev;
}
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index adbf674..fb8cd84 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -153,7 +153,9 @@
hv_ringbuffer_cleanup(&channel->inbound);
if (channel->ringbuffer_page) {
- __free_pages(channel->ringbuffer_page,
+ /* In a CoCo VM leak the memory if it didn't get re-encrypted */
+ if (!channel->ringbuffer_gpadlhandle.decrypted)
+ __free_pages(channel->ringbuffer_page,
get_order(channel->ringbuffer_pagecount
<< PAGE_SHIFT));
channel->ringbuffer_page = NULL;
@@ -436,9 +438,18 @@
(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);
ret = create_gpadl_header(type, kbuffer, size, send_offset, &msginfo);
- if (ret)
+ if (ret) {
+ gpadl->decrypted = false;
return ret;
+ }
+ /*
+ * Set the "decrypted" flag to true for the set_memory_decrypted()
+ * success case. In the failure case, the encryption state of the
+ * memory is unknown. Leave "decrypted" as true to ensure the
+ * memory will be leaked instead of going back on the free list.
+ */
+ gpadl->decrypted = true;
ret = set_memory_decrypted((unsigned long)kbuffer,
PFN_UP(size));
if (ret) {
@@ -527,9 +538,15 @@
kfree(msginfo);
- if (ret)
- set_memory_encrypted((unsigned long)kbuffer,
- PFN_UP(size));
+ if (ret) {
+ /*
+ * If set_memory_encrypted() fails, the decrypted flag is
+ * left as true so the memory is leaked instead of being
+ * put back on the free list.
+ */
+ if (!set_memory_encrypted((unsigned long)kbuffer, PFN_UP(size)))
+ gpadl->decrypted = false;
+ }
return ret;
}
@@ -850,6 +867,8 @@
if (ret)
pr_warn("Fail to set mem host visibility in GPADL teardown %d.\n", ret);
+ gpadl->decrypted = ret;
+
return ret;
}
EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 3cabeea..f001ae8 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -237,8 +237,17 @@
vmbus_connection.monitor_pages[0], 1);
ret |= set_memory_decrypted((unsigned long)
vmbus_connection.monitor_pages[1], 1);
- if (ret)
+ if (ret) {
+ /*
+ * If set_memory_decrypted() fails, the encryption state
+ * of the memory is unknown. So leak the memory instead
+ * of risking returning decrypted memory to the free list.
+ * For simplicity, always handle both pages the same.
+ */
+ vmbus_connection.monitor_pages[0] = NULL;
+ vmbus_connection.monitor_pages[1] = NULL;
goto cleanup;
+ }
/*
* Set_memory_decrypted() will change the memory contents if
@@ -337,13 +346,19 @@
vmbus_connection.int_page = NULL;
}
- set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[0], 1);
- set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[1], 1);
+ if (vmbus_connection.monitor_pages[0]) {
+ if (!set_memory_encrypted(
+ (unsigned long)vmbus_connection.monitor_pages[0], 1))
+ hv_free_hyperv_page(vmbus_connection.monitor_pages[0]);
+ vmbus_connection.monitor_pages[0] = NULL;
+ }
- hv_free_hyperv_page(vmbus_connection.monitor_pages[0]);
- hv_free_hyperv_page(vmbus_connection.monitor_pages[1]);
- vmbus_connection.monitor_pages[0] = NULL;
- vmbus_connection.monitor_pages[1] = NULL;
+ if (vmbus_connection.monitor_pages[1]) {
+ if (!set_memory_encrypted(
+ (unsigned long)vmbus_connection.monitor_pages[1], 1))
+ hv_free_hyperv_page(vmbus_connection.monitor_pages[1]);
+ vmbus_connection.monitor_pages[1] = NULL;
+ }
}
/*
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 4cb1760..12a707a 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -131,7 +131,7 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n", hv_dev->channel->offermsg.child_relid);
+ return sysfs_emit(buf, "%d\n", hv_dev->channel->offermsg.child_relid);
}
static DEVICE_ATTR_RO(id);
@@ -142,7 +142,7 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n", hv_dev->channel->state);
+ return sysfs_emit(buf, "%d\n", hv_dev->channel->state);
}
static DEVICE_ATTR_RO(state);
@@ -153,7 +153,7 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n", hv_dev->channel->offermsg.monitorid);
+ return sysfs_emit(buf, "%d\n", hv_dev->channel->offermsg.monitorid);
}
static DEVICE_ATTR_RO(monitor_id);
@@ -164,8 +164,8 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "{%pUl}\n",
- &hv_dev->channel->offermsg.offer.if_type);
+ return sysfs_emit(buf, "{%pUl}\n",
+ &hv_dev->channel->offermsg.offer.if_type);
}
static DEVICE_ATTR_RO(class_id);
@@ -176,8 +176,8 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "{%pUl}\n",
- &hv_dev->channel->offermsg.offer.if_instance);
+ return sysfs_emit(buf, "{%pUl}\n",
+ &hv_dev->channel->offermsg.offer.if_instance);
}
static DEVICE_ATTR_RO(device_id);
@@ -186,7 +186,7 @@
{
struct hv_device *hv_dev = device_to_hv_device(dev);
- return sprintf(buf, "vmbus:%*phN\n", UUID_SIZE, &hv_dev->dev_type);
+ return sysfs_emit(buf, "vmbus:%*phN\n", UUID_SIZE, &hv_dev->dev_type);
}
static DEVICE_ATTR_RO(modalias);
@@ -199,7 +199,7 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n", cpu_to_node(hv_dev->channel->target_cpu));
+ return sysfs_emit(buf, "%d\n", cpu_to_node(hv_dev->channel->target_cpu));
}
static DEVICE_ATTR_RO(numa_node);
#endif
@@ -212,9 +212,8 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n",
- channel_pending(hv_dev->channel,
- vmbus_connection.monitor_pages[0]));
+ return sysfs_emit(buf, "%d\n", channel_pending(hv_dev->channel,
+ vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_pending);
@@ -226,9 +225,8 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n",
- channel_pending(hv_dev->channel,
- vmbus_connection.monitor_pages[1]));
+ return sysfs_emit(buf, "%d\n", channel_pending(hv_dev->channel,
+ vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_pending);
@@ -240,9 +238,8 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n",
- channel_latency(hv_dev->channel,
- vmbus_connection.monitor_pages[0]));
+ return sysfs_emit(buf, "%d\n", channel_latency(hv_dev->channel,
+ vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_latency);
@@ -254,9 +251,8 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n",
- channel_latency(hv_dev->channel,
- vmbus_connection.monitor_pages[1]));
+ return sysfs_emit(buf, "%d\n", channel_latency(hv_dev->channel,
+ vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_latency);
@@ -268,9 +264,8 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n",
- channel_conn_id(hv_dev->channel,
- vmbus_connection.monitor_pages[0]));
+ return sysfs_emit(buf, "%d\n", channel_conn_id(hv_dev->channel,
+ vmbus_connection.monitor_pages[0]));
}
static DEVICE_ATTR_RO(server_monitor_conn_id);
@@ -282,9 +277,8 @@
if (!hv_dev->channel)
return -ENODEV;
- return sprintf(buf, "%d\n",
- channel_conn_id(hv_dev->channel,
- vmbus_connection.monitor_pages[1]));
+ return sysfs_emit(buf, "%d\n", channel_conn_id(hv_dev->channel,
+ vmbus_connection.monitor_pages[1]));
}
static DEVICE_ATTR_RO(client_monitor_conn_id);
@@ -303,7 +297,7 @@
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", outbound.current_interrupt_mask);
+ return sysfs_emit(buf, "%d\n", outbound.current_interrupt_mask);
}
static DEVICE_ATTR_RO(out_intr_mask);
@@ -321,7 +315,7 @@
&outbound);
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", outbound.current_read_index);
+ return sysfs_emit(buf, "%d\n", outbound.current_read_index);
}
static DEVICE_ATTR_RO(out_read_index);
@@ -340,7 +334,7 @@
&outbound);
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", outbound.current_write_index);
+ return sysfs_emit(buf, "%d\n", outbound.current_write_index);
}
static DEVICE_ATTR_RO(out_write_index);
@@ -359,7 +353,7 @@
&outbound);
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", outbound.bytes_avail_toread);
+ return sysfs_emit(buf, "%d\n", outbound.bytes_avail_toread);
}
static DEVICE_ATTR_RO(out_read_bytes_avail);
@@ -378,7 +372,7 @@
&outbound);
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", outbound.bytes_avail_towrite);
+ return sysfs_emit(buf, "%d\n", outbound.bytes_avail_towrite);
}
static DEVICE_ATTR_RO(out_write_bytes_avail);
@@ -396,7 +390,7 @@
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", inbound.current_interrupt_mask);
+ return sysfs_emit(buf, "%d\n", inbound.current_interrupt_mask);
}
static DEVICE_ATTR_RO(in_intr_mask);
@@ -414,7 +408,7 @@
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", inbound.current_read_index);
+ return sysfs_emit(buf, "%d\n", inbound.current_read_index);
}
static DEVICE_ATTR_RO(in_read_index);
@@ -432,7 +426,7 @@
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", inbound.current_write_index);
+ return sysfs_emit(buf, "%d\n", inbound.current_write_index);
}
static DEVICE_ATTR_RO(in_write_index);
@@ -451,7 +445,7 @@
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", inbound.bytes_avail_toread);
+ return sysfs_emit(buf, "%d\n", inbound.bytes_avail_toread);
}
static DEVICE_ATTR_RO(in_read_bytes_avail);
@@ -470,7 +464,7 @@
if (ret < 0)
return ret;
- return sprintf(buf, "%d\n", inbound.bytes_avail_towrite);
+ return sysfs_emit(buf, "%d\n", inbound.bytes_avail_towrite);
}
static DEVICE_ATTR_RO(in_write_bytes_avail);
@@ -480,7 +474,7 @@
{
struct hv_device *hv_dev = device_to_hv_device(dev);
struct vmbus_channel *channel = hv_dev->channel, *cur_sc;
- int buf_size = PAGE_SIZE, n_written, tot_written;
+ int n_written;
struct list_head *cur;
if (!channel)
@@ -488,25 +482,21 @@
mutex_lock(&vmbus_connection.channel_mutex);
- tot_written = snprintf(buf, buf_size, "%u:%u\n",
- channel->offermsg.child_relid, channel->target_cpu);
+ n_written = sysfs_emit(buf, "%u:%u\n",
+ channel->offermsg.child_relid,
+ channel->target_cpu);
list_for_each(cur, &channel->sc_list) {
- if (tot_written >= buf_size - 1)
- break;
cur_sc = list_entry(cur, struct vmbus_channel, sc_list);
- n_written = scnprintf(buf + tot_written,
- buf_size - tot_written,
- "%u:%u\n",
- cur_sc->offermsg.child_relid,
- cur_sc->target_cpu);
- tot_written += n_written;
+ n_written += sysfs_emit_at(buf, n_written, "%u:%u\n",
+ cur_sc->offermsg.child_relid,
+ cur_sc->target_cpu);
}
mutex_unlock(&vmbus_connection.channel_mutex);
- return tot_written;
+ return n_written;
}
static DEVICE_ATTR_RO(channel_vp_mapping);
@@ -516,7 +506,7 @@
{
struct hv_device *hv_dev = device_to_hv_device(dev);
- return sprintf(buf, "0x%x\n", hv_dev->vendor_id);
+ return sysfs_emit(buf, "0x%x\n", hv_dev->vendor_id);
}
static DEVICE_ATTR_RO(vendor);
@@ -526,7 +516,7 @@
{
struct hv_device *hv_dev = device_to_hv_device(dev);
- return sprintf(buf, "0x%x\n", hv_dev->device_id);
+ return sysfs_emit(buf, "0x%x\n", hv_dev->device_id);
}
static DEVICE_ATTR_RO(device);
@@ -551,7 +541,7 @@
ssize_t len;
device_lock(dev);
- len = snprintf(buf, PAGE_SIZE, "%s\n", hv_dev->driver_override);
+ len = sysfs_emit(buf, "%s\n", hv_dev->driver_override);
device_unlock(dev);
return len;
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index ff5c486..db0d1ac 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -2200,13 +2200,18 @@
* Returns negative errno, else the number of messages executed.
*
* Adapter lock must be held when calling this function. No debug logging
- * takes place. adap->algo->master_xfer existence isn't checked.
+ * takes place.
*/
int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
{
unsigned long orig_jiffies;
int ret, try;
+ if (!adap->algo->master_xfer) {
+ dev_dbg(&adap->dev, "I2C level transfers not supported\n");
+ return -EOPNOTSUPP;
+ }
+
if (WARN_ON(!msgs || num < 1))
return -EINVAL;
@@ -2273,11 +2278,6 @@
{
int ret;
- if (!adap->algo->master_xfer) {
- dev_dbg(&adap->dev, "I2C level transfers not supported\n");
- return -EOPNOTSUPP;
- }
-
/* REVISIT the fault reporting model here is weak:
*
* - When we get an error after receiving N bytes from a slave,
diff --git a/drivers/iio/accel/mxc4005.c b/drivers/iio/accel/mxc4005.c
index 61839be..63c3566 100644
--- a/drivers/iio/accel/mxc4005.c
+++ b/drivers/iio/accel/mxc4005.c
@@ -5,6 +5,7 @@
* Copyright (c) 2014, Intel Corporation.
*/
+#include <linux/delay.h>
#include <linux/module.h>
#include <linux/i2c.h>
#include <linux/iio/iio.h>
@@ -27,11 +28,16 @@
#define MXC4005_REG_ZOUT_UPPER 0x07
#define MXC4005_REG_ZOUT_LOWER 0x08
+#define MXC4005_REG_INT_MASK0 0x0A
+
#define MXC4005_REG_INT_MASK1 0x0B
#define MXC4005_REG_INT_MASK1_BIT_DRDYE 0x01
+#define MXC4005_REG_INT_CLR0 0x00
+
#define MXC4005_REG_INT_CLR1 0x01
#define MXC4005_REG_INT_CLR1_BIT_DRDYC 0x01
+#define MXC4005_REG_INT_CLR1_SW_RST 0x10
#define MXC4005_REG_CONTROL 0x0D
#define MXC4005_REG_CONTROL_MASK_FSR GENMASK(6, 5)
@@ -39,6 +45,9 @@
#define MXC4005_REG_DEVICE_ID 0x0E
+/* Datasheet does not specify a reset time, this is a conservative guess */
+#define MXC4005_RESET_TIME_US 2000
+
enum mxc4005_axis {
AXIS_X,
AXIS_Y,
@@ -62,6 +71,8 @@
s64 timestamp __aligned(8);
} scan;
bool trigger_enabled;
+ unsigned int control;
+ unsigned int int_mask1;
};
/*
@@ -113,7 +124,9 @@
static bool mxc4005_is_writeable_reg(struct device *dev, unsigned int reg)
{
switch (reg) {
+ case MXC4005_REG_INT_CLR0:
case MXC4005_REG_INT_CLR1:
+ case MXC4005_REG_INT_MASK0:
case MXC4005_REG_INT_MASK1:
case MXC4005_REG_CONTROL:
return true;
@@ -330,23 +343,20 @@
{
struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
struct mxc4005_data *data = iio_priv(indio_dev);
+ unsigned int val;
int ret;
mutex_lock(&data->mutex);
- if (state) {
- ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1,
- MXC4005_REG_INT_MASK1_BIT_DRDYE);
- } else {
- ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1,
- ~MXC4005_REG_INT_MASK1_BIT_DRDYE);
- }
+ val = state ? MXC4005_REG_INT_MASK1_BIT_DRDYE : 0;
+ ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, val);
if (ret < 0) {
mutex_unlock(&data->mutex);
dev_err(data->dev, "failed to update reg_int_mask1");
return ret;
}
+ data->int_mask1 = val;
data->trigger_enabled = state;
mutex_unlock(&data->mutex);
@@ -382,6 +392,21 @@
dev_dbg(data->dev, "MXC4005 chip id %02x\n", reg);
+ ret = regmap_write(data->regmap, MXC4005_REG_INT_CLR1,
+ MXC4005_REG_INT_CLR1_SW_RST);
+ if (ret < 0)
+ return dev_err_probe(data->dev, ret, "resetting chip\n");
+
+ fsleep(MXC4005_RESET_TIME_US);
+
+ ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK0, 0);
+ if (ret < 0)
+ return dev_err_probe(data->dev, ret, "writing INT_MASK0\n");
+
+ ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, 0);
+ if (ret < 0)
+ return dev_err_probe(data->dev, ret, "writing INT_MASK1\n");
+
return 0;
}
@@ -469,6 +494,58 @@
return devm_iio_device_register(&client->dev, indio_dev);
}
+static int mxc4005_suspend(struct device *dev)
+{
+ struct iio_dev *indio_dev = dev_get_drvdata(dev);
+ struct mxc4005_data *data = iio_priv(indio_dev);
+ int ret;
+
+ /* Save control to restore it on resume */
+ ret = regmap_read(data->regmap, MXC4005_REG_CONTROL, &data->control);
+ if (ret < 0)
+ dev_err(data->dev, "failed to read reg_control\n");
+
+ return ret;
+}
+
+static int mxc4005_resume(struct device *dev)
+{
+ struct iio_dev *indio_dev = dev_get_drvdata(dev);
+ struct mxc4005_data *data = iio_priv(indio_dev);
+ int ret;
+
+ ret = regmap_write(data->regmap, MXC4005_REG_INT_CLR1,
+ MXC4005_REG_INT_CLR1_SW_RST);
+ if (ret) {
+ dev_err(data->dev, "failed to reset chip: %d\n", ret);
+ return ret;
+ }
+
+ fsleep(MXC4005_RESET_TIME_US);
+
+ ret = regmap_write(data->regmap, MXC4005_REG_CONTROL, data->control);
+ if (ret) {
+ dev_err(data->dev, "failed to restore control register\n");
+ return ret;
+ }
+
+ ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK0, 0);
+ if (ret) {
+ dev_err(data->dev, "failed to restore interrupt 0 mask\n");
+ return ret;
+ }
+
+ ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, data->int_mask1);
+ if (ret) {
+ dev_err(data->dev, "failed to restore interrupt 1 mask\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(mxc4005_pm_ops, mxc4005_suspend, mxc4005_resume);
+
static const struct acpi_device_id mxc4005_acpi_match[] = {
{"MXC4005", 0},
{"MXC6655", 0},
@@ -496,6 +573,7 @@
.name = MXC4005_DRV_NAME,
.acpi_match_table = mxc4005_acpi_match,
.of_match_table = mxc4005_of_match,
+ .pm = pm_sleep_ptr(&mxc4005_pm_ops),
},
.probe = mxc4005_probe,
.id_table = mxc4005_id,
diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c
index 01f55cc..060a21c 100644
--- a/drivers/iio/imu/adis16475.c
+++ b/drivers/iio/imu/adis16475.c
@@ -1289,6 +1289,7 @@
struct device *dev = &st->adis.spi->dev;
const struct adis16475_sync *sync;
u32 sync_mode;
+ u16 val;
/* default to internal clk */
st->clk_freq = st->info->int_clk * 1000;
@@ -1350,8 +1351,9 @@
* I'm keeping this for simplicity and avoiding extra variables
* in chip_info.
*/
+ val = ADIS16475_SYNC_MODE(sync->sync_mode);
ret = __adis_update_bits(&st->adis, ADIS16475_REG_MSG_CTRL,
- ADIS16475_SYNC_MODE_MASK, sync->sync_mode);
+ ADIS16475_SYNC_MODE_MASK, val);
if (ret)
return ret;
diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index fe87344..62e9e93 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -1233,6 +1233,7 @@
.chip_id = bmp380_chip_ids,
.num_chip_id = ARRAY_SIZE(bmp380_chip_ids),
.regmap_config = &bmp380_regmap_config,
+ .spi_read_extra_byte = true,
.start_up_time = 2000,
.channels = bmp380_channels,
.num_channels = 2,
diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c
index a444d4b..4e19ea0 100644
--- a/drivers/iio/pressure/bmp280-spi.c
+++ b/drivers/iio/pressure/bmp280-spi.c
@@ -96,15 +96,10 @@
chip_info = spi_get_device_match_data(spi);
- switch (chip_info->chip_id[0]) {
- case BMP380_CHIP_ID:
- case BMP390_CHIP_ID:
+ if (chip_info->spi_read_extra_byte)
bmp_regmap_bus = &bmp380_regmap_bus;
- break;
- default:
+ else
bmp_regmap_bus = &bmp280_regmap_bus;
- break;
- }
regmap = devm_regmap_init(&spi->dev,
bmp_regmap_bus,
@@ -127,7 +122,7 @@
{ .compatible = "bosch,bmp180", .data = &bmp180_chip_info },
{ .compatible = "bosch,bmp181", .data = &bmp180_chip_info },
{ .compatible = "bosch,bmp280", .data = &bmp280_chip_info },
- { .compatible = "bosch,bme280", .data = &bmp280_chip_info },
+ { .compatible = "bosch,bme280", .data = &bme280_chip_info },
{ .compatible = "bosch,bmp380", .data = &bmp380_chip_info },
{ .compatible = "bosch,bmp580", .data = &bmp580_chip_info },
{ },
@@ -139,7 +134,7 @@
{ "bmp180", (kernel_ulong_t)&bmp180_chip_info },
{ "bmp181", (kernel_ulong_t)&bmp180_chip_info },
{ "bmp280", (kernel_ulong_t)&bmp280_chip_info },
- { "bme280", (kernel_ulong_t)&bmp280_chip_info },
+ { "bme280", (kernel_ulong_t)&bme280_chip_info },
{ "bmp380", (kernel_ulong_t)&bmp380_chip_info },
{ "bmp580", (kernel_ulong_t)&bmp580_chip_info },
{ }
diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h
index 4012387..5812a34 100644
--- a/drivers/iio/pressure/bmp280.h
+++ b/drivers/iio/pressure/bmp280.h
@@ -423,6 +423,7 @@
int num_chip_id;
const struct regmap_config *regmap_config;
+ bool spi_read_extra_byte;
const struct iio_chan_spec *channels;
int num_channels;
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index bf0df6ee..07fb8d3 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -1026,23 +1026,26 @@
}
}
-static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id)
+static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id,
+ enum ib_cm_state old_state)
{
struct cm_id_private *cm_id_priv;
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
- pr_err("%s: cm_id=%p timed out. state=%d refcnt=%d\n", __func__,
- cm_id, cm_id->state, refcount_read(&cm_id_priv->refcount));
+ pr_err("%s: cm_id=%p timed out. state %d -> %d, refcnt=%d\n", __func__,
+ cm_id, old_state, cm_id->state, refcount_read(&cm_id_priv->refcount));
}
static void cm_destroy_id(struct ib_cm_id *cm_id, int err)
{
struct cm_id_private *cm_id_priv;
+ enum ib_cm_state old_state;
struct cm_work *work;
int ret;
cm_id_priv = container_of(cm_id, struct cm_id_private, id);
spin_lock_irq(&cm_id_priv->lock);
+ old_state = cm_id->state;
retest:
switch (cm_id->state) {
case IB_CM_LISTEN:
@@ -1151,7 +1154,7 @@
msecs_to_jiffies(
CM_DESTROY_ID_WAIT_TIMEOUT));
if (!ret) /* timeout happened */
- cm_destroy_id_wait_timeout(cm_id);
+ cm_destroy_id_wait_timeout(cm_id, old_state);
} while (!ret);
while ((work = cm_dequeue_work(cm_id_priv)) != NULL)
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 0c3c4e6..3e43687 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -188,7 +188,8 @@
mdev = dev->mdev;
mdev_port_num = 1;
}
- if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) {
+ if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1 &&
+ !mlx5_core_mp_enabled(mdev)) {
/* set local port to one for Function-Per-Port HCA. */
mdev = dev->mdev;
mdev_port_num = 1;
diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index ae466e7..255677b 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -33,6 +33,8 @@
if (rxe->tfm)
crypto_free_shash(rxe->tfm);
+
+ mutex_destroy(&rxe->usdev_lock);
}
/* initialize rxe device parameters */
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index f50848e..6fadadd 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -208,6 +208,7 @@
{ 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 },
{ 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 },
{ 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 },
+ { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE },
{ 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX },
{ 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX },
{ 0x0c12, 0x8802, "Zeroplus Xbox Controller", 0, XTYPE_XBOX },
@@ -487,6 +488,7 @@
{ USB_DEVICE(0x0738, 0x4540) }, /* Mad Catz Beat Pad */
XPAD_XBOXONE_VENDOR(0x0738), /* Mad Catz FightStick TE 2 */
XPAD_XBOX360_VENDOR(0x07ff), /* Mad Catz Gamepad */
+ XPAD_XBOXONE_VENDOR(0x0b05), /* ASUS controllers */
XPAD_XBOX360_VENDOR(0x0c12), /* Zeroplus X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x0e6f), /* 0x0e6f Xbox 360 controllers */
XPAD_XBOXONE_VENDOR(0x0e6f), /* 0x0e6f Xbox One controllers */
diff --git a/drivers/input/mouse/amimouse.c b/drivers/input/mouse/amimouse.c
index cda0c3f..2fbbaeb 100644
--- a/drivers/input/mouse/amimouse.c
+++ b/drivers/input/mouse/amimouse.c
@@ -132,7 +132,13 @@
input_unregister_device(dev);
}
-static struct platform_driver amimouse_driver = {
+/*
+ * amimouse_remove() lives in .exit.text. For drivers registered via
+ * module_platform_driver_probe() this is ok because they cannot get unbound at
+ * runtime. So mark the driver struct with __refdata to prevent modpost
+ * triggering a section mismatch warning.
+ */
+static struct platform_driver amimouse_driver __refdata = {
.remove_new = __exit_p(amimouse_remove),
.driver = {
.name = "amiga-mouse",
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index 5d1010c..7e9b996 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -176,6 +176,8 @@
path->num_nodes = num_nodes;
+ mutex_lock(&icc_bw_lock);
+
for (i = num_nodes - 1; i >= 0; i--) {
node->provider->users++;
hlist_add_head(&path->reqs[i].req_node, &node->req_list);
@@ -186,6 +188,8 @@
node = node->reverse;
}
+ mutex_unlock(&icc_bw_lock);
+
return path;
}
@@ -792,12 +796,16 @@
pr_err("%s: error (%d)\n", __func__, ret);
mutex_lock(&icc_lock);
+ mutex_lock(&icc_bw_lock);
+
for (i = 0; i < path->num_nodes; i++) {
node = path->reqs[i].node;
hlist_del(&path->reqs[i].req_node);
if (!WARN_ON(!node->provider->users))
node->provider->users--;
}
+
+ mutex_unlock(&icc_bw_lock);
mutex_unlock(&icc_lock);
kfree_const(path->name);
diff --git a/drivers/interconnect/qcom/x1e80100.c b/drivers/interconnect/qcom/x1e80100.c
index 9982467..654abb9 100644
--- a/drivers/interconnect/qcom/x1e80100.c
+++ b/drivers/interconnect/qcom/x1e80100.c
@@ -116,15 +116,6 @@
.links = { X1E80100_SLAVE_A2NOC_SNOC },
};
-static struct qcom_icc_node ddr_perf_mode_master = {
- .name = "ddr_perf_mode_master",
- .id = X1E80100_MASTER_DDR_PERF_MODE,
- .channels = 1,
- .buswidth = 4,
- .num_links = 1,
- .links = { X1E80100_SLAVE_DDR_PERF_MODE },
-};
-
static struct qcom_icc_node qup0_core_master = {
.name = "qup0_core_master",
.id = X1E80100_MASTER_QUP_CORE_0,
@@ -688,14 +679,6 @@
.links = { X1E80100_MASTER_A2NOC_SNOC },
};
-static struct qcom_icc_node ddr_perf_mode_slave = {
- .name = "ddr_perf_mode_slave",
- .id = X1E80100_SLAVE_DDR_PERF_MODE,
- .channels = 1,
- .buswidth = 4,
- .num_links = 0,
-};
-
static struct qcom_icc_node qup0_core_slave = {
.name = "qup0_core_slave",
.id = X1E80100_SLAVE_QUP_CORE_0,
@@ -1377,12 +1360,6 @@
.nodes = { &ebi },
};
-static struct qcom_icc_bcm bcm_acv_perf = {
- .name = "ACV_PERF",
- .num_nodes = 1,
- .nodes = { &ddr_perf_mode_slave },
-};
-
static struct qcom_icc_bcm bcm_ce0 = {
.name = "CE0",
.num_nodes = 1,
@@ -1583,18 +1560,15 @@
};
static struct qcom_icc_bcm * const clk_virt_bcms[] = {
- &bcm_acv_perf,
&bcm_qup0,
&bcm_qup1,
&bcm_qup2,
};
static struct qcom_icc_node * const clk_virt_nodes[] = {
- [MASTER_DDR_PERF_MODE] = &ddr_perf_mode_master,
[MASTER_QUP_CORE_0] = &qup0_core_master,
[MASTER_QUP_CORE_1] = &qup1_core_master,
[MASTER_QUP_CORE_2] = &qup2_core_master,
- [SLAVE_DDR_PERF_MODE] = &ddr_perf_mode_slave,
[SLAVE_QUP_CORE_0] = &qup0_core_slave,
[SLAVE_QUP_CORE_1] = &qup1_core_slave,
[SLAVE_QUP_CORE_2] = &qup2_core_slave,
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 33228c1..ac6754a 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -3232,28 +3232,29 @@
return;
/*
* The SNP support requires that IOMMU must be enabled, and is
- * not configured in the passthrough mode.
+ * configured with V1 page table (DTE[Mode] = 0 is not supported).
*/
if (no_iommu || iommu_default_passthrough()) {
- pr_err("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n");
- cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
- return;
+ pr_warn("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n");
+ goto disable_snp;
+ }
+
+ if (amd_iommu_pgtable != AMD_IOMMU_V1) {
+ pr_warn("SNP: IOMMU is configured with V2 page table mode, SNP cannot be supported.\n");
+ goto disable_snp;
}
amd_iommu_snp_en = check_feature(FEATURE_SNP);
if (!amd_iommu_snp_en) {
- pr_err("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n");
- cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
- return;
+ pr_warn("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n");
+ goto disable_snp;
}
pr_info("IOMMU SNP support enabled.\n");
+ return;
- /* Enforce IOMMU v1 pagetable when SNP is enabled. */
- if (amd_iommu_pgtable != AMD_IOMMU_V1) {
- pr_warn("Forcing use of AMD IOMMU v1 page table due to SNP.\n");
- amd_iommu_pgtable = AMD_IOMMU_V1;
- }
+disable_snp:
+ cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
#endif
}
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index d35c1b8..e692217 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1692,26 +1692,29 @@
static u16 domain_id_alloc(void)
{
+ unsigned long flags;
int id;
- spin_lock(&pd_bitmap_lock);
+ spin_lock_irqsave(&pd_bitmap_lock, flags);
id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID);
BUG_ON(id == 0);
if (id > 0 && id < MAX_DOMAIN_ID)
__set_bit(id, amd_iommu_pd_alloc_bitmap);
else
id = 0;
- spin_unlock(&pd_bitmap_lock);
+ spin_unlock_irqrestore(&pd_bitmap_lock, flags);
return id;
}
static void domain_id_free(int id)
{
- spin_lock(&pd_bitmap_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&pd_bitmap_lock, flags);
if (id > 0 && id < MAX_DOMAIN_ID)
__clear_bit(id, amd_iommu_pd_alloc_bitmap);
- spin_unlock(&pd_bitmap_lock);
+ spin_unlock_irqrestore(&pd_bitmap_lock, flags);
}
static void free_gcr3_tbl_level1(u64 *tbl)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 50eb9ae..a7ecd903 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4299,9 +4299,11 @@
}
dev_iommu_priv_set(dev, info);
- ret = device_rbtree_insert(iommu, info);
- if (ret)
- goto free;
+ if (pdev && pci_ats_supported(pdev)) {
+ ret = device_rbtree_insert(iommu, info);
+ if (ret)
+ goto free;
+ }
if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
ret = intel_pasid_alloc_table(dev);
@@ -4336,7 +4338,8 @@
struct intel_iommu *iommu = info->iommu;
mutex_lock(&iommu->iopf_lock);
- device_rbtree_remove(info);
+ if (dev_is_pci(dev) && pci_ats_supported(to_pci_dev(dev)))
+ device_rbtree_remove(info);
mutex_unlock(&iommu->iopf_lock);
if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev) &&
diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c
index cf43e79..44083d0 100644
--- a/drivers/iommu/intel/perfmon.c
+++ b/drivers/iommu/intel/perfmon.c
@@ -438,7 +438,7 @@
iommu_pmu_set_filter(domain, event->attr.config1,
IOMMU_PMU_FILTER_DOMAIN, idx,
event->attr.config1);
- iommu_pmu_set_filter(pasid, event->attr.config1,
+ iommu_pmu_set_filter(pasid, event->attr.config2,
IOMMU_PMU_FILTER_PASID, idx,
event->attr.config1);
iommu_pmu_set_filter(ats, event->attr.config2,
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index c1bed89..ee3b469 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -66,7 +66,7 @@
struct page *pages;
int irq, ret;
- pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, PRQ_ORDER);
+ pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO, PRQ_ORDER);
if (!pages) {
pr_warn("IOMMU: %s: Failed to allocate page request queue\n",
iommu->name);
diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig
index 99d4b07..76656fe 100644
--- a/drivers/iommu/iommufd/Kconfig
+++ b/drivers/iommu/iommufd/Kconfig
@@ -37,6 +37,7 @@
depends on DEBUG_KERNEL
depends on FAULT_INJECTION
depends on RUNTIME_TESTING_MENU
+ select IOMMUFD_DRIVER
default n
help
This is dangerous, do not enable unless running
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index b8c47f1..6a2707f 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -1790,6 +1790,7 @@
{ .compatible = "mediatek,mt8365-m4u", .data = &mt8365_data},
{}
};
+MODULE_DEVICE_TABLE(of, mtk_iommu_of_ids);
static struct platform_driver mtk_iommu_driver = {
.probe = mtk_iommu_probe,
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index a9fa2a5..d6e4002 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -600,6 +600,7 @@
{ .compatible = "mediatek,mt2701-m4u", },
{}
};
+MODULE_DEVICE_TABLE(of, mtk_iommu_v1_of_ids);
static const struct component_master_ops mtk_iommu_v1_com_ops = {
.bind = mtk_iommu_v1_bind,
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index fca888b..5f7d3db 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -786,6 +786,7 @@
struct its_cmd_block *cmd,
struct its_cmd_desc *desc)
{
+ struct its_vpe *vpe = valid_vpe(its, desc->its_vmapp_cmd.vpe);
unsigned long vpt_addr, vconf_addr;
u64 target;
bool alloc;
@@ -798,6 +799,11 @@
if (is_v4_1(its)) {
alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count);
its_encode_alloc(cmd, alloc);
+ /*
+ * Unmapping a VPE is self-synchronizing on GICv4.1,
+ * no need to issue a VSYNC.
+ */
+ vpe = NULL;
}
goto out;
@@ -832,7 +838,7 @@
out:
its_fixup_cmd(cmd);
- return valid_vpe(its, desc->its_vmapp_cmd.vpe);
+ return vpe;
}
static struct its_vpe *its_build_vmapti_cmd(struct its_node *its,
@@ -4561,13 +4567,8 @@
irqd_set_resend_when_in_progress(irq_get_irq_data(virq + i));
}
- if (err) {
- if (i > 0)
- its_vpe_irq_domain_free(domain, virq, i);
-
- its_lpi_free(bitmap, base, nr_ids);
- its_free_prop_table(vprop_page);
- }
+ if (err)
+ its_vpe_irq_domain_free(domain, virq, i);
return err;
}
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 2776ca5..b215b28 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -401,23 +401,23 @@
}
static int data_sock_setsockopt(struct socket *sock, int level, int optname,
- sockptr_t optval, unsigned int len)
+ sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
int err = 0, opt = 0;
if (*debug & DEBUG_SOCKET)
printk(KERN_DEBUG "%s(%p, %d, %x, optval, %d)\n", __func__, sock,
- level, optname, len);
+ level, optname, optlen);
lock_sock(sk);
switch (optname) {
case MISDN_TIME_STAMP:
- if (copy_from_sockptr(&opt, optval, sizeof(int))) {
- err = -EFAULT;
+ err = copy_safe_from_sockptr(&opt, sizeof(opt),
+ optval, optlen);
+ if (err)
break;
- }
if (opt)
_pms(sk)->cmask |= MISDN_TIME_STAMP;
diff --git a/drivers/md/dm-vdo/murmurhash3.c b/drivers/md/dm-vdo/murmurhash3.c
index 01d2743..3a989ef 100644
--- a/drivers/md/dm-vdo/murmurhash3.c
+++ b/drivers/md/dm-vdo/murmurhash3.c
@@ -137,7 +137,7 @@
break;
default:
break;
- };
+ }
}
/* finalization */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 56aa2a8..7d0746b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -765,7 +765,7 @@
return td;
out_blkdev_put:
- fput(bdev_file);
+ __fput_sync(bdev_file);
out_free_td:
kfree(td);
return ERR_PTR(r);
@@ -778,7 +778,13 @@
{
if (md->disk->slave_dir)
bd_unlink_disk_holder(td->dm_dev.bdev, md->disk);
- fput(td->dm_dev.bdev_file);
+
+ /* Leverage async fput() if DMF_DEFERRED_REMOVE set */
+ if (unlikely(test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
+ fput(td->dm_dev.bdev_file);
+ else
+ __fput_sync(td->dm_dev.bdev_file);
+
put_dax(td->dm_dev.dax_dev);
list_del(&td->list);
kfree(td);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index be8ac24..7b8a71c 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1558,7 +1558,7 @@
for (j = 0; j < i; j++)
if (r1_bio->bios[j])
rdev_dec_pending(conf->mirrors[j].rdev, mddev);
- free_r1bio(r1_bio);
+ mempool_free(r1_bio, &conf->r1bio_pool);
allow_barrier(conf, bio->bi_iter.bi_sector);
if (bio->bi_opf & REQ_NOWAIT) {
diff --git a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c
index 4c34344..d7027d6 100644
--- a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c
+++ b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c
@@ -50,12 +50,12 @@
dev_err(&dev->plat_dev->dev, "Watchdog timeout!!");
- mutex_lock(&dev->dev_mutex);
+ mutex_lock(&dev->dev_ctx_lock);
list_for_each_entry(ctx, &dev->ctx_list, list) {
ctx->state = MTK_STATE_ABORT;
mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id);
}
- mutex_unlock(&dev->dev_mutex);
+ mutex_unlock(&dev->dev_ctx_lock);
}
static void mtk_vcodec_vpu_reset_enc_handler(void *priv)
@@ -65,12 +65,12 @@
dev_err(&dev->plat_dev->dev, "Watchdog timeout!!");
- mutex_lock(&dev->dev_mutex);
+ mutex_lock(&dev->dev_ctx_lock);
list_for_each_entry(ctx, &dev->ctx_list, list) {
ctx->state = MTK_STATE_ABORT;
mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id);
}
- mutex_unlock(&dev->dev_mutex);
+ mutex_unlock(&dev->dev_ctx_lock);
}
static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = {
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c
index f47c98f..2073781 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c
@@ -268,7 +268,9 @@
ctx->dev->vdec_pdata->init_vdec_params(ctx);
+ mutex_lock(&dev->dev_ctx_lock);
list_add(&ctx->list, &dev->ctx_list);
+ mutex_unlock(&dev->dev_ctx_lock);
mtk_vcodec_dbgfs_create(ctx);
mutex_unlock(&dev->dev_mutex);
@@ -311,7 +313,9 @@
v4l2_ctrl_handler_free(&ctx->ctrl_hdl);
mtk_vcodec_dbgfs_remove(dev, ctx->id);
+ mutex_lock(&dev->dev_ctx_lock);
list_del_init(&ctx->list);
+ mutex_unlock(&dev->dev_ctx_lock);
kfree(ctx);
mutex_unlock(&dev->dev_mutex);
return 0;
@@ -404,6 +408,7 @@
for (i = 0; i < MTK_VDEC_HW_MAX; i++)
mutex_init(&dev->dec_mutex[i]);
mutex_init(&dev->dev_mutex);
+ mutex_init(&dev->dev_ctx_lock);
spin_lock_init(&dev->irqlock);
snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s",
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h
index 849b89d..85b2c0d 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h
+++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h
@@ -241,6 +241,7 @@
*
* @dec_mutex: decoder hardware lock
* @dev_mutex: video_device lock
+ * @dev_ctx_lock: the lock of context list
* @decode_workqueue: decode work queue
*
* @irqlock: protect data access by irq handler and work thread
@@ -282,6 +283,7 @@
/* decoder hardware mutex lock */
struct mutex dec_mutex[MTK_VDEC_HW_MAX];
struct mutex dev_mutex;
+ struct mutex dev_ctx_lock;
struct workqueue_struct *decode_workqueue;
spinlock_t irqlock;
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
index 06ed47d..21836dd 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
@@ -869,7 +869,6 @@
inst->vpu.codec_type = ctx->current_codec;
inst->vpu.capture_type = ctx->capture_fourcc;
- ctx->drv_handle = inst;
err = vpu_dec_init(&inst->vpu);
if (err) {
mtk_vdec_err(ctx, "vdec_hevc init err=%d", err);
@@ -898,6 +897,7 @@
mtk_vdec_debug(ctx, "lat hevc instance >> %p, codec_type = 0x%x",
inst, inst->vpu.codec_type);
+ ctx->drv_handle = inst;
return 0;
error_free_inst:
kfree(inst);
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
index 19407f9..987b3d7 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
@@ -449,7 +449,7 @@
inst->frm_cnt, y_fb_dma, c_fb_dma, fb);
inst->cur_fb = fb;
- dec->bs_dma = (unsigned long)bs->dma_addr;
+ dec->bs_dma = (uint64_t)bs->dma_addr;
dec->bs_sz = bs->size;
dec->cur_y_fb_dma = y_fb_dma;
dec->cur_c_fb_dma = c_fb_dma;
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c
index 55355fa..039082f 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c
@@ -16,6 +16,7 @@
#include "../vdec_drv_base.h"
#include "../vdec_vpu_if.h"
+#define VP9_MAX_SUPER_FRAMES_NUM 8
#define VP9_SUPER_FRAME_BS_SZ 64
#define MAX_VP9_DPB_SIZE 9
@@ -133,11 +134,11 @@
*/
struct vdec_vp9_vsi {
unsigned char sf_bs_buf[VP9_SUPER_FRAME_BS_SZ];
- struct vp9_sf_ref_fb sf_ref_fb[VP9_MAX_FRM_BUF_NUM-1];
+ struct vp9_sf_ref_fb sf_ref_fb[VP9_MAX_SUPER_FRAMES_NUM];
int sf_next_ref_fb_idx;
unsigned int sf_frm_cnt;
- unsigned int sf_frm_offset[VP9_MAX_FRM_BUF_NUM-1];
- unsigned int sf_frm_sz[VP9_MAX_FRM_BUF_NUM-1];
+ unsigned int sf_frm_offset[VP9_MAX_SUPER_FRAMES_NUM];
+ unsigned int sf_frm_sz[VP9_MAX_SUPER_FRAMES_NUM];
unsigned int sf_frm_idx;
unsigned int sf_init;
struct vdec_fb fb;
@@ -526,7 +527,7 @@
/* if this super frame and it is not last sub-frame, get next fb for
* sub-frame decode
*/
- if (vsi->sf_frm_cnt > 0 && vsi->sf_frm_idx != vsi->sf_frm_cnt - 1)
+ if (vsi->sf_frm_cnt > 0 && vsi->sf_frm_idx != vsi->sf_frm_cnt)
vsi->sf_next_ref_fb_idx = vp9_get_sf_ref_fb(inst);
}
@@ -735,7 +736,7 @@
static int validate_vsi_array_indexes(struct vdec_vp9_inst *inst,
struct vdec_vp9_vsi *vsi) {
- if (vsi->sf_frm_idx >= VP9_MAX_FRM_BUF_NUM - 1) {
+ if (vsi->sf_frm_idx > VP9_MAX_SUPER_FRAMES_NUM) {
mtk_vdec_err(inst->ctx, "Invalid vsi->sf_frm_idx=%u.", vsi->sf_frm_idx);
return -EIO;
}
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
index cf48d09..eea709d 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
@@ -1074,7 +1074,7 @@
unsigned int mi_row;
unsigned int mi_col;
unsigned int offset;
- unsigned int pa;
+ dma_addr_t pa;
unsigned int size;
struct vdec_vp9_slice_tiles *tiles;
unsigned char *pos;
@@ -1109,7 +1109,7 @@
pos = va + offset;
end = va + bs->size;
/* truncated */
- pa = (unsigned int)bs->dma_addr + offset;
+ pa = bs->dma_addr + offset;
tb = instance->tile.va;
for (i = 0; i < rows; i++) {
for (j = 0; j < cols; j++) {
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
index 82e57ae..da6be55 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
@@ -77,12 +77,14 @@
struct mtk_vcodec_dec_ctx *ctx;
int ret = false;
+ mutex_lock(&dec_dev->dev_ctx_lock);
list_for_each_entry(ctx, &dec_dev->ctx_list, list) {
if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) {
ret = true;
break;
}
}
+ mutex_unlock(&dec_dev->dev_ctx_lock);
return ret;
}
diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c
index 6319f24..3cb8a16 100644
--- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c
+++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c
@@ -177,7 +177,9 @@
mtk_v4l2_venc_dbg(2, ctx, "Create instance [%d]@%p m2m_ctx=%p ",
ctx->id, ctx, ctx->m2m_ctx);
+ mutex_lock(&dev->dev_ctx_lock);
list_add(&ctx->list, &dev->ctx_list);
+ mutex_unlock(&dev->dev_ctx_lock);
mutex_unlock(&dev->dev_mutex);
mtk_v4l2_venc_dbg(0, ctx, "%s encoder [%d]", dev_name(&dev->plat_dev->dev),
@@ -212,7 +214,9 @@
v4l2_fh_exit(&ctx->fh);
v4l2_ctrl_handler_free(&ctx->ctrl_hdl);
+ mutex_lock(&dev->dev_ctx_lock);
list_del_init(&ctx->list);
+ mutex_unlock(&dev->dev_ctx_lock);
kfree(ctx);
mutex_unlock(&dev->dev_mutex);
return 0;
@@ -294,6 +298,7 @@
mutex_init(&dev->enc_mutex);
mutex_init(&dev->dev_mutex);
+ mutex_init(&dev->dev_ctx_lock);
spin_lock_init(&dev->irqlock);
snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s",
diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h
index a042f60..0bd85d0 100644
--- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h
+++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h
@@ -178,6 +178,7 @@
*
* @enc_mutex: encoder hardware lock.
* @dev_mutex: video_device lock
+ * @dev_ctx_lock: the lock of context list
* @encode_workqueue: encode work queue
*
* @enc_irq: h264 encoder irq resource
@@ -205,6 +206,7 @@
/* encoder hardware mutex lock */
struct mutex enc_mutex;
struct mutex dev_mutex;
+ struct mutex dev_ctx_lock;
struct workqueue_struct *encode_workqueue;
int enc_irq;
diff --git a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c
index 84ad1cc..51bb7ee 100644
--- a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c
+++ b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c
@@ -47,12 +47,14 @@
struct mtk_vcodec_enc_ctx *ctx;
int ret = false;
+ mutex_lock(&enc_dev->dev_ctx_lock);
list_for_each_entry(ctx, &enc_dev->ctx_list, list) {
if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) {
ret = true;
break;
}
}
+ mutex_unlock(&enc_dev->dev_ctx_lock);
return ret;
}
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 1a64364..0ad2ff9 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -1002,7 +1002,7 @@
} else {
pcr->card_removed |= SD_EXIST;
pcr->card_inserted &= ~SD_EXIST;
- if (PCI_PID(pcr) == PID_5261) {
+ if ((PCI_PID(pcr) == PID_5261) || (PCI_PID(pcr) == PID_5264)) {
rtsx_pci_write_register(pcr, RTS5261_FW_STATUS,
RTS5261_EXPRESS_LINK_FAIL_MASK, 0);
pcr->extra_caps |= EXTRA_CAPS_SD_EXPRESS;
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 572333e..4bd4f32 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -758,15 +758,6 @@
}
pm_runtime_enable(dev);
- at24->nvmem = devm_nvmem_register(dev, &nvmem_config);
- if (IS_ERR(at24->nvmem)) {
- pm_runtime_disable(dev);
- if (!pm_runtime_status_suspended(dev))
- regulator_disable(at24->vcc_reg);
- return dev_err_probe(dev, PTR_ERR(at24->nvmem),
- "failed to register nvmem\n");
- }
-
/*
* Perform a one-byte test read to verify that the chip is functional,
* unless powering on the device is to be avoided during probe (i.e.
@@ -782,6 +773,15 @@
}
}
+ at24->nvmem = devm_nvmem_register(dev, &nvmem_config);
+ if (IS_ERR(at24->nvmem)) {
+ pm_runtime_disable(dev);
+ if (!pm_runtime_status_suspended(dev))
+ regulator_disable(at24->vcc_reg);
+ return dev_err_probe(dev, PTR_ERR(at24->nvmem),
+ "failed to register nvmem\n");
+ }
+
/* If this a SPD EEPROM, probe for DDR3 thermal sensor */
if (cdata == &at24_data_spd)
at24_probe_temp_sensor(client);
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index aac3675..c3a6657 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -115,6 +115,8 @@
#define MEI_DEV_ID_ARL_S 0x7F68 /* Arrow Lake Point S */
#define MEI_DEV_ID_ARL_H 0x7770 /* Arrow Lake Point H */
+#define MEI_DEV_ID_LNL_M 0xA870 /* Lunar Lake Point M */
+
/*
* MEI HW Section
*/
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index b575799..7f59dd3 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -116,12 +116,14 @@
{MEI_PCI_DEVICE(MEI_DEV_ID_ADP_P, MEI_ME_PCH15_CFG)},
{MEI_PCI_DEVICE(MEI_DEV_ID_ADP_N, MEI_ME_PCH15_CFG)},
- {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_SPS_CFG)},
{MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)},
{MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)},
{MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)},
+
/* required last entry */
{0, }
};
diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c
index 6c9f00b..b543e6b 100644
--- a/drivers/misc/mei/platform-vsc.c
+++ b/drivers/misc/mei/platform-vsc.c
@@ -400,25 +400,40 @@
static int mei_vsc_suspend(struct device *dev)
{
struct mei_device *mei_dev = dev_get_drvdata(dev);
+ struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
mei_stop(mei_dev);
+ mei_disable_interrupts(mei_dev);
+
+ vsc_tp_free_irq(hw->tp);
+
return 0;
}
static int mei_vsc_resume(struct device *dev)
{
struct mei_device *mei_dev = dev_get_drvdata(dev);
+ struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev);
int ret;
+ ret = vsc_tp_request_irq(hw->tp);
+ if (ret)
+ return ret;
+
ret = mei_restart(mei_dev);
if (ret)
- return ret;
+ goto err_free;
/* start timer if stopped in suspend */
schedule_delayed_work(&mei_dev->timer_work, HZ);
return 0;
+
+err_free:
+ vsc_tp_free_irq(hw->tp);
+
+ return ret;
}
static DEFINE_SIMPLE_DEV_PM_OPS(mei_vsc_pm_ops, mei_vsc_suspend, mei_vsc_resume);
diff --git a/drivers/misc/mei/pxp/mei_pxp.c b/drivers/misc/mei/pxp/mei_pxp.c
index b1e4c23..49abc95 100644
--- a/drivers/misc/mei/pxp/mei_pxp.c
+++ b/drivers/misc/mei/pxp/mei_pxp.c
@@ -236,8 +236,11 @@
pdev = to_pci_dev(dev);
- if (pdev->class != (PCI_CLASS_DISPLAY_VGA << 8) ||
- pdev->vendor != PCI_VENDOR_ID_INTEL)
+ if (pdev->vendor != PCI_VENDOR_ID_INTEL)
+ return 0;
+
+ if (pdev->class != (PCI_CLASS_DISPLAY_VGA << 8) &&
+ pdev->class != (PCI_CLASS_DISPLAY_OTHER << 8))
return 0;
if (subcomponent != I915_COMPONENT_PXP)
diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
index ecfb70c..e6a98db 100644
--- a/drivers/misc/mei/vsc-tp.c
+++ b/drivers/misc/mei/vsc-tp.c
@@ -94,6 +94,27 @@
{}
};
+static irqreturn_t vsc_tp_isr(int irq, void *data)
+{
+ struct vsc_tp *tp = data;
+
+ atomic_inc(&tp->assert_cnt);
+
+ wake_up(&tp->xfer_wait);
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t vsc_tp_thread_isr(int irq, void *data)
+{
+ struct vsc_tp *tp = data;
+
+ if (tp->event_notify)
+ tp->event_notify(tp->event_notify_context);
+
+ return IRQ_HANDLED;
+}
+
/* wakeup firmware and wait for response */
static int vsc_tp_wakeup_request(struct vsc_tp *tp)
{
@@ -384,6 +405,37 @@
EXPORT_SYMBOL_NS_GPL(vsc_tp_register_event_cb, VSC_TP);
/**
+ * vsc_tp_request_irq - request irq for vsc_tp device
+ * @tp: vsc_tp device handle
+ */
+int vsc_tp_request_irq(struct vsc_tp *tp)
+{
+ struct spi_device *spi = tp->spi;
+ struct device *dev = &spi->dev;
+ int ret;
+
+ irq_set_status_flags(spi->irq, IRQ_DISABLE_UNLAZY);
+ ret = request_threaded_irq(spi->irq, vsc_tp_isr, vsc_tp_thread_isr,
+ IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+ dev_name(dev), tp);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_request_irq, VSC_TP);
+
+/**
+ * vsc_tp_free_irq - free irq for vsc_tp device
+ * @tp: vsc_tp device handle
+ */
+void vsc_tp_free_irq(struct vsc_tp *tp)
+{
+ free_irq(tp->spi->irq, tp);
+}
+EXPORT_SYMBOL_NS_GPL(vsc_tp_free_irq, VSC_TP);
+
+/**
* vsc_tp_intr_synchronize - synchronize vsc_tp interrupt
* @tp: vsc_tp device handle
*/
@@ -413,27 +465,6 @@
}
EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_disable, VSC_TP);
-static irqreturn_t vsc_tp_isr(int irq, void *data)
-{
- struct vsc_tp *tp = data;
-
- atomic_inc(&tp->assert_cnt);
-
- return IRQ_WAKE_THREAD;
-}
-
-static irqreturn_t vsc_tp_thread_isr(int irq, void *data)
-{
- struct vsc_tp *tp = data;
-
- wake_up(&tp->xfer_wait);
-
- if (tp->event_notify)
- tp->event_notify(tp->event_notify_context);
-
- return IRQ_HANDLED;
-}
-
static int vsc_tp_match_any(struct acpi_device *adev, void *data)
{
struct acpi_device **__adev = data;
@@ -490,10 +521,9 @@
tp->spi = spi;
irq_set_status_flags(spi->irq, IRQ_DISABLE_UNLAZY);
- ret = devm_request_threaded_irq(dev, spi->irq, vsc_tp_isr,
- vsc_tp_thread_isr,
- IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
- dev_name(dev), tp);
+ ret = request_threaded_irq(spi->irq, vsc_tp_isr, vsc_tp_thread_isr,
+ IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+ dev_name(dev), tp);
if (ret)
return ret;
@@ -522,6 +552,8 @@
err_destroy_lock:
mutex_destroy(&tp->mutex);
+ free_irq(spi->irq, tp);
+
return ret;
}
@@ -532,6 +564,8 @@
platform_device_unregister(tp->pdev);
mutex_destroy(&tp->mutex);
+
+ free_irq(spi->irq, tp);
}
static const struct acpi_device_id vsc_tp_acpi_ids[] = {
diff --git a/drivers/misc/mei/vsc-tp.h b/drivers/misc/mei/vsc-tp.h
index f9513dd..14ca195 100644
--- a/drivers/misc/mei/vsc-tp.h
+++ b/drivers/misc/mei/vsc-tp.h
@@ -37,6 +37,9 @@
int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb,
void *context);
+int vsc_tp_request_irq(struct vsc_tp *tp);
+void vsc_tp_free_irq(struct vsc_tp *tp);
+
void vsc_tp_intr_enable(struct vsc_tp *tp);
void vsc_tp_intr_disable(struct vsc_tp *tp);
void vsc_tp_intr_synchronize(struct vsc_tp *tp);
diff --git a/drivers/misc/pvpanic/pvpanic-pci.c b/drivers/misc/pvpanic/pvpanic-pci.c
index 9ad20e8..b21598a 100644
--- a/drivers/misc/pvpanic/pvpanic-pci.c
+++ b/drivers/misc/pvpanic/pvpanic-pci.c
@@ -44,8 +44,6 @@
.name = "pvpanic-pci",
.id_table = pvpanic_pci_id_tbl,
.probe = pvpanic_pci_probe,
- .driver = {
- .dev_groups = pvpanic_dev_groups,
- },
+ .dev_groups = pvpanic_dev_groups,
};
module_pci_driver(pvpanic_pci_driver);
diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c
index b88d6de..9a5f751 100644
--- a/drivers/mmc/host/moxart-mmc.c
+++ b/drivers/mmc/host/moxart-mmc.c
@@ -300,6 +300,7 @@
remain = sgm->length;
if (remain > host->data_len)
remain = host->data_len;
+ sgm->consumed = 0;
if (data->flags & MMC_DATA_WRITE) {
while (remain > 0) {
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index 088f8ed..a8ee0df 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -1114,10 +1114,25 @@
host = slot->host;
- if (slot->vsd)
- gpiod_set_value(slot->vsd, power_on);
- if (slot->vio)
- gpiod_set_value(slot->vio, power_on);
+ if (power_on) {
+ if (slot->vsd) {
+ gpiod_set_value(slot->vsd, power_on);
+ msleep(1);
+ }
+ if (slot->vio) {
+ gpiod_set_value(slot->vio, power_on);
+ msleep(1);
+ }
+ } else {
+ if (slot->vio) {
+ gpiod_set_value(slot->vio, power_on);
+ msleep(50);
+ }
+ if (slot->vsd) {
+ gpiod_set_value(slot->vsd, power_on);
+ msleep(50);
+ }
+ }
if (slot->pdata->set_power != NULL)
slot->pdata->set_power(mmc_dev(slot->mmc), slot->id, power_on,
@@ -1254,18 +1269,18 @@
slot->pdata = &host->pdata->slots[id];
/* Check for some optional GPIO controls */
- slot->vsd = gpiod_get_index_optional(host->dev, "vsd",
- id, GPIOD_OUT_LOW);
+ slot->vsd = devm_gpiod_get_index_optional(host->dev, "vsd",
+ id, GPIOD_OUT_LOW);
if (IS_ERR(slot->vsd))
return dev_err_probe(host->dev, PTR_ERR(slot->vsd),
"error looking up VSD GPIO\n");
- slot->vio = gpiod_get_index_optional(host->dev, "vio",
- id, GPIOD_OUT_LOW);
+ slot->vio = devm_gpiod_get_index_optional(host->dev, "vio",
+ id, GPIOD_OUT_LOW);
if (IS_ERR(slot->vio))
return dev_err_probe(host->dev, PTR_ERR(slot->vio),
"error looking up VIO GPIO\n");
- slot->cover = gpiod_get_index_optional(host->dev, "cover",
- id, GPIOD_IN);
+ slot->cover = devm_gpiod_get_index_optional(host->dev, "cover",
+ id, GPIOD_IN);
if (IS_ERR(slot->cover))
return dev_err_probe(host->dev, PTR_ERR(slot->cover),
"error looking up cover switch GPIO\n");
@@ -1379,13 +1394,6 @@
if (IS_ERR(host->virt_base))
return PTR_ERR(host->virt_base);
- host->slot_switch = gpiod_get_optional(host->dev, "switch",
- GPIOD_OUT_LOW);
- if (IS_ERR(host->slot_switch))
- return dev_err_probe(host->dev, PTR_ERR(host->slot_switch),
- "error looking up slot switch GPIO\n");
-
-
INIT_WORK(&host->slot_release_work, mmc_omap_slot_release_work);
INIT_WORK(&host->send_stop_work, mmc_omap_send_stop_work);
@@ -1404,6 +1412,12 @@
host->dev = &pdev->dev;
platform_set_drvdata(pdev, host);
+ host->slot_switch = devm_gpiod_get_optional(host->dev, "switch",
+ GPIOD_OUT_LOW);
+ if (IS_ERR(host->slot_switch))
+ return dev_err_probe(host->dev, PTR_ERR(host->slot_switch),
+ "error looking up slot switch GPIO\n");
+
host->id = pdev->id;
host->irq = irq;
host->phys_base = res->start;
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 668e0ac..e113b99 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -2694,6 +2694,11 @@
struct sdhci_host *host = dev_get_drvdata(dev);
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+ unsigned long flags;
+
+ spin_lock_irqsave(&host->lock, flags);
+ host->runtime_suspended = true;
+ spin_unlock_irqrestore(&host->lock, flags);
/* Drop the performance vote */
dev_pm_opp_set_rate(dev, 0);
@@ -2708,6 +2713,7 @@
struct sdhci_host *host = dev_get_drvdata(dev);
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+ unsigned long flags;
int ret;
ret = clk_bulk_prepare_enable(ARRAY_SIZE(msm_host->bulk_clks),
@@ -2726,7 +2732,15 @@
dev_pm_opp_set_rate(dev, msm_host->clk_rate);
- return sdhci_msm_ice_resume(msm_host);
+ ret = sdhci_msm_ice_resume(msm_host);
+ if (ret)
+ return ret;
+
+ spin_lock_irqsave(&host->lock, flags);
+ host->runtime_suspended = false;
+ spin_unlock_irqrestore(&host->lock, flags);
+
+ return ret;
}
static const struct dev_pm_ops sdhci_msm_pm_ops = {
diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c
index 1d8f5a7..f2e4a93 100644
--- a/drivers/mmc/host/sdhci-of-dwcmshc.c
+++ b/drivers/mmc/host/sdhci-of-dwcmshc.c
@@ -626,6 +626,7 @@
/* perform tuning */
sdhci_start_tuning(host);
+ host->tuning_loop_count = 128;
host->tuning_err = __sdhci_execute_tuning(host, opcode);
if (host->tuning_err) {
/* disable auto-tuning upon tuning error */
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 5887feb..0de87bc 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -900,7 +900,7 @@
config.name = compatible;
config.id = NVMEM_DEVID_AUTO;
config.owner = THIS_MODULE;
- config.add_legacy_fixed_of_cells = true;
+ config.add_legacy_fixed_of_cells = !mtd_type_is_nand(mtd);
config.type = NVMEM_TYPE_OTP;
config.root_only = true;
config.ignore_wp = true;
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index a8d12c7..1b2ec0f 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -857,7 +857,7 @@
struct brcmnand_soc *soc = ctrl->soc;
int i;
- if (soc->read_data_bus) {
+ if (soc && soc->read_data_bus) {
soc->read_data_bus(soc, flash_cache, buffer, fc_words);
} else {
for (i = 0; i < fc_words; i++)
diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 5243fab..8db7fc4 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -53,7 +53,7 @@
0xe8000, 0xea000, 0xec000, 0xee000,
#endif
#endif
- 0xffffffff };
+};
static struct mtd_info *doclist = NULL;
@@ -1554,7 +1554,7 @@
if (ret < 0)
return ret;
} else {
- for (i = 0; (doc_locations[i] != 0xffffffff); i++) {
+ for (i = 0; i < ARRAY_SIZE(doc_locations); i++) {
doc_probe(doc_locations[i]);
}
}
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index b079605..b8cff92 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2815,7 +2815,7 @@
host->cfg0_raw & ~(7 << CW_PER_PAGE));
nandc_set_reg(chip, NAND_DEV0_CFG1, host->cfg1_raw);
instrs = 3;
- } else {
+ } else if (q_op.cmd_reg != OP_RESET_DEVICE) {
return 0;
}
@@ -2830,9 +2830,8 @@
nandc_set_reg(chip, NAND_EXEC_CMD, 1);
write_reg_dma(nandc, NAND_FLASH_CMD, instrs, NAND_BAM_NEXT_SGL);
- (q_op.cmd_reg == OP_BLOCK_ERASE) ? write_reg_dma(nandc, NAND_DEV0_CFG0,
- 2, NAND_BAM_NEXT_SGL) : read_reg_dma(nandc,
- NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL);
+ if (q_op.cmd_reg == OP_BLOCK_ERASE)
+ write_reg_dma(nandc, NAND_DEV0_CFG0, 2, NAND_BAM_NEXT_SGL);
write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL);
read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL);
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 1035820..8090390 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -950,20 +950,173 @@
mutex_unlock(&priv->reg_mutex);
}
-/* On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std
- * 802.1Q™-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA
- * must only be propagated to C-VLAN and MAC Bridge components. That means
- * VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports,
- * these frames are supposed to be processed by the CPU (software). So we make
- * the switch only forward them to the CPU port. And if received from a CPU
- * port, forward to a single port. The software is responsible of making the
- * switch conform to the latter by setting a single port as destination port on
- * the special tag.
+/* In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL)
+ * of the Open Systems Interconnection basic reference model (OSI/RM) are
+ * described; the medium access control (MAC) and logical link control (LLC)
+ * sublayers. The MAC sublayer is the one facing the physical layer.
*
- * This switch intellectual property cannot conform to this part of the standard
- * fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC
- * DAs, it also includes :22-FF which the scope of propagation is not supposed
- * to be restricted for these MAC DAs.
+ * In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A
+ * Bridge component comprises a MAC Relay Entity for interconnecting the Ports
+ * of the Bridge, at least two Ports, and higher layer entities with at least a
+ * Spanning Tree Protocol Entity included.
+ *
+ * Each Bridge Port also functions as an end station and shall provide the MAC
+ * Service to an LLC Entity. Each instance of the MAC Service is provided to a
+ * distinct LLC Entity that supports protocol identification, multiplexing, and
+ * demultiplexing, for protocol data unit (PDU) transmission and reception by
+ * one or more higher layer entities.
+ *
+ * It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC
+ * Entity associated with each Bridge Port is modeled as being directly
+ * connected to the attached Local Area Network (LAN).
+ *
+ * On the switch with CPU port architecture, CPU port functions as Management
+ * Port, and the Management Port functionality is provided by software which
+ * functions as an end station. Software is connected to an IEEE 802 LAN that is
+ * wholly contained within the system that incorporates the Bridge. Software
+ * provides access to the LLC Entity associated with each Bridge Port by the
+ * value of the source port field on the special tag on the frame received by
+ * software.
+ *
+ * We call frames that carry control information to determine the active
+ * topology and current extent of each Virtual Local Area Network (VLAN), i.e.,
+ * spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration
+ * Protocol Data Units (MVRPDUs), and frames from other link constrained
+ * protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and
+ * Link Layer Discovery Protocol (LLDP), link-local frames. They are not
+ * forwarded by a Bridge. Permanently configured entries in the filtering
+ * database (FDB) ensure that such frames are discarded by the Forwarding
+ * Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail:
+ *
+ * Each of the reserved MAC addresses specified in Table 8-1
+ * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be
+ * permanently configured in the FDB in C-VLAN components and ERs.
+ *
+ * Each of the reserved MAC addresses specified in Table 8-2
+ * (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently
+ * configured in the FDB in S-VLAN components.
+ *
+ * Each of the reserved MAC addresses specified in Table 8-3
+ * (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in
+ * TPMR components.
+ *
+ * The FDB entries for reserved MAC addresses shall specify filtering for all
+ * Bridge Ports and all VIDs. Management shall not provide the capability to
+ * modify or remove entries for reserved MAC addresses.
+ *
+ * The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of
+ * propagation of PDUs within a Bridged Network, as follows:
+ *
+ * The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no
+ * conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN)
+ * component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward.
+ * PDUs transmitted using this destination address, or any other addresses
+ * that appear in Table 8-1, Table 8-2, and Table 8-3
+ * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can
+ * therefore travel no further than those stations that can be reached via a
+ * single individual LAN from the originating station.
+ *
+ * The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an
+ * address that no conformant S-VLAN component, C-VLAN component, or MAC
+ * Bridge can forward; however, this address is relayed by a TPMR component.
+ * PDUs using this destination address, or any of the other addresses that
+ * appear in both Table 8-1 and Table 8-2 but not in Table 8-3
+ * (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by
+ * any TPMRs but will propagate no further than the nearest S-VLAN component,
+ * C-VLAN component, or MAC Bridge.
+ *
+ * The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address
+ * that no conformant C-VLAN component, MAC Bridge can forward; however, it is
+ * relayed by TPMR components and S-VLAN components. PDUs using this
+ * destination address, or any of the other addresses that appear in Table 8-1
+ * but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]),
+ * will be relayed by TPMR components and S-VLAN components but will propagate
+ * no further than the nearest C-VLAN component or MAC Bridge.
+ *
+ * Because the LLC Entity associated with each Bridge Port is provided via CPU
+ * port, we must not filter these frames but forward them to CPU port.
+ *
+ * In a Bridge, the transmission Port is majorly decided by ingress and egress
+ * rules, FDB, and spanning tree Port State functions of the Forwarding Process.
+ * For link-local frames, only CPU port should be designated as destination port
+ * in the FDB, and the other functions of the Forwarding Process must not
+ * interfere with the decision of the transmission Port. We call this process
+ * trapping frames to CPU port.
+ *
+ * Therefore, on the switch with CPU port architecture, link-local frames must
+ * be trapped to CPU port, and certain link-local frames received by a Port of a
+ * Bridge comprising a TPMR component or an S-VLAN component must be excluded
+ * from it.
+ *
+ * A Bridge of the switch with CPU port architecture cannot comprise a Two-Port
+ * MAC Relay (TPMR) component as a TPMR component supports only a subset of the
+ * functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port
+ * doesn't count) of this architecture will either function as a standard MAC
+ * Bridge or a standard VLAN Bridge.
+ *
+ * Therefore, a Bridge of this architecture can only comprise S-VLAN components,
+ * C-VLAN components, or MAC Bridge components. Since there's no TPMR component,
+ * we don't need to relay PDUs using the destination addresses specified on the
+ * Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge
+ * section where they must be relayed by TPMR components.
+ *
+ * One option to trap link-local frames to CPU port is to add static FDB entries
+ * with CPU port designated as destination port. However, because that
+ * Independent VLAN Learning (IVL) is being used on every VID, each entry only
+ * applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC
+ * Bridge component or a C-VLAN component, there would have to be 16 times 4096
+ * entries. This switch intellectual property can only hold a maximum of 2048
+ * entries. Using this option, there also isn't a mechanism to prevent
+ * link-local frames from being discarded when the spanning tree Port State of
+ * the reception Port is discarding.
+ *
+ * The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4
+ * registers. Whilst this applies to every VID, it doesn't contain all of the
+ * reserved MAC addresses without affecting the remaining Standard Group MAC
+ * Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the
+ * remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination
+ * addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF
+ * destination addresses which may be relayed by MAC Bridges or VLAN Bridges.
+ * The latter option provides better but not complete conformance.
+ *
+ * This switch intellectual property also does not provide a mechanism to trap
+ * link-local frames with specific destination addresses to CPU port by Bridge,
+ * to conform to the filtering rules for the distinct Bridge components.
+ *
+ * Therefore, regardless of the type of the Bridge component, link-local frames
+ * with these destination addresses will be trapped to CPU port:
+ *
+ * 01-80-C2-00-00-[00,01,02,03,0E]
+ *
+ * In a Bridge comprising a MAC Bridge component or a C-VLAN component:
+ *
+ * Link-local frames with these destination addresses won't be trapped to CPU
+ * port which won't conform to IEEE Std 802.1Q-2022:
+ *
+ * 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F]
+ *
+ * In a Bridge comprising an S-VLAN component:
+ *
+ * Link-local frames with these destination addresses will be trapped to CPU
+ * port which won't conform to IEEE Std 802.1Q-2022:
+ *
+ * 01-80-C2-00-00-00
+ *
+ * Link-local frames with these destination addresses won't be trapped to CPU
+ * port which won't conform to IEEE Std 802.1Q-2022:
+ *
+ * 01-80-C2-00-00-[04,05,06,07,08,09,0A]
+ *
+ * To trap link-local frames to CPU port as conformant as this switch
+ * intellectual property can allow, link-local frames are made to be regarded as
+ * Bridge Protocol Data Units (BPDUs). This is because this switch intellectual
+ * property only lets the frames regarded as BPDUs bypass the spanning tree Port
+ * State function of the Forwarding Process.
+ *
+ * The only remaining interference is the ingress rules. When the reception Port
+ * has no PVID assigned on software, VLAN-untagged frames won't be allowed in.
+ * There doesn't seem to be a mechanism on the switch intellectual property to
+ * have link-local frames bypass this function of the Forwarding Process.
*/
static void
mt753x_trap_frames(struct mt7530_priv *priv)
@@ -971,35 +1124,43 @@
/* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them
* VLAN-untagged.
*/
- mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_EG_TAG_MASK |
- MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK |
- MT753X_BPDU_PORT_FW_MASK,
- MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) |
- MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_BPDU_CPU_ONLY);
+ mt7530_rmw(priv, MT753X_BPC,
+ MT753X_PAE_BPDU_FR | MT753X_PAE_EG_TAG_MASK |
+ MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK |
+ MT753X_BPDU_PORT_FW_MASK,
+ MT753X_PAE_BPDU_FR |
+ MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+ MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_BPDU_CPU_ONLY);
/* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress
* them VLAN-untagged.
*/
- mt7530_rmw(priv, MT753X_RGAC1, MT753X_R02_EG_TAG_MASK |
- MT753X_R02_PORT_FW_MASK | MT753X_R01_EG_TAG_MASK |
- MT753X_R01_PORT_FW_MASK,
- MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) |
- MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_BPDU_CPU_ONLY);
+ mt7530_rmw(priv, MT753X_RGAC1,
+ MT753X_R02_BPDU_FR | MT753X_R02_EG_TAG_MASK |
+ MT753X_R02_PORT_FW_MASK | MT753X_R01_BPDU_FR |
+ MT753X_R01_EG_TAG_MASK | MT753X_R01_PORT_FW_MASK,
+ MT753X_R02_BPDU_FR |
+ MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+ MT753X_R01_BPDU_FR |
+ MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_BPDU_CPU_ONLY);
/* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress
* them VLAN-untagged.
*/
- mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_EG_TAG_MASK |
- MT753X_R0E_PORT_FW_MASK | MT753X_R03_EG_TAG_MASK |
- MT753X_R03_PORT_FW_MASK,
- MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) |
- MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_BPDU_CPU_ONLY);
+ mt7530_rmw(priv, MT753X_RGAC2,
+ MT753X_R0E_BPDU_FR | MT753X_R0E_EG_TAG_MASK |
+ MT753X_R0E_PORT_FW_MASK | MT753X_R03_BPDU_FR |
+ MT753X_R03_EG_TAG_MASK | MT753X_R03_PORT_FW_MASK,
+ MT753X_R0E_BPDU_FR |
+ MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+ MT753X_R03_BPDU_FR |
+ MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_BPDU_CPU_ONLY);
}
static void
@@ -1722,14 +1883,16 @@
static int mt753x_mirror_port_get(unsigned int id, u32 val)
{
- return (id == ID_MT7531) ? MT7531_MIRROR_PORT_GET(val) :
- MIRROR_PORT(val);
+ return (id == ID_MT7531 || id == ID_MT7988) ?
+ MT7531_MIRROR_PORT_GET(val) :
+ MIRROR_PORT(val);
}
static int mt753x_mirror_port_set(unsigned int id, u32 val)
{
- return (id == ID_MT7531) ? MT7531_MIRROR_PORT_SET(val) :
- MIRROR_PORT(val);
+ return (id == ID_MT7531 || id == ID_MT7988) ?
+ MT7531_MIRROR_PORT_SET(val) :
+ MIRROR_PORT(val);
}
static int mt753x_port_mirror_add(struct dsa_switch *ds, int port,
@@ -2319,6 +2482,9 @@
PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
}
+ /* Allow mirroring frames received on the local port (monitor port). */
+ mt7530_set(priv, MT753X_AGC, LOCAL_EN);
+
/* Setup VLAN ID 0 for VLAN-unaware bridges */
ret = mt7530_setup_vlan0(priv);
if (ret)
@@ -2430,6 +2596,9 @@
PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
}
+ /* Allow mirroring frames received on the local port (monitor port). */
+ mt7530_set(priv, MT753X_AGC, LOCAL_EN);
+
/* Flush the FDB table */
ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL);
if (ret < 0)
@@ -2505,18 +2674,25 @@
mt7530_rmw(priv, MT7531_GPIO_MODE0, MT7531_GPIO0_MASK,
MT7531_GPIO0_INTERRUPT);
- /* Enable PHY core PLL, since phy_device has not yet been created
- * provided for phy_[read,write]_mmd_indirect is called, we provide
- * our own mt7531_ind_mmd_phy_[read,write] to complete this
- * function.
+ /* Enable Energy-Efficient Ethernet (EEE) and PHY core PLL, since
+ * phy_device has not yet been created provided for
+ * phy_[read,write]_mmd_indirect is called, we provide our own
+ * mt7531_ind_mmd_phy_[read,write] to complete this function.
*/
val = mt7531_ind_c45_phy_read(priv, MT753X_CTRL_PHY_ADDR,
MDIO_MMD_VEND2, CORE_PLL_GROUP4);
- val |= MT7531_PHY_PLL_BYPASS_MODE;
+ val |= MT7531_RG_SYSPLL_DMY2 | MT7531_PHY_PLL_BYPASS_MODE;
val &= ~MT7531_PHY_PLL_OFF;
mt7531_ind_c45_phy_write(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2,
CORE_PLL_GROUP4, val);
+ /* Disable EEE advertisement on the switch PHYs. */
+ for (i = MT753X_CTRL_PHY_ADDR;
+ i < MT753X_CTRL_PHY_ADDR + MT7530_NUM_PHYS; i++) {
+ mt7531_ind_c45_phy_write(priv, i, MDIO_MMD_AN, MDIO_AN_EEE_ADV,
+ 0);
+ }
+
mt7531_setup_common(ds);
/* Setup VLAN ID 0 for VLAN-unaware bridges */
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index d17b318..a080533 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -32,6 +32,10 @@
#define SYSC_REG_RSTCTRL 0x34
#define RESET_MCM BIT(2)
+/* Register for ARL global control */
+#define MT753X_AGC 0xc
+#define LOCAL_EN BIT(7)
+
/* Registers to mac forward control for unknown frames */
#define MT7530_MFC 0x10
#define BC_FFP(x) (((x) & 0xff) << 24)
@@ -65,6 +69,7 @@
/* Registers for BPDU and PAE frame control*/
#define MT753X_BPC 0x24
+#define MT753X_PAE_BPDU_FR BIT(25)
#define MT753X_PAE_EG_TAG_MASK GENMASK(24, 22)
#define MT753X_PAE_EG_TAG(x) FIELD_PREP(MT753X_PAE_EG_TAG_MASK, x)
#define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16)
@@ -75,20 +80,24 @@
/* Register for :01 and :02 MAC DA frame control */
#define MT753X_RGAC1 0x28
+#define MT753X_R02_BPDU_FR BIT(25)
#define MT753X_R02_EG_TAG_MASK GENMASK(24, 22)
#define MT753X_R02_EG_TAG(x) FIELD_PREP(MT753X_R02_EG_TAG_MASK, x)
#define MT753X_R02_PORT_FW_MASK GENMASK(18, 16)
#define MT753X_R02_PORT_FW(x) FIELD_PREP(MT753X_R02_PORT_FW_MASK, x)
+#define MT753X_R01_BPDU_FR BIT(9)
#define MT753X_R01_EG_TAG_MASK GENMASK(8, 6)
#define MT753X_R01_EG_TAG(x) FIELD_PREP(MT753X_R01_EG_TAG_MASK, x)
#define MT753X_R01_PORT_FW_MASK GENMASK(2, 0)
/* Register for :03 and :0E MAC DA frame control */
#define MT753X_RGAC2 0x2c
+#define MT753X_R0E_BPDU_FR BIT(25)
#define MT753X_R0E_EG_TAG_MASK GENMASK(24, 22)
#define MT753X_R0E_EG_TAG(x) FIELD_PREP(MT753X_R0E_EG_TAG_MASK, x)
#define MT753X_R0E_PORT_FW_MASK GENMASK(18, 16)
#define MT753X_R0E_PORT_FW(x) FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x)
+#define MT753X_R03_BPDU_FR BIT(9)
#define MT753X_R03_EG_TAG_MASK GENMASK(8, 6)
#define MT753X_R03_EG_TAG(x) FIELD_PREP(MT753X_R03_EG_TAG_MASK, x)
#define MT753X_R03_PORT_FW_MASK GENMASK(2, 0)
@@ -616,6 +625,7 @@
#define RG_SYSPLL_DDSFBK_EN BIT(12)
#define RG_SYSPLL_BIAS_EN BIT(11)
#define RG_SYSPLL_BIAS_LPF_EN BIT(10)
+#define MT7531_RG_SYSPLL_DMY2 BIT(6)
#define MT7531_PHY_PLL_OFF BIT(5)
#define MT7531_PHY_PLL_BYPASS_MODE BIT(4)
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index c95787c..14daf43 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -566,13 +566,61 @@
phy_interface_set_rgmii(supported);
}
+static void
+mv88e6250_setup_supported_interfaces(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
+{
+ unsigned long *supported = config->supported_interfaces;
+ int err;
+ u16 reg;
+
+ err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®);
+ if (err) {
+ dev_err(chip->dev, "p%d: failed to read port status\n", port);
+ return;
+ }
+
+ switch (reg & MV88E6250_PORT_STS_PORTMODE_MASK) {
+ case MV88E6250_PORT_STS_PORTMODE_MII_10_HALF_PHY:
+ case MV88E6250_PORT_STS_PORTMODE_MII_100_HALF_PHY:
+ case MV88E6250_PORT_STS_PORTMODE_MII_10_FULL_PHY:
+ case MV88E6250_PORT_STS_PORTMODE_MII_100_FULL_PHY:
+ __set_bit(PHY_INTERFACE_MODE_REVMII, supported);
+ break;
+
+ case MV88E6250_PORT_STS_PORTMODE_MII_HALF:
+ case MV88E6250_PORT_STS_PORTMODE_MII_FULL:
+ __set_bit(PHY_INTERFACE_MODE_MII, supported);
+ break;
+
+ case MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL_PHY:
+ case MV88E6250_PORT_STS_PORTMODE_MII_200_RMII_FULL_PHY:
+ case MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_HALF_PHY:
+ case MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL_PHY:
+ __set_bit(PHY_INTERFACE_MODE_REVRMII, supported);
+ break;
+
+ case MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL:
+ case MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL:
+ __set_bit(PHY_INTERFACE_MODE_RMII, supported);
+ break;
+
+ case MV88E6250_PORT_STS_PORTMODE_MII_100_RGMII:
+ __set_bit(PHY_INTERFACE_MODE_RGMII, supported);
+ break;
+
+ default:
+ dev_err(chip->dev,
+ "p%d: invalid port mode in status register: %04x\n",
+ port, reg);
+ }
+}
+
static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
struct phylink_config *config)
{
- unsigned long *supported = config->supported_interfaces;
-
- /* Translate the default cmode */
- mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
+ if (!mv88e6xxx_phy_is_internal(chip, port))
+ mv88e6250_setup_supported_interfaces(chip, port, config);
config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100;
}
@@ -5657,7 +5705,7 @@
.prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6141,
.family = MV88E6XXX_FAMILY_6341,
.name = "Marvell 88E6141",
- .num_databases = 4096,
+ .num_databases = 256,
.num_macs = 2048,
.num_ports = 6,
.num_internal_phys = 5,
@@ -6116,7 +6164,7 @@
.prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6341,
.family = MV88E6XXX_FAMILY_6341,
.name = "Marvell 88E6341",
- .num_databases = 4096,
+ .num_databases = 256,
.num_macs = 2048,
.num_internal_phys = 5,
.num_ports = 6,
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 86deeb3..ddadeb9 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -25,10 +25,25 @@
#define MV88E6250_PORT_STS_PORTMODE_PHY_100_HALF 0x0900
#define MV88E6250_PORT_STS_PORTMODE_PHY_10_FULL 0x0a00
#define MV88E6250_PORT_STS_PORTMODE_PHY_100_FULL 0x0b00
-#define MV88E6250_PORT_STS_PORTMODE_MII_10_HALF 0x0c00
-#define MV88E6250_PORT_STS_PORTMODE_MII_100_HALF 0x0d00
-#define MV88E6250_PORT_STS_PORTMODE_MII_10_FULL 0x0e00
-#define MV88E6250_PORT_STS_PORTMODE_MII_100_FULL 0x0f00
+/* - Modes with PHY suffix use output instead of input clock
+ * - Modes without RMII or RGMII use MII
+ * - Modes without speed do not have a fixed speed specified in the manual
+ * ("DC to x MHz" - variable clock support?)
+ */
+#define MV88E6250_PORT_STS_PORTMODE_MII_DISABLED 0x0000
+#define MV88E6250_PORT_STS_PORTMODE_MII_100_RGMII 0x0100
+#define MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL_PHY 0x0200
+#define MV88E6250_PORT_STS_PORTMODE_MII_200_RMII_FULL_PHY 0x0400
+#define MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL 0x0600
+#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL 0x0700
+#define MV88E6250_PORT_STS_PORTMODE_MII_HALF 0x0800
+#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_HALF_PHY 0x0900
+#define MV88E6250_PORT_STS_PORTMODE_MII_FULL 0x0a00
+#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL_PHY 0x0b00
+#define MV88E6250_PORT_STS_PORTMODE_MII_10_HALF_PHY 0x0c00
+#define MV88E6250_PORT_STS_PORTMODE_MII_100_HALF_PHY 0x0d00
+#define MV88E6250_PORT_STS_PORTMODE_MII_10_FULL_PHY 0x0e00
+#define MV88E6250_PORT_STS_PORTMODE_MII_100_FULL_PHY 0x0f00
#define MV88E6XXX_PORT_STS_LINK 0x0800
#define MV88E6XXX_PORT_STS_DUPLEX 0x0400
#define MV88E6XXX_PORT_STS_SPEED_MASK 0x0300
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 9e9e4a03..2d8a66e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -351,7 +351,7 @@
ENA_COM_BOUNCE_BUFFER_CNTRL_CNT;
io_sq->bounce_buf_ctrl.next_to_use = 0;
- size = io_sq->bounce_buf_ctrl.buffer_size *
+ size = (size_t)io_sq->bounce_buf_ctrl.buffer_size *
io_sq->bounce_buf_ctrl.buffers_num;
dev_node = dev_to_node(ena_dev->dmadev);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 09e7da1..be5acfa 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -718,8 +718,11 @@
static void ena_free_tx_bufs(struct ena_ring *tx_ring)
{
bool print_once = true;
+ bool is_xdp_ring;
u32 i;
+ is_xdp_ring = ENA_IS_XDP_INDEX(tx_ring->adapter, tx_ring->qid);
+
for (i = 0; i < tx_ring->ring_size; i++) {
struct ena_tx_buffer *tx_info = &tx_ring->tx_buffer_info[i];
@@ -739,10 +742,15 @@
ena_unmap_tx_buff(tx_ring, tx_info);
- dev_kfree_skb_any(tx_info->skb);
+ if (is_xdp_ring)
+ xdp_return_frame(tx_info->xdpf);
+ else
+ dev_kfree_skb_any(tx_info->skb);
}
- netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev,
- tx_ring->qid));
+
+ if (!is_xdp_ring)
+ netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev,
+ tx_ring->qid));
}
static void ena_free_all_tx_bufs(struct ena_adapter *adapter)
@@ -3481,10 +3489,11 @@
{
struct ena_ring *tx_ring;
struct ena_ring *rx_ring;
- int i, budget, rc;
+ int qid, budget, rc;
int io_queue_count;
io_queue_count = adapter->xdp_num_queues + adapter->num_io_queues;
+
/* Make sure the driver doesn't turn the device in other process */
smp_rmb();
@@ -3497,27 +3506,29 @@
if (adapter->missing_tx_completion_to == ENA_HW_HINTS_NO_TIMEOUT)
return;
- budget = ENA_MONITORED_TX_QUEUES;
+ budget = min_t(u32, io_queue_count, ENA_MONITORED_TX_QUEUES);
- for (i = adapter->last_monitored_tx_qid; i < io_queue_count; i++) {
- tx_ring = &adapter->tx_ring[i];
- rx_ring = &adapter->rx_ring[i];
+ qid = adapter->last_monitored_tx_qid;
+
+ while (budget) {
+ qid = (qid + 1) % io_queue_count;
+
+ tx_ring = &adapter->tx_ring[qid];
+ rx_ring = &adapter->rx_ring[qid];
rc = check_missing_comp_in_tx_queue(adapter, tx_ring);
if (unlikely(rc))
return;
- rc = !ENA_IS_XDP_INDEX(adapter, i) ?
+ rc = !ENA_IS_XDP_INDEX(adapter, qid) ?
check_for_rx_interrupt_queue(adapter, rx_ring) : 0;
if (unlikely(rc))
return;
budget--;
- if (!budget)
- break;
}
- adapter->last_monitored_tx_qid = i % io_queue_count;
+ adapter->last_monitored_tx_qid = qid;
}
/* trigger napi schedule after 2 consecutive detections */
diff --git a/drivers/net/ethernet/amazon/ena/ena_xdp.c b/drivers/net/ethernet/amazon/ena/ena_xdp.c
index 337c435..5b175e7e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_xdp.c
+++ b/drivers/net/ethernet/amazon/ena/ena_xdp.c
@@ -89,7 +89,7 @@
rc = ena_xdp_tx_map_frame(tx_ring, tx_info, xdpf, &ena_tx_ctx);
if (unlikely(rc))
- return rc;
+ goto err;
ena_tx_ctx.req_id = req_id;
@@ -112,7 +112,9 @@
error_unmap_dma:
ena_unmap_tx_buff(tx_ring, tx_info);
+err:
tx_info->xdpf = NULL;
+
return rc;
}
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 9662ee7..536635e 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -593,6 +593,16 @@
pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY);
}
+void pdsc_pci_reset_thread(struct work_struct *work)
+{
+ struct pdsc *pdsc = container_of(work, struct pdsc, pci_reset_work);
+ struct pci_dev *pdev = pdsc->pdev;
+
+ pci_dev_get(pdev);
+ pci_reset_function(pdev);
+ pci_dev_put(pdev);
+}
+
static void pdsc_check_pci_health(struct pdsc *pdsc)
{
u8 fw_status;
@@ -607,7 +617,8 @@
if (fw_status != PDS_RC_BAD_PCI)
return;
- pci_reset_function(pdsc->pdev);
+ /* prevent deadlock between pdsc_reset_prepare and pdsc_health_thread */
+ queue_work(pdsc->wq, &pdsc->pci_reset_work);
}
void pdsc_health_thread(struct work_struct *work)
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 92d7657..a3e17a0 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -197,6 +197,7 @@
struct pdsc_qcq notifyqcq;
u64 last_eid;
struct pdsc_viftype *viftype_status;
+ struct work_struct pci_reset_work;
};
/** enum pds_core_dbell_bits - bitwise composition of dbell values.
@@ -313,5 +314,6 @@
void pdsc_fw_down(struct pdsc *pdsc);
void pdsc_fw_up(struct pdsc *pdsc);
+void pdsc_pci_reset_thread(struct work_struct *work);
#endif /* _PDSC_H_ */
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index e494e12..495ef4e 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -229,6 +229,9 @@
.reset.opcode = PDS_CORE_CMD_RESET,
};
+ if (!pdsc_is_fw_running(pdsc))
+ return 0;
+
return pdsc_devcmd(pdsc, &cmd, &comp, pdsc->devcmd_timeout);
}
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index ab6133e..660268f 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -239,6 +239,7 @@
snprintf(wq_name, sizeof(wq_name), "%s.%d", PDS_CORE_DRV_NAME, pdsc->uid);
pdsc->wq = create_singlethread_workqueue(wq_name);
INIT_WORK(&pdsc->health_work, pdsc_health_thread);
+ INIT_WORK(&pdsc->pci_reset_work, pdsc_pci_reset_thread);
timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
pdsc->wdtimer_period = PDSC_WATCHDOG_SECS * HZ;
diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
index 72ea97c..82768b0 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c
@@ -436,10 +436,8 @@
umac_wl(intf, 0x800, UMC_RX_MAX_PKT_SZ);
}
-static int bcmasp_tx_poll(struct napi_struct *napi, int budget)
+static int bcmasp_tx_reclaim(struct bcmasp_intf *intf)
{
- struct bcmasp_intf *intf =
- container_of(napi, struct bcmasp_intf, tx_napi);
struct bcmasp_intf_stats64 *stats = &intf->stats64;
struct device *kdev = &intf->parent->pdev->dev;
unsigned long read, released = 0;
@@ -482,10 +480,16 @@
DESC_RING_COUNT);
}
- /* Ensure all descriptors have been written to DRAM for the hardware
- * to see updated contents.
- */
- wmb();
+ return released;
+}
+
+static int bcmasp_tx_poll(struct napi_struct *napi, int budget)
+{
+ struct bcmasp_intf *intf =
+ container_of(napi, struct bcmasp_intf, tx_napi);
+ int released = 0;
+
+ released = bcmasp_tx_reclaim(intf);
napi_complete(&intf->tx_napi);
@@ -797,6 +801,7 @@
intf->tx_spb_dma_read = intf->tx_spb_dma_addr;
intf->tx_spb_index = 0;
intf->tx_spb_clean_index = 0;
+ memset(intf->tx_cbs, 0, sizeof(struct bcmasp_tx_cb) * DESC_RING_COUNT);
/* Make sure channels are disabled */
tx_spb_ctrl_wl(intf, 0x0, TX_SPB_CTRL_ENABLE);
@@ -885,6 +890,8 @@
} while (timeout-- > 0);
tx_spb_dma_wl(intf, 0x0, TX_SPB_DMA_FIFO_CTRL);
+ bcmasp_tx_reclaim(intf);
+
umac_enable_set(intf, UMC_CMD_TX_EN, 0);
phy_stop(dev->phydev);
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 3e4fb3c3..1be6d14 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -2009,12 +2009,14 @@
bp->flags |= B44_FLAG_TX_PAUSE;
else
bp->flags &= ~B44_FLAG_TX_PAUSE;
- if (bp->flags & B44_FLAG_PAUSE_AUTO) {
- b44_halt(bp);
- b44_init_rings(bp);
- b44_init_hw(bp, B44_FULL_RESET);
- } else {
- __b44_set_flow_ctrl(bp, bp->flags);
+ if (netif_running(dev)) {
+ if (bp->flags & B44_FLAG_PAUSE_AUTO) {
+ b44_halt(bp);
+ b44_init_rings(bp);
+ b44_init_hw(bp, B44_FULL_RESET);
+ } else {
+ __b44_set_flow_ctrl(bp, bp->flags);
+ }
}
spin_unlock_irq(&bp->lock);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 493b724..2c2ee79 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1778,7 +1778,7 @@
skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping);
if (!skb) {
bnxt_abort_tpa(cpr, idx, agg_bufs);
- cpr->sw_stats.rx.rx_oom_discards += 1;
+ cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
return NULL;
}
} else {
@@ -1788,7 +1788,7 @@
new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, GFP_ATOMIC);
if (!new_data) {
bnxt_abort_tpa(cpr, idx, agg_bufs);
- cpr->sw_stats.rx.rx_oom_discards += 1;
+ cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
return NULL;
}
@@ -1804,7 +1804,7 @@
if (!skb) {
skb_free_frag(data);
bnxt_abort_tpa(cpr, idx, agg_bufs);
- cpr->sw_stats.rx.rx_oom_discards += 1;
+ cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
return NULL;
}
skb_reserve(skb, bp->rx_offset);
@@ -1815,7 +1815,7 @@
skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true);
if (!skb) {
/* Page reuse already handled by bnxt_rx_pages(). */
- cpr->sw_stats.rx.rx_oom_discards += 1;
+ cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
return NULL;
}
}
@@ -2094,11 +2094,8 @@
u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
cp_cons, agg_bufs,
false);
- if (!frag_len) {
- cpr->sw_stats.rx.rx_oom_discards += 1;
- rc = -ENOMEM;
- goto next_rx;
- }
+ if (!frag_len)
+ goto oom_next_rx;
}
xdp_active = true;
}
@@ -2121,9 +2118,7 @@
else
bnxt_xdp_buff_frags_free(rxr, &xdp);
}
- cpr->sw_stats.rx.rx_oom_discards += 1;
- rc = -ENOMEM;
- goto next_rx;
+ goto oom_next_rx;
}
} else {
u32 payload;
@@ -2134,29 +2129,21 @@
payload = 0;
skb = bp->rx_skb_func(bp, rxr, cons, data, data_ptr, dma_addr,
payload | len);
- if (!skb) {
- cpr->sw_stats.rx.rx_oom_discards += 1;
- rc = -ENOMEM;
- goto next_rx;
- }
+ if (!skb)
+ goto oom_next_rx;
}
if (agg_bufs) {
if (!xdp_active) {
skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false);
- if (!skb) {
- cpr->sw_stats.rx.rx_oom_discards += 1;
- rc = -ENOMEM;
- goto next_rx;
- }
+ if (!skb)
+ goto oom_next_rx;
} else {
skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1);
if (!skb) {
/* we should be able to free the old skb here */
bnxt_xdp_buff_frags_free(rxr, &xdp);
- cpr->sw_stats.rx.rx_oom_discards += 1;
- rc = -ENOMEM;
- goto next_rx;
+ goto oom_next_rx;
}
}
}
@@ -2234,6 +2221,11 @@
*raw_cons = tmp_raw_cons;
return rc;
+
+oom_next_rx:
+ cpr->bnapi->cp_ring.sw_stats.rx.rx_oom_discards += 1;
+ rc = -ENOMEM;
+ goto next_rx;
}
/* In netpoll mode, if we are using a combined completion ring, we need to
@@ -2280,7 +2272,7 @@
}
rc = bnxt_rx_pkt(bp, cpr, raw_cons, event);
if (rc && rc != -EBUSY)
- cpr->sw_stats.rx.rx_netpoll_discards += 1;
+ cpr->bnapi->cp_ring.sw_stats.rx.rx_netpoll_discards += 1;
return rc;
}
@@ -9089,7 +9081,7 @@
BNXT_FW_HEALTH_WIN_BASE +
BNXT_GRC_REG_CHIP_NUM);
}
- if (!BNXT_CHIP_P5(bp))
+ if (!BNXT_CHIP_P5_PLUS(bp))
return;
status_loc = BNXT_GRC_REG_STATUS_P5 |
@@ -11758,6 +11750,8 @@
/* VF-reps may need to be re-opened after the PF is re-opened */
if (BNXT_PF(bp))
bnxt_vf_reps_open(bp);
+ if (bp->ptp_cfg)
+ atomic_set(&bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
bnxt_ptp_init_rtc(bp, true);
bnxt_ptp_cfg_tstamp_filters(bp);
bnxt_cfg_usr_fltrs(bp);
@@ -13035,6 +13029,16 @@
bnxt_rtnl_unlock_sp(bp);
}
+static void bnxt_fw_fatal_close(struct bnxt *bp)
+{
+ bnxt_tx_disable(bp);
+ bnxt_disable_napi(bp);
+ bnxt_disable_int_sync(bp);
+ bnxt_free_irq(bp);
+ bnxt_clear_int_mode(bp);
+ pci_disable_device(bp->pdev);
+}
+
static void bnxt_fw_reset_close(struct bnxt *bp)
{
bnxt_ulp_stop(bp);
@@ -13048,12 +13052,7 @@
pci_read_config_word(bp->pdev, PCI_SUBSYSTEM_ID, &val);
if (val == 0xffff)
bp->fw_reset_min_dsecs = 0;
- bnxt_tx_disable(bp);
- bnxt_disable_napi(bp);
- bnxt_disable_int_sync(bp);
- bnxt_free_irq(bp);
- bnxt_clear_int_mode(bp);
- pci_disable_device(bp->pdev);
+ bnxt_fw_fatal_close(bp);
}
__bnxt_close_nic(bp, true, false);
bnxt_vf_reps_free(bp);
@@ -15371,6 +15370,7 @@
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct bnxt *bp = netdev_priv(netdev);
+ bool abort = false;
netdev_info(netdev, "PCI I/O error detected\n");
@@ -15379,16 +15379,27 @@
bnxt_ulp_stop(bp);
- if (state == pci_channel_io_perm_failure) {
+ if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
+ netdev_err(bp->dev, "Firmware reset already in progress\n");
+ abort = true;
+ }
+
+ if (abort || state == pci_channel_io_perm_failure) {
rtnl_unlock();
return PCI_ERS_RESULT_DISCONNECT;
}
- if (state == pci_channel_io_frozen)
+ /* Link is not reliable anymore if state is pci_channel_io_frozen
+ * so we disable bus master to prevent any potential bad DMAs before
+ * freeing kernel memory.
+ */
+ if (state == pci_channel_io_frozen) {
set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state);
+ bnxt_fw_fatal_close(bp);
+ }
if (netif_running(netdev))
- bnxt_close(netdev);
+ __bnxt_close_nic(bp, true, true);
if (pci_is_enabled(pdev))
pci_disable_device(pdev);
@@ -15472,6 +15483,7 @@
}
reset_exit:
+ clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
bnxt_clear_reservations(bp, true);
rtnl_unlock();
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 93f9bd5..195c02d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -210,6 +210,9 @@
if (err)
return;
+ if (edev->ulp_tbl->msix_requested)
+ bnxt_fill_msix_vecs(bp, edev->msix_entries);
+
if (aux_priv) {
struct auxiliary_device *adev;
@@ -392,12 +395,13 @@
if (!edev)
goto aux_dev_uninit;
+ aux_priv->edev = edev;
+
ulp = kzalloc(sizeof(*ulp), GFP_KERNEL);
if (!ulp)
goto aux_dev_uninit;
edev->ulp_tbl = ulp;
- aux_priv->edev = edev;
bp->edev = edev;
bnxt_set_edev_info(edev, bp);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index b1f84b3..c7e7dac 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2,7 +2,7 @@
/*
* Broadcom GENET (Gigabit Ethernet) controller driver
*
- * Copyright (c) 2014-2020 Broadcom
+ * Copyright (c) 2014-2024 Broadcom
*/
#define pr_fmt(fmt) "bcmgenet: " fmt
@@ -2467,14 +2467,18 @@
{
u32 reg;
+ spin_lock_bh(&priv->reg_lock);
reg = bcmgenet_umac_readl(priv, UMAC_CMD);
- if (reg & CMD_SW_RESET)
+ if (reg & CMD_SW_RESET) {
+ spin_unlock_bh(&priv->reg_lock);
return;
+ }
if (enable)
reg |= mask;
else
reg &= ~mask;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ spin_unlock_bh(&priv->reg_lock);
/* UniMAC stops on a packet boundary, wait for a full-size packet
* to be processed
@@ -2490,8 +2494,10 @@
udelay(10);
/* issue soft reset and disable MAC while updating its registers */
+ spin_lock_bh(&priv->reg_lock);
bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD);
udelay(2);
+ spin_unlock_bh(&priv->reg_lock);
}
static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
@@ -3334,7 +3340,9 @@
struct bcmgenet_priv *priv = netdev_priv(dev);
/* Start the network engine */
+ netif_addr_lock_bh(dev);
bcmgenet_set_rx_mode(dev);
+ netif_addr_unlock_bh(dev);
bcmgenet_enable_rx_napi(priv);
umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true);
@@ -3595,16 +3603,19 @@
* 3. The number of filters needed exceeds the number filters
* supported by the hardware.
*/
+ spin_lock(&priv->reg_lock);
reg = bcmgenet_umac_readl(priv, UMAC_CMD);
if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) ||
(nfilter > MAX_MDF_FILTER)) {
reg |= CMD_PROMISC;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ spin_unlock(&priv->reg_lock);
bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL);
return;
} else {
reg &= ~CMD_PROMISC;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ spin_unlock(&priv->reg_lock);
}
/* update MDF filter */
@@ -4003,6 +4014,7 @@
goto err;
}
+ spin_lock_init(&priv->reg_lock);
spin_lock_init(&priv->lock);
/* Set default pause parameters */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 7523b60..43b923c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * Copyright (c) 2014-2020 Broadcom
+ * Copyright (c) 2014-2024 Broadcom
*/
#ifndef __BCMGENET_H__
@@ -573,6 +573,8 @@
/* device context */
struct bcmgenet_priv {
void __iomem *base;
+ /* reg_lock: lock to serialize access to shared registers */
+ spinlock_t reg_lock;
enum bcmgenet_version version;
struct net_device *dev;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 7a41cad..1248792 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -2,7 +2,7 @@
/*
* Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
*
- * Copyright (c) 2014-2020 Broadcom
+ * Copyright (c) 2014-2024 Broadcom
*/
#define pr_fmt(fmt) "bcmgenet_wol: " fmt
@@ -151,6 +151,7 @@
}
/* Can't suspend with WoL if MAC is still in reset */
+ spin_lock_bh(&priv->reg_lock);
reg = bcmgenet_umac_readl(priv, UMAC_CMD);
if (reg & CMD_SW_RESET)
reg &= ~CMD_SW_RESET;
@@ -158,6 +159,7 @@
/* disable RX */
reg &= ~CMD_RX_EN;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ spin_unlock_bh(&priv->reg_lock);
mdelay(10);
if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
@@ -203,6 +205,7 @@
}
/* Enable CRC forward */
+ spin_lock_bh(&priv->reg_lock);
reg = bcmgenet_umac_readl(priv, UMAC_CMD);
priv->crc_fwd_en = 1;
reg |= CMD_CRC_FWD;
@@ -210,6 +213,7 @@
/* Receiver must be enabled for WOL MP detection */
reg |= CMD_RX_EN;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ spin_unlock_bh(&priv->reg_lock);
reg = UMAC_IRQ_MPD_R;
if (hfb_enable)
@@ -256,7 +260,9 @@
}
/* Disable CRC Forward */
+ spin_lock_bh(&priv->reg_lock);
reg = bcmgenet_umac_readl(priv, UMAC_CMD);
reg &= ~CMD_CRC_FWD;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ spin_unlock_bh(&priv->reg_lock);
}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 9ada893..c4a3698 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -2,7 +2,7 @@
/*
* Broadcom GENET MDIO routines
*
- * Copyright (c) 2014-2017 Broadcom
+ * Copyright (c) 2014-2024 Broadcom
*/
#include <linux/acpi.h>
@@ -76,6 +76,7 @@
reg |= RGMII_LINK;
bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
+ spin_lock_bh(&priv->reg_lock);
reg = bcmgenet_umac_readl(priv, UMAC_CMD);
reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) |
CMD_HD_EN |
@@ -88,6 +89,7 @@
reg |= CMD_TX_EN | CMD_RX_EN;
}
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+ spin_unlock_bh(&priv->reg_lock);
active = phy_init_eee(phydev, 0) >= 0;
bcmgenet_eee_enable_set(dev,
@@ -275,6 +277,7 @@
* block for the interface to work, unconditionally clear the
* Out-of-band disable since we do not need it.
*/
+ mutex_lock(&phydev->lock);
reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
reg &= ~OOB_DISABLE;
if (priv->ext_phy) {
@@ -286,6 +289,7 @@
reg |= RGMII_MODE_EN;
}
bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
+ mutex_unlock(&phydev->lock);
if (init)
dev_info(kdev, "configuring instance for %s\n", phy_name);
diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
index 7246e13..97291bf 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c
@@ -312,7 +312,7 @@
void *kern_buf;
/* Copy the user space buf */
- kern_buf = memdup_user(buf, nbytes);
+ kern_buf = memdup_user_nul(buf, nbytes);
if (IS_ERR(kern_buf))
return PTR_ERR(kern_buf);
@@ -372,7 +372,7 @@
void *kern_buf;
/* Copy the user space buf */
- kern_buf = memdup_user(buf, nbytes);
+ kern_buf = memdup_user_nul(buf, nbytes);
if (IS_ERR(kern_buf))
return PTR_ERR(kern_buf);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 49d5808..de52bcb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2670,12 +2670,12 @@
lb->loopback = 1;
q = &adap->sge.ethtxq[pi->first_qset];
- __netif_tx_lock(q->txq, smp_processor_id());
+ __netif_tx_lock_bh(q->txq);
reclaim_completed_tx(adap, &q->q, -1, true);
credits = txq_avail(&q->q) - ndesc;
if (unlikely(credits < 0)) {
- __netif_tx_unlock(q->txq);
+ __netif_tx_unlock_bh(q->txq);
return -ENOMEM;
}
@@ -2710,7 +2710,7 @@
init_completion(&lb->completion);
txq_advance(&q->q, ndesc);
cxgb4_ring_tx_db(adap, &q->q, ndesc);
- __netif_tx_unlock(q->txq);
+ __netif_tx_unlock_bh(q->txq);
/* wait for the pkt to return */
ret = wait_for_completion_timeout(&lb->completion, 10 * HZ);
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index 93544f1..f7ae0e0a 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -157,7 +157,7 @@
* the lower time out
*/
for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) {
- usleep_range(50, 60);
+ udelay(50);
mdic = er32(MDIC);
if (mdic & E1000_MDIC_READY)
break;
@@ -181,7 +181,7 @@
* reading duplicate data in the next MDIC transaction.
*/
if (hw->mac.type == e1000_pch2lan)
- usleep_range(100, 150);
+ udelay(100);
if (success) {
*data = (u16)mdic;
@@ -237,7 +237,7 @@
* the lower time out
*/
for (i = 0; i < (E1000_GEN_POLL_TIMEOUT * 3); i++) {
- usleep_range(50, 60);
+ udelay(50);
mdic = er32(MDIC);
if (mdic & E1000_MDIC_READY)
break;
@@ -261,7 +261,7 @@
* reading duplicate data in the next MDIC transaction.
*/
if (hw->mac.type == e1000_pch2lan)
- usleep_range(100, 150);
+ udelay(100);
if (success)
return 0;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 48b9ddb..ffb9f9f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -16107,8 +16107,8 @@
val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK,
rd32(&pf->hw, I40E_PRTGL_SAH));
if (val < MAX_FRAME_SIZE_DEFAULT)
- dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n",
- pf->hw.port, val);
+ dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n",
+ pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT);
/* Add a filter to drop all Flow control frames from any VSI from being
* transmitted. By doing so we stop a malicious VF from sending out
@@ -16650,7 +16650,7 @@
* since we need to be able to guarantee forward progress even under
* memory pressure.
*/
- i40e_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, i40e_driver_name);
+ i40e_wq = alloc_workqueue("%s", 0, 0, i40e_driver_name);
if (!i40e_wq) {
pr_err("%s: Failed to create workqueue\n", i40e_driver_name);
return -ENOMEM;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index ef2440f..166832a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3503,6 +3503,34 @@
}
/**
+ * iavf_is_tc_config_same - Compare the mqprio TC config with the
+ * TC config already configured on this adapter.
+ * @adapter: board private structure
+ * @mqprio_qopt: TC config received from kernel.
+ *
+ * This function compares the TC config received from the kernel
+ * with the config already configured on the adapter.
+ *
+ * Return: True if configuration is same, false otherwise.
+ **/
+static bool iavf_is_tc_config_same(struct iavf_adapter *adapter,
+ struct tc_mqprio_qopt *mqprio_qopt)
+{
+ struct virtchnl_channel_info *ch = &adapter->ch_config.ch_info[0];
+ int i;
+
+ if (adapter->num_tc != mqprio_qopt->num_tc)
+ return false;
+
+ for (i = 0; i < adapter->num_tc; i++) {
+ if (ch[i].count != mqprio_qopt->count[i] ||
+ ch[i].offset != mqprio_qopt->offset[i])
+ return false;
+ }
+ return true;
+}
+
+/**
* __iavf_setup_tc - configure multiple traffic classes
* @netdev: network interface device structure
* @type_data: tc offload data
@@ -3559,7 +3587,7 @@
if (ret)
return ret;
/* Return if same TC config is requested */
- if (adapter->num_tc == num_tc)
+ if (iavf_is_tc_config_same(adapter, &mqprio_qopt->qopt))
return 0;
adapter->num_tc = num_tc;
diff --git a/drivers/net/ethernet/intel/ice/ice_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c
index d252d98..9fc0fd9 100644
--- a/drivers/net/ethernet/intel/ice/ice_debugfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c
@@ -171,7 +171,7 @@
if (*ppos != 0 || count > 8)
return -EINVAL;
- cmd_buf = memdup_user(buf, count);
+ cmd_buf = memdup_user_nul(buf, count);
if (IS_ERR(cmd_buf))
return PTR_ERR(cmd_buf);
@@ -257,7 +257,7 @@
if (*ppos != 0 || count > 4)
return -EINVAL;
- cmd_buf = memdup_user(buf, count);
+ cmd_buf = memdup_user_nul(buf, count);
if (IS_ERR(cmd_buf))
return PTR_ERR(cmd_buf);
@@ -332,7 +332,7 @@
if (*ppos != 0 || count > 2)
return -EINVAL;
- cmd_buf = memdup_user(buf, count);
+ cmd_buf = memdup_user_nul(buf, count);
if (IS_ERR(cmd_buf))
return PTR_ERR(cmd_buf);
@@ -428,7 +428,7 @@
if (*ppos != 0 || count > 5)
return -EINVAL;
- cmd_buf = memdup_user(buf, count);
+ cmd_buf = memdup_user_nul(buf, count);
if (IS_ERR(cmd_buf))
return PTR_ERR(cmd_buf);
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index b890410..688ccb0 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -28,6 +28,8 @@
* - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified)
* - Tunnel flag (present if tunnel)
*/
+ if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS)
+ lkups_cnt++;
if (flags & ICE_TC_FLWR_FIELD_TENANT_ID)
lkups_cnt++;
@@ -363,6 +365,11 @@
/* Always add direction metadata */
ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]);
+ if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) {
+ ice_rule_add_src_vsi_metadata(&list[i]);
+ i++;
+ }
+
rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type);
if (tc_fltr->tunnel_type != TNL_LAST) {
i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i);
@@ -772,7 +779,7 @@
int ret;
int i;
- if (!flags || (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT)) {
+ if (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT) {
NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)");
return -EOPNOTSUPP;
}
@@ -820,6 +827,7 @@
/* specify the cookie as filter_rule_id */
rule_info.fltr_rule_id = fltr->cookie;
+ rule_info.src_vsi = vsi->idx;
ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added);
if (ret == -EEXIST) {
@@ -1481,7 +1489,10 @@
(BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) |
BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) |
BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) |
- BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) {
+ BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) |
+ BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) |
+ BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) |
+ BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL))) {
NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel");
return -EOPNOTSUPP;
} else {
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 21d26e193..d10a4be 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -856,6 +856,11 @@
return 0;
}
+ if (flags & ICE_VF_RESET_LOCK)
+ mutex_lock(&vf->cfg_lock);
+ else
+ lockdep_assert_held(&vf->cfg_lock);
+
lag = pf->lag;
mutex_lock(&pf->lag_mutex);
if (lag && lag->bonded && lag->primary) {
@@ -867,11 +872,6 @@
act_prt = ICE_LAG_INVALID_PORT;
}
- if (flags & ICE_VF_RESET_LOCK)
- mutex_lock(&vf->cfg_lock);
- else
- lockdep_assert_held(&vf->cfg_lock);
-
if (ice_is_vf_disabled(vf)) {
vsi = ice_get_vf_vsi(vf);
if (!vsi) {
@@ -956,14 +956,14 @@
ice_mbx_clear_malvf(&vf->mbx_info);
out_unlock:
- if (flags & ICE_VF_RESET_LOCK)
- mutex_unlock(&vf->cfg_lock);
-
if (lag && lag->bonded && lag->primary &&
act_prt != ICE_LAG_INVALID_PORT)
ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt);
mutex_unlock(&pf->lag_mutex);
+ if (flags & ICE_VF_RESET_LOCK)
+ mutex_unlock(&vf->cfg_lock);
+
return err;
}
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 90316dc..6bc56c7 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -298,6 +298,7 @@
/* LEDs */
struct mutex led_mutex;
+ struct igc_led_classdev *leds;
};
void igc_up(struct igc_adapter *adapter);
@@ -723,6 +724,7 @@
void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter);
int igc_led_setup(struct igc_adapter *adapter);
+void igc_led_free(struct igc_adapter *adapter);
#define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring))
diff --git a/drivers/net/ethernet/intel/igc/igc_leds.c b/drivers/net/ethernet/intel/igc/igc_leds.c
index bf240c5..3929b25 100644
--- a/drivers/net/ethernet/intel/igc/igc_leds.c
+++ b/drivers/net/ethernet/intel/igc/igc_leds.c
@@ -236,8 +236,8 @@
pci_dev_id(adapter->pdev), index);
}
-static void igc_setup_ldev(struct igc_led_classdev *ldev,
- struct net_device *netdev, int index)
+static int igc_setup_ldev(struct igc_led_classdev *ldev,
+ struct net_device *netdev, int index)
{
struct igc_adapter *adapter = netdev_priv(netdev);
struct led_classdev *led_cdev = &ldev->led;
@@ -257,24 +257,46 @@
led_cdev->hw_control_get = igc_led_hw_control_get;
led_cdev->hw_control_get_device = igc_led_hw_control_get_device;
- devm_led_classdev_register(&netdev->dev, led_cdev);
+ return led_classdev_register(&netdev->dev, led_cdev);
}
int igc_led_setup(struct igc_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
- struct device *dev = &netdev->dev;
struct igc_led_classdev *leds;
- int i;
+ int i, err;
mutex_init(&adapter->led_mutex);
- leds = devm_kcalloc(dev, IGC_NUM_LEDS, sizeof(*leds), GFP_KERNEL);
+ leds = kcalloc(IGC_NUM_LEDS, sizeof(*leds), GFP_KERNEL);
if (!leds)
return -ENOMEM;
- for (i = 0; i < IGC_NUM_LEDS; i++)
- igc_setup_ldev(leds + i, netdev, i);
+ for (i = 0; i < IGC_NUM_LEDS; i++) {
+ err = igc_setup_ldev(leds + i, netdev, i);
+ if (err)
+ goto err;
+ }
+
+ adapter->leds = leds;
return 0;
+
+err:
+ for (i--; i >= 0; i--)
+ led_classdev_unregister(&((leds + i)->led));
+
+ kfree(leds);
+ return err;
+}
+
+void igc_led_free(struct igc_adapter *adapter)
+{
+ struct igc_led_classdev *leds = adapter->leds;
+ int i;
+
+ for (i = 0; i < IGC_NUM_LEDS; i++)
+ led_classdev_unregister(&((leds + i)->led));
+
+ kfree(leds);
}
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 35ad40a..4d975d6 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -7021,6 +7021,9 @@
cancel_work_sync(&adapter->watchdog_task);
hrtimer_cancel(&adapter->hrtimer);
+ if (IS_ENABLED(CONFIG_IGC_LEDS))
+ igc_led_free(adapter);
+
/* Release control of h/w to f/w. If f/w is AMT enabled, this
* would have already happened in close and is redundant.
*/
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 2500f5b..881d704 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -999,12 +999,10 @@
u16 pcifunc;
int ret, lf;
- cmd_buf = memdup_user(buffer, count + 1);
+ cmd_buf = memdup_user_nul(buffer, count);
if (IS_ERR(cmd_buf))
return -ENOMEM;
- cmd_buf[count] = '\0';
-
cmd_buf_tmp = strchr(cmd_buf, '\n');
if (cmd_buf_tmp) {
*cmd_buf_tmp = '\0';
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index d39001c..00af888 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -4819,19 +4819,19 @@
*/
rvu_write64(rvu, blkaddr, NIX_AF_CFG,
rvu_read64(rvu, blkaddr, NIX_AF_CFG) | 0x40ULL);
-
- /* Set chan/link to backpressure TL3 instead of TL2 */
- rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01);
-
- /* Disable SQ manager's sticky mode operation (set TM6 = 0)
- * This sticky mode is known to cause SQ stalls when multiple
- * SQs are mapped to same SMQ and transmitting pkts at a time.
- */
- cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS);
- cfg &= ~BIT_ULL(15);
- rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg);
}
+ /* Set chan/link to backpressure TL3 instead of TL2 */
+ rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01);
+
+ /* Disable SQ manager's sticky mode operation (set TM6 = 0)
+ * This sticky mode is known to cause SQ stalls when multiple
+ * SQs are mapped to same SMQ and transmitting pkts at a time.
+ */
+ cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS);
+ cfg &= ~BIT_ULL(15);
+ rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg);
+
ltdefs = rvu->kpu.lt_def;
/* Calibrate X2P bus to check if CGX/LBK links are fine */
err = nix_calibrate_x2p(rvu, blkaddr);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index be709f8..e8b73b9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -2181,7 +2181,6 @@
kfree(pkind->rsrc.bmap);
npc_mcam_rsrcs_deinit(rvu);
- kfree(mcam->counters.bmap);
if (rvu->kpu_prfl_addr)
iounmap(rvu->kpu_prfl_addr);
else
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 87bdb93..f4655a8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -689,6 +689,7 @@
if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
struct flow_match_control match;
+ u32 val;
flow_rule_match_control(rule, &match);
if (match.mask->flags & FLOW_DIS_FIRST_FRAG) {
@@ -697,12 +698,14 @@
}
if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) {
+ val = match.key->flags & FLOW_DIS_IS_FRAGMENT;
if (ntohs(flow_spec->etype) == ETH_P_IP) {
- flow_spec->ip_flag = IPV4_FLAG_MORE;
+ flow_spec->ip_flag = val ? IPV4_FLAG_MORE : 0;
flow_mask->ip_flag = IPV4_FLAG_MORE;
req->features |= BIT_ULL(NPC_IPFRAG_IPV4);
} else if (ntohs(flow_spec->etype) == ETH_P_IPV6) {
- flow_spec->next_header = IPPROTO_FRAGMENT;
+ flow_spec->next_header = val ?
+ IPPROTO_FRAGMENT : 0;
flow_mask->next_header = 0xff;
req->features |= BIT_ULL(NPC_IPFRAG_IPV6);
} else {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 1e77bbf..1723e99 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -382,6 +382,7 @@
otx2_qos_read_txschq_cfg_tl(node, cfg);
cnt = cfg->static_node_pos[node->level];
cfg->schq_contig_list[node->level][cnt] = node->schq;
+ cfg->schq_index_used[node->level][cnt] = true;
cfg->schq_contig[node->level]++;
cfg->static_node_pos[node->level]++;
otx2_qos_read_txschq_cfg_schq(node, cfg);
diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
index c895e26..61334a7 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed.c
@@ -1074,13 +1074,13 @@
static void
mtk_wed_stop(struct mtk_wed_device *dev)
{
+ mtk_wed_dma_disable(dev);
mtk_wed_set_ext_int(dev, false);
wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER, 0);
wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, 0);
wdma_w32(dev, MTK_WDMA_INT_MASK, 0);
wdma_w32(dev, MTK_WDMA_INT_GRP2, 0);
- wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0);
if (!mtk_wed_get_rx_capa(dev))
return;
@@ -1093,7 +1093,6 @@
mtk_wed_deinit(struct mtk_wed_device *dev)
{
mtk_wed_stop(dev);
- mtk_wed_dma_disable(dev);
wed_clr(dev, MTK_WED_CTRL,
MTK_WED_CTRL_WDMA_INT_AGENT_EN |
@@ -2605,9 +2604,6 @@
static void
mtk_wed_irq_set_mask(struct mtk_wed_device *dev, u32 mask)
{
- if (!dev->running)
- return;
-
mtk_wed_set_ext_int(dev, !!mask);
wed_w32(dev, MTK_WED_INT_MASK, mask);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 86f1854..883c044 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -95,9 +95,15 @@
}
static inline u8
+mlx5e_ptp_metadata_fifo_peek(struct mlx5e_ptp_metadata_fifo *fifo)
+{
+ return fifo->data[fifo->mask & fifo->cc];
+}
+
+static inline void
mlx5e_ptp_metadata_fifo_pop(struct mlx5e_ptp_metadata_fifo *fifo)
{
- return fifo->data[fifo->mask & fifo->cc++];
+ fifo->cc++;
}
static inline void
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index e87e26f..6743806 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -83,24 +83,25 @@
txq_ix = mlx5e_qid_from_qos(chs, node_qid);
- WARN_ON(node_qid > priv->htb_max_qos_sqs);
- if (node_qid == priv->htb_max_qos_sqs) {
- struct mlx5e_sq_stats *stats, **stats_list = NULL;
+ WARN_ON(node_qid >= mlx5e_htb_cur_leaf_nodes(priv->htb));
+ if (!priv->htb_qos_sq_stats) {
+ struct mlx5e_sq_stats **stats_list;
- if (priv->htb_max_qos_sqs == 0) {
- stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev),
- sizeof(*stats_list),
- GFP_KERNEL);
- if (!stats_list)
- return -ENOMEM;
- }
- stats = kzalloc(sizeof(*stats), GFP_KERNEL);
- if (!stats) {
- kvfree(stats_list);
+ stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev),
+ sizeof(*stats_list), GFP_KERNEL);
+ if (!stats_list)
return -ENOMEM;
- }
- if (stats_list)
- WRITE_ONCE(priv->htb_qos_sq_stats, stats_list);
+
+ WRITE_ONCE(priv->htb_qos_sq_stats, stats_list);
+ }
+
+ if (!priv->htb_qos_sq_stats[node_qid]) {
+ struct mlx5e_sq_stats *stats;
+
+ stats = kzalloc(sizeof(*stats), GFP_KERNEL);
+ if (!stats)
+ return -ENOMEM;
+
WRITE_ONCE(priv->htb_qos_sq_stats[node_qid], stats);
/* Order htb_max_qos_sqs increment after writing the array pointer.
* Pairs with smp_load_acquire in en_stats.c.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 0ab9db3..22918b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -108,7 +108,10 @@
mlx5e_reset_txqsq_cc_pc(sq);
sq->stats->recover++;
clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
+ rtnl_lock();
mlx5e_activate_txqsq(sq);
+ rtnl_unlock();
+
if (sq->channel)
mlx5e_trigger_napi_icosq(sq->channel);
else
@@ -179,12 +182,16 @@
carrier_ok = netif_carrier_ok(netdev);
netif_carrier_off(netdev);
+ rtnl_lock();
mlx5e_deactivate_priv_channels(priv);
+ rtnl_unlock();
mlx5e_ptp_close(chs->ptp);
err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp);
+ rtnl_lock();
mlx5e_activate_priv_channels(priv);
+ rtnl_unlock();
/* return carrier back if needed */
if (carrier_ok)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
index bcafb4b..8d9a3b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
@@ -179,6 +179,13 @@
return min_t(u32, rqt_size, max_cap_rqt_size);
}
+#define MLX5E_MAX_RQT_SIZE_ALLOWED_WITH_XOR8_HASH 256
+
+unsigned int mlx5e_rqt_max_num_channels_allowed_for_xor8(void)
+{
+ return MLX5E_MAX_RQT_SIZE_ALLOWED_WITH_XOR8_HASH / MLX5E_UNIFORM_SPREAD_RQT_FACTOR;
+}
+
void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt)
{
mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
index e0bc303..2f9e04a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
@@ -38,6 +38,7 @@
}
u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels);
+unsigned int mlx5e_rqt_max_num_channels_allowed_for_xor8(void);
int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id);
int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids,
unsigned int num_rqns,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c
index f675b19..f66bbc8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c
@@ -57,6 +57,7 @@
void mlx5e_selq_cleanup(struct mlx5e_selq *selq)
{
+ mutex_lock(selq->state_lock);
WARN_ON_ONCE(selq->is_prepared);
kvfree(selq->standby);
@@ -67,6 +68,7 @@
kvfree(selq->standby);
selq->standby = NULL;
+ mutex_unlock(selq->state_lock);
}
void mlx5e_selq_prepare_params(struct mlx5e_selq *selq, struct mlx5e_params *params)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index b2cabd6..cc9bcc4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -1640,6 +1640,7 @@
.mdo_add_secy = mlx5e_macsec_add_secy,
.mdo_upd_secy = mlx5e_macsec_upd_secy,
.mdo_del_secy = mlx5e_macsec_del_secy,
+ .rx_uses_md_dst = true,
};
bool mlx5e_macsec_handle_tx_skb(struct mlx5e_macsec *macsec, struct sk_buff *skb)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index c7f542d..93cf232 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -46,6 +46,10 @@
struct hlist_head rules_hash[ARFS_HASH_SIZE];
};
+enum {
+ MLX5E_ARFS_STATE_ENABLED,
+};
+
enum arfs_type {
ARFS_IPV4_TCP,
ARFS_IPV6_TCP,
@@ -60,6 +64,7 @@
spinlock_t arfs_lock;
int last_filter_id;
struct workqueue_struct *wq;
+ unsigned long state;
};
struct arfs_tuple {
@@ -170,6 +175,8 @@
return err;
}
}
+ set_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state);
+
return 0;
}
@@ -455,6 +462,8 @@
int i;
int j;
+ clear_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state);
+
spin_lock_bh(&arfs->arfs_lock);
mlx5e_for_each_arfs_rule(rule, htmp, arfs->arfs_tables, i, j) {
hlist_del_init(&rule->hlist);
@@ -627,17 +636,8 @@
struct mlx5_flow_handle *rule;
arfs = mlx5e_fs_get_arfs(priv->fs);
- mutex_lock(&priv->state_lock);
- if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
- spin_lock_bh(&arfs->arfs_lock);
- hlist_del(&arfs_rule->hlist);
- spin_unlock_bh(&arfs->arfs_lock);
-
- mutex_unlock(&priv->state_lock);
- kfree(arfs_rule);
- goto out;
- }
- mutex_unlock(&priv->state_lock);
+ if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state))
+ return;
if (!arfs_rule->rule) {
rule = arfs_add_rule(priv, arfs_rule);
@@ -753,6 +753,11 @@
return -EPROTONOSUPPORT;
spin_lock_bh(&arfs->arfs_lock);
+ if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) {
+ spin_unlock_bh(&arfs->arfs_lock);
+ return -EPERM;
+ }
+
arfs_rule = arfs_find_rule(arfs_t, &fk);
if (arfs_rule) {
if (arfs_rule->rxq == rxq_index || work_busy(&arfs_rule->arfs_work)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index cc51ce1..67a2982 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -451,6 +451,34 @@
mutex_lock(&priv->state_lock);
+ if (mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc == ETH_RSS_HASH_XOR) {
+ unsigned int xor8_max_channels = mlx5e_rqt_max_num_channels_allowed_for_xor8();
+
+ if (count > xor8_max_channels) {
+ err = -EINVAL;
+ netdev_err(priv->netdev, "%s: Requested number of channels (%d) exceeds the maximum allowed by the XOR8 RSS hfunc (%d)\n",
+ __func__, count, xor8_max_channels);
+ goto out;
+ }
+ }
+
+ /* If RXFH is configured, changing the channels number is allowed only if
+ * it does not require resizing the RSS table. This is because the previous
+ * configuration may no longer be compatible with the new RSS table.
+ */
+ if (netif_is_rxfh_configured(priv->netdev)) {
+ int cur_rqt_size = mlx5e_rqt_size(priv->mdev, cur_params->num_channels);
+ int new_rqt_size = mlx5e_rqt_size(priv->mdev, count);
+
+ if (new_rqt_size != cur_rqt_size) {
+ err = -EINVAL;
+ netdev_err(priv->netdev,
+ "%s: RXFH is configured, block changing channels number that affects RSS table size (new: %d, current: %d)\n",
+ __func__, new_rqt_size, cur_rqt_size);
+ goto out;
+ }
+ }
+
/* Don't allow changing the number of channels if HTB offload is active,
* because the numeration of the QoS SQs will change, while per-queue
* qdiscs are attached.
@@ -561,12 +589,12 @@
static void
mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
{
- struct mlx5_core_dev *mdev = priv->mdev;
int tc;
int i;
for (i = 0; i < priv->channels.num; ++i) {
struct mlx5e_channel *c = priv->channels.c[i];
+ struct mlx5_core_dev *mdev = c->mdev;
for (tc = 0; tc < c->num_tc; tc++) {
mlx5_core_modify_cq_moderation(mdev,
@@ -580,11 +608,11 @@
static void
mlx5e_set_priv_channels_rx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal)
{
- struct mlx5_core_dev *mdev = priv->mdev;
int i;
for (i = 0; i < priv->channels.num; ++i) {
struct mlx5e_channel *c = priv->channels.c[i];
+ struct mlx5_core_dev *mdev = c->mdev;
mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq,
coal->rx_coalesce_usecs,
@@ -1281,17 +1309,30 @@
struct mlx5e_priv *priv = netdev_priv(dev);
u32 *rss_context = &rxfh->rss_context;
u8 hfunc = rxfh->hfunc;
+ unsigned int count;
int err;
mutex_lock(&priv->state_lock);
+
+ count = priv->channels.params.num_channels;
+
+ if (hfunc == ETH_RSS_HASH_XOR) {
+ unsigned int xor8_max_channels = mlx5e_rqt_max_num_channels_allowed_for_xor8();
+
+ if (count > xor8_max_channels) {
+ err = -EINVAL;
+ netdev_err(priv->netdev, "%s: Cannot set RSS hash function to XOR, current number of channels (%d) exceeds the maximum allowed for XOR8 RSS hfunc (%d)\n",
+ __func__, count, xor8_max_channels);
+ goto unlock;
+ }
+ }
+
if (*rss_context && rxfh->rss_delete) {
err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context);
goto unlock;
}
if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
- unsigned int count = priv->channels.params.num_channels;
-
err = mlx5e_rx_res_rss_init(priv->rx_res, rss_context, count);
if (err)
goto unlock;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 91848ea..319930c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -209,8 +209,8 @@
*data,
mlx5e_devcom_event_mpv,
priv);
- if (IS_ERR_OR_NULL(priv->devcom))
- return -EOPNOTSUPP;
+ if (IS_ERR(priv->devcom))
+ return PTR_ERR(priv->devcom);
if (mlx5_core_is_mp_master(priv->mdev)) {
mlx5_devcom_send_event(priv->devcom, MPV_DEVCOM_MASTER_UP,
@@ -5726,9 +5726,7 @@
kfree(priv->tx_rates);
kfree(priv->txq2sq);
destroy_workqueue(priv->wq);
- mutex_lock(&priv->state_lock);
mlx5e_selq_cleanup(&priv->selq);
- mutex_unlock(&priv->state_lock);
free_cpumask_var(priv->scratchpad.cpumask);
for (i = 0; i < priv->htb_max_qos_sqs; i++)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 2fa076b..e21a3b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -398,6 +398,8 @@
(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) {
u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata);
+ mlx5e_ptp_metadata_fifo_pop(&sq->ptpsq->metadata_freelist);
+
mlx5e_skb_cb_hwtstamp_init(skb);
mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb,
metadata_index);
@@ -496,9 +498,6 @@
err_drop:
stats->dropped++;
- if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
- mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist,
- be32_to_cpu(eseg->flow_table_metadata));
dev_kfree_skb_any(skb);
mlx5e_tx_flush(sq);
}
@@ -657,7 +656,7 @@
{
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
eseg->flow_table_metadata =
- cpu_to_be32(mlx5e_ptp_metadata_fifo_pop(&ptpsq->metadata_freelist));
+ cpu_to_be32(mlx5e_ptp_metadata_fifo_peek(&ptpsq->metadata_freelist));
}
static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 3047d701..1789800 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1868,6 +1868,7 @@
if (err)
goto abort;
+ dev->priv.eswitch = esw;
err = esw_offloads_init(esw);
if (err)
goto reps_err;
@@ -1892,11 +1893,6 @@
esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
else
esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
- if (MLX5_ESWITCH_MANAGER(dev) &&
- mlx5_esw_vport_match_metadata_supported(esw))
- esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
-
- dev->priv.eswitch = esw;
BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);
esw_info(dev,
@@ -1908,6 +1904,7 @@
reps_err:
mlx5_esw_vports_cleanup(esw);
+ dev->priv.eswitch = NULL;
abort:
if (esw->work_queue)
destroy_workqueue(esw->work_queue);
@@ -1926,7 +1923,6 @@
esw_info(esw->dev, "cleanup\n");
- esw->dev->priv.eswitch = NULL;
destroy_workqueue(esw->work_queue);
WARN_ON(refcount_read(&esw->qos.refcnt));
mutex_destroy(&esw->state_lock);
@@ -1937,6 +1933,7 @@
mutex_destroy(&esw->offloads.encap_tbl_lock);
mutex_destroy(&esw->offloads.decap_tbl_lock);
esw_offloads_cleanup(esw);
+ esw->dev->priv.eswitch = NULL;
mlx5_esw_vports_cleanup(esw);
debugfs_remove_recursive(esw->debugfs_root);
devl_params_unregister(priv_to_devlink(esw->dev), mlx5_eswitch_params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index baaae62..844d3e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -43,6 +43,7 @@
#include "rdma.h"
#include "en.h"
#include "fs_core.h"
+#include "lib/mlx5.h"
#include "lib/devcom.h"
#include "lib/eq.h"
#include "lib/fs_chains.h"
@@ -2476,6 +2477,10 @@
if (err)
return err;
+ if (MLX5_ESWITCH_MANAGER(esw->dev) &&
+ mlx5_esw_vport_match_metadata_supported(esw))
+ esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
+
err = devl_params_register(priv_to_devlink(esw->dev),
esw_devlink_params,
ARRAY_SIZE(esw_devlink_params));
@@ -3055,7 +3060,7 @@
key,
mlx5_esw_offloads_devcom_event,
esw);
- if (IS_ERR_OR_NULL(esw->devcom))
+ if (IS_ERR(esw->devcom))
return;
mlx5_devcom_send_event(esw->devcom,
@@ -3707,6 +3712,12 @@
if (esw_mode_from_devlink(mode, &mlx5_mode))
return -EINVAL;
+ if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && mlx5_get_sd(esw->dev)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Can't change E-Switch mode to switchdev when multi-PF netdev (Socket Direct) is configured.");
+ return -EPERM;
+ }
+
mlx5_lag_disable_change(esw->dev);
err = mlx5_esw_try_lock(esw);
if (err < 0) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index e6bfa7e..cf085a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1664,6 +1664,16 @@
return err;
}
+static bool mlx5_pkt_reformat_cmp(struct mlx5_pkt_reformat *p1,
+ struct mlx5_pkt_reformat *p2)
+{
+ return p1->owner == p2->owner &&
+ (p1->owner == MLX5_FLOW_RESOURCE_OWNER_FW ?
+ p1->id == p2->id :
+ mlx5_fs_dr_action_get_pkt_reformat_id(p1) ==
+ mlx5_fs_dr_action_get_pkt_reformat_id(p2));
+}
+
static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
struct mlx5_flow_destination *d2)
{
@@ -1675,8 +1685,8 @@
((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ?
(d1->vport.vhca_id == d2->vport.vhca_id) : true) &&
((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
- (d1->vport.pkt_reformat->id ==
- d2->vport.pkt_reformat->id) : true)) ||
+ mlx5_pkt_reformat_cmp(d1->vport.pkt_reformat,
+ d2->vport.pkt_reformat) : true)) ||
(d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
d1->ft == d2->ft) ||
(d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
@@ -1808,8 +1818,9 @@
}
trace_mlx5_fs_set_fte(fte, false);
+ /* Link newly added rules into the tree. */
for (i = 0; i < handle->num_rules; i++) {
- if (refcount_read(&handle->rule[i]->node.refcount) == 1) {
+ if (!handle->rule[i]->node.parent) {
tree_add_node(&handle->rule[i]->node, &fte->node);
trace_mlx5_fs_add_rule(handle->rule[i]);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index d14459e..69d482f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -703,8 +703,10 @@
return err;
}
- if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags))
+ if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) {
mlx5_lag_port_sel_destroy(ldev);
+ ldev->buckets = 1;
+ }
if (mlx5_lag_has_drop_rule(ldev))
mlx5_lag_drop_rule_cleanup(ldev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
index e7d59cf..7b0766c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -220,7 +220,7 @@
struct mlx5_devcom_comp *comp;
if (IS_ERR_OR_NULL(devc))
- return NULL;
+ return ERR_PTR(-EINVAL);
mutex_lock(&comp_list_lock);
comp = devcom_component_get(devc, id, key, handler);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
index 5b28084..dd5d186 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
@@ -213,8 +213,8 @@
sd = mlx5_get_sd(dev);
devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP,
sd->group_id, NULL, dev);
- if (!devcom)
- return -ENOMEM;
+ if (IS_ERR(devcom))
+ return PTR_ERR(devcom);
sd->devcom = devcom;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c259362..331ce47 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -956,7 +956,7 @@
mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_HCA_PORTS,
mlx5_query_nic_system_image_guid(dev),
NULL, dev);
- if (IS_ERR_OR_NULL(dev->priv.hca_devcom_comp))
+ if (IS_ERR(dev->priv.hca_devcom_comp))
mlx5_core_err(dev, "Failed to register devcom HCA component\n");
}
@@ -1480,6 +1480,14 @@
if (err)
goto err_register;
+ err = mlx5_crdump_enable(dev);
+ if (err)
+ mlx5_core_err(dev, "mlx5_crdump_enable failed with error code %d\n", err);
+
+ err = mlx5_hwmon_dev_register(dev);
+ if (err)
+ mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err);
+
mutex_unlock(&dev->intf_state_mutex);
return 0;
@@ -1505,7 +1513,10 @@
int err;
devl_lock(devlink);
+ devl_register(devlink);
err = mlx5_init_one_devl_locked(dev);
+ if (err)
+ devl_unregister(devlink);
devl_unlock(devlink);
return err;
}
@@ -1517,6 +1528,8 @@
devl_lock(devlink);
mutex_lock(&dev->intf_state_mutex);
+ mlx5_hwmon_dev_unregister(dev);
+ mlx5_crdump_disable(dev);
mlx5_unregister_device(dev);
if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
@@ -1534,6 +1547,7 @@
mlx5_function_teardown(dev, true);
out:
mutex_unlock(&dev->intf_state_mutex);
+ devl_unregister(devlink);
devl_unlock(devlink);
}
@@ -1680,16 +1694,23 @@
}
devl_lock(devlink);
+ devl_register(devlink);
+
err = mlx5_devlink_params_register(priv_to_devlink(dev));
- devl_unlock(devlink);
if (err) {
mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err);
- goto query_hca_caps_err;
+ goto params_reg_err;
}
+ devl_unlock(devlink);
return 0;
+params_reg_err:
+ devl_unregister(devlink);
+ devl_unlock(devlink);
query_hca_caps_err:
+ devl_unregister(devlink);
+ devl_unlock(devlink);
mlx5_function_disable(dev, true);
out:
dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
@@ -1702,6 +1723,7 @@
devl_lock(devlink);
mlx5_devlink_params_unregister(priv_to_devlink(dev));
+ devl_unregister(devlink);
devl_unlock(devlink);
if (dev->state != MLX5_DEVICE_STATE_UP)
return;
@@ -1943,16 +1965,7 @@
goto err_init_one;
}
- err = mlx5_crdump_enable(dev);
- if (err)
- dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
-
- err = mlx5_hwmon_dev_register(dev);
- if (err)
- mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err);
-
pci_save_state(pdev);
- devlink_register(devlink);
return 0;
err_init_one:
@@ -1973,16 +1986,9 @@
struct devlink *devlink = priv_to_devlink(dev);
set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
- /* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using
- * devlink notify APIs.
- * Hence, we must drain them before unregistering the devlink.
- */
mlx5_drain_fw_reset(dev);
mlx5_drain_health_wq(dev);
- devlink_unregister(devlink);
mlx5_sriov_disable(pdev, false);
- mlx5_hwmon_dev_unregister(dev);
- mlx5_crdump_disable(dev);
mlx5_uninit_one(dev);
mlx5_pci_close(dev);
mlx5_mdev_uninit(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 4dcf995..6bac8ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -19,6 +19,7 @@
#define MLX5_IRQ_CTRL_SF_MAX 8
/* min num of vectors for SFs to be enabled */
#define MLX5_IRQ_VEC_COMP_BASE_SF 2
+#define MLX5_IRQ_VEC_COMP_BASE 1
#define MLX5_EQ_SHARE_IRQ_MAX_COMP (8)
#define MLX5_EQ_SHARE_IRQ_MAX_CTRL (UINT_MAX)
@@ -246,6 +247,7 @@
return;
}
+ vecidx -= MLX5_IRQ_VEC_COMP_BASE;
snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx);
}
@@ -585,7 +587,7 @@
struct mlx5_irq_table *table = mlx5_irq_table_get(dev);
struct mlx5_irq_pool *pool = table->pcif_pool;
struct irq_affinity_desc af_desc;
- int offset = 1;
+ int offset = MLX5_IRQ_VEC_COMP_BASE;
if (!pool->xa_num_irqs.max)
offset = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index bc863e1..7ebe712 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -75,7 +75,6 @@
goto peer_devlink_set_err;
}
- devlink_register(devlink);
return 0;
peer_devlink_set_err:
@@ -101,7 +100,6 @@
devlink = priv_to_devlink(mdev);
set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
mlx5_drain_health_wq(mdev);
- devlink_unregister(devlink);
if (mlx5_dev_is_lightweight(mdev))
mlx5_uninit_one_light(mdev);
else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
index 64f4cc2..030a577 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
@@ -205,12 +205,11 @@
}
static int
-dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id,
+dr_dump_rule_action_mem(struct seq_file *file, char *buff, const u64 rule_id,
struct mlx5dr_rule_action_member *action_mem)
{
struct mlx5dr_action *action = action_mem->action;
const u64 action_id = DR_DBG_PTR_TO_ID(action);
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
u64 hit_tbl_ptr, miss_tbl_ptr;
u32 hit_tbl_id, miss_tbl_id;
int ret;
@@ -488,10 +487,9 @@
}
static int
-dr_dump_rule_mem(struct seq_file *file, struct mlx5dr_ste *ste,
+dr_dump_rule_mem(struct seq_file *file, char *buff, struct mlx5dr_ste *ste,
bool is_rx, const u64 rule_id, u8 format_ver)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
char hw_ste_dump[DR_HEX_SIZE];
u32 mem_rec_type;
int ret;
@@ -522,7 +520,8 @@
}
static int
-dr_dump_rule_rx_tx(struct seq_file *file, struct mlx5dr_rule_rx_tx *rule_rx_tx,
+dr_dump_rule_rx_tx(struct seq_file *file, char *buff,
+ struct mlx5dr_rule_rx_tx *rule_rx_tx,
bool is_rx, const u64 rule_id, u8 format_ver)
{
struct mlx5dr_ste *ste_arr[DR_RULE_MAX_STES + DR_ACTION_MAX_STES];
@@ -533,7 +532,7 @@
return 0;
while (i--) {
- ret = dr_dump_rule_mem(file, ste_arr[i], is_rx, rule_id,
+ ret = dr_dump_rule_mem(file, buff, ste_arr[i], is_rx, rule_id,
format_ver);
if (ret < 0)
return ret;
@@ -542,7 +541,8 @@
return 0;
}
-static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule)
+static noinline_for_stack int
+dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule)
{
struct mlx5dr_rule_action_member *action_mem;
const u64 rule_id = DR_DBG_PTR_TO_ID(rule);
@@ -565,19 +565,19 @@
return ret;
if (rx->nic_matcher) {
- ret = dr_dump_rule_rx_tx(file, rx, true, rule_id, format_ver);
+ ret = dr_dump_rule_rx_tx(file, buff, rx, true, rule_id, format_ver);
if (ret < 0)
return ret;
}
if (tx->nic_matcher) {
- ret = dr_dump_rule_rx_tx(file, tx, false, rule_id, format_ver);
+ ret = dr_dump_rule_rx_tx(file, buff, tx, false, rule_id, format_ver);
if (ret < 0)
return ret;
}
list_for_each_entry(action_mem, &rule->rule_actions_list, list) {
- ret = dr_dump_rule_action_mem(file, rule_id, action_mem);
+ ret = dr_dump_rule_action_mem(file, buff, rule_id, action_mem);
if (ret < 0)
return ret;
}
@@ -586,10 +586,10 @@
}
static int
-dr_dump_matcher_mask(struct seq_file *file, struct mlx5dr_match_param *mask,
+dr_dump_matcher_mask(struct seq_file *file, char *buff,
+ struct mlx5dr_match_param *mask,
u8 criteria, const u64 matcher_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
char dump[DR_HEX_SIZE];
int ret;
@@ -681,10 +681,10 @@
}
static int
-dr_dump_matcher_builder(struct seq_file *file, struct mlx5dr_ste_build *builder,
+dr_dump_matcher_builder(struct seq_file *file, char *buff,
+ struct mlx5dr_ste_build *builder,
u32 index, bool is_rx, const u64 matcher_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
int ret;
ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH,
@@ -702,11 +702,10 @@
}
static int
-dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx,
+dr_dump_matcher_rx_tx(struct seq_file *file, char *buff, bool is_rx,
struct mlx5dr_matcher_rx_tx *matcher_rx_tx,
const u64 matcher_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
enum dr_dump_rec_type rec_type;
u64 s_icm_addr, e_icm_addr;
int i, ret;
@@ -731,7 +730,7 @@
return ret;
for (i = 0; i < matcher_rx_tx->num_of_builders; i++) {
- ret = dr_dump_matcher_builder(file,
+ ret = dr_dump_matcher_builder(file, buff,
&matcher_rx_tx->ste_builder[i],
i, is_rx, matcher_id);
if (ret < 0)
@@ -741,7 +740,7 @@
return 0;
}
-static int
+static noinline_for_stack int
dr_dump_matcher(struct seq_file *file, struct mlx5dr_matcher *matcher)
{
struct mlx5dr_matcher_rx_tx *rx = &matcher->rx;
@@ -763,19 +762,19 @@
if (ret)
return ret;
- ret = dr_dump_matcher_mask(file, &matcher->mask,
+ ret = dr_dump_matcher_mask(file, buff, &matcher->mask,
matcher->match_criteria, matcher_id);
if (ret < 0)
return ret;
if (rx->nic_tbl) {
- ret = dr_dump_matcher_rx_tx(file, true, rx, matcher_id);
+ ret = dr_dump_matcher_rx_tx(file, buff, true, rx, matcher_id);
if (ret < 0)
return ret;
}
if (tx->nic_tbl) {
- ret = dr_dump_matcher_rx_tx(file, false, tx, matcher_id);
+ ret = dr_dump_matcher_rx_tx(file, buff, false, tx, matcher_id);
if (ret < 0)
return ret;
}
@@ -803,11 +802,10 @@
}
static int
-dr_dump_table_rx_tx(struct seq_file *file, bool is_rx,
+dr_dump_table_rx_tx(struct seq_file *file, char *buff, bool is_rx,
struct mlx5dr_table_rx_tx *table_rx_tx,
const u64 table_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
enum dr_dump_rec_type rec_type;
u64 s_icm_addr;
int ret;
@@ -829,7 +827,8 @@
return 0;
}
-static int dr_dump_table(struct seq_file *file, struct mlx5dr_table *table)
+static noinline_for_stack int
+dr_dump_table(struct seq_file *file, struct mlx5dr_table *table)
{
struct mlx5dr_table_rx_tx *rx = &table->rx;
struct mlx5dr_table_rx_tx *tx = &table->tx;
@@ -848,14 +847,14 @@
return ret;
if (rx->nic_dmn) {
- ret = dr_dump_table_rx_tx(file, true, rx,
+ ret = dr_dump_table_rx_tx(file, buff, true, rx,
DR_DBG_PTR_TO_ID(table));
if (ret < 0)
return ret;
}
if (tx->nic_dmn) {
- ret = dr_dump_table_rx_tx(file, false, tx,
+ ret = dr_dump_table_rx_tx(file, buff, false, tx,
DR_DBG_PTR_TO_ID(table));
if (ret < 0)
return ret;
@@ -881,10 +880,10 @@
}
static int
-dr_dump_send_ring(struct seq_file *file, struct mlx5dr_send_ring *ring,
+dr_dump_send_ring(struct seq_file *file, char *buff,
+ struct mlx5dr_send_ring *ring,
const u64 domain_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
int ret;
ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH,
@@ -902,13 +901,13 @@
return 0;
}
-static noinline_for_stack int
+static int
dr_dump_domain_info_flex_parser(struct seq_file *file,
+ char *buff,
const char *flex_parser_name,
const u8 flex_parser_value,
const u64 domain_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
int ret;
ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH,
@@ -925,11 +924,11 @@
return 0;
}
-static noinline_for_stack int
-dr_dump_domain_info_caps(struct seq_file *file, struct mlx5dr_cmd_caps *caps,
+static int
+dr_dump_domain_info_caps(struct seq_file *file, char *buff,
+ struct mlx5dr_cmd_caps *caps,
const u64 domain_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
struct mlx5dr_cmd_vport_cap *vport_caps;
unsigned long i, vports_num;
int ret;
@@ -969,34 +968,35 @@
}
static int
-dr_dump_domain_info(struct seq_file *file, struct mlx5dr_domain_info *info,
+dr_dump_domain_info(struct seq_file *file, char *buff,
+ struct mlx5dr_domain_info *info,
const u64 domain_id)
{
int ret;
- ret = dr_dump_domain_info_caps(file, &info->caps, domain_id);
+ ret = dr_dump_domain_info_caps(file, buff, &info->caps, domain_id);
if (ret < 0)
return ret;
- ret = dr_dump_domain_info_flex_parser(file, "icmp_dw0",
+ ret = dr_dump_domain_info_flex_parser(file, buff, "icmp_dw0",
info->caps.flex_parser_id_icmp_dw0,
domain_id);
if (ret < 0)
return ret;
- ret = dr_dump_domain_info_flex_parser(file, "icmp_dw1",
+ ret = dr_dump_domain_info_flex_parser(file, buff, "icmp_dw1",
info->caps.flex_parser_id_icmp_dw1,
domain_id);
if (ret < 0)
return ret;
- ret = dr_dump_domain_info_flex_parser(file, "icmpv6_dw0",
+ ret = dr_dump_domain_info_flex_parser(file, buff, "icmpv6_dw0",
info->caps.flex_parser_id_icmpv6_dw0,
domain_id);
if (ret < 0)
return ret;
- ret = dr_dump_domain_info_flex_parser(file, "icmpv6_dw1",
+ ret = dr_dump_domain_info_flex_parser(file, buff, "icmpv6_dw1",
info->caps.flex_parser_id_icmpv6_dw1,
domain_id);
if (ret < 0)
@@ -1032,12 +1032,12 @@
if (ret)
return ret;
- ret = dr_dump_domain_info(file, &dmn->info, domain_id);
+ ret = dr_dump_domain_info(file, buff, &dmn->info, domain_id);
if (ret < 0)
return ret;
if (dmn->info.supp_sw_steering) {
- ret = dr_dump_send_ring(file, dmn->send_ring, domain_id);
+ ret = dr_dump_send_ring(file, buff, dmn->send_ring, domain_id);
if (ret < 0)
return ret;
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index e4d7739..4a79c0d7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -849,7 +849,7 @@
static const struct mlxsw_listener mlxsw_emad_rx_listener =
MLXSW_RXL(mlxsw_emad_rx_listener_func, ETHEMAD, TRAP_TO_CPU, false,
- EMAD, DISCARD);
+ EMAD, FORWARD);
static int mlxsw_emad_tlv_enable(struct mlxsw_core *mlxsw_core)
{
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 53b150b..6c06b05 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -1357,24 +1357,20 @@
.got_inactive = mlxsw_env_got_inactive,
};
-static int mlxsw_env_max_module_eeprom_len_query(struct mlxsw_env *mlxsw_env)
+static void mlxsw_env_max_module_eeprom_len_query(struct mlxsw_env *mlxsw_env)
{
char mcam_pl[MLXSW_REG_MCAM_LEN];
- bool mcia_128b_supported;
+ bool mcia_128b_supported = false;
int err;
mlxsw_reg_mcam_pack(mcam_pl,
MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES);
err = mlxsw_reg_query(mlxsw_env->core, MLXSW_REG(mcam), mcam_pl);
- if (err)
- return err;
-
- mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_MCIA_128B,
- &mcia_128b_supported);
+ if (!err)
+ mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_MCIA_128B,
+ &mcia_128b_supported);
mlxsw_env->max_eeprom_len = mcia_128b_supported ? 128 : 48;
-
- return 0;
}
int mlxsw_env_init(struct mlxsw_core *mlxsw_core,
@@ -1445,15 +1441,11 @@
if (err)
goto err_type_set;
- err = mlxsw_env_max_module_eeprom_len_query(env);
- if (err)
- goto err_eeprom_len_query;
-
+ mlxsw_env_max_module_eeprom_len_query(env);
env->line_cards[0]->active = true;
return 0;
-err_eeprom_len_query:
err_type_set:
mlxsw_env_module_event_disable(env, 0);
err_mlxsw_env_module_event_enable:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index af99bf1..f42a1b1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1530,7 +1530,7 @@
{
struct pci_dev *pdev = mlxsw_pci->pdev;
char mcam_pl[MLXSW_REG_MCAM_LEN];
- bool pci_reset_supported;
+ bool pci_reset_supported = false;
u32 sys_status;
int err;
@@ -1548,11 +1548,9 @@
mlxsw_reg_mcam_pack(mcam_pl,
MLXSW_REG_MCAM_FEATURE_GROUP_ENHANCED_FEATURES);
err = mlxsw_reg_query(mlxsw_pci->core, MLXSW_REG(mcam), mcam_pl);
- if (err)
- return err;
-
- mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET,
- &pci_reset_supported);
+ if (!err)
+ mlxsw_reg_mcam_unpack(mcam_pl, MLXSW_REG_MCAM_PCI_RESET,
+ &pci_reset_supported);
if (pci_reset_supported) {
pci_dbg(pdev, "Starting PCI reset flow\n");
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index f200527..92a406f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -10,6 +10,7 @@
#include <linux/netdevice.h>
#include <linux/mutex.h>
#include <linux/refcount.h>
+#include <linux/idr.h>
#include <net/devlink.h>
#include <trace/events/mlxsw.h>
@@ -58,41 +59,43 @@
static int mlxsw_sp_acl_tcam_region_id_get(struct mlxsw_sp_acl_tcam *tcam,
u16 *p_id)
{
- u16 id;
+ int id;
- id = find_first_zero_bit(tcam->used_regions, tcam->max_regions);
- if (id < tcam->max_regions) {
- __set_bit(id, tcam->used_regions);
- *p_id = id;
- return 0;
- }
- return -ENOBUFS;
+ id = ida_alloc_max(&tcam->used_regions, tcam->max_regions - 1,
+ GFP_KERNEL);
+ if (id < 0)
+ return id;
+
+ *p_id = id;
+
+ return 0;
}
static void mlxsw_sp_acl_tcam_region_id_put(struct mlxsw_sp_acl_tcam *tcam,
u16 id)
{
- __clear_bit(id, tcam->used_regions);
+ ida_free(&tcam->used_regions, id);
}
static int mlxsw_sp_acl_tcam_group_id_get(struct mlxsw_sp_acl_tcam *tcam,
u16 *p_id)
{
- u16 id;
+ int id;
- id = find_first_zero_bit(tcam->used_groups, tcam->max_groups);
- if (id < tcam->max_groups) {
- __set_bit(id, tcam->used_groups);
- *p_id = id;
- return 0;
- }
- return -ENOBUFS;
+ id = ida_alloc_max(&tcam->used_groups, tcam->max_groups - 1,
+ GFP_KERNEL);
+ if (id < 0)
+ return id;
+
+ *p_id = id;
+
+ return 0;
}
static void mlxsw_sp_acl_tcam_group_id_put(struct mlxsw_sp_acl_tcam *tcam,
u16 id)
{
- __clear_bit(id, tcam->used_groups);
+ ida_free(&tcam->used_groups, id);
}
struct mlxsw_sp_acl_tcam_pattern {
@@ -715,7 +718,9 @@
rehash.dw.work);
int credits = MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS;
+ mutex_lock(&vregion->lock);
mlxsw_sp_acl_tcam_vregion_rehash(vregion->mlxsw_sp, vregion, &credits);
+ mutex_unlock(&vregion->lock);
if (credits < 0)
/* Rehash gone out of credits so it was interrupted.
* Schedule the work as soon as possible to continue.
@@ -726,6 +731,17 @@
}
static void
+mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+ /* The entry markers are relative to the current chunk and therefore
+ * needs to be reset together with the chunk marker.
+ */
+ ctx->current_vchunk = NULL;
+ ctx->start_ventry = NULL;
+ ctx->stop_ventry = NULL;
+}
+
+static void
mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(struct mlxsw_sp_acl_tcam_vchunk *vchunk)
{
struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion;
@@ -747,7 +763,7 @@
* the current chunk pointer to make sure all chunks
* are properly migrated.
*/
- vregion->rehash.ctx.current_vchunk = NULL;
+ mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(&vregion->rehash.ctx);
}
static struct mlxsw_sp_acl_tcam_vregion *
@@ -820,10 +836,14 @@
struct mlxsw_sp_acl_tcam *tcam = vregion->tcam;
if (vgroup->vregion_rehash_enabled && ops->region_rehash_hints_get) {
+ struct mlxsw_sp_acl_tcam_rehash_ctx *ctx = &vregion->rehash.ctx;
+
mutex_lock(&tcam->lock);
list_del(&vregion->tlist);
mutex_unlock(&tcam->lock);
- cancel_delayed_work_sync(&vregion->rehash.dw);
+ if (cancel_delayed_work_sync(&vregion->rehash.dw) &&
+ ctx->hints_priv)
+ ops->region_rehash_hints_put(ctx->hints_priv);
}
mlxsw_sp_acl_tcam_vgroup_vregion_detach(mlxsw_sp, vregion);
if (vregion->region2)
@@ -1154,8 +1174,14 @@
struct mlxsw_sp_acl_tcam_ventry *ventry,
bool *activity)
{
- return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp,
- ventry->entry, activity);
+ struct mlxsw_sp_acl_tcam_vregion *vregion = ventry->vchunk->vregion;
+ int err;
+
+ mutex_lock(&vregion->lock);
+ err = mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, ventry->entry,
+ activity);
+ mutex_unlock(&vregion->lock);
+ return err;
}
static int
@@ -1189,6 +1215,8 @@
{
struct mlxsw_sp_acl_tcam_chunk *new_chunk;
+ WARN_ON(vchunk->chunk2);
+
new_chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region);
if (IS_ERR(new_chunk))
return PTR_ERR(new_chunk);
@@ -1207,7 +1235,7 @@
{
mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2);
vchunk->chunk2 = NULL;
- ctx->current_vchunk = NULL;
+ mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx);
}
static int
@@ -1230,6 +1258,9 @@
return 0;
}
+ if (list_empty(&vchunk->ventry_list))
+ goto out;
+
/* If the migration got interrupted, we have the ventry to start from
* stored in context.
*/
@@ -1239,6 +1270,8 @@
ventry = list_first_entry(&vchunk->ventry_list,
typeof(*ventry), list);
+ WARN_ON(ventry->vchunk != vchunk);
+
list_for_each_entry_from(ventry, &vchunk->ventry_list, list) {
/* During rollback, once we reach the ventry that failed
* to migrate, we are done.
@@ -1279,6 +1312,7 @@
}
}
+out:
mlxsw_sp_acl_tcam_vchunk_migrate_end(mlxsw_sp, vchunk, ctx);
return 0;
}
@@ -1292,6 +1326,9 @@
struct mlxsw_sp_acl_tcam_vchunk *vchunk;
int err;
+ if (list_empty(&vregion->vchunk_list))
+ return 0;
+
/* If the migration got interrupted, we have the vchunk
* we are working on stored in context.
*/
@@ -1320,16 +1357,17 @@
int err, err2;
trace_mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion);
- mutex_lock(&vregion->lock);
err = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion,
ctx, credits);
if (err) {
+ if (ctx->this_is_rollback)
+ return err;
/* In case migration was not successful, we need to swap
* so the original region pointer is assigned again
* to vregion->region.
*/
swap(vregion->region, vregion->region2);
- ctx->current_vchunk = NULL;
+ mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx);
ctx->this_is_rollback = true;
err2 = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion,
ctx, credits);
@@ -1340,7 +1378,6 @@
/* Let the rollback to be continued later on. */
}
}
- mutex_unlock(&vregion->lock);
trace_mlxsw_sp_acl_tcam_vregion_migrate_end(mlxsw_sp, vregion);
return err;
}
@@ -1389,6 +1426,7 @@
ctx->hints_priv = hints_priv;
ctx->this_is_rollback = false;
+ mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(ctx);
return 0;
@@ -1441,7 +1479,8 @@
err = mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion,
ctx, credits);
if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n");
+ dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n");
+ return;
}
if (*credits >= 0)
@@ -1549,19 +1588,11 @@
if (max_tcam_regions < max_regions)
max_regions = max_tcam_regions;
- tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL);
- if (!tcam->used_regions) {
- err = -ENOMEM;
- goto err_alloc_used_regions;
- }
+ ida_init(&tcam->used_regions);
tcam->max_regions = max_regions;
max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS);
- tcam->used_groups = bitmap_zalloc(max_groups, GFP_KERNEL);
- if (!tcam->used_groups) {
- err = -ENOMEM;
- goto err_alloc_used_groups;
- }
+ ida_init(&tcam->used_groups);
tcam->max_groups = max_groups;
tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
ACL_MAX_GROUP_SIZE);
@@ -1575,10 +1606,8 @@
return 0;
err_tcam_init:
- bitmap_free(tcam->used_groups);
-err_alloc_used_groups:
- bitmap_free(tcam->used_regions);
-err_alloc_used_regions:
+ ida_destroy(&tcam->used_groups);
+ ida_destroy(&tcam->used_regions);
mlxsw_sp_acl_tcam_rehash_params_unregister(mlxsw_sp);
err_rehash_params_register:
mutex_destroy(&tcam->lock);
@@ -1591,8 +1620,8 @@
const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
ops->fini(mlxsw_sp, tcam->priv);
- bitmap_free(tcam->used_groups);
- bitmap_free(tcam->used_regions);
+ ida_destroy(&tcam->used_groups);
+ ida_destroy(&tcam->used_regions);
mlxsw_sp_acl_tcam_rehash_params_unregister(mlxsw_sp);
mutex_destroy(&tcam->lock);
}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 462bf44..79a1d86 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -6,15 +6,16 @@
#include <linux/list.h>
#include <linux/parman.h>
+#include <linux/idr.h>
#include "reg.h"
#include "spectrum.h"
#include "core_acl_flex_keys.h"
struct mlxsw_sp_acl_tcam {
- unsigned long *used_regions; /* bit array */
+ struct ida used_regions;
unsigned int max_regions;
- unsigned long *used_groups; /* bit array */
+ struct ida used_groups;
unsigned int max_groups;
unsigned int max_group_size;
struct mutex lock; /* guards vregion list */
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index e5ec0a3..31f75b4 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -368,7 +368,6 @@
* @rdfifo: FIFO read callback
* @wrfifo: FIFO write callback
* @start_xmit: start_xmit() implementation callback
- * @rx_skb: rx_skb() implementation callback
* @flush_tx_work: flush_tx_work() implementation callback
*
* The @statelock is used to protect information in the structure which may
@@ -423,8 +422,6 @@
struct sk_buff *txp, bool irq);
netdev_tx_t (*start_xmit)(struct sk_buff *skb,
struct net_device *dev);
- void (*rx_skb)(struct ks8851_net *ks,
- struct sk_buff *skb);
void (*flush_tx_work)(struct ks8851_net *ks);
};
diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c
index 0bf13b3..d4cdf3d 100644
--- a/drivers/net/ethernet/micrel/ks8851_common.c
+++ b/drivers/net/ethernet/micrel/ks8851_common.c
@@ -232,16 +232,6 @@
}
/**
- * ks8851_rx_skb - receive skbuff
- * @ks: The device state.
- * @skb: The skbuff
- */
-static void ks8851_rx_skb(struct ks8851_net *ks, struct sk_buff *skb)
-{
- ks->rx_skb(ks, skb);
-}
-
-/**
* ks8851_rx_pkts - receive packets from the host
* @ks: The device information.
*
@@ -309,7 +299,7 @@
ks8851_dbg_dumpkkt(ks, rxpkt);
skb->protocol = eth_type_trans(skb, ks->netdev);
- ks8851_rx_skb(ks, skb);
+ __netif_rx(skb);
ks->netdev->stats.rx_packets++;
ks->netdev->stats.rx_bytes += rxlen;
@@ -340,6 +330,8 @@
unsigned long flags;
unsigned int status;
+ local_bh_disable();
+
ks8851_lock(ks, &flags);
status = ks8851_rdreg16(ks, KS_ISR);
@@ -416,6 +408,8 @@
if (status & IRQ_LCI)
mii_check_link(&ks->mii);
+ local_bh_enable();
+
return IRQ_HANDLED;
}
diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c
index 2a7f298..381b9cd 100644
--- a/drivers/net/ethernet/micrel/ks8851_par.c
+++ b/drivers/net/ethernet/micrel/ks8851_par.c
@@ -210,16 +210,6 @@
iowrite16_rep(ksp->hw_addr, txp->data, len / 2);
}
-/**
- * ks8851_rx_skb_par - receive skbuff
- * @ks: The device state.
- * @skb: The skbuff
- */
-static void ks8851_rx_skb_par(struct ks8851_net *ks, struct sk_buff *skb)
-{
- netif_rx(skb);
-}
-
static unsigned int ks8851_rdreg16_par_txqcr(struct ks8851_net *ks)
{
return ks8851_rdreg16_par(ks, KS_TXQCR);
@@ -298,7 +288,6 @@
ks->rdfifo = ks8851_rdfifo_par;
ks->wrfifo = ks8851_wrfifo_par;
ks->start_xmit = ks8851_start_xmit_par;
- ks->rx_skb = ks8851_rx_skb_par;
#define STD_IRQ (IRQ_LCI | /* Link Change */ \
IRQ_RXI | /* RX done */ \
diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c
index 2f80337..670c1de 100644
--- a/drivers/net/ethernet/micrel/ks8851_spi.c
+++ b/drivers/net/ethernet/micrel/ks8851_spi.c
@@ -299,16 +299,6 @@
}
/**
- * ks8851_rx_skb_spi - receive skbuff
- * @ks: The device state
- * @skb: The skbuff
- */
-static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb)
-{
- netif_rx(skb);
-}
-
-/**
* ks8851_tx_work - process tx packet(s)
* @work: The work strucutre what was scheduled.
*
@@ -435,7 +425,6 @@
ks->rdfifo = ks8851_rdfifo_spi;
ks->wrfifo = ks8851_wrfifo_spi;
ks->start_xmit = ks8851_start_xmit_spi;
- ks->rx_skb = ks8851_rx_skb_spi;
ks->flush_tx_work = ks8851_flush_tx_work_spi;
#define STD_IRQ (IRQ_LCI | /* Link Change */ \
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
index 3a1b1a1..60dd2fd 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
@@ -731,7 +731,7 @@
bool sgmii = false, inband_aneg = false;
int err;
- if (port->conf.inband) {
+ if (conf->inband) {
if (conf->portmode == PHY_INTERFACE_MODE_SGMII ||
conf->portmode == PHY_INTERFACE_MODE_QSGMII)
inband_aneg = true; /* Cisco-SGMII in-band-aneg */
@@ -948,7 +948,7 @@
if (err)
return -EINVAL;
- if (port->conf.inband) {
+ if (conf->inband) {
/* Enable/disable 1G counters in ASM */
spx5_rmw(ASM_PORT_CFG_CSC_STAT_DIS_SET(high_speed_dev),
ASM_PORT_CFG_CSC_STAT_DIS,
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
index 523e0c4..55f255a 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c
@@ -36,6 +36,27 @@
u16 l3_proto; /* protocol specified in the template */
};
+/* SparX-5 VCAP fragment types:
+ * 0 = no fragment, 1 = initial fragment,
+ * 2 = suspicious fragment, 3 = valid follow-up fragment
+ */
+enum { /* key / mask */
+ FRAG_NOT = 0x03, /* 0 / 3 */
+ FRAG_SOME = 0x11, /* 1 / 1 */
+ FRAG_FIRST = 0x13, /* 1 / 3 */
+ FRAG_LATER = 0x33, /* 3 / 3 */
+ FRAG_INVAL = 0xff, /* invalid */
+};
+
+/* Flower fragment flag to VCAP fragment type mapping */
+static const u8 sparx5_vcap_frag_map[4][4] = { /* is_frag */
+ { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_FIRST }, /* 0/0 */
+ { FRAG_NOT, FRAG_NOT, FRAG_INVAL, FRAG_INVAL }, /* 0/1 */
+ { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_INVAL }, /* 1/0 */
+ { FRAG_SOME, FRAG_LATER, FRAG_INVAL, FRAG_FIRST } /* 1/1 */
+ /* 0/0 0/1 1/0 1/1 <-- first_frag */
+};
+
static int
sparx5_tc_flower_es0_tpid(struct vcap_tc_flower_parse_usage *st)
{
@@ -145,29 +166,27 @@
flow_rule_match_control(st->frule, &mt);
if (mt.mask->flags) {
- if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) {
- if (mt.key->flags & FLOW_DIS_FIRST_FRAG) {
- value = 1; /* initial fragment */
- mask = 0x3;
- } else {
- if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) {
- value = 3; /* follow up fragment */
- mask = 0x3;
- } else {
- value = 0; /* no fragment */
- mask = 0x3;
- }
- }
- } else {
- if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) {
- value = 3; /* follow up fragment */
- mask = 0x3;
- } else {
- value = 0; /* no fragment */
- mask = 0x3;
- }
+ u8 is_frag_key = !!(mt.key->flags & FLOW_DIS_IS_FRAGMENT);
+ u8 is_frag_mask = !!(mt.mask->flags & FLOW_DIS_IS_FRAGMENT);
+ u8 is_frag_idx = (is_frag_key << 1) | is_frag_mask;
+
+ u8 first_frag_key = !!(mt.key->flags & FLOW_DIS_FIRST_FRAG);
+ u8 first_frag_mask = !!(mt.mask->flags & FLOW_DIS_FIRST_FRAG);
+ u8 first_frag_idx = (first_frag_key << 1) | first_frag_mask;
+
+ /* Lookup verdict based on the 2 + 2 input bits */
+ u8 vdt = sparx5_vcap_frag_map[is_frag_idx][first_frag_idx];
+
+ if (vdt == FRAG_INVAL) {
+ NL_SET_ERR_MSG_MOD(st->fco->common.extack,
+ "Match on invalid fragment flag combination");
+ return -EINVAL;
}
+ /* Extract VCAP fragment key and mask from verdict */
+ value = (vdt >> 4) & 0x3;
+ mask = vdt & 0x3;
+
err = vcap_rule_add_key_u32(st->vrule,
VCAP_KF_L3_FRAGMENT_TYPE,
value, mask);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index a5ac21a..cb6b33a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1868,8 +1868,8 @@
struct flow_cls_offload *f)
{
struct qede_arfs_fltr_node *n;
- int min_hlen, rc = -EINVAL;
struct qede_arfs_tuple t;
+ int min_hlen, rc;
__qede_lock(edev);
@@ -1879,7 +1879,8 @@
}
/* parse flower attribute and prepare filter */
- if (qede_parse_flow_attr(edev, proto, f->rule, &t))
+ rc = qede_parse_flow_attr(edev, proto, f->rule, &t);
+ if (rc)
goto unlock;
/* Validate profile mode and number of filters */
@@ -1888,11 +1889,13 @@
DP_NOTICE(edev,
"Filter configuration invalidated, filter mode=0x%x, configured mode=0x%x, filter count=0x%x\n",
t.mode, edev->arfs->mode, edev->arfs->filter_count);
+ rc = -EINVAL;
goto unlock;
}
/* parse tc actions and get the vf_id */
- if (qede_parse_actions(edev, &f->rule->action, f->common.extack))
+ rc = qede_parse_actions(edev, &f->rule->action, f->common.extack);
+ if (rc)
goto unlock;
if (qede_flow_find_fltr(edev, &t)) {
@@ -1998,10 +2001,9 @@
if (IS_ERR(flow))
return PTR_ERR(flow);
- if (qede_parse_flow_attr(edev, proto, flow->rule, t)) {
- err = -EINVAL;
+ err = qede_parse_flow_attr(edev, proto, flow->rule, t);
+ if (err)
goto err_out;
- }
/* Make sure location is valid and filter isn't already set */
err = qede_flow_spec_validate(edev, &flow->rule->action, t,
diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index 4c04305..00882ffc7 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -73,6 +73,7 @@
};
struct rtl8169_private;
+struct r8169_led_classdev;
void r8169_apply_firmware(struct rtl8169_private *tp);
u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp);
@@ -84,7 +85,8 @@
char *buf, int buf_len);
int rtl8168_get_led_mode(struct rtl8169_private *tp);
int rtl8168_led_mod_ctrl(struct rtl8169_private *tp, u16 mask, u16 val);
-void rtl8168_init_leds(struct net_device *ndev);
+struct r8169_led_classdev *rtl8168_init_leds(struct net_device *ndev);
int rtl8125_get_led_mode(struct rtl8169_private *tp, int index);
int rtl8125_set_led_mode(struct rtl8169_private *tp, int index, u16 mode);
-void rtl8125_init_leds(struct net_device *ndev);
+struct r8169_led_classdev *rtl8125_init_leds(struct net_device *ndev);
+void r8169_remove_leds(struct r8169_led_classdev *leds);
diff --git a/drivers/net/ethernet/realtek/r8169_leds.c b/drivers/net/ethernet/realtek/r8169_leds.c
index 7c5dc9d..e10bee7 100644
--- a/drivers/net/ethernet/realtek/r8169_leds.c
+++ b/drivers/net/ethernet/realtek/r8169_leds.c
@@ -146,22 +146,22 @@
led_cdev->hw_control_get_device = r8169_led_hw_control_get_device;
/* ignore errors */
- devm_led_classdev_register(&ndev->dev, led_cdev);
+ led_classdev_register(&ndev->dev, led_cdev);
}
-void rtl8168_init_leds(struct net_device *ndev)
+struct r8169_led_classdev *rtl8168_init_leds(struct net_device *ndev)
{
- /* bind resource mgmt to netdev */
- struct device *dev = &ndev->dev;
struct r8169_led_classdev *leds;
int i;
- leds = devm_kcalloc(dev, RTL8168_NUM_LEDS, sizeof(*leds), GFP_KERNEL);
+ leds = kcalloc(RTL8168_NUM_LEDS + 1, sizeof(*leds), GFP_KERNEL);
if (!leds)
- return;
+ return NULL;
for (i = 0; i < RTL8168_NUM_LEDS; i++)
rtl8168_setup_ldev(leds + i, ndev, i);
+
+ return leds;
}
static int rtl8125_led_hw_control_is_supported(struct led_classdev *led_cdev,
@@ -245,20 +245,31 @@
led_cdev->hw_control_get_device = r8169_led_hw_control_get_device;
/* ignore errors */
- devm_led_classdev_register(&ndev->dev, led_cdev);
+ led_classdev_register(&ndev->dev, led_cdev);
}
-void rtl8125_init_leds(struct net_device *ndev)
+struct r8169_led_classdev *rtl8125_init_leds(struct net_device *ndev)
{
- /* bind resource mgmt to netdev */
- struct device *dev = &ndev->dev;
struct r8169_led_classdev *leds;
int i;
- leds = devm_kcalloc(dev, RTL8125_NUM_LEDS, sizeof(*leds), GFP_KERNEL);
+ leds = kcalloc(RTL8125_NUM_LEDS + 1, sizeof(*leds), GFP_KERNEL);
if (!leds)
- return;
+ return NULL;
for (i = 0; i < RTL8125_NUM_LEDS; i++)
rtl8125_setup_led_ldev(leds + i, ndev, i);
+
+ return leds;
+}
+
+void r8169_remove_leds(struct r8169_led_classdev *leds)
+{
+ if (!leds)
+ return;
+
+ for (struct r8169_led_classdev *l = leds; l->ndev; l++)
+ led_classdev_unregister(&l->led);
+
+ kfree(leds);
}
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 6f1e6f3..0fc5fe5 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -647,6 +647,8 @@
const char *fw_name;
struct rtl_fw *rtl_fw;
+ struct r8169_led_classdev *leds;
+
u32 ocp_base;
};
@@ -5044,6 +5046,9 @@
cancel_work_sync(&tp->wk.work);
+ if (IS_ENABLED(CONFIG_R8169_LEDS))
+ r8169_remove_leds(tp->leds);
+
unregister_netdev(tp->dev);
if (tp->dash_type != RTL_DASH_NONE)
@@ -5501,9 +5506,9 @@
if (IS_ENABLED(CONFIG_R8169_LEDS)) {
if (rtl_is_8125(tp))
- rtl8125_init_leds(dev);
+ tp->leds = rtl8125_init_leds(dev);
else if (tp->mac_version > RTL_GIGA_MAC_VER_06)
- rtl8168_init_leds(dev);
+ tp->leds = rtl8168_init_leds(dev);
}
netdev_info(dev, "%s, %pM, XID %03x, IRQ %d\n",
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index ba01c8c..9b1f639 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -769,25 +769,28 @@
dma_addr_t dma_addr;
int rx_packets = 0;
u8 desc_status;
- u16 pkt_len;
+ u16 desc_len;
u8 die_dt;
int entry;
int limit;
int i;
- entry = priv->cur_rx[q] % priv->num_rx_ring[q];
limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q];
stats = &priv->stats[q];
- desc = &priv->rx_ring[q].desc[entry];
- for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) {
+ for (i = 0; i < limit; i++, priv->cur_rx[q]++) {
+ entry = priv->cur_rx[q] % priv->num_rx_ring[q];
+ desc = &priv->rx_ring[q].desc[entry];
+ if (rx_packets == *quota || desc->die_dt == DT_FEMPTY)
+ break;
+
/* Descriptor type must be checked before all other reads */
dma_rmb();
desc_status = desc->msc;
- pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS;
+ desc_len = le16_to_cpu(desc->ds_cc) & RX_DS;
/* We use 0-byte descriptors to mark the DMA mapping errors */
- if (!pkt_len)
+ if (!desc_len)
continue;
if (desc_status & MSC_MC)
@@ -808,25 +811,25 @@
switch (die_dt) {
case DT_FSINGLE:
skb = ravb_get_skb_gbeth(ndev, entry, desc);
- skb_put(skb, pkt_len);
+ skb_put(skb, desc_len);
skb->protocol = eth_type_trans(skb, ndev);
if (ndev->features & NETIF_F_RXCSUM)
ravb_rx_csum_gbeth(skb);
napi_gro_receive(&priv->napi[q], skb);
rx_packets++;
- stats->rx_bytes += pkt_len;
+ stats->rx_bytes += desc_len;
break;
case DT_FSTART:
priv->rx_1st_skb = ravb_get_skb_gbeth(ndev, entry, desc);
- skb_put(priv->rx_1st_skb, pkt_len);
+ skb_put(priv->rx_1st_skb, desc_len);
break;
case DT_FMID:
skb = ravb_get_skb_gbeth(ndev, entry, desc);
skb_copy_to_linear_data_offset(priv->rx_1st_skb,
priv->rx_1st_skb->len,
skb->data,
- pkt_len);
- skb_put(priv->rx_1st_skb, pkt_len);
+ desc_len);
+ skb_put(priv->rx_1st_skb, desc_len);
dev_kfree_skb(skb);
break;
case DT_FEND:
@@ -834,23 +837,20 @@
skb_copy_to_linear_data_offset(priv->rx_1st_skb,
priv->rx_1st_skb->len,
skb->data,
- pkt_len);
- skb_put(priv->rx_1st_skb, pkt_len);
+ desc_len);
+ skb_put(priv->rx_1st_skb, desc_len);
dev_kfree_skb(skb);
priv->rx_1st_skb->protocol =
eth_type_trans(priv->rx_1st_skb, ndev);
if (ndev->features & NETIF_F_RXCSUM)
- ravb_rx_csum_gbeth(skb);
+ ravb_rx_csum_gbeth(priv->rx_1st_skb);
+ stats->rx_bytes += priv->rx_1st_skb->len;
napi_gro_receive(&priv->napi[q],
priv->rx_1st_skb);
rx_packets++;
- stats->rx_bytes += pkt_len;
break;
}
}
-
- entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q];
- desc = &priv->rx_ring[q].desc[entry];
}
/* Refill the RX ring buffers. */
@@ -891,30 +891,29 @@
{
struct ravb_private *priv = netdev_priv(ndev);
const struct ravb_hw_info *info = priv->info;
- int entry = priv->cur_rx[q] % priv->num_rx_ring[q];
- int boguscnt = (priv->dirty_rx[q] + priv->num_rx_ring[q]) -
- priv->cur_rx[q];
struct net_device_stats *stats = &priv->stats[q];
struct ravb_ex_rx_desc *desc;
+ unsigned int limit, i;
struct sk_buff *skb;
dma_addr_t dma_addr;
struct timespec64 ts;
+ int rx_packets = 0;
u8 desc_status;
u16 pkt_len;
- int limit;
+ int entry;
- boguscnt = min(boguscnt, *quota);
- limit = boguscnt;
- desc = &priv->rx_ring[q].ex_desc[entry];
- while (desc->die_dt != DT_FEMPTY) {
+ limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q];
+ for (i = 0; i < limit; i++, priv->cur_rx[q]++) {
+ entry = priv->cur_rx[q] % priv->num_rx_ring[q];
+ desc = &priv->rx_ring[q].ex_desc[entry];
+ if (rx_packets == *quota || desc->die_dt == DT_FEMPTY)
+ break;
+
/* Descriptor type must be checked before all other reads */
dma_rmb();
desc_status = desc->msc;
pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS;
- if (--boguscnt < 0)
- break;
-
/* We use 0-byte descriptors to mark the DMA mapping errors */
if (!pkt_len)
continue;
@@ -960,12 +959,9 @@
if (ndev->features & NETIF_F_RXCSUM)
ravb_rx_csum(skb);
napi_gro_receive(&priv->napi[q], skb);
- stats->rx_packets++;
+ rx_packets++;
stats->rx_bytes += pkt_len;
}
-
- entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q];
- desc = &priv->rx_ring[q].ex_desc[entry];
}
/* Refill the RX ring buffers. */
@@ -995,9 +991,9 @@
desc->die_dt = DT_FEMPTY;
}
- *quota -= limit - (++boguscnt);
-
- return boguscnt <= 0;
+ stats->rx_packets += rx_packets;
+ *quota -= rx_packets;
+ return *quota == 0;
}
/* Packet receive function for Ethernet AVB */
@@ -2726,19 +2722,18 @@
struct platform_device *pdev = priv->pdev;
struct net_device *ndev = priv->ndev;
struct device *dev = &pdev->dev;
- const char *dev_name;
+ const char *devname = dev_name(dev);
unsigned long flags;
int error, irq_num;
if (irq_name) {
- dev_name = devm_kasprintf(dev, GFP_KERNEL, "%s:%s", ndev->name, ch);
- if (!dev_name)
+ devname = devm_kasprintf(dev, GFP_KERNEL, "%s:%s", devname, ch);
+ if (!devname)
return -ENOMEM;
irq_num = platform_get_irq_byname(pdev, irq_name);
flags = 0;
} else {
- dev_name = ndev->name;
irq_num = platform_get_irq(pdev, 0);
flags = IRQF_SHARED;
}
@@ -2748,9 +2743,9 @@
if (irq)
*irq = irq_num;
- error = devm_request_irq(dev, irq_num, handler, flags, dev_name, ndev);
+ error = devm_request_irq(dev, irq_num, handler, flags, devname, ndev);
if (error)
- netdev_err(ndev, "cannot request IRQ %s\n", dev_name);
+ netdev_err(ndev, "cannot request IRQ %s\n", devname);
return error;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index a6fefe6..3b7d4ac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -553,6 +553,7 @@
extern const struct stmmac_mode_ops dwmac4_ring_mode_ops;
struct mac_link {
+ u32 caps;
u32 speed_mask;
u32 speed10;
u32 speed100;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index b21d99f..e1b761d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1096,6 +1096,8 @@
priv->dev->priv_flags |= IFF_UNICAST_FLT;
+ mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_10 | MAC_100 | MAC_1000;
/* The loopback bit seems to be re-set when link change
* Simply mask it each time
* Speed 10/100/1000 are set in BIT(2)/BIT(3)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 3927609..8555299 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -539,6 +539,8 @@
if (mac->multicast_filter_bins)
mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
+ mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_10 | MAC_100 | MAC_1000;
mac->link.duplex = GMAC_CONTROL_DM;
mac->link.speed10 = GMAC_CONTROL_PS;
mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index a6e8d7b..7667d10 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -175,6 +175,8 @@
dev_info(priv->device, "\tDWMAC100\n");
mac->pcsr = priv->ioaddr;
+ mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_10 | MAC_100;
mac->link.duplex = MAC_CONTROL_F;
mac->link.speed10 = 0;
mac->link.speed100 = 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index cef25ef..a38226d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -70,7 +70,10 @@
static void dwmac4_phylink_get_caps(struct stmmac_priv *priv)
{
- priv->phylink_config.mac_capabilities |= MAC_2500FD;
+ if (priv->plat->tx_queues_to_use > 1)
+ priv->hw->link.caps &= ~(MAC_10HD | MAC_100HD | MAC_1000HD);
+ else
+ priv->hw->link.caps |= (MAC_10HD | MAC_100HD | MAC_1000HD);
}
static void dwmac4_rx_queue_enable(struct mac_device_info *hw,
@@ -1378,6 +1381,8 @@
if (mac->multicast_filter_bins)
mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
+ mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD;
mac->link.duplex = GMAC_CONFIG_DM;
mac->link.speed10 = GMAC_CONFIG_PS;
mac->link.speed100 = GMAC_CONFIG_FES | GMAC_CONFIG_PS;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index e841e31..f8e7775 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -47,14 +47,6 @@
writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN);
}
-static void xgmac_phylink_get_caps(struct stmmac_priv *priv)
-{
- priv->phylink_config.mac_capabilities |= MAC_2500FD | MAC_5000FD |
- MAC_10000FD | MAC_25000FD |
- MAC_40000FD | MAC_50000FD |
- MAC_100000FD;
-}
-
static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable)
{
u32 tx = readl(ioaddr + XGMAC_TX_CONFIG);
@@ -1540,7 +1532,6 @@
const struct stmmac_ops dwxgmac210_ops = {
.core_init = dwxgmac2_core_init,
- .phylink_get_caps = xgmac_phylink_get_caps,
.set_mac = dwxgmac2_set_mac,
.rx_ipc = dwxgmac2_rx_ipc,
.rx_queue_enable = dwxgmac2_rx_queue_enable,
@@ -1601,7 +1592,6 @@
const struct stmmac_ops dwxlgmac2_ops = {
.core_init = dwxgmac2_core_init,
- .phylink_get_caps = xgmac_phylink_get_caps,
.set_mac = dwxgmac2_set_mac,
.rx_ipc = dwxgmac2_rx_ipc,
.rx_queue_enable = dwxlgmac2_rx_queue_enable,
@@ -1661,6 +1651,9 @@
if (mac->multicast_filter_bins)
mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
+ mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_1000FD | MAC_2500FD | MAC_5000FD |
+ MAC_10000FD;
mac->link.duplex = 0;
mac->link.speed10 = XGMAC_CONFIG_SS_10_MII;
mac->link.speed100 = XGMAC_CONFIG_SS_100_MII;
@@ -1698,6 +1691,11 @@
if (mac->multicast_filter_bins)
mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
+ mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_1000FD | MAC_2500FD | MAC_5000FD |
+ MAC_10000FD | MAC_25000FD |
+ MAC_40000FD | MAC_50000FD |
+ MAC_100000FD;
mac->link.duplex = 0;
mac->link.speed1000 = XLGMAC_CONFIG_SS_1000;
mac->link.speed2500 = XLGMAC_CONFIG_SS_2500;
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h
index dff02d7..5d1ea3e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc.h
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h
@@ -52,6 +52,7 @@
unsigned int mmc_tx_excessdef;
unsigned int mmc_tx_pause_frame;
unsigned int mmc_tx_vlan_frame_g;
+ unsigned int mmc_tx_oversize_g;
unsigned int mmc_tx_lpi_usec;
unsigned int mmc_tx_lpi_tran;
@@ -80,6 +81,7 @@
unsigned int mmc_rx_fifo_overflow;
unsigned int mmc_rx_vlan_frames_gb;
unsigned int mmc_rx_watchdog_error;
+ unsigned int mmc_rx_error;
unsigned int mmc_rx_lpi_usec;
unsigned int mmc_rx_lpi_tran;
unsigned int mmc_rx_discard_frames_gb;
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index 7eb477f..0fab842 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -53,6 +53,7 @@
#define MMC_TX_EXCESSDEF 0x6c
#define MMC_TX_PAUSE_FRAME 0x70
#define MMC_TX_VLAN_FRAME_G 0x74
+#define MMC_TX_OVERSIZE_G 0x78
/* MMC RX counter registers */
#define MMC_RX_FRAMECOUNT_GB 0x80
@@ -79,6 +80,13 @@
#define MMC_RX_FIFO_OVERFLOW 0xd4
#define MMC_RX_VLAN_FRAMES_GB 0xd8
#define MMC_RX_WATCHDOG_ERROR 0xdc
+#define MMC_RX_ERROR 0xe0
+
+#define MMC_TX_LPI_USEC 0xec
+#define MMC_TX_LPI_TRAN 0xf0
+#define MMC_RX_LPI_USEC 0xf4
+#define MMC_RX_LPI_TRAN 0xf8
+
/* IPC*/
#define MMC_RX_IPC_INTR_MASK 0x100
#define MMC_RX_IPC_INTR 0x108
@@ -283,6 +291,9 @@
mmc->mmc_tx_excessdef += readl(mmcaddr + MMC_TX_EXCESSDEF);
mmc->mmc_tx_pause_frame += readl(mmcaddr + MMC_TX_PAUSE_FRAME);
mmc->mmc_tx_vlan_frame_g += readl(mmcaddr + MMC_TX_VLAN_FRAME_G);
+ mmc->mmc_tx_oversize_g += readl(mmcaddr + MMC_TX_OVERSIZE_G);
+ mmc->mmc_tx_lpi_usec += readl(mmcaddr + MMC_TX_LPI_USEC);
+ mmc->mmc_tx_lpi_tran += readl(mmcaddr + MMC_TX_LPI_TRAN);
/* MMC RX counter registers */
mmc->mmc_rx_framecount_gb += readl(mmcaddr + MMC_RX_FRAMECOUNT_GB);
@@ -316,6 +327,10 @@
mmc->mmc_rx_fifo_overflow += readl(mmcaddr + MMC_RX_FIFO_OVERFLOW);
mmc->mmc_rx_vlan_frames_gb += readl(mmcaddr + MMC_RX_VLAN_FRAMES_GB);
mmc->mmc_rx_watchdog_error += readl(mmcaddr + MMC_RX_WATCHDOG_ERROR);
+ mmc->mmc_rx_error += readl(mmcaddr + MMC_RX_ERROR);
+ mmc->mmc_rx_lpi_usec += readl(mmcaddr + MMC_RX_LPI_USEC);
+ mmc->mmc_rx_lpi_tran += readl(mmcaddr + MMC_RX_LPI_TRAN);
+
/* IPv4 */
mmc->mmc_rx_ipv4_gd += readl(mmcaddr + MMC_RX_IPV4_GD);
mmc->mmc_rx_ipv4_hderr += readl(mmcaddr + MMC_RX_IPV4_HDERR);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index e1537a5..542e263 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -212,6 +212,7 @@
STMMAC_MMC_STAT(mmc_tx_excessdef),
STMMAC_MMC_STAT(mmc_tx_pause_frame),
STMMAC_MMC_STAT(mmc_tx_vlan_frame_g),
+ STMMAC_MMC_STAT(mmc_tx_oversize_g),
STMMAC_MMC_STAT(mmc_tx_lpi_usec),
STMMAC_MMC_STAT(mmc_tx_lpi_tran),
STMMAC_MMC_STAT(mmc_rx_framecount_gb),
@@ -238,6 +239,7 @@
STMMAC_MMC_STAT(mmc_rx_fifo_overflow),
STMMAC_MMC_STAT(mmc_rx_vlan_frames_gb),
STMMAC_MMC_STAT(mmc_rx_watchdog_error),
+ STMMAC_MMC_STAT(mmc_rx_error),
STMMAC_MMC_STAT(mmc_rx_lpi_usec),
STMMAC_MMC_STAT(mmc_rx_lpi_tran),
STMMAC_MMC_STAT(mmc_rx_discard_frames_gb),
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 24cd8049..7c6fb14 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1198,17 +1198,6 @@
return ret;
}
-static void stmmac_set_half_duplex(struct stmmac_priv *priv)
-{
- /* Half-Duplex can only work with single tx queue */
- if (priv->plat->tx_queues_to_use > 1)
- priv->phylink_config.mac_capabilities &=
- ~(MAC_10HD | MAC_100HD | MAC_1000HD);
- else
- priv->phylink_config.mac_capabilities |=
- (MAC_10HD | MAC_100HD | MAC_1000HD);
-}
-
static int stmmac_phy_setup(struct stmmac_priv *priv)
{
struct stmmac_mdio_bus_data *mdio_bus_data;
@@ -1236,15 +1225,11 @@
xpcs_get_interfaces(priv->hw->xpcs,
priv->phylink_config.supported_interfaces);
- priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
- MAC_10FD | MAC_100FD |
- MAC_1000FD;
-
- stmmac_set_half_duplex(priv);
-
/* Get the MAC specific capabilities */
stmmac_mac_phylink_get_caps(priv);
+ priv->phylink_config.mac_capabilities = priv->hw->link.caps;
+
max_speed = priv->plat->max_speed;
if (max_speed)
phylink_limit_mac_speed(&priv->phylink_config, max_speed);
@@ -7342,6 +7327,7 @@
{
struct stmmac_priv *priv = netdev_priv(dev);
int ret = 0, i;
+ int max_speed;
if (netif_running(dev))
stmmac_release(dev);
@@ -7355,7 +7341,14 @@
priv->rss.table[i] = ethtool_rxfh_indir_default(i,
rx_cnt);
- stmmac_set_half_duplex(priv);
+ stmmac_mac_phylink_get_caps(priv);
+
+ priv->phylink_config.mac_capabilities = priv->hw->link.caps;
+
+ max_speed = priv->plat->max_speed;
+ if (max_speed)
+ phylink_limit_mac_speed(&priv->phylink_config, max_speed);
+
stmmac_napi_add(dev);
if (netif_running(dev))
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 2939a21..1d00e21 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2793,6 +2793,8 @@
static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
{
+ struct am65_cpsw_rx_chn *rx_chan = &common->rx_chns;
+ struct am65_cpsw_tx_chn *tx_chan = common->tx_chns;
struct device *dev = common->dev;
struct am65_cpsw_port *port;
int ret = 0, i;
@@ -2805,6 +2807,22 @@
if (ret)
return ret;
+ /* The DMA Channels are not guaranteed to be in a clean state.
+ * Reset and disable them to ensure that they are back to the
+ * clean state and ready to be used.
+ */
+ for (i = 0; i < common->tx_ch_num; i++) {
+ k3_udma_glue_reset_tx_chn(tx_chan[i].tx_chn, &tx_chan[i],
+ am65_cpsw_nuss_tx_cleanup);
+ k3_udma_glue_disable_tx_chn(tx_chan[i].tx_chn);
+ }
+
+ for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++)
+ k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i, rx_chan,
+ am65_cpsw_nuss_rx_cleanup, !!i);
+
+ k3_udma_glue_disable_rx_chn(rx_chan->rx_chn);
+
ret = am65_cpsw_nuss_register_devlink(common);
if (ret)
return ret;
diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c
index c66618d..f89716b 100644
--- a/drivers/net/ethernet/ti/am65-cpts.c
+++ b/drivers/net/ethernet/ti/am65-cpts.c
@@ -784,6 +784,11 @@
struct am65_cpts_skb_cb_data *skb_cb =
(struct am65_cpts_skb_cb_data *)skb->cb;
+ if ((ptp_classify_raw(skb) & PTP_CLASS_V1) &&
+ ((mtype_seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK) ==
+ (skb_cb->skb_mtype_seqid & AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK)))
+ mtype_seqid = skb_cb->skb_mtype_seqid;
+
if (mtype_seqid == skb_cb->skb_mtype_seqid) {
u64 ns = event->timestamp;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index cf7b73f..b69af69 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -421,12 +421,14 @@
if (!i)
fdqring_id = k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn,
i);
- rx_chn->irq[i] = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
- if (rx_chn->irq[i] <= 0) {
- ret = rx_chn->irq[i];
+ ret = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
+ if (ret <= 0) {
+ if (!ret)
+ ret = -ENXIO;
netdev_err(ndev, "Failed to get rx dma irq");
goto fail;
}
+ rx_chn->irq[i] = ret;
}
return 0;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 6dff2c8..6fae161 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -1598,7 +1598,7 @@
*/
static int wx_acquire_msix_vectors(struct wx *wx)
{
- struct irq_affinity affd = {0, };
+ struct irq_affinity affd = { .pre_vectors = 1 };
int nvecs, i;
/* We start by asking for one vector per queue pair */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 2fa5112..9329591 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -20,8 +20,6 @@
#include "txgbe_phy.h"
#include "txgbe_hw.h"
-#define TXGBE_I2C_CLK_DEV_NAME "i2c_dw"
-
static int txgbe_swnodes_register(struct txgbe *txgbe)
{
struct txgbe_nodes *nodes = &txgbe->nodes;
@@ -573,8 +571,8 @@
char clk_name[32];
struct clk *clk;
- snprintf(clk_name, sizeof(clk_name), "%s.%d",
- TXGBE_I2C_CLK_DEV_NAME, pci_dev_id(pdev));
+ snprintf(clk_name, sizeof(clk_name), "i2c_designware.%d",
+ pci_dev_id(pdev));
clk = clk_register_fixed_rate(NULL, clk_name, NULL, 0, 156250000);
if (IS_ERR(clk))
@@ -636,7 +634,7 @@
info.parent = &pdev->dev;
info.fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_I2C]);
- info.name = TXGBE_I2C_CLK_DEV_NAME;
+ info.name = "i2c_designware";
info.id = pci_dev_id(pdev);
info.res = &DEFINE_RES_IRQ(pdev->irq);
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 2f6739f..6c28350 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -822,7 +822,7 @@
__be16 sport;
int err;
- if (!pskb_inet_may_pull(skb))
+ if (!skb_vlan_inet_prepare(skb))
return -EINVAL;
if (!gs4)
@@ -929,7 +929,7 @@
__be16 sport;
int err;
- if (!pskb_inet_may_pull(skb))
+ if (!skb_vlan_inet_prepare(skb))
return -EINVAL;
if (!gs6)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index ba4704c..e62d6cb 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1098,11 +1098,12 @@
static void gtp_dellink(struct net_device *dev, struct list_head *head)
{
struct gtp_dev *gtp = netdev_priv(dev);
+ struct hlist_node *next;
struct pdp_ctx *pctx;
int i;
for (i = 0; i < gtp->hash_size; i++)
- hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid)
+ hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid)
pdp_context_delete(pctx);
list_del_rcu(>p->list);
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index a6fcbda..2b6ec97 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -154,8 +154,11 @@
int i;
kfree(nvdev->extension);
- vfree(nvdev->recv_buf);
- vfree(nvdev->send_buf);
+
+ if (!nvdev->recv_buf_gpadl_handle.decrypted)
+ vfree(nvdev->recv_buf);
+ if (!nvdev->send_buf_gpadl_handle.decrypted)
+ vfree(nvdev->send_buf);
bitmap_free(nvdev->send_section_map);
for (i = 0; i < VRSS_CHANNEL_MAX; i++) {
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 0206b84..ff016c1 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -999,10 +999,12 @@
struct metadata_dst *md_dst;
struct macsec_rxh_data *rxd;
struct macsec_dev *macsec;
+ bool is_macsec_md_dst;
rcu_read_lock();
rxd = macsec_data_rcu(skb->dev);
md_dst = skb_metadata_dst(skb);
+ is_macsec_md_dst = md_dst && md_dst->type == METADATA_MACSEC;
list_for_each_entry_rcu(macsec, &rxd->secys, secys) {
struct sk_buff *nskb;
@@ -1013,14 +1015,42 @@
* the SecTAG, so we have to deduce which port to deliver to.
*/
if (macsec_is_offloaded(macsec) && netif_running(ndev)) {
- struct macsec_rx_sc *rx_sc = NULL;
+ const struct macsec_ops *ops;
- if (md_dst && md_dst->type == METADATA_MACSEC)
- rx_sc = find_rx_sc(&macsec->secy, md_dst->u.macsec_info.sci);
+ ops = macsec_get_ops(macsec, NULL);
- if (md_dst && md_dst->type == METADATA_MACSEC && !rx_sc)
+ if (ops->rx_uses_md_dst && !is_macsec_md_dst)
continue;
+ if (is_macsec_md_dst) {
+ struct macsec_rx_sc *rx_sc;
+
+ /* All drivers that implement MACsec offload
+ * support using skb metadata destinations must
+ * indicate that they do so.
+ */
+ DEBUG_NET_WARN_ON_ONCE(!ops->rx_uses_md_dst);
+ rx_sc = find_rx_sc(&macsec->secy,
+ md_dst->u.macsec_info.sci);
+ if (!rx_sc)
+ continue;
+ /* device indicated macsec offload occurred */
+ skb->dev = ndev;
+ skb->pkt_type = PACKET_HOST;
+ eth_skb_pkt_type(skb, ndev);
+ ret = RX_HANDLER_ANOTHER;
+ goto out;
+ }
+
+ /* This datapath is insecure because it is unable to
+ * enforce isolation of broadcast/multicast traffic and
+ * unicast traffic with promiscuous mode on the macsec
+ * netdev. Since the core stack has no mechanism to
+ * check that the hardware did indeed receive MACsec
+ * traffic, it is possible that the response handling
+ * done by the MACsec port was to a plaintext packet.
+ * This violates the MACsec protocol standard.
+ */
if (ether_addr_equal_64bits(hdr->h_dest,
ndev->dev_addr)) {
/* exact match, divert skb to this port */
@@ -1036,14 +1066,10 @@
break;
nskb->dev = ndev;
- if (ether_addr_equal_64bits(hdr->h_dest,
- ndev->broadcast))
- nskb->pkt_type = PACKET_BROADCAST;
- else
- nskb->pkt_type = PACKET_MULTICAST;
+ eth_skb_pkt_type(nskb, ndev);
__netif_rx(nskb);
- } else if (rx_sc || ndev->flags & IFF_PROMISC) {
+ } else if (ndev->flags & IFF_PROMISC) {
skb->dev = ndev;
skb->pkt_type = PACKET_HOST;
ret = RX_HANDLER_ANOTHER;
diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c
index fa8c6fd..d7aaefb 100644
--- a/drivers/net/phy/dp83869.c
+++ b/drivers/net/phy/dp83869.c
@@ -695,7 +695,8 @@
phy_ctrl_val = dp83869->mode;
if (phydev->interface == PHY_INTERFACE_MODE_MII) {
if (dp83869->mode == DP83869_100M_MEDIA_CONVERT ||
- dp83869->mode == DP83869_RGMII_100_BASE) {
+ dp83869->mode == DP83869_RGMII_100_BASE ||
+ dp83869->mode == DP83869_RGMII_COPPER_ETHERNET) {
phy_ctrl_val |= DP83869_OP_MODE_MII;
} else {
phydev_err(phydev, "selected op-mode is not valid with MII mode\n");
diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek-ge-soc.c
index 0f3a153..f4f9412 100644
--- a/drivers/net/phy/mediatek-ge-soc.c
+++ b/drivers/net/phy/mediatek-ge-soc.c
@@ -216,6 +216,9 @@
#define MTK_PHY_LED_ON_LINK1000 BIT(0)
#define MTK_PHY_LED_ON_LINK100 BIT(1)
#define MTK_PHY_LED_ON_LINK10 BIT(2)
+#define MTK_PHY_LED_ON_LINK (MTK_PHY_LED_ON_LINK10 |\
+ MTK_PHY_LED_ON_LINK100 |\
+ MTK_PHY_LED_ON_LINK1000)
#define MTK_PHY_LED_ON_LINKDOWN BIT(3)
#define MTK_PHY_LED_ON_FDX BIT(4) /* Full duplex */
#define MTK_PHY_LED_ON_HDX BIT(5) /* Half duplex */
@@ -231,6 +234,12 @@
#define MTK_PHY_LED_BLINK_100RX BIT(3)
#define MTK_PHY_LED_BLINK_10TX BIT(4)
#define MTK_PHY_LED_BLINK_10RX BIT(5)
+#define MTK_PHY_LED_BLINK_RX (MTK_PHY_LED_BLINK_10RX |\
+ MTK_PHY_LED_BLINK_100RX |\
+ MTK_PHY_LED_BLINK_1000RX)
+#define MTK_PHY_LED_BLINK_TX (MTK_PHY_LED_BLINK_10TX |\
+ MTK_PHY_LED_BLINK_100TX |\
+ MTK_PHY_LED_BLINK_1000TX)
#define MTK_PHY_LED_BLINK_COLLISION BIT(6)
#define MTK_PHY_LED_BLINK_RX_CRC_ERR BIT(7)
#define MTK_PHY_LED_BLINK_RX_IDLE_ERR BIT(8)
@@ -1247,11 +1256,9 @@
if (blink < 0)
return -EIO;
- if ((on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 |
- MTK_PHY_LED_ON_LINK10)) ||
- (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX |
- MTK_PHY_LED_BLINK_10RX | MTK_PHY_LED_BLINK_1000TX |
- MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX)))
+ if ((on & (MTK_PHY_LED_ON_LINK | MTK_PHY_LED_ON_FDX | MTK_PHY_LED_ON_HDX |
+ MTK_PHY_LED_ON_LINKDOWN)) ||
+ (blink & (MTK_PHY_LED_BLINK_RX | MTK_PHY_LED_BLINK_TX)))
set_bit(bit_netdev, &priv->led_state);
else
clear_bit(bit_netdev, &priv->led_state);
@@ -1269,7 +1276,7 @@
if (!rules)
return 0;
- if (on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 | MTK_PHY_LED_ON_LINK10))
+ if (on & MTK_PHY_LED_ON_LINK)
*rules |= BIT(TRIGGER_NETDEV_LINK);
if (on & MTK_PHY_LED_ON_LINK10)
@@ -1287,10 +1294,10 @@
if (on & MTK_PHY_LED_ON_HDX)
*rules |= BIT(TRIGGER_NETDEV_HALF_DUPLEX);
- if (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX | MTK_PHY_LED_BLINK_10RX))
+ if (blink & MTK_PHY_LED_BLINK_RX)
*rules |= BIT(TRIGGER_NETDEV_RX);
- if (blink & (MTK_PHY_LED_BLINK_1000TX | MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX))
+ if (blink & MTK_PHY_LED_BLINK_TX)
*rules |= BIT(TRIGGER_NETDEV_TX);
return 0;
@@ -1323,15 +1330,19 @@
on |= MTK_PHY_LED_ON_LINK1000;
if (rules & BIT(TRIGGER_NETDEV_RX)) {
- blink |= MTK_PHY_LED_BLINK_10RX |
- MTK_PHY_LED_BLINK_100RX |
- MTK_PHY_LED_BLINK_1000RX;
+ blink |= (on & MTK_PHY_LED_ON_LINK) ?
+ (((on & MTK_PHY_LED_ON_LINK10) ? MTK_PHY_LED_BLINK_10RX : 0) |
+ ((on & MTK_PHY_LED_ON_LINK100) ? MTK_PHY_LED_BLINK_100RX : 0) |
+ ((on & MTK_PHY_LED_ON_LINK1000) ? MTK_PHY_LED_BLINK_1000RX : 0)) :
+ MTK_PHY_LED_BLINK_RX;
}
if (rules & BIT(TRIGGER_NETDEV_TX)) {
- blink |= MTK_PHY_LED_BLINK_10TX |
- MTK_PHY_LED_BLINK_100TX |
- MTK_PHY_LED_BLINK_1000TX;
+ blink |= (on & MTK_PHY_LED_ON_LINK) ?
+ (((on & MTK_PHY_LED_ON_LINK10) ? MTK_PHY_LED_BLINK_10TX : 0) |
+ ((on & MTK_PHY_LED_ON_LINK100) ? MTK_PHY_LED_BLINK_100TX : 0) |
+ ((on & MTK_PHY_LED_ON_LINK1000) ? MTK_PHY_LED_BLINK_1000TX : 0)) :
+ MTK_PHY_LED_BLINK_TX;
}
if (blink || on)
@@ -1344,9 +1355,7 @@
MTK_PHY_LED0_ON_CTRL,
MTK_PHY_LED_ON_FDX |
MTK_PHY_LED_ON_HDX |
- MTK_PHY_LED_ON_LINK10 |
- MTK_PHY_LED_ON_LINK100 |
- MTK_PHY_LED_ON_LINK1000,
+ MTK_PHY_LED_ON_LINK,
on);
if (ret)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0b3f21c..92da8c0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2125,14 +2125,16 @@
tun_is_little_endian(tun), true,
vlan_hlen)) {
struct skb_shared_info *sinfo = skb_shinfo(skb);
- pr_err("unexpected GSO type: "
- "0x%x, gso_size %d, hdr_len %d\n",
- sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
- tun16_to_cpu(tun, gso.hdr_len));
- print_hex_dump(KERN_ERR, "tun: ",
- DUMP_PREFIX_NONE,
- 16, 1, skb->head,
- min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
+
+ if (net_ratelimit()) {
+ netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
+ sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
+ tun16_to_cpu(tun, gso.hdr_len));
+ print_hex_dump(KERN_ERR, "tun: ",
+ DUMP_PREFIX_NONE,
+ 16, 1, skb->head,
+ min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
+ }
WARN_ON_ONCE(1);
return -EINVAL;
}
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index a9c4188..df9d767 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -1317,6 +1317,8 @@
netif_set_tso_max_size(dev->net, 16384);
+ ax88179_reset(dev);
+
return 0;
}
@@ -1454,21 +1456,16 @@
/* Skip IP alignment pseudo header */
skb_pull(skb, 2);
- skb->truesize = SKB_TRUESIZE(pkt_len_plus_padd);
ax88179_rx_checksum(skb, pkt_hdr);
return 1;
}
- ax_skb = skb_clone(skb, GFP_ATOMIC);
+ ax_skb = netdev_alloc_skb_ip_align(dev->net, pkt_len);
if (!ax_skb)
return 0;
- skb_trim(ax_skb, pkt_len);
+ skb_put(ax_skb, pkt_len);
+ memcpy(ax_skb->data, skb->data + 2, pkt_len);
- /* Skip IP alignment pseudo header */
- skb_pull(ax_skb, 2);
-
- skb->truesize = pkt_len_plus_padd +
- SKB_DATA_ALIGN(sizeof(struct sk_buff));
ax88179_rx_checksum(ax_skb, pkt_hdr);
usbnet_skb_return(dev, ax_skb);
@@ -1695,7 +1692,6 @@
.unbind = ax88179_unbind,
.status = ax88179_status,
.link_reset = ax88179_link_reset,
- .reset = ax88179_reset,
.stop = ax88179_stop,
.flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
@@ -1708,7 +1704,6 @@
.unbind = ax88179_unbind,
.status = ax88179_status,
.link_reset = ax88179_link_reset,
- .reset = ax88179_reset,
.stop = ax88179_stop,
.flags = FLAG_ETHER | FLAG_FRAMING_AX,
.rx_fixup = ax88179_rx_fixup,
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index e2e1813..a5469cf 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1368,6 +1368,9 @@
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990 */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990 */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a9, 0)}, /* Telit FN920C04 */
{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */
{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */
{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */
@@ -1431,6 +1434,7 @@
{QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */
{QMI_QUIRK_SET_DTR(0x1546, 0x1312, 4)}, /* u-blox LARA-R6 01B */
{QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */
+ {QMI_QUIRK_SET_DTR(0x33f8, 0x0104, 4)}, /* Rolling RW101 RMNET */
/* 4. Gobi 1000 devices */
{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c22d111..115c3c5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3807,6 +3807,7 @@
struct netlink_ext_ack *extack)
{
struct virtnet_info *vi = netdev_priv(dev);
+ bool update = false;
int i;
if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
@@ -3814,13 +3815,28 @@
return -EOPNOTSUPP;
if (rxfh->indir) {
+ if (!vi->has_rss)
+ return -EOPNOTSUPP;
+
for (i = 0; i < vi->rss_indir_table_size; ++i)
vi->ctrl->rss.indirection_table[i] = rxfh->indir[i];
+ update = true;
}
- if (rxfh->key)
- memcpy(vi->ctrl->rss.key, rxfh->key, vi->rss_key_size);
- virtnet_commit_rss_command(vi);
+ if (rxfh->key) {
+ /* If either _F_HASH_REPORT or _F_RSS are negotiated, the
+ * device provides hash calculation capabilities, that is,
+ * hash_key is configured.
+ */
+ if (!vi->has_rss && !vi->has_rss_hash_report)
+ return -EOPNOTSUPP;
+
+ memcpy(vi->ctrl->rss.key, rxfh->key, vi->rss_key_size);
+ update = true;
+ }
+
+ if (update)
+ virtnet_commit_rss_command(vi);
return 0;
}
@@ -4729,13 +4745,15 @@
if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT))
vi->has_rss_hash_report = true;
- if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS))
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) {
vi->has_rss = true;
- if (vi->has_rss || vi->has_rss_hash_report) {
vi->rss_indir_table_size =
virtio_cread16(vdev, offsetof(struct virtio_net_config,
rss_max_indirection_table_length));
+ }
+
+ if (vi->has_rss || vi->has_rss_hash_report) {
vi->rss_key_size =
virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size));
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 3495591..3a9148f 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1615,6 +1615,10 @@
if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
return false;
+ /* Ignore packets from invalid src-address */
+ if (!is_valid_ether_addr(eth_hdr(skb)->h_source))
+ return false;
+
/* Get address from the outer IP header */
if (vxlan_get_sk_family(vs) == AF_INET) {
saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
@@ -1670,6 +1674,7 @@
bool raw_proto = false;
void *oiph;
__be32 vni = 0;
+ int nh;
/* Need UDP and VXLAN header to be present */
if (!pskb_may_pull(skb, VXLAN_HLEN))
@@ -1758,12 +1763,28 @@
skb->pkt_type = PACKET_HOST;
}
- oiph = skb_network_header(skb);
+ /* Save offset of outer header relative to skb->head,
+ * because we are going to reset the network header to the inner header
+ * and might change skb->head.
+ */
+ nh = skb_network_header(skb) - skb->head;
+
skb_reset_network_header(skb);
+ if (!pskb_inet_may_pull(skb)) {
+ DEV_STATS_INC(vxlan->dev, rx_length_errors);
+ DEV_STATS_INC(vxlan->dev, rx_errors);
+ vxlan_vnifilter_count(vxlan, vni, vninode,
+ VXLAN_VNI_STATS_RX_ERRORS, 0);
+ goto drop;
+ }
+
+ /* Get the outer header. */
+ oiph = skb->head + nh;
+
if (!vxlan_ecn_decapsulate(vs, oiph, skb)) {
- ++vxlan->dev->stats.rx_frame_errors;
- ++vxlan->dev->stats.rx_errors;
+ DEV_STATS_INC(vxlan->dev, rx_frame_errors);
+ DEV_STATS_INC(vxlan->dev, rx_errors);
vxlan_vnifilter_count(vxlan, vni, vninode,
VXLAN_VNI_STATS_RX_ERRORS, 0);
goto drop;
@@ -1833,7 +1854,9 @@
goto out;
if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
- dev->stats.tx_dropped++;
+ dev_core_stats_tx_dropped_inc(dev);
+ vxlan_vnifilter_count(vxlan, vni, NULL,
+ VXLAN_VNI_STATS_TX_DROPS, 0);
goto out;
}
parp = arp_hdr(skb);
@@ -1889,7 +1912,7 @@
reply->pkt_type = PACKET_HOST;
if (netif_rx(reply) == NET_RX_DROP) {
- dev->stats.rx_dropped++;
+ dev_core_stats_rx_dropped_inc(dev);
vxlan_vnifilter_count(vxlan, vni, NULL,
VXLAN_VNI_STATS_RX_DROPS, 0);
}
@@ -2048,7 +2071,7 @@
goto out;
if (netif_rx(reply) == NET_RX_DROP) {
- dev->stats.rx_dropped++;
+ dev_core_stats_rx_dropped_inc(dev);
vxlan_vnifilter_count(vxlan, vni, NULL,
VXLAN_VNI_STATS_RX_DROPS, 0);
}
@@ -2259,7 +2282,7 @@
len);
} else {
drop:
- dev->stats.rx_dropped++;
+ dev_core_stats_rx_dropped_inc(dev);
vxlan_vnifilter_count(dst_vxlan, vni, NULL,
VXLAN_VNI_STATS_RX_DROPS, 0);
}
@@ -2291,7 +2314,7 @@
addr_family, dst_port,
vxlan->cfg.flags);
if (!dst_vxlan) {
- dev->stats.tx_errors++;
+ DEV_STATS_INC(dev, tx_errors);
vxlan_vnifilter_count(vxlan, vni, NULL,
VXLAN_VNI_STATS_TX_ERRORS, 0);
kfree_skb(skb);
@@ -2555,7 +2578,7 @@
return;
drop:
- dev->stats.tx_dropped++;
+ dev_core_stats_tx_dropped_inc(dev);
vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0);
dev_kfree_skb(skb);
return;
@@ -2563,11 +2586,11 @@
tx_error:
rcu_read_unlock();
if (err == -ELOOP)
- dev->stats.collisions++;
+ DEV_STATS_INC(dev, collisions);
else if (err == -ENETUNREACH)
- dev->stats.tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
dst_release(ndst);
- dev->stats.tx_errors++;
+ DEV_STATS_INC(dev, tx_errors);
vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0);
kfree_skb(skb);
}
@@ -2600,7 +2623,7 @@
return;
drop:
- dev->stats.tx_dropped++;
+ dev_core_stats_tx_dropped_inc(dev);
vxlan_vnifilter_count(netdev_priv(dev), vni, NULL,
VXLAN_VNI_STATS_TX_DROPS, 0);
dev_kfree_skb(skb);
@@ -2638,7 +2661,7 @@
return NETDEV_TX_OK;
drop:
- dev->stats.tx_dropped++;
+ dev_core_stats_tx_dropped_inc(dev);
vxlan_vnifilter_count(netdev_priv(dev), vni, NULL,
VXLAN_VNI_STATS_TX_DROPS, 0);
dev_kfree_skb(skb);
@@ -2735,7 +2758,7 @@
!is_multicast_ether_addr(eth->h_dest))
vxlan_fdb_miss(vxlan, eth->h_dest);
- dev->stats.tx_dropped++;
+ dev_core_stats_tx_dropped_inc(dev);
vxlan_vnifilter_count(vxlan, vni, NULL,
VXLAN_VNI_STATS_TX_DROPS, 0);
kfree_skb(skb);
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index a6a37d6..9f4bf41 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -9020,6 +9020,7 @@
offload = &arvif->arp_ns_offload;
count = 0;
+ /* Note: read_lock_bh() calls rcu_read_lock() */
read_lock_bh(&idev->lock);
memset(offload->ipv6_addr, 0, sizeof(offload->ipv6_addr));
@@ -9050,7 +9051,8 @@
}
/* get anycast address */
- for (ifaca6 = idev->ac_list; ifaca6; ifaca6 = ifaca6->aca_next) {
+ for (ifaca6 = rcu_dereference(idev->ac_list); ifaca6;
+ ifaca6 = rcu_dereference(ifaca6->aca_next)) {
if (count >= ATH11K_IPV6_MAX_COUNT)
goto generate;
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index 072b0a5..eca1457 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -10,7 +10,7 @@
#include "fw/api/txq.h"
/* Highest firmware API version supported */
-#define IWL_BZ_UCODE_API_MAX 90
+#define IWL_BZ_UCODE_API_MAX 89
/* Lowest firmware API version supported */
#define IWL_BZ_UCODE_API_MIN 80
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index 9b79279..dbbcb2d 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -10,7 +10,7 @@
#include "fw/api/txq.h"
/* Highest firmware API version supported */
-#define IWL_SC_UCODE_API_MAX 90
+#define IWL_SC_UCODE_API_MAX 89
/* Lowest firmware API version supported */
#define IWL_SC_UCODE_API_MIN 82
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index 4863a3c..d84d7e9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -53,6 +53,8 @@
if (!pasn)
return -ENOBUFS;
+ iwl_mvm_ftm_remove_pasn_sta(mvm, addr);
+
pasn->cipher = iwl_mvm_cipher_to_location_cipher(cipher);
switch (pasn->cipher) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index 9f69e04..fe5bba8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -279,6 +279,7 @@
RCU_INIT_POINTER(mvm->link_id_to_link_conf[link_info->fw_link_id],
NULL);
+ iwl_mvm_release_fw_link_id(mvm, link_info->fw_link_id);
return 0;
}
@@ -296,7 +297,6 @@
return 0;
cmd.link_id = cpu_to_le32(link_info->fw_link_id);
- iwl_mvm_release_fw_link_id(mvm, link_info->fw_link_id);
link_info->fw_link_id = IWL_MVM_FW_LINK_ID_INVALID;
cmd.spec_link_id = link_conf->link_id;
cmd.phy_id = cpu_to_le32(FW_CTXT_INVALID);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index f3e3986..11559563 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -2813,7 +2813,8 @@
if (ver_handler->version != scan_ver)
continue;
- return ver_handler->handler(mvm, vif, params, type, uid);
+ err = ver_handler->handler(mvm, vif, params, type, uid);
+ return err ? : uid;
}
err = iwl_mvm_scan_umac(mvm, vif, params, type, uid);
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index b55fe32..59e1fc0 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -3899,7 +3899,7 @@
}
nla_for_each_nested(peer, peers, rem) {
- struct cfg80211_pmsr_result result;
+ struct cfg80211_pmsr_result result = {};
err = mac80211_hwsim_parse_pmsr_result(peer, &result, info);
if (err)
diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c
index 7eb17f4..9e1a34e 100644
--- a/drivers/nfc/trf7970a.c
+++ b/drivers/nfc/trf7970a.c
@@ -424,7 +424,8 @@
enum trf7970a_state state;
struct device *dev;
struct spi_device *spi;
- struct regulator *regulator;
+ struct regulator *vin_regulator;
+ struct regulator *vddio_regulator;
struct nfc_digital_dev *ddev;
u32 quirks;
bool is_initiator;
@@ -1883,7 +1884,7 @@
if (trf->state != TRF7970A_ST_PWR_OFF)
return 0;
- ret = regulator_enable(trf->regulator);
+ ret = regulator_enable(trf->vin_regulator);
if (ret) {
dev_err(trf->dev, "%s - Can't enable VIN: %d\n", __func__, ret);
return ret;
@@ -1926,7 +1927,7 @@
if (trf->en2_gpiod && !(trf->quirks & TRF7970A_QUIRK_EN2_MUST_STAY_LOW))
gpiod_set_value_cansleep(trf->en2_gpiod, 0);
- ret = regulator_disable(trf->regulator);
+ ret = regulator_disable(trf->vin_regulator);
if (ret)
dev_err(trf->dev, "%s - Can't disable VIN: %d\n", __func__,
ret);
@@ -2065,37 +2066,37 @@
mutex_init(&trf->lock);
INIT_DELAYED_WORK(&trf->timeout_work, trf7970a_timeout_work_handler);
- trf->regulator = devm_regulator_get(&spi->dev, "vin");
- if (IS_ERR(trf->regulator)) {
- ret = PTR_ERR(trf->regulator);
+ trf->vin_regulator = devm_regulator_get(&spi->dev, "vin");
+ if (IS_ERR(trf->vin_regulator)) {
+ ret = PTR_ERR(trf->vin_regulator);
dev_err(trf->dev, "Can't get VIN regulator: %d\n", ret);
goto err_destroy_lock;
}
- ret = regulator_enable(trf->regulator);
+ ret = regulator_enable(trf->vin_regulator);
if (ret) {
dev_err(trf->dev, "Can't enable VIN: %d\n", ret);
goto err_destroy_lock;
}
- uvolts = regulator_get_voltage(trf->regulator);
+ uvolts = regulator_get_voltage(trf->vin_regulator);
if (uvolts > 4000000)
trf->chip_status_ctrl = TRF7970A_CHIP_STATUS_VRS5_3;
- trf->regulator = devm_regulator_get(&spi->dev, "vdd-io");
- if (IS_ERR(trf->regulator)) {
- ret = PTR_ERR(trf->regulator);
+ trf->vddio_regulator = devm_regulator_get(&spi->dev, "vdd-io");
+ if (IS_ERR(trf->vddio_regulator)) {
+ ret = PTR_ERR(trf->vddio_regulator);
dev_err(trf->dev, "Can't get VDD_IO regulator: %d\n", ret);
- goto err_destroy_lock;
+ goto err_disable_vin_regulator;
}
- ret = regulator_enable(trf->regulator);
+ ret = regulator_enable(trf->vddio_regulator);
if (ret) {
dev_err(trf->dev, "Can't enable VDD_IO: %d\n", ret);
- goto err_destroy_lock;
+ goto err_disable_vin_regulator;
}
- if (regulator_get_voltage(trf->regulator) == 1800000) {
+ if (regulator_get_voltage(trf->vddio_regulator) == 1800000) {
trf->io_ctrl = TRF7970A_REG_IO_CTRL_IO_LOW;
dev_dbg(trf->dev, "trf7970a config vdd_io to 1.8V\n");
}
@@ -2108,7 +2109,7 @@
if (!trf->ddev) {
dev_err(trf->dev, "Can't allocate NFC digital device\n");
ret = -ENOMEM;
- goto err_disable_regulator;
+ goto err_disable_vddio_regulator;
}
nfc_digital_set_parent_dev(trf->ddev, trf->dev);
@@ -2137,8 +2138,10 @@
trf7970a_shutdown(trf);
err_free_ddev:
nfc_digital_free_device(trf->ddev);
-err_disable_regulator:
- regulator_disable(trf->regulator);
+err_disable_vddio_regulator:
+ regulator_disable(trf->vddio_regulator);
+err_disable_vin_regulator:
+ regulator_disable(trf->vin_regulator);
err_destroy_lock:
mutex_destroy(&trf->lock);
return ret;
@@ -2157,7 +2160,8 @@
nfc_digital_unregister_device(trf->ddev);
nfc_digital_free_device(trf->ddev);
- regulator_disable(trf->regulator);
+ regulator_disable(trf->vddio_regulator);
+ regulator_disable(trf->vin_regulator);
mutex_destroy(&trf->lock);
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 27281a9..095f59e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -629,27 +629,6 @@
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
/*
- * Returns true for sink states that can't ever transition back to live.
- */
-static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
-{
- switch (nvme_ctrl_state(ctrl)) {
- case NVME_CTRL_NEW:
- case NVME_CTRL_LIVE:
- case NVME_CTRL_RESETTING:
- case NVME_CTRL_CONNECTING:
- return false;
- case NVME_CTRL_DELETING:
- case NVME_CTRL_DELETING_NOIO:
- case NVME_CTRL_DEAD:
- return true;
- default:
- WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
- return true;
- }
-}
-
-/*
* Waits for the controller state to be resetting, or returns false if it is
* not possible to ever transition to that state.
*/
@@ -3681,7 +3660,7 @@
"Found shared namespace %d, but multipathing not supported.\n",
info->nsid);
dev_warn_once(ctrl->device,
- "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0\n.");
+ "Support for shared namespaces without CONFIG_NVME_MULTIPATH is deprecated and will be removed in Linux 6.0.\n");
}
}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5397fb4..d16e976 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -247,7 +247,8 @@
if (nvme_path_is_disabled(ns))
continue;
- if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
+ if (ns->ctrl->numa_node != NUMA_NO_NODE &&
+ READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
distance = node_distance(node, ns->ctrl->numa_node);
else
distance = LOCAL_DISTANCE;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index d0ed64d..b564c5f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -741,6 +741,27 @@
nvme_tag_from_cid(command_id) >= NVME_AQ_BLK_MQ_DEPTH;
}
+/*
+ * Returns true for sink states that can't ever transition back to live.
+ */
+static inline bool nvme_state_terminal(struct nvme_ctrl *ctrl)
+{
+ switch (nvme_ctrl_state(ctrl)) {
+ case NVME_CTRL_NEW:
+ case NVME_CTRL_LIVE:
+ case NVME_CTRL_RESETTING:
+ case NVME_CTRL_CONNECTING:
+ return false;
+ case NVME_CTRL_DELETING:
+ case NVME_CTRL_DELETING_NOIO:
+ case NVME_CTRL_DEAD:
+ return true;
+ default:
+ WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
+ return true;
+ }
+}
+
void nvme_complete_rq(struct request *req);
void nvme_complete_batch_req(struct request *req);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8e0bb96..e393f69 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1286,6 +1286,9 @@
u32 csts = readl(dev->bar + NVME_REG_CSTS);
u8 opcode;
+ if (nvme_state_terminal(&dev->ctrl))
+ goto disable;
+
/* If PCI error recovery process is happening, we cannot reset or
* the recovery mechanism will surely fail.
*/
@@ -1390,8 +1393,11 @@
return BLK_EH_RESET_TIMER;
disable:
- if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) {
+ if (nvme_state_terminal(&dev->ctrl))
+ nvme_dev_disable(dev, true);
return BLK_EH_DONE;
+ }
nvme_dev_disable(dev, false);
if (nvme_try_sched_reset(&dev->ctrl))
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index fdbcdce..28bc2f3 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -360,12 +360,18 @@
} while (ret > 0);
}
-static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+static inline bool nvme_tcp_queue_has_pending(struct nvme_tcp_queue *queue)
{
return !list_empty(&queue->send_list) ||
!llist_empty(&queue->req_list);
}
+static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+{
+ return !nvme_tcp_tls(&queue->ctrl->ctrl) &&
+ nvme_tcp_queue_has_pending(queue);
+}
+
static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
bool sync, bool last)
{
@@ -386,7 +392,7 @@
mutex_unlock(&queue->send_mutex);
}
- if (last && nvme_tcp_queue_more(queue))
+ if (last && nvme_tcp_queue_has_pending(queue))
queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
}
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index 3ddbc38..fb518b0 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -285,9 +285,9 @@
}
if (shash_len != crypto_shash_digestsize(shash_tfm)) {
- pr_debug("%s: hash len mismatch (len %d digest %d)\n",
- __func__, shash_len,
- crypto_shash_digestsize(shash_tfm));
+ pr_err("%s: hash len mismatch (len %d digest %d)\n",
+ __func__, shash_len,
+ crypto_shash_digestsize(shash_tfm));
ret = -EINVAL;
goto out_free_tfm;
}
@@ -370,7 +370,7 @@
nvme_auth_free_key(transformed_key);
out_free_tfm:
crypto_free_shash(shash_tfm);
- return 0;
+ return ret;
}
int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index a232533..89a0011 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -754,6 +754,19 @@
NULL,
};
+bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid)
+{
+ struct config_item *ns_item;
+ char name[4] = {};
+
+ if (sprintf(name, "%u", nsid) <= 0)
+ return false;
+ mutex_lock(&subsys->namespaces_group.cg_subsys->su_mutex);
+ ns_item = config_group_find_item(&subsys->namespaces_group, name);
+ mutex_unlock(&subsys->namespaces_group.cg_subsys->su_mutex);
+ return ns_item != NULL;
+}
+
static void nvmet_ns_release(struct config_item *item)
{
struct nvmet_ns *ns = to_nvmet_ns(item);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 8860a3e..e06013c 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -437,10 +437,13 @@
u16 nvmet_req_find_ns(struct nvmet_req *req)
{
u32 nsid = le32_to_cpu(req->cmd->common.nsid);
+ struct nvmet_subsys *subsys = nvmet_req_subsys(req);
- req->ns = xa_load(&nvmet_req_subsys(req)->namespaces, nsid);
+ req->ns = xa_load(&subsys->namespaces, nsid);
if (unlikely(!req->ns)) {
req->error_loc = offsetof(struct nvme_common_command, nsid);
+ if (nvmet_subsys_nsid_exists(subsys, nsid))
+ return NVME_SC_INTERNAL_PATH_ERROR;
return NVME_SC_INVALID_NS | NVME_SC_DNR;
}
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index f460728..c1306de 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -543,6 +543,7 @@
struct nvmet_host *host);
void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
u8 event_info, u8 log_page);
+bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid);
#define NVMET_MIN_QUEUE_SIZE 16
#define NVMET_MAX_QUEUE_SIZE 1024
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index a5422e2..380f22e 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -348,6 +348,7 @@
return 0;
}
+/* If cmd buffers are NULL, no operation is performed */
static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd)
{
kfree(cmd->iov);
@@ -1581,13 +1582,9 @@
struct nvmet_tcp_cmd *cmd = queue->cmds;
int i;
- for (i = 0; i < queue->nr_cmds; i++, cmd++) {
- if (nvmet_tcp_need_data_in(cmd))
- nvmet_tcp_free_cmd_buffers(cmd);
- }
-
- if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect))
- nvmet_tcp_free_cmd_buffers(&queue->connect);
+ for (i = 0; i < queue->nr_cmds; i++, cmd++)
+ nvmet_tcp_free_cmd_buffers(cmd);
+ nvmet_tcp_free_cmd_buffers(&queue->connect);
}
static void nvmet_tcp_release_queue_work(struct work_struct *w)
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index bf48332..eff7f5d 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3766,14 +3766,6 @@
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CAVIUM, 0xa100, quirk_no_bus_reset);
/*
- * Apparently the LSI / Agere FW643 can't recover after a Secondary Bus
- * Reset and requires a power-off or suspend/resume and rescan. Prevent
- * use of that reset.
- */
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATT, 0x5900, quirk_no_bus_reset);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATT, 0x5901, quirk_no_bus_reset);
-
-/*
* Some TI KeyStone C667X devices do not support bus/hot reset. The PCIESS
* automatically disables LTSSM when Secondary Bus Reset is received and
* the device stops working. Prevent bus reset for these devices. With
diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
index b700f52..11fcb18 100644
--- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
+++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
@@ -110,8 +110,10 @@
/* Source clock from SoC internal PLL */
writel(ANA_PLL_CLK_OUT_TO_EXT_IO_SEL,
imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG062);
- writel(AUX_PLL_REFCLK_SEL_SYS_PLL,
- imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG063);
+ if (imx8_phy->drvdata->variant != IMX8MM) {
+ writel(AUX_PLL_REFCLK_SEL_SYS_PLL,
+ imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG063);
+ }
val = ANA_AUX_RX_TX_SEL_TX | ANA_AUX_TX_TERM;
writel(val | ANA_AUX_RX_TERM_GND_EN,
imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG064);
diff --git a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c
index 41162d7..1d1db17 100644
--- a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c
+++ b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c
@@ -603,7 +603,7 @@
u16 val;
fix_idx = 0;
- for (addr = 0; addr < 512; addr++) {
+ for (addr = 0; addr < ARRAY_SIZE(gbe_phy_init); addr++) {
/*
* All PHY register values are defined in full for 3.125Gbps
* SERDES speed. The values required for 1.25 Gbps are almost
@@ -611,11 +611,12 @@
* comparison to 3.125 Gbps values. These register values are
* stored in "gbe_phy_init_fix" array.
*/
- if (!is_1gbps && gbe_phy_init_fix[fix_idx].addr == addr) {
+ if (!is_1gbps &&
+ fix_idx < ARRAY_SIZE(gbe_phy_init_fix) &&
+ gbe_phy_init_fix[fix_idx].addr == addr) {
/* Use new value */
val = gbe_phy_init_fix[fix_idx].value;
- if (fix_idx < ARRAY_SIZE(gbe_phy_init_fix))
- fix_idx++;
+ fix_idx++;
} else {
val = gbe_phy_init[addr];
}
diff --git a/drivers/phy/qualcomm/phy-qcom-m31.c b/drivers/phy/qualcomm/phy-qcom-m31.c
index 03fb0d4..20d4c02 100644
--- a/drivers/phy/qualcomm/phy-qcom-m31.c
+++ b/drivers/phy/qualcomm/phy-qcom-m31.c
@@ -297,7 +297,7 @@
return dev_err_probe(dev, PTR_ERR(qphy->phy),
"failed to create phy\n");
- qphy->vreg = devm_regulator_get(dev, "vdda-phy");
+ qphy->vreg = devm_regulator_get(dev, "vdd");
if (IS_ERR(qphy->vreg))
return dev_err_probe(dev, PTR_ERR(qphy->vreg),
"failed to get vreg\n");
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
index 7d585a4..c21cdb8 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c
@@ -77,6 +77,7 @@
QPHY_COM_BIAS_EN_CLKBUFLR_EN,
QPHY_DP_PHY_STATUS,
+ QPHY_DP_PHY_VCO_DIV,
QPHY_TX_TX_POL_INV,
QPHY_TX_TX_DRV_LVL,
@@ -102,6 +103,7 @@
[QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN,
[QPHY_DP_PHY_STATUS] = QSERDES_V3_DP_PHY_STATUS,
+ [QPHY_DP_PHY_VCO_DIV] = QSERDES_V3_DP_PHY_VCO_DIV,
[QPHY_TX_TX_POL_INV] = QSERDES_V3_TX_TX_POL_INV,
[QPHY_TX_TX_DRV_LVL] = QSERDES_V3_TX_TX_DRV_LVL,
@@ -126,6 +128,7 @@
[QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V4_COM_BIAS_EN_CLKBUFLR_EN,
[QPHY_DP_PHY_STATUS] = QSERDES_V4_DP_PHY_STATUS,
+ [QPHY_DP_PHY_VCO_DIV] = QSERDES_V4_DP_PHY_VCO_DIV,
[QPHY_TX_TX_POL_INV] = QSERDES_V4_TX_TX_POL_INV,
[QPHY_TX_TX_DRV_LVL] = QSERDES_V4_TX_TX_DRV_LVL,
@@ -150,6 +153,7 @@
[QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V5_COM_BIAS_EN_CLKBUFLR_EN,
[QPHY_DP_PHY_STATUS] = QSERDES_V5_DP_PHY_STATUS,
+ [QPHY_DP_PHY_VCO_DIV] = QSERDES_V5_DP_PHY_VCO_DIV,
[QPHY_TX_TX_POL_INV] = QSERDES_V5_5NM_TX_TX_POL_INV,
[QPHY_TX_TX_DRV_LVL] = QSERDES_V5_5NM_TX_TX_DRV_LVL,
@@ -174,6 +178,7 @@
[QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V6_COM_PLL_BIAS_EN_CLK_BUFLR_EN,
[QPHY_DP_PHY_STATUS] = QSERDES_V6_DP_PHY_STATUS,
+ [QPHY_DP_PHY_VCO_DIV] = QSERDES_V6_DP_PHY_VCO_DIV,
[QPHY_TX_TX_POL_INV] = QSERDES_V6_TX_TX_POL_INV,
[QPHY_TX_TX_DRV_LVL] = QSERDES_V6_TX_TX_DRV_LVL,
@@ -2150,9 +2155,9 @@
writel(val, qmp->dp_dp_phy + QSERDES_DP_PHY_PD_CTL);
if (reverse)
- writel(0x4c, qmp->pcs + QSERDES_DP_PHY_MODE);
+ writel(0x4c, qmp->dp_dp_phy + QSERDES_DP_PHY_MODE);
else
- writel(0x5c, qmp->pcs + QSERDES_DP_PHY_MODE);
+ writel(0x5c, qmp->dp_dp_phy + QSERDES_DP_PHY_MODE);
return reverse;
}
@@ -2162,6 +2167,7 @@
const struct phy_configure_opts_dp *dp_opts = &qmp->dp_opts;
u32 phy_vco_div;
unsigned long pixel_freq;
+ const struct qmp_phy_cfg *cfg = qmp->cfg;
switch (dp_opts->link_rate) {
case 1620:
@@ -2184,7 +2190,7 @@
/* Other link rates aren't supported */
return -EINVAL;
}
- writel(phy_vco_div, qmp->dp_dp_phy + QSERDES_V4_DP_PHY_VCO_DIV);
+ writel(phy_vco_div, qmp->dp_dp_phy + cfg->regs[QPHY_DP_PHY_VCO_DIV]);
clk_set_rate(qmp->dp_link_hw.clk, dp_opts->link_rate * 100000);
clk_set_rate(qmp->dp_pixel_hw.clk, pixel_freq);
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v5.h b/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v5.h
index f5cfacf..1810574 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v5.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v5.h
@@ -7,6 +7,7 @@
#define QCOM_PHY_QMP_DP_PHY_V5_H_
/* Only for QMP V5 PHY - DP PHY registers */
+#define QSERDES_V5_DP_PHY_VCO_DIV 0x070
#define QSERDES_V5_DP_PHY_AUX_INTERRUPT_STATUS 0x0d8
#define QSERDES_V5_DP_PHY_STATUS 0x0dc
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v6.h
index 01a20d3..fa967a1 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v6.h
@@ -7,6 +7,7 @@
#define QCOM_PHY_QMP_DP_PHY_V6_H_
/* Only for QMP V6 PHY - DP PHY registers */
+#define QSERDES_V6_DP_PHY_VCO_DIV 0x070
#define QSERDES_V6_DP_PHY_AUX_INTERRUPT_STATUS 0x0e0
#define QSERDES_V6_DP_PHY_STATUS 0x0e4
diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig
index a34f67b..b60a4b6 100644
--- a/drivers/phy/rockchip/Kconfig
+++ b/drivers/phy/rockchip/Kconfig
@@ -87,6 +87,7 @@
tristate "Rockchip Samsung HDMI/eDP Combo PHY driver"
depends on (ARCH_ROCKCHIP || COMPILE_TEST) && OF
select GENERIC_PHY
+ select RATIONAL
help
Enable this to support the Rockchip HDMI/eDP Combo PHY
with Samsung IP block.
diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
index 76b9cf4..bf74e42 100644
--- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
@@ -125,12 +125,15 @@
};
struct rockchip_combphy_cfg {
+ unsigned int num_phys;
+ unsigned int phy_ids[3];
const struct rockchip_combphy_grfcfg *grfcfg;
int (*combphy_cfg)(struct rockchip_combphy_priv *priv);
};
struct rockchip_combphy_priv {
u8 type;
+ int id;
void __iomem *mmio;
int num_clks;
struct clk_bulk_data *clks;
@@ -320,7 +323,7 @@
struct rockchip_combphy_priv *priv;
const struct rockchip_combphy_cfg *phy_cfg;
struct resource *res;
- int ret;
+ int ret, id;
phy_cfg = of_device_get_match_data(dev);
if (!phy_cfg) {
@@ -338,6 +341,15 @@
return ret;
}
+ /* find the phy-id from the io address */
+ priv->id = -ENODEV;
+ for (id = 0; id < phy_cfg->num_phys; id++) {
+ if (res->start == phy_cfg->phy_ids[id]) {
+ priv->id = id;
+ break;
+ }
+ }
+
priv->dev = dev;
priv->type = PHY_NONE;
priv->cfg = phy_cfg;
@@ -562,6 +574,12 @@
};
static const struct rockchip_combphy_cfg rk3568_combphy_cfgs = {
+ .num_phys = 3,
+ .phy_ids = {
+ 0xfe820000,
+ 0xfe830000,
+ 0xfe840000,
+ },
.grfcfg = &rk3568_combphy_grfcfgs,
.combphy_cfg = rk3568_combphy_cfg,
};
@@ -578,8 +596,14 @@
rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_pcie, true);
rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_pcie, true);
rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_pcie, true);
- rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l0_sel, true);
- rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l1_sel, true);
+ switch (priv->id) {
+ case 1:
+ rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l0_sel, true);
+ break;
+ case 2:
+ rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l1_sel, true);
+ break;
+ }
break;
case PHY_TYPE_USB3:
/* Set SSC downward spread spectrum */
@@ -736,6 +760,12 @@
};
static const struct rockchip_combphy_cfg rk3588_combphy_cfgs = {
+ .num_phys = 3,
+ .phy_ids = {
+ 0xfee00000,
+ 0xfee10000,
+ 0xfee20000,
+ },
.grfcfg = &rk3588_combphy_grfcfgs,
.combphy_cfg = rk3588_combphy_cfg,
};
diff --git a/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c b/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c
index 121e596..9857ee4 100644
--- a/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c
+++ b/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c
@@ -40,6 +40,8 @@
#define RK3588_BIFURCATION_LANE_0_1 BIT(0)
#define RK3588_BIFURCATION_LANE_2_3 BIT(1)
#define RK3588_LANE_AGGREGATION BIT(2)
+#define RK3588_PCIE1LN_SEL_EN (GENMASK(1, 0) << 16)
+#define RK3588_PCIE30_PHY_MODE_EN (GENMASK(2, 0) << 16)
struct rockchip_p3phy_ops;
@@ -132,7 +134,7 @@
static int rockchip_p3phy_rk3588_init(struct rockchip_p3phy_priv *priv)
{
u32 reg = 0;
- u8 mode = 0;
+ u8 mode = RK3588_LANE_AGGREGATION; /* default */
int ret;
/* Deassert PCIe PMA output clamp mode */
@@ -140,31 +142,24 @@
/* Set bifurcation if needed */
for (int i = 0; i < priv->num_lanes; i++) {
- if (!priv->lanes[i])
- mode |= (BIT(i) << 3);
-
if (priv->lanes[i] > 1)
- mode |= (BIT(i) >> 1);
+ mode &= ~RK3588_LANE_AGGREGATION;
+ if (priv->lanes[i] == 3)
+ mode |= RK3588_BIFURCATION_LANE_0_1;
+ if (priv->lanes[i] == 4)
+ mode |= RK3588_BIFURCATION_LANE_2_3;
}
- if (!mode)
- reg = RK3588_LANE_AGGREGATION;
- else {
- if (mode & (BIT(0) | BIT(1)))
- reg |= RK3588_BIFURCATION_LANE_0_1;
-
- if (mode & (BIT(2) | BIT(3)))
- reg |= RK3588_BIFURCATION_LANE_2_3;
- }
-
- regmap_write(priv->phy_grf, RK3588_PCIE3PHY_GRF_CMN_CON0, (0x7<<16) | reg);
+ reg = mode;
+ regmap_write(priv->phy_grf, RK3588_PCIE3PHY_GRF_CMN_CON0,
+ RK3588_PCIE30_PHY_MODE_EN | reg);
/* Set pcie1ln_sel in PHP_GRF_PCIESEL_CON */
if (!IS_ERR(priv->pipe_grf)) {
- reg = (mode & (BIT(6) | BIT(7))) >> 6;
+ reg = mode & (RK3588_BIFURCATION_LANE_0_1 | RK3588_BIFURCATION_LANE_2_3);
if (reg)
regmap_write(priv->pipe_grf, PHP_GRF_PCIESEL_CON,
- (reg << 16) | reg);
+ RK3588_PCIE1LN_SEL_EN | reg);
}
reset_control_deassert(priv->p30phy);
diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c
index 13cd614..751fecd 100644
--- a/drivers/phy/ti/phy-tusb1210.c
+++ b/drivers/phy/ti/phy-tusb1210.c
@@ -69,7 +69,6 @@
struct delayed_work chg_det_work;
struct notifier_block psy_nb;
struct power_supply *psy;
- struct power_supply *charger;
#endif
};
@@ -236,19 +235,24 @@
static bool tusb1210_get_online(struct tusb1210 *tusb)
{
+ struct power_supply *charger = NULL;
union power_supply_propval val;
- int i;
+ bool online = false;
+ int i, ret;
- for (i = 0; i < ARRAY_SIZE(tusb1210_chargers) && !tusb->charger; i++)
- tusb->charger = power_supply_get_by_name(tusb1210_chargers[i]);
+ for (i = 0; i < ARRAY_SIZE(tusb1210_chargers) && !charger; i++)
+ charger = power_supply_get_by_name(tusb1210_chargers[i]);
- if (!tusb->charger)
+ if (!charger)
return false;
- if (power_supply_get_property(tusb->charger, POWER_SUPPLY_PROP_ONLINE, &val))
- return false;
+ ret = power_supply_get_property(charger, POWER_SUPPLY_PROP_ONLINE, &val);
+ if (ret == 0)
+ online = val.intval;
- return val.intval;
+ power_supply_put(charger);
+
+ return online;
}
static void tusb1210_chg_det_work(struct work_struct *work)
@@ -473,9 +477,6 @@
cancel_delayed_work_sync(&tusb->chg_det_work);
power_supply_unregister(tusb->psy);
}
-
- if (tusb->charger)
- power_supply_put(tusb->charger);
}
#else
static void tusb1210_probe_charger_detect(struct tusb1210 *tusb) { }
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
index d376fa7..029efe1 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
@@ -43,7 +43,7 @@
#define SCU614 0x614 /* Disable GPIO Internal Pull-Down #1 */
#define SCU618 0x618 /* Disable GPIO Internal Pull-Down #2 */
#define SCU61C 0x61c /* Disable GPIO Internal Pull-Down #3 */
-#define SCU620 0x620 /* Disable GPIO Internal Pull-Down #4 */
+#define SCU630 0x630 /* Disable GPIO Internal Pull-Down #4 */
#define SCU634 0x634 /* Disable GPIO Internal Pull-Down #5 */
#define SCU638 0x638 /* Disable GPIO Internal Pull-Down #6 */
#define SCU690 0x690 /* Multi-function Pin Control #24 */
@@ -2495,38 +2495,38 @@
ASPEED_PULL_DOWN_PINCONF(D14, SCU61C, 0),
/* GPIOS7 */
- ASPEED_PULL_DOWN_PINCONF(T24, SCU620, 23),
+ ASPEED_PULL_DOWN_PINCONF(T24, SCU630, 23),
/* GPIOS6 */
- ASPEED_PULL_DOWN_PINCONF(P23, SCU620, 22),
+ ASPEED_PULL_DOWN_PINCONF(P23, SCU630, 22),
/* GPIOS5 */
- ASPEED_PULL_DOWN_PINCONF(P24, SCU620, 21),
+ ASPEED_PULL_DOWN_PINCONF(P24, SCU630, 21),
/* GPIOS4 */
- ASPEED_PULL_DOWN_PINCONF(R26, SCU620, 20),
+ ASPEED_PULL_DOWN_PINCONF(R26, SCU630, 20),
/* GPIOS3*/
- ASPEED_PULL_DOWN_PINCONF(R24, SCU620, 19),
+ ASPEED_PULL_DOWN_PINCONF(R24, SCU630, 19),
/* GPIOS2 */
- ASPEED_PULL_DOWN_PINCONF(T26, SCU620, 18),
+ ASPEED_PULL_DOWN_PINCONF(T26, SCU630, 18),
/* GPIOS1 */
- ASPEED_PULL_DOWN_PINCONF(T25, SCU620, 17),
+ ASPEED_PULL_DOWN_PINCONF(T25, SCU630, 17),
/* GPIOS0 */
- ASPEED_PULL_DOWN_PINCONF(R23, SCU620, 16),
+ ASPEED_PULL_DOWN_PINCONF(R23, SCU630, 16),
/* GPIOR7 */
- ASPEED_PULL_DOWN_PINCONF(U26, SCU620, 15),
+ ASPEED_PULL_DOWN_PINCONF(U26, SCU630, 15),
/* GPIOR6 */
- ASPEED_PULL_DOWN_PINCONF(W26, SCU620, 14),
+ ASPEED_PULL_DOWN_PINCONF(W26, SCU630, 14),
/* GPIOR5 */
- ASPEED_PULL_DOWN_PINCONF(T23, SCU620, 13),
+ ASPEED_PULL_DOWN_PINCONF(T23, SCU630, 13),
/* GPIOR4 */
- ASPEED_PULL_DOWN_PINCONF(U25, SCU620, 12),
+ ASPEED_PULL_DOWN_PINCONF(U25, SCU630, 12),
/* GPIOR3*/
- ASPEED_PULL_DOWN_PINCONF(V26, SCU620, 11),
+ ASPEED_PULL_DOWN_PINCONF(V26, SCU630, 11),
/* GPIOR2 */
- ASPEED_PULL_DOWN_PINCONF(V24, SCU620, 10),
+ ASPEED_PULL_DOWN_PINCONF(V24, SCU630, 10),
/* GPIOR1 */
- ASPEED_PULL_DOWN_PINCONF(U24, SCU620, 9),
+ ASPEED_PULL_DOWN_PINCONF(U24, SCU630, 9),
/* GPIOR0 */
- ASPEED_PULL_DOWN_PINCONF(V25, SCU620, 8),
+ ASPEED_PULL_DOWN_PINCONF(V25, SCU630, 8),
/* GPIOX7 */
ASPEED_PULL_DOWN_PINCONF(AB10, SCU634, 31),
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 6649357..cffeb86 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -2124,13 +2124,7 @@
error = pinctrl_claim_hogs(pctldev);
if (error) {
- dev_err(pctldev->dev, "could not claim hogs: %i\n",
- error);
- pinctrl_free_pindescs(pctldev, pctldev->desc->pins,
- pctldev->desc->npins);
- mutex_destroy(&pctldev->mutex);
- kfree(pctldev);
-
+ dev_err(pctldev->dev, "could not claim hogs: %i\n", error);
return error;
}
diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c
index df1efc2e..6a94ecd 100644
--- a/drivers/pinctrl/devicetree.c
+++ b/drivers/pinctrl/devicetree.c
@@ -220,14 +220,16 @@
for (state = 0; ; state++) {
/* Retrieve the pinctrl-* property */
propname = kasprintf(GFP_KERNEL, "pinctrl-%d", state);
- if (!propname)
- return -ENOMEM;
+ if (!propname) {
+ ret = -ENOMEM;
+ goto err;
+ }
prop = of_find_property(np, propname, &size);
kfree(propname);
if (!prop) {
if (state == 0) {
- of_node_put(np);
- return -ENODEV;
+ ret = -ENODEV;
+ goto err;
}
break;
}
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index ac97724..4e87f5b 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -231,6 +231,7 @@
/* SCORE groups */
static const unsigned int byt_score_uart1_pins[] = { 70, 71, 72, 73 };
static const unsigned int byt_score_uart2_pins[] = { 74, 75, 76, 77 };
+static const unsigned int byt_score_uart3_pins[] = { 57, 61 };
static const unsigned int byt_score_pwm0_pins[] = { 94 };
static const unsigned int byt_score_pwm1_pins[] = { 95 };
@@ -278,37 +279,38 @@
static const unsigned int byt_score_smbus_pins[] = { 51, 52, 53 };
static const struct intel_pingroup byt_score_groups[] = {
- PIN_GROUP("uart1_grp", byt_score_uart1_pins, 1),
- PIN_GROUP("uart2_grp", byt_score_uart2_pins, 1),
- PIN_GROUP("pwm0_grp", byt_score_pwm0_pins, 1),
- PIN_GROUP("pwm1_grp", byt_score_pwm1_pins, 1),
- PIN_GROUP("ssp2_grp", byt_score_ssp2_pins, 1),
- PIN_GROUP("sio_spi_grp", byt_score_sio_spi_pins, 1),
- PIN_GROUP("i2c5_grp", byt_score_i2c5_pins, 1),
- PIN_GROUP("i2c6_grp", byt_score_i2c6_pins, 1),
- PIN_GROUP("i2c4_grp", byt_score_i2c4_pins, 1),
- PIN_GROUP("i2c3_grp", byt_score_i2c3_pins, 1),
- PIN_GROUP("i2c2_grp", byt_score_i2c2_pins, 1),
- PIN_GROUP("i2c1_grp", byt_score_i2c1_pins, 1),
- PIN_GROUP("i2c0_grp", byt_score_i2c0_pins, 1),
- PIN_GROUP("ssp0_grp", byt_score_ssp0_pins, 1),
- PIN_GROUP("ssp1_grp", byt_score_ssp1_pins, 1),
- PIN_GROUP("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values),
- PIN_GROUP("sdio_grp", byt_score_sdio_pins, 1),
- PIN_GROUP("emmc_grp", byt_score_emmc_pins, 1),
- PIN_GROUP("lpc_grp", byt_score_ilb_lpc_pins, 1),
- PIN_GROUP("sata_grp", byt_score_sata_pins, 1),
- PIN_GROUP("plt_clk0_grp", byt_score_plt_clk0_pins, 1),
- PIN_GROUP("plt_clk1_grp", byt_score_plt_clk1_pins, 1),
- PIN_GROUP("plt_clk2_grp", byt_score_plt_clk2_pins, 1),
- PIN_GROUP("plt_clk3_grp", byt_score_plt_clk3_pins, 1),
- PIN_GROUP("plt_clk4_grp", byt_score_plt_clk4_pins, 1),
- PIN_GROUP("plt_clk5_grp", byt_score_plt_clk5_pins, 1),
- PIN_GROUP("smbus_grp", byt_score_smbus_pins, 1),
+ PIN_GROUP_GPIO("uart1_grp", byt_score_uart1_pins, 1),
+ PIN_GROUP_GPIO("uart2_grp", byt_score_uart2_pins, 1),
+ PIN_GROUP_GPIO("uart3_grp", byt_score_uart3_pins, 1),
+ PIN_GROUP_GPIO("pwm0_grp", byt_score_pwm0_pins, 1),
+ PIN_GROUP_GPIO("pwm1_grp", byt_score_pwm1_pins, 1),
+ PIN_GROUP_GPIO("ssp2_grp", byt_score_ssp2_pins, 1),
+ PIN_GROUP_GPIO("sio_spi_grp", byt_score_sio_spi_pins, 1),
+ PIN_GROUP_GPIO("i2c5_grp", byt_score_i2c5_pins, 1),
+ PIN_GROUP_GPIO("i2c6_grp", byt_score_i2c6_pins, 1),
+ PIN_GROUP_GPIO("i2c4_grp", byt_score_i2c4_pins, 1),
+ PIN_GROUP_GPIO("i2c3_grp", byt_score_i2c3_pins, 1),
+ PIN_GROUP_GPIO("i2c2_grp", byt_score_i2c2_pins, 1),
+ PIN_GROUP_GPIO("i2c1_grp", byt_score_i2c1_pins, 1),
+ PIN_GROUP_GPIO("i2c0_grp", byt_score_i2c0_pins, 1),
+ PIN_GROUP_GPIO("ssp0_grp", byt_score_ssp0_pins, 1),
+ PIN_GROUP_GPIO("ssp1_grp", byt_score_ssp1_pins, 1),
+ PIN_GROUP_GPIO("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values),
+ PIN_GROUP_GPIO("sdio_grp", byt_score_sdio_pins, 1),
+ PIN_GROUP_GPIO("emmc_grp", byt_score_emmc_pins, 1),
+ PIN_GROUP_GPIO("lpc_grp", byt_score_ilb_lpc_pins, 1),
+ PIN_GROUP_GPIO("sata_grp", byt_score_sata_pins, 1),
+ PIN_GROUP_GPIO("plt_clk0_grp", byt_score_plt_clk0_pins, 1),
+ PIN_GROUP_GPIO("plt_clk1_grp", byt_score_plt_clk1_pins, 1),
+ PIN_GROUP_GPIO("plt_clk2_grp", byt_score_plt_clk2_pins, 1),
+ PIN_GROUP_GPIO("plt_clk3_grp", byt_score_plt_clk3_pins, 1),
+ PIN_GROUP_GPIO("plt_clk4_grp", byt_score_plt_clk4_pins, 1),
+ PIN_GROUP_GPIO("plt_clk5_grp", byt_score_plt_clk5_pins, 1),
+ PIN_GROUP_GPIO("smbus_grp", byt_score_smbus_pins, 1),
};
static const char * const byt_score_uart_groups[] = {
- "uart1_grp", "uart2_grp",
+ "uart1_grp", "uart2_grp", "uart3_grp",
};
static const char * const byt_score_pwm_groups[] = {
"pwm0_grp", "pwm1_grp",
@@ -332,12 +334,14 @@
};
static const char * const byt_score_smbus_groups[] = { "smbus_grp" };
static const char * const byt_score_gpio_groups[] = {
- "uart1_grp", "uart2_grp", "pwm0_grp", "pwm1_grp", "ssp0_grp",
- "ssp1_grp", "ssp2_grp", "sio_spi_grp", "i2c0_grp", "i2c1_grp",
- "i2c2_grp", "i2c3_grp", "i2c4_grp", "i2c5_grp", "i2c6_grp",
- "sdcard_grp", "sdio_grp", "emmc_grp", "lpc_grp", "sata_grp",
- "plt_clk0_grp", "plt_clk1_grp", "plt_clk2_grp", "plt_clk3_grp",
- "plt_clk4_grp", "plt_clk5_grp", "smbus_grp",
+ "uart1_grp_gpio", "uart2_grp_gpio", "uart3_grp_gpio", "pwm0_grp_gpio",
+ "pwm1_grp_gpio", "ssp0_grp_gpio", "ssp1_grp_gpio", "ssp2_grp_gpio",
+ "sio_spi_grp_gpio", "i2c0_grp_gpio", "i2c1_grp_gpio", "i2c2_grp_gpio",
+ "i2c3_grp_gpio", "i2c4_grp_gpio", "i2c5_grp_gpio", "i2c6_grp_gpio",
+ "sdcard_grp_gpio", "sdio_grp_gpio", "emmc_grp_gpio", "lpc_grp_gpio",
+ "sata_grp_gpio", "plt_clk0_grp_gpio", "plt_clk1_grp_gpio",
+ "plt_clk2_grp_gpio", "plt_clk3_grp_gpio", "plt_clk4_grp_gpio",
+ "plt_clk5_grp_gpio", "smbus_grp_gpio",
};
static const struct intel_function byt_score_functions[] = {
@@ -456,8 +460,8 @@
PIN_GROUP("usb_oc_grp_gpio", byt_sus_usb_over_current_pins, byt_sus_usb_over_current_gpio_mode_values),
PIN_GROUP("usb_ulpi_grp_gpio", byt_sus_usb_ulpi_pins, byt_sus_usb_ulpi_gpio_mode_values),
PIN_GROUP("pcu_spi_grp_gpio", byt_sus_pcu_spi_pins, byt_sus_pcu_spi_gpio_mode_values),
- PIN_GROUP("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1),
- PIN_GROUP("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1),
+ PIN_GROUP_GPIO("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1),
+ PIN_GROUP_GPIO("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1),
};
static const char * const byt_sus_usb_groups[] = {
@@ -469,7 +473,7 @@
};
static const char * const byt_sus_gpio_groups[] = {
"usb_oc_grp_gpio", "usb_ulpi_grp_gpio", "pcu_spi_grp_gpio",
- "pmu_clk1_grp", "pmu_clk2_grp",
+ "pmu_clk1_grp_gpio", "pmu_clk2_grp_gpio",
};
static const struct intel_function byt_sus_functions[] = {
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index fde65e1..6981e2f 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -179,6 +179,10 @@
.modes = __builtin_choose_expr(__builtin_constant_p((m)), NULL, (m)), \
}
+#define PIN_GROUP_GPIO(n, p, m) \
+ PIN_GROUP(n, p, m), \
+ PIN_GROUP(n "_gpio", p, 0)
+
#define FUNCTION(n, g) \
{ \
.func = PINCTRL_PINFUNCTION((n), (g), ARRAY_SIZE(g)), \
diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c
index b6bc31a..b19bc39 100644
--- a/drivers/pinctrl/mediatek/pinctrl-paris.c
+++ b/drivers/pinctrl/mediatek/pinctrl-paris.c
@@ -165,20 +165,21 @@
err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_SR, &ret);
break;
case PIN_CONFIG_INPUT_ENABLE:
- case PIN_CONFIG_OUTPUT_ENABLE:
+ err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_IES, &ret);
+ if (!ret)
+ err = -EINVAL;
+ break;
+ case PIN_CONFIG_OUTPUT:
err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DIR, &ret);
if (err)
break;
- /* CONFIG Current direction return value
- * ------------- ----------------- ----------------------
- * OUTPUT_ENABLE output 1 (= HW value)
- * input 0 (= HW value)
- * INPUT_ENABLE output 0 (= reverse HW value)
- * input 1 (= reverse HW value)
- */
- if (param == PIN_CONFIG_INPUT_ENABLE)
- ret = !ret;
+ if (!ret) {
+ err = -EINVAL;
+ break;
+ }
+
+ err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DO, &ret);
break;
case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_DIR, &ret);
@@ -193,6 +194,8 @@
}
err = mtk_hw_get_value(hw, desc, PINCTRL_PIN_REG_SMT, &ret);
+ if (!ret)
+ err = -EINVAL;
break;
case PIN_CONFIG_DRIVE_STRENGTH:
if (!hw->soc->drive_get)
@@ -281,26 +284,9 @@
break;
err = hw->soc->bias_set_combo(hw, desc, 0, arg);
break;
- case PIN_CONFIG_OUTPUT_ENABLE:
- err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_SMT,
- MTK_DISABLE);
- /* Keep set direction to consider the case that a GPIO pin
- * does not have SMT control
- */
- if (err != -ENOTSUPP)
- break;
-
- err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_DIR,
- MTK_OUTPUT);
- break;
case PIN_CONFIG_INPUT_ENABLE:
/* regard all non-zero value as enable */
err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_IES, !!arg);
- if (err)
- break;
-
- err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_DIR,
- MTK_INPUT);
break;
case PIN_CONFIG_SLEW_RATE:
/* regard all non-zero value as enable */
diff --git a/drivers/pinctrl/meson/pinctrl-meson-a1.c b/drivers/pinctrl/meson/pinctrl-meson-a1.c
index 79f5d75..50a87d9 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-a1.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-a1.c
@@ -250,7 +250,7 @@
static const unsigned int pdm_din2_a_pins[] = { GPIOA_6 };
static const unsigned int pdm_din1_a_pins[] = { GPIOA_7 };
static const unsigned int pdm_din0_a_pins[] = { GPIOA_8 };
-static const unsigned int pdm_dclk_pins[] = { GPIOA_9 };
+static const unsigned int pdm_dclk_a_pins[] = { GPIOA_9 };
/* gen_clk */
static const unsigned int gen_clk_x_pins[] = { GPIOX_7 };
@@ -591,7 +591,7 @@
GROUP(pdm_din2_a, 3),
GROUP(pdm_din1_a, 3),
GROUP(pdm_din0_a, 3),
- GROUP(pdm_dclk, 3),
+ GROUP(pdm_dclk_a, 3),
GROUP(pwm_c_a, 3),
GROUP(pwm_b_a, 3),
@@ -755,7 +755,7 @@
static const char * const pdm_groups[] = {
"pdm_din0_x", "pdm_din1_x", "pdm_din2_x", "pdm_dclk_x", "pdm_din2_a",
- "pdm_din1_a", "pdm_din0_a", "pdm_dclk",
+ "pdm_din1_a", "pdm_din0_a", "pdm_dclk_a",
};
static const char * const gen_clk_groups[] = {
diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index eb5a8c6..20425af 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -2045,7 +2045,9 @@
for (unsigned int i = 0; i < RZG2L_TINT_MAX_INTERRUPT; i++) {
struct irq_data *data;
+ unsigned long flags;
unsigned int virq;
+ int ret;
if (!pctrl->hwirq[i])
continue;
@@ -2063,8 +2065,18 @@
continue;
}
- if (!irqd_irq_disabled(data))
+ /*
+ * This has to be atomically executed to protect against a concurrent
+ * interrupt.
+ */
+ raw_spin_lock_irqsave(&pctrl->lock.rlock, flags);
+ ret = rzg2l_gpio_irq_set_type(data, irqd_get_trigger_type(data));
+ if (!ret && !irqd_irq_disabled(data))
rzg2l_gpio_irq_enable(data);
+ raw_spin_unlock_irqrestore(&pctrl->lock.rlock, flags);
+
+ if (ret)
+ dev_crit(pctrl->dev, "Failed to set IRQ type for virq=%u\n", virq);
}
}
diff --git a/drivers/platform/chrome/cros_ec_uart.c b/drivers/platform/chrome/cros_ec_uart.c
index 8ea867c..62bc24f6d 100644
--- a/drivers/platform/chrome/cros_ec_uart.c
+++ b/drivers/platform/chrome/cros_ec_uart.c
@@ -263,12 +263,6 @@
if (!ec_dev)
return -ENOMEM;
- ret = devm_serdev_device_open(dev, serdev);
- if (ret) {
- dev_err(dev, "Unable to open UART device");
- return ret;
- }
-
serdev_device_set_drvdata(serdev, ec_dev);
init_waitqueue_head(&ec_uart->response.wait_queue);
@@ -280,14 +274,6 @@
return ret;
}
- ret = serdev_device_set_baudrate(serdev, ec_uart->baudrate);
- if (ret < 0) {
- dev_err(dev, "Failed to set up host baud rate (%d)", ret);
- return ret;
- }
-
- serdev_device_set_flow_control(serdev, ec_uart->flowcontrol);
-
/* Initialize ec_dev for cros_ec */
ec_dev->phys_name = dev_name(dev);
ec_dev->dev = dev;
@@ -301,6 +287,20 @@
serdev_device_set_client_ops(serdev, &cros_ec_uart_client_ops);
+ ret = devm_serdev_device_open(dev, serdev);
+ if (ret) {
+ dev_err(dev, "Unable to open UART device");
+ return ret;
+ }
+
+ ret = serdev_device_set_baudrate(serdev, ec_uart->baudrate);
+ if (ret < 0) {
+ dev_err(dev, "Failed to set up host baud rate (%d)", ret);
+ return ret;
+ }
+
+ serdev_device_set_flow_control(serdev, ec_uart->flowcontrol);
+
return cros_ec_register(ec_dev);
}
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index ee2e164..38c932d 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -598,6 +598,15 @@
.driver_data = &quirk_acer_predator_v4,
},
{
+ .callback = dmi_matched,
+ .ident = "Acer Predator PH18-71",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Predator PH18-71"),
+ },
+ .driver_data = &quirk_acer_predator_v4,
+ },
+ {
.callback = set_force_caps,
.ident = "Acer Aspire Switch 10E SW3-016",
.matches = {
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index b456370..b4f4972 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -208,6 +208,15 @@
DMI_MATCH(DMI_BIOS_VERSION, "03.03"),
}
},
+ {
+ .ident = "Framework Laptop 13 (Phoenix)",
+ .driver_data = &quirk_spurious_8042,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Framework"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Laptop 13 (AMD Ryzen 7040Series)"),
+ DMI_MATCH(DMI_BIOS_VERSION, "03.05"),
+ }
+ },
{}
};
diff --git a/drivers/platform/x86/amd/pmf/Makefile b/drivers/platform/x86/amd/pmf/Makefile
index 6b26e48..7d6079b 100644
--- a/drivers/platform/x86/amd/pmf/Makefile
+++ b/drivers/platform/x86/amd/pmf/Makefile
@@ -7,4 +7,4 @@
obj-$(CONFIG_AMD_PMF) += amd-pmf.o
amd-pmf-objs := core.o acpi.o sps.o \
auto-mode.o cnqf.o \
- tee-if.o spc.o
+ tee-if.o spc.o pmf-quirks.o
diff --git a/drivers/platform/x86/amd/pmf/acpi.c b/drivers/platform/x86/amd/pmf/acpi.c
index d0cf46e..1157ec1 100644
--- a/drivers/platform/x86/amd/pmf/acpi.c
+++ b/drivers/platform/x86/amd/pmf/acpi.c
@@ -343,7 +343,10 @@
if (err)
return err;
- pdev->supported_func = output.supported_functions;
+ /* only set if not already set by a quirk */
+ if (!pdev->supported_func)
+ pdev->supported_func = output.supported_functions;
+
dev_dbg(pdev->dev, "supported functions:0x%x notifications:0x%x version:%u\n",
output.supported_functions, output.notification_mask, output.version);
@@ -437,7 +440,7 @@
status = acpi_walk_resources(ahandle, METHOD_NAME__CRS, apmf_walk_resources, pmf_dev);
if (ACPI_FAILURE(status)) {
- dev_err(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status);
+ dev_dbg(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status);
return -EINVAL;
}
diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index 5d4f806..64e6e34 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -445,6 +445,7 @@
mutex_init(&dev->lock);
mutex_init(&dev->update_mutex);
+ amd_pmf_quirks_init(dev);
apmf_acpi_init(dev);
platform_set_drvdata(pdev, dev);
amd_pmf_dbgfs_register(dev);
diff --git a/drivers/platform/x86/amd/pmf/pmf-quirks.c b/drivers/platform/x86/amd/pmf/pmf-quirks.c
new file mode 100644
index 0000000..0b2eb0a
--- /dev/null
+++ b/drivers/platform/x86/amd/pmf/pmf-quirks.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * AMD Platform Management Framework Driver Quirks
+ *
+ * Copyright (c) 2024, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Author: Mario Limonciello <mario.limonciello@amd.com>
+ */
+
+#include <linux/dmi.h>
+
+#include "pmf.h"
+
+struct quirk_entry {
+ u32 supported_func;
+};
+
+static struct quirk_entry quirk_no_sps_bug = {
+ .supported_func = 0x4003,
+};
+
+static const struct dmi_system_id fwbug_list[] = {
+ {
+ .ident = "ROG Zephyrus G14",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "GA403UV"),
+ },
+ .driver_data = &quirk_no_sps_bug,
+ },
+ {}
+};
+
+void amd_pmf_quirks_init(struct amd_pmf_dev *dev)
+{
+ const struct dmi_system_id *dmi_id;
+ struct quirk_entry *quirks;
+
+ dmi_id = dmi_first_match(fwbug_list);
+ if (!dmi_id)
+ return;
+
+ quirks = dmi_id->driver_data;
+ if (quirks->supported_func) {
+ dev->supported_func = quirks->supported_func;
+ pr_info("Using supported funcs quirk to avoid %s platform firmware bug\n",
+ dmi_id->ident);
+ }
+}
+
diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index 8c4df57..eeedd0c 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -720,4 +720,7 @@
void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in);
void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in);
+/* Quirk infrastructure */
+void amd_pmf_quirks_init(struct amd_pmf_dev *dev);
+
#endif /* PMF_H */
diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 7457ca2b2..c7a8276 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -49,6 +49,8 @@
{"INTC1076", 0},
{"INTC1077", 0},
{"INTC1078", 0},
+ {"INTC107B", 0},
+ {"INTC10CB", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
@@ -504,6 +506,7 @@
struct platform_device *device = context;
struct intel_hid_priv *priv = dev_get_drvdata(&device->dev);
unsigned long long ev_index;
+ struct key_entry *ke;
int err;
/*
@@ -545,11 +548,15 @@
if (event == 0xc0 || !priv->array)
return;
- if (!sparse_keymap_entry_from_scancode(priv->array, event)) {
+ ke = sparse_keymap_entry_from_scancode(priv->array, event);
+ if (!ke) {
dev_info(&device->dev, "unknown event 0x%x\n", event);
return;
}
+ if (ke->type == KE_IGNORE)
+ return;
+
wakeup:
pm_wakeup_hard_event(&device->dev);
diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
index 08df949..1accdaa 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c
@@ -719,7 +719,9 @@
};
static const struct x86_cpu_id hpm_cpu_ids[] = {
+ X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, NULL),
X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, NULL),
+ X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, NULL),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, NULL),
{}
};
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index bd75d61..ef73020 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -29,7 +29,7 @@
#include "uncore-frequency-common.h"
#define UNCORE_MAJOR_VERSION 0
-#define UNCORE_MINOR_VERSION 1
+#define UNCORE_MINOR_VERSION 2
#define UNCORE_HEADER_INDEX 0
#define UNCORE_FABRIC_CLUSTER_OFFSET 8
@@ -329,7 +329,7 @@
goto remove_clusters;
}
- if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) != UNCORE_MINOR_VERSION)
+ if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) > UNCORE_MINOR_VERSION)
dev_info(&auxdev->dev, "Uncore: Ignore: Unsupported minor version:%lx\n",
TPMI_MINOR_VERSION(pd_info->ufs_header_ver));
diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c
index 084c355..79bb2c8 100644
--- a/drivers/platform/x86/intel/vbtn.c
+++ b/drivers/platform/x86/intel/vbtn.c
@@ -136,8 +136,6 @@
priv->switches_dev->id.bustype = BUS_HOST;
if (priv->has_switches) {
- detect_tablet_mode(&device->dev);
-
ret = input_register_device(priv->switches_dev);
if (ret)
return ret;
@@ -258,9 +256,6 @@
static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel)
{
- unsigned long long vgbs;
- acpi_status status;
-
/* See dual_accel_detect.h for more info */
if (dual_accel)
return false;
@@ -268,8 +263,7 @@
if (!dmi_check_system(dmi_switches_allow_list))
return false;
- status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs);
- return ACPI_SUCCESS(status);
+ return acpi_has_method(handle, "VGBS");
}
static int intel_vbtn_probe(struct platform_device *device)
@@ -316,6 +310,9 @@
if (ACPI_FAILURE(status))
dev_err(&device->dev, "Error VBDL failed with ACPI status %d\n", status);
}
+ // Check switches after buttons since VBDL may have side effects.
+ if (has_switches)
+ detect_tablet_mode(&device->dev);
device_init_wakeup(&device->dev, true);
/*
diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c
index ad3c39e..e714ee6 100644
--- a/drivers/platform/x86/lg-laptop.c
+++ b/drivers/platform/x86/lg-laptop.c
@@ -736,7 +736,7 @@
default:
year = 2019;
}
- pr_info("product: %s year: %d\n", product, year);
+ pr_info("product: %s year: %d\n", product ?: "unknown", year);
if (year >= 2019)
battery_limit_use_wmbb = 1;
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 291f14e..77244c9 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -264,6 +264,7 @@
{ KE_KEY, 0xb32, { KEY_NEXTSONG } },
{ KE_KEY, 0xb33, { KEY_PLAYPAUSE } },
{ KE_KEY, 0xb5a, { KEY_MEDIA } },
+ { KE_IGNORE, 0x0e00, { KEY_RESERVED } }, /* Wake from sleep */
{ KE_IGNORE, 0x1430, { KEY_RESERVED } }, /* Wake from sleep */
{ KE_IGNORE, 0x1501, { KEY_RESERVED } }, /* Output changed */
{ KE_IGNORE, 0x1502, { KEY_RESERVED } }, /* HDMI plugged/unplugged */
@@ -3523,9 +3524,10 @@
(dev->kbd_mode == SCI_KBD_MODE_ON) ?
LED_FULL : LED_OFF);
break;
+ case 0x8e: /* Power button pressed */
+ break;
case 0x85: /* Unknown */
case 0x8d: /* Unknown */
- case 0x8e: /* Unknown */
case 0x94: /* Unknown */
case 0x95: /* Unknown */
default:
diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c
index 1305cba..aca12378 100644
--- a/drivers/power/supply/mt6360_charger.c
+++ b/drivers/power/supply/mt6360_charger.c
@@ -588,7 +588,7 @@
};
static const struct regulator_desc mt6360_otg_rdesc = {
- .of_match = "usb-otg-vbus",
+ .of_match = "usb-otg-vbus-regulator",
.name = "usb-otg-vbus",
.ops = &mt6360_chg_otg_ops,
.owner = THIS_MODULE,
diff --git a/drivers/power/supply/rt9455_charger.c b/drivers/power/supply/rt9455_charger.c
index c345a77..e4dbacd 100644
--- a/drivers/power/supply/rt9455_charger.c
+++ b/drivers/power/supply/rt9455_charger.c
@@ -192,6 +192,7 @@
4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000
};
+#if IS_ENABLED(CONFIG_USB_PHY)
/*
* When the charger is in boost mode, REG02[7:2] represent boost output
* voltage.
@@ -207,6 +208,7 @@
5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000,
5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000,
};
+#endif
/* REG07[3:0] (VMREG) in uV */
static const int rt9455_vmreg_values[] = {
diff --git a/drivers/pwm/pwm-dwc-core.c b/drivers/pwm/pwm-dwc-core.c
index 0437369..c842549 100644
--- a/drivers/pwm/pwm-dwc-core.c
+++ b/drivers/pwm/pwm-dwc-core.c
@@ -172,7 +172,6 @@
dwc->clk_ns = 10;
chip->ops = &dwc_pwm_ops;
- dev_set_drvdata(dev, chip);
return chip;
}
EXPORT_SYMBOL_GPL(dwc_pwm_alloc);
diff --git a/drivers/pwm/pwm-dwc.c b/drivers/pwm/pwm-dwc.c
index 676eaf8..fb3eadf 100644
--- a/drivers/pwm/pwm-dwc.c
+++ b/drivers/pwm/pwm-dwc.c
@@ -31,26 +31,34 @@
.size = 0x1000,
};
-static int dwc_pwm_init_one(struct device *dev, void __iomem *base, unsigned int offset)
+static int dwc_pwm_init_one(struct device *dev, struct dwc_pwm_drvdata *ddata, unsigned int idx)
{
struct pwm_chip *chip;
struct dwc_pwm *dwc;
+ int ret;
chip = dwc_pwm_alloc(dev);
if (IS_ERR(chip))
return PTR_ERR(chip);
dwc = to_dwc_pwm(chip);
- dwc->base = base + offset;
+ dwc->base = ddata->io_base + (ddata->info->size * idx);
- return devm_pwmchip_add(dev, chip);
+ ret = devm_pwmchip_add(dev, chip);
+ if (ret)
+ return ret;
+
+ ddata->chips[idx] = chip;
+ return 0;
}
static int dwc_pwm_probe(struct pci_dev *pci, const struct pci_device_id *id)
{
const struct dwc_pwm_info *info;
struct device *dev = &pci->dev;
- int i, ret;
+ struct dwc_pwm_drvdata *ddata;
+ unsigned int idx;
+ int ret;
ret = pcim_enable_device(pci);
if (ret)
@@ -63,17 +71,25 @@
return dev_err_probe(dev, ret, "Failed to iomap PCI BAR\n");
info = (const struct dwc_pwm_info *)id->driver_data;
+ ddata = devm_kzalloc(dev, struct_size(ddata, chips, info->nr), GFP_KERNEL);
+ if (!ddata)
+ return -ENOMEM;
- for (i = 0; i < info->nr; i++) {
- /*
- * No need to check for pcim_iomap_table() failure,
- * pcim_iomap_regions() already does it for us.
- */
- ret = dwc_pwm_init_one(dev, pcim_iomap_table(pci)[0], i * info->size);
+ /*
+ * No need to check for pcim_iomap_table() failure,
+ * pcim_iomap_regions() already does it for us.
+ */
+ ddata->io_base = pcim_iomap_table(pci)[0];
+ ddata->info = info;
+
+ for (idx = 0; idx < ddata->info->nr; idx++) {
+ ret = dwc_pwm_init_one(dev, ddata, idx);
if (ret)
return ret;
}
+ dev_set_drvdata(dev, ddata);
+
pm_runtime_put(dev);
pm_runtime_allow(dev);
@@ -88,19 +104,24 @@
static int dwc_pwm_suspend(struct device *dev)
{
- struct pwm_chip *chip = dev_get_drvdata(dev);
- struct dwc_pwm *dwc = to_dwc_pwm(chip);
- int i;
+ struct dwc_pwm_drvdata *ddata = dev_get_drvdata(dev);
+ unsigned int idx;
- for (i = 0; i < DWC_TIMERS_TOTAL; i++) {
- if (chip->pwms[i].state.enabled) {
- dev_err(dev, "PWM %u in use by consumer (%s)\n",
- i, chip->pwms[i].label);
- return -EBUSY;
+ for (idx = 0; idx < ddata->info->nr; idx++) {
+ struct pwm_chip *chip = ddata->chips[idx];
+ struct dwc_pwm *dwc = to_dwc_pwm(chip);
+ unsigned int i;
+
+ for (i = 0; i < DWC_TIMERS_TOTAL; i++) {
+ if (chip->pwms[i].state.enabled) {
+ dev_err(dev, "PWM %u in use by consumer (%s)\n",
+ i, chip->pwms[i].label);
+ return -EBUSY;
+ }
+ dwc->ctx[i].cnt = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT(i));
+ dwc->ctx[i].cnt2 = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT2(i));
+ dwc->ctx[i].ctrl = dwc_pwm_readl(dwc, DWC_TIM_CTRL(i));
}
- dwc->ctx[i].cnt = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT(i));
- dwc->ctx[i].cnt2 = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT2(i));
- dwc->ctx[i].ctrl = dwc_pwm_readl(dwc, DWC_TIM_CTRL(i));
}
return 0;
@@ -108,14 +129,19 @@
static int dwc_pwm_resume(struct device *dev)
{
- struct pwm_chip *chip = dev_get_drvdata(dev);
- struct dwc_pwm *dwc = to_dwc_pwm(chip);
- int i;
+ struct dwc_pwm_drvdata *ddata = dev_get_drvdata(dev);
+ unsigned int idx;
- for (i = 0; i < DWC_TIMERS_TOTAL; i++) {
- dwc_pwm_writel(dwc, dwc->ctx[i].cnt, DWC_TIM_LD_CNT(i));
- dwc_pwm_writel(dwc, dwc->ctx[i].cnt2, DWC_TIM_LD_CNT2(i));
- dwc_pwm_writel(dwc, dwc->ctx[i].ctrl, DWC_TIM_CTRL(i));
+ for (idx = 0; idx < ddata->info->nr; idx++) {
+ struct pwm_chip *chip = ddata->chips[idx];
+ struct dwc_pwm *dwc = to_dwc_pwm(chip);
+ unsigned int i;
+
+ for (i = 0; i < DWC_TIMERS_TOTAL; i++) {
+ dwc_pwm_writel(dwc, dwc->ctx[i].cnt, DWC_TIM_LD_CNT(i));
+ dwc_pwm_writel(dwc, dwc->ctx[i].cnt2, DWC_TIM_LD_CNT2(i));
+ dwc_pwm_writel(dwc, dwc->ctx[i].ctrl, DWC_TIM_CTRL(i));
+ }
}
return 0;
diff --git a/drivers/pwm/pwm-dwc.h b/drivers/pwm/pwm-dwc.h
index a8b0748..c6e2df5 100644
--- a/drivers/pwm/pwm-dwc.h
+++ b/drivers/pwm/pwm-dwc.h
@@ -38,6 +38,12 @@
unsigned int size;
};
+struct dwc_pwm_drvdata {
+ const struct dwc_pwm_info *info;
+ void __iomem *io_base;
+ struct pwm_chip *chips[];
+};
+
struct dwc_pwm_ctx {
u32 cnt;
u32 cnt2;
diff --git a/drivers/regulator/irq_helpers.c b/drivers/regulator/irq_helpers.c
index fe7ae0f..5ab1a0b 100644
--- a/drivers/regulator/irq_helpers.c
+++ b/drivers/regulator/irq_helpers.c
@@ -352,6 +352,9 @@
h->irq = irq;
h->desc = *d;
+ h->desc.name = devm_kstrdup(dev, d->name, GFP_KERNEL);
+ if (!h->desc.name)
+ return ERR_PTR(-ENOMEM);
ret = init_rdev_state(dev, h, rdev, common_errs, per_rdev_errs,
rdev_amount);
diff --git a/drivers/regulator/mt6360-regulator.c b/drivers/regulator/mt6360-regulator.c
index ad6587a..24cc9fc 100644
--- a/drivers/regulator/mt6360-regulator.c
+++ b/drivers/regulator/mt6360-regulator.c
@@ -319,15 +319,15 @@
}
}
-#define MT6360_REGULATOR_DESC(_name, _sname, ereg, emask, vreg, vmask, \
- mreg, mmask, streg, stmask, vranges, \
- vcnts, offon_delay, irq_tbls) \
+#define MT6360_REGULATOR_DESC(match, _name, _sname, ereg, emask, vreg, \
+ vmask, mreg, mmask, streg, stmask, \
+ vranges, vcnts, offon_delay, irq_tbls) \
{ \
.desc = { \
.name = #_name, \
.supply_name = #_sname, \
.id = MT6360_REGULATOR_##_name, \
- .of_match = of_match_ptr(#_name), \
+ .of_match = of_match_ptr(match), \
.regulators_node = of_match_ptr("regulator"), \
.of_map_mode = mt6360_regulator_of_map_mode, \
.owner = THIS_MODULE, \
@@ -351,21 +351,29 @@
}
static const struct mt6360_regulator_desc mt6360_regulator_descs[] = {
- MT6360_REGULATOR_DESC(BUCK1, BUCK1_VIN, 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04,
+ MT6360_REGULATOR_DESC("buck1", BUCK1, BUCK1_VIN,
+ 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04,
buck_vout_ranges, 256, 0, buck1_irq_tbls),
- MT6360_REGULATOR_DESC(BUCK2, BUCK2_VIN, 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04,
+ MT6360_REGULATOR_DESC("buck2", BUCK2, BUCK2_VIN,
+ 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04,
buck_vout_ranges, 256, 0, buck2_irq_tbls),
- MT6360_REGULATOR_DESC(LDO6, LDO_VIN3, 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04,
+ MT6360_REGULATOR_DESC("ldo6", LDO6, LDO_VIN3,
+ 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04,
ldo_vout_ranges1, 256, 0, ldo6_irq_tbls),
- MT6360_REGULATOR_DESC(LDO7, LDO_VIN3, 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04,
+ MT6360_REGULATOR_DESC("ldo7", LDO7, LDO_VIN3,
+ 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04,
ldo_vout_ranges1, 256, 0, ldo7_irq_tbls),
- MT6360_REGULATOR_DESC(LDO1, LDO_VIN1, 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04,
+ MT6360_REGULATOR_DESC("ldo1", LDO1, LDO_VIN1,
+ 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04,
ldo_vout_ranges2, 256, 0, ldo1_irq_tbls),
- MT6360_REGULATOR_DESC(LDO2, LDO_VIN1, 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04,
+ MT6360_REGULATOR_DESC("ldo2", LDO2, LDO_VIN1,
+ 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04,
ldo_vout_ranges2, 256, 0, ldo2_irq_tbls),
- MT6360_REGULATOR_DESC(LDO3, LDO_VIN1, 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04,
+ MT6360_REGULATOR_DESC("ldo3", LDO3, LDO_VIN1,
+ 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04,
ldo_vout_ranges2, 256, 100, ldo3_irq_tbls),
- MT6360_REGULATOR_DESC(LDO5, LDO_VIN2, 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04,
+ MT6360_REGULATOR_DESC("ldo5", LDO5, LDO_VIN2,
+ 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04,
ldo_vout_ranges3, 128, 100, ldo5_irq_tbls),
};
diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c
index 656fe330..063e12c 100644
--- a/drivers/regulator/qcom-refgen-regulator.c
+++ b/drivers/regulator/qcom-refgen-regulator.c
@@ -140,6 +140,7 @@
{ .compatible = "qcom,sm8250-refgen-regulator", .data = &sm8250_refgen_desc },
{ }
};
+MODULE_DEVICE_TABLE(of, qcom_refgen_match_table);
static struct platform_driver qcom_refgen_driver = {
.probe = qcom_refgen_probe,
diff --git a/drivers/regulator/vqmmc-ipq4019-regulator.c b/drivers/regulator/vqmmc-ipq4019-regulator.c
index 086da36..4955616 100644
--- a/drivers/regulator/vqmmc-ipq4019-regulator.c
+++ b/drivers/regulator/vqmmc-ipq4019-regulator.c
@@ -84,6 +84,7 @@
{ .compatible = "qcom,vqmmc-ipq4019-regulator", },
{},
};
+MODULE_DEVICE_TABLE(of, regulator_ipq4019_of_match);
static struct platform_driver ipq4019_regulator_driver = {
.probe = ipq4019_regulator_probe,
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 37173cb..c57694b 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -162,7 +162,8 @@
/*
* Setup ccw.
*/
- rq->ccw.cda = virt_to_dma32(rq->buffer);
+ if (rq->buffer)
+ rq->ccw.cda = virt_to_dma32(rq->buffer);
rq->ccw.flags = CCW_FLAG_SLI;
return rq;
@@ -188,7 +189,8 @@
return -EBUSY;
rq->ccw.cmd_code = 0;
rq->ccw.count = 0;
- rq->ccw.cda = virt_to_dma32(rq->buffer);
+ if (rq->buffer)
+ rq->ccw.cda = virt_to_dma32(rq->buffer);
rq->ccw.flags = CCW_FLAG_SLI;
rq->rescnt = 0;
rq->rc = 0;
diff --git a/drivers/s390/cio/cio_inject.c b/drivers/s390/cio/cio_inject.c
index 8613fa9..a2e771e 100644
--- a/drivers/s390/cio/cio_inject.c
+++ b/drivers/s390/cio/cio_inject.c
@@ -95,7 +95,7 @@
return -EINVAL;
}
- buffer = vmemdup_user(buf, lbuf);
+ buffer = memdup_user_nul(buf, lbuf);
if (IS_ERR(buffer))
return -ENOMEM;
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index f95d123..920f550b 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -363,10 +363,8 @@
spin_lock_irq(cdev->ccwlock);
ret = ccw_device_online(cdev);
- spin_unlock_irq(cdev->ccwlock);
- if (ret == 0)
- wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev));
- else {
+ if (ret) {
+ spin_unlock_irq(cdev->ccwlock);
CIO_MSG_EVENT(0, "ccw_device_online returned %d, "
"device 0.%x.%04x\n",
ret, cdev->private->dev_id.ssid,
@@ -375,7 +373,12 @@
put_device(&cdev->dev);
return ret;
}
- spin_lock_irq(cdev->ccwlock);
+ /* Wait until a final state is reached */
+ while (!dev_fsm_final_state(cdev)) {
+ spin_unlock_irq(cdev->ccwlock);
+ wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev));
+ spin_lock_irq(cdev->ccwlock);
+ }
/* Check if online processing was successful */
if ((cdev->private->state != DEV_STATE_ONLINE) &&
(cdev->private->state != DEV_STATE_W4SENSE)) {
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 65d8b2c..42791fa 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -504,6 +504,11 @@
ccw_device_done(cdev, DEV_STATE_ONLINE);
/* Deliver fake irb to device driver, if needed. */
if (cdev->private->flags.fake_irb) {
+ CIO_MSG_EVENT(2, "fakeirb: deliver device 0.%x.%04x intparm %lx type=%d\n",
+ cdev->private->dev_id.ssid,
+ cdev->private->dev_id.devno,
+ cdev->private->intparm,
+ cdev->private->flags.fake_irb);
create_fake_irb(&cdev->private->dma_area->irb,
cdev->private->flags.fake_irb);
cdev->private->flags.fake_irb = 0;
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index 40c97f8..acd6790 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -208,6 +208,10 @@
if (!cdev->private->flags.fake_irb) {
cdev->private->flags.fake_irb = FAKE_CMD_IRB;
cdev->private->intparm = intparm;
+ CIO_MSG_EVENT(2, "fakeirb: queue device 0.%x.%04x intparm %lx type=%d\n",
+ cdev->private->dev_id.ssid,
+ cdev->private->dev_id.devno, intparm,
+ cdev->private->flags.fake_irb);
return 0;
} else
/* There's already a fake I/O around. */
@@ -551,6 +555,10 @@
if (!cdev->private->flags.fake_irb) {
cdev->private->flags.fake_irb = FAKE_TM_IRB;
cdev->private->intparm = intparm;
+ CIO_MSG_EVENT(2, "fakeirb: queue device 0.%x.%04x intparm %lx type=%d\n",
+ cdev->private->dev_id.ssid,
+ cdev->private->dev_id.devno, intparm,
+ cdev->private->flags.fake_irb);
return 0;
} else
/* There's already a fake I/O around. */
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 3d9f083..a1cb39f 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -722,8 +722,8 @@
lgr_info_log();
}
-static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat,
- int dstat)
+static int qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat,
+ int dstat, int dcc)
{
DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qest irq");
@@ -731,15 +731,18 @@
goto error;
if (dstat & ~(DEV_STAT_DEV_END | DEV_STAT_CHN_END))
goto error;
+ if (dcc == 1)
+ return -EAGAIN;
if (!(dstat & DEV_STAT_DEV_END))
goto error;
qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ESTABLISHED);
- return;
+ return 0;
error:
DBF_ERROR("%4x EQ:error", irq_ptr->schid.sch_no);
DBF_ERROR("ds: %2x cs:%2x", dstat, cstat);
qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR);
+ return -EIO;
}
/* qdio interrupt handler */
@@ -748,7 +751,7 @@
{
struct qdio_irq *irq_ptr = cdev->private->qdio_data;
struct subchannel_id schid;
- int cstat, dstat;
+ int cstat, dstat, rc, dcc;
if (!intparm || !irq_ptr) {
ccw_device_get_schid(cdev, &schid);
@@ -768,10 +771,12 @@
qdio_irq_check_sense(irq_ptr, irb);
cstat = irb->scsw.cmd.cstat;
dstat = irb->scsw.cmd.dstat;
+ dcc = scsw_cmd_is_valid_cc(&irb->scsw) ? irb->scsw.cmd.cc : 0;
+ rc = 0;
switch (irq_ptr->state) {
case QDIO_IRQ_STATE_INACTIVE:
- qdio_establish_handle_irq(irq_ptr, cstat, dstat);
+ rc = qdio_establish_handle_irq(irq_ptr, cstat, dstat, dcc);
break;
case QDIO_IRQ_STATE_CLEANUP:
qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE);
@@ -785,12 +790,25 @@
if (cstat || dstat)
qdio_handle_activate_check(irq_ptr, intparm, cstat,
dstat);
+ else if (dcc == 1)
+ rc = -EAGAIN;
break;
case QDIO_IRQ_STATE_STOPPED:
break;
default:
WARN_ON_ONCE(1);
}
+
+ if (rc == -EAGAIN) {
+ DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qint retry");
+ rc = ccw_device_start(cdev, irq_ptr->ccw, intparm, 0, 0);
+ if (!rc)
+ return;
+ DBF_ERROR("%4x RETRY ERR", irq_ptr->schid.sch_no);
+ DBF_ERROR("rc:%4x", rc);
+ qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR);
+ }
+
wake_up(&cdev->private->wait_q);
}
diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c
index 0a3a678..6087547 100644
--- a/drivers/s390/crypto/zcrypt_ccamisc.c
+++ b/drivers/s390/crypto/zcrypt_ccamisc.c
@@ -658,7 +658,7 @@
(int)prepcblk->ccp_rtcode,
(int)prepcblk->ccp_rscode);
if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290)
- rc = -EAGAIN;
+ rc = -EBUSY;
else
rc = -EIO;
goto out;
@@ -1263,7 +1263,7 @@
(int)prepcblk->ccp_rtcode,
(int)prepcblk->ccp_rscode);
if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290)
- rc = -EAGAIN;
+ rc = -EBUSY;
else
rc = -EIO;
goto out;
@@ -1426,7 +1426,7 @@
(int)prepcblk->ccp_rtcode,
(int)prepcblk->ccp_rscode);
if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290)
- rc = -EAGAIN;
+ rc = -EBUSY;
else
rc = -EIO;
goto out;
diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c
index eb7f548..9bcf8fc 100644
--- a/drivers/s390/crypto/zcrypt_ep11misc.c
+++ b/drivers/s390/crypto/zcrypt_ep11misc.c
@@ -556,13 +556,29 @@
pl += 2;
ret = *((u32 *)pl);
if (ret != 0) {
- ZCRYPT_DBF_ERR("%s return value 0x%04x != 0\n", func, ret);
+ ZCRYPT_DBF_ERR("%s return value 0x%08x != 0\n", func, ret);
return -EIO;
}
return 0;
}
+/* Check ep11 reply cprb, return 0 or suggested errno value. */
+static int check_reply_cprb(const struct ep11_cprb *rep, const char *func)
+{
+ /* check ep11 reply return code field */
+ if (rep->ret_code) {
+ ZCRYPT_DBF_ERR("%s ep11 reply ret_code=0x%08x\n", __func__,
+ rep->ret_code);
+ if (rep->ret_code == 0x000c0003)
+ return -EBUSY;
+ else
+ return -EIO;
+ }
+
+ return 0;
+}
+
/*
* Helper function which does an ep11 query with given query type.
*/
@@ -627,6 +643,12 @@
goto out;
}
+ /* check ep11 reply cprb */
+ rc = check_reply_cprb(rep, __func__);
+ if (rc)
+ goto out;
+
+ /* check payload */
rc = check_reply_pl((u8 *)rep_pl, __func__);
if (rc)
goto out;
@@ -877,6 +899,12 @@
goto out;
}
+ /* check ep11 reply cprb */
+ rc = check_reply_cprb(rep, __func__);
+ if (rc)
+ goto out;
+
+ /* check payload */
rc = check_reply_pl((u8 *)rep_pl, __func__);
if (rc)
goto out;
@@ -1028,6 +1056,12 @@
goto out;
}
+ /* check ep11 reply cprb */
+ rc = check_reply_cprb(rep, __func__);
+ if (rc)
+ goto out;
+
+ /* check payload */
rc = check_reply_pl((u8 *)rep_pl, __func__);
if (rc)
goto out;
@@ -1185,6 +1219,12 @@
goto out;
}
+ /* check ep11 reply cprb */
+ rc = check_reply_cprb(rep, __func__);
+ if (rc)
+ goto out;
+
+ /* check payload */
rc = check_reply_pl((u8 *)rep_pl, __func__);
if (rc)
goto out;
@@ -1339,6 +1379,12 @@
goto out;
}
+ /* check ep11 reply cprb */
+ rc = check_reply_cprb(rep, __func__);
+ if (rc)
+ goto out;
+
+ /* check payload */
rc = check_reply_pl((u8 *)rep_pl, __func__);
if (rc)
goto out;
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 2c8e964..43778b0 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -292,13 +292,16 @@
static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
{
clear_bit(dmb->sba_idx, ism->sba_bitmap);
- dma_free_coherent(&ism->pdev->dev, dmb->dmb_len,
- dmb->cpu_addr, dmb->dma_addr);
+ dma_unmap_page(&ism->pdev->dev, dmb->dma_addr, dmb->dmb_len,
+ DMA_FROM_DEVICE);
+ folio_put(virt_to_folio(dmb->cpu_addr));
}
static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb)
{
+ struct folio *folio;
unsigned long bit;
+ int rc;
if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev))
return -EINVAL;
@@ -315,14 +318,30 @@
test_and_set_bit(dmb->sba_idx, ism->sba_bitmap))
return -EINVAL;
- dmb->cpu_addr = dma_alloc_coherent(&ism->pdev->dev, dmb->dmb_len,
- &dmb->dma_addr,
- GFP_KERNEL | __GFP_NOWARN |
- __GFP_NOMEMALLOC | __GFP_NORETRY);
- if (!dmb->cpu_addr)
- clear_bit(dmb->sba_idx, ism->sba_bitmap);
+ folio = folio_alloc(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC |
+ __GFP_NORETRY, get_order(dmb->dmb_len));
- return dmb->cpu_addr ? 0 : -ENOMEM;
+ if (!folio) {
+ rc = -ENOMEM;
+ goto out_bit;
+ }
+
+ dmb->cpu_addr = folio_address(folio);
+ dmb->dma_addr = dma_map_page(&ism->pdev->dev,
+ virt_to_page(dmb->cpu_addr), 0,
+ dmb->dmb_len, DMA_FROM_DEVICE);
+ if (dma_mapping_error(&ism->pdev->dev, dmb->dma_addr)) {
+ rc = -ENOMEM;
+ goto out_free;
+ }
+
+ return 0;
+
+out_free:
+ kfree(dmb->cpu_addr);
+out_bit:
+ clear_bit(dmb->sba_idx, ism->sba_bitmap);
+ return rc;
}
int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb,
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index f0b8b70..a3adaec 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -364,22 +364,6 @@
return rc;
}
-static int qeth_alloc_cq(struct qeth_card *card)
-{
- if (card->options.cq == QETH_CQ_ENABLED) {
- QETH_CARD_TEXT(card, 2, "cqon");
- card->qdio.c_q = qeth_alloc_qdio_queue();
- if (!card->qdio.c_q) {
- dev_err(&card->gdev->dev, "Failed to create completion queue\n");
- return -ENOMEM;
- }
- } else {
- QETH_CARD_TEXT(card, 2, "nocq");
- card->qdio.c_q = NULL;
- }
- return 0;
-}
-
static void qeth_free_cq(struct qeth_card *card)
{
if (card->qdio.c_q) {
@@ -388,6 +372,25 @@
}
}
+static int qeth_alloc_cq(struct qeth_card *card)
+{
+ if (card->options.cq == QETH_CQ_ENABLED) {
+ QETH_CARD_TEXT(card, 2, "cqon");
+ if (!card->qdio.c_q) {
+ card->qdio.c_q = qeth_alloc_qdio_queue();
+ if (!card->qdio.c_q) {
+ dev_err(&card->gdev->dev,
+ "Failed to create completion queue\n");
+ return -ENOMEM;
+ }
+ }
+ } else {
+ QETH_CARD_TEXT(card, 2, "nocq");
+ qeth_free_cq(card);
+ }
+ return 0;
+}
+
static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15,
int delayed)
{
@@ -2628,6 +2631,10 @@
QETH_CARD_TEXT(card, 2, "allcqdbf");
+ /* completion */
+ if (qeth_alloc_cq(card))
+ goto out_err;
+
if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED,
QETH_QDIO_ALLOCATED) != QETH_QDIO_UNINITIALIZED)
return 0;
@@ -2663,10 +2670,6 @@
queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT;
}
- /* completion */
- if (qeth_alloc_cq(card))
- goto out_freeoutq;
-
return 0;
out_freeoutq:
@@ -2677,6 +2680,8 @@
qeth_free_buffer_pool(card);
out_buffer_pool:
atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED);
+ qeth_free_cq(card);
+out_err:
return -ENOMEM;
}
@@ -2684,11 +2689,12 @@
{
int i, j;
+ qeth_free_cq(card);
+
if (atomic_xchg(&card->qdio.state, QETH_QDIO_UNINITIALIZED) ==
QETH_QDIO_UNINITIALIZED)
return;
- qeth_free_cq(card);
for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
if (card->qdio.in_q->bufs[j].rx_skb) {
consume_skb(card->qdio.in_q->bufs[j].rx_skb);
@@ -3742,24 +3748,11 @@
int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq)
{
- int rc;
+ if (card->options.cq == QETH_CQ_NOTAVAILABLE)
+ return -1;
- if (card->options.cq == QETH_CQ_NOTAVAILABLE) {
- rc = -1;
- goto out;
- } else {
- if (card->options.cq == cq) {
- rc = 0;
- goto out;
- }
-
- qeth_free_qdio_queues(card);
- card->options.cq = cq;
- rc = 0;
- }
-out:
- return rc;
-
+ card->options.cq = cq;
+ return 0;
}
EXPORT_SYMBOL_GPL(qeth_configure_cq);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 097dfe4..35f8e00 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1797,7 +1797,7 @@
if (dev_is_sata(device)) {
struct ata_link *link = &device->sata_dev.ap->link;
- rc = ata_wait_after_reset(link, HISI_SAS_WAIT_PHYUP_TIMEOUT,
+ rc = ata_wait_after_reset(link, jiffies + HISI_SAS_WAIT_PHYUP_TIMEOUT,
smp_ata_check_ready_type);
} else {
msleep(2000);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 7d2a335..34f96cc 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2244,7 +2244,15 @@
case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP:
if ((dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) &&
(sipc_rx_err_type & RX_FIS_STATUS_ERR_MSK)) {
- ts->stat = SAS_PROTO_RESPONSE;
+ if (task->ata_task.use_ncq) {
+ struct domain_device *device = task->dev;
+ struct hisi_sas_device *sas_dev = device->lldd_dev;
+
+ sas_dev->dev_status = HISI_SAS_DEV_NCQ_ERR;
+ slot->abort = 1;
+ } else {
+ ts->stat = SAS_PROTO_RESPONSE;
+ }
} else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) {
ts->residual = trans_tx_fail_type;
ts->stat = SAS_DATA_UNDERRUN;
diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c
index 26e6b3e..dcde55c 100644
--- a/drivers/scsi/qla2xxx/qla_edif.c
+++ b/drivers/scsi/qla2xxx/qla_edif.c
@@ -1100,7 +1100,7 @@
list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) {
if (fcport->edif.enable) {
- if (pcnt > app_req.num_ports)
+ if (pcnt >= app_req.num_ports)
break;
app_reply->elem[pcnt].rekey_count =
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 2e28e23..5b3230e 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -635,10 +635,9 @@
if (blk_queue_add_random(q))
add_disk_randomness(req->q->disk);
- if (!blk_rq_is_passthrough(req)) {
- WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED));
- cmd->flags &= ~SCMD_INITIALIZED;
- }
+ WARN_ON_ONCE(!blk_rq_is_passthrough(req) &&
+ !(cmd->flags & SCMD_INITIALIZED));
+ cmd->flags = 0;
/*
* Calling rcu_barrier() is not necessary here because the
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 58fdf67..65cdc8b 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3120,6 +3120,7 @@
{
struct scsi_device *sdp = sdkp->device;
const struct scsi_io_group_descriptor *desc, *start, *end;
+ u16 permanent_stream_count_old;
struct scsi_sense_hdr sshdr;
struct scsi_mode_data data;
int res;
@@ -3140,12 +3141,13 @@
for (desc = start; desc < end; desc++)
if (!desc->st_enble || !sd_is_perm_stream(sdkp, desc - start))
break;
+ permanent_stream_count_old = sdkp->permanent_stream_count;
sdkp->permanent_stream_count = desc - start;
if (sdkp->rscs && sdkp->permanent_stream_count < 2)
sd_printk(KERN_INFO, sdkp,
"Unexpected: RSCS has been set and the permanent stream count is %u\n",
sdkp->permanent_stream_count);
- else if (sdkp->permanent_stream_count)
+ else if (sdkp->permanent_stream_count != permanent_stream_count_old)
sd_printk(KERN_INFO, sdkp, "permanent stream count = %d\n",
sdkp->permanent_stream_count);
}
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 386981c6..baf870a 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -285,6 +285,7 @@
int dev = iminor(inode);
int flags = filp->f_flags;
struct request_queue *q;
+ struct scsi_device *device;
Sg_device *sdp;
Sg_fd *sfp;
int retval;
@@ -301,11 +302,12 @@
/* This driver's module count bumped by fops_get in <linux/fs.h> */
/* Prevent the device driver from vanishing while we sleep */
- retval = scsi_device_get(sdp->device);
+ device = sdp->device;
+ retval = scsi_device_get(device);
if (retval)
goto sg_put;
- retval = scsi_autopm_get_device(sdp->device);
+ retval = scsi_autopm_get_device(device);
if (retval)
goto sdp_put;
@@ -313,7 +315,7 @@
* check if O_NONBLOCK. Permits SCSI commands to be issued
* during error recovery. Tread carefully. */
if (!((flags & O_NONBLOCK) ||
- scsi_block_when_processing_errors(sdp->device))) {
+ scsi_block_when_processing_errors(device))) {
retval = -ENXIO;
/* we are in error recovery for this device */
goto error_out;
@@ -344,7 +346,7 @@
if (sdp->open_cnt < 1) { /* no existing opens */
sdp->sgdebug = 0;
- q = sdp->device->request_queue;
+ q = device->request_queue;
sdp->sg_tablesize = queue_max_segments(q);
}
sfp = sg_add_sfp(sdp);
@@ -370,10 +372,11 @@
error_mutex_locked:
mutex_unlock(&sdp->open_rel_lock);
error_out:
- scsi_autopm_put_device(sdp->device);
+ scsi_autopm_put_device(device);
sdp_put:
- scsi_device_put(sdp->device);
- goto sg_put;
+ kref_put(&sdp->d_ref, sg_device_destroy);
+ scsi_device_put(device);
+ return retval;
}
/* Release resources associated with a successful sg_open()
@@ -2233,7 +2236,6 @@
"sg_remove_sfp: sfp=0x%p\n", sfp));
kfree(sfp);
- WARN_ON_ONCE(kref_read(&sdp->d_ref) != 1);
kref_put(&sdp->d_ref, sg_device_destroy);
scsi_device_put(device);
module_put(THIS_MODULE);
diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c
index efeba82..a09a26b 100644
--- a/drivers/slimbus/qcom-ngd-ctrl.c
+++ b/drivers/slimbus/qcom-ngd-ctrl.c
@@ -1451,7 +1451,11 @@
ctrl = container_of(work, struct qcom_slim_ngd_ctrl, ngd_up_work);
/* Make sure qmi service is up before continuing */
- wait_for_completion_interruptible(&ctrl->qmi_up);
+ if (!wait_for_completion_interruptible_timeout(&ctrl->qmi_up,
+ msecs_to_jiffies(MSEC_PER_SEC))) {
+ dev_err(ctrl->dev, "QMI wait timeout\n");
+ return;
+ }
mutex_lock(&ctrl->ssr_lock);
qcom_slim_ngd_enable(ctrl, true);
diff --git a/drivers/soc/mediatek/Kconfig b/drivers/soc/mediatek/Kconfig
index 50c664b..1b7afb1 100644
--- a/drivers/soc/mediatek/Kconfig
+++ b/drivers/soc/mediatek/Kconfig
@@ -72,6 +72,7 @@
tristate "MediaTek SoC Information"
default y
depends on NVMEM_MTK_EFUSE
+ select SOC_BUS
help
The MediaTek SoC Information (mtk-socinfo) driver provides
information about the SoC to the userspace including the
diff --git a/drivers/soc/mediatek/mtk-svs.c b/drivers/soc/mediatek/mtk-svs.c
index c832f5c..9a91298 100644
--- a/drivers/soc/mediatek/mtk-svs.c
+++ b/drivers/soc/mediatek/mtk-svs.c
@@ -1768,6 +1768,7 @@
const struct svs_bank_pdata *bdata;
struct svs_bank *svsb;
struct dev_pm_opp *opp;
+ char tz_name_buf[20];
unsigned long freq;
int count, ret;
u32 idx, i;
@@ -1819,10 +1820,12 @@
}
if (!IS_ERR_OR_NULL(bdata->tzone_name)) {
- svsb->tzd = thermal_zone_get_zone_by_name(bdata->tzone_name);
+ snprintf(tz_name_buf, ARRAY_SIZE(tz_name_buf),
+ "%s-thermal", bdata->tzone_name);
+ svsb->tzd = thermal_zone_get_zone_by_name(tz_name_buf);
if (IS_ERR(svsb->tzd)) {
dev_err(svsb->dev, "cannot get \"%s\" thermal zone\n",
- bdata->tzone_name);
+ tz_name_buf);
return PTR_ERR(svsb->tzd);
}
}
diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index 7cd24bd..6bcf8e7 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -130,6 +130,19 @@
writel(frame_size, amd_manager->mmio + ACP_SW_FRAMESIZE);
}
+static void amd_sdw_wake_enable(struct amd_sdw_manager *amd_manager, bool enable)
+{
+ u32 wake_ctrl;
+
+ wake_ctrl = readl(amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11);
+ if (enable)
+ wake_ctrl |= AMD_SDW_WAKE_INTR_MASK;
+ else
+ wake_ctrl &= ~AMD_SDW_WAKE_INTR_MASK;
+
+ writel(wake_ctrl, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11);
+}
+
static void amd_sdw_ctl_word_prep(u32 *lower_word, u32 *upper_word, struct sdw_msg *msg,
int cmd_offset)
{
@@ -1095,6 +1108,7 @@
}
if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) {
+ amd_sdw_wake_enable(amd_manager, false);
return amd_sdw_clock_stop(amd_manager);
} else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) {
/*
@@ -1121,6 +1135,7 @@
return 0;
}
if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) {
+ amd_sdw_wake_enable(amd_manager, true);
return amd_sdw_clock_stop(amd_manager);
} else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) {
ret = amd_sdw_clock_stop(amd_manager);
diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h
index 418b679..7070654 100644
--- a/drivers/soundwire/amd_manager.h
+++ b/drivers/soundwire/amd_manager.h
@@ -152,7 +152,7 @@
#define AMD_SDW0_EXT_INTR_MASK 0x200000
#define AMD_SDW1_EXT_INTR_MASK 4
#define AMD_SDW_IRQ_MASK_0TO7 0x77777777
-#define AMD_SDW_IRQ_MASK_8TO11 0x000d7777
+#define AMD_SDW_IRQ_MASK_8TO11 0x000c7777
#define AMD_SDW_IRQ_ERROR_MASK 0xff
#define AMD_SDW_MAX_FREQ_NUM 1
#define AMD_SDW0_MAX_TX_PORTS 3
@@ -190,6 +190,7 @@
#define AMD_SDW_CLK_RESUME_REQ 2
#define AMD_SDW_CLK_RESUME_DONE 3
#define AMD_SDW_WAKE_STAT_MASK BIT(16)
+#define AMD_SDW_WAKE_INTR_MASK BIT(16)
static u32 amd_sdw_freq_tbl[AMD_SDW_MAX_FREQ_NUM] = {
AMD_SDW_DEFAULT_CLK_FREQ,
diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
index 7cc219d..e358ac5 100644
--- a/drivers/spi/spi-axi-spi-engine.c
+++ b/drivers/spi/spi-axi-spi-engine.c
@@ -623,7 +623,7 @@
version = readl(spi_engine->base + ADI_AXI_REG_VERSION);
if (ADI_AXI_PCORE_VER_MAJOR(version) != 1) {
- dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n",
+ dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%u\n",
ADI_AXI_PCORE_VER_MAJOR(version),
ADI_AXI_PCORE_VER_MINOR(version),
ADI_AXI_PCORE_VER_PATCH(version));
diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c
index 35ef5e8..77e9738 100644
--- a/drivers/spi/spi-hisi-kunpeng.c
+++ b/drivers/spi/spi-hisi-kunpeng.c
@@ -151,8 +151,6 @@
HISI_SPI_DBGFS_REG("ENR", HISI_SPI_ENR),
HISI_SPI_DBGFS_REG("FIFOC", HISI_SPI_FIFOC),
HISI_SPI_DBGFS_REG("IMR", HISI_SPI_IMR),
- HISI_SPI_DBGFS_REG("DIN", HISI_SPI_DIN),
- HISI_SPI_DBGFS_REG("DOUT", HISI_SPI_DOUT),
HISI_SPI_DBGFS_REG("SR", HISI_SPI_SR),
HISI_SPI_DBGFS_REG("RISR", HISI_SPI_RISR),
HISI_SPI_DBGFS_REG("ISR", HISI_SPI_ISR),
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index ff75838..a2c467d 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -4523,6 +4523,7 @@
wait_for_completion(&done);
status = message->status;
}
+ message->complete = NULL;
message->context = NULL;
return status;
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index c1fbcdd..c40217f 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -3672,6 +3672,8 @@
{
struct configfs_subsystem *subsys = &target_core_fabrics;
struct t10_alua_lu_gp *lu_gp;
+ struct cred *kern_cred;
+ const struct cred *old_cred;
int ret;
pr_debug("TARGET_CORE[0]: Loading Generic Kernel Storage"
@@ -3748,11 +3750,21 @@
if (ret < 0)
goto out;
+ /* We use the kernel credentials to access the target directory */
+ kern_cred = prepare_kernel_cred(&init_task);
+ if (!kern_cred) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ old_cred = override_creds(kern_cred);
target_init_dbroot();
+ revert_creds(old_cred);
+ put_cred(kern_cred);
return 0;
out:
+ target_xcopy_release_pt();
configfs_unregister_subsystem(subsys);
core_dev_release_virtual_lun0();
rd_module_exit();
diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
index c617e8b..5693cc8b 100644
--- a/drivers/thermal/thermal_debugfs.c
+++ b/drivers/thermal/thermal_debugfs.c
@@ -139,11 +139,13 @@
* we keep track of the current position in the history array.
*
* @tz_episodes: a list of thermal mitigation episodes
+ * @tz: thermal zone this object belongs to
* @trips_crossed: an array of trip points crossed by id
* @nr_trips: the number of trip points currently being crossed
*/
struct tz_debugfs {
struct list_head tz_episodes;
+ struct thermal_zone_device *tz;
int *trips_crossed;
int nr_trips;
};
@@ -503,15 +505,23 @@
*/
void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev)
{
- struct thermal_debugfs *thermal_dbg = cdev->debugfs;
+ struct thermal_debugfs *thermal_dbg;
- if (!thermal_dbg)
+ mutex_lock(&cdev->lock);
+
+ thermal_dbg = cdev->debugfs;
+ if (!thermal_dbg) {
+ mutex_unlock(&cdev->lock);
return;
+ }
+
+ cdev->debugfs = NULL;
+
+ mutex_unlock(&cdev->lock);
mutex_lock(&thermal_dbg->lock);
thermal_debugfs_cdev_clear(&thermal_dbg->cdev_dbg);
- cdev->debugfs = NULL;
mutex_unlock(&thermal_dbg->lock);
@@ -616,6 +626,7 @@
tze->trip_stats[trip_id].timestamp = now;
tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, temperature);
tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, temperature);
+ tze->trip_stats[trip_id].count++;
tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg +
(temperature - tze->trip_stats[trip_id].avg) /
tze->trip_stats[trip_id].count;
@@ -715,8 +726,7 @@
static void *tze_seq_start(struct seq_file *s, loff_t *pos)
{
- struct thermal_zone_device *tz = s->private;
- struct thermal_debugfs *thermal_dbg = tz->debugfs;
+ struct thermal_debugfs *thermal_dbg = s->private;
struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg;
mutex_lock(&thermal_dbg->lock);
@@ -726,8 +736,7 @@
static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos)
{
- struct thermal_zone_device *tz = s->private;
- struct thermal_debugfs *thermal_dbg = tz->debugfs;
+ struct thermal_debugfs *thermal_dbg = s->private;
struct tz_debugfs *tz_dbg = &thermal_dbg->tz_dbg;
return seq_list_next(v, &tz_dbg->tz_episodes, pos);
@@ -735,15 +744,15 @@
static void tze_seq_stop(struct seq_file *s, void *v)
{
- struct thermal_zone_device *tz = s->private;
- struct thermal_debugfs *thermal_dbg = tz->debugfs;
+ struct thermal_debugfs *thermal_dbg = s->private;
mutex_unlock(&thermal_dbg->lock);
}
static int tze_seq_show(struct seq_file *s, void *v)
{
- struct thermal_zone_device *tz = s->private;
+ struct thermal_debugfs *thermal_dbg = s->private;
+ struct thermal_zone_device *tz = thermal_dbg->tz_dbg.tz;
struct thermal_trip *trip;
struct tz_episode *tze;
const char *type;
@@ -809,6 +818,8 @@
tz_dbg = &thermal_dbg->tz_dbg;
+ tz_dbg->tz = tz;
+
tz_dbg->trips_crossed = kzalloc(sizeof(int) * tz->num_trips, GFP_KERNEL);
if (!tz_dbg->trips_crossed) {
thermal_debugfs_remove_id(thermal_dbg);
@@ -817,23 +828,44 @@
INIT_LIST_HEAD(&tz_dbg->tz_episodes);
- debugfs_create_file("mitigations", 0400, thermal_dbg->d_top, tz, &tze_fops);
+ debugfs_create_file("mitigations", 0400, thermal_dbg->d_top,
+ thermal_dbg, &tze_fops);
tz->debugfs = thermal_dbg;
}
void thermal_debug_tz_remove(struct thermal_zone_device *tz)
{
- struct thermal_debugfs *thermal_dbg = tz->debugfs;
+ struct thermal_debugfs *thermal_dbg;
+ struct tz_episode *tze, *tmp;
+ struct tz_debugfs *tz_dbg;
+ int *trips_crossed;
- if (!thermal_dbg)
+ mutex_lock(&tz->lock);
+
+ thermal_dbg = tz->debugfs;
+ if (!thermal_dbg) {
+ mutex_unlock(&tz->lock);
return;
+ }
+
+ tz->debugfs = NULL;
+
+ mutex_unlock(&tz->lock);
+
+ tz_dbg = &thermal_dbg->tz_dbg;
mutex_lock(&thermal_dbg->lock);
- tz->debugfs = NULL;
+ trips_crossed = tz_dbg->trips_crossed;
+
+ list_for_each_entry_safe(tze, tmp, &tz_dbg->tz_episodes, node) {
+ list_del(&tze->node);
+ kfree(tze);
+ }
mutex_unlock(&thermal_dbg->lock);
thermal_debugfs_remove_id(thermal_dbg);
+ kfree(trips_crossed);
}
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 6ffc4e8..326433d 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -3180,22 +3180,29 @@
{
struct tb_port *up, *down;
- if (sw->is_unplugged)
- return;
if (!tb_route(sw) || tb_switch_is_icm(sw))
return;
+ /*
+ * Unconfigure downstream port so that wake-on-connect can be
+ * configured after router unplug. No need to unconfigure upstream port
+ * since its router is unplugged.
+ */
+ up = tb_upstream_port(sw);
+ down = up->remote;
+ if (tb_switch_is_usb4(down->sw))
+ usb4_port_unconfigure(down);
+ else
+ tb_lc_unconfigure_port(down);
+
+ if (sw->is_unplugged)
+ return;
+
up = tb_upstream_port(sw);
if (tb_switch_is_usb4(up->sw))
usb4_port_unconfigure(up);
else
tb_lc_unconfigure_port(up);
-
- down = up->remote;
- if (tb_switch_is_usb4(down->sw))
- usb4_port_unconfigure(down);
- else
- tb_lc_unconfigure_port(down);
}
static void tb_switch_credits_init(struct tb_switch *sw)
@@ -3441,7 +3448,26 @@
return tb_lc_set_wake(sw, flags);
}
-int tb_switch_resume(struct tb_switch *sw)
+static void tb_switch_check_wakes(struct tb_switch *sw)
+{
+ if (device_may_wakeup(&sw->dev)) {
+ if (tb_switch_is_usb4(sw))
+ usb4_switch_check_wakes(sw);
+ }
+}
+
+/**
+ * tb_switch_resume() - Resume a switch after sleep
+ * @sw: Switch to resume
+ * @runtime: Is this resume from runtime suspend or system sleep
+ *
+ * Resumes and re-enumerates router (and all its children), if still plugged
+ * after suspend. Don't enumerate device router whose UID was changed during
+ * suspend. If this is resume from system sleep, notifies PM core about the
+ * wakes occurred during suspend. Disables all wakes, except USB4 wake of
+ * upstream port for USB4 routers that shall be always enabled.
+ */
+int tb_switch_resume(struct tb_switch *sw, bool runtime)
{
struct tb_port *port;
int err;
@@ -3490,6 +3516,9 @@
if (err)
return err;
+ if (!runtime)
+ tb_switch_check_wakes(sw);
+
/* Disable wakes */
tb_switch_set_wake(sw, 0);
@@ -3519,7 +3548,8 @@
*/
if (tb_port_unlock(port))
tb_port_warn(port, "failed to unlock port\n");
- if (port->remote && tb_switch_resume(port->remote->sw)) {
+ if (port->remote &&
+ tb_switch_resume(port->remote->sw, runtime)) {
tb_port_warn(port,
"lost during suspend, disconnecting\n");
tb_sw_set_unplugged(port->remote->sw);
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index c5ce7a6..3e44c78 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -1801,6 +1801,12 @@
continue;
}
+ /* Needs to be on different routers */
+ if (in->sw == port->sw) {
+ tb_port_dbg(port, "skipping DP OUT on same router\n");
+ continue;
+ }
+
tb_port_dbg(port, "DP OUT available\n");
/*
@@ -2936,7 +2942,7 @@
if (!tb_switch_is_usb4(tb->root_switch))
tb_switch_reset(tb->root_switch);
- tb_switch_resume(tb->root_switch);
+ tb_switch_resume(tb->root_switch, false);
tb_free_invalid_tunnels(tb);
tb_free_unplugged_children(tb->root_switch);
tb_restore_children(tb->root_switch);
@@ -3062,7 +3068,7 @@
struct tb_tunnel *tunnel, *n;
mutex_lock(&tb->lock);
- tb_switch_resume(tb->root_switch);
+ tb_switch_resume(tb->root_switch, true);
tb_free_invalid_tunnels(tb);
tb_restore_children(tb->root_switch);
list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list)
diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h
index feed8ec..18aae4c 100644
--- a/drivers/thunderbolt/tb.h
+++ b/drivers/thunderbolt/tb.h
@@ -827,7 +827,7 @@
int tb_switch_add(struct tb_switch *sw);
void tb_switch_remove(struct tb_switch *sw);
void tb_switch_suspend(struct tb_switch *sw, bool runtime);
-int tb_switch_resume(struct tb_switch *sw);
+int tb_switch_resume(struct tb_switch *sw, bool runtime);
int tb_switch_reset(struct tb_switch *sw);
int tb_switch_wait_for_bit(struct tb_switch *sw, u32 offset, u32 bit,
u32 value, int timeout_msec);
@@ -1288,6 +1288,7 @@
return usb4_switch_version(sw) > 0;
}
+void usb4_switch_check_wakes(struct tb_switch *sw);
int usb4_switch_setup(struct tb_switch *sw);
int usb4_switch_configuration_valid(struct tb_switch *sw);
int usb4_switch_read_uid(struct tb_switch *sw, u64 *uid);
diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c
index 9860b49..78b06e9 100644
--- a/drivers/thunderbolt/usb4.c
+++ b/drivers/thunderbolt/usb4.c
@@ -155,7 +155,13 @@
tx_dwords, rx_data, rx_dwords);
}
-static void usb4_switch_check_wakes(struct tb_switch *sw)
+/**
+ * usb4_switch_check_wakes() - Check for wakes and notify PM core about them
+ * @sw: Router whose wakes to check
+ *
+ * Checks wakes occurred during suspend and notify the PM core about them.
+ */
+void usb4_switch_check_wakes(struct tb_switch *sw)
{
bool wakeup_usb4 = false;
struct usb4_port *usb4;
@@ -163,9 +169,6 @@
bool wakeup = false;
u32 val;
- if (!device_may_wakeup(&sw->dev))
- return;
-
if (tb_route(sw)) {
if (tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_6, 1))
return;
@@ -244,8 +247,6 @@
u32 val = 0;
int ret;
- usb4_switch_check_wakes(sw);
-
if (!tb_route(sw))
return 0;
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index a3acbf0..1300c92 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -356,9 +356,9 @@
long rate;
int ret;
+ clk_disable_unprepare(d->clk);
rate = clk_round_rate(d->clk, newrate);
- if (rate > 0 && p->uartclk != rate) {
- clk_disable_unprepare(d->clk);
+ if (rate > 0) {
/*
* Note that any clock-notifer worker will block in
* serial8250_update_uartclk() until we are done.
@@ -366,8 +366,8 @@
ret = clk_set_rate(d->clk, newrate);
if (!ret)
p->uartclk = rate;
- clk_prepare_enable(d->clk);
}
+ clk_prepare_enable(d->clk);
dw8250_do_set_termios(p, termios, old);
}
diff --git a/drivers/tty/serial/8250/8250_lpc18xx.c b/drivers/tty/serial/8250/8250_lpc18xx.c
index 7984ee0..47e1a05 100644
--- a/drivers/tty/serial/8250/8250_lpc18xx.c
+++ b/drivers/tty/serial/8250/8250_lpc18xx.c
@@ -151,7 +151,7 @@
ret = uart_read_port_properties(&uart.port);
if (ret)
- return ret;
+ goto dis_uart_clk;
uart.port.iotype = UPIO_MEM32;
uart.port.regshift = 2;
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 0d35c77..e2e4f99 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -5010,12 +5010,6 @@
{ PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_QUATRO_B,
PCI_ANY_ID, PCI_ANY_ID, 0, 0,
pbn_b0_bt_2_115200 },
- { PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_QUATTRO_A,
- PCI_ANY_ID, PCI_ANY_ID, 0, 0,
- pbn_b0_bt_2_115200 },
- { PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_QUATTRO_B,
- PCI_ANY_ID, PCI_ANY_ID, 0, 0,
- pbn_b0_bt_2_115200 },
{ PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_OCTO_A,
PCI_ANY_ID, PCI_ANY_ID, 0, 0,
pbn_b0_bt_4_460800 },
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 4749331..1e8853e 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -1086,11 +1086,13 @@
static irqreturn_t mxs_auart_irq_handle(int irq, void *context)
{
- u32 istat;
+ u32 istat, stat;
struct mxs_auart_port *s = context;
u32 mctrl_temp = s->mctrl_prev;
- u32 stat = mxs_read(s, REG_STAT);
+ uart_port_lock(&s->port);
+
+ stat = mxs_read(s, REG_STAT);
istat = mxs_read(s, REG_INTR);
/* ack irq */
@@ -1126,6 +1128,8 @@
istat &= ~AUART_INTR_TXIS;
}
+ uart_port_unlock(&s->port);
+
return IRQ_HANDLED;
}
diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c
index 05d97e8..92195f9 100644
--- a/drivers/tty/serial/pmac_zilog.c
+++ b/drivers/tty/serial/pmac_zilog.c
@@ -210,7 +210,6 @@
{
struct tty_port *port;
unsigned char ch, r1, drop, flag;
- int loops = 0;
/* Sanity check, make sure the old bug is no longer happening */
if (uap->port.state == NULL) {
@@ -291,25 +290,12 @@
if (r1 & Rx_OVR)
tty_insert_flip_char(port, 0, TTY_OVERRUN);
next_char:
- /* We can get stuck in an infinite loop getting char 0 when the
- * line is in a wrong HW state, we break that here.
- * When that happens, I disable the receive side of the driver.
- * Note that what I've been experiencing is a real irq loop where
- * I'm getting flooded regardless of the actual port speed.
- * Something strange is going on with the HW
- */
- if ((++loops) > 1000)
- goto flood;
ch = read_zsreg(uap, R0);
if (!(ch & Rx_CH_AV))
break;
}
return true;
- flood:
- pmz_interrupt_control(uap, 0);
- pmz_error("pmz: rx irq flood !\n");
- return true;
}
static void pmz_status_handle(struct uart_pmac_port *uap)
diff --git a/drivers/tty/serial/serial_base.h b/drivers/tty/serial/serial_base.h
index c74c548..b6c38d2 100644
--- a/drivers/tty/serial/serial_base.h
+++ b/drivers/tty/serial/serial_base.h
@@ -22,6 +22,7 @@
struct serial_port_device {
struct device dev;
struct uart_port *port;
+ unsigned int tx_enabled:1;
};
int serial_base_ctrl_init(void);
@@ -30,6 +31,9 @@
int serial_base_port_init(void);
void serial_base_port_exit(void);
+void serial_base_port_startup(struct uart_port *port);
+void serial_base_port_shutdown(struct uart_port *port);
+
int serial_base_driver_register(struct device_driver *driver);
void serial_base_driver_unregister(struct device_driver *driver);
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index ff85ebd..c476d88 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -156,7 +156,7 @@
* enabled, serial_port_runtime_resume() calls start_tx() again
* after enabling the device.
*/
- if (pm_runtime_active(&port_dev->dev))
+ if (!pm_runtime_enabled(port->dev) || pm_runtime_active(&port_dev->dev))
port->ops->start_tx(port);
pm_runtime_mark_last_busy(&port_dev->dev);
pm_runtime_put_autosuspend(&port_dev->dev);
@@ -323,16 +323,26 @@
bool init_hw)
{
struct tty_port *port = &state->port;
+ struct uart_port *uport;
int retval;
if (tty_port_initialized(port))
- return 0;
+ goto out_base_port_startup;
retval = uart_port_startup(tty, state, init_hw);
- if (retval)
+ if (retval) {
set_bit(TTY_IO_ERROR, &tty->flags);
+ return retval;
+ }
- return retval;
+out_base_port_startup:
+ uport = uart_port_check(state);
+ if (!uport)
+ return -EIO;
+
+ serial_base_port_startup(uport);
+
+ return 0;
}
/*
@@ -355,6 +365,9 @@
if (tty)
set_bit(TTY_IO_ERROR, &tty->flags);
+ if (uport)
+ serial_base_port_shutdown(uport);
+
if (tty_port_initialized(port)) {
tty_port_set_initialized(port, false);
@@ -1775,6 +1788,7 @@
uport->ops->stop_rx(uport);
uart_port_unlock_irq(uport);
+ serial_base_port_shutdown(uport);
uart_port_shutdown(port);
/*
@@ -1788,6 +1802,7 @@
* Free the transmit buffer.
*/
uart_port_lock_irq(uport);
+ uart_circ_clear(&state->xmit);
buf = state->xmit.buf;
state->xmit.buf = NULL;
uart_port_unlock_irq(uport);
diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c
index 22b9eeb..7e3a1c7 100644
--- a/drivers/tty/serial/serial_port.c
+++ b/drivers/tty/serial/serial_port.c
@@ -39,8 +39,12 @@
/* Flush any pending TX for the port */
uart_port_lock_irqsave(port, &flags);
+ if (!port_dev->tx_enabled)
+ goto unlock;
if (__serial_port_busy(port))
port->ops->start_tx(port);
+
+unlock:
uart_port_unlock_irqrestore(port, flags);
out:
@@ -60,6 +64,11 @@
return 0;
uart_port_lock_irqsave(port, &flags);
+ if (!port_dev->tx_enabled) {
+ uart_port_unlock_irqrestore(port, flags);
+ return 0;
+ }
+
busy = __serial_port_busy(port);
if (busy)
port->ops->start_tx(port);
@@ -71,6 +80,31 @@
return busy ? -EBUSY : 0;
}
+static void serial_base_port_set_tx(struct uart_port *port,
+ struct serial_port_device *port_dev,
+ bool enabled)
+{
+ unsigned long flags;
+
+ uart_port_lock_irqsave(port, &flags);
+ port_dev->tx_enabled = enabled;
+ uart_port_unlock_irqrestore(port, flags);
+}
+
+void serial_base_port_startup(struct uart_port *port)
+{
+ struct serial_port_device *port_dev = port->port_dev;
+
+ serial_base_port_set_tx(port, port_dev, true);
+}
+
+void serial_base_port_shutdown(struct uart_port *port)
+{
+ struct serial_port_device *port_dev = port->port_dev;
+
+ serial_base_port_set_tx(port, port_dev, false);
+}
+
static DEFINE_RUNTIME_DEV_PM_OPS(serial_port_pm,
serial_port_runtime_suspend,
serial_port_runtime_resume, NULL);
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index 58d169e..4fa5a03 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -861,6 +861,7 @@
const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs;
u32 sr;
unsigned int size;
+ irqreturn_t ret = IRQ_NONE;
sr = readl_relaxed(port->membase + ofs->isr);
@@ -869,11 +870,14 @@
(sr & USART_SR_TC)) {
stm32_usart_tc_interrupt_disable(port);
stm32_usart_rs485_rts_disable(port);
+ ret = IRQ_HANDLED;
}
- if ((sr & USART_SR_RTOF) && ofs->icr != UNDEF_REG)
+ if ((sr & USART_SR_RTOF) && ofs->icr != UNDEF_REG) {
writel_relaxed(USART_ICR_RTOCF,
port->membase + ofs->icr);
+ ret = IRQ_HANDLED;
+ }
if ((sr & USART_SR_WUF) && ofs->icr != UNDEF_REG) {
/* Clear wake up flag and disable wake up interrupt */
@@ -882,6 +886,7 @@
stm32_usart_clr_bits(port, ofs->cr3, USART_CR3_WUFIE);
if (irqd_is_wakeup_set(irq_get_irq_data(port->irq)))
pm_wakeup_event(tport->tty->dev, 0);
+ ret = IRQ_HANDLED;
}
/*
@@ -896,6 +901,7 @@
uart_unlock_and_check_sysrq(port);
if (size)
tty_flip_buffer_push(tport);
+ ret = IRQ_HANDLED;
}
}
@@ -903,6 +909,7 @@
uart_port_lock(port);
stm32_usart_transmit_chars(port);
uart_port_unlock(port);
+ ret = IRQ_HANDLED;
}
/* Receiver timeout irq for DMA RX */
@@ -912,9 +919,10 @@
uart_unlock_and_check_sysrq(port);
if (size)
tty_flip_buffer_push(tport);
+ ret = IRQ_HANDLED;
}
- return IRQ_HANDLED;
+ return ret;
}
static void stm32_usart_set_mctrl(struct uart_port *port, unsigned int mctrl)
@@ -1084,6 +1092,7 @@
val |= USART_CR2_SWAP;
writel_relaxed(val, port->membase + ofs->cr2);
}
+ stm32_port->throttled = false;
/* RX FIFO Flush */
if (ofs->rqr != UNDEF_REG)
diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 06859e1..7a00004 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -47,7 +47,7 @@
TSTBUS_MAX,
};
-#define QCOM_UFS_MAX_GEAR 4
+#define QCOM_UFS_MAX_GEAR 5
#define QCOM_UFS_MAX_LANE 2
enum {
@@ -67,26 +67,32 @@
[MODE_PWM][UFS_PWM_G2][UFS_LANE_1] = { 1844, 1000 },
[MODE_PWM][UFS_PWM_G3][UFS_LANE_1] = { 3688, 1000 },
[MODE_PWM][UFS_PWM_G4][UFS_LANE_1] = { 7376, 1000 },
+ [MODE_PWM][UFS_PWM_G5][UFS_LANE_1] = { 14752, 1000 },
[MODE_PWM][UFS_PWM_G1][UFS_LANE_2] = { 1844, 1000 },
[MODE_PWM][UFS_PWM_G2][UFS_LANE_2] = { 3688, 1000 },
[MODE_PWM][UFS_PWM_G3][UFS_LANE_2] = { 7376, 1000 },
[MODE_PWM][UFS_PWM_G4][UFS_LANE_2] = { 14752, 1000 },
+ [MODE_PWM][UFS_PWM_G5][UFS_LANE_2] = { 29504, 1000 },
[MODE_HS_RA][UFS_HS_G1][UFS_LANE_1] = { 127796, 1000 },
[MODE_HS_RA][UFS_HS_G2][UFS_LANE_1] = { 255591, 1000 },
[MODE_HS_RA][UFS_HS_G3][UFS_LANE_1] = { 1492582, 102400 },
[MODE_HS_RA][UFS_HS_G4][UFS_LANE_1] = { 2915200, 204800 },
+ [MODE_HS_RA][UFS_HS_G5][UFS_LANE_1] = { 5836800, 409600 },
[MODE_HS_RA][UFS_HS_G1][UFS_LANE_2] = { 255591, 1000 },
[MODE_HS_RA][UFS_HS_G2][UFS_LANE_2] = { 511181, 1000 },
[MODE_HS_RA][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 },
[MODE_HS_RA][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 },
+ [MODE_HS_RA][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 },
[MODE_HS_RB][UFS_HS_G1][UFS_LANE_1] = { 149422, 1000 },
[MODE_HS_RB][UFS_HS_G2][UFS_LANE_1] = { 298189, 1000 },
[MODE_HS_RB][UFS_HS_G3][UFS_LANE_1] = { 1492582, 102400 },
[MODE_HS_RB][UFS_HS_G4][UFS_LANE_1] = { 2915200, 204800 },
+ [MODE_HS_RB][UFS_HS_G5][UFS_LANE_1] = { 5836800, 409600 },
[MODE_HS_RB][UFS_HS_G1][UFS_LANE_2] = { 298189, 1000 },
[MODE_HS_RB][UFS_HS_G2][UFS_LANE_2] = { 596378, 1000 },
[MODE_HS_RB][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 },
[MODE_HS_RB][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 },
+ [MODE_HS_RB][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 },
[MODE_MAX][0][0] = { 7643136, 307200 },
};
diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
index 20d9762..6be3462 100644
--- a/drivers/uio/uio_hv_generic.c
+++ b/drivers/uio/uio_hv_generic.c
@@ -181,12 +181,14 @@
{
if (pdata->send_gpadl.gpadl_handle) {
vmbus_teardown_gpadl(dev->channel, &pdata->send_gpadl);
- vfree(pdata->send_buf);
+ if (!pdata->send_gpadl.decrypted)
+ vfree(pdata->send_buf);
}
if (pdata->recv_gpadl.gpadl_handle) {
vmbus_teardown_gpadl(dev->channel, &pdata->recv_gpadl);
- vfree(pdata->recv_buf);
+ if (!pdata->recv_gpadl.decrypted)
+ vfree(pdata->recv_buf);
}
}
@@ -295,7 +297,8 @@
ret = vmbus_establish_gpadl(channel, pdata->recv_buf,
RECV_BUFFER_SIZE, &pdata->recv_gpadl);
if (ret) {
- vfree(pdata->recv_buf);
+ if (!pdata->recv_gpadl.decrypted)
+ vfree(pdata->recv_buf);
goto fail_close;
}
@@ -317,7 +320,8 @@
ret = vmbus_establish_gpadl(channel, pdata->send_buf,
SEND_BUFFER_SIZE, &pdata->send_gpadl);
if (ret) {
- vfree(pdata->send_buf);
+ if (!pdata->send_gpadl.decrypted)
+ vfree(pdata->send_buf);
goto fail_close;
}
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index c8262e2..c553dec 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -485,7 +485,6 @@
static int service_outstanding_interrupt(struct wdm_device *desc)
{
int rv = 0;
- int used;
/* submit read urb only if the device is waiting for it */
if (!desc->resp_count || !--desc->resp_count)
@@ -500,10 +499,7 @@
goto out;
}
- used = test_and_set_bit(WDM_RESPONDING, &desc->flags);
- if (used)
- goto out;
-
+ set_bit(WDM_RESPONDING, &desc->flags);
spin_unlock_irq(&desc->iuspin);
rv = usb_submit_urb(desc->response, GFP_KERNEL);
spin_lock_irq(&desc->iuspin);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 9446660..0080530 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -5110,9 +5110,10 @@
}
if (usb_endpoint_maxp(&udev->ep0.desc) == i) {
; /* Initial ep0 maxpacket guess is right */
- } else if ((udev->speed == USB_SPEED_FULL ||
+ } else if (((udev->speed == USB_SPEED_FULL ||
udev->speed == USB_SPEED_HIGH) &&
- (i == 8 || i == 16 || i == 32 || i == 64)) {
+ (i == 8 || i == 16 || i == 32 || i == 64)) ||
+ (udev->speed >= USB_SPEED_SUPER && i > 0)) {
/* Initial guess is wrong; use the descriptor's value */
if (udev->speed == USB_SPEED_FULL)
dev_dbg(&udev->dev, "ep0 maxpacket = %d\n", i);
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index 686c01a..e7da2fc 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -51,13 +51,15 @@
struct usb_port *port_dev = to_usb_port(dev);
struct usb_device *hdev = to_usb_device(dev->parent->parent);
struct usb_hub *hub = usb_hub_to_struct_hub(hdev);
- struct usb_interface *intf = to_usb_interface(hub->intfdev);
+ struct usb_interface *intf = to_usb_interface(dev->parent);
int port1 = port_dev->portnum;
u16 portstatus, unused;
bool disabled;
int rc;
struct kernfs_node *kn;
+ if (!hub)
+ return -ENODEV;
hub_get(hub);
rc = usb_autopm_get_interface(intf);
if (rc < 0)
@@ -101,12 +103,14 @@
struct usb_port *port_dev = to_usb_port(dev);
struct usb_device *hdev = to_usb_device(dev->parent->parent);
struct usb_hub *hub = usb_hub_to_struct_hub(hdev);
- struct usb_interface *intf = to_usb_interface(hub->intfdev);
+ struct usb_interface *intf = to_usb_interface(dev->parent);
int port1 = port_dev->portnum;
bool disabled;
int rc;
struct kernfs_node *kn;
+ if (!hub)
+ return -ENODEV;
rc = kstrtobool(buf, &disabled);
if (rc)
return rc;
@@ -449,8 +453,10 @@
{
struct usb_port *port_dev = to_usb_port(dev);
- if (port_dev->child)
+ if (port_dev->child) {
usb_disable_usb2_hardware_lpm(port_dev->child);
+ usb_unlocked_disable_lpm(port_dev->child);
+ }
}
static const struct dev_pm_ops usb_port_pm_ops = {
diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c
index 79582b1..994a78a 100644
--- a/drivers/usb/dwc2/hcd_ddma.c
+++ b/drivers/usb/dwc2/hcd_ddma.c
@@ -867,13 +867,15 @@
struct dwc2_dma_desc *dma_desc;
struct dwc2_hcd_iso_packet_desc *frame_desc;
u16 frame_desc_idx;
- struct urb *usb_urb = qtd->urb->priv;
+ struct urb *usb_urb;
u16 remain = 0;
int rc = 0;
if (!qtd->urb)
return -EINVAL;
+ usb_urb = qtd->urb->priv;
+
dma_sync_single_for_cpu(hsotg->dev, qh->desc_list_dma + (idx *
sizeof(struct dwc2_dma_desc)),
sizeof(struct dwc2_dma_desc),
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 31684cd..1000413 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -104,6 +104,27 @@
return 0;
}
+void dwc3_enable_susphy(struct dwc3 *dwc, bool enable)
+{
+ u32 reg;
+
+ reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0));
+ if (enable && !dwc->dis_u3_susphy_quirk)
+ reg |= DWC3_GUSB3PIPECTL_SUSPHY;
+ else
+ reg &= ~DWC3_GUSB3PIPECTL_SUSPHY;
+
+ dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), reg);
+
+ reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
+ if (enable && !dwc->dis_u2_susphy_quirk)
+ reg |= DWC3_GUSB2PHYCFG_SUSPHY;
+ else
+ reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
+
+ dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
+}
+
void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode)
{
u32 reg;
@@ -585,11 +606,8 @@
*/
static int dwc3_phy_setup(struct dwc3 *dwc)
{
- unsigned int hw_mode;
u32 reg;
- hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0);
-
reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0));
/*
@@ -599,21 +617,16 @@
reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX;
/*
- * Above 1.94a, it is recommended to set DWC3_GUSB3PIPECTL_SUSPHY
- * to '0' during coreConsultant configuration. So default value
- * will be '0' when the core is reset. Application needs to set it
- * to '1' after the core initialization is completed.
+ * Above DWC_usb3.0 1.94a, it is recommended to set
+ * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration.
+ * So default value will be '0' when the core is reset. Application
+ * needs to set it to '1' after the core initialization is completed.
+ *
+ * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be
+ * cleared after power-on reset, and it can be set after core
+ * initialization.
*/
- if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A))
- reg |= DWC3_GUSB3PIPECTL_SUSPHY;
-
- /*
- * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be cleared after
- * power-on reset, and it can be set after core initialization, which is
- * after device soft-reset during initialization.
- */
- if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD)
- reg &= ~DWC3_GUSB3PIPECTL_SUSPHY;
+ reg &= ~DWC3_GUSB3PIPECTL_SUSPHY;
if (dwc->u2ss_inp3_quirk)
reg |= DWC3_GUSB3PIPECTL_U2SSINP3OK;
@@ -639,9 +652,6 @@
if (dwc->tx_de_emphasis_quirk)
reg |= DWC3_GUSB3PIPECTL_TX_DEEPH(dwc->tx_de_emphasis);
- if (dwc->dis_u3_susphy_quirk)
- reg &= ~DWC3_GUSB3PIPECTL_SUSPHY;
-
if (dwc->dis_del_phy_power_chg_quirk)
reg &= ~DWC3_GUSB3PIPECTL_DEPOCHANGE;
@@ -689,24 +699,15 @@
}
/*
- * Above 1.94a, it is recommended to set DWC3_GUSB2PHYCFG_SUSPHY to
- * '0' during coreConsultant configuration. So default value will
- * be '0' when the core is reset. Application needs to set it to
- * '1' after the core initialization is completed.
+ * Above DWC_usb3.0 1.94a, it is recommended to set
+ * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration.
+ * So default value will be '0' when the core is reset. Application
+ * needs to set it to '1' after the core initialization is completed.
+ *
+ * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared
+ * after power-on reset, and it can be set after core initialization.
*/
- if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A))
- reg |= DWC3_GUSB2PHYCFG_SUSPHY;
-
- /*
- * For DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared after
- * power-on reset, and it can be set after core initialization, which is
- * after device soft-reset during initialization.
- */
- if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD)
- reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
-
- if (dwc->dis_u2_susphy_quirk)
- reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
+ reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
if (dwc->dis_enblslpm_quirk)
reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM;
@@ -1227,21 +1228,6 @@
if (ret)
goto err_exit_phy;
- if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD &&
- !DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) {
- if (!dwc->dis_u3_susphy_quirk) {
- reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0));
- reg |= DWC3_GUSB3PIPECTL_SUSPHY;
- dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), reg);
- }
-
- if (!dwc->dis_u2_susphy_quirk) {
- reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
- reg |= DWC3_GUSB2PHYCFG_SUSPHY;
- dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
- }
- }
-
dwc3_core_setup_global_control(dwc);
dwc3_core_num_eps(dwc);
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 7e80dd3..180dd8d 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1580,6 +1580,7 @@
void dwc3_event_buffers_cleanup(struct dwc3 *dwc);
int dwc3_core_soft_reset(struct dwc3 *dwc);
+void dwc3_enable_susphy(struct dwc3 *dwc, bool enable);
#if IS_ENABLED(CONFIG_USB_DWC3_HOST) || IS_ENABLED(CONFIG_USB_DWC3_DUAL_ROLE)
int dwc3_host_init(struct dwc3 *dwc);
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 72bb722..d96ffbe 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -226,7 +226,8 @@
/* reinitialize physical ep1 */
dep = dwc->eps[1];
- dep->flags = DWC3_EP_ENABLED;
+ dep->flags &= DWC3_EP_RESOURCE_ALLOCATED;
+ dep->flags |= DWC3_EP_ENABLED;
/* stall is always issued on EP0 */
dep = dwc->eps[0];
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 4df2661..f94f68f 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2924,6 +2924,7 @@
dwc3_ep0_out_start(dwc);
dwc3_gadget_enable_irq(dwc);
+ dwc3_enable_susphy(dwc, true);
return 0;
@@ -4690,6 +4691,7 @@
if (!dwc->gadget)
return;
+ dwc3_enable_susphy(dwc, false);
usb_del_gadget(dwc->gadget);
dwc3_gadget_free_endpoints(dwc);
usb_put_gadget(dwc->gadget);
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index 0204787..a171b27 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -10,10 +10,13 @@
#include <linux/irq.h>
#include <linux/of.h>
#include <linux/platform_device.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
#include "../host/xhci-port.h"
#include "../host/xhci-ext-caps.h"
#include "../host/xhci-caps.h"
+#include "../host/xhci-plat.h"
#include "core.h"
#define XHCI_HCSPARAMS1 0x4
@@ -57,6 +60,24 @@
}
}
+static void dwc3_xhci_plat_start(struct usb_hcd *hcd)
+{
+ struct platform_device *pdev;
+ struct dwc3 *dwc;
+
+ if (!usb_hcd_is_primary_hcd(hcd))
+ return;
+
+ pdev = to_platform_device(hcd->self.controller);
+ dwc = dev_get_drvdata(pdev->dev.parent);
+
+ dwc3_enable_susphy(dwc, true);
+}
+
+static const struct xhci_plat_priv dwc3_xhci_plat_quirk = {
+ .plat_start = dwc3_xhci_plat_start,
+};
+
static void dwc3_host_fill_xhci_irq_res(struct dwc3 *dwc,
int irq, char *name)
{
@@ -167,6 +188,11 @@
}
}
+ ret = platform_device_add_data(xhci, &dwc3_xhci_plat_quirk,
+ sizeof(struct xhci_plat_priv));
+ if (ret)
+ goto err;
+
ret = platform_device_add(xhci);
if (ret) {
dev_err(dwc->dev, "failed to register xHCI device\n");
@@ -192,6 +218,7 @@
if (dwc->sys_wakeup)
device_init_wakeup(&dwc->xhci->dev, false);
+ dwc3_enable_susphy(dwc, false);
platform_device_unregister(dwc->xhci);
dwc->xhci = NULL;
}
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 0ace45b..0e151b5 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2112,7 +2112,7 @@
buf[5] = 0x01;
switch (ctrl->bRequestType & USB_RECIP_MASK) {
case USB_RECIP_DEVICE:
- if (w_index != 0x4 || (w_value >> 8))
+ if (w_index != 0x4 || (w_value & 0xff))
break;
buf[6] = w_index;
/* Number of ext compat interfaces */
@@ -2128,9 +2128,9 @@
}
break;
case USB_RECIP_INTERFACE:
- if (w_index != 0x5 || (w_value >> 8))
+ if (w_index != 0x5 || (w_value & 0xff))
break;
- interface = w_value & 0xFF;
+ interface = w_value >> 8;
if (interface >= MAX_CONFIG_INTERFACES ||
!os_desc_cfg->interface[interface])
break;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index bffbc1d..a057cbe 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -46,6 +46,8 @@
#define FUNCTIONFS_MAGIC 0xa647361 /* Chosen by a honest dice roll ;) */
+#define DMABUF_ENQUEUE_TIMEOUT_MS 5000
+
MODULE_IMPORT_NS(DMA_BUF);
/* Reference counter handling */
@@ -850,6 +852,7 @@
work);
int ret = io_data->status;
bool kiocb_has_eventfd = io_data->kiocb->ki_flags & IOCB_EVENTFD;
+ unsigned long flags;
if (io_data->read && ret > 0) {
kthread_use_mm(io_data->mm);
@@ -862,6 +865,11 @@
if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd)
eventfd_signal(io_data->ffs->ffs_eventfd);
+ spin_lock_irqsave(&io_data->ffs->eps_lock, flags);
+ usb_ep_free_request(io_data->ep, io_data->req);
+ io_data->req = NULL;
+ spin_unlock_irqrestore(&io_data->ffs->eps_lock, flags);
+
if (io_data->read)
kfree(io_data->to_free);
ffs_free_buffer(io_data);
@@ -875,7 +883,6 @@
struct ffs_data *ffs = io_data->ffs;
io_data->status = req->status ? req->status : req->actual;
- usb_ep_free_request(_ep, req);
INIT_WORK(&io_data->work, ffs_user_copy_worker);
queue_work(ffs->io_completion_wq, &io_data->work);
@@ -1578,10 +1585,13 @@
struct ffs_dmabuf_priv *priv;
struct ffs_dma_fence *fence;
struct usb_request *usb_req;
+ enum dma_resv_usage resv_dir;
struct dma_buf *dmabuf;
+ unsigned long timeout;
struct ffs_ep *ep;
bool cookie;
u32 seqno;
+ long retl;
int ret;
if (req->flags & ~USB_FFS_DMABUF_TRANSFER_MASK)
@@ -1615,17 +1625,14 @@
goto err_attachment_put;
/* Make sure we don't have writers */
- if (!dma_resv_test_signaled(dmabuf->resv, DMA_RESV_USAGE_WRITE)) {
- pr_vdebug("FFS WRITE fence is not signaled\n");
- ret = -EBUSY;
- goto err_resv_unlock;
- }
-
- /* If we're writing to the DMABUF, make sure we don't have readers */
- if (epfile->in &&
- !dma_resv_test_signaled(dmabuf->resv, DMA_RESV_USAGE_READ)) {
- pr_vdebug("FFS READ fence is not signaled\n");
- ret = -EBUSY;
+ timeout = nonblock ? 0 : msecs_to_jiffies(DMABUF_ENQUEUE_TIMEOUT_MS);
+ retl = dma_resv_wait_timeout(dmabuf->resv,
+ dma_resv_usage_rw(epfile->in),
+ true, timeout);
+ if (retl == 0)
+ retl = -EBUSY;
+ if (retl < 0) {
+ ret = (int)retl;
goto err_resv_unlock;
}
@@ -1665,8 +1672,9 @@
dma_fence_init(&fence->base, &ffs_dmabuf_fence_ops,
&priv->lock, priv->context, seqno);
- dma_resv_add_fence(dmabuf->resv, &fence->base,
- dma_resv_usage_rw(epfile->in));
+ resv_dir = epfile->in ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ;
+
+ dma_resv_add_fence(dmabuf->resv, &fence->base, resv_dir);
dma_resv_unlock(dmabuf->resv);
/* Now that the dma_fence is in place, queue the transfer. */
@@ -3803,7 +3811,7 @@
__ffs_event_add(ffs, FUNCTIONFS_SETUP);
spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags);
- return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0;
+ return ffs->ev.setup.wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0;
}
static bool ffs_func_req_match(struct usb_function *f,
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 28f4e65..0acc32e 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -878,7 +878,7 @@
if (alt > 1)
goto fail;
- if (ncm->port.in_ep->enabled) {
+ if (ncm->netdev) {
DBG(cdev, "reset ncm\n");
ncm->netdev = NULL;
gether_disconnect(&ncm->port);
@@ -1367,7 +1367,7 @@
DBG(cdev, "ncm deactivated\n");
- if (ncm->port.in_ep->enabled) {
+ if (ncm->netdev) {
ncm->netdev = NULL;
gether_disconnect(&ncm->port);
}
diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c
index 7e704b2..a4377df 100644
--- a/drivers/usb/gadget/function/uvc_configfs.c
+++ b/drivers/usb/gadget/function/uvc_configfs.c
@@ -92,10 +92,10 @@
while (pg - page < len) {
i = 0;
- while (i < sizeof(buf) && (pg - page < len) &&
+ while (i < bufsize && (pg - page < len) &&
*pg != '\0' && *pg != '\n')
buf[i++] = *pg++;
- if (i == sizeof(buf)) {
+ if (i == bufsize) {
ret = -EINVAL;
goto out_free_buf;
}
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index e82d032..3432ebf 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -868,7 +868,7 @@
{
struct fsl_ep *ep = container_of(_ep, struct fsl_ep, ep);
struct fsl_req *req = container_of(_req, struct fsl_req, req);
- struct fsl_udc *udc;
+ struct fsl_udc *udc = ep->udc;
unsigned long flags;
int ret;
@@ -878,7 +878,7 @@
dev_vdbg(&udc->gadget.dev, "%s, bad params\n", __func__);
return -EINVAL;
}
- if (unlikely(!_ep || !ep->ep.desc)) {
+ if (unlikely(!ep->ep.desc)) {
dev_vdbg(&udc->gadget.dev, "%s, bad ep\n", __func__);
return -EINVAL;
}
@@ -887,7 +887,6 @@
return -EMSGSIZE;
}
- udc = ep->udc;
if (!udc->driver || udc->gadget.speed == USB_SPEED_UNKNOWN)
return -ESHUTDOWN;
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 4f9982e..5cec764 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -888,6 +888,7 @@
/* Check for an all 1's result which is a typical consequence
* of dead, unclocked, or unplugged (CardBus...) devices
*/
+again:
if (ints == ~(u32)0) {
ohci->rh_state = OHCI_RH_HALTED;
ohci_dbg (ohci, "device removed!\n");
@@ -982,6 +983,13 @@
}
spin_unlock(&ohci->lock);
+ /* repeat until all enabled interrupts are handled */
+ if (ohci->rh_state != OHCI_RH_HALTED) {
+ ints = ohci_readl(ohci, ®s->intrstatus);
+ if (ints && (ints & ohci_readl(ohci, ®s->intrenable)))
+ goto again;
+ }
+
return IRQ_HANDLED;
}
diff --git a/drivers/usb/host/xhci-plat.h b/drivers/usb/host/xhci-plat.h
index 2d15386..6475130 100644
--- a/drivers/usb/host/xhci-plat.h
+++ b/drivers/usb/host/xhci-plat.h
@@ -8,7 +8,9 @@
#ifndef _XHCI_PLAT_H
#define _XHCI_PLAT_H
-#include "xhci.h" /* for hcd_to_xhci() */
+struct device;
+struct platform_device;
+struct usb_hcd;
struct xhci_plat_priv {
const char *firmware_name;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 52278af..575f0fd 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3133,7 +3133,7 @@
irqreturn_t xhci_irq(struct usb_hcd *hcd)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
- irqreturn_t ret = IRQ_NONE;
+ irqreturn_t ret = IRQ_HANDLED;
u32 status;
spin_lock(&xhci->lock);
@@ -3141,12 +3141,13 @@
status = readl(&xhci->op_regs->status);
if (status == ~(u32)0) {
xhci_hc_died(xhci);
- ret = IRQ_HANDLED;
goto out;
}
- if (!(status & STS_EINT))
+ if (!(status & STS_EINT)) {
+ ret = IRQ_NONE;
goto out;
+ }
if (status & STS_HCE) {
xhci_warn(xhci, "WARNING: Host Controller Error\n");
@@ -3156,7 +3157,6 @@
if (status & STS_FATAL) {
xhci_warn(xhci, "WARNING: Host System Error\n");
xhci_halt(xhci);
- ret = IRQ_HANDLED;
goto out;
}
@@ -3167,7 +3167,6 @@
*/
status |= STS_EINT;
writel(status, &xhci->op_regs->status);
- ret = IRQ_HANDLED;
/* This is the handler of the primary interrupter */
xhci_handle_events(xhci, xhci->interrupters[0]);
diff --git a/drivers/usb/host/xhci-rzv2m.c b/drivers/usb/host/xhci-rzv2m.c
index ec65b24..4f59867 100644
--- a/drivers/usb/host/xhci-rzv2m.c
+++ b/drivers/usb/host/xhci-rzv2m.c
@@ -6,6 +6,7 @@
*/
#include <linux/usb/rzv2m_usb3drd.h>
+#include "xhci.h"
#include "xhci-plat.h"
#include "xhci-rzv2m.h"
diff --git a/drivers/usb/host/xhci-trace.h b/drivers/usb/host/xhci-trace.h
index 1740000..5762564 100644
--- a/drivers/usb/host/xhci-trace.h
+++ b/drivers/usb/host/xhci-trace.h
@@ -172,8 +172,7 @@
__field(void *, vdev)
__field(unsigned long long, out_ctx)
__field(unsigned long long, in_ctx)
- __field(int, hcd_portnum)
- __field(int, hw_portnum)
+ __field(int, slot_id)
__field(u16, current_mel)
),
@@ -181,13 +180,12 @@
__entry->vdev = vdev;
__entry->in_ctx = (unsigned long long) vdev->in_ctx->dma;
__entry->out_ctx = (unsigned long long) vdev->out_ctx->dma;
- __entry->hcd_portnum = (int) vdev->rhub_port->hcd_portnum;
- __entry->hw_portnum = (int) vdev->rhub_port->hw_portnum;
+ __entry->slot_id = (int) vdev->slot_id;
__entry->current_mel = (u16) vdev->current_mel;
),
- TP_printk("vdev %p ctx %llx | %llx hcd_portnum %d hw_portnum %d current_mel %d",
- __entry->vdev, __entry->in_ctx, __entry->out_ctx,
- __entry->hcd_portnum, __entry->hw_portnum, __entry->current_mel
+ TP_printk("vdev %p slot %d ctx %llx | %llx current_mel %d",
+ __entry->vdev, __entry->slot_id, __entry->in_ctx,
+ __entry->out_ctx, __entry->current_mel
)
);
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index c6101ed..d804927 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -78,7 +78,7 @@
err = regulator_bulk_enable(hub->pdata->num_supplies, hub->supplies);
if (err) {
dev_err(hub->dev, "failed to enable supplies: %pe\n", ERR_PTR(err));
- return err;
+ goto disable_clk;
}
fsleep(hub->pdata->reset_us);
@@ -87,6 +87,10 @@
hub->is_powered_on = true;
return 0;
+
+disable_clk:
+ clk_disable_unprepare(hub->clk);
+ return err;
}
static int onboard_hub_power_off(struct onboard_hub *hub)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 55a65d9..8a5846d 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -255,6 +255,10 @@
#define QUECTEL_PRODUCT_EM061K_LMS 0x0124
#define QUECTEL_PRODUCT_EC25 0x0125
#define QUECTEL_PRODUCT_EM060K_128 0x0128
+#define QUECTEL_PRODUCT_EM060K_129 0x0129
+#define QUECTEL_PRODUCT_EM060K_12a 0x012a
+#define QUECTEL_PRODUCT_EM060K_12b 0x012b
+#define QUECTEL_PRODUCT_EM060K_12c 0x012c
#define QUECTEL_PRODUCT_EG91 0x0191
#define QUECTEL_PRODUCT_EG95 0x0195
#define QUECTEL_PRODUCT_BG96 0x0296
@@ -1218,6 +1222,18 @@
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0x00, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x30) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0x00, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x30) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0x00, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x30) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0x00, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x30) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0x00, 0x40) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0x00, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x40) },
@@ -1360,6 +1376,12 @@
.driver_info = NCTRL(2) | RSVD(3) },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff), /* Telit FE990 (ECM) */
.driver_info = NCTRL(0) | RSVD(1) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a0, 0xff), /* Telit FN20C04 (rmnet) */
+ .driver_info = RSVD(0) | NCTRL(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a4, 0xff), /* Telit FN20C04 (rmnet) */
+ .driver_info = RSVD(0) | NCTRL(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a9, 0xff), /* Telit FN20C04 (rmnet) */
+ .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
@@ -2052,6 +2074,10 @@
.driver_info = RSVD(3) },
{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9803, 0xff),
.driver_info = RSVD(4) },
+ { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b05), /* Longsung U8300 */
+ .driver_info = RSVD(4) | RSVD(5) },
+ { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b3c), /* Longsung U9300 */
+ .driver_info = RSVD(0) | RSVD(4) },
{ USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) },
{ USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) },
{ USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) },
@@ -2272,15 +2298,29 @@
{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */
{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */
{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) }, /* Fibocom FM160 (MBIM mode) */
+ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0115, 0xff), /* Fibocom FM135 (laptop MBIM) */
+ .driver_info = RSVD(5) },
{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */
{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */
{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */
.driver_info = RSVD(4) },
+ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a04, 0xff) }, /* Fibocom FM650-CN (ECM mode) */
+ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a05, 0xff) }, /* Fibocom FM650-CN (NCM mode) */
+ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a06, 0xff) }, /* Fibocom FM650-CN (RNDIS mode) */
+ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a07, 0xff) }, /* Fibocom FM650-CN (MBIM mode) */
{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */
{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */
{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */
{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */
+ { USB_DEVICE(0x33f8, 0x0104), /* Rolling RW101-GL (laptop RMNET) */
+ .driver_info = RSVD(4) | RSVD(5) },
+ { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a2, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */
+ { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a3, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */
+ { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a4, 0xff), /* Rolling RW101-GL (laptop MBIM) */
+ .driver_info = RSVD(4) },
+ { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0115, 0xff), /* Rolling RW135-GL (laptop MBIM) */
+ .driver_info = RSVD(5) },
{ USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) },
diff --git a/drivers/usb/typec/mux/it5205.c b/drivers/usb/typec/mux/it5205.c
index 5535932..4357cc6 100644
--- a/drivers/usb/typec/mux/it5205.c
+++ b/drivers/usb/typec/mux/it5205.c
@@ -22,7 +22,7 @@
#include <linux/usb/typec_mux.h>
#define IT5205_REG_CHIP_ID(x) (0x4 + (x))
-#define IT5205FN_CHIP_ID 0x35323035 /* "5205" */
+#define IT5205FN_CHIP_ID 0x35303235 /* "5025" -> "5205" */
/* MUX power down register */
#define IT5205_REG_MUXPDR 0x10
diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c
index e48412c..d3958c0 100644
--- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c
+++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c
@@ -104,14 +104,18 @@
ret = tcpm->port_start(tcpm, tcpm->tcpm_port);
if (ret)
- goto fwnode_remove;
+ goto port_unregister;
ret = tcpm->pdphy_start(tcpm, tcpm->tcpm_port);
if (ret)
- goto fwnode_remove;
+ goto port_stop;
return 0;
+port_stop:
+ tcpm->port_stop(tcpm);
+port_unregister:
+ tcpm_unregister_port(tcpm->tcpm_port);
fwnode_remove:
fwnode_remove_software_node(tcpm->tcpc.fwnode);
diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c
index 6560f4f..5b7f52b 100644
--- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c
+++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c
@@ -475,10 +475,8 @@
qcom_pmic_typec_pdphy_reset_off(pmic_typec_pdphy);
done:
- if (ret) {
- regulator_disable(pmic_typec_pdphy->vdd_pdphy);
+ if (ret)
dev_err(dev, "pdphy_enable fail %d\n", ret);
- }
return ret;
}
@@ -524,12 +522,17 @@
ret = pmic_typec_pdphy_reset(pmic_typec_pdphy);
if (ret)
- return ret;
+ goto err_disable_vdd_pdhy;
for (i = 0; i < pmic_typec_pdphy->nr_irqs; i++)
enable_irq(pmic_typec_pdphy->irq_data[i].irq);
return 0;
+
+err_disable_vdd_pdhy:
+ regulator_disable(pmic_typec_pdphy->vdd_pdphy);
+
+ return ret;
}
static void qcom_pmic_typec_pdphy_stop(struct pmic_typec *tcpm)
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index c26fb70..8a1af08 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -1564,8 +1564,12 @@
static void tcpm_queue_vdm_unlocked(struct tcpm_port *port, const u32 header,
const u32 *data, int cnt, enum tcpm_transmit_type tx_sop_type)
{
+ if (port->state != SRC_READY && port->state != SNK_READY &&
+ port->state != SRC_VDM_IDENTITY_REQUEST)
+ return;
+
mutex_lock(&port->lock);
- tcpm_queue_vdm(port, header, data, cnt, TCPC_TX_SOP);
+ tcpm_queue_vdm(port, header, data, cnt, tx_sop_type);
mutex_unlock(&port->lock);
}
@@ -1580,7 +1584,8 @@
port->partner_ident.cert_stat = p[VDO_INDEX_CSTAT];
port->partner_ident.product = product;
- typec_partner_set_identity(port->partner);
+ if (port->partner)
+ typec_partner_set_identity(port->partner);
tcpm_log(port, "Identity: %04x:%04x.%04x",
PD_IDH_VID(vdo),
@@ -1742,6 +1747,9 @@
struct typec_altmode *altmode;
int i;
+ if (!port->partner)
+ return;
+
for (i = 0; i < modep->altmodes; i++) {
altmode = typec_partner_register_altmode(port->partner,
&modep->altmode_desc[i]);
@@ -2996,7 +3004,7 @@
{
struct usb_power_delivery_desc desc = { port->negotiated_rev };
struct usb_power_delivery_capabilities_desc caps = { };
- struct usb_power_delivery_capabilities *cap;
+ struct usb_power_delivery_capabilities *cap = port->partner_source_caps;
if (!port->partner_pd)
port->partner_pd = usb_power_delivery_register(NULL, &desc);
@@ -3006,6 +3014,9 @@
memcpy(caps.pdo, port->source_caps, sizeof(u32) * port->nr_source_caps);
caps.role = TYPEC_SOURCE;
+ if (cap)
+ usb_power_delivery_unregister_capabilities(cap);
+
cap = usb_power_delivery_register_capabilities(port->partner_pd, &caps);
if (IS_ERR(cap))
return PTR_ERR(cap);
@@ -4231,7 +4242,10 @@
static void tcpm_typec_connect(struct tcpm_port *port)
{
+ struct typec_partner *partner;
+
if (!port->connected) {
+ port->connected = true;
/* Make sure we don't report stale identity information */
memset(&port->partner_ident, 0, sizeof(port->partner_ident));
port->partner_desc.usb_pd = port->pd_capable;
@@ -4241,9 +4255,13 @@
port->partner_desc.accessory = TYPEC_ACCESSORY_AUDIO;
else
port->partner_desc.accessory = TYPEC_ACCESSORY_NONE;
- port->partner = typec_register_partner(port->typec_port,
- &port->partner_desc);
- port->connected = true;
+ partner = typec_register_partner(port->typec_port, &port->partner_desc);
+ if (IS_ERR(partner)) {
+ dev_err(port->dev, "Failed to register partner (%ld)\n", PTR_ERR(partner));
+ return;
+ }
+
+ port->partner = partner;
typec_partner_set_usb_power_delivery(port->partner, port->partner_pd);
}
}
@@ -4323,9 +4341,11 @@
port->plug_prime = NULL;
port->cable = NULL;
if (port->connected) {
- typec_partner_set_usb_power_delivery(port->partner, NULL);
- typec_unregister_partner(port->partner);
- port->partner = NULL;
+ if (port->partner) {
+ typec_partner_set_usb_power_delivery(port->partner, NULL);
+ typec_unregister_partner(port->partner);
+ port->partner = NULL;
+ }
port->connected = false;
}
}
@@ -4549,6 +4569,9 @@
static void tcpm_set_initial_svdm_version(struct tcpm_port *port)
{
+ if (!port->partner)
+ return;
+
switch (port->negotiated_rev) {
case PD_REV30:
break;
@@ -5605,6 +5628,7 @@
break;
case PORT_RESET:
tcpm_reset_port(port);
+ port->pd_events = 0;
if (port->self_powered)
tcpm_set_cc(port, TYPEC_CC_OPEN);
else
@@ -6855,14 +6879,14 @@
if (data->sink_desc.pdo[0]) {
for (i = 0; i < PDO_MAX_OBJECTS && data->sink_desc.pdo[i]; i++)
port->snk_pdo[i] = data->sink_desc.pdo[i];
- port->nr_snk_pdo = i + 1;
+ port->nr_snk_pdo = i;
port->operating_snk_mw = data->operating_snk_mw;
}
if (data->source_desc.pdo[0]) {
for (i = 0; i < PDO_MAX_OBJECTS && data->source_desc.pdo[i]; i++)
port->src_pdo[i] = data->source_desc.pdo[i];
- port->nr_src_pdo = i + 1;
+ port->nr_src_pdo = i;
}
switch (port->state) {
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 31d8a46..bd6ae92 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1736,11 +1736,13 @@
ucsi->connector = connector;
ucsi->ntfy = ntfy;
+ mutex_lock(&ucsi->ppm_lock);
ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci));
+ mutex_unlock(&ucsi->ppm_lock);
if (ret)
return ret;
- if (UCSI_CCI_CONNECTOR(READ_ONCE(cci)))
- ucsi_connector_change(ucsi, cci);
+ if (UCSI_CCI_CONNECTOR(cci))
+ ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci));
return 0;
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index b246067..6cb96a1 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -967,7 +967,7 @@
val_u32 = __virtio32_to_cpu(true, config->size_max);
- return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, val_u32);
+ return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SIZE_MAX, val_u32);
}
/* fill the block size*/
@@ -1089,7 +1089,7 @@
u8 ro;
ro = ((features & BIT_ULL(VIRTIO_BLK_F_RO)) == 0) ? 0 : 1;
- if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, ro))
+ if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_READ_ONLY, ro))
return -EMSGSIZE;
return 0;
@@ -1100,7 +1100,7 @@
u8 flush;
flush = ((features & BIT_ULL(VIRTIO_BLK_F_FLUSH)) == 0) ? 0 : 1;
- if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_FLUSH, flush))
+ if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_FLUSH, flush))
return -EMSGSIZE;
return 0;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 045f666..8995730 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2515,7 +2515,7 @@
vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
- vq_err(vq, "Guest moved used index from %u to %u",
+ vq_err(vq, "Guest moved avail index from %u to %u",
last_avail_idx, vq->avail_idx);
return -EFAULT;
}
@@ -2799,9 +2799,19 @@
r = vhost_get_avail_idx(vq, &avail_idx);
if (unlikely(r))
return false;
- vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
- return vq->avail_idx == vq->last_avail_idx;
+ vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
+ if (vq->avail_idx != vq->last_avail_idx) {
+ /* Since we have updated avail_idx, the following
+ * call to vhost_get_vq_desc() will read available
+ * ring entries. Make sure that read happens after
+ * the avail_idx read.
+ */
+ smp_rmb();
+ return false;
+ }
+
+ return true;
}
EXPORT_SYMBOL_GPL(vhost_vq_avail_empty);
@@ -2838,9 +2848,19 @@
&vq->avail->idx, r);
return false;
}
- vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
- return vq->avail_idx != vq->last_avail_idx;
+ vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
+ if (vq->avail_idx != vq->last_avail_idx) {
+ /* Since we have updated avail_idx, the following
+ * call to vhost_get_vq_desc() will read available
+ * ring entries. Make sure that read happens after
+ * the avail_idx read.
+ */
+ smp_rmb();
+ return true;
+ }
+
+ return false;
}
EXPORT_SYMBOL_GPL(vhost_enable_notify);
diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index dae96c9..806ecd3 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -196,7 +196,7 @@
*/
static vm_fault_t fb_deferred_io_page_mkwrite(struct fb_info *info, struct vm_fault *vmf)
{
- unsigned long offset = vmf->address - vmf->vma->vm_start;
+ unsigned long offset = vmf->pgoff << PAGE_SHIFT;
struct page *page = vmf->page;
file_update_time(vmf->vma->vm_file);
diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c
index b67a28d..a1c467a 100644
--- a/drivers/virt/vmgenid.c
+++ b/drivers/virt/vmgenid.c
@@ -68,7 +68,6 @@
static void vmgenid_notify(struct acpi_device *device, u32 event)
{
struct vmgenid_state *state = acpi_driver_data(device);
- char *envp[] = { "NEW_VMGENID=1", NULL };
u8 old_id[VMGENID_SIZE];
memcpy(old_id, state->this_id, sizeof(old_id));
@@ -76,7 +75,6 @@
if (!memcmp(old_id, state->this_id, sizeof(old_id)))
return;
add_vmfork_randomness(state->this_id, sizeof(state->this_id));
- kobject_uevent_env(&device->dev.kobj, KOBJ_CHANGE, envp);
}
static const struct acpi_device_id vmgenid_ids[] = {
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index f173587..9510c55 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -362,14 +362,16 @@
.remove = virtio_dev_remove,
};
-int register_virtio_driver(struct virtio_driver *driver)
+int __register_virtio_driver(struct virtio_driver *driver, struct module *owner)
{
/* Catch this early. */
BUG_ON(driver->feature_table_size && !driver->feature_table);
driver->driver.bus = &virtio_bus;
+ driver->driver.owner = owner;
+
return driver_register(&driver->driver);
}
-EXPORT_SYMBOL_GPL(register_virtio_driver);
+EXPORT_SYMBOL_GPL(__register_virtio_driver);
void unregister_virtio_driver(struct virtio_driver *driver)
{
diff --git a/fs/9p/fid.h b/fs/9p/fid.h
index 29281b7..0d6138b 100644
--- a/fs/9p/fid.h
+++ b/fs/9p/fid.h
@@ -49,9 +49,6 @@
static inline void v9fs_fid_add_modes(struct p9_fid *fid, unsigned int s_flags,
unsigned int s_cache, unsigned int f_flags)
{
- if (fid->qid.type != P9_QTFILE)
- return;
-
if ((!s_cache) ||
((fid->qid.version == 0) && !(s_flags & V9FS_IGNORE_QV)) ||
(s_flags & V9FS_DIRECT_IO) || (f_flags & O_DIRECT)) {
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 9defa12..1775fcc 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -179,13 +179,14 @@
struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags);
-extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid);
+extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid,
+ bool new);
extern const struct inode_operations v9fs_dir_inode_operations_dotl;
extern const struct inode_operations v9fs_file_inode_operations_dotl;
extern const struct inode_operations v9fs_symlink_inode_operations_dotl;
extern const struct netfs_request_ops v9fs_req_ops;
extern struct inode *v9fs_fid_iget_dotl(struct super_block *sb,
- struct p9_fid *fid);
+ struct p9_fid *fid, bool new);
/* other default globals */
#define V9FS_PORT 564
@@ -224,12 +225,12 @@
*/
static inline struct inode *
v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
- struct super_block *sb)
+ struct super_block *sb, bool new)
{
if (v9fs_proto_dotl(v9ses))
- return v9fs_fid_iget_dotl(sb, fid);
+ return v9fs_fid_iget_dotl(sb, fid, new);
else
- return v9fs_fid_iget(sb, fid);
+ return v9fs_fid_iget(sb, fid, new);
}
#endif
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index abdbbae..348cc90 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -520,6 +520,7 @@
.splice_read = v9fs_file_splice_read,
.splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync,
+ .setlease = simple_nosetlease,
};
const struct file_operations v9fs_file_operations_dotl = {
@@ -534,4 +535,5 @@
.splice_read = v9fs_file_splice_read,
.splice_write = iter_file_splice_write,
.fsync = v9fs_file_fsync_dotl,
+ .setlease = simple_nosetlease,
};
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index b01b1bb..7a3308d 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -83,7 +83,7 @@
int res;
int mode = stat->mode;
- res = mode & S_IALLUGO;
+ res = mode & 0777; /* S_IRWXUGO */
if (v9fs_proto_dotu(v9ses)) {
if ((mode & P9_DMSETUID) == P9_DMSETUID)
res |= S_ISUID;
@@ -178,6 +178,9 @@
break;
}
+ if (uflags & O_TRUNC)
+ ret |= P9_OTRUNC;
+
if (extended) {
if (uflags & O_EXCL)
ret |= P9_OEXCL;
@@ -361,7 +364,8 @@
clear_inode(inode);
}
-struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid)
+struct inode *
+v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, bool new)
{
dev_t rdev;
int retval;
@@ -373,8 +377,18 @@
inode = iget_locked(sb, QID2INO(&fid->qid));
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
- if (!(inode->i_state & I_NEW))
- return inode;
+ if (!(inode->i_state & I_NEW)) {
+ if (!new) {
+ goto done;
+ } else {
+ p9_debug(P9_DEBUG_VFS, "WARNING: Inode collision %ld\n",
+ inode->i_ino);
+ iput(inode);
+ remove_inode_hash(inode);
+ inode = iget_locked(sb, QID2INO(&fid->qid));
+ WARN_ON(!(inode->i_state & I_NEW));
+ }
+ }
/*
* initialize the inode with the stat info
@@ -398,11 +412,11 @@
v9fs_set_netfs_context(inode);
v9fs_cache_inode_get_cookie(inode);
unlock_new_inode(inode);
+done:
return inode;
error:
iget_failed(inode);
return ERR_PTR(retval);
-
}
/**
@@ -434,8 +448,15 @@
*/
static void v9fs_dec_count(struct inode *inode)
{
- if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
- drop_nlink(inode);
+ if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) {
+ if (inode->i_nlink) {
+ drop_nlink(inode);
+ } else {
+ p9_debug(P9_DEBUG_VFS,
+ "WARNING: unexpected i_nlink zero %d inode %ld\n",
+ inode->i_nlink, inode->i_ino);
+ }
+ }
}
/**
@@ -486,6 +507,9 @@
} else
v9fs_dec_count(inode);
+ if (inode->i_nlink <= 0) /* no more refs unhash it */
+ remove_inode_hash(inode);
+
v9fs_invalidate_inode_attr(inode);
v9fs_invalidate_inode_attr(dir);
@@ -551,7 +575,7 @@
/*
* instantiate inode and assign the unopened fid to the dentry
*/
- inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
+ inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, true);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS,
@@ -680,7 +704,7 @@
else if (IS_ERR(fid))
inode = ERR_CAST(fid);
else
- inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
+ inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, false);
/*
* If we had a rename on the server and a parallel lookup
* for the new name, then make sure we instantiate with
@@ -1061,8 +1085,6 @@
struct v9fs_session_info *v9ses = sb->s_fs_info;
struct v9fs_inode *v9inode = V9FS_I(inode);
- set_nlink(inode, 1);
-
inode_set_atime(inode, stat->atime, 0);
inode_set_mtime(inode, stat->mtime, 0);
inode_set_ctime(inode, stat->mtime, 0);
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 55dde18..c61b97b 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -52,7 +52,10 @@
return current_fsgid();
}
-struct inode *v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid)
+
+
+struct inode *
+v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid, bool new)
{
int retval;
struct inode *inode;
@@ -62,8 +65,18 @@
inode = iget_locked(sb, QID2INO(&fid->qid));
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
- if (!(inode->i_state & I_NEW))
- return inode;
+ if (!(inode->i_state & I_NEW)) {
+ if (!new) {
+ goto done;
+ } else { /* deal with race condition in inode number reuse */
+ p9_debug(P9_DEBUG_ERROR, "WARNING: Inode collision %lx\n",
+ inode->i_ino);
+ iput(inode);
+ remove_inode_hash(inode);
+ inode = iget_locked(sb, QID2INO(&fid->qid));
+ WARN_ON(!(inode->i_state & I_NEW));
+ }
+ }
/*
* initialize the inode with the stat info
@@ -90,12 +103,11 @@
goto error;
unlock_new_inode(inode);
-
+done:
return inode;
error:
iget_failed(inode);
return ERR_PTR(retval);
-
}
struct dotl_openflag_map {
@@ -247,7 +259,7 @@
p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
goto out;
}
- inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
+ inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err);
@@ -340,7 +352,7 @@
}
/* instantiate inode and assign the unopened fid to the dentry */
- inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
+ inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
@@ -776,7 +788,7 @@
err);
goto error;
}
- inode = v9fs_fid_iget_dotl(dir->i_sb, fid);
+ inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n",
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 4236058..f52fdf4 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -139,7 +139,7 @@
else
sb->s_d_op = &v9fs_dentry_operations;
- inode = v9fs_get_inode_from_fid(v9ses, fid, sb);
+ inode = v9fs_get_inode_from_fid(v9ses, fid, sb, true);
if (IS_ERR(inode)) {
retval = PTR_ERR(inode);
goto release_sb;
@@ -244,6 +244,21 @@
return res;
}
+static int v9fs_drop_inode(struct inode *inode)
+{
+ struct v9fs_session_info *v9ses;
+
+ v9ses = v9fs_inode2v9ses(inode);
+ if (v9ses->cache & (CACHE_META|CACHE_LOOSE))
+ return generic_drop_inode(inode);
+ /*
+ * in case of non cached mode always drop the
+ * inode because we want the inode attribute
+ * to always match that on the server.
+ */
+ return 1;
+}
+
static int v9fs_write_inode(struct inode *inode,
struct writeback_control *wbc)
{
@@ -268,6 +283,7 @@
.alloc_inode = v9fs_alloc_inode,
.free_inode = v9fs_free_inode,
.statfs = simple_statfs,
+ .drop_inode = v9fs_drop_inode,
.evict_inode = v9fs_evict_inode,
.show_options = v9fs_show_options,
.umount_begin = v9fs_umount_begin,
@@ -278,6 +294,7 @@
.alloc_inode = v9fs_alloc_inode,
.free_inode = v9fs_free_inode,
.statfs = v9fs_statfs,
+ .drop_inode = v9fs_drop_inode,
.evict_inode = v9fs_evict_inode,
.show_options = v9fs_show_options,
.umount_begin = v9fs_umount_begin,
diff --git a/fs/bcachefs/acl.c b/fs/bcachefs/acl.c
index 3640f41..5c180fd 100644
--- a/fs/bcachefs/acl.c
+++ b/fs/bcachefs/acl.c
@@ -281,7 +281,6 @@
struct xattr_search_key search = X_SEARCH(acl_to_xattr_type(type), "", 0);
struct btree_trans *trans = bch2_trans_get(c);
struct btree_iter iter = { NULL };
- struct bkey_s_c_xattr xattr;
struct posix_acl *acl = NULL;
struct bkey_s_c k;
int ret;
@@ -290,29 +289,28 @@
ret = bch2_hash_lookup(trans, &iter, bch2_xattr_hash_desc,
&hash, inode_inum(inode), &search, 0);
- if (ret) {
- if (!bch2_err_matches(ret, ENOENT))
- acl = ERR_PTR(ret);
- goto out;
- }
+ if (ret)
+ goto err;
k = bch2_btree_iter_peek_slot(&iter);
ret = bkey_err(k);
- if (ret) {
- acl = ERR_PTR(ret);
- goto out;
- }
+ if (ret)
+ goto err;
- xattr = bkey_s_c_to_xattr(k);
+ struct bkey_s_c_xattr xattr = bkey_s_c_to_xattr(k);
acl = bch2_acl_from_disk(trans, xattr_val(xattr.v),
- le16_to_cpu(xattr.v->x_val_len));
-
- if (!IS_ERR(acl))
- set_cached_acl(&inode->v, type, acl);
-out:
- if (bch2_err_matches(PTR_ERR_OR_ZERO(acl), BCH_ERR_transaction_restart))
+ le16_to_cpu(xattr.v->x_val_len));
+ ret = PTR_ERR_OR_ZERO(acl);
+err:
+ if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
goto retry;
+ if (ret)
+ acl = !bch2_err_matches(ret, ENOENT) ? ERR_PTR(ret) : NULL;
+
+ if (!IS_ERR_OR_NULL(acl))
+ set_cached_acl(&inode->v, type, acl);
+
bch2_trans_iter_exit(trans, &iter);
bch2_trans_put(trans);
return acl;
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index 114328a..a200442 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -49,13 +49,15 @@
if (!bch2_dev_exists2(c, bp.k->p.inode))
return 0;
+ struct bch_dev *ca = bch_dev_bkey_exists(c, bp.k->p.inode);
struct bpos bucket = bp_pos_to_bucket(c, bp.k->p);
int ret = 0;
- bkey_fsck_err_on(!bpos_eq(bp.k->p, bucket_pos_to_bp(c, bucket, bp.v->bucket_offset)),
+ bkey_fsck_err_on((bp.v->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT) >= ca->mi.bucket_size ||
+ !bpos_eq(bp.k->p, bucket_pos_to_bp(c, bucket, bp.v->bucket_offset)),
c, err,
- backpointer_pos_wrong,
- "backpointer at wrong pos");
+ backpointer_bucket_offset_wrong,
+ "backpointer bucket_offset wrong");
fsck_err:
return ret;
}
@@ -468,7 +470,7 @@
goto err;
}
- bio = bio_alloc(ca->disk_sb.bdev, 1, REQ_OP_READ, GFP_KERNEL);
+ bio = bio_alloc(ca->disk_sb.bdev, buf_pages(data_buf, bytes), REQ_OP_READ, GFP_KERNEL);
bio->bi_iter.bi_sector = p.ptr.offset;
bch2_bio_map(bio, data_buf, bytes);
ret = submit_bio_wait(bio);
diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h
index da012ca..85949b9 100644
--- a/fs/bcachefs/backpointers.h
+++ b/fs/bcachefs/backpointers.h
@@ -53,14 +53,11 @@
u64 bucket_offset)
{
struct bch_dev *ca = bch_dev_bkey_exists(c, bucket.inode);
- struct bpos ret;
-
- ret = POS(bucket.inode,
- (bucket_to_sector(ca, bucket.offset) <<
- MAX_EXTENT_COMPRESS_RATIO_SHIFT) + bucket_offset);
+ struct bpos ret = POS(bucket.inode,
+ (bucket_to_sector(ca, bucket.offset) <<
+ MAX_EXTENT_COMPRESS_RATIO_SHIFT) + bucket_offset);
EBUG_ON(!bkey_eq(bucket, bp_pos_to_bucket(c, ret)));
-
return ret;
}
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index a31a5f7..91c3c1f 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -709,6 +709,8 @@
x(stripe_delete) \
x(reflink) \
x(fallocate) \
+ x(fsync) \
+ x(dio_write) \
x(discard) \
x(discard_fast) \
x(invalidate) \
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 6310299..f7fbfcc 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -578,7 +578,8 @@
__le64 nbuckets; /* device size */
__le16 first_bucket; /* index of first bucket used */
__le16 bucket_size; /* sectors */
- __le32 pad;
+ __u8 btree_bitmap_shift;
+ __u8 pad[3];
__le64 last_mount; /* time_t */
__le64 flags;
@@ -587,6 +588,7 @@
__le64 errors_at_reset[BCH_MEMBER_ERROR_NR];
__le64 errors_reset_time;
__le64 seq;
+ __le64 btree_allocated_bitmap;
};
#define BCH_MEMBER_V1_BYTES 56
@@ -876,7 +878,8 @@
x(rebalance_work, BCH_VERSION(1, 3)) \
x(member_seq, BCH_VERSION(1, 4)) \
x(subvolume_fs_parent, BCH_VERSION(1, 5)) \
- x(btree_subvolume_children, BCH_VERSION(1, 6))
+ x(btree_subvolume_children, BCH_VERSION(1, 6)) \
+ x(mi_btree_bitmap, BCH_VERSION(1, 7))
enum bcachefs_metadata_version {
bcachefs_metadata_version_min = 9,
@@ -1314,7 +1317,7 @@
x(write_buffer_keys, 11) \
x(datetime, 12)
-enum {
+enum bch_jset_entry_type {
#define x(f, nr) BCH_JSET_ENTRY_##f = nr,
BCH_JSET_ENTRY_TYPES()
#undef x
@@ -1360,7 +1363,7 @@
x(inodes, 1) \
x(key_version, 2)
-enum {
+enum bch_fs_usage_type {
#define x(f, nr) BCH_FS_USAGE_##f = nr,
BCH_FS_USAGE_TYPES()
#undef x
@@ -1501,7 +1504,8 @@
BIT_ULL(KEY_TYPE_stripe)) \
x(reflink, 7, BTREE_ID_EXTENTS|BTREE_ID_DATA, \
BIT_ULL(KEY_TYPE_reflink_v)| \
- BIT_ULL(KEY_TYPE_indirect_inline_data)) \
+ BIT_ULL(KEY_TYPE_indirect_inline_data)| \
+ BIT_ULL(KEY_TYPE_error)) \
x(subvolumes, 8, 0, \
BIT_ULL(KEY_TYPE_subvolume)) \
x(snapshots, 9, 0, \
@@ -1535,6 +1539,20 @@
BTREE_ID_NR
};
+static inline bool btree_id_is_alloc(enum btree_id id)
+{
+ switch (id) {
+ case BTREE_ID_alloc:
+ case BTREE_ID_backpointers:
+ case BTREE_ID_need_discard:
+ case BTREE_ID_freespace:
+ case BTREE_ID_bucket_gens:
+ return true;
+ default:
+ return false;
+ }
+}
+
#define BTREE_MAX_DEPTH 4U
/* Btree nodes */
diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h
index cf23ff4..3a45d12 100644
--- a/fs/bcachefs/bkey.h
+++ b/fs/bcachefs/bkey.h
@@ -314,6 +314,12 @@
return bkey_packed(k) ? format->key_u64s : BKEY_U64s;
}
+static inline bool bkeyp_u64s_valid(const struct bkey_format *f,
+ const struct bkey_packed *k)
+{
+ return ((unsigned) k->u64s - bkeyp_key_u64s(f, k) <= U8_MAX - BKEY_U64s);
+}
+
static inline unsigned bkeyp_key_bytes(const struct bkey_format *format,
const struct bkey_packed *k)
{
diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c
index 5e52684..db336a4 100644
--- a/fs/bcachefs/bkey_methods.c
+++ b/fs/bcachefs/bkey_methods.c
@@ -171,11 +171,15 @@
if (type >= BKEY_TYPE_NR)
return 0;
- bkey_fsck_err_on((flags & BKEY_INVALID_COMMIT) &&
+ bkey_fsck_err_on((type == BKEY_TYPE_btree ||
+ (flags & BKEY_INVALID_COMMIT)) &&
!(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)), c, err,
bkey_invalid_type_for_btree,
"invalid key type for btree %s (%s)",
- bch2_btree_node_type_str(type), bch2_bkey_types[k.k->type]);
+ bch2_btree_node_type_str(type),
+ k.k->type < KEY_TYPE_MAX
+ ? bch2_bkey_types[k.k->type]
+ : "(unknown)");
if (btree_node_type_is_extents(type) && !bkey_whiteout(k.k)) {
bkey_fsck_err_on(k.k->size == 0, c, err,
diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 8447432..02c70e8 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -709,9 +709,31 @@
struct bch_fs *c = trans->c;
struct btree_cache *bc = &c->btree_cache;
struct btree *b;
- u32 seq;
- BUG_ON(level + 1 >= BTREE_MAX_DEPTH);
+ if (unlikely(level >= BTREE_MAX_DEPTH)) {
+ int ret = bch2_fs_topology_error(c, "attempting to get btree node at level %u, >= max depth %u",
+ level, BTREE_MAX_DEPTH);
+ return ERR_PTR(ret);
+ }
+
+ if (unlikely(!bkey_is_btree_ptr(&k->k))) {
+ struct printbuf buf = PRINTBUF;
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k));
+
+ int ret = bch2_fs_topology_error(c, "attempting to get btree node with non-btree key %s", buf.buf);
+ printbuf_exit(&buf);
+ return ERR_PTR(ret);
+ }
+
+ if (unlikely(k->k.u64s > BKEY_BTREE_PTR_U64s_MAX)) {
+ struct printbuf buf = PRINTBUF;
+ bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k));
+
+ int ret = bch2_fs_topology_error(c, "attempting to get btree node with too big key %s", buf.buf);
+ printbuf_exit(&buf);
+ return ERR_PTR(ret);
+ }
+
/*
* Parent node must be locked, else we could read in a btree node that's
* been freed:
@@ -752,34 +774,26 @@
}
set_btree_node_read_in_flight(b);
-
six_unlock_write(&b->c.lock);
- seq = six_lock_seq(&b->c.lock);
- six_unlock_intent(&b->c.lock);
-
- /* Unlock before doing IO: */
- if (path && sync)
- bch2_trans_unlock_noassert(trans);
-
- bch2_btree_node_read(trans, b, sync);
-
- if (!sync)
- return NULL;
if (path) {
- int ret = bch2_trans_relock(trans) ?:
- bch2_btree_path_relock_intent(trans, path);
- if (ret) {
- BUG_ON(!trans->restarted);
- return ERR_PTR(ret);
- }
- }
+ u32 seq = six_lock_seq(&b->c.lock);
- if (!six_relock_type(&b->c.lock, lock_type, seq)) {
- BUG_ON(!path);
+ /* Unlock before doing IO: */
+ six_unlock_intent(&b->c.lock);
+ bch2_trans_unlock_noassert(trans);
- trace_and_count(c, trans_restart_relock_after_fill, trans, _THIS_IP_, path);
- return ERR_PTR(btree_trans_restart(trans, BCH_ERR_transaction_restart_relock_after_fill));
+ bch2_btree_node_read(trans, b, sync);
+
+ if (!sync)
+ return NULL;
+
+ if (!six_relock_type(&b->c.lock, lock_type, seq))
+ b = NULL;
+ } else {
+ bch2_btree_node_read(trans, b, sync);
+ if (lock_type == SIX_LOCK_read)
+ six_lock_downgrade(&b->c.lock);
}
return b;
@@ -1112,18 +1126,19 @@
{
struct bch_fs *c = trans->c;
struct btree_cache *bc = &c->btree_cache;
- struct btree *b;
BUG_ON(path && !btree_node_locked(path, level + 1));
BUG_ON(level >= BTREE_MAX_DEPTH);
- b = btree_cache_find(bc, k);
+ struct btree *b = btree_cache_find(bc, k);
if (b)
return 0;
b = bch2_btree_node_fill(trans, path, k, btree_id,
level, SIX_LOCK_read, false);
- return PTR_ERR_OR_ZERO(b);
+ if (!IS_ERR_OR_NULL(b))
+ six_unlock_read(&b->c.lock);
+ return bch2_trans_relock(trans) ?: PTR_ERR_OR_ZERO(b);
}
void bch2_btree_node_evict(struct btree_trans *trans, const struct bkey_i *k)
@@ -1148,6 +1163,8 @@
btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent);
btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_write);
+ if (unlikely(b->hash_val != btree_ptr_hash_val(k)))
+ goto out;
if (btree_node_dirty(b)) {
__bch2_btree_node_write(c, b, BTREE_WRITE_cache_reclaim);
@@ -1162,7 +1179,7 @@
btree_node_data_free(c, b);
bch2_btree_node_hash_remove(bc, b);
mutex_unlock(&bc->lock);
-
+out:
six_unlock_write(&b->c.lock);
six_unlock_intent(&b->c.lock);
}
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 6280da1..791470b 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -368,11 +368,16 @@
buf.buf)) {
bch2_btree_node_evict(trans, cur_k.k);
cur = NULL;
- ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes) ?:
- bch2_journal_key_delete(c, b->c.btree_id,
- b->c.level, cur_k.k->k.p);
+ ret = bch2_journal_key_delete(c, b->c.btree_id,
+ b->c.level, cur_k.k->k.p);
if (ret)
break;
+
+ if (!btree_id_is_alloc(b->c.btree_id)) {
+ ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes);
+ if (ret)
+ break;
+ }
continue;
}
@@ -544,12 +549,12 @@
bch2_btree_root_alloc_fake(c, i, 0);
} else {
bch2_btree_root_alloc_fake(c, i, 1);
+ bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
if (ret)
break;
}
- bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
reconstructed_root = true;
}
@@ -823,6 +828,7 @@
struct bch_fs *c = trans->c;
struct bkey deleted = KEY(0, 0, 0);
struct bkey_s_c old = (struct bkey_s_c) { &deleted, NULL };
+ struct printbuf buf = PRINTBUF;
int ret = 0;
deleted.p = k->k->p;
@@ -843,11 +849,23 @@
if (ret)
goto err;
+ if (mustfix_fsck_err_on(level && !bch2_dev_btree_bitmap_marked(c, *k),
+ c, btree_bitmap_not_marked,
+ "btree ptr not marked in member info btree allocated bitmap\n %s",
+ (bch2_bkey_val_to_text(&buf, c, *k),
+ buf.buf))) {
+ mutex_lock(&c->sb_lock);
+ bch2_dev_btree_bitmap_mark(c, *k);
+ bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
+ }
+
ret = commit_do(trans, NULL, NULL, 0,
bch2_key_trigger(trans, btree_id, level, old,
unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC));
fsck_err:
err:
+ printbuf_exit(&buf);
bch_err_fn(c, ret);
return ret;
}
@@ -1569,7 +1587,7 @@
struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k);
ret = PTR_ERR_OR_ZERO(new);
if (ret)
- return ret;
+ goto out;
if (!r->refcount)
new->k.type = KEY_TYPE_deleted;
@@ -1577,6 +1595,7 @@
*bkey_refcount(bkey_i_to_s(new)) = cpu_to_le64(r->refcount);
ret = bch2_trans_update(trans, iter, new, 0);
}
+out:
fsck_err:
printbuf_exit(&buf);
return ret;
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index d7de82a..debb0ed 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -831,7 +831,7 @@
(rw == WRITE ? bch2_bkey_val_invalid(c, k, READ, err) : 0);
}
-static bool __bkey_valid(struct bch_fs *c, struct btree *b,
+static bool bkey_packed_valid(struct bch_fs *c, struct btree *b,
struct bset *i, struct bkey_packed *k)
{
if (bkey_p_next(k) > vstruct_last(i))
@@ -840,7 +840,7 @@
if (k->format > KEY_FORMAT_CURRENT)
return false;
- if (k->u64s < bkeyp_key_u64s(&b->format, k))
+ if (!bkeyp_u64s_valid(&b->format, k))
return false;
struct printbuf buf = PRINTBUF;
@@ -884,11 +884,13 @@
"invalid bkey format %u", k->format))
goto drop_this_key;
- if (btree_err_on(k->u64s < bkeyp_key_u64s(&b->format, k),
+ if (btree_err_on(!bkeyp_u64s_valid(&b->format, k),
-BCH_ERR_btree_node_read_err_fixable,
c, NULL, b, i,
btree_node_bkey_bad_u64s,
- "k->u64s too small (%u < %u)", k->u64s, bkeyp_key_u64s(&b->format, k)))
+ "bad k->u64s %u (min %u max %zu)", k->u64s,
+ bkeyp_key_u64s(&b->format, k),
+ U8_MAX - BKEY_U64s + bkeyp_key_u64s(&b->format, k)))
goto drop_this_key;
if (!write)
@@ -947,13 +949,12 @@
* do
*/
- if (!__bkey_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) {
+ if (!bkey_packed_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) {
for (next_good_key = 1;
next_good_key < (u64 *) vstruct_last(i) - (u64 *) k;
next_good_key++)
- if (__bkey_valid(c, b, i, (void *) ((u64 *) k + next_good_key)))
+ if (bkey_packed_valid(c, b, i, (void *) ((u64 *) k + next_good_key)))
goto got_good_key;
-
}
/*
@@ -1339,7 +1340,9 @@
rb->start_time);
bio_put(&rb->bio);
- if (saw_error && !btree_node_read_error(b)) {
+ if (saw_error &&
+ !btree_node_read_error(b) &&
+ c->curr_recovery_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes) {
printbuf_reset(&buf);
bch2_bpos_to_text(&buf, b->key.k.p);
bch_err_ratelimited(c, "%s: rewriting btree node at btree=%s level=%u %s due to error",
diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index 2477253..1c70836 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -498,8 +498,13 @@
{
struct btree_trans *trans = iter->trans;
- if (!trans->restarted)
- btree_iter_path(trans, iter)->preserve = false;
+ if (!iter->path || trans->restarted)
+ return;
+
+ struct btree_path *path = btree_iter_path(trans, iter);
+ path->preserve = false;
+ if (path->ref == 1)
+ path->should_be_locked = false;
}
void *__bch2_trans_kmalloc(struct btree_trans *, size_t);
@@ -642,7 +647,7 @@
static inline int btree_trans_too_many_iters(struct btree_trans *trans)
{
- if (bitmap_weight(trans->paths_allocated, trans->nr_paths) > BTREE_ITER_INITIAL - 8)
+ if (bitmap_weight(trans->paths_allocated, trans->nr_paths) > BTREE_ITER_NORMAL_LIMIT - 8)
return __bch2_btree_trans_too_many_iters(trans);
return 0;
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index 5cbcbfe..1e8cf49a 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -130,12 +130,30 @@
return bch2_journal_keys_peek_upto(c, btree_id, level, pos, pos, &idx);
}
+static void journal_iter_verify(struct journal_iter *iter)
+{
+ struct journal_keys *keys = iter->keys;
+ size_t gap_size = keys->size - keys->nr;
+
+ BUG_ON(iter->idx >= keys->gap &&
+ iter->idx < keys->gap + gap_size);
+
+ if (iter->idx < keys->size) {
+ struct journal_key *k = keys->data + iter->idx;
+
+ int cmp = cmp_int(k->btree_id, iter->btree_id) ?:
+ cmp_int(k->level, iter->level);
+ BUG_ON(cmp < 0);
+ }
+}
+
static void journal_iters_fix(struct bch_fs *c)
{
struct journal_keys *keys = &c->journal_keys;
/* The key we just inserted is immediately before the gap: */
size_t gap_end = keys->gap + (keys->size - keys->nr);
- struct btree_and_journal_iter *iter;
+ struct journal_key *new_key = &keys->data[keys->gap - 1];
+ struct journal_iter *iter;
/*
* If an iterator points one after the key we just inserted, decrement
@@ -143,9 +161,14 @@
* decrement was unnecessary, bch2_btree_and_journal_iter_peek() will
* handle that:
*/
- list_for_each_entry(iter, &c->journal_iters, journal.list)
- if (iter->journal.idx == gap_end)
- iter->journal.idx = keys->gap - 1;
+ list_for_each_entry(iter, &c->journal_iters, list) {
+ journal_iter_verify(iter);
+ if (iter->idx == gap_end &&
+ new_key->btree_id == iter->btree_id &&
+ new_key->level == iter->level)
+ iter->idx = keys->gap - 1;
+ journal_iter_verify(iter);
+ }
}
static void journal_iters_move_gap(struct bch_fs *c, size_t old_gap, size_t new_gap)
@@ -192,7 +215,12 @@
if (idx > keys->gap)
idx -= keys->size - keys->nr;
+ size_t old_gap = keys->gap;
+
if (keys->nr == keys->size) {
+ journal_iters_move_gap(c, old_gap, keys->size);
+ old_gap = keys->size;
+
struct journal_keys new_keys = {
.nr = keys->nr,
.size = max_t(size_t, keys->size, 8) * 2,
@@ -216,7 +244,7 @@
keys->gap = keys->nr;
}
- journal_iters_move_gap(c, keys->gap, idx);
+ journal_iters_move_gap(c, old_gap, idx);
move_gap(keys, idx);
@@ -301,16 +329,21 @@
static struct bkey_s_c bch2_journal_iter_peek(struct journal_iter *iter)
{
- struct journal_key *k = iter->keys->data + iter->idx;
+ journal_iter_verify(iter);
- while (k < iter->keys->data + iter->keys->size &&
- k->btree_id == iter->btree_id &&
- k->level == iter->level) {
+ while (iter->idx < iter->keys->size) {
+ struct journal_key *k = iter->keys->data + iter->idx;
+
+ int cmp = cmp_int(k->btree_id, iter->btree_id) ?:
+ cmp_int(k->level, iter->level);
+ if (cmp > 0)
+ break;
+ BUG_ON(cmp);
+
if (!k->overwritten)
return bkey_i_to_s_c(k->k);
bch2_journal_iter_advance(iter);
- k = iter->keys->data + iter->idx;
}
return bkey_s_c_null;
@@ -330,6 +363,8 @@
iter->level = level;
iter->keys = &c->journal_keys;
iter->idx = bch2_journal_key_search(&c->journal_keys, id, level, pos);
+
+ journal_iter_verify(iter);
}
static struct bkey_s_c bch2_journal_iter_peek_btree(struct btree_and_journal_iter *iter)
@@ -434,10 +469,15 @@
iter->trans = trans;
iter->b = b;
iter->node_iter = node_iter;
- bch2_journal_iter_init(trans->c, &iter->journal, b->c.btree_id, b->c.level, pos);
- INIT_LIST_HEAD(&iter->journal.list);
iter->pos = b->data->min_key;
iter->at_end = false;
+ INIT_LIST_HEAD(&iter->journal.list);
+
+ if (trans->journal_replay_not_finished) {
+ bch2_journal_iter_init(trans->c, &iter->journal, b->c.btree_id, b->c.level, pos);
+ if (!test_bit(BCH_FS_may_go_rw, &trans->c->flags))
+ list_add(&iter->journal.list, &trans->c->journal_iters);
+ }
}
/*
@@ -452,9 +492,6 @@
bch2_btree_node_iter_init_from_start(&node_iter, b);
__bch2_btree_and_journal_iter_init_node_iter(trans, iter, b, node_iter, b->data->min_key);
- if (trans->journal_replay_not_finished &&
- !test_bit(BCH_FS_may_go_rw, &trans->c->flags))
- list_add(&iter->journal.list, &trans->c->journal_iters);
}
/* sort and dedup all keys in the journal: */
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 581edcb..e8c1c53 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -169,6 +169,7 @@
} else {
mutex_lock(&bc->lock);
list_move_tail(&ck->list, &bc->freed_pcpu);
+ bc->nr_freed_pcpu++;
mutex_unlock(&bc->lock);
}
}
@@ -245,6 +246,7 @@
if (!list_empty(&bc->freed_pcpu)) {
ck = list_last_entry(&bc->freed_pcpu, struct bkey_cached, list);
list_del_init(&ck->list);
+ bc->nr_freed_pcpu--;
}
mutex_unlock(&bc->lock);
}
@@ -659,7 +661,7 @@
commit_flags |= BCH_WATERMARK_reclaim;
if (ck->journal.seq != journal_last_seq(j) ||
- j->watermark == BCH_WATERMARK_stripe)
+ !test_bit(JOURNAL_SPACE_LOW, &c->journal.flags))
commit_flags |= BCH_TRANS_COMMIT_no_journal_res;
ret = bch2_btree_iter_traverse(&b_iter) ?:
@@ -840,8 +842,6 @@
* Newest freed entries are at the end of the list - once we hit one
* that's too new to be freed, we can bail out:
*/
- scanned += bc->nr_freed_nonpcpu;
-
list_for_each_entry_safe(ck, t, &bc->freed_nonpcpu, list) {
if (!poll_state_synchronize_srcu(&c->btree_trans_barrier,
ck->btree_trans_barrier_seq))
@@ -855,11 +855,6 @@
bc->nr_freed_nonpcpu--;
}
- if (scanned >= nr)
- goto out;
-
- scanned += bc->nr_freed_pcpu;
-
list_for_each_entry_safe(ck, t, &bc->freed_pcpu, list) {
if (!poll_state_synchronize_srcu(&c->btree_trans_barrier,
ck->btree_trans_barrier_seq))
@@ -873,9 +868,6 @@
bc->nr_freed_pcpu--;
}
- if (scanned >= nr)
- goto out;
-
rcu_read_lock();
tbl = rht_dereference_rcu(bc->table.tbl, &bc->table);
if (bc->shrink_iter >= tbl->size)
@@ -891,12 +883,12 @@
next = rht_dereference_bucket_rcu(pos->next, tbl, bc->shrink_iter);
ck = container_of(pos, struct bkey_cached, hash);
- if (test_bit(BKEY_CACHED_DIRTY, &ck->flags))
+ if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) {
goto next;
-
- if (test_bit(BKEY_CACHED_ACCESSED, &ck->flags))
+ } else if (test_bit(BKEY_CACHED_ACCESSED, &ck->flags)) {
clear_bit(BKEY_CACHED_ACCESSED, &ck->flags);
- else if (bkey_cached_lock_for_evict(ck)) {
+ goto next;
+ } else if (bkey_cached_lock_for_evict(ck)) {
bkey_cached_evict(bc, ck);
bkey_cached_free(bc, ck);
}
@@ -914,7 +906,6 @@
} while (scanned < nr && bc->shrink_iter != start);
rcu_read_unlock();
-out:
memalloc_nofs_restore(flags);
srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);
mutex_unlock(&bc->lock);
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index b9b151e..f2caf49 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -440,33 +440,7 @@
struct btree_path *path,
struct btree_bkey_cached_common *b)
{
- struct btree_path *linked;
- unsigned i, iter;
- int ret;
-
- /*
- * XXX BIG FAT NOTICE
- *
- * Drop all read locks before taking a write lock:
- *
- * This is a hack, because bch2_btree_node_lock_write_nofail() is a
- * hack - but by dropping read locks first, this should never fail, and
- * we only use this in code paths where whatever read locks we've
- * already taken are no longer needed:
- */
-
- trans_for_each_path(trans, linked, iter) {
- if (!linked->nodes_locked)
- continue;
-
- for (i = 0; i < BTREE_MAX_DEPTH; i++)
- if (btree_node_read_locked(linked, i)) {
- btree_node_unlock(trans, linked, i);
- btree_path_set_dirty(linked, BTREE_ITER_NEED_RELOCK);
- }
- }
-
- ret = __btree_node_lock_write(trans, path, b, true);
+ int ret = __btree_node_lock_write(trans, path, b, true);
BUG_ON(ret);
}
diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
index 3f33be7..45cb814 100644
--- a/fs/bcachefs/btree_node_scan.c
+++ b/fs/bcachefs/btree_node_scan.c
@@ -57,13 +57,14 @@
bp->v.seq = cpu_to_le64(f->cookie);
bp->v.sectors_written = 0;
bp->v.flags = 0;
+ bp->v.sectors_written = cpu_to_le16(f->sectors_written);
bp->v.min_key = f->min_key;
SET_BTREE_PTR_RANGE_UPDATED(&bp->v, f->range_updated);
memcpy(bp->v.start, f->ptrs, sizeof(struct bch_extent_ptr) * f->nr_ptrs);
}
static bool found_btree_node_is_readable(struct btree_trans *trans,
- const struct found_btree_node *f)
+ struct found_btree_node *f)
{
struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } k;
@@ -71,8 +72,10 @@
struct btree *b = bch2_btree_node_get_noiter(trans, &k.k, f->btree_id, f->level, false);
bool ret = !IS_ERR_OR_NULL(b);
- if (ret)
+ if (ret) {
+ f->sectors_written = b->written;
six_unlock_read(&b->c.lock);
+ }
/*
* We might update this node's range; if that happens, we need the node
@@ -133,6 +136,19 @@
if (le64_to_cpu(bn->magic) != bset_magic(c))
return;
+ if (bch2_csum_type_is_encryption(BSET_CSUM_TYPE(&bn->keys))) {
+ struct nonce nonce = btree_nonce(&bn->keys, 0);
+ unsigned bytes = (void *) &bn->keys - (void *) &bn->flags;
+
+ bch2_encrypt(c, BSET_CSUM_TYPE(&bn->keys), nonce, &bn->flags, bytes);
+ }
+
+ if (btree_id_is_alloc(BTREE_NODE_ID(bn)))
+ return;
+
+ if (BTREE_NODE_LEVEL(bn) >= BTREE_MAX_DEPTH)
+ return;
+
rcu_read_lock();
struct found_btree_node n = {
.btree_id = BTREE_NODE_ID(bn),
@@ -192,8 +208,13 @@
last_print = jiffies;
}
- try_read_btree_node(w->f, ca, bio, buf,
- bucket * ca->mi.bucket_size + bucket_offset);
+ u64 sector = bucket * ca->mi.bucket_size + bucket_offset;
+
+ if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_mi_btree_bitmap &&
+ !bch2_dev_btree_bitmap_marked_sectors(ca, sector, btree_sectors(c)))
+ continue;
+
+ try_read_btree_node(w->f, ca, bio, buf, sector);
}
err:
bio_put(bio);
@@ -213,6 +234,9 @@
closure_init_stack(&cl);
for_each_online_member(c, ca) {
+ if (!(ca->mi.data_allowed & BIT(BCH_DATA_btree)))
+ continue;
+
struct find_btree_nodes_worker *w = kmalloc(sizeof(*w), GFP_KERNEL);
struct task_struct *t;
@@ -281,6 +305,8 @@
start->max_key = bpos_predecessor(n->min_key);
start->range_updated = true;
+ } else if (n->level) {
+ n->overwritten = true;
} else {
struct printbuf buf = PRINTBUF;
@@ -290,7 +316,7 @@
found_btree_node_to_text(&buf, c, n);
bch_err(c, "%s", buf.buf);
printbuf_exit(&buf);
- return -1;
+ return -BCH_ERR_fsck_repair_unimplemented;
}
}
@@ -436,6 +462,9 @@
int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree,
unsigned level, struct bpos node_min, struct bpos node_max)
{
+ if (btree_id_is_alloc(btree))
+ return 0;
+
struct find_btree_nodes *f = &c->found_btree_nodes;
int ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes);
diff --git a/fs/bcachefs/btree_node_scan_types.h b/fs/bcachefs/btree_node_scan_types.h
index abb7b27..5cfaeb5 100644
--- a/fs/bcachefs/btree_node_scan_types.h
+++ b/fs/bcachefs/btree_node_scan_types.h
@@ -9,6 +9,7 @@
bool overwritten:1;
u8 btree_id;
u8 level;
+ unsigned sectors_written;
u32 seq;
u64 cookie;
diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index aa9da49..bbec91e 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -397,12 +397,13 @@
struct bkey_cached *ck = (void *) path->l[0].b;
unsigned new_u64s;
struct bkey_i *new_k;
+ unsigned watermark = flags & BCH_WATERMARK_MASK;
EBUG_ON(path->level);
- if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags) &&
- bch2_btree_key_cache_must_wait(c) &&
- !(flags & BCH_TRANS_COMMIT_journal_reclaim))
+ if (watermark < BCH_WATERMARK_reclaim &&
+ !test_bit(BKEY_CACHED_DIRTY, &ck->flags) &&
+ bch2_btree_key_cache_must_wait(c))
return -BCH_ERR_btree_insert_need_journal_reclaim;
/*
@@ -499,9 +500,8 @@
}
static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id,
- struct btree_insert_entry *btree_id_start)
+ unsigned btree_id_start)
{
- struct btree_insert_entry *i;
bool trans_trigger_run;
int ret, overwrite;
@@ -514,13 +514,13 @@
do {
trans_trigger_run = false;
- for (i = btree_id_start;
- i < trans->updates + trans->nr_updates && i->btree_id <= btree_id;
+ for (unsigned i = btree_id_start;
+ i < trans->nr_updates && trans->updates[i].btree_id <= btree_id;
i++) {
- if (i->btree_id != btree_id)
+ if (trans->updates[i].btree_id != btree_id)
continue;
- ret = run_one_trans_trigger(trans, i, overwrite);
+ ret = run_one_trans_trigger(trans, trans->updates + i, overwrite);
if (ret < 0)
return ret;
if (ret)
@@ -534,8 +534,7 @@
static int bch2_trans_commit_run_triggers(struct btree_trans *trans)
{
- struct btree_insert_entry *btree_id_start = trans->updates;
- unsigned btree_id = 0;
+ unsigned btree_id = 0, btree_id_start = 0;
int ret = 0;
/*
@@ -549,8 +548,8 @@
if (btree_id == BTREE_ID_alloc)
continue;
- while (btree_id_start < trans->updates + trans->nr_updates &&
- btree_id_start->btree_id < btree_id)
+ while (btree_id_start < trans->nr_updates &&
+ trans->updates[btree_id_start].btree_id < btree_id)
btree_id_start++;
ret = run_btree_triggers(trans, btree_id, btree_id_start);
@@ -558,11 +557,13 @@
return ret;
}
- trans_for_each_update(trans, i) {
+ for (unsigned idx = 0; idx < trans->nr_updates; idx++) {
+ struct btree_insert_entry *i = trans->updates + idx;
+
if (i->btree_id > BTREE_ID_alloc)
break;
if (i->btree_id == BTREE_ID_alloc) {
- ret = run_btree_triggers(trans, BTREE_ID_alloc, i);
+ ret = run_btree_triggers(trans, BTREE_ID_alloc, idx);
if (ret)
return ret;
break;
@@ -826,7 +827,8 @@
struct bch_fs *c = trans->c;
int ret = 0, u64s_delta = 0;
- trans_for_each_update(trans, i) {
+ for (unsigned idx = 0; idx < trans->nr_updates; idx++) {
+ struct btree_insert_entry *i = trans->updates + idx;
if (i->cached)
continue;
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index 9404d96..c69b233 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -321,9 +321,9 @@
struct btree_bkey_cached_common c;
unsigned long flags;
+ unsigned long btree_trans_barrier_seq;
u16 u64s;
bool valid;
- u32 btree_trans_barrier_seq;
struct bkey_cached_key key;
struct rhash_head hash;
@@ -364,7 +364,21 @@
unsigned long ip_allocated;
};
+/* Number of btree paths we preallocate, usually enough */
#define BTREE_ITER_INITIAL 64
+/*
+ * Lmiit for btree_trans_too_many_iters(); this is enough that almost all code
+ * paths should run inside this limit, and if they don't it usually indicates a
+ * bug (leaking/duplicated btree paths).
+ *
+ * exception: some fsck paths
+ *
+ * bugs with excessive path usage seem to have possibly been eliminated now, so
+ * we might consider eliminating this (and btree_trans_too_many_iter()) at some
+ * point.
+ */
+#define BTREE_ITER_NORMAL_LIMIT 256
+/* never exceed limit */
#define BTREE_ITER_MAX (1U << 10)
struct btree_trans_commit_hook;
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 32397b9..b4efd8c 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -21,14 +21,15 @@
#include "keylist.h"
#include "recovery_passes.h"
#include "replicas.h"
+#include "sb-members.h"
#include "super-io.h"
#include "trace.h"
#include <linux/random.h>
-const char * const bch2_btree_update_modes[] = {
+static const char * const bch2_btree_update_modes[] = {
#define x(t) #t,
- BCH_WATERMARKS()
+ BTREE_UPDATE_MODES()
#undef x
NULL
};
@@ -605,6 +606,26 @@
bch2_keylist_push(keys);
}
+static bool btree_update_new_nodes_marked_sb(struct btree_update *as)
+{
+ for_each_keylist_key(&as->new_keys, k)
+ if (!bch2_dev_btree_bitmap_marked(as->c, bkey_i_to_s_c(k)))
+ return false;
+ return true;
+}
+
+static void btree_update_new_nodes_mark_sb(struct btree_update *as)
+{
+ struct bch_fs *c = as->c;
+
+ mutex_lock(&c->sb_lock);
+ for_each_keylist_key(&as->new_keys, k)
+ bch2_dev_btree_bitmap_mark(c, bkey_i_to_s_c(k));
+
+ bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
+}
+
/*
* The transactional part of an interior btree node update, where we journal the
* update we did to the interior node and update alloc info:
@@ -662,6 +683,9 @@
if (ret)
goto err;
+ if (!btree_update_new_nodes_marked_sb(as))
+ btree_update_new_nodes_mark_sb(as);
+
/*
* Wait for any in flight writes to finish before we free the old nodes
* on disk:
@@ -704,9 +728,13 @@
bch2_fs_fatal_err_on(ret && !bch2_journal_error(&c->journal), c,
"%s", bch2_err_str(ret));
err:
- if (as->b) {
-
- b = as->b;
+ /*
+ * We have to be careful because another thread might be getting ready
+ * to free as->b and calling btree_update_reparent() on us - we'll
+ * recheck under btree_update_lock below:
+ */
+ b = READ_ONCE(as->b);
+ if (b) {
btree_path_idx_t path_idx = get_unlocked_mut_path(trans,
as->btree_id, b->c.level, b->key.k.p);
struct btree_path *path = trans->paths + path_idx;
@@ -850,15 +878,17 @@
{
struct bch_fs *c = as->c;
- mutex_lock(&c->btree_interior_update_lock);
- list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten);
-
BUG_ON(as->mode != BTREE_UPDATE_none);
+ BUG_ON(as->update_level_end < b->c.level);
BUG_ON(!btree_node_dirty(b));
BUG_ON(!b->c.level);
+ mutex_lock(&c->btree_interior_update_lock);
+ list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten);
+
as->mode = BTREE_UPDATE_node;
as->b = b;
+ as->update_level_end = b->c.level;
set_btree_node_write_blocked(b);
list_add(&as->write_blocked_list, &b->write_blocked);
@@ -1100,7 +1130,7 @@
static struct btree_update *
bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
- unsigned level, bool split, unsigned flags)
+ unsigned level_start, bool split, unsigned flags)
{
struct bch_fs *c = trans->c;
struct btree_update *as;
@@ -1108,7 +1138,7 @@
int disk_res_flags = (flags & BCH_TRANS_COMMIT_no_enospc)
? BCH_DISK_RESERVATION_NOFAIL : 0;
unsigned nr_nodes[2] = { 0, 0 };
- unsigned update_level = level;
+ unsigned level_end = level_start;
enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
int ret = 0;
u32 restart_count = trans->restart_count;
@@ -1123,34 +1153,30 @@
flags &= ~BCH_WATERMARK_MASK;
flags |= watermark;
- if (watermark < c->journal.watermark) {
- struct journal_res res = { 0 };
- unsigned journal_flags = watermark|JOURNAL_RES_GET_CHECK;
+ if (watermark < BCH_WATERMARK_reclaim &&
+ test_bit(JOURNAL_SPACE_LOW, &c->journal.flags)) {
+ if (flags & BCH_TRANS_COMMIT_journal_reclaim)
+ return ERR_PTR(-BCH_ERR_journal_reclaim_would_deadlock);
- if ((flags & BCH_TRANS_COMMIT_journal_reclaim) &&
- watermark < BCH_WATERMARK_reclaim)
- journal_flags |= JOURNAL_RES_GET_NONBLOCK;
-
- ret = drop_locks_do(trans,
- bch2_journal_res_get(&c->journal, &res, 1, journal_flags));
- if (bch2_err_matches(ret, BCH_ERR_operation_blocked))
- ret = -BCH_ERR_journal_reclaim_would_deadlock;
+ bch2_trans_unlock(trans);
+ wait_event(c->journal.wait, !test_bit(JOURNAL_SPACE_LOW, &c->journal.flags));
+ ret = bch2_trans_relock(trans);
if (ret)
return ERR_PTR(ret);
}
while (1) {
- nr_nodes[!!update_level] += 1 + split;
- update_level++;
+ nr_nodes[!!level_end] += 1 + split;
+ level_end++;
- ret = bch2_btree_path_upgrade(trans, path, update_level + 1);
+ ret = bch2_btree_path_upgrade(trans, path, level_end + 1);
if (ret)
return ERR_PTR(ret);
- if (!btree_path_node(path, update_level)) {
+ if (!btree_path_node(path, level_end)) {
/* Allocating new root? */
nr_nodes[1] += split;
- update_level = BTREE_MAX_DEPTH;
+ level_end = BTREE_MAX_DEPTH;
break;
}
@@ -1158,11 +1184,11 @@
* Always check for space for two keys, even if we won't have to
* split at prior level - it might have been a merge instead:
*/
- if (bch2_btree_node_insert_fits(path->l[update_level].b,
+ if (bch2_btree_node_insert_fits(path->l[level_end].b,
BKEY_BTREE_PTR_U64s_MAX * 2))
break;
- split = path->l[update_level].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c);
+ split = path->l[level_end].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c);
}
if (!down_read_trylock(&c->gc_lock)) {
@@ -1176,14 +1202,15 @@
as = mempool_alloc(&c->btree_interior_update_pool, GFP_NOFS);
memset(as, 0, sizeof(*as));
closure_init(&as->cl, NULL);
- as->c = c;
- as->start_time = start_time;
- as->ip_started = _RET_IP_;
- as->mode = BTREE_UPDATE_none;
- as->watermark = watermark;
- as->took_gc_lock = true;
- as->btree_id = path->btree_id;
- as->update_level = update_level;
+ as->c = c;
+ as->start_time = start_time;
+ as->ip_started = _RET_IP_;
+ as->mode = BTREE_UPDATE_none;
+ as->watermark = watermark;
+ as->took_gc_lock = true;
+ as->btree_id = path->btree_id;
+ as->update_level_start = level_start;
+ as->update_level_end = level_end;
INIT_LIST_HEAD(&as->list);
INIT_LIST_HEAD(&as->unwritten_list);
INIT_LIST_HEAD(&as->write_blocked_list);
@@ -1277,23 +1304,29 @@
bch2_recalc_btree_reserve(c);
}
-static void bch2_btree_set_root(struct btree_update *as,
- struct btree_trans *trans,
- struct btree_path *path,
- struct btree *b)
+static int bch2_btree_set_root(struct btree_update *as,
+ struct btree_trans *trans,
+ struct btree_path *path,
+ struct btree *b,
+ bool nofail)
{
struct bch_fs *c = as->c;
- struct btree *old;
trace_and_count(c, btree_node_set_root, trans, b);
- old = btree_node_root(c, b);
+ struct btree *old = btree_node_root(c, b);
/*
* Ensure no one is using the old root while we switch to the
* new root:
*/
- bch2_btree_node_lock_write_nofail(trans, path, &old->c);
+ if (nofail) {
+ bch2_btree_node_lock_write_nofail(trans, path, &old->c);
+ } else {
+ int ret = bch2_btree_node_lock_write(trans, path, &old->c);
+ if (ret)
+ return ret;
+ }
bch2_btree_set_root_inmem(c, b);
@@ -1307,6 +1340,7 @@
* depend on the new root would have to update the new root.
*/
bch2_btree_node_unlock_write(trans, path, old);
+ return 0;
}
/* Interior node updates: */
@@ -1373,12 +1407,12 @@
}
static void
-__bch2_btree_insert_keys_interior(struct btree_update *as,
- struct btree_trans *trans,
- struct btree_path *path,
- struct btree *b,
- struct btree_node_iter node_iter,
- struct keylist *keys)
+bch2_btree_insert_keys_interior(struct btree_update *as,
+ struct btree_trans *trans,
+ struct btree_path *path,
+ struct btree *b,
+ struct btree_node_iter node_iter,
+ struct keylist *keys)
{
struct bkey_i *insert = bch2_keylist_front(keys);
struct bkey_packed *k;
@@ -1534,7 +1568,7 @@
bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p);
- __bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
+ bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
BUG_ON(bch2_btree_node_check_topology(trans, b));
}
@@ -1649,15 +1683,16 @@
if (parent) {
/* Split a non root node */
ret = bch2_btree_insert_node(as, trans, path, parent, &as->parent_keys);
- if (ret)
- goto err;
} else if (n3) {
- bch2_btree_set_root(as, trans, trans->paths + path, n3);
+ ret = bch2_btree_set_root(as, trans, trans->paths + path, n3, false);
} else {
/* Root filled up but didn't need to be split */
- bch2_btree_set_root(as, trans, trans->paths + path, n1);
+ ret = bch2_btree_set_root(as, trans, trans->paths + path, n1, false);
}
+ if (ret)
+ goto err;
+
if (n3) {
bch2_btree_update_get_open_buckets(as, n3);
bch2_btree_node_write(c, n3, SIX_LOCK_intent, 0);
@@ -1714,27 +1749,6 @@
goto out;
}
-static void
-bch2_btree_insert_keys_interior(struct btree_update *as,
- struct btree_trans *trans,
- struct btree_path *path,
- struct btree *b,
- struct keylist *keys)
-{
- struct btree_path *linked;
- unsigned i;
-
- __bch2_btree_insert_keys_interior(as, trans, path, b,
- path->l[b->c.level].iter, keys);
-
- btree_update_updated_node(as, b);
-
- trans_for_each_path_with_node(trans, b, linked, i)
- bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b);
-
- bch2_trans_verify_paths(trans);
-}
-
/**
* bch2_btree_insert_node - insert bkeys into a given btree node
*
@@ -1755,7 +1769,8 @@
struct keylist *keys)
{
struct bch_fs *c = as->c;
- struct btree_path *path = trans->paths + path_idx;
+ struct btree_path *path = trans->paths + path_idx, *linked;
+ unsigned i;
int old_u64s = le16_to_cpu(btree_bset_last(b)->u64s);
int old_live_u64s = b->nr.live_u64s;
int live_u64s_added, u64s_added;
@@ -1784,7 +1799,13 @@
return ret;
}
- bch2_btree_insert_keys_interior(as, trans, path, b, keys);
+ bch2_btree_insert_keys_interior(as, trans, path, b,
+ path->l[b->c.level].iter, keys);
+
+ trans_for_each_path_with_node(trans, b, linked, i)
+ bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b);
+
+ bch2_trans_verify_paths(trans);
live_u64s_added = (int) b->nr.live_u64s - old_live_u64s;
u64s_added = (int) le16_to_cpu(btree_bset_last(b)->u64s) - old_u64s;
@@ -1798,6 +1819,7 @@
bch2_maybe_compact_whiteouts(c, b))
bch2_trans_node_reinit_iter(trans, b);
+ btree_update_updated_node(as, b);
bch2_btree_node_unlock_write(trans, path, b);
BUG_ON(bch2_btree_node_check_topology(trans, b));
@@ -1807,7 +1829,7 @@
* We could attempt to avoid the transaction restart, by calling
* bch2_btree_path_upgrade() and allocating more nodes:
*/
- if (b->c.level >= as->update_level) {
+ if (b->c.level >= as->update_level_end) {
trace_and_count(c, trans_restart_split_race, trans, _THIS_IP_, b);
return btree_trans_restart(trans, BCH_ERR_transaction_restart_split_race);
}
@@ -1873,7 +1895,9 @@
bch2_keylist_add(&as->parent_keys, &b->key);
btree_split_insert_keys(as, trans, path_idx, n, &as->parent_keys);
- bch2_btree_set_root(as, trans, path, n);
+ int ret = bch2_btree_set_root(as, trans, path, n, true);
+ BUG_ON(ret);
+
bch2_btree_update_get_open_buckets(as, n);
bch2_btree_node_write(c, n, SIX_LOCK_intent, 0);
bch2_trans_node_add(trans, path, n);
@@ -1926,6 +1950,22 @@
BUG_ON(!trans->paths[path].should_be_locked);
BUG_ON(!btree_node_locked(&trans->paths[path], level));
+ /*
+ * Work around a deadlock caused by the btree write buffer not doing
+ * merges and leaving tons of merges for us to do - we really don't need
+ * to be doing merges at all from the interior update path, and if the
+ * interior update path is generating too many new interior updates we
+ * deadlock:
+ */
+ if ((flags & BCH_WATERMARK_MASK) == BCH_WATERMARK_interior_updates)
+ return 0;
+
+ if ((flags & BCH_WATERMARK_MASK) <= BCH_WATERMARK_reclaim) {
+ flags &= ~BCH_WATERMARK_MASK;
+ flags |= BCH_WATERMARK_btree;
+ flags |= BCH_TRANS_COMMIT_journal_reclaim;
+ }
+
b = trans->paths[path].l[level].b;
if ((sib == btree_prev_sib && bpos_eq(b->data->min_key, POS_MIN)) ||
@@ -2071,6 +2111,10 @@
bch2_path_put(trans, new_path, true);
bch2_path_put(trans, sib_path, true);
bch2_trans_verify_locks(trans);
+ if (ret == -BCH_ERR_journal_reclaim_would_deadlock)
+ ret = 0;
+ if (!ret)
+ ret = bch2_trans_relock(trans);
return ret;
err_free_update:
bch2_btree_node_free_never_used(as, trans, n);
@@ -2116,12 +2160,13 @@
if (parent) {
bch2_keylist_add(&as->parent_keys, &n->key);
ret = bch2_btree_insert_node(as, trans, iter->path, parent, &as->parent_keys);
- if (ret)
- goto err;
} else {
- bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n);
+ ret = bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n, false);
}
+ if (ret)
+ goto err;
+
bch2_btree_update_get_open_buckets(as, n);
bch2_btree_node_write(c, n, SIX_LOCK_intent, 0);
@@ -2519,9 +2564,11 @@
static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as)
{
- prt_printf(out, "%ps: btree=%s watermark=%s mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
+ prt_printf(out, "%ps: btree=%s l=%u-%u watermark=%s mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
(void *) as->ip_started,
bch2_btree_id_str(as->btree_id),
+ as->update_level_start,
+ as->update_level_end,
bch2_watermarks[as->watermark],
bch2_btree_update_modes[as->mode],
as->nodes_written,
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index 88dcf5a..c1a479e 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -57,7 +57,8 @@
unsigned took_gc_lock:1;
enum btree_id btree_id;
- unsigned update_level;
+ unsigned update_level_start;
+ unsigned update_level_end;
struct disk_reservation disk_res;
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index baf63e2..36a6f42 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -316,6 +316,16 @@
bpos_gt(k->k.k.p, path->l[0].b->key.k.p)) {
bch2_btree_node_unlock_write(trans, path, path->l[0].b);
write_locked = false;
+
+ ret = lockrestart_do(trans,
+ bch2_btree_iter_traverse(&iter) ?:
+ bch2_foreground_maybe_merge(trans, iter.path, 0,
+ BCH_WATERMARK_reclaim|
+ BCH_TRANS_COMMIT_journal_reclaim|
+ BCH_TRANS_COMMIT_no_check_rw|
+ BCH_TRANS_COMMIT_no_enospc));
+ if (ret)
+ goto err;
}
}
@@ -382,10 +392,10 @@
ret = commit_do(trans, NULL, NULL,
BCH_WATERMARK_reclaim|
+ BCH_TRANS_COMMIT_journal_reclaim|
BCH_TRANS_COMMIT_no_check_rw|
BCH_TRANS_COMMIT_no_enospc|
- BCH_TRANS_COMMIT_no_journal_res|
- BCH_TRANS_COMMIT_journal_reclaim,
+ BCH_TRANS_COMMIT_no_journal_res ,
btree_write_buffered_insert(trans, i));
if (ret)
goto err;
diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c
index 941401a2..82f1792 100644
--- a/fs/bcachefs/buckets.c
+++ b/fs/bcachefs/buckets.c
@@ -525,7 +525,6 @@
"different types of data in same bucket: %s, %s",
bch2_data_type_str(g->data_type),
bch2_data_type_str(data_type))) {
- BUG();
ret = -EIO;
goto err;
}
@@ -629,7 +628,6 @@
bch2_data_type_str(ptr_data_type),
(printbuf_reset(&buf),
bch2_bkey_val_to_text(&buf, c, k), buf.buf));
- BUG();
ret = -EIO;
goto err;
}
diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h
index 00aaf4b..f9af5ada 100644
--- a/fs/bcachefs/buckets.h
+++ b/fs/bcachefs/buckets.h
@@ -395,14 +395,6 @@
: "(invalid data type)";
}
-static inline void bch2_prt_data_type(struct printbuf *out, enum bch_data_type type)
-{
- if (type < BCH_DATA_NR)
- prt_str(out, __bch2_data_types[type]);
- else
- prt_printf(out, "(invalid data type %u)", type);
-}
-
/* disk reservations: */
static inline void bch2_disk_reservation_put(struct bch_fs *c,
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index cbfa645..4d14f19 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -134,42 +134,38 @@
struct fsck_thread {
struct thread_with_stdio thr;
struct bch_fs *c;
- char **devs;
- size_t nr_devs;
struct bch_opts opts;
};
static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr)
{
struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr);
- if (thr->devs)
- for (size_t i = 0; i < thr->nr_devs; i++)
- kfree(thr->devs[i]);
- kfree(thr->devs);
kfree(thr);
}
static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio)
{
struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr);
- struct bch_fs *c = bch2_fs_open(thr->devs, thr->nr_devs, thr->opts);
+ struct bch_fs *c = thr->c;
- if (IS_ERR(c))
- return PTR_ERR(c);
+ int ret = PTR_ERR_OR_ZERO(c);
+ if (ret)
+ return ret;
- int ret = 0;
- if (test_bit(BCH_FS_errors_fixed, &c->flags))
- ret |= 1;
- if (test_bit(BCH_FS_error, &c->flags))
- ret |= 4;
+ ret = bch2_fs_start(thr->c);
+ if (ret)
+ goto err;
- bch2_fs_stop(c);
-
- if (ret & 1)
+ if (test_bit(BCH_FS_errors_fixed, &c->flags)) {
bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name);
- if (ret & 4)
+ ret |= 1;
+ }
+ if (test_bit(BCH_FS_error, &c->flags)) {
bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name);
-
+ ret |= 4;
+ }
+err:
+ bch2_fs_stop(c);
return ret;
}
@@ -182,7 +178,7 @@
{
struct bch_ioctl_fsck_offline arg;
struct fsck_thread *thr = NULL;
- u64 *devs = NULL;
+ darray_str(devs) = {};
long ret = 0;
if (copy_from_user(&arg, user_arg, sizeof(arg)))
@@ -194,28 +190,31 @@
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!(devs = kcalloc(arg.nr_devs, sizeof(*devs), GFP_KERNEL)) ||
- !(thr = kzalloc(sizeof(*thr), GFP_KERNEL)) ||
- !(thr->devs = kcalloc(arg.nr_devs, sizeof(*thr->devs), GFP_KERNEL))) {
+ for (size_t i = 0; i < arg.nr_devs; i++) {
+ u64 dev_u64;
+ ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64));
+ if (ret)
+ goto err;
+
+ char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX);
+ ret = PTR_ERR_OR_ZERO(dev_str);
+ if (ret)
+ goto err;
+
+ ret = darray_push(&devs, dev_str);
+ if (ret) {
+ kfree(dev_str);
+ goto err;
+ }
+ }
+
+ thr = kzalloc(sizeof(*thr), GFP_KERNEL);
+ if (!thr) {
ret = -ENOMEM;
goto err;
}
thr->opts = bch2_opts_empty();
- thr->nr_devs = arg.nr_devs;
-
- if (copy_from_user(devs, &user_arg->devs[0],
- array_size(sizeof(user_arg->devs[0]), arg.nr_devs))) {
- ret = -EINVAL;
- goto err;
- }
-
- for (size_t i = 0; i < arg.nr_devs; i++) {
- thr->devs[i] = strndup_user((char __user *)(unsigned long) devs[i], PATH_MAX);
- ret = PTR_ERR_OR_ZERO(thr->devs[i]);
- if (ret)
- goto err;
- }
if (arg.opts) {
char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16);
@@ -230,15 +229,28 @@
opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio);
- ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_offline_fsck_ops);
-err:
- if (ret < 0) {
- if (thr)
- bch2_fsck_thread_exit(&thr->thr);
- pr_err("ret %s", bch2_err_str(ret));
- }
- kfree(devs);
+ /* We need request_key() to be called before we punt to kthread: */
+ opt_set(thr->opts, nostart, true);
+
+ bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops);
+
+ thr->c = bch2_fs_open(devs.data, arg.nr_devs, thr->opts);
+
+ if (!IS_ERR(thr->c) &&
+ thr->c->opts.errors == BCH_ON_ERROR_panic)
+ thr->c->opts.errors = BCH_ON_ERROR_ro;
+
+ ret = __bch2_run_thread_with_stdio(&thr->thr);
+out:
+ darray_for_each(devs, i)
+ kfree(*i);
+ darray_exit(&devs);
return ret;
+err:
+ if (thr)
+ bch2_fsck_thread_exit(&thr->thr);
+ pr_err("ret %s", bch2_err_str(ret));
+ goto out;
}
static long bch2_global_ioctl(unsigned cmd, void __user *arg)
diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c
index 4701457..7ed779b 100644
--- a/fs/bcachefs/checksum.c
+++ b/fs/bcachefs/checksum.c
@@ -429,15 +429,20 @@
extent_nonce(version, crc_old), bio);
if (bch2_crc_cmp(merged, crc_old.csum) && !c->opts.no_data_io) {
- bch_err(c, "checksum error in %s() (memory corruption or bug?)\n"
- "expected %0llx:%0llx got %0llx:%0llx (old type %s new type %s)",
- __func__,
- crc_old.csum.hi,
- crc_old.csum.lo,
- merged.hi,
- merged.lo,
- bch2_csum_types[crc_old.csum_type],
- bch2_csum_types[new_csum_type]);
+ struct printbuf buf = PRINTBUF;
+ prt_printf(&buf, "checksum error in %s() (memory corruption or bug?)\n"
+ "expected %0llx:%0llx got %0llx:%0llx (old type ",
+ __func__,
+ crc_old.csum.hi,
+ crc_old.csum.lo,
+ merged.hi,
+ merged.lo);
+ bch2_prt_csum_type(&buf, crc_old.csum_type);
+ prt_str(&buf, " new type ");
+ bch2_prt_csum_type(&buf, new_csum_type);
+ prt_str(&buf, ")");
+ bch_err(c, "%s", buf.buf);
+ printbuf_exit(&buf);
return -EIO;
}
diff --git a/fs/bcachefs/checksum.h b/fs/bcachefs/checksum.h
index 1b8c2c1..e40499f 100644
--- a/fs/bcachefs/checksum.h
+++ b/fs/bcachefs/checksum.h
@@ -61,11 +61,12 @@
struct bch_csum expected,
struct bch_csum got)
{
- prt_printf(out, "checksum error: got ");
+ prt_str(out, "checksum error, type ");
+ bch2_prt_csum_type(out, type);
+ prt_str(out, ": got ");
bch2_csum_to_text(out, type, got);
prt_str(out, " should be ");
bch2_csum_to_text(out, type, expected);
- prt_printf(out, " type %s", bch2_csum_types[type]);
}
int bch2_chacha_encrypt_key(struct bch_key *, struct nonce, void *, size_t);
diff --git a/fs/bcachefs/compress.h b/fs/bcachefs/compress.h
index 58c2eb4..607fd5e 100644
--- a/fs/bcachefs/compress.h
+++ b/fs/bcachefs/compress.h
@@ -47,14 +47,6 @@
return __bch2_compression_opt_to_type[bch2_compression_decode(v).type];
}
-static inline void bch2_prt_compression_type(struct printbuf *out, enum bch_compression_type type)
-{
- if (type < BCH_COMPRESSION_TYPE_NR)
- prt_str(out, __bch2_compression_types[type]);
- else
- prt_printf(out, "(invalid compression type %u)", type);
-}
-
int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *,
struct bch_extent_crc_unpacked *);
int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *,
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 34731ee..0022b51 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -598,6 +598,8 @@
i++;
}
+ unsigned durability_required = max(0, (int) (io_opts.data_replicas - durability_have));
+
/*
* If current extent durability is less than io_opts.data_replicas,
* we're not trying to rereplicate the extent up to data_replicas here -
@@ -607,7 +609,7 @@
* rereplicate, currently, so that users don't get an unexpected -ENOSPC
*/
if (!(m->data_opts.write_flags & BCH_WRITE_CACHED) &&
- durability_have >= io_opts.data_replicas) {
+ !durability_required) {
m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs;
m->data_opts.rewrite_ptrs = 0;
/* if iter == NULL, it's just a promote */
@@ -616,11 +618,18 @@
goto done;
}
- m->op.nr_replicas = min(durability_removing, io_opts.data_replicas - durability_have) +
+ m->op.nr_replicas = min(durability_removing, durability_required) +
m->data_opts.extra_replicas;
- m->op.nr_replicas_required = m->op.nr_replicas;
- BUG_ON(!m->op.nr_replicas);
+ /*
+ * If device(s) were set to durability=0 after data was written to them
+ * we can end up with a duribilty=0 extent, and the normal algorithm
+ * that tries not to increase durability doesn't work:
+ */
+ if (!(durability_have + durability_removing))
+ m->op.nr_replicas = max((unsigned) m->op.nr_replicas, 1);
+
+ m->op.nr_replicas_required = m->op.nr_replicas;
if (reserve_sectors) {
ret = bch2_disk_reservation_add(c, &m->op.res, reserve_sectors,
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index 208ce6f..cd99b73 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -13,6 +13,7 @@
#include "btree_iter.h"
#include "btree_locking.h"
#include "btree_update.h"
+#include "btree_update_interior.h"
#include "buckets.h"
#include "debug.h"
#include "error.h"
@@ -668,7 +669,7 @@
i->size = size;
i->ret = 0;
- do {
+ while (1) {
err = flush_buf(i);
if (err)
return err;
@@ -676,9 +677,12 @@
if (!i->size)
break;
+ if (done)
+ break;
+
done = bch2_journal_seq_pins_to_text(&i->buf, &c->journal, &i->iter);
i->iter++;
- } while (!done);
+ }
if (i->buf.allocation_failure)
return -ENOMEM;
@@ -693,13 +697,45 @@
.read = bch2_journal_pins_read,
};
+static ssize_t bch2_btree_updates_read(struct file *file, char __user *buf,
+ size_t size, loff_t *ppos)
+{
+ struct dump_iter *i = file->private_data;
+ struct bch_fs *c = i->c;
+ int err;
+
+ i->ubuf = buf;
+ i->size = size;
+ i->ret = 0;
+
+ if (!i->iter) {
+ bch2_btree_updates_to_text(&i->buf, c);
+ i->iter++;
+ }
+
+ err = flush_buf(i);
+ if (err)
+ return err;
+
+ if (i->buf.allocation_failure)
+ return -ENOMEM;
+
+ return i->ret;
+}
+
+static const struct file_operations btree_updates_ops = {
+ .owner = THIS_MODULE,
+ .open = bch2_dump_open,
+ .release = bch2_dump_release,
+ .read = bch2_btree_updates_read,
+};
+
static int btree_transaction_stats_open(struct inode *inode, struct file *file)
{
struct bch_fs *c = inode->i_private;
struct dump_iter *i;
i = kzalloc(sizeof(struct dump_iter), GFP_KERNEL);
-
if (!i)
return -ENOMEM;
@@ -866,6 +902,20 @@
debugfs_remove_recursive(c->fs_debug_dir);
}
+static void bch2_fs_debug_btree_init(struct bch_fs *c, struct btree_debug *bd)
+{
+ struct dentry *d;
+
+ d = debugfs_create_dir(bch2_btree_id_str(bd->id), c->btree_debug_dir);
+
+ debugfs_create_file("keys", 0400, d, bd, &btree_debug_ops);
+
+ debugfs_create_file("formats", 0400, d, bd, &btree_format_debug_ops);
+
+ debugfs_create_file("bfloat-failed", 0400, d, bd,
+ &bfloat_failed_debug_ops);
+}
+
void bch2_fs_debug_init(struct bch_fs *c)
{
struct btree_debug *bd;
@@ -888,6 +938,9 @@
debugfs_create_file("journal_pins", 0400, c->fs_debug_dir,
c->btree_debug, &journal_pins_ops);
+ debugfs_create_file("btree_updates", 0400, c->fs_debug_dir,
+ c->btree_debug, &btree_updates_ops);
+
debugfs_create_file("btree_transaction_stats", 0400, c->fs_debug_dir,
c, &btree_transaction_stats_op);
@@ -902,21 +955,7 @@
bd < c->btree_debug + ARRAY_SIZE(c->btree_debug);
bd++) {
bd->id = bd - c->btree_debug;
- debugfs_create_file(bch2_btree_id_str(bd->id),
- 0400, c->btree_debug_dir, bd,
- &btree_debug_ops);
-
- snprintf(name, sizeof(name), "%s-formats",
- bch2_btree_id_str(bd->id));
-
- debugfs_create_file(name, 0400, c->btree_debug_dir, bd,
- &btree_format_debug_ops);
-
- snprintf(name, sizeof(name), "%s-bfloat-failed",
- bch2_btree_id_str(bd->id));
-
- debugfs_create_file(name, 0400, c->btree_debug_dir, bd,
- &bfloat_failed_debug_ops);
+ bch2_fs_debug_btree_init(c, bd);
}
}
diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index 0820752..556a217 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -131,29 +131,33 @@
void bch2_stripe_to_text(struct printbuf *out, struct bch_fs *c,
struct bkey_s_c k)
{
- const struct bch_stripe *s = bkey_s_c_to_stripe(k).v;
- unsigned i, nr_data = s->nr_blocks - s->nr_redundant;
+ const struct bch_stripe *sp = bkey_s_c_to_stripe(k).v;
+ struct bch_stripe s = {};
- prt_printf(out, "algo %u sectors %u blocks %u:%u csum %u gran %u",
- s->algorithm,
- le16_to_cpu(s->sectors),
- nr_data,
- s->nr_redundant,
- s->csum_type,
- 1U << s->csum_granularity_bits);
+ memcpy(&s, sp, min(sizeof(s), bkey_val_bytes(k.k)));
- for (i = 0; i < s->nr_blocks; i++) {
- const struct bch_extent_ptr *ptr = s->ptrs + i;
- struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev);
- u32 offset;
- u64 b = sector_to_bucket_and_offset(ca, ptr->offset, &offset);
+ unsigned nr_data = s.nr_blocks - s.nr_redundant;
- prt_printf(out, " %u:%llu:%u", ptr->dev, b, offset);
- if (i < nr_data)
- prt_printf(out, "#%u", stripe_blockcount_get(s, i));
- prt_printf(out, " gen %u", ptr->gen);
- if (ptr_stale(ca, ptr))
- prt_printf(out, " stale");
+ prt_printf(out, "algo %u sectors %u blocks %u:%u csum ",
+ s.algorithm,
+ le16_to_cpu(s.sectors),
+ nr_data,
+ s.nr_redundant);
+ bch2_prt_csum_type(out, s.csum_type);
+ prt_printf(out, " gran %u", 1U << s.csum_granularity_bits);
+
+ for (unsigned i = 0; i < s.nr_blocks; i++) {
+ const struct bch_extent_ptr *ptr = sp->ptrs + i;
+
+ if ((void *) ptr >= bkey_val_end(k))
+ break;
+
+ bch2_extent_ptr_to_text(out, c, ptr);
+
+ if (s.csum_type < BCH_CSUM_NR &&
+ i < nr_data &&
+ stripe_blockcount_offset(&s, i) < bkey_val_bytes(k.k))
+ prt_printf(out, "#%u", stripe_blockcount_get(sp, i));
}
}
@@ -607,10 +611,8 @@
struct printbuf err = PRINTBUF;
struct bch_dev *ca = bch_dev_bkey_exists(c, v->ptrs[i].dev);
- prt_printf(&err, "stripe checksum error: expected %0llx:%0llx got %0llx:%0llx (type %s)\n",
- want.hi, want.lo,
- got.hi, got.lo,
- bch2_csum_types[v->csum_type]);
+ prt_str(&err, "stripe ");
+ bch2_csum_err_msg(&err, v->csum_type, want, got);
prt_printf(&err, " for %ps at %u of\n ", (void *) _RET_IP_, i);
bch2_bkey_val_to_text(&err, c, bkey_i_to_s_c(&buf->key));
bch_err_ratelimited(ca, "%s", err.buf);
diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h
index f4369b0..f042616 100644
--- a/fs/bcachefs/ec.h
+++ b/fs/bcachefs/ec.h
@@ -32,6 +32,8 @@
static inline unsigned stripe_csum_offset(const struct bch_stripe *s,
unsigned dev, unsigned csum_idx)
{
+ EBUG_ON(s->csum_type >= BCH_CSUM_NR);
+
unsigned csum_bytes = bch_crc_bytes[s->csum_type];
return sizeof(struct bch_stripe) +
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 0e3ca99..1a331e5 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -998,7 +998,9 @@
prt_str(out, " cached");
if (ptr->unwritten)
prt_str(out, " unwritten");
- if (ca && ptr_stale(ca, ptr))
+ if (b >= ca->mi.first_bucket &&
+ b < ca->mi.nbuckets &&
+ ptr_stale(ca, ptr))
prt_printf(out, " stale");
}
}
@@ -1028,11 +1030,12 @@
struct bch_extent_crc_unpacked crc =
bch2_extent_crc_unpack(k.k, entry_to_crc(entry));
- prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum %s compress ",
+ prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum ",
crc.compressed_size,
crc.uncompressed_size,
- crc.offset, crc.nonce,
- bch2_csum_types[crc.csum_type]);
+ crc.offset, crc.nonce);
+ bch2_prt_csum_type(out, crc.csum_type);
+ prt_str(out, " compress ");
bch2_prt_compression_type(out, crc.compression_type);
break;
}
diff --git a/fs/bcachefs/eytzinger.c b/fs/bcachefs/eytzinger.c
index 4ce5e95..0f955c3 100644
--- a/fs/bcachefs/eytzinger.c
+++ b/fs/bcachefs/eytzinger.c
@@ -115,7 +115,7 @@
struct wrapper {
cmp_func_t cmp;
- swap_func_t swap;
+ swap_func_t swap_func;
};
/*
@@ -125,7 +125,7 @@
static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv)
{
if (swap_func == SWAP_WRAPPER) {
- ((const struct wrapper *)priv)->swap(a, b, (int)size);
+ ((const struct wrapper *)priv)->swap_func(a, b, (int)size);
return;
}
@@ -174,7 +174,7 @@
int i, c, r;
/* called from 'sort' without swap function, let's pick the default */
- if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap)
+ if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap_func)
swap_func = NULL;
if (!swap_func) {
@@ -227,7 +227,7 @@
{
struct wrapper w = {
.cmp = cmp_func,
- .swap = swap_func,
+ .swap_func = swap_func,
};
return eytzinger0_sort_r(base, n, size, _CMP_WRAPPER, SWAP_WRAPPER, &w);
diff --git a/fs/bcachefs/eytzinger.h b/fs/bcachefs/eytzinger.h
index ee0e2df..24840ae 100644
--- a/fs/bcachefs/eytzinger.h
+++ b/fs/bcachefs/eytzinger.h
@@ -242,8 +242,8 @@
(_i) = eytzinger0_next((_i), (_size)))
/* return greatest node <= @search, or -1 if not found */
-static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size,
- cmp_func_t cmp, const void *search)
+static inline int eytzinger0_find_le(void *base, size_t nr, size_t size,
+ cmp_func_t cmp, const void *search)
{
unsigned i, n = 0;
@@ -256,18 +256,32 @@
} while (n < nr);
if (n & 1) {
- /* @i was greater than @search, return previous node: */
+ /*
+ * @i was greater than @search, return previous node:
+ *
+ * if @i was leftmost/smallest element,
+ * eytzinger0_prev(eytzinger0_first())) returns -1, as expected
+ */
return eytzinger0_prev(i, nr);
} else {
return i;
}
}
-static inline ssize_t eytzinger0_find_gt(void *base, size_t nr, size_t size,
- cmp_func_t cmp, const void *search)
+static inline int eytzinger0_find_gt(void *base, size_t nr, size_t size,
+ cmp_func_t cmp, const void *search)
{
ssize_t idx = eytzinger0_find_le(base, nr, size, cmp, search);
- return eytzinger0_next(idx, size);
+
+ /*
+ * if eytitzinger0_find_le() returned -1 - no element was <= search - we
+ * want to return the first element; next/prev identities mean this work
+ * as expected
+ *
+ * similarly if find_le() returns last element, we should return -1;
+ * identities mean this all works out:
+ */
+ return eytzinger0_next(idx, nr);
}
#define eytzinger0_find(base, nr, size, _cmp, search) \
diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c
index f49e6c0..b889370 100644
--- a/fs/bcachefs/fs-io-direct.c
+++ b/fs/bcachefs/fs-io-direct.c
@@ -387,6 +387,8 @@
ret = dio->op.error ?: ((long) dio->written << 9);
bio_put(&dio->op.wbio.bio);
+ bch2_write_ref_put(dio->op.c, BCH_WRITE_REF_dio_write);
+
/* inode->i_dio_count is our ref on inode and thus bch_fs */
inode_dio_end(&inode->v);
@@ -590,22 +592,25 @@
prefetch(&inode->ei_inode);
prefetch((void *) &inode->ei_inode + 64);
+ if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_dio_write))
+ return -EROFS;
+
inode_lock(&inode->v);
ret = generic_write_checks(req, iter);
if (unlikely(ret <= 0))
- goto err;
+ goto err_put_write_ref;
ret = file_remove_privs(file);
if (unlikely(ret))
- goto err;
+ goto err_put_write_ref;
ret = file_update_time(file);
if (unlikely(ret))
- goto err;
+ goto err_put_write_ref;
if (unlikely((req->ki_pos|iter->count) & (block_bytes(c) - 1)))
- goto err;
+ goto err_put_write_ref;
inode_dio_begin(&inode->v);
bch2_pagecache_block_get(inode);
@@ -645,7 +650,7 @@
}
ret = bch2_dio_write_loop(dio);
-err:
+out:
if (locked)
inode_unlock(&inode->v);
return ret;
@@ -653,7 +658,9 @@
bch2_pagecache_block_put(inode);
bio_put(bio);
inode_dio_end(&inode->v);
- goto err;
+err_put_write_ref:
+ bch2_write_ref_put(c, BCH_WRITE_REF_dio_write);
+ goto out;
}
void bch2_fs_fs_io_direct_exit(struct bch_fs *c)
diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 8c70123..20b4047 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -174,18 +174,18 @@
static int bch2_flush_inode(struct bch_fs *c,
struct bch_inode_info *inode)
{
- struct bch_inode_unpacked u;
- int ret;
-
if (c->opts.journal_flush_disabled)
return 0;
- ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u);
- if (ret)
- return ret;
+ if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync))
+ return -EROFS;
- return bch2_journal_flush_seq(&c->journal, u.bi_journal_seq) ?:
- bch2_inode_flush_nocow_writes(c, inode);
+ struct bch_inode_unpacked u;
+ int ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u) ?:
+ bch2_journal_flush_seq(&c->journal, u.bi_journal_seq) ?:
+ bch2_inode_flush_nocow_writes(c, inode);
+ bch2_write_ref_put(c, BCH_WRITE_REF_fsync);
+ return ret;
}
int bch2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index b5ea9fa..fce6900 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -188,7 +188,8 @@
BUG_ON(!old);
if (unlikely(old != inode)) {
- discard_new_inode(&inode->v);
+ __destroy_inode(&inode->v);
+ kmem_cache_free(bch2_inode_cache, inode);
inode = old;
} else {
mutex_lock(&c->vfs_inodes_lock);
@@ -225,8 +226,10 @@
if (unlikely(!inode)) {
int ret = drop_locks_do(trans, (inode = to_bch_ei(new_inode(c->vfs_sb))) ? 0 : -ENOMEM);
- if (ret && inode)
- discard_new_inode(&inode->v);
+ if (ret && inode) {
+ __destroy_inode(&inode->v);
+ kmem_cache_free(bch2_inode_cache, inode);
+ }
if (ret)
return ERR_PTR(ret);
}
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index ca4a066..0f95d7f 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -606,7 +606,7 @@
struct bkey_s new,
unsigned flags)
{
- s64 nr = bkey_is_inode(new.k) - bkey_is_inode(old.k);
+ s64 nr = (s64) bkey_is_inode(new.k) - (s64) bkey_is_inode(old.k);
if (flags & BTREE_TRIGGER_TRANSACTIONAL) {
if (nr) {
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 725fcf4..eb1f9d6 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -247,7 +247,7 @@
if (entry) {
prt_str(out, " type=");
- prt_str(out, bch2_jset_entry_types[entry->type]);
+ bch2_prt_jset_entry_type(out, entry->type);
}
if (!jset) {
@@ -403,7 +403,8 @@
jset_entry_for_each_key(entry, k) {
if (!first) {
prt_newline(out);
- prt_printf(out, "%s: ", bch2_jset_entry_types[entry->type]);
+ bch2_prt_jset_entry_type(out, entry->type);
+ prt_str(out, ": ");
}
prt_printf(out, "btree=%s l=%u ", bch2_btree_id_str(entry->btree_id), entry->level);
bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(k));
@@ -563,9 +564,9 @@
struct jset_entry_usage *u =
container_of(entry, struct jset_entry_usage, entry);
- prt_printf(out, "type=%s v=%llu",
- bch2_fs_usage_types[u->entry.btree_id],
- le64_to_cpu(u->v));
+ prt_str(out, "type=");
+ bch2_prt_fs_usage_type(out, u->entry.btree_id);
+ prt_printf(out, " v=%llu", le64_to_cpu(u->v));
}
static int journal_entry_data_usage_validate(struct bch_fs *c,
@@ -827,11 +828,11 @@
void bch2_journal_entry_to_text(struct printbuf *out, struct bch_fs *c,
struct jset_entry *entry)
{
+ bch2_prt_jset_entry_type(out, entry->type);
+
if (entry->type < BCH_JSET_ENTRY_NR) {
- prt_printf(out, "%s: ", bch2_jset_entry_types[entry->type]);
+ prt_str(out, ": ");
bch2_jset_entry_ops[entry->type].to_text(out, c, entry);
- } else {
- prt_printf(out, "(unknown type %u)", entry->type);
}
}
@@ -1722,7 +1723,7 @@
percpu_ref_put(&ca->io_ref);
}
-static CLOSURE_CALLBACK(do_journal_write)
+static CLOSURE_CALLBACK(journal_write_submit)
{
closure_type(w, struct journal_buf, io);
struct journal *j = container_of(w, struct journal, buf[w->idx]);
@@ -1767,6 +1768,44 @@
continue_at(cl, journal_write_done, j->wq);
}
+static CLOSURE_CALLBACK(journal_write_preflush)
+{
+ closure_type(w, struct journal_buf, io);
+ struct journal *j = container_of(w, struct journal, buf[w->idx]);
+ struct bch_fs *c = container_of(j, struct bch_fs, journal);
+
+ if (j->seq_ondisk + 1 != le64_to_cpu(w->data->seq)) {
+ spin_lock(&j->lock);
+ closure_wait(&j->async_wait, cl);
+ spin_unlock(&j->lock);
+
+ continue_at(cl, journal_write_preflush, j->wq);
+ return;
+ }
+
+ if (w->separate_flush) {
+ for_each_rw_member(c, ca) {
+ percpu_ref_get(&ca->io_ref);
+
+ struct journal_device *ja = &ca->journal;
+ struct bio *bio = &ja->bio[w->idx]->bio;
+ bio_reset(bio, ca->disk_sb.bdev,
+ REQ_OP_WRITE|REQ_SYNC|REQ_META|REQ_PREFLUSH);
+ bio->bi_end_io = journal_write_endio;
+ bio->bi_private = ca;
+ closure_bio_submit(bio, cl);
+ }
+
+ continue_at(cl, journal_write_submit, j->wq);
+ } else {
+ /*
+ * no need to punt to another work item if we're not waiting on
+ * preflushes
+ */
+ journal_write_submit(&cl->work);
+ }
+}
+
static int bch2_journal_write_prep(struct journal *j, struct journal_buf *w)
{
struct bch_fs *c = container_of(j, struct bch_fs, journal);
@@ -2032,23 +2071,9 @@
goto err;
if (!JSET_NO_FLUSH(w->data))
- closure_wait_event(&j->async_wait, j->seq_ondisk + 1 == le64_to_cpu(w->data->seq));
-
- if (!JSET_NO_FLUSH(w->data) && w->separate_flush) {
- for_each_rw_member(c, ca) {
- percpu_ref_get(&ca->io_ref);
-
- struct journal_device *ja = &ca->journal;
- struct bio *bio = &ja->bio[w->idx]->bio;
- bio_reset(bio, ca->disk_sb.bdev,
- REQ_OP_WRITE|REQ_SYNC|REQ_META|REQ_PREFLUSH);
- bio->bi_end_io = journal_write_endio;
- bio->bi_private = ca;
- closure_bio_submit(bio, cl);
- }
- }
-
- continue_at(cl, do_journal_write, j->wq);
+ continue_at(cl, journal_write_preflush, j->wq);
+ else
+ continue_at(cl, journal_write_submit, j->wq);
return;
no_io:
continue_at(cl, journal_write_done, j->wq);
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index ab811c0..04a5778 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -67,6 +67,8 @@
track_event_change(&c->times[BCH_TIME_blocked_write_buffer_full], low_on_wb))
trace_and_count(c, journal_full, c);
+ mod_bit(JOURNAL_SPACE_LOW, &j->flags, low_on_space || low_on_pin);
+
swap(watermark, j->watermark);
if (watermark > j->watermark)
journal_wake(j);
diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h
index 8c053cb..b5161b5 100644
--- a/fs/bcachefs/journal_types.h
+++ b/fs/bcachefs/journal_types.h
@@ -134,6 +134,7 @@
JOURNAL_STARTED,
JOURNAL_MAY_SKIP_FLUSH,
JOURNAL_NEED_FLUSH_WRITE,
+ JOURNAL_SPACE_LOW,
};
/* Reasons we may fail to get a journal reservation: */
diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c
index e1800c4..bb068fd 100644
--- a/fs/bcachefs/opts.c
+++ b/fs/bcachefs/opts.c
@@ -43,7 +43,7 @@
NULL
};
-const char * const bch2_csum_types[] = {
+static const char * const __bch2_csum_types[] = {
BCH_CSUM_TYPES()
NULL
};
@@ -53,7 +53,7 @@
NULL
};
-const char * const __bch2_compression_types[] = {
+static const char * const __bch2_compression_types[] = {
BCH_COMPRESSION_TYPES()
NULL
};
@@ -83,18 +83,39 @@
NULL
};
-const char * const bch2_jset_entry_types[] = {
+static const char * const __bch2_jset_entry_types[] = {
BCH_JSET_ENTRY_TYPES()
NULL
};
-const char * const bch2_fs_usage_types[] = {
+static const char * const __bch2_fs_usage_types[] = {
BCH_FS_USAGE_TYPES()
NULL
};
#undef x
+static void prt_str_opt_boundscheck(struct printbuf *out, const char * const opts[],
+ unsigned nr, const char *type, unsigned idx)
+{
+ if (idx < nr)
+ prt_str(out, opts[idx]);
+ else
+ prt_printf(out, "(unknown %s %u)", type, idx);
+}
+
+#define PRT_STR_OPT_BOUNDSCHECKED(name, type) \
+void bch2_prt_##name(struct printbuf *out, type t) \
+{ \
+ prt_str_opt_boundscheck(out, __bch2_##name##s, ARRAY_SIZE(__bch2_##name##s) - 1, #name, t);\
+}
+
+PRT_STR_OPT_BOUNDSCHECKED(jset_entry_type, enum bch_jset_entry_type);
+PRT_STR_OPT_BOUNDSCHECKED(fs_usage_type, enum bch_fs_usage_type);
+PRT_STR_OPT_BOUNDSCHECKED(data_type, enum bch_data_type);
+PRT_STR_OPT_BOUNDSCHECKED(csum_type, enum bch_csum_type);
+PRT_STR_OPT_BOUNDSCHECKED(compression_type, enum bch_compression_type);
+
static int bch2_opt_fix_errors_parse(struct bch_fs *c, const char *val, u64 *res,
struct printbuf *err)
{
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 1ac4135..84e4528 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -16,18 +16,20 @@
extern const char * const bch2_sb_features[];
extern const char * const bch2_sb_compat[];
extern const char * const __bch2_btree_ids[];
-extern const char * const bch2_csum_types[];
extern const char * const bch2_csum_opts[];
-extern const char * const __bch2_compression_types[];
extern const char * const bch2_compression_opts[];
extern const char * const bch2_str_hash_types[];
extern const char * const bch2_str_hash_opts[];
extern const char * const __bch2_data_types[];
extern const char * const bch2_member_states[];
-extern const char * const bch2_jset_entry_types[];
-extern const char * const bch2_fs_usage_types[];
extern const char * const bch2_d_types[];
+void bch2_prt_jset_entry_type(struct printbuf *, enum bch_jset_entry_type);
+void bch2_prt_fs_usage_type(struct printbuf *, enum bch_fs_usage_type);
+void bch2_prt_data_type(struct printbuf *, enum bch_data_type);
+void bch2_prt_csum_type(struct printbuf *, enum bch_csum_type);
+void bch2_prt_compression_type(struct printbuf *, enum bch_compression_type);
+
static inline const char *bch2_d_type_str(unsigned d_type)
{
return (d_type < BCH_DT_MAX ? bch2_d_types[d_type] : NULL) ?: "(bad d_type)";
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index b76c161..be5b476 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -47,20 +47,6 @@
}
}
-static bool btree_id_is_alloc(enum btree_id id)
-{
- switch (id) {
- case BTREE_ID_alloc:
- case BTREE_ID_backpointers:
- case BTREE_ID_need_discard:
- case BTREE_ID_freespace:
- case BTREE_ID_bucket_gens:
- return true;
- default:
- return false;
- }
-}
-
/* for -o reconstruct_alloc: */
static void bch2_reconstruct_alloc(struct bch_fs *c)
{
@@ -263,7 +249,10 @@
struct journal_key *k = *kp;
- replay_now_at(j, k->journal_seq);
+ if (k->journal_seq)
+ replay_now_at(j, k->journal_seq);
+ else
+ replay_now_at(j, j->replay_journal_seq_end);
ret = commit_do(trans, NULL, NULL,
BCH_TRANS_COMMIT_no_enospc|
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index cb50146..0cec0f7 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -44,7 +44,7 @@
set_bit(BCH_FS_may_go_rw, &c->flags);
- if (keys->nr || c->opts.fsck || !c->sb.clean)
+ if (keys->nr || c->opts.fsck || !c->sb.clean || c->recovery_passes_explicit)
return bch2_fs_read_write_early(c);
return 0;
}
diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c
index 5980ba2..35ca3f1 100644
--- a/fs/bcachefs/sb-clean.c
+++ b/fs/bcachefs/sb-clean.c
@@ -29,6 +29,14 @@
for (entry = clean->start;
entry < (struct jset_entry *) vstruct_end(&clean->field);
entry = vstruct_next(entry)) {
+ if (vstruct_end(entry) > vstruct_end(&clean->field)) {
+ bch_err(c, "journal entry (u64s %u) overran end of superblock clean section (u64s %u) by %zu",
+ le16_to_cpu(entry->u64s), le32_to_cpu(clean->field.u64s),
+ (u64 *) vstruct_end(entry) - (u64 *) vstruct_end(&clean->field));
+ bch2_sb_error_count(c, BCH_FSCK_ERR_sb_clean_entry_overrun);
+ return -BCH_ERR_fsck_repair_unimplemented;
+ }
+
ret = bch2_journal_entry_validate(c, NULL, entry,
le16_to_cpu(c->disk_sb.sb->version),
BCH_SB_BIG_ENDIAN(c->disk_sb.sb),
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index d6f8117..a98ef94 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -51,7 +51,10 @@
BCH_FSCK_ERR_subvol_fs_path_parent_wrong) \
x(btree_subvolume_children, \
BIT_ULL(BCH_RECOVERY_PASS_check_subvols), \
- BCH_FSCK_ERR_subvol_children_not_set)
+ BCH_FSCK_ERR_subvol_children_not_set) \
+ x(mi_btree_bitmap, \
+ BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \
+ BCH_FSCK_ERR_btree_bitmap_not_marked)
#define DOWNGRADE_TABLE()
diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h
index d7d6091..06c7a64 100644
--- a/fs/bcachefs/sb-errors_types.h
+++ b/fs/bcachefs/sb-errors_types.h
@@ -130,7 +130,7 @@
x(bucket_gens_nonzero_for_invalid_buckets, 122) \
x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \
x(need_discard_freespace_key_bad, 124) \
- x(backpointer_pos_wrong, 125) \
+ x(backpointer_bucket_offset_wrong, 125) \
x(backpointer_to_missing_device, 126) \
x(backpointer_to_missing_alloc, 127) \
x(backpointer_to_missing_ptr, 128) \
@@ -270,7 +270,9 @@
x(btree_ptr_v2_min_key_bad, 262) \
x(btree_root_unreadable_and_scan_found_nothing, 263) \
x(snapshot_node_missing, 264) \
- x(dup_backpointer_to_bad_csum_extent, 265)
+ x(dup_backpointer_to_bad_csum_extent, 265) \
+ x(btree_bitmap_not_marked, 266) \
+ x(sb_clean_entry_overrun, 267)
enum bch_sb_error_id {
#define x(t, n) BCH_FSCK_ERR_##t = n,
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index eff5ce1..5b8e621 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include "bcachefs.h"
+#include "btree_cache.h"
#include "disk_groups.h"
#include "opts.h"
#include "replicas.h"
@@ -426,3 +427,55 @@
bch2_write_super(c);
mutex_unlock(&c->sb_lock);
}
+
+/*
+ * Per member "range has btree nodes" bitmap:
+ *
+ * This is so that if we ever have to run the btree node scan to repair we don't
+ * have to scan full devices:
+ */
+
+bool bch2_dev_btree_bitmap_marked(struct bch_fs *c, struct bkey_s_c k)
+{
+ bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr)
+ if (!bch2_dev_btree_bitmap_marked_sectors(bch_dev_bkey_exists(c, ptr->dev),
+ ptr->offset, btree_sectors(c)))
+ return false;
+ return true;
+}
+
+static void __bch2_dev_btree_bitmap_mark(struct bch_sb_field_members_v2 *mi, unsigned dev,
+ u64 start, unsigned sectors)
+{
+ struct bch_member *m = __bch2_members_v2_get_mut(mi, dev);
+ u64 bitmap = le64_to_cpu(m->btree_allocated_bitmap);
+
+ u64 end = start + sectors;
+
+ int resize = ilog2(roundup_pow_of_two(end)) - (m->btree_bitmap_shift + 6);
+ if (resize > 0) {
+ u64 new_bitmap = 0;
+
+ for (unsigned i = 0; i < 64; i++)
+ if (bitmap & BIT_ULL(i))
+ new_bitmap |= BIT_ULL(i >> resize);
+ bitmap = new_bitmap;
+ m->btree_bitmap_shift += resize;
+ }
+
+ for (unsigned bit = start >> m->btree_bitmap_shift;
+ (u64) bit << m->btree_bitmap_shift < end;
+ bit++)
+ bitmap |= BIT_ULL(bit);
+
+ m->btree_allocated_bitmap = cpu_to_le64(bitmap);
+}
+
+void bch2_dev_btree_bitmap_mark(struct bch_fs *c, struct bkey_s_c k)
+{
+ lockdep_assert_held(&c->sb_lock);
+
+ struct bch_sb_field_members_v2 *mi = bch2_sb_field_get(c->disk_sb.sb, members_v2);
+ bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr)
+ __bch2_dev_btree_bitmap_mark(mi, ptr->dev, ptr->offset, btree_sectors(c));
+}
diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h
index be0a941..5efa64e 100644
--- a/fs/bcachefs/sb-members.h
+++ b/fs/bcachefs/sb-members.h
@@ -3,6 +3,7 @@
#define _BCACHEFS_SB_MEMBERS_H
#include "darray.h"
+#include "bkey_types.h"
extern char * const bch2_member_error_strs[];
@@ -220,6 +221,8 @@
: 1,
.freespace_initialized = BCH_MEMBER_FREESPACE_INITIALIZED(mi),
.valid = bch2_member_exists(mi),
+ .btree_bitmap_shift = mi->btree_bitmap_shift,
+ .btree_allocated_bitmap = le64_to_cpu(mi->btree_allocated_bitmap),
};
}
@@ -228,4 +231,22 @@
void bch2_dev_io_errors_to_text(struct printbuf *, struct bch_dev *);
void bch2_dev_errors_reset(struct bch_dev *);
+static inline bool bch2_dev_btree_bitmap_marked_sectors(struct bch_dev *ca, u64 start, unsigned sectors)
+{
+ u64 end = start + sectors;
+
+ if (end > 64ULL << ca->mi.btree_bitmap_shift)
+ return false;
+
+ for (unsigned bit = start >> ca->mi.btree_bitmap_shift;
+ (u64) bit << ca->mi.btree_bitmap_shift < end;
+ bit++)
+ if (!(ca->mi.btree_allocated_bitmap & BIT_ULL(bit)))
+ return false;
+ return true;
+}
+
+bool bch2_dev_btree_bitmap_marked(struct bch_fs *, struct bkey_s_c);
+void bch2_dev_btree_bitmap_mark(struct bch_fs *, struct bkey_s_c);
+
#endif /* _BCACHEFS_SB_MEMBERS_H */
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 0e806f0..544322d 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -125,6 +125,15 @@
return s->parent;
}
+static bool test_ancestor_bitmap(struct snapshot_table *t, u32 id, u32 ancestor)
+{
+ const struct snapshot_t *s = __snapshot_t(t, id);
+ if (!s)
+ return false;
+
+ return test_bit(ancestor - id - 1, s->is_ancestor);
+}
+
bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
{
bool ret;
@@ -140,13 +149,11 @@
while (id && id < ancestor - IS_ANCESTOR_BITMAP)
id = get_ancestor_below(t, id, ancestor);
- if (id && id < ancestor) {
- ret = test_bit(ancestor - id - 1, __snapshot_t(t, id)->is_ancestor);
+ ret = id && id < ancestor
+ ? test_ancestor_bitmap(t, id, ancestor)
+ : id == ancestor;
- EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor));
- } else {
- ret = id == ancestor;
- }
+ EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor));
out:
rcu_read_unlock();
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index 5eee055..08ea3db 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -700,8 +700,11 @@
return -ENOMEM;
sb->sb_name = kstrdup(path, GFP_KERNEL);
- if (!sb->sb_name)
- return -ENOMEM;
+ if (!sb->sb_name) {
+ ret = -ENOMEM;
+ prt_printf(&err, "error allocating memory for sb_name");
+ goto err;
+ }
#ifndef __KERNEL__
if (opt_get(*opts, direct_io) == false)
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index ed63018..88e214c 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -288,8 +288,13 @@
if (test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags) &&
!test_bit(BCH_FS_emergency_ro, &c->flags))
set_bit(BCH_FS_clean_shutdown, &c->flags);
+
bch2_fs_journal_stop(&c->journal);
+ bch_info(c, "%sshutdown complete, journal seq %llu",
+ test_bit(BCH_FS_clean_shutdown, &c->flags) ? "" : "un",
+ c->journal.seq_ondisk);
+
/*
* After stopping journal:
*/
@@ -539,6 +544,7 @@
bch2_find_btree_nodes_exit(&c->found_btree_nodes);
bch2_free_pending_node_rewrites(c);
+ bch2_fs_allocator_background_exit(c);
bch2_fs_sb_errors_exit(c);
bch2_fs_counters_exit(c);
bch2_fs_snapshots_exit(c);
diff --git a/fs/bcachefs/super_types.h b/fs/bcachefs/super_types.h
index ec784d97..11bcef1 100644
--- a/fs/bcachefs/super_types.h
+++ b/fs/bcachefs/super_types.h
@@ -37,6 +37,8 @@
u8 durability;
u8 freespace_initialized;
u8 valid;
+ u8 btree_bitmap_shift;
+ u64 btree_allocated_bitmap;
};
#endif /* _BCACHEFS_SUPER_TYPES_H */
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index c86a93a8..5be92fe 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -17,7 +17,6 @@
#include "btree_iter.h"
#include "btree_key_cache.h"
#include "btree_update.h"
-#include "btree_update_interior.h"
#include "btree_gc.h"
#include "buckets.h"
#include "clock.h"
@@ -26,6 +25,7 @@
#include "ec.h"
#include "inode.h"
#include "journal.h"
+#include "journal_reclaim.h"
#include "keylist.h"
#include "move.h"
#include "movinggc.h"
@@ -139,6 +139,7 @@
write_attribute(trigger_gc);
write_attribute(trigger_discards);
write_attribute(trigger_invalidates);
+write_attribute(trigger_journal_flush);
write_attribute(prune_cache);
write_attribute(btree_wakeup);
rw_attribute(btree_gc_periodic);
@@ -166,7 +167,6 @@
read_attribute(btree_cache_size);
read_attribute(compression_stats);
read_attribute(journal_debug);
-read_attribute(btree_updates);
read_attribute(btree_cache);
read_attribute(btree_key_cache);
read_attribute(stripes_heap);
@@ -415,9 +415,6 @@
if (attr == &sysfs_journal_debug)
bch2_journal_debug_to_text(out, &c->journal);
- if (attr == &sysfs_btree_updates)
- bch2_btree_updates_to_text(out, c);
-
if (attr == &sysfs_btree_cache)
bch2_btree_cache_to_text(out, c);
@@ -505,7 +502,7 @@
/* Debugging: */
- if (!test_bit(BCH_FS_rw, &c->flags))
+ if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_sysfs))
return -EROFS;
if (attr == &sysfs_prune_cache) {
@@ -538,6 +535,11 @@
if (attr == &sysfs_trigger_invalidates)
bch2_do_invalidates(c);
+ if (attr == &sysfs_trigger_journal_flush) {
+ bch2_journal_flush_all_pins(&c->journal);
+ bch2_journal_meta(&c->journal);
+ }
+
#ifdef CONFIG_BCACHEFS_TESTS
if (attr == &sysfs_perf_test) {
char *tmp = kstrdup(buf, GFP_KERNEL), *p = tmp;
@@ -558,6 +560,7 @@
size = ret;
}
#endif
+ bch2_write_ref_put(c, BCH_WRITE_REF_sysfs);
return size;
}
SYSFS_OPS(bch2_fs);
@@ -639,7 +642,6 @@
struct attribute *bch2_fs_internal_files[] = {
&sysfs_flags,
&sysfs_journal_debug,
- &sysfs_btree_updates,
&sysfs_btree_cache,
&sysfs_btree_key_cache,
&sysfs_new_stripes,
@@ -657,6 +659,7 @@
&sysfs_trigger_gc,
&sysfs_trigger_discards,
&sysfs_trigger_invalidates,
+ &sysfs_trigger_journal_flush,
&sysfs_prune_cache,
&sysfs_btree_wakeup,
diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c
index b3fe9fc..bfec656 100644
--- a/fs/bcachefs/tests.c
+++ b/fs/bcachefs/tests.c
@@ -672,7 +672,7 @@
bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, pos,
BTREE_ITER_INTENT);
- k = bch2_btree_iter_peek(&iter);
+ k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX));
ret = bkey_err(k);
if (ret)
goto err;
diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c
index 940db15..b1af7ac 100644
--- a/fs/bcachefs/thread_with_file.c
+++ b/fs/bcachefs/thread_with_file.c
@@ -294,16 +294,27 @@
return 0;
}
-int bch2_run_thread_with_stdio(struct thread_with_stdio *thr,
- const struct thread_with_stdio_ops *ops)
+void bch2_thread_with_stdio_init(struct thread_with_stdio *thr,
+ const struct thread_with_stdio_ops *ops)
{
stdio_buf_init(&thr->stdio.input);
stdio_buf_init(&thr->stdio.output);
thr->ops = ops;
+}
+int __bch2_run_thread_with_stdio(struct thread_with_stdio *thr)
+{
return bch2_run_thread_with_file(&thr->thr, &thread_with_stdio_fops, thread_with_stdio_fn);
}
+int bch2_run_thread_with_stdio(struct thread_with_stdio *thr,
+ const struct thread_with_stdio_ops *ops)
+{
+ bch2_thread_with_stdio_init(thr, ops);
+
+ return __bch2_run_thread_with_stdio(thr);
+}
+
int bch2_run_thread_with_stdout(struct thread_with_stdio *thr,
const struct thread_with_stdio_ops *ops)
{
diff --git a/fs/bcachefs/thread_with_file.h b/fs/bcachefs/thread_with_file.h
index af54ea8..1d63d14 100644
--- a/fs/bcachefs/thread_with_file.h
+++ b/fs/bcachefs/thread_with_file.h
@@ -63,6 +63,9 @@
const struct thread_with_stdio_ops *ops;
};
+void bch2_thread_with_stdio_init(struct thread_with_stdio *,
+ const struct thread_with_stdio_ops *);
+int __bch2_run_thread_with_stdio(struct thread_with_stdio *);
int bch2_run_thread_with_stdio(struct thread_with_stdio *,
const struct thread_with_stdio_ops *);
int bch2_run_thread_with_stdout(struct thread_with_stdio *,
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index b7e7c29..5cf885b 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -788,6 +788,14 @@
#endif
+static inline void mod_bit(long nr, volatile unsigned long *addr, bool v)
+{
+ if (v)
+ set_bit(nr, addr);
+ else
+ clear_bit(nr, addr);
+}
+
static inline void __set_bit_le64(size_t bit, __le64 *addr)
{
addr[bit / 64] |= cpu_to_le64(BIT_ULL(bit % 64));
@@ -795,7 +803,7 @@
static inline void __clear_bit_le64(size_t bit, __le64 *addr)
{
- addr[bit / 64] &= !cpu_to_le64(BIT_ULL(bit % 64));
+ addr[bit / 64] &= ~cpu_to_le64(BIT_ULL(bit % 64));
}
static inline bool test_bit_le64(size_t bit, __le64 *addr)
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index c1e6a5b..58110c9 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -2776,20 +2776,14 @@
size_t alloc_bytes;
alloc_bytes = max_t(size_t, total_bytes, sizeof(*data));
- data = kvmalloc(alloc_bytes, GFP_KERNEL);
+ data = kvzalloc(alloc_bytes, GFP_KERNEL);
if (!data)
return ERR_PTR(-ENOMEM);
- if (total_bytes >= sizeof(*data)) {
+ if (total_bytes >= sizeof(*data))
data->bytes_left = total_bytes - sizeof(*data);
- data->bytes_missing = 0;
- } else {
+ else
data->bytes_missing = sizeof(*data) - total_bytes;
- data->bytes_left = 0;
- }
-
- data->elem_cnt = 0;
- data->elem_missed = 0;
return data;
}
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index dd6f566..121ab89 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1133,6 +1133,9 @@
if (ret)
return ret;
+ ret = btrfs_record_root_in_trans(trans, node->root);
+ if (ret)
+ return ret;
ret = btrfs_update_delayed_inode(trans, node->root, path, node);
return ret;
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index beedd6e..257d044 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3464,6 +3464,14 @@
if (root_id != BTRFS_TREE_LOG_OBJECTID) {
struct btrfs_ref generic_ref = { 0 };
+ /*
+ * Assert that the extent buffer is not cleared due to
+ * EXTENT_BUFFER_ZONED_ZEROOUT. Please refer
+ * btrfs_clear_buffer_dirty() and btree_csum_one_bio() for
+ * detail.
+ */
+ ASSERT(btrfs_header_bytenr(buf) != 0);
+
btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
buf->start, buf->len, parent,
btrfs_header_owner(buf));
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 61594ea..2776112 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -681,31 +681,21 @@
int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array,
gfp_t extra_gfp)
{
+ const gfp_t gfp = GFP_NOFS | extra_gfp;
unsigned int allocated;
for (allocated = 0; allocated < nr_pages;) {
unsigned int last = allocated;
- allocated = alloc_pages_bulk_array(GFP_NOFS | extra_gfp,
- nr_pages, page_array);
-
- if (allocated == nr_pages)
- return 0;
-
- /*
- * During this iteration, no page could be allocated, even
- * though alloc_pages_bulk_array() falls back to alloc_page()
- * if it could not bulk-allocate. So we must be out of memory.
- */
- if (allocated == last) {
+ allocated = alloc_pages_bulk_array(gfp, nr_pages, page_array);
+ if (unlikely(allocated == last)) {
+ /* No progress, fail and do cleanup. */
for (int i = 0; i < allocated; i++) {
__free_page(page_array[i]);
page_array[i] = NULL;
}
return -ENOMEM;
}
-
- memalloc_retry_wait(GFP_NOFS);
}
return 0;
}
@@ -4154,7 +4144,7 @@
* The actual zeroout of the buffer will happen later in
* btree_csum_one_bio.
*/
- if (btrfs_is_zoned(fs_info)) {
+ if (btrfs_is_zoned(fs_info) && test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
set_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags);
return;
}
@@ -4193,6 +4183,7 @@
num_folios = num_extent_folios(eb);
WARN_ON(atomic_read(&eb->refs) == 0);
WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
+ WARN_ON(test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags));
if (!was_dirty) {
bool subpage = eb->fs_info->nodesize < PAGE_SIZE;
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 445f771..24a0482 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -817,7 +817,7 @@
split->block_len = em->block_len;
split->orig_start = em->orig_start;
} else {
- const u64 diff = start + len - em->start;
+ const u64 diff = end - em->start;
split->block_len = split->len;
split->block_start += diff;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3770153..7fed887 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1145,13 +1145,13 @@
0, *alloc_hint, &ins, 1, 1);
if (ret) {
/*
- * Here we used to try again by going back to non-compressed
- * path for ENOSPC. But we can't reserve space even for
- * compressed size, how could it work for uncompressed size
- * which requires larger size? So here we directly go error
- * path.
+ * We can't reserve contiguous space for the compressed size.
+ * Unlikely, but it's possible that we could have enough
+ * non-contiguous space for the uncompressed size instead. So
+ * fall back to uncompressed.
*/
- goto out_free;
+ submit_uncompressed_range(inode, async_extent, locked_page);
+ goto done;
}
/* Here we're doing allocation and writeback of the compressed pages */
@@ -1203,7 +1203,6 @@
out_free_reserve:
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
-out_free:
mapping_set_error(inode->vfs_inode.i_mapping, -EIO);
extent_clear_unlock_delalloc(inode, start, end,
NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
@@ -2533,7 +2532,7 @@
*/
if (bits & EXTENT_CLEAR_META_RESV &&
root != fs_info->tree_root)
- btrfs_delalloc_release_metadata(inode, len, false);
+ btrfs_delalloc_release_metadata(inode, len, true);
/* For sanity tests. */
if (btrfs_is_testing(fs_info))
@@ -4503,6 +4502,7 @@
struct btrfs_trans_handle *trans;
struct btrfs_block_rsv block_rsv;
u64 root_flags;
+ u64 qgroup_reserved = 0;
int ret;
down_write(&fs_info->subvol_sem);
@@ -4547,12 +4547,20 @@
ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
if (ret)
goto out_undead;
+ qgroup_reserved = block_rsv.qgroup_rsv_reserved;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out_release;
}
+ ret = btrfs_record_root_in_trans(trans, root);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_end_trans;
+ }
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+ qgroup_reserved = 0;
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
@@ -4611,7 +4619,9 @@
ret = btrfs_end_transaction(trans);
inode->i_flags |= S_DEAD;
out_release:
- btrfs_subvolume_release_metadata(root, &block_rsv);
+ btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
+ if (qgroup_reserved)
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
out_undead:
if (ret) {
spin_lock(&dest->root_item_lock);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 294e31e..0493272 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -613,6 +613,7 @@
int ret;
dev_t anon_dev;
u64 objectid;
+ u64 qgroup_reserved = 0;
root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
if (!root_item)
@@ -650,13 +651,18 @@
trans_num_items, false);
if (ret)
goto out_new_inode_args;
+ qgroup_reserved = block_rsv.qgroup_rsv_reserved;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- btrfs_subvolume_release_metadata(root, &block_rsv);
- goto out_new_inode_args;
+ goto out_release_rsv;
}
+ ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root);
+ if (ret)
+ goto out;
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+ qgroup_reserved = 0;
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
/* Tree log can't currently deal with an inode which is a new root. */
@@ -767,9 +773,11 @@
out:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
- btrfs_subvolume_release_metadata(root, &block_rsv);
-
btrfs_end_transaction(trans);
+out_release_rsv:
+ btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
+ if (qgroup_reserved)
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
out_new_inode_args:
btrfs_new_inode_args_destroy(&new_inode_args);
out_inode:
@@ -791,6 +799,8 @@
struct btrfs_pending_snapshot *pending_snapshot;
unsigned int trans_num_items;
struct btrfs_trans_handle *trans;
+ struct btrfs_block_rsv *block_rsv;
+ u64 qgroup_reserved = 0;
int ret;
/* We do not support snapshotting right now. */
@@ -827,19 +837,19 @@
goto free_pending;
}
- btrfs_init_block_rsv(&pending_snapshot->block_rsv,
- BTRFS_BLOCK_RSV_TEMP);
+ block_rsv = &pending_snapshot->block_rsv;
+ btrfs_init_block_rsv(block_rsv, BTRFS_BLOCK_RSV_TEMP);
/*
* 1 to add dir item
* 1 to add dir index
* 1 to update parent inode item
*/
trans_num_items = create_subvol_num_items(inherit) + 3;
- ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
- &pending_snapshot->block_rsv,
+ ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, block_rsv,
trans_num_items, false);
if (ret)
goto free_pending;
+ qgroup_reserved = block_rsv->qgroup_rsv_reserved;
pending_snapshot->dentry = dentry;
pending_snapshot->root = root;
@@ -852,6 +862,13 @@
ret = PTR_ERR(trans);
goto fail;
}
+ ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root);
+ if (ret) {
+ btrfs_end_transaction(trans);
+ goto fail;
+ }
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+ qgroup_reserved = 0;
trans->pending_snapshot = pending_snapshot;
@@ -881,7 +898,9 @@
if (ret && pending_snapshot->snap)
pending_snapshot->snap->anon_dev = 0;
btrfs_put_root(pending_snapshot->snap);
- btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv);
+ btrfs_block_rsv_release(fs_info, block_rsv, (u64)-1, NULL);
+ if (qgroup_reserved)
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
free_pending:
if (pending_snapshot->anon_dev)
free_anon_bdev(pending_snapshot->anon_dev);
@@ -3739,15 +3758,43 @@
goto drop_write;
}
- down_write(&fs_info->subvol_sem);
-
switch (sa->cmd) {
case BTRFS_QUOTA_CTL_ENABLE:
case BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA:
+ down_write(&fs_info->subvol_sem);
ret = btrfs_quota_enable(fs_info, sa);
+ up_write(&fs_info->subvol_sem);
break;
case BTRFS_QUOTA_CTL_DISABLE:
+ /*
+ * Lock the cleaner mutex to prevent races with concurrent
+ * relocation, because relocation may be building backrefs for
+ * blocks of the quota root while we are deleting the root. This
+ * is like dropping fs roots of deleted snapshots/subvolumes, we
+ * need the same protection.
+ *
+ * This also prevents races between concurrent tasks trying to
+ * disable quotas, because we will unlock and relock
+ * qgroup_ioctl_lock across BTRFS_FS_QUOTA_ENABLED changes.
+ *
+ * We take this here because we have the dependency of
+ *
+ * inode_lock -> subvol_sem
+ *
+ * because of rename. With relocation we can prealloc extents,
+ * so that makes the dependency chain
+ *
+ * cleaner_mutex -> inode_lock -> subvol_sem
+ *
+ * so we must take the cleaner_mutex here before we take the
+ * subvol_sem. The deadlock can't actually happen, but this
+ * quiets lockdep.
+ */
+ mutex_lock(&fs_info->cleaner_mutex);
+ down_write(&fs_info->subvol_sem);
ret = btrfs_quota_disable(fs_info);
+ up_write(&fs_info->subvol_sem);
+ mutex_unlock(&fs_info->cleaner_mutex);
break;
default:
ret = -EINVAL;
@@ -3755,7 +3802,6 @@
}
kfree(sa);
- up_write(&fs_info->subvol_sem);
drop_write:
mnt_drop_write_file(file);
return ret;
diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c
index c96dd66..210d9c8 100644
--- a/fs/btrfs/messages.c
+++ b/fs/btrfs/messages.c
@@ -7,7 +7,7 @@
#ifdef CONFIG_PRINTK
-#define STATE_STRING_PREFACE ": state "
+#define STATE_STRING_PREFACE " state "
#define STATE_STRING_BUF_LEN (sizeof(STATE_STRING_PREFACE) + BTRFS_FS_STATE_COUNT + 1)
/*
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index b749ba4..c2a42bc 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -1188,6 +1188,7 @@
ordered->disk_bytenr += len;
ordered->num_bytes -= len;
ordered->disk_num_bytes -= len;
+ ordered->ram_bytes -= len;
if (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags)) {
ASSERT(ordered->bytes_left == 0);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5f90f06..364acc9 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1342,16 +1342,10 @@
lockdep_assert_held_write(&fs_info->subvol_sem);
/*
- * Lock the cleaner mutex to prevent races with concurrent relocation,
- * because relocation may be building backrefs for blocks of the quota
- * root while we are deleting the root. This is like dropping fs roots
- * of deleted snapshots/subvolumes, we need the same protection.
- *
- * This also prevents races between concurrent tasks trying to disable
- * quotas, because we will unlock and relock qgroup_ioctl_lock across
- * BTRFS_FS_QUOTA_ENABLED changes.
+ * Relocation will mess with backrefs, so make sure we have the
+ * cleaner_mutex held to protect us from relocate.
*/
- mutex_lock(&fs_info->cleaner_mutex);
+ lockdep_assert_held(&fs_info->cleaner_mutex);
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (!fs_info->quota_root)
@@ -1373,9 +1367,13 @@
clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
btrfs_qgroup_wait_for_completion(fs_info, false);
+ /*
+ * We have nothing held here and no trans handle, just return the error
+ * if there is one.
+ */
ret = flush_reservations(fs_info);
if (ret)
- goto out_unlock_cleaner;
+ return ret;
/*
* 1 For the root item
@@ -1439,9 +1437,6 @@
btrfs_end_transaction(trans);
else if (trans)
ret = btrfs_commit_transaction(trans);
-out_unlock_cleaner:
- mutex_unlock(&fs_info->cleaner_mutex);
-
return ret;
}
@@ -4495,6 +4490,8 @@
BTRFS_QGROUP_RSV_META_PREALLOC);
trace_qgroup_meta_convert(root, num_bytes);
qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes);
+ if (!sb_rdonly(fs_info->sb))
+ add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS);
}
/*
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 4bb538a..7007f9e 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -548,13 +548,3 @@
}
return ret;
}
-
-void btrfs_subvolume_release_metadata(struct btrfs_root *root,
- struct btrfs_block_rsv *rsv)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- u64 qgroup_to_release;
-
- btrfs_block_rsv_release(fs_info, rsv, (u64)-1, &qgroup_to_release);
- btrfs_qgroup_convert_reserved_meta(root, qgroup_to_release);
-}
diff --git a/fs/btrfs/root-tree.h b/fs/btrfs/root-tree.h
index 6f929cf..8f5739e 100644
--- a/fs/btrfs/root-tree.h
+++ b/fs/btrfs/root-tree.h
@@ -18,8 +18,6 @@
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int nitems, bool use_global_rsv);
-void btrfs_subvolume_release_metadata(struct btrfs_root *root,
- struct btrfs_block_rsv *rsv);
int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
u64 ref_id, u64 dirid, u64 sequence,
const struct fscrypt_str *name);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index fa25004..4b22cfe 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1012,6 +1012,7 @@
struct btrfs_fs_info *fs_info = sctx->fs_info;
int num_copies = btrfs_num_copies(fs_info, stripe->bg->start,
stripe->bg->length);
+ unsigned long repaired;
int mirror;
int i;
@@ -1078,16 +1079,15 @@
* Submit the repaired sectors. For zoned case, we cannot do repair
* in-place, but queue the bg to be relocated.
*/
- if (btrfs_is_zoned(fs_info)) {
- if (!bitmap_empty(&stripe->error_bitmap, stripe->nr_sectors))
+ bitmap_andnot(&repaired, &stripe->init_error_bitmap, &stripe->error_bitmap,
+ stripe->nr_sectors);
+ if (!sctx->readonly && !bitmap_empty(&repaired, stripe->nr_sectors)) {
+ if (btrfs_is_zoned(fs_info)) {
btrfs_repair_one_zone(fs_info, sctx->stripes[0].bg->start);
- } else if (!sctx->readonly) {
- unsigned long repaired;
-
- bitmap_andnot(&repaired, &stripe->init_error_bitmap,
- &stripe->error_bitmap, stripe->nr_sectors);
- scrub_write_sectors(sctx, stripe, repaired, false);
- wait_scrub_stripe_io(stripe);
+ } else {
+ scrub_write_sectors(sctx, stripe, repaired, false);
+ wait_scrub_stripe_io(stripe);
+ }
}
scrub_stripe_report_errors(sctx, stripe);
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index 253cce7..47b5d30 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -847,6 +847,11 @@
goto out;
}
+ if (em->block_start != SZ_32K + SZ_4K) {
+ test_err("em->block_start is %llu, expected 36K", em->block_start);
+ goto out;
+ }
+
free_extent_map(em);
read_lock(&em_tree->lock);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 46e8426..85f359e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -745,14 +745,6 @@
h->reloc_reserved = reloc_reserved;
}
- /*
- * Now that we have found a transaction to be a part of, convert the
- * qgroup reservation from prealloc to pertrans. A different transaction
- * can't race in and free our pertrans out from under us.
- */
- if (qgroup_reserved)
- btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
-
got_it:
if (!current->journal_info)
current->journal_info = h;
@@ -786,8 +778,15 @@
* not just freed.
*/
btrfs_end_transaction(h);
- return ERR_PTR(ret);
+ goto reserve_fail;
}
+ /*
+ * Now that we have found a transaction to be a part of, convert the
+ * qgroup reservation from prealloc to pertrans. A different transaction
+ * can't race in and free our pertrans out from under us.
+ */
+ if (qgroup_reserved)
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
return h;
@@ -1495,6 +1494,7 @@
radix_tree_tag_clear(&fs_info->fs_roots_radix,
(unsigned long)root->root_key.objectid,
BTRFS_ROOT_TRANS_TAG);
+ btrfs_qgroup_free_meta_all_pertrans(root);
spin_unlock(&fs_info->fs_roots_radix_lock);
btrfs_free_log(trans, root);
@@ -1519,7 +1519,6 @@
if (ret2)
return ret2;
spin_lock(&fs_info->fs_roots_radix_lock);
- btrfs_qgroup_free_meta_all_pertrans(root);
}
}
spin_unlock(&fs_info->fs_roots_radix_lock);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f15591f..ef6bd2f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3455,6 +3455,7 @@
* alignment and size).
*/
ret = -EUCLEAN;
+ mutex_unlock(&fs_info->reclaim_bgs_lock);
goto error;
}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1340d77..ee9caf7 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -795,8 +795,10 @@
ihold(inode);
if (wbc->sync_mode == WB_SYNC_NONE &&
- ceph_inode_to_fs_client(inode)->write_congested)
+ ceph_inode_to_fs_client(inode)->write_congested) {
+ redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
+ }
wait_on_page_fscache(page);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 55051ad..c4941ba 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -4783,13 +4783,13 @@
doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode,
ceph_vinop(inode));
- spin_lock(&mdsc->cap_unlink_delay_lock);
+ spin_lock(&mdsc->cap_delay_lock);
ci->i_ceph_flags |= CEPH_I_FLUSH;
if (!list_empty(&ci->i_cap_delay_list))
list_del_init(&ci->i_cap_delay_list);
list_add_tail(&ci->i_cap_delay_list,
&mdsc->cap_unlink_delay_list);
- spin_unlock(&mdsc->cap_unlink_delay_lock);
+ spin_unlock(&mdsc->cap_delay_lock);
/*
* Fire the work immediately, because the MDS maybe
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 3ab9c26..360b686 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2504,7 +2504,7 @@
struct ceph_client *cl = mdsc->fsc->client;
doutc(cl, "begin\n");
- spin_lock(&mdsc->cap_unlink_delay_lock);
+ spin_lock(&mdsc->cap_delay_lock);
while (!list_empty(&mdsc->cap_unlink_delay_list)) {
struct ceph_inode_info *ci;
struct inode *inode;
@@ -2516,15 +2516,15 @@
inode = igrab(&ci->netfs.inode);
if (inode) {
- spin_unlock(&mdsc->cap_unlink_delay_lock);
+ spin_unlock(&mdsc->cap_delay_lock);
doutc(cl, "on %p %llx.%llx\n", inode,
ceph_vinop(inode));
ceph_check_caps(ci, CHECK_CAPS_FLUSH);
iput(inode);
- spin_lock(&mdsc->cap_unlink_delay_lock);
+ spin_lock(&mdsc->cap_delay_lock);
}
}
- spin_unlock(&mdsc->cap_unlink_delay_lock);
+ spin_unlock(&mdsc->cap_delay_lock);
doutc(cl, "done\n");
}
@@ -5404,7 +5404,6 @@
INIT_LIST_HEAD(&mdsc->cap_wait_list);
spin_lock_init(&mdsc->cap_delay_lock);
INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list);
- spin_lock_init(&mdsc->cap_unlink_delay_lock);
INIT_LIST_HEAD(&mdsc->snap_flush_list);
spin_lock_init(&mdsc->snap_flush_lock);
mdsc->last_cap_flush_tid = 1;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 03f8ff0..b88e804 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -461,9 +461,8 @@
struct delayed_work delayed_work; /* delayed work */
unsigned long last_renew_caps; /* last time we renewed our caps */
struct list_head cap_delay_list; /* caps with delayed release */
- spinlock_t cap_delay_lock; /* protects cap_delay_list */
struct list_head cap_unlink_delay_list; /* caps with delayed release for unlink */
- spinlock_t cap_unlink_delay_lock; /* protects cap_unlink_delay_list */
+ spinlock_t cap_delay_lock; /* protects cap_delay_list and cap_unlink_delay_list */
struct list_head snap_flush_list; /* cap_snaps ready to flush */
spinlock_t snap_flush_lock;
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 8aff1a7..62da538 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -151,7 +151,7 @@
if (WARN_ON(len == 0))
source = NETFS_INVALID_READ;
if (source != NETFS_READ_FROM_CACHE) {
- erofs_err(NULL, "prepare_read failed (source %d)", source);
+ erofs_err(NULL, "prepare_ondemand_read failed (source %d)", source);
return -EIO;
}
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 39c6711..d28ccfc 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -84,13 +84,6 @@
bool flatdev;
};
-struct erofs_fs_context {
- struct erofs_mount_opts opt;
- struct erofs_dev_context *devs;
- char *fsid;
- char *domain_id;
-};
-
/* all filesystem-wide lz4 configurations */
struct erofs_sb_lz4_info {
/* # of pages needed for EROFS lz4 rolling decompression */
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index c0eb139..30b49b2 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -370,18 +370,18 @@
return ret;
}
-static void erofs_default_options(struct erofs_fs_context *ctx)
+static void erofs_default_options(struct erofs_sb_info *sbi)
{
#ifdef CONFIG_EROFS_FS_ZIP
- ctx->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND;
- ctx->opt.max_sync_decompress_pages = 3;
- ctx->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO;
+ sbi->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND;
+ sbi->opt.max_sync_decompress_pages = 3;
+ sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO;
#endif
#ifdef CONFIG_EROFS_FS_XATTR
- set_opt(&ctx->opt, XATTR_USER);
+ set_opt(&sbi->opt, XATTR_USER);
#endif
#ifdef CONFIG_EROFS_FS_POSIX_ACL
- set_opt(&ctx->opt, POSIX_ACL);
+ set_opt(&sbi->opt, POSIX_ACL);
#endif
}
@@ -426,16 +426,16 @@
static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode)
{
#ifdef CONFIG_FS_DAX
- struct erofs_fs_context *ctx = fc->fs_private;
+ struct erofs_sb_info *sbi = fc->s_fs_info;
switch (mode) {
case EROFS_MOUNT_DAX_ALWAYS:
- set_opt(&ctx->opt, DAX_ALWAYS);
- clear_opt(&ctx->opt, DAX_NEVER);
+ set_opt(&sbi->opt, DAX_ALWAYS);
+ clear_opt(&sbi->opt, DAX_NEVER);
return true;
case EROFS_MOUNT_DAX_NEVER:
- set_opt(&ctx->opt, DAX_NEVER);
- clear_opt(&ctx->opt, DAX_ALWAYS);
+ set_opt(&sbi->opt, DAX_NEVER);
+ clear_opt(&sbi->opt, DAX_ALWAYS);
return true;
default:
DBG_BUGON(1);
@@ -450,7 +450,7 @@
static int erofs_fc_parse_param(struct fs_context *fc,
struct fs_parameter *param)
{
- struct erofs_fs_context *ctx = fc->fs_private;
+ struct erofs_sb_info *sbi = fc->s_fs_info;
struct fs_parse_result result;
struct erofs_device_info *dif;
int opt, ret;
@@ -463,9 +463,9 @@
case Opt_user_xattr:
#ifdef CONFIG_EROFS_FS_XATTR
if (result.boolean)
- set_opt(&ctx->opt, XATTR_USER);
+ set_opt(&sbi->opt, XATTR_USER);
else
- clear_opt(&ctx->opt, XATTR_USER);
+ clear_opt(&sbi->opt, XATTR_USER);
#else
errorfc(fc, "{,no}user_xattr options not supported");
#endif
@@ -473,16 +473,16 @@
case Opt_acl:
#ifdef CONFIG_EROFS_FS_POSIX_ACL
if (result.boolean)
- set_opt(&ctx->opt, POSIX_ACL);
+ set_opt(&sbi->opt, POSIX_ACL);
else
- clear_opt(&ctx->opt, POSIX_ACL);
+ clear_opt(&sbi->opt, POSIX_ACL);
#else
errorfc(fc, "{,no}acl options not supported");
#endif
break;
case Opt_cache_strategy:
#ifdef CONFIG_EROFS_FS_ZIP
- ctx->opt.cache_strategy = result.uint_32;
+ sbi->opt.cache_strategy = result.uint_32;
#else
errorfc(fc, "compression not supported, cache_strategy ignored");
#endif
@@ -504,27 +504,27 @@
kfree(dif);
return -ENOMEM;
}
- down_write(&ctx->devs->rwsem);
- ret = idr_alloc(&ctx->devs->tree, dif, 0, 0, GFP_KERNEL);
- up_write(&ctx->devs->rwsem);
+ down_write(&sbi->devs->rwsem);
+ ret = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL);
+ up_write(&sbi->devs->rwsem);
if (ret < 0) {
kfree(dif->path);
kfree(dif);
return ret;
}
- ++ctx->devs->extra_devices;
+ ++sbi->devs->extra_devices;
break;
#ifdef CONFIG_EROFS_FS_ONDEMAND
case Opt_fsid:
- kfree(ctx->fsid);
- ctx->fsid = kstrdup(param->string, GFP_KERNEL);
- if (!ctx->fsid)
+ kfree(sbi->fsid);
+ sbi->fsid = kstrdup(param->string, GFP_KERNEL);
+ if (!sbi->fsid)
return -ENOMEM;
break;
case Opt_domain_id:
- kfree(ctx->domain_id);
- ctx->domain_id = kstrdup(param->string, GFP_KERNEL);
- if (!ctx->domain_id)
+ kfree(sbi->domain_id);
+ sbi->domain_id = kstrdup(param->string, GFP_KERNEL);
+ if (!sbi->domain_id)
return -ENOMEM;
break;
#else
@@ -581,8 +581,7 @@
static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;
- struct erofs_sb_info *sbi;
- struct erofs_fs_context *ctx = fc->fs_private;
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
int err;
sb->s_magic = EROFS_SUPER_MAGIC;
@@ -590,19 +589,6 @@
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_op = &erofs_sops;
- sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
- if (!sbi)
- return -ENOMEM;
-
- sb->s_fs_info = sbi;
- sbi->opt = ctx->opt;
- sbi->devs = ctx->devs;
- ctx->devs = NULL;
- sbi->fsid = ctx->fsid;
- ctx->fsid = NULL;
- sbi->domain_id = ctx->domain_id;
- ctx->domain_id = NULL;
-
sbi->blkszbits = PAGE_SHIFT;
if (erofs_is_fscache_mode(sb)) {
sb->s_blocksize = PAGE_SIZE;
@@ -706,9 +692,9 @@
static int erofs_fc_get_tree(struct fs_context *fc)
{
- struct erofs_fs_context *ctx = fc->fs_private;
+ struct erofs_sb_info *sbi = fc->s_fs_info;
- if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && ctx->fsid)
+ if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid)
return get_tree_nodev(fc, erofs_fc_fill_super);
return get_tree_bdev(fc, erofs_fc_fill_super);
@@ -718,19 +704,19 @@
{
struct super_block *sb = fc->root->d_sb;
struct erofs_sb_info *sbi = EROFS_SB(sb);
- struct erofs_fs_context *ctx = fc->fs_private;
+ struct erofs_sb_info *new_sbi = fc->s_fs_info;
DBG_BUGON(!sb_rdonly(sb));
- if (ctx->fsid || ctx->domain_id)
+ if (new_sbi->fsid || new_sbi->domain_id)
erofs_info(sb, "ignoring reconfiguration for fsid|domain_id.");
- if (test_opt(&ctx->opt, POSIX_ACL))
+ if (test_opt(&new_sbi->opt, POSIX_ACL))
fc->sb_flags |= SB_POSIXACL;
else
fc->sb_flags &= ~SB_POSIXACL;
- sbi->opt = ctx->opt;
+ sbi->opt = new_sbi->opt;
fc->sb_flags |= SB_RDONLY;
return 0;
@@ -761,12 +747,15 @@
static void erofs_fc_free(struct fs_context *fc)
{
- struct erofs_fs_context *ctx = fc->fs_private;
+ struct erofs_sb_info *sbi = fc->s_fs_info;
- erofs_free_dev_context(ctx->devs);
- kfree(ctx->fsid);
- kfree(ctx->domain_id);
- kfree(ctx);
+ if (!sbi)
+ return;
+
+ erofs_free_dev_context(sbi->devs);
+ kfree(sbi->fsid);
+ kfree(sbi->domain_id);
+ kfree(sbi);
}
static const struct fs_context_operations erofs_context_ops = {
@@ -778,38 +767,35 @@
static int erofs_init_fs_context(struct fs_context *fc)
{
- struct erofs_fs_context *ctx;
+ struct erofs_sb_info *sbi;
- ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
- if (!ctx)
+ sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+ if (!sbi)
return -ENOMEM;
- ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL);
- if (!ctx->devs) {
- kfree(ctx);
+
+ sbi->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL);
+ if (!sbi->devs) {
+ kfree(sbi);
return -ENOMEM;
}
- fc->fs_private = ctx;
+ fc->s_fs_info = sbi;
- idr_init(&ctx->devs->tree);
- init_rwsem(&ctx->devs->rwsem);
- erofs_default_options(ctx);
+ idr_init(&sbi->devs->tree);
+ init_rwsem(&sbi->devs->rwsem);
+ erofs_default_options(sbi);
fc->ops = &erofs_context_ops;
return 0;
}
static void erofs_kill_sb(struct super_block *sb)
{
- struct erofs_sb_info *sbi;
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
- if (erofs_is_fscache_mode(sb))
+ if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid)
kill_anon_super(sb);
else
kill_block_super(sb);
- sbi = EROFS_SB(sb);
- if (!sbi)
- return;
-
erofs_free_dev_context(sbi->devs);
fs_put_dax(sbi->dax_dev, NULL);
erofs_fscache_unregister_fs(sb);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 882b89e..f53ca4f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -980,6 +980,34 @@
}
/*
+ * The ffd.file pointer may be in the process of being torn down due to
+ * being closed, but we may not have finished eventpoll_release() yet.
+ *
+ * Normally, even with the atomic_long_inc_not_zero, the file may have
+ * been free'd and then gotten re-allocated to something else (since
+ * files are not RCU-delayed, they are SLAB_TYPESAFE_BY_RCU).
+ *
+ * But for epoll, users hold the ep->mtx mutex, and as such any file in
+ * the process of being free'd will block in eventpoll_release_file()
+ * and thus the underlying file allocation will not be free'd, and the
+ * file re-use cannot happen.
+ *
+ * For the same reason we can avoid a rcu_read_lock() around the
+ * operation - 'ffd.file' cannot go away even if the refcount has
+ * reached zero (but we must still not call out to ->poll() functions
+ * etc).
+ */
+static struct file *epi_fget(const struct epitem *epi)
+{
+ struct file *file;
+
+ file = epi->ffd.file;
+ if (!atomic_long_inc_not_zero(&file->f_count))
+ file = NULL;
+ return file;
+}
+
+/*
* Differs from ep_eventpoll_poll() in that internal callers already have
* the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
* is correctly annotated.
@@ -987,14 +1015,22 @@
static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
int depth)
{
- struct file *file = epi->ffd.file;
+ struct file *file = epi_fget(epi);
__poll_t res;
+ /*
+ * We could return EPOLLERR | EPOLLHUP or something, but let's
+ * treat this more as "file doesn't exist, poll didn't happen".
+ */
+ if (!file)
+ return 0;
+
pt->_key = epi->event.events;
if (!is_file_epoll(file))
res = vfs_poll(file, pt);
else
res = __ep_eventpoll_poll(file, pt, depth);
+ fput(file);
return res & epi->event.events;
}
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index b6cad10..0b2da7b 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -310,6 +310,10 @@
/**
* cuse_process_init_reply - finish initializing CUSE channel
*
+ * @fm: The fuse mount information containing the CUSE connection.
+ * @args: The arguments passed to the init reply.
+ * @error: The error code signifying if any error occurred during the process.
+ *
* This function creates the character device and sets up all the
* required data structures for it. Please read the comment at the
* top of this file for high level overview.
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 4a6df59..2b0d478 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1321,6 +1321,7 @@
err = fuse_do_statx(inode, file, stat);
if (err == -ENOSYS) {
fc->no_statx = 1;
+ err = 0;
goto retry;
}
} else {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index a56e7bf..b57ce415 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1362,7 +1362,7 @@
bool *exclusive)
{
struct inode *inode = file_inode(iocb->ki_filp);
- struct fuse_file *ff = iocb->ki_filp->private_data;
+ struct fuse_inode *fi = get_fuse_inode(inode);
*exclusive = fuse_dio_wr_exclusive_lock(iocb, from);
if (*exclusive) {
@@ -1377,7 +1377,7 @@
* have raced, so check it again.
*/
if (fuse_io_past_eof(iocb, from) ||
- fuse_file_uncached_io_start(inode, ff, NULL) != 0) {
+ fuse_inode_uncached_io_start(fi, NULL) != 0) {
inode_unlock_shared(inode);
inode_lock(inode);
*exclusive = true;
@@ -1388,13 +1388,13 @@
static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive)
{
struct inode *inode = file_inode(iocb->ki_filp);
- struct fuse_file *ff = iocb->ki_filp->private_data;
+ struct fuse_inode *fi = get_fuse_inode(inode);
if (exclusive) {
inode_unlock(inode);
} else {
/* Allow opens in caching mode after last parallel dio end */
- fuse_file_uncached_io_end(inode, ff);
+ fuse_inode_uncached_io_end(fi);
inode_unlock_shared(inode);
}
}
@@ -2574,8 +2574,10 @@
* First mmap of direct_io file enters caching inode io mode.
* Also waits for parallel dio writers to go into serial mode
* (exclusive instead of shared lock).
+ * After first mmap, the inode stays in caching io mode until
+ * the direct_io file release.
*/
- rc = fuse_file_cached_io_start(inode, ff);
+ rc = fuse_file_cached_io_open(inode, ff);
if (rc)
return rc;
}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index b24084b..f239196 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1394,9 +1394,10 @@
struct dentry *dentry, struct fileattr *fa);
/* iomode.c */
-int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff);
-int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb);
-void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff);
+int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff);
+int fuse_inode_uncached_io_start(struct fuse_inode *fi,
+ struct fuse_backing *fb);
+void fuse_inode_uncached_io_end(struct fuse_inode *fi);
int fuse_file_io_open(struct file *file, struct inode *inode);
void fuse_file_io_release(struct fuse_file *ff, struct inode *inode);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 3a5d888..99e44ea 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -175,6 +175,7 @@
}
}
if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) {
+ WARN_ON(fi->iocachectr != 0);
WARN_ON(!list_empty(&fi->write_files));
WARN_ON(!list_empty(&fi->queued_writes));
}
diff --git a/fs/fuse/iomode.c b/fs/fuse/iomode.c
index c653ddc..c99e285 100644
--- a/fs/fuse/iomode.c
+++ b/fs/fuse/iomode.c
@@ -21,12 +21,13 @@
}
/*
- * Start cached io mode.
+ * Called on cached file open() and on first mmap() of direct_io file.
+ * Takes cached_io inode mode reference to be dropped on file release.
*
* Blocks new parallel dio writes and waits for the in-progress parallel dio
* writes to complete.
*/
-int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff)
+int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff)
{
struct fuse_inode *fi = get_fuse_inode(inode);
@@ -67,10 +68,9 @@
return 0;
}
-static void fuse_file_cached_io_end(struct inode *inode, struct fuse_file *ff)
+static void fuse_file_cached_io_release(struct fuse_file *ff,
+ struct fuse_inode *fi)
{
- struct fuse_inode *fi = get_fuse_inode(inode);
-
spin_lock(&fi->lock);
WARN_ON(fi->iocachectr <= 0);
WARN_ON(ff->iomode != IOM_CACHED);
@@ -82,16 +82,15 @@
}
/* Start strictly uncached io mode where cache access is not allowed */
-int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb)
+int fuse_inode_uncached_io_start(struct fuse_inode *fi, struct fuse_backing *fb)
{
- struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_backing *oldfb;
int err = 0;
spin_lock(&fi->lock);
/* deny conflicting backing files on same fuse inode */
oldfb = fuse_inode_backing(fi);
- if (oldfb && oldfb != fb) {
+ if (fb && oldfb && oldfb != fb) {
err = -EBUSY;
goto unlock;
}
@@ -99,12 +98,10 @@
err = -ETXTBSY;
goto unlock;
}
- WARN_ON(ff->iomode != IOM_NONE);
fi->iocachectr--;
- ff->iomode = IOM_UNCACHED;
/* fuse inode holds a single refcount of backing file */
- if (!oldfb) {
+ if (fb && !oldfb) {
oldfb = fuse_inode_backing_set(fi, fb);
WARN_ON_ONCE(oldfb != NULL);
} else {
@@ -115,15 +112,29 @@
return err;
}
-void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff)
+/* Takes uncached_io inode mode reference to be dropped on file release */
+static int fuse_file_uncached_io_open(struct inode *inode,
+ struct fuse_file *ff,
+ struct fuse_backing *fb)
{
struct fuse_inode *fi = get_fuse_inode(inode);
+ int err;
+
+ err = fuse_inode_uncached_io_start(fi, fb);
+ if (err)
+ return err;
+
+ WARN_ON(ff->iomode != IOM_NONE);
+ ff->iomode = IOM_UNCACHED;
+ return 0;
+}
+
+void fuse_inode_uncached_io_end(struct fuse_inode *fi)
+{
struct fuse_backing *oldfb = NULL;
spin_lock(&fi->lock);
WARN_ON(fi->iocachectr >= 0);
- WARN_ON(ff->iomode != IOM_UNCACHED);
- ff->iomode = IOM_NONE;
fi->iocachectr++;
if (!fi->iocachectr) {
wake_up(&fi->direct_io_waitq);
@@ -134,6 +145,15 @@
fuse_backing_put(oldfb);
}
+/* Drop uncached_io reference from passthrough open */
+static void fuse_file_uncached_io_release(struct fuse_file *ff,
+ struct fuse_inode *fi)
+{
+ WARN_ON(ff->iomode != IOM_UNCACHED);
+ ff->iomode = IOM_NONE;
+ fuse_inode_uncached_io_end(fi);
+}
+
/*
* Open flags that are allowed in combination with FOPEN_PASSTHROUGH.
* A combination of FOPEN_PASSTHROUGH and FOPEN_DIRECT_IO means that read/write
@@ -163,7 +183,7 @@
return PTR_ERR(fb);
/* First passthrough file open denies caching inode io mode */
- err = fuse_file_uncached_io_start(inode, ff, fb);
+ err = fuse_file_uncached_io_open(inode, ff, fb);
if (!err)
return 0;
@@ -216,7 +236,7 @@
if (ff->open_flags & FOPEN_PASSTHROUGH)
err = fuse_file_passthrough_open(inode, file);
else
- err = fuse_file_cached_io_start(inode, ff);
+ err = fuse_file_cached_io_open(inode, ff);
if (err)
goto fail;
@@ -236,8 +256,10 @@
/* No more pending io and no new io possible to inode via open/mmapped file */
void fuse_file_io_release(struct fuse_file *ff, struct inode *inode)
{
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
/*
- * Last parallel dio close allows caching inode io mode.
+ * Last passthrough file close allows caching inode io mode.
* Last caching file close exits caching inode io mode.
*/
switch (ff->iomode) {
@@ -245,10 +267,10 @@
/* Nothing to do */
break;
case IOM_UNCACHED:
- fuse_file_uncached_io_end(inode, ff);
+ fuse_file_uncached_io_release(ff, fi);
break;
case IOM_CACHED:
- fuse_file_cached_io_end(inode, ff);
+ fuse_file_cached_io_release(ff, fi);
break;
}
}
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 1d5abfd..fb0628e 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -769,7 +769,7 @@
struct fsuuid2 u = { .len = sb->s_uuid_len, };
if (!sb->s_uuid_len)
- return -ENOIOCTLCMD;
+ return -ENOTTY;
memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len);
@@ -781,7 +781,7 @@
struct super_block *sb = file_inode(file)->i_sb;
if (!strlen(sb->s_sysfs_name))
- return -ENOIOCTLCMD;
+ return -ENOTTY;
struct fs_sysfs_path u = {};
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e9df2f8..8502ef6 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -636,11 +636,18 @@
* each file a separate locking class. Let's differentiate on
* whether the file has mmap or not for now.
*
- * Both paths of the branch look the same. They're supposed to
+ * For similar reasons, writable and readonly files are given different
+ * lockdep key, because the writable file /sys/power/resume may call vfs
+ * lookup helpers for arbitrary paths and readonly files can be read by
+ * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs.
+ *
+ * All three cases look the same. They're supposed to
* look that way and give @of->mutex different static lockdep keys.
*/
if (has_mmap)
mutex_init(&of->mutex);
+ else if (file->f_mode & FMODE_WRITE)
+ mutex_init(&of->mutex);
else
mutex_init(&of->mutex);
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 9a0d32e..267b622 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -164,7 +164,7 @@
enum netfs_how_to_modify howto;
enum netfs_folio_trace trace;
unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC;
- ssize_t written = 0, ret;
+ ssize_t written = 0, ret, ret2;
loff_t i_size, pos = iocb->ki_pos, from, to;
size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
bool maybe_trouble = false;
@@ -172,15 +172,14 @@
if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) ||
iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC))
) {
- if (pos < i_size_read(inode)) {
- ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count);
- if (ret < 0) {
- goto out;
- }
- }
-
wbc_attach_fdatawrite_inode(&wbc, mapping->host);
+ ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count);
+ if (ret < 0) {
+ wbc_detach_inode(&wbc);
+ goto out;
+ }
+
wreq = netfs_begin_writethrough(iocb, iter->count);
if (IS_ERR(wreq)) {
wbc_detach_inode(&wbc);
@@ -395,10 +394,12 @@
out:
if (unlikely(wreq)) {
- ret = netfs_end_writethrough(wreq, iocb);
+ ret2 = netfs_end_writethrough(wreq, iocb);
wbc_detach_inode(&wbc);
- if (ret == -EIOCBQUEUED)
- return ret;
+ if (ret2 == -EIOCBQUEUED)
+ return ret2;
+ if (ret == 0)
+ ret = ret2;
}
iocb->ki_pos += written;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c709c29..acef52e 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2429,7 +2429,12 @@
struct nfs_net *nn = net_generic(net, nfs_net_id);
nfs_clients_init(net);
- rpc_proc_register(net, &nn->rpcstats);
+
+ if (!rpc_proc_register(net, &nn->rpcstats)) {
+ nfs_clients_exit(net);
+ return -ENOMEM;
+ }
+
return nfs_fs_proc_net_init(net);
}
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 87c9547..e88aca0 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -983,15 +983,7 @@
static bool nfsd4_queue_cb(struct nfsd4_callback *cb)
{
trace_nfsd_cb_queue(cb->cb_clp, cb);
- return queue_delayed_work(callback_wq, &cb->cb_work, 0);
-}
-
-static void nfsd4_queue_cb_delayed(struct nfsd4_callback *cb,
- unsigned long msecs)
-{
- trace_nfsd_cb_queue(cb->cb_clp, cb);
- queue_delayed_work(callback_wq, &cb->cb_work,
- msecs_to_jiffies(msecs));
+ return queue_work(callback_wq, &cb->cb_work);
}
static void nfsd41_cb_inflight_begin(struct nfs4_client *clp)
@@ -1490,7 +1482,7 @@
nfsd4_run_cb_work(struct work_struct *work)
{
struct nfsd4_callback *cb =
- container_of(work, struct nfsd4_callback, cb_work.work);
+ container_of(work, struct nfsd4_callback, cb_work);
struct nfs4_client *clp = cb->cb_clp;
struct rpc_clnt *clnt;
int flags;
@@ -1502,16 +1494,8 @@
clnt = clp->cl_cb_client;
if (!clnt) {
- if (test_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags))
- nfsd41_destroy_cb(cb);
- else {
- /*
- * XXX: Ideally, we could wait for the client to
- * reconnect, but I haven't figured out how
- * to do that yet.
- */
- nfsd4_queue_cb_delayed(cb, 25);
- }
+ /* Callback channel broken, or client killed; give up: */
+ nfsd41_destroy_cb(cb);
return;
}
@@ -1544,7 +1528,7 @@
cb->cb_msg.rpc_argp = cb;
cb->cb_msg.rpc_resp = cb;
cb->cb_ops = ops;
- INIT_DELAYED_WORK(&cb->cb_work, nfsd4_run_cb_work);
+ INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
cb->cb_status = 0;
cb->cb_need_restart = false;
cb->cb_holds_slot = false;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index fac938f..a644460 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3490,11 +3490,13 @@
struct dentry *dentry, const u32 *bmval,
int ignore_crossmnt)
{
+ DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
struct nfsd4_fattr_args args;
struct svc_fh *tempfh = NULL;
int starting_len = xdr->buf->len;
__be32 *attrlen_p, status;
int attrlen_offset;
+ u32 attrmask[3];
int err;
struct nfsd4_compoundres *resp = rqstp->rq_resp;
u32 minorversion = resp->cstate.minorversion;
@@ -3502,10 +3504,6 @@
.mnt = exp->ex_path.mnt,
.dentry = dentry,
};
- union {
- u32 attrmask[3];
- unsigned long mask[2];
- } u;
unsigned long bit;
bool file_modified = false;
u64 size = 0;
@@ -3517,24 +3515,24 @@
args.exp = exp;
args.dentry = dentry;
args.ignore_crossmnt = (ignore_crossmnt != 0);
+ args.acl = NULL;
/*
* Make a local copy of the attribute bitmap that can be modified.
*/
- memset(&u, 0, sizeof(u));
- u.attrmask[0] = bmval[0];
- u.attrmask[1] = bmval[1];
- u.attrmask[2] = bmval[2];
+ attrmask[0] = bmval[0];
+ attrmask[1] = bmval[1];
+ attrmask[2] = bmval[2];
args.rdattr_err = 0;
if (exp->ex_fslocs.migrated) {
- status = fattr_handle_absent_fs(&u.attrmask[0], &u.attrmask[1],
- &u.attrmask[2], &args.rdattr_err);
+ status = fattr_handle_absent_fs(&attrmask[0], &attrmask[1],
+ &attrmask[2], &args.rdattr_err);
if (status)
goto out;
}
args.size = 0;
- if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
+ if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry),
&file_modified, &size);
if (status)
@@ -3553,16 +3551,16 @@
if (!(args.stat.result_mask & STATX_BTIME))
/* underlying FS does not offer btime so we can't share it */
- u.attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
- if ((u.attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
+ attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
+ if ((attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) ||
- (u.attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
+ (attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
FATTR4_WORD1_SPACE_TOTAL))) {
err = vfs_statfs(&path, &args.statfs);
if (err)
goto out_nfserr;
}
- if ((u.attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) &&
+ if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) &&
!fhp) {
tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
status = nfserr_jukebox;
@@ -3576,11 +3574,10 @@
} else
args.fhp = fhp;
- args.acl = NULL;
- if (u.attrmask[0] & FATTR4_WORD0_ACL) {
+ if (attrmask[0] & FATTR4_WORD0_ACL) {
err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl);
if (err == -EOPNOTSUPP)
- u.attrmask[0] &= ~FATTR4_WORD0_ACL;
+ attrmask[0] &= ~FATTR4_WORD0_ACL;
else if (err == -EINVAL) {
status = nfserr_attrnotsupp;
goto out;
@@ -3592,17 +3589,17 @@
#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
args.context = NULL;
- if ((u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) ||
- u.attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
+ if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) ||
+ attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
if (exp->ex_flags & NFSEXP_SECURITY_LABEL)
err = security_inode_getsecctx(d_inode(dentry),
&args.context, &args.contextlen);
else
err = -EOPNOTSUPP;
args.contextsupport = (err == 0);
- if (u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) {
+ if (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) {
if (err == -EOPNOTSUPP)
- u.attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
+ attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
else if (err)
goto out_nfserr;
}
@@ -3610,8 +3607,8 @@
#endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
/* attrmask */
- status = nfsd4_encode_bitmap4(xdr, u.attrmask[0],
- u.attrmask[1], u.attrmask[2]);
+ status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1],
+ attrmask[2]);
if (status)
goto out;
@@ -3620,7 +3617,9 @@
attrlen_p = xdr_reserve_space(xdr, XDR_UNIT);
if (!attrlen_p)
goto out_resource;
- for_each_set_bit(bit, (const unsigned long *)&u.mask,
+ bitmap_from_arr32(attr_bitmap, attrmask,
+ ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
+ for_each_set_bit(bit, attr_bitmap,
ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) {
status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args);
if (status != nfs_ok)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 01c6f34..2ed0fcf 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -68,7 +68,7 @@
struct nfs4_client *cb_clp;
struct rpc_message cb_msg;
const struct nfsd4_callback_ops *cb_ops;
- struct delayed_work cb_work;
+ struct work_struct cb_work;
int cb_seq_status;
int cb_status;
bool cb_need_restart;
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index bc846b9..aee40db 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -240,7 +240,7 @@
#define S_SHIFT 12
static unsigned char
-nilfs_type_by_mode[S_IFMT >> S_SHIFT] = {
+nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
[S_IFREG >> S_SHIFT] = NILFS_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = NILFS_FT_DIR,
[S_IFCHR >> S_SHIFT] = NILFS_FT_CHRDEV,
diff --git a/fs/ntfs3/Kconfig b/fs/ntfs3/Kconfig
index cdfdf51..7bc31d6 100644
--- a/fs/ntfs3/Kconfig
+++ b/fs/ntfs3/Kconfig
@@ -46,3 +46,12 @@
NOTE: this is linux only feature. Windows will ignore these ACLs.
If you don't know what Access Control Lists are, say N.
+
+config NTFS_FS
+ tristate "NTFS file system support"
+ select NTFS3_FS
+ select BUFFER_HEAD
+ select NLS
+ help
+ This config option is here only for backward compatibility. NTFS
+ filesystem is now handled by the NTFS3 driver.
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 5cf3d9d..2636351 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -616,4 +616,11 @@
.compat_ioctl = ntfs_compat_ioctl,
#endif
};
+
+const struct file_operations ntfs_legacy_dir_operations = {
+ .llseek = generic_file_llseek,
+ .read = generic_read_dir,
+ .iterate_shared = ntfs_readdir,
+ .open = ntfs_file_open,
+};
// clang-format on
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 5418662..b73969e 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -1236,4 +1236,12 @@
.fallocate = ntfs_fallocate,
.release = ntfs_file_release,
};
+
+const struct file_operations ntfs_legacy_file_operations = {
+ .llseek = generic_file_llseek,
+ .read_iter = ntfs_file_read_iter,
+ .splice_read = ntfs_file_splice_read,
+ .open = ntfs_file_open,
+ .release = ntfs_file_release,
+};
// clang-format on
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index eb7a8c9..d273eda 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -440,7 +440,10 @@
* Usually a hard links to directories are disabled.
*/
inode->i_op = &ntfs_dir_inode_operations;
- inode->i_fop = &ntfs_dir_operations;
+ if (is_legacy_ntfs(inode->i_sb))
+ inode->i_fop = &ntfs_legacy_dir_operations;
+ else
+ inode->i_fop = &ntfs_dir_operations;
ni->i_valid = 0;
} else if (S_ISLNK(mode)) {
ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY;
@@ -450,7 +453,10 @@
} else if (S_ISREG(mode)) {
ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY;
inode->i_op = &ntfs_file_inode_operations;
- inode->i_fop = &ntfs_file_operations;
+ if (is_legacy_ntfs(inode->i_sb))
+ inode->i_fop = &ntfs_legacy_file_operations;
+ else
+ inode->i_fop = &ntfs_file_operations;
inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr :
&ntfs_aops;
if (ino != MFT_REC_MFT)
@@ -1614,7 +1620,10 @@
if (S_ISDIR(mode)) {
inode->i_op = &ntfs_dir_inode_operations;
- inode->i_fop = &ntfs_dir_operations;
+ if (is_legacy_ntfs(inode->i_sb))
+ inode->i_fop = &ntfs_legacy_dir_operations;
+ else
+ inode->i_fop = &ntfs_dir_operations;
} else if (S_ISLNK(mode)) {
inode->i_op = &ntfs_link_inode_operations;
inode->i_fop = NULL;
@@ -1623,7 +1632,10 @@
inode_nohighmem(inode);
} else if (S_ISREG(mode)) {
inode->i_op = &ntfs_file_inode_operations;
- inode->i_fop = &ntfs_file_operations;
+ if (is_legacy_ntfs(inode->i_sb))
+ inode->i_fop = &ntfs_legacy_file_operations;
+ else
+ inode->i_fop = &ntfs_file_operations;
inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr :
&ntfs_aops;
init_rwsem(&ni->file.run_lock);
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 79356fd..5f4d288 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -493,6 +493,7 @@
struct ntfs_fnd *fnd);
bool dir_is_empty(struct inode *dir);
extern const struct file_operations ntfs_dir_operations;
+extern const struct file_operations ntfs_legacy_dir_operations;
/* Globals from file.c */
int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path,
@@ -507,6 +508,7 @@
extern const struct inode_operations ntfs_special_inode_operations;
extern const struct inode_operations ntfs_file_inode_operations;
extern const struct file_operations ntfs_file_operations;
+extern const struct file_operations ntfs_legacy_file_operations;
/* Globals from frecord.c */
void ni_remove_mi(struct ntfs_inode *ni, struct mft_inode *mi);
@@ -1154,4 +1156,6 @@
*var = cpu_to_le64(le64_to_cpu(*var) - val);
}
+bool is_legacy_ntfs(struct super_block *sb);
+
#endif /* _LINUX_NTFS3_NTFS_FS_H */
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 9df7c20..b26d95a 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -408,6 +408,12 @@
struct ntfs_mount_options *new_opts = fc->fs_private;
int ro_rw;
+ /* If ntfs3 is used as legacy ntfs enforce read-only mode. */
+ if (is_legacy_ntfs(sb)) {
+ fc->sb_flags |= SB_RDONLY;
+ goto out;
+ }
+
ro_rw = sb_rdonly(sb) && !(fc->sb_flags & SB_RDONLY);
if (ro_rw && (sbi->flags & NTFS_FLAGS_NEED_REPLAY)) {
errorf(fc,
@@ -427,8 +433,6 @@
fc,
"ntfs3: Cannot use different iocharset when remounting!");
- sync_filesystem(sb);
-
if (ro_rw && (sbi->volume.flags & VOLUME_FLAG_DIRTY) &&
!new_opts->force) {
errorf(fc,
@@ -436,6 +440,8 @@
return -EINVAL;
}
+out:
+ sync_filesystem(sb);
swap(sbi->options, fc->fs_private);
return 0;
@@ -1613,6 +1619,8 @@
}
#endif
+ if (is_legacy_ntfs(sb))
+ sb->s_flags |= SB_RDONLY;
return 0;
put_inode_out:
@@ -1730,7 +1738,7 @@
* This will called when mount/remount. We will first initialize
* options so that if remount we can use just that.
*/
-static int ntfs_init_fs_context(struct fs_context *fc)
+static int __ntfs_init_fs_context(struct fs_context *fc)
{
struct ntfs_mount_options *opts;
struct ntfs_sb_info *sbi;
@@ -1778,6 +1786,11 @@
return -ENOMEM;
}
+static int ntfs_init_fs_context(struct fs_context *fc)
+{
+ return __ntfs_init_fs_context(fc);
+}
+
static void ntfs3_kill_sb(struct super_block *sb)
{
struct ntfs_sb_info *sbi = sb->s_fs_info;
@@ -1798,6 +1811,50 @@
.kill_sb = ntfs3_kill_sb,
.fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
};
+
+#if IS_ENABLED(CONFIG_NTFS_FS)
+static int ntfs_legacy_init_fs_context(struct fs_context *fc)
+{
+ int ret;
+
+ ret = __ntfs_init_fs_context(fc);
+ /* If ntfs3 is used as legacy ntfs enforce read-only mode. */
+ fc->sb_flags |= SB_RDONLY;
+ return ret;
+}
+
+static struct file_system_type ntfs_legacy_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "ntfs",
+ .init_fs_context = ntfs_legacy_init_fs_context,
+ .parameters = ntfs_fs_parameters,
+ .kill_sb = ntfs3_kill_sb,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
+};
+MODULE_ALIAS_FS("ntfs");
+
+static inline void register_as_ntfs_legacy(void)
+{
+ int err = register_filesystem(&ntfs_legacy_fs_type);
+ if (err)
+ pr_warn("ntfs3: Failed to register legacy ntfs filesystem driver: %d\n", err);
+}
+
+static inline void unregister_as_ntfs_legacy(void)
+{
+ unregister_filesystem(&ntfs_legacy_fs_type);
+}
+bool is_legacy_ntfs(struct super_block *sb)
+{
+ return sb->s_type == &ntfs_legacy_fs_type;
+}
+#else
+static inline void register_as_ntfs_legacy(void) {}
+static inline void unregister_as_ntfs_legacy(void) {}
+bool is_legacy_ntfs(struct super_block *sb) { return false; }
+#endif
+
+
// clang-format on
static int __init init_ntfs_fs(void)
@@ -1832,6 +1889,7 @@
goto out1;
}
+ register_as_ntfs_legacy();
err = register_filesystem(&ntfs_fs_type);
if (err)
goto out;
@@ -1849,6 +1907,7 @@
rcu_barrier();
kmem_cache_destroy(ntfs_inode_cachep);
unregister_filesystem(&ntfs_fs_type);
+ unregister_as_ntfs_legacy();
ntfs3_exit_bitmap();
#ifdef CONFIG_PROC_FS
diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c
index 902b326..87dcaae 100644
--- a/fs/proc/bootconfig.c
+++ b/fs/proc/bootconfig.c
@@ -62,12 +62,12 @@
break;
dst += ret;
}
- if (ret >= 0 && boot_command_line[0]) {
- ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n",
- boot_command_line);
- if (ret > 0)
- dst += ret;
- }
+ }
+ if (cmdline_has_extra_options() && ret >= 0 && boot_command_line[0]) {
+ ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n",
+ boot_command_line);
+ if (ret > 0)
+ dst += ret;
}
out:
kfree(key);
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 195b077..9223856 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -67,7 +67,7 @@
*/
ppage = pfn_to_online_page(pfn);
- if (!ppage || PageSlab(ppage) || page_has_type(ppage))
+ if (!ppage)
pcount = 0;
else
pcount = page_mapcount(ppage);
@@ -124,11 +124,8 @@
/*
* pseudo flags for the well known (anonymous) memory mapped pages
- *
- * Note that page->_mapcount is overloaded in SLAB, so the
- * simple test in page_mapped() is not enough.
*/
- if (!PageSlab(page) && page_mapped(page))
+ if (page_mapped(page))
u |= 1 << KPF_MMAP;
if (PageAnon(page))
u |= 1 << KPF_ANON;
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 13a9d7a..0ff2491 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -433,8 +433,8 @@
if (cfid->is_open) {
rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid,
cfid->fid.volatile_fid);
- if (rc != -EBUSY && rc != -EAGAIN)
- atomic_dec(&cfid->tcon->num_remote_opens);
+ if (rc) /* should we retry on -EBUSY or -EAGAIN? */
+ cifs_dbg(VFS, "close cached dir rc %d\n", rc);
}
free_cached_dir(cfid);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index d41eedb..39277c3 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -389,6 +389,7 @@
* server, can not assume caching of file data or metadata.
*/
cifs_set_oplock_level(cifs_inode, 0);
+ cifs_inode->lease_granted = false;
cifs_inode->flags = 0;
spin_lock_init(&cifs_inode->writers_lock);
cifs_inode->writers = 0;
@@ -739,6 +740,8 @@
spin_lock(&cifs_tcp_ses_lock);
spin_lock(&tcon->tc_lock);
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_see_umount);
if ((tcon->tc_count > 1) || (tcon->status == TID_EXITING)) {
/* we have other mounts to same share or we have
already tried to umount this and woken up
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index f6a3022..6ff3557 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1077,6 +1077,7 @@
and after mount option parsing we fill it */
char *domainName;
char *password;
+ char *password2; /* When key rotation used, new password may be set before it expires */
char workstation_name[CIFS_MAX_WORKSTATION_LEN];
struct session_key auth_key;
struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */
@@ -1189,6 +1190,7 @@
*/
struct cifs_tcon {
struct list_head tcon_list;
+ int debug_id; /* Debugging for tracing */
int tc_count;
struct list_head rlist; /* reconnect list */
spinlock_t tc_lock; /* protect anything here that is not protected */
@@ -1275,7 +1277,9 @@
__u32 max_cached_dirs;
#ifdef CONFIG_CIFS_FSCACHE
u64 resource_id; /* server resource id */
+ bool fscache_acquired; /* T if we've tried acquiring a cookie */
struct fscache_volume *fscache; /* cookie for share */
+ struct mutex fscache_lock; /* Prevent regetting a cookie */
#endif
struct list_head pending_opens; /* list of incomplete opens */
struct cached_fids *cfids;
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index c0513fb..c46d418 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -882,7 +882,7 @@
__u8 OplockLevel;
__u16 Fid;
__le32 CreateAction;
- struct_group(common_attributes,
+ struct_group_attr(common_attributes, __packed,
__le64 CreationTime;
__le64 LastAccessTime;
__le64 LastWriteTime;
@@ -2266,7 +2266,7 @@
/* QueryFileInfo/QueryPathinfo (also for SetPath/SetFile) data buffer formats */
/******************************************************************************/
typedef struct { /* data block encoding of response to level 263 QPathInfo */
- struct_group(common_attributes,
+ struct_group_attr(common_attributes, __packed,
__le64 CreationTime;
__le64 LastAccessTime;
__le64 LastWriteTime;
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 8e0a348..fbc358c 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -303,7 +303,7 @@
struct TCP_Server_Info *primary_server);
extern void cifs_put_tcp_session(struct TCP_Server_Info *server,
int from_reconnect);
-extern void cifs_put_tcon(struct cifs_tcon *tcon);
+extern void cifs_put_tcon(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace);
extern void cifs_release_automount_timer(void);
@@ -530,8 +530,9 @@
extern struct cifs_ses *sesInfoAlloc(void);
extern void sesInfoFree(struct cifs_ses *);
-extern struct cifs_tcon *tcon_info_alloc(bool dir_leases_enabled);
-extern void tconInfoFree(struct cifs_tcon *);
+extern struct cifs_tcon *tcon_info_alloc(bool dir_leases_enabled,
+ enum smb3_tcon_ref_trace trace);
+extern void tconInfoFree(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace);
extern int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server,
__u32 *pexpected_response_sequence_number);
@@ -721,8 +722,6 @@
return options;
}
-struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon);
-void cifs_put_tcon_super(struct super_block *sb);
int cifs_wait_for_server_reconnect(struct TCP_Server_Info *server, bool retry);
/* Put references of @ses and its children */
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 85679ae..7a16e12 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -1943,7 +1943,7 @@
}
/* no need to setup directory caching on IPC share, so pass in false */
- tcon = tcon_info_alloc(false);
+ tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_ipc);
if (tcon == NULL)
return -ENOMEM;
@@ -1960,7 +1960,7 @@
if (rc) {
cifs_server_dbg(VFS, "failed to connect to IPC (rc=%d)\n", rc);
- tconInfoFree(tcon);
+ tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc_fail);
goto out;
}
@@ -2043,7 +2043,7 @@
* files on session close, as specified in MS-SMB2 3.3.5.6 Receiving an
* SMB2 LOGOFF Request.
*/
- tconInfoFree(tcon);
+ tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc);
if (do_logoff) {
xid = get_xid();
rc = server->ops->logoff(xid, ses);
@@ -2183,6 +2183,7 @@
}
++delim;
+ /* BB consider adding support for password2 (Key Rotation) for multiuser in future */
ctx->password = kstrndup(delim, len, GFP_KERNEL);
if (!ctx->password) {
cifs_dbg(FYI, "Unable to allocate %zd bytes for password\n",
@@ -2206,6 +2207,7 @@
kfree(ctx->username);
ctx->username = NULL;
kfree_sensitive(ctx->password);
+ /* no need to free ctx->password2 since not allocated in this path */
ctx->password = NULL;
goto out_key_put;
}
@@ -2317,6 +2319,12 @@
if (!ses->password)
goto get_ses_fail;
}
+ /* ctx->password freed at unmount */
+ if (ctx->password2) {
+ ses->password2 = kstrdup(ctx->password2, GFP_KERNEL);
+ if (!ses->password2)
+ goto get_ses_fail;
+ }
if (ctx->domainname) {
ses->domainName = kstrdup(ctx->domainname, GFP_KERNEL);
if (!ses->domainName)
@@ -2424,6 +2432,8 @@
continue;
}
++tcon->tc_count;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_get_find);
spin_unlock(&tcon->tc_lock);
spin_unlock(&cifs_tcp_ses_lock);
return tcon;
@@ -2433,7 +2443,7 @@
}
void
-cifs_put_tcon(struct cifs_tcon *tcon)
+cifs_put_tcon(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace)
{
unsigned int xid;
struct cifs_ses *ses;
@@ -2449,6 +2459,7 @@
cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count);
spin_lock(&cifs_tcp_ses_lock);
spin_lock(&tcon->tc_lock);
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count - 1, trace);
if (--tcon->tc_count > 0) {
spin_unlock(&tcon->tc_lock);
spin_unlock(&cifs_tcp_ses_lock);
@@ -2485,7 +2496,7 @@
_free_xid(xid);
cifs_fscache_release_super_cookie(tcon);
- tconInfoFree(tcon);
+ tconInfoFree(tcon, netfs_trace_tcon_ref_free);
cifs_put_smb_ses(ses);
}
@@ -2539,7 +2550,7 @@
nohandlecache = ctx->nohandlecache;
else
nohandlecache = true;
- tcon = tcon_info_alloc(!nohandlecache);
+ tcon = tcon_info_alloc(!nohandlecache, netfs_trace_tcon_ref_new);
if (tcon == NULL) {
rc = -ENOMEM;
goto out_fail;
@@ -2729,7 +2740,7 @@
return tcon;
out_fail:
- tconInfoFree(tcon);
+ tconInfoFree(tcon, netfs_trace_tcon_ref_free_fail);
return ERR_PTR(rc);
}
@@ -2746,7 +2757,7 @@
}
if (!IS_ERR(tlink_tcon(tlink)))
- cifs_put_tcon(tlink_tcon(tlink));
+ cifs_put_tcon(tlink_tcon(tlink), netfs_trace_tcon_ref_put_tlink);
kfree(tlink);
}
@@ -3311,7 +3322,7 @@
int rc = 0;
if (mnt_ctx->tcon)
- cifs_put_tcon(mnt_ctx->tcon);
+ cifs_put_tcon(mnt_ctx->tcon, netfs_trace_tcon_ref_put_mnt_ctx);
else if (mnt_ctx->ses)
cifs_put_smb_ses(mnt_ctx->ses);
else if (mnt_ctx->server)
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index b7bfe70..3bbac92 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -162,6 +162,7 @@
fsparam_string("username", Opt_user),
fsparam_string("pass", Opt_pass),
fsparam_string("password", Opt_pass),
+ fsparam_string("password2", Opt_pass2),
fsparam_string("ip", Opt_ip),
fsparam_string("addr", Opt_ip),
fsparam_string("domain", Opt_domain),
@@ -345,6 +346,7 @@
new_ctx->nodename = NULL;
new_ctx->username = NULL;
new_ctx->password = NULL;
+ new_ctx->password2 = NULL;
new_ctx->server_hostname = NULL;
new_ctx->domainname = NULL;
new_ctx->UNC = NULL;
@@ -357,6 +359,7 @@
DUP_CTX_STR(prepath);
DUP_CTX_STR(username);
DUP_CTX_STR(password);
+ DUP_CTX_STR(password2);
DUP_CTX_STR(server_hostname);
DUP_CTX_STR(UNC);
DUP_CTX_STR(source);
@@ -745,6 +748,16 @@
/* set the port that we got earlier */
cifs_set_port((struct sockaddr *)&ctx->dstaddr, ctx->port);
+ if (ctx->uid_specified && !ctx->forceuid_specified) {
+ ctx->override_uid = 1;
+ pr_notice("enabling forceuid mount option implicitly because uid= option is specified\n");
+ }
+
+ if (ctx->gid_specified && !ctx->forcegid_specified) {
+ ctx->override_gid = 1;
+ pr_notice("enabling forcegid mount option implicitly because gid= option is specified\n");
+ }
+
if (ctx->override_uid && !ctx->uid_specified) {
ctx->override_uid = 0;
pr_notice("ignoring forceuid mount option specified with no uid= option\n");
@@ -905,6 +918,8 @@
else {
kfree_sensitive(ses->password);
ses->password = kstrdup(ctx->password, GFP_KERNEL);
+ kfree_sensitive(ses->password2);
+ ses->password2 = kstrdup(ctx->password2, GFP_KERNEL);
}
STEAL_STRING(cifs_sb, ctx, domainname);
STEAL_STRING(cifs_sb, ctx, nodename);
@@ -1014,12 +1029,14 @@
ctx->override_uid = 0;
else
ctx->override_uid = 1;
+ ctx->forceuid_specified = true;
break;
case Opt_forcegid:
if (result.negated)
ctx->override_gid = 0;
else
ctx->override_gid = 1;
+ ctx->forcegid_specified = true;
break;
case Opt_perm:
if (result.negated)
@@ -1305,6 +1322,18 @@
goto cifs_parse_mount_err;
}
break;
+ case Opt_pass2:
+ kfree_sensitive(ctx->password2);
+ ctx->password2 = NULL;
+ if (strlen(param->string) == 0)
+ break;
+
+ ctx->password2 = kstrdup(param->string, GFP_KERNEL);
+ if (ctx->password2 == NULL) {
+ cifs_errorf(fc, "OOM when copying password2 string\n");
+ goto cifs_parse_mount_err;
+ }
+ break;
case Opt_ip:
if (strlen(param->string) == 0) {
ctx->got_ip = false;
@@ -1608,6 +1637,8 @@
cifs_parse_mount_err:
kfree_sensitive(ctx->password);
ctx->password = NULL;
+ kfree_sensitive(ctx->password2);
+ ctx->password2 = NULL;
return -EINVAL;
}
@@ -1713,6 +1744,8 @@
ctx->username = NULL;
kfree_sensitive(ctx->password);
ctx->password = NULL;
+ kfree_sensitive(ctx->password2);
+ ctx->password2 = NULL;
kfree(ctx->server_hostname);
ctx->server_hostname = NULL;
kfree(ctx->UNC);
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index 8a35645..cf577ec 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -145,6 +145,7 @@
Opt_source,
Opt_user,
Opt_pass,
+ Opt_pass2,
Opt_ip,
Opt_domain,
Opt_srcaddr,
@@ -164,6 +165,8 @@
};
struct smb3_fs_context {
+ bool forceuid_specified;
+ bool forcegid_specified;
bool uid_specified;
bool cruid_specified;
bool gid_specified;
@@ -177,6 +180,7 @@
char *username;
char *password;
+ char *password2;
char *domainname;
char *source;
char *server_hostname;
diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
index 340efce..1a895e6 100644
--- a/fs/smb/client/fscache.c
+++ b/fs/smb/client/fscache.c
@@ -43,12 +43,23 @@
char *key;
int ret = -ENOMEM;
+ if (tcon->fscache_acquired)
+ return 0;
+
+ mutex_lock(&tcon->fscache_lock);
+ if (tcon->fscache_acquired) {
+ mutex_unlock(&tcon->fscache_lock);
+ return 0;
+ }
+ tcon->fscache_acquired = true;
+
tcon->fscache = NULL;
switch (sa->sa_family) {
case AF_INET:
case AF_INET6:
break;
default:
+ mutex_unlock(&tcon->fscache_lock);
cifs_dbg(VFS, "Unknown network family '%d'\n", sa->sa_family);
return -EINVAL;
}
@@ -57,6 +68,7 @@
sharename = extract_sharename(tcon->tree_name);
if (IS_ERR(sharename)) {
+ mutex_unlock(&tcon->fscache_lock);
cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__);
return PTR_ERR(sharename);
}
@@ -82,6 +94,11 @@
}
pr_err("Cache volume key already in use (%s)\n", key);
vcookie = NULL;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_see_fscache_collision);
+ } else {
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_see_fscache_okay);
}
tcon->fscache = vcookie;
@@ -90,6 +107,7 @@
kfree(key);
out:
kfree(sharename);
+ mutex_unlock(&tcon->fscache_lock);
return ret;
}
@@ -102,6 +120,8 @@
cifs_fscache_fill_volume_coherency(tcon, &cd);
fscache_relinquish_volume(tcon->fscache, &cd, false);
tcon->fscache = NULL;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_see_fscache_relinq);
}
void cifs_fscache_get_inode_cookie(struct inode *inode)
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 91b07ef..60afab5 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1105,7 +1105,8 @@
} else {
cifs_open_info_to_fattr(fattr, data, sb);
}
- if (!rc && fattr->cf_flags & CIFS_FATTR_DELETE_PENDING)
+ if (!rc && *inode &&
+ (fattr->cf_flags & CIFS_FATTR_DELETE_PENDING))
cifs_mark_open_handles_for_deleted_file(*inode, full_path);
break;
case -EREMOTE:
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index 33ac4f8..07c468d 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -98,6 +98,7 @@
kfree(buf_to_free->serverDomain);
kfree(buf_to_free->serverNOS);
kfree_sensitive(buf_to_free->password);
+ kfree_sensitive(buf_to_free->password2);
kfree(buf_to_free->user_name);
kfree(buf_to_free->domainName);
kfree_sensitive(buf_to_free->auth_key.response);
@@ -110,9 +111,10 @@
}
struct cifs_tcon *
-tcon_info_alloc(bool dir_leases_enabled)
+tcon_info_alloc(bool dir_leases_enabled, enum smb3_tcon_ref_trace trace)
{
struct cifs_tcon *ret_buf;
+ static atomic_t tcon_debug_id;
ret_buf = kzalloc(sizeof(*ret_buf), GFP_KERNEL);
if (!ret_buf)
@@ -129,7 +131,8 @@
atomic_inc(&tconInfoAllocCount);
ret_buf->status = TID_NEW;
- ++ret_buf->tc_count;
+ ret_buf->debug_id = atomic_inc_return(&tcon_debug_id);
+ ret_buf->tc_count = 1;
spin_lock_init(&ret_buf->tc_lock);
INIT_LIST_HEAD(&ret_buf->openFileList);
INIT_LIST_HEAD(&ret_buf->tcon_list);
@@ -138,17 +141,22 @@
atomic_set(&ret_buf->num_local_opens, 0);
atomic_set(&ret_buf->num_remote_opens, 0);
ret_buf->stats_from_time = ktime_get_real_seconds();
+#ifdef CONFIG_CIFS_FSCACHE
+ mutex_init(&ret_buf->fscache_lock);
+#endif
+ trace_smb3_tcon_ref(ret_buf->debug_id, ret_buf->tc_count, trace);
return ret_buf;
}
void
-tconInfoFree(struct cifs_tcon *tcon)
+tconInfoFree(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace)
{
if (tcon == NULL) {
cifs_dbg(FYI, "Null buffer passed to tconInfoFree\n");
return;
}
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, trace);
free_cached_dirs(tcon->cfids);
atomic_dec(&tconInfoAllocCount);
kfree(tcon->nativeFileSystem);
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index cc72be5..677ef6f 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -767,7 +767,7 @@
if (rc)
cifs_tcon_dbg(VFS, "Close cancelled mid failed rc:%d\n", rc);
- cifs_put_tcon(tcon);
+ cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_close_fid);
kfree(cancelled);
}
@@ -811,6 +811,8 @@
if (tcon->tc_count <= 0) {
struct TCP_Server_Info *server = NULL;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_see_cancelled_close);
WARN_ONCE(tcon->tc_count < 0, "tcon refcount is negative");
spin_unlock(&cifs_tcp_ses_lock);
@@ -823,12 +825,14 @@
return 0;
}
tcon->tc_count++;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_get_cancelled_close);
spin_unlock(&cifs_tcp_ses_lock);
rc = __smb2_handle_cancelled_cmd(tcon, SMB2_CLOSE_HE, 0,
persistent_fid, volatile_fid);
if (rc)
- cifs_put_tcon(tcon);
+ cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_close);
return rc;
}
@@ -856,7 +860,7 @@
rsp->PersistentFileId,
rsp->VolatileFileId);
if (rc)
- cifs_put_tcon(tcon);
+ cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cancelled_mid);
return rc;
}
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index b156eef..28f0b7d 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -2915,8 +2915,11 @@
tcon = list_first_entry_or_null(&ses->tcon_list,
struct cifs_tcon,
tcon_list);
- if (tcon)
+ if (tcon) {
tcon->tc_count++;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_get_dfs_refer);
+ }
spin_unlock(&cifs_tcp_ses_lock);
}
@@ -2980,6 +2983,8 @@
/* ipc tcons are not refcounted */
spin_lock(&cifs_tcp_ses_lock);
tcon->tc_count--;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_dec_dfs_refer);
/* tc_count can never go negative */
WARN_ON(tcon->tc_count < 0);
spin_unlock(&cifs_tcp_ses_lock);
@@ -4964,68 +4969,84 @@
return 0;
}
-int cifs_sfu_make_node(unsigned int xid, struct inode *inode,
- struct dentry *dentry, struct cifs_tcon *tcon,
- const char *full_path, umode_t mode, dev_t dev)
+static int __cifs_sfu_make_node(unsigned int xid, struct inode *inode,
+ struct dentry *dentry, struct cifs_tcon *tcon,
+ const char *full_path, umode_t mode, dev_t dev)
{
- struct cifs_open_info_data buf = {};
struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_open_parms oparms;
struct cifs_io_parms io_parms = {};
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_fid fid;
unsigned int bytes_written;
- struct win_dev *pdev;
+ struct win_dev pdev = {};
struct kvec iov[2];
__u32 oplock = server->oplocks ? REQ_OPLOCK : 0;
int rc;
- if (!S_ISCHR(mode) && !S_ISBLK(mode) && !S_ISFIFO(mode))
+ switch (mode & S_IFMT) {
+ case S_IFCHR:
+ strscpy(pdev.type, "IntxCHR");
+ pdev.major = cpu_to_le64(MAJOR(dev));
+ pdev.minor = cpu_to_le64(MINOR(dev));
+ break;
+ case S_IFBLK:
+ strscpy(pdev.type, "IntxBLK");
+ pdev.major = cpu_to_le64(MAJOR(dev));
+ pdev.minor = cpu_to_le64(MINOR(dev));
+ break;
+ case S_IFIFO:
+ strscpy(pdev.type, "LnxFIFO");
+ break;
+ default:
return -EPERM;
+ }
- oparms = (struct cifs_open_parms) {
- .tcon = tcon,
- .cifs_sb = cifs_sb,
- .desired_access = GENERIC_WRITE,
- .create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR |
- CREATE_OPTION_SPECIAL),
- .disposition = FILE_CREATE,
- .path = full_path,
- .fid = &fid,
- };
+ oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, GENERIC_WRITE,
+ FILE_CREATE, CREATE_NOT_DIR |
+ CREATE_OPTION_SPECIAL, ACL_NO_MODE);
+ oparms.fid = &fid;
- rc = server->ops->open(xid, &oparms, &oplock, &buf);
+ rc = server->ops->open(xid, &oparms, &oplock, NULL);
if (rc)
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.fi;
io_parms.pid = current->tgid;
io_parms.tcon = tcon;
- io_parms.length = sizeof(*pdev);
- iov[1].iov_base = pdev;
- iov[1].iov_len = sizeof(*pdev);
- if (S_ISCHR(mode)) {
- memcpy(pdev->type, "IntxCHR", 8);
- pdev->major = cpu_to_le64(MAJOR(dev));
- pdev->minor = cpu_to_le64(MINOR(dev));
- } else if (S_ISBLK(mode)) {
- memcpy(pdev->type, "IntxBLK", 8);
- pdev->major = cpu_to_le64(MAJOR(dev));
- pdev->minor = cpu_to_le64(MINOR(dev));
- } else if (S_ISFIFO(mode)) {
- memcpy(pdev->type, "LnxFIFO", 8);
- }
+ io_parms.length = sizeof(pdev);
+ iov[1].iov_base = &pdev;
+ iov[1].iov_len = sizeof(pdev);
rc = server->ops->sync_write(xid, &fid, &io_parms,
&bytes_written, iov, 1);
server->ops->close(xid, tcon, &fid);
- d_drop(dentry);
- /* FIXME: add code here to set EAs */
- cifs_free_open_info(&buf);
+ return rc;
+}
+
+int cifs_sfu_make_node(unsigned int xid, struct inode *inode,
+ struct dentry *dentry, struct cifs_tcon *tcon,
+ const char *full_path, umode_t mode, dev_t dev)
+{
+ struct inode *new = NULL;
+ int rc;
+
+ rc = __cifs_sfu_make_node(xid, inode, dentry, tcon,
+ full_path, mode, dev);
+ if (rc)
+ return rc;
+
+ if (tcon->posix_extensions) {
+ rc = smb311_posix_get_inode_info(&new, full_path, NULL,
+ inode->i_sb, xid);
+ } else if (tcon->unix_ext) {
+ rc = cifs_get_inode_info_unix(&new, full_path,
+ inode->i_sb, xid);
+ } else {
+ rc = cifs_get_inode_info(&new, full_path, NULL,
+ inode->i_sb, xid, NULL);
+ }
+ if (!rc)
+ d_instantiate(dentry, new);
return rc;
}
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index c0c4933..a5efce0 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -367,6 +367,17 @@
}
rc = cifs_setup_session(0, ses, server, nls_codepage);
+ if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) {
+ /*
+ * Try alternate password for next reconnect (key rotation
+ * could be enabled on the server e.g.) if an alternate
+ * password is available and the current password is expired,
+ * but do not swap on non pwd related errors like host down
+ */
+ if (ses->password2)
+ swap(ses->password2, ses->password);
+ }
+
if ((rc == -EACCES) && !tcon->retry) {
mutex_unlock(&ses->session_mutex);
rc = -EHOSTDOWN;
@@ -4127,6 +4138,8 @@
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
if (tcon->need_reconnect || tcon->need_reopen_files) {
tcon->tc_count++;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_get_reconnect_server);
list_add_tail(&tcon->rlist, &tmp_list);
tcon_selected = true;
}
@@ -4165,14 +4178,14 @@
if (tcon->ipc)
cifs_put_smb_ses(tcon->ses);
else
- cifs_put_tcon(tcon);
+ cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_reconnect_server);
}
if (!ses_exist)
goto done;
/* allocate a dummy tcon struct used for reconnect */
- tcon = tcon_info_alloc(false);
+ tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_reconnect_server);
if (!tcon) {
resched = true;
list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) {
@@ -4195,7 +4208,7 @@
list_del_init(&ses->rlist);
cifs_put_smb_ses(ses);
}
- tconInfoFree(tcon);
+ tconInfoFree(tcon, netfs_trace_tcon_ref_free_reconnect_server);
done:
cifs_dbg(FYI, "Reconnecting tcons and channels finished\n");
diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h
index c72a3b2..2fccf0d4 100644
--- a/fs/smb/client/smb2pdu.h
+++ b/fs/smb/client/smb2pdu.h
@@ -320,7 +320,7 @@
} __packed;
struct smb2_file_network_open_info {
- struct_group(network_open_info,
+ struct_group_attr(network_open_info, __packed,
__le64 CreationTime;
__le64 LastAccessTime;
__le64 LastWriteTime;
diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index 1d6e54f..02135a6 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -189,6 +189,8 @@
if (tcon->tid != tid)
continue;
++tcon->tc_count;
+ trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count,
+ netfs_trace_tcon_ref_get_find_sess_tcon);
return tcon;
}
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 5e83cb9..604e528 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -3,6 +3,9 @@
* Copyright (C) 2018, Microsoft Corporation.
*
* Author(s): Steve French <stfrench@microsoft.com>
+ *
+ * Please use this 3-part article as a reference for writing new tracepoints:
+ * https://lwn.net/Articles/379903/
*/
#undef TRACE_SYSTEM
#define TRACE_SYSTEM cifs
@@ -15,9 +18,70 @@
#include <linux/inet.h>
/*
- * Please use this 3-part article as a reference for writing new tracepoints:
- * https://lwn.net/Articles/379903/
+ * Specify enums for tracing information.
*/
+#define smb3_tcon_ref_traces \
+ EM(netfs_trace_tcon_ref_dec_dfs_refer, "DEC DfsRef") \
+ EM(netfs_trace_tcon_ref_free, "FRE ") \
+ EM(netfs_trace_tcon_ref_free_fail, "FRE Fail ") \
+ EM(netfs_trace_tcon_ref_free_ipc, "FRE Ipc ") \
+ EM(netfs_trace_tcon_ref_free_ipc_fail, "FRE Ipc-F ") \
+ EM(netfs_trace_tcon_ref_free_reconnect_server, "FRE Reconn") \
+ EM(netfs_trace_tcon_ref_get_cancelled_close, "GET Cn-Cls") \
+ EM(netfs_trace_tcon_ref_get_dfs_refer, "GET DfsRef") \
+ EM(netfs_trace_tcon_ref_get_find, "GET Find ") \
+ EM(netfs_trace_tcon_ref_get_find_sess_tcon, "GET FndSes") \
+ EM(netfs_trace_tcon_ref_get_reconnect_server, "GET Reconn") \
+ EM(netfs_trace_tcon_ref_new, "NEW ") \
+ EM(netfs_trace_tcon_ref_new_ipc, "NEW Ipc ") \
+ EM(netfs_trace_tcon_ref_new_reconnect_server, "NEW Reconn") \
+ EM(netfs_trace_tcon_ref_put_cancelled_close, "PUT Cn-Cls") \
+ EM(netfs_trace_tcon_ref_put_cancelled_close_fid, "PUT Cn-Fid") \
+ EM(netfs_trace_tcon_ref_put_cancelled_mid, "PUT Cn-Mid") \
+ EM(netfs_trace_tcon_ref_put_mnt_ctx, "PUT MntCtx") \
+ EM(netfs_trace_tcon_ref_put_reconnect_server, "PUT Reconn") \
+ EM(netfs_trace_tcon_ref_put_tlink, "PUT Tlink ") \
+ EM(netfs_trace_tcon_ref_see_cancelled_close, "SEE Cn-Cls") \
+ EM(netfs_trace_tcon_ref_see_fscache_collision, "SEE FV-CO!") \
+ EM(netfs_trace_tcon_ref_see_fscache_okay, "SEE FV-Ok ") \
+ EM(netfs_trace_tcon_ref_see_fscache_relinq, "SEE FV-Rlq") \
+ E_(netfs_trace_tcon_ref_see_umount, "SEE Umount")
+
+#undef EM
+#undef E_
+
+/*
+ * Define those tracing enums.
+ */
+#ifndef __SMB3_DECLARE_TRACE_ENUMS_ONCE_ONLY
+#define __SMB3_DECLARE_TRACE_ENUMS_ONCE_ONLY
+
+#define EM(a, b) a,
+#define E_(a, b) a
+
+enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);
+
+#undef EM
+#undef E_
+#endif
+
+/*
+ * Export enum symbols via userspace.
+ */
+#define EM(a, b) TRACE_DEFINE_ENUM(a);
+#define E_(a, b) TRACE_DEFINE_ENUM(a);
+
+smb3_tcon_ref_traces;
+
+#undef EM
+#undef E_
+
+/*
+ * Now redefine the EM() and E_() macros to map the enums to the strings that
+ * will be printed in the output.
+ */
+#define EM(a, b) { a, b },
+#define E_(a, b) { a, b }
/* For logging errors in read or write */
DECLARE_EVENT_CLASS(smb3_rw_err_class,
@@ -1125,6 +1189,30 @@
DEFINE_SMB3_CREDIT_EVENT(overflow_credits);
DEFINE_SMB3_CREDIT_EVENT(set_credits);
+
+TRACE_EVENT(smb3_tcon_ref,
+ TP_PROTO(unsigned int tcon_debug_id, int ref,
+ enum smb3_tcon_ref_trace trace),
+ TP_ARGS(tcon_debug_id, ref, trace),
+ TP_STRUCT__entry(
+ __field(unsigned int, tcon)
+ __field(int, ref)
+ __field(enum smb3_tcon_ref_trace, trace)
+ ),
+ TP_fast_assign(
+ __entry->tcon = tcon_debug_id;
+ __entry->ref = ref;
+ __entry->trace = trace;
+ ),
+ TP_printk("TC=%08x %s r=%u",
+ __entry->tcon,
+ __print_symbolic(__entry->trace, smb3_tcon_ref_traces),
+ __entry->ref)
+ );
+
+
+#undef EM
+#undef E_
#endif /* _CIFS_TRACE_H */
#undef TRACE_INCLUDE_PATH
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index 994d701..ddf1a3a 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -909,12 +909,15 @@
list_del_init(&mid->qhead);
mid->mid_flags |= MID_DELETED;
}
+ spin_unlock(&server->mid_lock);
cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n",
__func__, mid->mid, mid->mid_state);
rc = -EIO;
+ goto sync_mid_done;
}
spin_unlock(&server->mid_lock);
+sync_mid_done:
release_mid(mid);
return rc;
}
@@ -1057,9 +1060,11 @@
index = (uint)atomic_inc_return(&ses->chan_seq);
index %= ses->chan_count;
}
+
+ server = ses->chans[index].server;
spin_unlock(&ses->chan_lock);
- return ses->chans[index].server;
+ return server;
}
int
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index 1b59430..202ff91 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -711,7 +711,7 @@
__le16 StructureSize; /* 60 */
__le16 Flags;
__le32 Reserved;
- struct_group(network_open_info,
+ struct_group_attr(network_open_info, __packed,
__le64 CreationTime;
__le64 LastAccessTime;
__le64 LastWriteTime;
diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h
index 686b321..f4e5519 100644
--- a/fs/smb/server/ksmbd_netlink.h
+++ b/fs/smb/server/ksmbd_netlink.h
@@ -340,23 +340,24 @@
/*
* Share config flags.
*/
-#define KSMBD_SHARE_FLAG_INVALID (0)
-#define KSMBD_SHARE_FLAG_AVAILABLE BIT(0)
-#define KSMBD_SHARE_FLAG_BROWSEABLE BIT(1)
-#define KSMBD_SHARE_FLAG_WRITEABLE BIT(2)
-#define KSMBD_SHARE_FLAG_READONLY BIT(3)
-#define KSMBD_SHARE_FLAG_GUEST_OK BIT(4)
-#define KSMBD_SHARE_FLAG_GUEST_ONLY BIT(5)
-#define KSMBD_SHARE_FLAG_STORE_DOS_ATTRS BIT(6)
-#define KSMBD_SHARE_FLAG_OPLOCKS BIT(7)
-#define KSMBD_SHARE_FLAG_PIPE BIT(8)
-#define KSMBD_SHARE_FLAG_HIDE_DOT_FILES BIT(9)
-#define KSMBD_SHARE_FLAG_INHERIT_OWNER BIT(10)
-#define KSMBD_SHARE_FLAG_STREAMS BIT(11)
-#define KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS BIT(12)
-#define KSMBD_SHARE_FLAG_ACL_XATTR BIT(13)
-#define KSMBD_SHARE_FLAG_UPDATE BIT(14)
-#define KSMBD_SHARE_FLAG_CROSSMNT BIT(15)
+#define KSMBD_SHARE_FLAG_INVALID (0)
+#define KSMBD_SHARE_FLAG_AVAILABLE BIT(0)
+#define KSMBD_SHARE_FLAG_BROWSEABLE BIT(1)
+#define KSMBD_SHARE_FLAG_WRITEABLE BIT(2)
+#define KSMBD_SHARE_FLAG_READONLY BIT(3)
+#define KSMBD_SHARE_FLAG_GUEST_OK BIT(4)
+#define KSMBD_SHARE_FLAG_GUEST_ONLY BIT(5)
+#define KSMBD_SHARE_FLAG_STORE_DOS_ATTRS BIT(6)
+#define KSMBD_SHARE_FLAG_OPLOCKS BIT(7)
+#define KSMBD_SHARE_FLAG_PIPE BIT(8)
+#define KSMBD_SHARE_FLAG_HIDE_DOT_FILES BIT(9)
+#define KSMBD_SHARE_FLAG_INHERIT_OWNER BIT(10)
+#define KSMBD_SHARE_FLAG_STREAMS BIT(11)
+#define KSMBD_SHARE_FLAG_FOLLOW_SYMLINKS BIT(12)
+#define KSMBD_SHARE_FLAG_ACL_XATTR BIT(13)
+#define KSMBD_SHARE_FLAG_UPDATE BIT(14)
+#define KSMBD_SHARE_FLAG_CROSSMNT BIT(15)
+#define KSMBD_SHARE_FLAG_CONTINUOUS_AVAILABILITY BIT(16)
/*
* Tree connect request flags.
diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c
index c078818..c67fbc8 100644
--- a/fs/smb/server/server.c
+++ b/fs/smb/server/server.c
@@ -167,20 +167,17 @@
int rc;
bool is_chained = false;
- if (conn->ops->allocate_rsp_buf(work))
- return;
-
if (conn->ops->is_transform_hdr &&
conn->ops->is_transform_hdr(work->request_buf)) {
rc = conn->ops->decrypt_req(work);
- if (rc < 0) {
- conn->ops->set_rsp_status(work, STATUS_DATA_ERROR);
- goto send;
- }
-
+ if (rc < 0)
+ return;
work->encrypted = true;
}
+ if (conn->ops->allocate_rsp_buf(work))
+ return;
+
rc = conn->ops->init_rsp_hdr(work);
if (rc) {
/* either uid or tid is not correct */
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 5723bbf..3558241 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -535,6 +535,10 @@
if (cmd == SMB2_QUERY_INFO_HE) {
struct smb2_query_info_req *req;
+ if (get_rfc1002_len(work->request_buf) <
+ offsetof(struct smb2_query_info_req, OutputBufferLength))
+ return -EINVAL;
+
req = smb2_get_msg(work->request_buf);
if ((req->InfoType == SMB2_O_INFO_FILE &&
(req->FileInfoClass == FILE_FULL_EA_INFORMATION ||
@@ -1984,7 +1988,12 @@
write_unlock(&sess->tree_conns_lock);
rsp->StructureSize = cpu_to_le16(16);
out_err1:
- rsp->Capabilities = 0;
+ if (server_conf.flags & KSMBD_GLOBAL_FLAG_DURABLE_HANDLE &&
+ test_share_config_flag(share,
+ KSMBD_SHARE_FLAG_CONTINUOUS_AVAILABILITY))
+ rsp->Capabilities = SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY;
+ else
+ rsp->Capabilities = 0;
rsp->Reserved = 0;
/* default manual caching */
rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING;
@@ -3498,7 +3507,9 @@
memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE);
if (dh_info.type == DURABLE_REQ_V2 || dh_info.type == DURABLE_REQ) {
- if (dh_info.type == DURABLE_REQ_V2 && dh_info.persistent)
+ if (dh_info.type == DURABLE_REQ_V2 && dh_info.persistent &&
+ test_share_config_flag(work->tcon->share_conf,
+ KSMBD_SHARE_FLAG_CONTINUOUS_AVAILABILITY))
fp->is_persistent = true;
else
fp->is_durable = true;
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 22f0f3d..51b1b0b 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -754,10 +754,15 @@
goto out4;
}
+ /*
+ * explicitly handle file overwrite case, for compatibility with
+ * filesystems that may not support rename flags (e.g: fuse)
+ */
if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) {
err = -EEXIST;
goto out4;
}
+ flags &= ~(RENAME_NOREPLACE);
if (old_child == trap) {
err = -EINVAL;
diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c
index aa34113..16bd693 100644
--- a/fs/squashfs/inode.c
+++ b/fs/squashfs/inode.c
@@ -48,6 +48,10 @@
gid_t i_gid;
int err;
+ inode->i_ino = le32_to_cpu(sqsh_ino->inode_number);
+ if (inode->i_ino == 0)
+ return -EINVAL;
+
err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &i_uid);
if (err)
return err;
@@ -58,7 +62,6 @@
i_uid_write(inode, i_uid);
i_gid_write(inode, i_gid);
- inode->i_ino = le32_to_cpu(sqsh_ino->inode_number);
inode_set_mtime(inode, le32_to_cpu(sqsh_ino->mtime), 0);
inode_set_atime(inode, inode_get_mtime_sec(inode), 0);
inode_set_ctime(inode, inode_get_mtime_sec(inode), 0);
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 6b7652f..7cd6402 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -463,6 +463,8 @@
kn = kernfs_find_and_get(kobj->sd, attr->name);
if (kn)
kernfs_break_active_protection(kn);
+ else
+ kobject_put(kobj);
return kn;
}
EXPORT_SYMBOL_GPL(sysfs_break_active_protection);
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index dc067ee..a878cea 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -37,6 +37,7 @@
struct eventfs_root_inode {
struct eventfs_inode ei;
+ struct inode *parent_inode;
struct dentry *events_dir;
};
@@ -68,11 +69,25 @@
EVENTFS_SAVE_MODE = BIT(16),
EVENTFS_SAVE_UID = BIT(17),
EVENTFS_SAVE_GID = BIT(18),
- EVENTFS_TOPLEVEL = BIT(19),
};
#define EVENTFS_MODE_MASK (EVENTFS_SAVE_MODE - 1)
+static void free_ei_rcu(struct rcu_head *rcu)
+{
+ struct eventfs_inode *ei = container_of(rcu, struct eventfs_inode, rcu);
+ struct eventfs_root_inode *rei;
+
+ kfree(ei->entry_attrs);
+ kfree_const(ei->name);
+ if (ei->is_events) {
+ rei = get_root_inode(ei);
+ kfree(rei);
+ } else {
+ kfree(ei);
+ }
+}
+
/*
* eventfs_inode reference count management.
*
@@ -84,18 +99,17 @@
static void release_ei(struct kref *ref)
{
struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
- struct eventfs_root_inode *rei;
+ const struct eventfs_entry *entry;
WARN_ON_ONCE(!ei->is_freed);
- kfree(ei->entry_attrs);
- kfree_const(ei->name);
- if (ei->is_events) {
- rei = get_root_inode(ei);
- kfree_rcu(rei, ei.rcu);
- } else {
- kfree_rcu(ei, rcu);
+ for (int i = 0; i < ei->nr_entries; i++) {
+ entry = &ei->entries[i];
+ if (entry->release)
+ entry->release(entry->name, ei->data);
}
+
+ call_rcu(&ei->rcu, free_ei_rcu);
}
static inline void put_ei(struct eventfs_inode *ei)
@@ -112,6 +126,18 @@
}
}
+/*
+ * Called when creation of an ei fails, do not call release() functions.
+ */
+static inline void cleanup_ei(struct eventfs_inode *ei)
+{
+ if (ei) {
+ /* Set nr_entries to 0 to prevent release() function being called */
+ ei->nr_entries = 0;
+ free_ei(ei);
+ }
+}
+
static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
{
if (ei)
@@ -181,21 +207,7 @@
* determined by the parent directory.
*/
if (dentry->d_inode->i_mode & S_IFDIR) {
- /*
- * The events directory dentry is never freed, unless its
- * part of an instance that is deleted. It's attr is the
- * default for its child files and directories.
- * Do not update it. It's not used for its own mode or ownership.
- */
- if (ei->is_events) {
- /* But it still needs to know if it was modified */
- if (iattr->ia_valid & ATTR_UID)
- ei->attr.mode |= EVENTFS_SAVE_UID;
- if (iattr->ia_valid & ATTR_GID)
- ei->attr.mode |= EVENTFS_SAVE_GID;
- } else {
- update_attr(&ei->attr, iattr);
- }
+ update_attr(&ei->attr, iattr);
} else {
name = dentry->d_name.name;
@@ -213,18 +225,25 @@
return ret;
}
-static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb)
+static void update_events_attr(struct eventfs_inode *ei, struct super_block *sb)
{
- struct inode *root;
+ struct eventfs_root_inode *rei;
+ struct inode *parent;
- /* Only update if the "events" was on the top level */
- if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL))
- return;
+ rei = get_root_inode(ei);
- /* Get the tracefs root inode. */
- root = d_inode(sb->s_root);
- ei->attr.uid = root->i_uid;
- ei->attr.gid = root->i_gid;
+ /* Use the parent inode permissions unless root set its permissions */
+ parent = rei->parent_inode;
+
+ if (rei->ei.attr.mode & EVENTFS_SAVE_UID)
+ ei->attr.uid = rei->ei.attr.uid;
+ else
+ ei->attr.uid = parent->i_uid;
+
+ if (rei->ei.attr.mode & EVENTFS_SAVE_GID)
+ ei->attr.gid = rei->ei.attr.gid;
+ else
+ ei->attr.gid = parent->i_gid;
}
static void set_top_events_ownership(struct inode *inode)
@@ -233,10 +252,10 @@
struct eventfs_inode *ei = ti->private;
/* The top events directory doesn't get automatically updated */
- if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL))
+ if (!ei || !ei->is_events)
return;
- update_top_events_attr(ei, inode->i_sb);
+ update_events_attr(ei, inode->i_sb);
if (!(ei->attr.mode & EVENTFS_SAVE_UID))
inode->i_uid = ei->attr.uid;
@@ -265,7 +284,7 @@
return generic_permission(idmap, inode, mask);
}
-static const struct inode_operations eventfs_root_dir_inode_operations = {
+static const struct inode_operations eventfs_dir_inode_operations = {
.lookup = eventfs_root_lookup,
.setattr = eventfs_set_attr,
.getattr = eventfs_get_attr,
@@ -282,6 +301,35 @@
.llseek = generic_file_llseek,
};
+/*
+ * On a remount of tracefs, if UID or GID options are set, then
+ * the mount point inode permissions should be used.
+ * Reset the saved permission flags appropriately.
+ */
+void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid)
+{
+ struct eventfs_inode *ei = ti->private;
+
+ if (!ei)
+ return;
+
+ if (update_uid)
+ ei->attr.mode &= ~EVENTFS_SAVE_UID;
+
+ if (update_gid)
+ ei->attr.mode &= ~EVENTFS_SAVE_GID;
+
+ if (!ei->entry_attrs)
+ return;
+
+ for (int i = 0; i < ei->nr_entries; i++) {
+ if (update_uid)
+ ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID;
+ if (update_gid)
+ ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID;
+ }
+}
+
/* Return the evenfs_inode of the "events" directory */
static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
{
@@ -304,7 +352,7 @@
// Walk upwards until you find the events inode
} while (!ei->is_events);
- update_top_events_attr(ei, dentry->d_sb);
+ update_events_attr(ei, dentry->d_sb);
return ei;
}
@@ -336,6 +384,7 @@
/**
* lookup_file - look up a file in the tracefs filesystem
+ * @parent_ei: Pointer to the eventfs_inode that represents parent of the file
* @dentry: the dentry to look up
* @mode: the permission that the file should have.
* @attr: saved attributes changed by user
@@ -389,6 +438,7 @@
/**
* lookup_dir_entry - look up a dir in the tracefs filesystem
* @dentry: the directory to look up
+ * @pei: Pointer to the parent eventfs_inode if available
* @ei: the eventfs_inode that represents the directory to create
*
* This function will look up a dentry for a directory represented by
@@ -408,7 +458,7 @@
update_inode_attr(dentry, inode, &ei->attr,
S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
- inode->i_op = &eventfs_root_dir_inode_operations;
+ inode->i_op = &eventfs_dir_inode_operations;
inode->i_fop = &eventfs_file_operations;
/* All directories will have the same inode number */
@@ -478,16 +528,20 @@
/**
* lookup_file_dentry - create a dentry for a file of an eventfs_inode
+ * @dentry: The parent dentry under which the new file's dentry will be created
* @ei: the eventfs_inode that the file will be created under
* @idx: the index into the entry_attrs[] of the @ei
- * @parent: The parent dentry of the created file.
- * @name: The name of the file to create
* @mode: The mode of the file.
* @data: The data to use to set the inode of the file with on open()
* @fops: The fops of the file to be created.
*
- * Create a dentry for a file of an eventfs_inode @ei and place it into the
- * address located at @e_dentry.
+ * This function creates a dentry for a file associated with an
+ * eventfs_inode @ei. It uses the entry attributes specified by @idx,
+ * if available. The file will have the specified @mode and its inode will be
+ * set up with @data upon open. The file operations will be set to @fops.
+ *
+ * Return: Returns a pointer to the newly created file's dentry or an error
+ * pointer.
*/
static struct dentry *
lookup_file_dentry(struct dentry *dentry,
@@ -728,7 +782,7 @@
/* Was the parent freed? */
if (list_empty(&ei->list)) {
- free_ei(ei);
+ cleanup_ei(ei);
ei = NULL;
}
return ei;
@@ -775,6 +829,7 @@
// Note: we have a ref to the dentry from tracefs_start_creating()
rei = get_root_inode(ei);
rei->events_dir = dentry;
+ rei->parent_inode = d_inode(dentry->d_sb->s_root);
ei->entries = entries;
ei->nr_entries = size;
@@ -784,29 +839,26 @@
uid = d_inode(dentry->d_parent)->i_uid;
gid = d_inode(dentry->d_parent)->i_gid;
- /*
- * If the events directory is of the top instance, then parent
- * is NULL. Set the attr.mode to reflect this and its permissions will
- * default to the tracefs root dentry.
- */
- if (!parent)
- ei->attr.mode = EVENTFS_TOPLEVEL;
-
- /* This is used as the default ownership of the files and directories */
ei->attr.uid = uid;
ei->attr.gid = gid;
+ /*
+ * When the "events" directory is created, it takes on the
+ * permissions of its parent. But can be reset on remount.
+ */
+ ei->attr.mode |= EVENTFS_SAVE_UID | EVENTFS_SAVE_GID;
+
INIT_LIST_HEAD(&ei->children);
INIT_LIST_HEAD(&ei->list);
ti = get_tracefs(inode);
- ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE;
+ ti->flags |= TRACEFS_EVENT_INODE;
ti->private = ei;
inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
inode->i_uid = uid;
inode->i_gid = gid;
- inode->i_op = &eventfs_root_dir_inode_operations;
+ inode->i_op = &eventfs_dir_inode_operations;
inode->i_fop = &eventfs_file_operations;
dentry->d_fsdata = get_ei(ei);
@@ -829,7 +881,7 @@
return ei;
fail:
- free_ei(ei);
+ cleanup_ei(ei);
tracefs_failed_creating(dentry);
return ERR_PTR(-ENOMEM);
}
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 5545e6b..417c840 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -30,20 +30,47 @@
static int tracefs_mount_count;
static bool tracefs_registered;
+/*
+ * Keep track of all tracefs_inodes in order to update their
+ * flags if necessary on a remount.
+ */
+static DEFINE_SPINLOCK(tracefs_inode_lock);
+static LIST_HEAD(tracefs_inodes);
+
static struct inode *tracefs_alloc_inode(struct super_block *sb)
{
struct tracefs_inode *ti;
+ unsigned long flags;
ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL);
if (!ti)
return NULL;
+ spin_lock_irqsave(&tracefs_inode_lock, flags);
+ list_add_rcu(&ti->list, &tracefs_inodes);
+ spin_unlock_irqrestore(&tracefs_inode_lock, flags);
+
return &ti->vfs_inode;
}
+static void tracefs_free_inode_rcu(struct rcu_head *rcu)
+{
+ struct tracefs_inode *ti;
+
+ ti = container_of(rcu, struct tracefs_inode, rcu);
+ kmem_cache_free(tracefs_inode_cachep, ti);
+}
+
static void tracefs_free_inode(struct inode *inode)
{
- kmem_cache_free(tracefs_inode_cachep, get_tracefs(inode));
+ struct tracefs_inode *ti = get_tracefs(inode);
+ unsigned long flags;
+
+ spin_lock_irqsave(&tracefs_inode_lock, flags);
+ list_del_rcu(&ti->list);
+ spin_unlock_irqrestore(&tracefs_inode_lock, flags);
+
+ call_rcu(&ti->rcu, tracefs_free_inode_rcu);
}
static ssize_t default_read_file(struct file *file, char __user *buf,
@@ -153,16 +180,39 @@
{
struct tracefs_inode *ti = get_tracefs(inode);
struct inode *root_inode = ti->private;
+ kuid_t uid;
+ kgid_t gid;
+
+ uid = root_inode->i_uid;
+ gid = root_inode->i_gid;
+
+ /*
+ * If the root is not the mount point, then check the root's
+ * permissions. If it was never set, then default to the
+ * mount point.
+ */
+ if (root_inode != d_inode(root_inode->i_sb->s_root)) {
+ struct tracefs_inode *rti;
+
+ rti = get_tracefs(root_inode);
+ root_inode = d_inode(root_inode->i_sb->s_root);
+
+ if (!(rti->flags & TRACEFS_UID_PERM_SET))
+ uid = root_inode->i_uid;
+
+ if (!(rti->flags & TRACEFS_GID_PERM_SET))
+ gid = root_inode->i_gid;
+ }
/*
* If this inode has never been referenced, then update
* the permissions to the superblock.
*/
if (!(ti->flags & TRACEFS_UID_PERM_SET))
- inode->i_uid = root_inode->i_uid;
+ inode->i_uid = uid;
if (!(ti->flags & TRACEFS_GID_PERM_SET))
- inode->i_gid = root_inode->i_gid;
+ inode->i_gid = gid;
}
static int tracefs_permission(struct mnt_idmap *idmap,
@@ -313,6 +363,8 @@
struct tracefs_fs_info *fsi = sb->s_fs_info;
struct inode *inode = d_inode(sb->s_root);
struct tracefs_mount_opts *opts = &fsi->mount_opts;
+ struct tracefs_inode *ti;
+ bool update_uid, update_gid;
umode_t tmp_mode;
/*
@@ -332,6 +384,25 @@
if (!remount || opts->opts & BIT(Opt_gid))
inode->i_gid = opts->gid;
+ if (remount && (opts->opts & BIT(Opt_uid) || opts->opts & BIT(Opt_gid))) {
+
+ update_uid = opts->opts & BIT(Opt_uid);
+ update_gid = opts->opts & BIT(Opt_gid);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ti, &tracefs_inodes, list) {
+ if (update_uid)
+ ti->flags &= ~TRACEFS_UID_PERM_SET;
+
+ if (update_gid)
+ ti->flags &= ~TRACEFS_GID_PERM_SET;
+
+ if (ti->flags & TRACEFS_EVENT_INODE)
+ eventfs_remount(ti, update_uid, update_gid);
+ }
+ rcu_read_unlock();
+ }
+
return 0;
}
@@ -398,7 +469,22 @@
return !(ei && ei->is_freed);
}
+static void tracefs_d_iput(struct dentry *dentry, struct inode *inode)
+{
+ struct tracefs_inode *ti = get_tracefs(inode);
+
+ /*
+ * This inode is being freed and cannot be used for
+ * eventfs. Clear the flag so that it doesn't call into
+ * eventfs during the remount flag updates. The eventfs_inode
+ * gets freed after an RCU cycle, so the content will still
+ * be safe if the iteration is going on now.
+ */
+ ti->flags &= ~TRACEFS_EVENT_INODE;
+}
+
static const struct dentry_operations tracefs_dentry_operations = {
+ .d_iput = tracefs_d_iput,
.d_revalidate = tracefs_d_revalidate,
.d_release = tracefs_d_release,
};
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 15c26f9..f704d834 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -4,15 +4,18 @@
enum {
TRACEFS_EVENT_INODE = BIT(1),
- TRACEFS_EVENT_TOP_INODE = BIT(2),
- TRACEFS_GID_PERM_SET = BIT(3),
- TRACEFS_UID_PERM_SET = BIT(4),
- TRACEFS_INSTANCE_INODE = BIT(5),
+ TRACEFS_GID_PERM_SET = BIT(2),
+ TRACEFS_UID_PERM_SET = BIT(3),
+ TRACEFS_INSTANCE_INODE = BIT(4),
};
struct tracefs_inode {
- struct inode vfs_inode;
+ union {
+ struct inode vfs_inode;
+ struct rcu_head rcu;
+ };
/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
+ struct list_head list;
unsigned long flags;
void *private;
};
@@ -73,6 +76,7 @@
struct dentry *tracefs_failed_creating(struct dentry *dentry);
struct inode *tracefs_get_inode(struct super_block *sb);
+void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid);
void eventfs_d_release(struct dentry *dentry);
#endif /* _TRACEFS_INTERNAL_H */
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index c6a124e..964fa7f 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -1048,7 +1048,7 @@
zonefs_info(sb, "Zone group \"%s\" has %u file%s\n",
zonefs_zgroup_name(ztype),
zgroup->g_nr_zones,
- zgroup->g_nr_zones > 1 ? "s" : "");
+ str_plural(zgroup->g_nr_zones));
return 0;
}
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 5de954e..e7796f3 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -911,17 +911,19 @@
* acpi_dev_hid_uid_match - Match device by supplied HID and UID
* @adev: ACPI device to match.
* @hid2: Hardware ID of the device.
- * @uid2: Unique ID of the device, pass 0 or NULL to not check _UID.
+ * @uid2: Unique ID of the device, pass NULL to not check _UID.
*
* Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2
* will be treated as a match. If user wants to validate @uid2, it should be
* done before calling this function.
*
- * Returns: %true if matches or @uid2 is 0 or NULL, %false otherwise.
+ * Returns: %true if matches or @uid2 is NULL, %false otherwise.
*/
#define acpi_dev_hid_uid_match(adev, hid2, uid2) \
(acpi_dev_hid_match(adev, hid2) && \
- (!(uid2) || acpi_dev_uid_match(adev, uid2)))
+ /* Distinguish integer 0 from NULL @uid2 */ \
+ (_Generic(uid2, ACPI_STR_TYPES(!(uid2)), default: 0) || \
+ acpi_dev_uid_match(adev, uid2)))
void acpi_dev_clear_dependencies(struct acpi_device *supplier);
bool acpi_dev_ready_for_enumeration(const struct acpi_device *device);
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 0c06957..d4f581c 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -294,5 +294,13 @@
#define io_stop_wc() do { } while (0)
#endif
+/*
+ * Architectures that guarantee an implicit smp_mb() in switch_mm()
+ * can override smp_mb__after_switch_mm.
+ */
+#ifndef smp_mb__after_switch_mm
+# define smp_mb__after_switch_mm() smp_mb()
+#endif
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 6e79442..b7de3a4 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -156,7 +156,10 @@
#else /* !CONFIG_BUG */
#ifndef HAVE_ARCH_BUG
-#define BUG() do {} while (1)
+#define BUG() do { \
+ do {} while (1); \
+ unreachable(); \
+} while (0)
#endif
#ifndef HAVE_ARCH_BUG_ON
diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
index 87e3d49..814207e 100644
--- a/include/asm-generic/hyperv-tlfs.h
+++ b/include/asm-generic/hyperv-tlfs.h
@@ -512,13 +512,9 @@
u32 proximity_info_valid : 1;
} __packed;
-/* Not a union in windows but useful for zeroing */
-union hv_proximity_domain_info {
- struct {
- u32 domain_id;
- struct hv_proximity_domain_flags flags;
- };
- u64 as_uint64;
+struct hv_proximity_domain_info {
+ u32 domain_id;
+ struct hv_proximity_domain_flags flags;
} __packed;
struct hv_lp_startup_status {
@@ -532,14 +528,13 @@
} __packed;
/* HvAddLogicalProcessor hypercall */
-struct hv_add_logical_processor_in {
+struct hv_input_add_logical_processor {
u32 lp_index;
u32 apic_id;
- union hv_proximity_domain_info proximity_domain_info;
- u64 flags;
+ struct hv_proximity_domain_info proximity_domain_info;
} __packed;
-struct hv_add_logical_processor_out {
+struct hv_output_add_logical_processor {
struct hv_lp_startup_status startup_status;
} __packed;
@@ -560,7 +555,7 @@
u8 padding[3];
u8 subnode_type;
u64 subnode_id;
- union hv_proximity_domain_info proximity_domain_info;
+ struct hv_proximity_domain_info proximity_domain_info;
u64 flags;
} __packed;
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index 9993577..8fe7aaa 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -21,6 +21,7 @@
#include <linux/types.h>
#include <linux/atomic.h>
#include <linux/bitops.h>
+#include <acpi/acpi_numa.h>
#include <linux/cpumask.h>
#include <linux/nmi.h>
#include <asm/ptrace.h>
@@ -67,6 +68,19 @@
bool hv_isolation_type_snp(void);
bool hv_isolation_type_tdx(void);
+static inline struct hv_proximity_domain_info hv_numa_node_to_pxm_info(int node)
+{
+ struct hv_proximity_domain_info pxm_info = {};
+
+ if (node != NUMA_NO_NODE) {
+ pxm_info.domain_id = node_to_pxm(node);
+ pxm_info.flags.proximity_info_valid = 1;
+ pxm_info.flags.proximity_preferred = 1;
+ }
+
+ return pxm_info;
+}
+
/* Helper functions that provide a consistent pattern for checking Hyper-V hypercall status. */
static inline int hv_result(u64 status)
{
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 172c918..69e7da3 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -128,6 +128,8 @@
#define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4))
/* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */
#define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5))
+/* return partition scanning errors */
+#define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6))
struct gendisk {
/*
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index ca73940..3f4b4ac 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -10,6 +10,7 @@
#ifdef __KERNEL__
#include <linux/kernel.h>
#include <linux/types.h>
+bool __init cmdline_has_extra_options(void);
#else /* !__KERNEL__ */
/*
* NOTE: This is only for tools/bootconfig, because tools/bootconfig will
@@ -287,7 +288,12 @@
int __init xbc_get_info(int *node_size, size_t *data_size);
/* XBC cleanup data structures */
-void __init xbc_exit(void);
+void __init _xbc_exit(bool early);
+
+static inline void xbc_exit(void)
+{
+ _xbc_exit(false);
+}
/* XBC embedded bootconfig data in kernel */
#ifdef CONFIG_BOOT_CONFIG_EMBED
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 00623f4..0fa56d6 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -286,6 +286,11 @@
return 0;
}
+static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk)
+{
+ return 0;
+}
+
static inline void clk_rate_exclusive_put(struct clk *clk) {}
#endif
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index c00cc6c..8c252e0 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -268,7 +268,7 @@
* - When one operand is a null pointer constant (i.e. when x is an integer
* constant expression) and the other is an object pointer (i.e. our
* third operand), the conditional operator returns the type of the
- * object pointer operand (i.e. "int *). Here, within the sizeof(), we
+ * object pointer operand (i.e. "int *"). Here, within the sizeof(), we
* would then get:
* sizeof(*((int *)(...)) == sizeof(int) == 4
* - When one operand is a void pointer (i.e. when x is not an integer
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 272e4e7..861c3bf 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -221,7 +221,18 @@
static inline void cpuhp_report_idle_dead(void) { }
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
+#ifdef CONFIG_CPU_MITIGATIONS
extern bool cpu_mitigations_off(void);
extern bool cpu_mitigations_auto_nosmt(void);
+#else
+static inline bool cpu_mitigations_off(void)
+{
+ return true;
+}
+static inline bool cpu_mitigations_auto_nosmt(void)
+{
+ return false;
+}
+#endif
#endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index e06bad4..c3f9bb6 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -682,4 +682,11 @@
return dma_fence_is_array(fence) || dma_fence_is_chain(fence);
}
+#define DMA_FENCE_WARN(f, fmt, args...) \
+ do { \
+ struct dma_fence *__ff = (f); \
+ pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\
+ ##args); \
+ } while (0)
+
#endif /* __LINUX_DMA_FENCE_H */
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 224645f..2972318 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -608,6 +608,31 @@
}
/**
+ * eth_skb_pkt_type - Assign packet type if destination address does not match
+ * @skb: Assigned a packet type if address does not match @dev address
+ * @dev: Network device used to compare packet address against
+ *
+ * If the destination MAC address of the packet does not match the network
+ * device address, assign an appropriate packet type.
+ */
+static inline void eth_skb_pkt_type(struct sk_buff *skb,
+ const struct net_device *dev)
+{
+ const struct ethhdr *eth = eth_hdr(skb);
+
+ if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) {
+ if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
+ if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
+ skb->pkt_type = PACKET_BROADCAST;
+ else
+ skb->pkt_type = PACKET_MULTICAST;
+ } else {
+ skb->pkt_type = PACKET_OTHERHOST;
+ }
+ }
+}
+
+/**
* eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame
* @skb: Buffer to pad
*
diff --git a/include/linux/filter.h b/include/linux/filter.h
index c99bc3d..219ee7a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -963,6 +963,7 @@
bool bpf_jit_supports_exceptions(void);
bool bpf_jit_supports_ptr_xchg(void);
bool bpf_jit_supports_arena(void);
+u64 bpf_arch_uaddress_limit(void);
void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);
bool bpf_helper_changes_pkt_data(void *func);
diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h
index 5c28298..366243e 100644
--- a/include/linux/firmware/qcom/qcom_qseecom.h
+++ b/include/linux/firmware/qcom/qcom_qseecom.h
@@ -10,6 +10,7 @@
#define __QCOM_QSEECOM_H
#include <linux/auxiliary_bus.h>
+#include <linux/dma-mapping.h>
#include <linux/types.h>
#include <linux/firmware/qcom/qcom_scm.h>
@@ -25,11 +26,56 @@
};
/**
+ * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client.
+ * @client: The QSEECOM client device.
+ *
+ * Returns the SCM device under which the provided QSEECOM client device
+ * operates. This function is intended to be used for DMA allocations.
+ */
+static inline struct device *qseecom_scm_dev(struct qseecom_client *client)
+{
+ return client->aux_dev.dev.parent->parent;
+}
+
+/**
+ * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client.
+ * @client: The QSEECOM client to allocate the memory for.
+ * @size: The number of bytes to allocate.
+ * @dma_handle: Pointer to where the DMA address should be stored.
+ * @gfp: Allocation flags.
+ *
+ * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for
+ * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details.
+ */
+static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp)
+{
+ return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp);
+}
+
+/**
+ * dma_free_coherent() - Free QSEECOM DMA memory.
+ * @client: The QSEECOM client for which the memory has been allocated.
+ * @size: The number of bytes allocated.
+ * @cpu_addr: Virtual memory address to free.
+ * @dma_handle: DMA memory address to free.
+ *
+ * Wrapper function for dma_free_coherent(), freeing memory previously
+ * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for
+ * details.
+ */
+static inline void qseecom_dma_free(struct qseecom_client *client, size_t size,
+ void *cpu_addr, dma_addr_t dma_handle)
+{
+ return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle);
+}
+
+/**
* qcom_qseecom_app_send() - Send to and receive data from a given QSEE app.
* @client: The QSEECOM client associated with the target app.
- * @req: Request buffer sent to the app (must be DMA-mappable).
+ * @req: DMA address of the request buffer sent to the app.
* @req_size: Size of the request buffer.
- * @rsp: Response buffer, written to by the app (must be DMA-mappable).
+ * @rsp: DMA address of the response buffer, written to by the app.
* @rsp_size: Size of the response buffer.
*
* Sends a request to the QSEE app associated with the given client and read
@@ -43,8 +89,9 @@
*
* Return: Zero on success, nonzero on failure.
*/
-static inline int qcom_qseecom_app_send(struct qseecom_client *client, void *req, size_t req_size,
- void *rsp, size_t rsp_size)
+static inline int qcom_qseecom_app_send(struct qseecom_client *client,
+ dma_addr_t req, size_t req_size,
+ dma_addr_t rsp, size_t rsp_size)
{
return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size);
}
diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h
index ccaf288..aaa19f9 100644
--- a/include/linux/firmware/qcom/qcom_scm.h
+++ b/include/linux/firmware/qcom/qcom_scm.h
@@ -118,8 +118,8 @@
#ifdef CONFIG_QCOM_QSEECOM
int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id);
-int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp,
- size_t rsp_size);
+int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size,
+ dma_addr_t rsp, size_t rsp_size);
#else /* CONFIG_QCOM_QSEECOM */
@@ -128,9 +128,9 @@
return -EINVAL;
}
-static inline int qcom_scm_qseecom_app_send(u32 app_id, void *req,
- size_t req_size, void *rsp,
- size_t rsp_size)
+static inline int qcom_scm_qseecom_app_send(u32 app_id,
+ dma_addr_t req, size_t req_size,
+ dma_addr_t rsp, size_t rsp_size)
{
return -EINVAL;
}
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 868c8fb..13becaf 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -2,6 +2,8 @@
#ifndef __LINUX_GFP_TYPES_H
#define __LINUX_GFP_TYPES_H
+#include <linux/bits.h>
+
/* The typedef is in types.h but we want the documentation here */
#if 0
/**
diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h
index 6c75c8b..1a14e23 100644
--- a/include/linux/gpio/property.h
+++ b/include/linux/gpio/property.h
@@ -2,7 +2,6 @@
#ifndef __LINUX_GPIO_PROPERTY_H
#define __LINUX_GPIO_PROPERTY_H
-#include <dt-bindings/gpio/gpio.h> /* for GPIO_* flags */
#include <linux/property.h>
#define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6ef0557b..96ceb40 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -832,6 +832,7 @@
u32 gpadl_handle;
u32 size;
void *buffer;
+ bool decrypted;
};
struct vmbus_channel {
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 05df0e3..ac333ea 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -13,7 +13,7 @@
* A hint to not wake right away but delay until there are enough of
* tw's queued to match the number of CQEs the task is waiting for.
*
- * Must not be used wirh requests generating more than one CQE.
+ * Must not be used with requests generating more than one CQE.
* It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set.
*/
IOU_F_TWQ_LAZY_WAKE = 1,
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 147feeb..3f003d5 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -114,7 +114,7 @@
# define lockdep_softirq_enter() do { } while (0)
# define lockdep_softirq_exit() do { } while (0)
# define lockdep_hrtimer_enter(__hrtimer) false
-# define lockdep_hrtimer_exit(__context) do { } while (0)
+# define lockdep_hrtimer_exit(__context) do { (void)(__context); } while (0)
# define lockdep_posixtimer_enter() do { } while (0)
# define lockdep_posixtimer_exit() do { } while (0)
# define lockdep_irq_work_enter(__work) do { } while (0)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0436b91..b6bdaa1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1223,14 +1223,16 @@
* a large folio, it includes the number of times this page is mapped
* as part of that folio.
*
- * The result is undefined for pages which cannot be mapped into userspace.
- * For example SLAB or special types of pages. See function page_has_type().
- * They use this field in struct page differently.
+ * Will report 0 for pages which cannot be mapped into userspace, eg
+ * slab, page tables and similar.
*/
static inline int page_mapcount(struct page *page)
{
int mapcount = atomic_read(&page->_mapcount) + 1;
+ /* Handle page_has_type() pages */
+ if (mapcount < 0)
+ mapcount = 0;
if (unlikely(PageCompound(page)))
mapcount += folio_entire_mapcount(page_folio(page));
@@ -2207,11 +2209,6 @@
*/
#include <linux/vmstat.h>
-static __always_inline void *lowmem_page_address(const struct page *page)
-{
- return page_to_virt(page);
-}
-
#if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
#define HASHED_PAGE_VIRTUAL
#endif
@@ -2234,6 +2231,11 @@
void page_address_init(void);
#endif
+static __always_inline void *lowmem_page_address(const struct page *page)
+{
+ return page_to_virt(page);
+}
+
#if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL)
#define page_address(page) lowmem_page_address(page)
#define set_page_address(page, address) do { } while(0)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 652d778..4bf1c25 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -190,7 +190,6 @@
/* At least one page in this folio has the hwpoison flag set */
PG_has_hwpoisoned = PG_error,
- PG_hugetlb = PG_active,
PG_large_rmappable = PG_workingset, /* anon or file-backed */
};
@@ -458,30 +457,51 @@
TESTSETFLAG(uname, lname, policy) \
TESTCLEARFLAG(uname, lname, policy)
+#define FOLIO_TEST_FLAG_FALSE(name) \
+static inline bool folio_test_##name(const struct folio *folio) \
+{ return false; }
+#define FOLIO_SET_FLAG_NOOP(name) \
+static inline void folio_set_##name(struct folio *folio) { }
+#define FOLIO_CLEAR_FLAG_NOOP(name) \
+static inline void folio_clear_##name(struct folio *folio) { }
+#define __FOLIO_SET_FLAG_NOOP(name) \
+static inline void __folio_set_##name(struct folio *folio) { }
+#define __FOLIO_CLEAR_FLAG_NOOP(name) \
+static inline void __folio_clear_##name(struct folio *folio) { }
+#define FOLIO_TEST_SET_FLAG_FALSE(name) \
+static inline bool folio_test_set_##name(struct folio *folio) \
+{ return false; }
+#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \
+static inline bool folio_test_clear_##name(struct folio *folio) \
+{ return false; }
+
+#define FOLIO_FLAG_FALSE(name) \
+FOLIO_TEST_FLAG_FALSE(name) \
+FOLIO_SET_FLAG_NOOP(name) \
+FOLIO_CLEAR_FLAG_NOOP(name)
+
#define TESTPAGEFLAG_FALSE(uname, lname) \
-static inline bool folio_test_##lname(const struct folio *folio) { return false; } \
+FOLIO_TEST_FLAG_FALSE(lname) \
static inline int Page##uname(const struct page *page) { return 0; }
#define SETPAGEFLAG_NOOP(uname, lname) \
-static inline void folio_set_##lname(struct folio *folio) { } \
+FOLIO_SET_FLAG_NOOP(lname) \
static inline void SetPage##uname(struct page *page) { }
#define CLEARPAGEFLAG_NOOP(uname, lname) \
-static inline void folio_clear_##lname(struct folio *folio) { } \
+FOLIO_CLEAR_FLAG_NOOP(lname) \
static inline void ClearPage##uname(struct page *page) { }
#define __CLEARPAGEFLAG_NOOP(uname, lname) \
-static inline void __folio_clear_##lname(struct folio *folio) { } \
+__FOLIO_CLEAR_FLAG_NOOP(lname) \
static inline void __ClearPage##uname(struct page *page) { }
#define TESTSETFLAG_FALSE(uname, lname) \
-static inline bool folio_test_set_##lname(struct folio *folio) \
-{ return 0; } \
+FOLIO_TEST_SET_FLAG_FALSE(lname) \
static inline int TestSetPage##uname(struct page *page) { return 0; }
#define TESTCLEARFLAG_FALSE(uname, lname) \
-static inline bool folio_test_clear_##lname(struct folio *folio) \
-{ return 0; } \
+FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \
static inline int TestClearPage##uname(struct page *page) { return 0; }
#define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \
@@ -855,29 +875,6 @@
#define PG_head_mask ((1UL << PG_head))
-#ifdef CONFIG_HUGETLB_PAGE
-int PageHuge(const struct page *page);
-SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND)
-CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND)
-
-/**
- * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs
- * @folio: The folio to test.
- *
- * Context: Any context. Caller should have a reference on the folio to
- * prevent it from being turned into a tail page.
- * Return: True for hugetlbfs folios, false for anon folios or folios
- * belonging to other filesystems.
- */
-static inline bool folio_test_hugetlb(const struct folio *folio)
-{
- return folio_test_large(folio) &&
- test_bit(PG_hugetlb, const_folio_flags(folio, 1));
-}
-#else
-TESTPAGEFLAG_FALSE(Huge, hugetlb)
-#endif
-
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* PageHuge() only returns true for hugetlbfs pages, but not for
@@ -934,33 +931,22 @@
#endif
/*
- * Check if a page is currently marked HWPoisoned. Note that this check is
- * best effort only and inherently racy: there is no way to synchronize with
- * failing hardware.
- */
-static inline bool is_page_hwpoison(struct page *page)
-{
- if (PageHWPoison(page))
- return true;
- return PageHuge(page) && PageHWPoison(compound_head(page));
-}
-
-/*
* For pages that are never mapped to userspace (and aren't PageSlab),
* page_type may be used. Because it is initialised to -1, we invert the
* sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and
* __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and
- * low bits so that an underflow or overflow of page_mapcount() won't be
+ * low bits so that an underflow or overflow of _mapcount won't be
* mistaken for a page type value.
*/
#define PAGE_TYPE_BASE 0xf0000000
-/* Reserve 0x0000007f to catch underflows of page_mapcount */
+/* Reserve 0x0000007f to catch underflows of _mapcount */
#define PAGE_MAPCOUNT_RESERVE -128
#define PG_buddy 0x00000080
#define PG_offline 0x00000100
#define PG_table 0x00000200
#define PG_guard 0x00000400
+#define PG_hugetlb 0x00000800
#define PageType(page, flag) \
((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
@@ -977,35 +963,38 @@
return page_type_has_type(page->page_type);
}
-#define PAGE_TYPE_OPS(uname, lname, fname) \
-static __always_inline int Page##uname(const struct page *page) \
-{ \
- return PageType(page, PG_##lname); \
-} \
-static __always_inline int folio_test_##fname(const struct folio *folio)\
+#define FOLIO_TYPE_OPS(lname, fname) \
+static __always_inline bool folio_test_##fname(const struct folio *folio)\
{ \
return folio_test_type(folio, PG_##lname); \
} \
-static __always_inline void __SetPage##uname(struct page *page) \
-{ \
- VM_BUG_ON_PAGE(!PageType(page, 0), page); \
- page->page_type &= ~PG_##lname; \
-} \
static __always_inline void __folio_set_##fname(struct folio *folio) \
{ \
VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \
folio->page.page_type &= ~PG_##lname; \
} \
-static __always_inline void __ClearPage##uname(struct page *page) \
-{ \
- VM_BUG_ON_PAGE(!Page##uname(page), page); \
- page->page_type |= PG_##lname; \
-} \
static __always_inline void __folio_clear_##fname(struct folio *folio) \
{ \
VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \
folio->page.page_type |= PG_##lname; \
+}
+
+#define PAGE_TYPE_OPS(uname, lname, fname) \
+FOLIO_TYPE_OPS(lname, fname) \
+static __always_inline int Page##uname(const struct page *page) \
+{ \
+ return PageType(page, PG_##lname); \
} \
+static __always_inline void __SetPage##uname(struct page *page) \
+{ \
+ VM_BUG_ON_PAGE(!PageType(page, 0), page); \
+ page->page_type &= ~PG_##lname; \
+} \
+static __always_inline void __ClearPage##uname(struct page *page) \
+{ \
+ VM_BUG_ON_PAGE(!Page##uname(page), page); \
+ page->page_type |= PG_##lname; \
+}
/*
* PageBuddy() indicates that the page is free and in the buddy system
@@ -1052,6 +1041,37 @@
*/
PAGE_TYPE_OPS(Guard, guard, guard)
+#ifdef CONFIG_HUGETLB_PAGE
+FOLIO_TYPE_OPS(hugetlb, hugetlb)
+#else
+FOLIO_TEST_FLAG_FALSE(hugetlb)
+#endif
+
+/**
+ * PageHuge - Determine if the page belongs to hugetlbfs
+ * @page: The page to test.
+ *
+ * Context: Any context.
+ * Return: True for hugetlbfs pages, false for anon pages or pages
+ * belonging to other filesystems.
+ */
+static inline bool PageHuge(const struct page *page)
+{
+ return folio_test_hugetlb(page_folio(page));
+}
+
+/*
+ * Check if a page is currently marked HWPoisoned. Note that this check is
+ * best effort only and inherently racy: there is no way to synchronize with
+ * failing hardware.
+ */
+static inline bool is_page_hwpoison(struct page *page)
+{
+ if (PageHWPoison(page))
+ return true;
+ return PageHuge(page) && PageHWPoison(compound_head(page));
+}
+
extern bool is_free_buddy_page(struct page *page);
PAGEFLAG(Isolated, isolated, PF_ANY);
@@ -1118,7 +1138,7 @@
*/
#define PAGE_FLAGS_SECOND \
(0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \
- 1UL << PG_hugetlb | 1UL << PG_large_rmappable)
+ 1UL << PG_large_rmappable)
#define PAGE_FLAGS_PRIVATE \
(1UL << PG_private | 1UL << PG_private_2)
diff --git a/include/linux/peci.h b/include/linux/peci.h
index 9b3d36a..90e2414 100644
--- a/include/linux/peci.h
+++ b/include/linux/peci.h
@@ -58,7 +58,6 @@
/**
* struct peci_device - PECI device
* @dev: device object to register PECI device to the device model
- * @controller: manages the bus segment hosting this PECI device
* @info: PECI device characteristics
* @info.family: device family
* @info.model: device model
diff --git a/include/linux/profile.h b/include/linux/profile.h
index 11db1ec..04ae5eb 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -18,13 +18,8 @@
struct notifier_block;
#if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS)
-void create_prof_cpu_mask(void);
int create_proc_profile(void);
#else
-static inline void create_prof_cpu_mask(void)
-{
-}
-
static inline int create_proc_profile(void)
{
return 0;
diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h
index 5d86850..6d92b68 100644
--- a/include/linux/randomize_kstack.h
+++ b/include/linux/randomize_kstack.h
@@ -80,7 +80,7 @@
if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
&randomize_kstack_offset)) { \
u32 offset = raw_cpu_read(kstack_offset); \
- offset ^= (rand); \
+ offset = ror32(offset, 5) ^ (rand); \
raw_cpu_write(kstack_offset, offset); \
} \
} while (0)
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index b743241..d470303 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -1230,6 +1230,7 @@
int regmap_raw_write_async(struct regmap *map, unsigned int reg,
const void *val, size_t val_len);
int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val);
+int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val);
int regmap_raw_read(struct regmap *map, unsigned int reg,
void *val, size_t val_len);
int regmap_noinc_read(struct regmap *map, unsigned int reg,
@@ -1739,6 +1740,13 @@
return -EINVAL;
}
+static inline int regmap_read_bypassed(struct regmap *map, unsigned int reg,
+ unsigned int *val)
+{
+ WARN_ONCE(1, "regmap API is disabled");
+ return -EINVAL;
+}
+
static inline int regmap_raw_read(struct regmap *map, unsigned int reg,
void *val, size_t val_len)
{
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 4660582..ed180ca 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -320,13 +320,13 @@
static inline int devm_regulator_get_enable(struct device *dev, const char *id)
{
- return -ENODEV;
+ return 0;
}
static inline int devm_regulator_get_enable_optional(struct device *dev,
const char *id)
{
- return -ENODEV;
+ return 0;
}
static inline struct regulator *__must_check
diff --git a/include/linux/rwbase_rt.h b/include/linux/rwbase_rt.h
index 29c4e4f..f2394a4 100644
--- a/include/linux/rwbase_rt.h
+++ b/include/linux/rwbase_rt.h
@@ -31,9 +31,9 @@
return atomic_read(&rwb->readers) != READER_BIAS;
}
-static inline void rw_base_assert_held_write(const struct rwbase_rt *rwb)
+static __always_inline bool rw_base_is_write_locked(const struct rwbase_rt *rwb)
{
- WARN_ON(atomic_read(&rwb->readers) != WRITER_BIAS);
+ return atomic_read(&rwb->readers) == WRITER_BIAS;
}
static __always_inline bool rw_base_is_contended(const struct rwbase_rt *rwb)
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 4f1c189..c8b543d 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -167,14 +167,14 @@
return rw_base_is_locked(&sem->rwbase);
}
-static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem)
+static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem)
{
WARN_ON(!rwsem_is_locked(sem));
}
-static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem)
+static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem)
{
- rw_base_assert_held_write(sem);
+ WARN_ON(!rw_base_is_write_locked(&sem->rwbase));
}
static __always_inline int rwsem_is_contended(struct rw_semaphore *sem)
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index a4c15db..3fb18f7 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -110,8 +110,17 @@
extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
int shmem_unuse(unsigned int type);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force,
struct mm_struct *mm, unsigned long vm_flags);
+#else
+static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force,
+ struct mm_struct *mm, unsigned long vm_flags)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_SHMEM
extern unsigned long shmem_swap_usage(struct vm_area_struct *vma);
#else
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e65ec3f..a509caf 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -461,10 +461,12 @@
static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock)
{
+ read_lock_bh(&sk->sk_callback_lock);
if (psock->saved_data_ready)
psock->saved_data_ready(sk);
else
sk->sk_data_ready(sk);
+ read_unlock_bh(&sk->sk_callback_lock);
}
static inline void psock_set_prog(struct bpf_prog **pprog,
diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index 307961b..317200c 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -50,11 +50,36 @@
return 0;
}
+/* Deprecated.
+ * This is unsafe, unless caller checked user provided optlen.
+ * Prefer copy_safe_from_sockptr() instead.
+ */
static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size)
{
return copy_from_sockptr_offset(dst, src, 0, size);
}
+/**
+ * copy_safe_from_sockptr: copy a struct from sockptr
+ * @dst: Destination address, in kernel space. This buffer must be @ksize
+ * bytes long.
+ * @ksize: Size of @dst struct.
+ * @optval: Source address. (in user or kernel space)
+ * @optlen: Size of @optval data.
+ *
+ * Returns:
+ * * -EINVAL: @optlen < @ksize
+ * * -EFAULT: access to userspace failed.
+ * * 0 : @ksize bytes were copied
+ */
+static inline int copy_safe_from_sockptr(void *dst, size_t ksize,
+ sockptr_t optval, unsigned int optlen)
+{
+ if (optlen < ksize)
+ return -EINVAL;
+ return copy_from_sockptr(dst, optval, ksize);
+}
+
static inline int copy_struct_from_sockptr(void *dst, size_t ksize,
sockptr_t src, size_t usize)
{
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 24cd199..d33bab3 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -210,7 +210,6 @@
*/
struct svc_rdma_write_info {
struct svcxprt_rdma *wi_rdma;
- struct list_head wi_list;
const struct svc_rdma_chunk *wi_chunk;
@@ -239,10 +238,7 @@
struct ib_cqe sc_cqe;
struct xdr_buf sc_hdrbuf;
struct xdr_stream sc_stream;
-
- struct list_head sc_write_info_list;
struct svc_rdma_write_info sc_reply_info;
-
void *sc_xprt_buf;
int sc_page_count;
int sc_cur_sge_no;
@@ -274,14 +270,11 @@
extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma,
struct svc_rdma_chunk_ctxt *cc,
enum dma_data_direction dir);
-extern void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma,
- struct svc_rdma_send_ctxt *ctxt);
extern void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma,
struct svc_rdma_send_ctxt *ctxt);
-extern int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma,
- const struct svc_rdma_pcl *write_pcl,
- struct svc_rdma_send_ctxt *sctxt,
- const struct xdr_buf *xdr);
+extern int svc_rdma_send_write_list(struct svcxprt_rdma *rdma,
+ const struct svc_rdma_recv_ctxt *rctxt,
+ const struct xdr_buf *xdr);
extern int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma,
const struct svc_rdma_pcl *write_pcl,
const struct svc_rdma_pcl *reply_pcl,
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 48b700b..a5c560a 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -390,6 +390,35 @@
}
#endif /* CONFIG_MIGRATION */
+#ifdef CONFIG_MEMORY_FAILURE
+
+/*
+ * Support for hardware poisoned pages
+ */
+static inline swp_entry_t make_hwpoison_entry(struct page *page)
+{
+ BUG_ON(!PageLocked(page));
+ return swp_entry(SWP_HWPOISON, page_to_pfn(page));
+}
+
+static inline int is_hwpoison_entry(swp_entry_t entry)
+{
+ return swp_type(entry) == SWP_HWPOISON;
+}
+
+#else
+
+static inline swp_entry_t make_hwpoison_entry(struct page *page)
+{
+ return swp_entry(0, 0);
+}
+
+static inline int is_hwpoison_entry(swp_entry_t swp)
+{
+ return 0;
+}
+#endif
+
typedef unsigned long pte_marker;
#define PTE_MARKER_UFFD_WP BIT(0)
@@ -483,8 +512,9 @@
/*
* A pfn swap entry is a special type of swap entry that always has a pfn stored
- * in the swap offset. They are used to represent unaddressable device memory
- * and to restrict access to a page undergoing migration.
+ * in the swap offset. They can either be used to represent unaddressable device
+ * memory, to restrict access to a page undergoing migration or to represent a
+ * pfn which has been hwpoisoned and unmapped.
*/
static inline bool is_pfn_swap_entry(swp_entry_t entry)
{
@@ -492,7 +522,7 @@
BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS);
return is_migration_entry(entry) || is_device_private_entry(entry) ||
- is_device_exclusive_entry(entry);
+ is_device_exclusive_entry(entry) || is_hwpoison_entry(entry);
}
struct page_vma_mapped_walk;
@@ -561,35 +591,6 @@
}
#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */
-#ifdef CONFIG_MEMORY_FAILURE
-
-/*
- * Support for hardware poisoned pages
- */
-static inline swp_entry_t make_hwpoison_entry(struct page *page)
-{
- BUG_ON(!PageLocked(page));
- return swp_entry(SWP_HWPOISON, page_to_pfn(page));
-}
-
-static inline int is_hwpoison_entry(swp_entry_t entry)
-{
- return swp_type(entry) == SWP_HWPOISON;
-}
-
-#else
-
-static inline swp_entry_t make_hwpoison_entry(struct page *page)
-{
- return swp_entry(0, 0);
-}
-
-static inline int is_hwpoison_entry(swp_entry_t swp)
-{
- return 0;
-}
-#endif
-
static inline int non_swap_entry(swp_entry_t entry)
{
return swp_type(entry) >= MAX_SWAPFILES;
diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h
index 7a5fe17..d03f746 100644
--- a/include/linux/tracefs.h
+++ b/include/linux/tracefs.h
@@ -62,6 +62,8 @@
typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data,
const struct file_operations **fops);
+typedef void (*eventfs_release)(const char *name, void *data);
+
/**
* struct eventfs_entry - dynamically created eventfs file call back handler
* @name: Then name of the dynamic file in an eventfs directory
@@ -72,6 +74,7 @@
struct eventfs_entry {
const char *name;
eventfs_callback callback;
+ eventfs_release release;
};
struct eventfs_inode;
diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index ffe48e6..4578799 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -135,10 +135,11 @@
p->v++;
}
-static inline void u64_stats_init(struct u64_stats_sync *syncp)
-{
- seqcount_init(&syncp->seq);
-}
+#define u64_stats_init(syncp) \
+ do { \
+ struct u64_stats_sync *__s = (syncp); \
+ seqcount_init(&__s->seq); \
+ } while (0)
static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp)
{
diff --git a/include/linux/udp.h b/include/linux/udp.h
index 17539d0..e398e1d 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -108,7 +108,7 @@
#define udp_assign_bit(nr, sk, val) \
assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val)
-#define UDP_MAX_SEGMENTS (1 << 6UL)
+#define UDP_MAX_SEGMENTS (1 << 7UL)
#define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk)
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index b020174..26c4325 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -170,7 +170,7 @@
/**
* struct virtio_driver - operations for a virtio I/O driver
- * @driver: underlying device driver (populate name and owner).
+ * @driver: underlying device driver (populate name).
* @id_table: the ids serviced by this driver.
* @feature_table: an array of feature numbers supported by this driver.
* @feature_table_size: number of entries in the feature table array.
@@ -208,7 +208,10 @@
return container_of(drv, struct virtio_driver, driver);
}
-int register_virtio_driver(struct virtio_driver *drv);
+/* use a macro to avoid include chaining to get THIS_MODULE */
+#define register_virtio_driver(drv) \
+ __register_virtio_driver(drv, THIS_MODULE)
+int __register_virtio_driver(struct virtio_driver *drv, struct module *owner);
void unregister_virtio_driver(struct virtio_driver *drv);
/* module_virtio_driver() - Helper macro for drivers that don't do
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 9d06eb9..62a407d 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -438,6 +438,10 @@
refcount_inc(&ifp->refcnt);
}
+static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp)
+{
+ return refcount_inc_not_zero(&ifp->refcnt);
+}
/*
* compute link-local solicited-node multicast address
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 627ea8e..3dee0b2 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -85,6 +85,9 @@
U_LOCK_NORMAL,
U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */
U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
+ U_LOCK_GC_LISTENER, /* used for listening socket while determining gc
+ * candidates to close a small race window.
+ */
};
static inline void unix_state_lock_nested(struct sock *sk,
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 9fe95a2..eaec5d6 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -585,6 +585,15 @@
return skb;
}
+static inline int bt_copy_from_sockptr(void *dst, size_t dst_size,
+ sockptr_t src, size_t src_size)
+{
+ if (dst_size > src_size)
+ return -EINVAL;
+
+ return copy_from_sockptr(dst, src, dst_size);
+}
+
int bt_to_errno(u16 code);
__u8 bt_status(int err);
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 56fb42d..e8f581f 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -738,6 +738,8 @@
__u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN];
__u16 le_per_adv_data_len;
__u16 le_per_adv_data_offset;
+ __u8 le_adv_phy;
+ __u8 le_adv_sec_phy;
__u8 le_tx_phy;
__u8 le_rx_phy;
__s8 rssi;
@@ -1512,7 +1514,7 @@
enum conn_reasons conn_reason);
struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
u8 dst_type, bool dst_resolved, u8 sec_level,
- u16 conn_timeout, u8 role);
+ u16 conn_timeout, u8 role, u8 phy, u8 sec_phy);
void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status);
struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
u8 sec_level, u8 auth_type,
@@ -1905,6 +1907,10 @@
#define privacy_mode_capable(dev) (use_ll_privacy(dev) && \
(hdev->commands[39] & 0x04))
+#define read_key_size_capable(dev) \
+ ((dev)->commands[20] & 0x10 && \
+ !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks))
+
/* Use enhanced synchronous connection if command is supported and its quirk
* has not been set.
*/
diff --git a/include/net/gro.h b/include/net/gro.h
index 50f1e40..c1d4ca0 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -87,6 +87,15 @@
/* used to support CHECKSUM_COMPLETE for tunneling protocols */
__wsum csum;
+
+ /* L3 offsets */
+ union {
+ struct {
+ u16 network_offset;
+ u16 inner_network_offset;
+ };
+ u16 network_offsets[2];
+ };
};
#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 5cd64bb..c286cc2 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -361,6 +361,39 @@
return pskb_network_may_pull(skb, nhlen);
}
+/* Variant of pskb_inet_may_pull().
+ */
+static inline bool skb_vlan_inet_prepare(struct sk_buff *skb)
+{
+ int nhlen = 0, maclen = ETH_HLEN;
+ __be16 type = skb->protocol;
+
+ /* Essentially this is skb_protocol(skb, true)
+ * And we get MAC len.
+ */
+ if (eth_type_vlan(type))
+ type = __vlan_get_protocol(skb, type, &maclen);
+
+ switch (type) {
+#if IS_ENABLED(CONFIG_IPV6)
+ case htons(ETH_P_IPV6):
+ nhlen = sizeof(struct ipv6hdr);
+ break;
+#endif
+ case htons(ETH_P_IP):
+ nhlen = sizeof(struct iphdr);
+ break;
+ }
+ /* For ETH_P_IPV6/ETH_P_IP we make sure to pull
+ * a base network header in skb->head.
+ */
+ if (!pskb_may_pull(skb, maclen + nhlen))
+ return false;
+
+ skb_set_network_header(skb, maclen);
+ return true;
+}
+
static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
{
const struct ip_tunnel_encap_ops *ops;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 353488a..2d7f87b 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -953,6 +953,8 @@
* of their QoS TID or other priority field values.
* @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally
* for sequence number assignment
+ * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted
+ * due to scanning, not in normal operation on the interface.
* @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this
* frame should be transmitted on the specific link. This really is
* only relevant for frames that do not have data present, and is
@@ -973,6 +975,7 @@
IEEE80211_TX_CTRL_NO_SEQNO = BIT(7),
IEEE80211_TX_CTRL_DONT_REORDER = BIT(8),
IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9),
+ IEEE80211_TX_CTRL_SCAN_TX = BIT(10),
IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000,
};
diff --git a/include/net/macsec.h b/include/net/macsec.h
index dbd2218..de216cb 100644
--- a/include/net/macsec.h
+++ b/include/net/macsec.h
@@ -321,6 +321,7 @@
* for the TX tag
* @needed_tailroom: number of bytes reserved at the end of the sk_buff for the
* TX tag
+ * @rx_uses_md_dst: whether MACsec device offload supports sk_buff md_dst
*/
struct macsec_ops {
/* Device wide */
@@ -352,6 +353,7 @@
struct sk_buff *skb);
unsigned int needed_headroom;
unsigned int needed_tailroom;
+ bool rx_uses_md_dst;
};
void macsec_pn_wrapped(struct macsec_secy *secy, struct macsec_tx_sa *tx_sa);
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index a763dd3..9abb7ee 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -336,7 +336,7 @@
int nf_flow_table_offload_init(void);
void nf_flow_table_offload_exit(void);
-static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb)
+static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb)
{
__be16 proto;
@@ -352,6 +352,16 @@
return 0;
}
+static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto)
+{
+ if (!pskb_may_pull(skb, PPPOE_SES_HLEN))
+ return false;
+
+ *inner_proto = __nf_flow_pppoe_proto(skb);
+
+ return true;
+}
+
#define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count)
#define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count)
#define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count) \
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index e27c28b..3f1ed46 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -307,9 +307,23 @@
return (void *)priv;
}
+
+/**
+ * enum nft_iter_type - nftables set iterator type
+ *
+ * @NFT_ITER_READ: read-only iteration over set elements
+ * @NFT_ITER_UPDATE: iteration under mutex to update set element state
+ */
+enum nft_iter_type {
+ NFT_ITER_UNSPEC,
+ NFT_ITER_READ,
+ NFT_ITER_UPDATE,
+};
+
struct nft_set;
struct nft_set_iter {
u8 genmask;
+ enum nft_iter_type type:8;
unsigned int count;
unsigned int skip;
int err;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index cefe0c4..41ca14e 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -117,6 +117,7 @@
struct qdisc_skb_head q;
struct gnet_stats_basic_sync bstats;
struct gnet_stats_queue qstats;
+ int owner;
unsigned long state;
unsigned long state2; /* must be written under qdisc spinlock */
struct Qdisc *next_sched;
diff --git a/include/net/sock.h b/include/net/sock.h
index f57bfd8..b4b553d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1410,32 +1410,34 @@
#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT))
extern int sysctl_mem_pcpu_rsv;
-static inline void
-sk_memory_allocated_add(struct sock *sk, int amt)
+static inline void proto_memory_pcpu_drain(struct proto *proto)
{
- int local_reserve;
+ int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0);
- preempt_disable();
- local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt);
- if (local_reserve >= READ_ONCE(sysctl_mem_pcpu_rsv)) {
- __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve);
- atomic_long_add(local_reserve, sk->sk_prot->memory_allocated);
- }
- preempt_enable();
+ if (val)
+ atomic_long_add(val, proto->memory_allocated);
}
static inline void
-sk_memory_allocated_sub(struct sock *sk, int amt)
+sk_memory_allocated_add(const struct sock *sk, int val)
{
- int local_reserve;
+ struct proto *proto = sk->sk_prot;
- preempt_disable();
- local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt);
- if (local_reserve <= -READ_ONCE(sysctl_mem_pcpu_rsv)) {
- __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve);
- atomic_long_add(local_reserve, sk->sk_prot->memory_allocated);
- }
- preempt_enable();
+ val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val);
+
+ if (unlikely(val >= READ_ONCE(sysctl_mem_pcpu_rsv)))
+ proto_memory_pcpu_drain(proto);
+}
+
+static inline void
+sk_memory_allocated_sub(const struct sock *sk, int val)
+{
+ struct proto *proto = sk->sk_prot;
+
+ val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val);
+
+ if (unlikely(val <= -READ_ONCE(sysctl_mem_pcpu_rsv)))
+ proto_memory_pcpu_drain(proto);
}
#define SK_ALLOC_PERCPU_COUNTER_BATCH 16
diff --git a/include/net/tls.h b/include/net/tls.h
index 340ad43..33f657d3 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -111,7 +111,8 @@
u32 stopped : 1;
u32 copy_mode : 1;
u32 mixed_decrypted : 1;
- u32 msg_ready : 1;
+
+ bool msg_ready;
struct strp_msg stm;
diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index e062969..1a3c6f6 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -267,6 +267,7 @@
bool fw_patched;
bool secured;
bool can_hibernate;
+ bool fw_owns_asp1;
bool cal_data_valid;
s8 cal_index;
struct cirrus_amp_cal_data cal_data;
@@ -283,6 +284,7 @@
extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC];
int cs35l56_set_patch(struct cs35l56_base *cs35l56_base);
+int cs35l56_init_asp1_regs_for_driver_control(struct cs35l56_base *cs35l56_base);
int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base);
int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command);
int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base);
diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index 1af9e68..234b5ba 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -1684,8 +1684,8 @@
unsigned int clock_fallback;
unsigned int optical_in; /* 0:SPDIF, 1:ADAT */
unsigned int optical_out; /* 0:SPDIF, 1:ADAT */
- struct work_struct firmware_work;
- struct work_struct clock_work;
+ struct work_struct work;
+ struct mutex lock;
};
struct snd_emu10k1 {
@@ -1834,6 +1834,9 @@
void snd_emu10k1_ptr20_write(struct snd_emu10k1 *emu, unsigned int reg, unsigned int chn, unsigned int data);
int snd_emu10k1_spi_write(struct snd_emu10k1 * emu, unsigned int data);
int snd_emu10k1_i2c_write(struct snd_emu10k1 *emu, u32 reg, u32 value);
+static inline void snd_emu1010_fpga_lock(struct snd_emu10k1 *emu) { mutex_lock(&emu->emu1010.lock); };
+static inline void snd_emu1010_fpga_unlock(struct snd_emu10k1 *emu) { mutex_unlock(&emu->emu1010.lock); };
+void snd_emu1010_fpga_write_lock(struct snd_emu10k1 *emu, u32 reg, u32 value);
void snd_emu1010_fpga_write(struct snd_emu10k1 *emu, u32 reg, u32 value);
void snd_emu1010_fpga_read(struct snd_emu10k1 *emu, u32 reg, u32 *value);
void snd_emu1010_fpga_link_dst_src_write(struct snd_emu10k1 *emu, u32 dst, u32 src);
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index d801409..d55e53a 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -135,6 +135,7 @@
#define DEF_PAGETYPE_NAME(_name) { PG_##_name, __stringify(_name) }
#define __def_pagetype_names \
+ DEF_PAGETYPE_NAME(hugetlb), \
DEF_PAGETYPE_NAME(offline), \
DEF_PAGETYPE_NAME(guard), \
DEF_PAGETYPE_NAME(table), \
diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h
index ba2d96a..f50fcaf 100644
--- a/include/trace/events/rpcgss.h
+++ b/include/trace/events/rpcgss.h
@@ -609,7 +609,7 @@
__field(unsigned int, timeout)
__field(u32, window_size)
__field(int, len)
- __string(acceptor, data)
+ __string_len(acceptor, data, len)
),
TP_fast_assign(
@@ -618,7 +618,7 @@
__entry->timeout = timeout;
__entry->window_size = window_size;
__entry->len = len;
- strncpy(__get_str(acceptor), data, len);
+ __assign_str(acceptor, data);
),
TP_printk("win_size=%u expiry=%lu now=%lu timeout=%u acceptor=%.*s",
diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h
index d87410a..af024d9 100644
--- a/include/uapi/drm/etnaviv_drm.h
+++ b/include/uapi/drm/etnaviv_drm.h
@@ -77,11 +77,6 @@
#define ETNAVIV_PARAM_GPU_PRODUCT_ID 0x1c
#define ETNAVIV_PARAM_GPU_CUSTOMER_ID 0x1d
#define ETNAVIV_PARAM_GPU_ECO_ID 0x1e
-#define ETNAVIV_PARAM_GPU_NN_CORE_COUNT 0x1f
-#define ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE 0x20
-#define ETNAVIV_PARAM_GPU_TP_CORE_COUNT 0x21
-#define ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE 0x22
-#define ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE 0x23
#define ETNA_MAX_PIPES 4
diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h
index 43c5169..842bf12 100644
--- a/include/uapi/linux/vdpa.h
+++ b/include/uapi/linux/vdpa.h
@@ -57,7 +57,7 @@
VDPA_ATTR_DEV_FEATURES, /* u64 */
VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */
- VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */
+ VDPA_ATTR_DEV_BLK_CFG_SIZE_MAX, /* u32 */
VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */
VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */
VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, /* u16 */
@@ -70,8 +70,8 @@
VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */
VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */
VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */
- VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, /* u8 */
- VDPA_ATTR_DEV_BLK_CFG_FLUSH, /* u8 */
+ VDPA_ATTR_DEV_BLK_READ_ONLY, /* u8 */
+ VDPA_ATTR_DEV_BLK_FLUSH, /* u8 */
/* new attributes must be added above here */
VDPA_ATTR_MAX,
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index bea6973..b95dd84 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -179,12 +179,6 @@
/* Get the config size */
#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32)
-/* Get the count of all virtqueues */
-#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32)
-
-/* Get the number of virtqueue groups. */
-#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32)
-
/* Get the number of address spaces. */
#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int)
@@ -228,10 +222,17 @@
#define VHOST_VDPA_GET_VRING_DESC_GROUP _IOWR(VHOST_VIRTIO, 0x7F, \
struct vhost_vring_state)
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32)
+
+/* Get the number of virtqueue groups. */
+#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32)
+
/* Get the queue size of a specific virtqueue.
* userspace set the vring index in vhost_vring_state.index
* kernel set the queue size in vhost_vring_state.num
*/
-#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x80, \
+#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x82, \
struct vhost_vring_state)
#endif
diff --git a/init/Kconfig b/init/Kconfig
index aa02aec..664bedb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1899,11 +1899,11 @@
bool "Rust support"
depends on HAVE_RUST
depends on RUST_IS_AVAILABLE
+ depends on !CFI_CLANG
depends on !MODVERSIONS
depends on !GCC_PLUGINS
depends on !RANDSTRUCT
depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE
- select CONSTRUCTORS
help
Enables Rust support in the kernel.
diff --git a/init/main.c b/init/main.c
index 2ca5247..5dcf527 100644
--- a/init/main.c
+++ b/init/main.c
@@ -487,6 +487,11 @@
early_param("bootconfig", warn_bootconfig);
+bool __init cmdline_has_extra_options(void)
+{
+ return extra_command_line || extra_init_args;
+}
+
/* Change NUL term back to "=", to make "param" the whole string. */
static void __init repair_env_string(char *param, char *val)
{
@@ -631,6 +636,8 @@
if (!saved_command_line)
panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen);
+ len = xlen + strlen(command_line) + 1;
+
static_command_line = memblock_alloc(len, SMP_CACHE_BYTES);
if (!static_command_line)
panic("%s: Failed to allocate %zu bytes\n", __func__, len);
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 4521c2b..c170a2b 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2602,19 +2602,6 @@
if (__io_cqring_events_user(ctx) >= min_events)
return 0;
- if (sig) {
-#ifdef CONFIG_COMPAT
- if (in_compat_syscall())
- ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig,
- sigsz);
- else
-#endif
- ret = set_user_sigmask(sig, sigsz);
-
- if (ret)
- return ret;
- }
-
init_waitqueue_func_entry(&iowq.wq, io_wake_function);
iowq.wq.private = current;
INIT_LIST_HEAD(&iowq.wq.entry);
@@ -2633,6 +2620,19 @@
io_napi_adjust_timeout(ctx, &iowq, &ts);
}
+ if (sig) {
+#ifdef CONFIG_COMPAT
+ if (in_compat_syscall())
+ ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig,
+ sigsz);
+ else
+#endif
+ ret = set_user_sigmask(sig, sigsz);
+
+ if (ret)
+ return ret;
+ }
+
io_napi_busy_loop(ctx, &iowq);
trace_io_uring_cqring_wait(ctx, min_events);
diff --git a/io_uring/net.c b/io_uring/net.c
index 1e7665f..4afb475 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1276,6 +1276,7 @@
if (req_has_async_data(req)) {
kmsg = req->async_data;
+ kmsg->msg.msg_control_user = sr->msg_control;
} else {
ret = io_sendmsg_copy_hdr(req, &iomsg);
if (ret)
diff --git a/kernel/bounds.c b/kernel/bounds.c
index c5a9fcd..29b2cd0 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -19,7 +19,7 @@
DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
#ifdef CONFIG_SMP
- DEFINE(NR_CPUS_BITS, bits_per(CONFIG_NR_CPUS));
+ DEFINE(NR_CPUS_BITS, order_base_2(CONFIG_NR_CPUS));
#endif
DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
#ifdef CONFIG_LRU_GEN
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 696bc55..1ea5ce5 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2942,6 +2942,15 @@
return false;
}
+u64 __weak bpf_arch_uaddress_limit(void)
+{
+#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE)
+ return TASK_SIZE;
+#else
+ return 0;
+#endif
+}
+
/* Return TRUE if the JIT backend satisfies the following two conditions:
* 1) JIT backend supports atomic_xchg() on pointer-sized words.
* 2) Under the specific arch, the implementation of xchg() is the same
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9818837..cb7ad1f7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -18289,8 +18289,7 @@
f = fdget(fd);
map = __bpf_map_get(f);
if (IS_ERR(map)) {
- verbose(env, "fd %d is not pointing to valid bpf_map\n",
- insn[0].imm);
+ verbose(env, "fd %d is not pointing to valid bpf_map\n", fd);
return PTR_ERR(map);
}
@@ -19676,6 +19675,36 @@
goto next_insn;
}
+ /* Make it impossible to de-reference a userspace address */
+ if (BPF_CLASS(insn->code) == BPF_LDX &&
+ (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) {
+ struct bpf_insn *patch = &insn_buf[0];
+ u64 uaddress_limit = bpf_arch_uaddress_limit();
+
+ if (!uaddress_limit)
+ goto next_insn;
+
+ *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg);
+ if (insn->off)
+ *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off);
+ *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32);
+ *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2);
+ *patch++ = *insn;
+ *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
+ *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0);
+
+ cnt = patch - insn_buf;
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ goto next_insn;
+ }
+
/* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */
if (BPF_CLASS(insn->code) == BPF_LD &&
(BPF_MODE(insn->code) == BPF_ABS ||
diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config
index 7a5bbfc..4b4cfcb 100644
--- a/kernel/configs/hardening.config
+++ b/kernel/configs/hardening.config
@@ -39,11 +39,12 @@
CONFIG_UBSAN_TRAP=y
CONFIG_UBSAN_BOUNDS=y
# CONFIG_UBSAN_SHIFT is not set
-# CONFIG_UBSAN_DIV_ZERO
-# CONFIG_UBSAN_UNREACHABLE
-# CONFIG_UBSAN_BOOL
-# CONFIG_UBSAN_ENUM
-# CONFIG_UBSAN_ALIGNMENT
+# CONFIG_UBSAN_DIV_ZERO is not set
+# CONFIG_UBSAN_UNREACHABLE is not set
+# CONFIG_UBSAN_SIGNED_WRAP is not set
+# CONFIG_UBSAN_BOOL is not set
+# CONFIG_UBSAN_ENUM is not set
+# CONFIG_UBSAN_ALIGNMENT is not set
# Sampling-based heap out-of-bounds and use-after-free detection.
CONFIG_KFENCE=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8f6affd..63447eb 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -3196,6 +3196,7 @@
this_cpu_write(cpuhp_state.target, CPUHP_ONLINE);
}
+#ifdef CONFIG_CPU_MITIGATIONS
/*
* These are used for a global "mitigations=" cmdline option for toggling
* optional CPU mitigations.
@@ -3206,8 +3207,7 @@
CPU_MITIGATIONS_AUTO_NOSMT,
};
-static enum cpu_mitigations cpu_mitigations __ro_after_init =
- CPU_MITIGATIONS_AUTO;
+static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
static int __init mitigations_parse_cmdline(char *arg)
{
@@ -3223,7 +3223,6 @@
return 0;
}
-early_param("mitigations", mitigations_parse_cmdline);
/* mitigations=off */
bool cpu_mitigations_off(void)
@@ -3238,3 +3237,11 @@
return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
+#else
+static int __init mitigations_parse_cmdline(char *arg)
+{
+ pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n");
+ return 0;
+}
+#endif
+early_param("mitigations", mitigations_parse_cmdline);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 86fe172..0de66f0 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -69,11 +69,14 @@
* @alloc_size: Size of the allocated buffer.
* @list: The free list describing the number of free entries available
* from each index.
+ * @pad_slots: Number of preceding padding slots. Valid only in the first
+ * allocated non-padding slot.
*/
struct io_tlb_slot {
phys_addr_t orig_addr;
size_t alloc_size;
- unsigned int list;
+ unsigned short list;
+ unsigned short pad_slots;
};
static bool swiotlb_force_bounce;
@@ -287,6 +290,7 @@
mem->nslabs - i);
mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
mem->slots[i].alloc_size = 0;
+ mem->slots[i].pad_slots = 0;
}
memset(vaddr, 0, bytes);
@@ -821,12 +825,30 @@
#endif
}
-/*
- * Return the offset into a iotlb slot required to keep the device happy.
+/**
+ * swiotlb_align_offset() - Get required offset into an IO TLB allocation.
+ * @dev: Owning device.
+ * @align_mask: Allocation alignment mask.
+ * @addr: DMA address.
+ *
+ * Return the minimum offset from the start of an IO TLB allocation which is
+ * required for a given buffer address and allocation alignment to keep the
+ * device happy.
+ *
+ * First, the address bits covered by min_align_mask must be identical in the
+ * original address and the bounce buffer address. High bits are preserved by
+ * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra
+ * padding bytes before the bounce buffer.
+ *
+ * Second, @align_mask specifies which bits of the first allocated slot must
+ * be zero. This may require allocating additional padding slots, and then the
+ * offset (in bytes) from the first such padding slot is returned.
*/
-static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
+static unsigned int swiotlb_align_offset(struct device *dev,
+ unsigned int align_mask, u64 addr)
{
- return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
+ return addr & dma_get_min_align_mask(dev) &
+ (align_mask | (IO_TLB_SIZE - 1));
}
/*
@@ -841,27 +863,23 @@
size_t alloc_size = mem->slots[index].alloc_size;
unsigned long pfn = PFN_DOWN(orig_addr);
unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
- unsigned int tlb_offset, orig_addr_offset;
+ int tlb_offset;
if (orig_addr == INVALID_PHYS_ADDR)
return;
- tlb_offset = tlb_addr & (IO_TLB_SIZE - 1);
- orig_addr_offset = swiotlb_align_offset(dev, orig_addr);
- if (tlb_offset < orig_addr_offset) {
- dev_WARN_ONCE(dev, 1,
- "Access before mapping start detected. orig offset %u, requested offset %u.\n",
- orig_addr_offset, tlb_offset);
- return;
- }
-
- tlb_offset -= orig_addr_offset;
- if (tlb_offset > alloc_size) {
- dev_WARN_ONCE(dev, 1,
- "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n",
- alloc_size, size, tlb_offset);
- return;
- }
+ /*
+ * It's valid for tlb_offset to be negative. This can happen when the
+ * "offset" returned by swiotlb_align_offset() is non-zero, and the
+ * tlb_addr is pointing within the first "offset" bytes of the second
+ * or subsequent slots of the allocated swiotlb area. While it's not
+ * valid for tlb_addr to be pointing within the first "offset" bytes
+ * of the first slot, there's no way to check for such an error since
+ * this function can't distinguish the first slot from the second and
+ * subsequent slots.
+ */
+ tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) -
+ swiotlb_align_offset(dev, 0, orig_addr);
orig_addr += tlb_offset;
alloc_size -= tlb_offset;
@@ -1005,7 +1023,7 @@
unsigned long max_slots = get_max_slots(boundary_mask);
unsigned int iotlb_align_mask = dma_get_min_align_mask(dev);
unsigned int nslots = nr_slots(alloc_size), stride;
- unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+ unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr);
unsigned int index, slots_checked, count = 0, i;
unsigned long flags;
unsigned int slot_base;
@@ -1328,11 +1346,12 @@
unsigned long attrs)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
- unsigned int offset = swiotlb_align_offset(dev, orig_addr);
+ unsigned int offset;
struct io_tlb_pool *pool;
unsigned int i;
int index;
phys_addr_t tlb_addr;
+ unsigned short pad_slots;
if (!mem || !mem->nslabs) {
dev_warn_ratelimited(dev,
@@ -1349,6 +1368,7 @@
return (phys_addr_t)DMA_MAPPING_ERROR;
}
+ offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr);
index = swiotlb_find_slots(dev, orig_addr,
alloc_size + offset, alloc_align_mask, &pool);
if (index == -1) {
@@ -1364,6 +1384,10 @@
* This is needed when we sync the memory. Then we sync the buffer if
* needed.
*/
+ pad_slots = offset >> IO_TLB_SHIFT;
+ offset &= (IO_TLB_SIZE - 1);
+ index += pad_slots;
+ pool->slots[index].pad_slots = pad_slots;
for (i = 0; i < nr_slots(alloc_size + offset); i++)
pool->slots[index + i].orig_addr = slot_addr(orig_addr, i);
tlb_addr = slot_addr(pool->start, index) + offset;
@@ -1384,13 +1408,17 @@
{
struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr);
unsigned long flags;
- unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
- int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
- int nslots = nr_slots(mem->slots[index].alloc_size + offset);
- int aindex = index / mem->area_nslabs;
- struct io_tlb_area *area = &mem->areas[aindex];
+ unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr);
+ int index, nslots, aindex;
+ struct io_tlb_area *area;
int count, i;
+ index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
+ index -= mem->slots[index].pad_slots;
+ nslots = nr_slots(mem->slots[index].alloc_size + offset);
+ aindex = index / mem->area_nslabs;
+ area = &mem->areas[aindex];
+
/*
* Return the buffer to the free list by setting the corresponding
* entries to indicate the number of contiguous entries available.
@@ -1413,6 +1441,7 @@
mem->slots[i].list = ++count;
mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
mem->slots[i].alloc_size = 0;
+ mem->slots[i].pad_slots = 0;
}
/*
@@ -1647,9 +1676,6 @@
static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
const char *dirname)
{
- atomic_long_set(&mem->total_used, 0);
- atomic_long_set(&mem->used_hiwater, 0);
-
mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs);
if (!mem->nslabs)
return;
@@ -1660,7 +1686,6 @@
debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem,
&fops_io_tlb_hiwater);
#ifdef CONFIG_SWIOTLB_DYNAMIC
- atomic_long_set(&mem->transient_nslabs, 0);
debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs,
mem, &fops_io_tlb_transient_used);
#endif
@@ -1773,6 +1798,7 @@
mem->for_alloc = true;
#ifdef CONFIG_SWIOTLB_DYNAMIC
spin_lock_init(&mem->lock);
+ INIT_LIST_HEAD_RCU(&mem->pools);
#endif
add_mem_pool(mem, pool);
diff --git a/kernel/fork.c b/kernel/fork.c
index 39a5046..aebb3e6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -714,6 +714,23 @@
} else if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
vm_flags_clear(tmp, VM_LOCKED_MASK);
+ /*
+ * Copy/update hugetlb private vma information.
+ */
+ if (is_vm_hugetlb_page(tmp))
+ hugetlb_dup_vma_private(tmp);
+
+ /*
+ * Link the vma into the MT. After using __mt_dup(), memory
+ * allocation is not necessary here, so it cannot fail.
+ */
+ vma_iter_bulk_store(&vmi, tmp);
+
+ mm->map_count++;
+
+ if (tmp->vm_ops && tmp->vm_ops->open)
+ tmp->vm_ops->open(tmp);
+
file = tmp->vm_file;
if (file) {
struct address_space *mapping = file->f_mapping;
@@ -730,25 +747,9 @@
i_mmap_unlock_write(mapping);
}
- /*
- * Copy/update hugetlb private vma information.
- */
- if (is_vm_hugetlb_page(tmp))
- hugetlb_dup_vma_private(tmp);
-
- /*
- * Link the vma into the MT. After using __mt_dup(), memory
- * allocation is not necessary here, so it cannot fail.
- */
- vma_iter_bulk_store(&vmi, tmp);
-
- mm->map_count++;
if (!(tmp->vm_flags & VM_WIPEONFORK))
retval = copy_page_range(tmp, mpnt);
- if (tmp->vm_ops && tmp->vm_ops->open)
- tmp->vm_ops->open(tmp);
-
if (retval) {
mpnt = vma_next(&vmi);
goto loop_out;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9d9095e..65adc81 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1567,10 +1567,17 @@
jump_label_lock();
preempt_disable();
- /* Ensure it is not in reserved area nor out of text */
- if (!(core_kernel_text((unsigned long) p->addr) ||
- is_module_text_address((unsigned long) p->addr)) ||
- in_gate_area_no_mm((unsigned long) p->addr) ||
+ /* Ensure the address is in a text area, and find a module if exists. */
+ *probed_mod = NULL;
+ if (!core_kernel_text((unsigned long) p->addr)) {
+ *probed_mod = __module_text_address((unsigned long) p->addr);
+ if (!(*probed_mod)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+ /* Ensure it is not in reserved area. */
+ if (in_gate_area_no_mm((unsigned long) p->addr) ||
within_kprobe_blacklist((unsigned long) p->addr) ||
jump_label_text_reserved(p->addr, p->addr) ||
static_call_text_reserved(p->addr, p->addr) ||
@@ -1580,8 +1587,7 @@
goto out;
}
- /* Check if 'p' is probing a module. */
- *probed_mod = __module_text_address((unsigned long) p->addr);
+ /* Get module refcount and reject __init functions for loaded modules. */
if (*probed_mod) {
/*
* We must hold a refcount of the probed module while updating
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index e3ae93b..09f8397b 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -106,6 +106,12 @@
swait_event_exclusive(s2idle_wait_head,
s2idle_state == S2IDLE_STATE_WAKE);
+ /*
+ * Kick all CPUs to ensure that they resume their timers and restore
+ * consistent system state.
+ */
+ wake_up_all_idle_cpus();
+
cpus_read_unlock();
raw_spin_lock_irq(&s2idle_lock);
diff --git a/kernel/profile.c b/kernel/profile.c
index 8a77769..2b775cc 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -344,49 +344,6 @@
#include <linux/seq_file.h>
#include <linux/uaccess.h>
-static int prof_cpu_mask_proc_show(struct seq_file *m, void *v)
-{
- seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask));
- return 0;
-}
-
-static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, prof_cpu_mask_proc_show, NULL);
-}
-
-static ssize_t prof_cpu_mask_proc_write(struct file *file,
- const char __user *buffer, size_t count, loff_t *pos)
-{
- cpumask_var_t new_value;
- int err;
-
- if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
- return -ENOMEM;
-
- err = cpumask_parse_user(buffer, count, new_value);
- if (!err) {
- cpumask_copy(prof_cpu_mask, new_value);
- err = count;
- }
- free_cpumask_var(new_value);
- return err;
-}
-
-static const struct proc_ops prof_cpu_mask_proc_ops = {
- .proc_open = prof_cpu_mask_proc_open,
- .proc_read = seq_read,
- .proc_lseek = seq_lseek,
- .proc_release = single_release,
- .proc_write = prof_cpu_mask_proc_write,
-};
-
-void create_prof_cpu_mask(void)
-{
- /* create /proc/irq/prof_cpu_mask */
- proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops);
-}
-
/*
* This function accesses profiling information. The returned data is
* binary: the sampling step and the actual contents of the profile
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 03be0d1..c62805d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -696,15 +696,21 @@
*
* XXX could add max_slice to the augmented data to track this.
*/
+static s64 entity_lag(u64 avruntime, struct sched_entity *se)
+{
+ s64 vlag, limit;
+
+ vlag = avruntime - se->vruntime;
+ limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
+
+ return clamp(vlag, -limit, limit);
+}
+
static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- s64 lag, limit;
-
SCHED_WARN_ON(!se->on_rq);
- lag = avg_vruntime(cfs_rq) - se->vruntime;
- limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
- se->vlag = clamp(lag, -limit, limit);
+ se->vlag = entity_lag(avg_vruntime(cfs_rq), se);
}
/*
@@ -3676,11 +3682,10 @@
dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
#endif
-static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
+static void reweight_eevdf(struct sched_entity *se, u64 avruntime,
unsigned long weight)
{
unsigned long old_weight = se->load.weight;
- u64 avruntime = avg_vruntime(cfs_rq);
s64 vlag, vslice;
/*
@@ -3761,7 +3766,7 @@
* = V - vl'
*/
if (avruntime != se->vruntime) {
- vlag = (s64)(avruntime - se->vruntime);
+ vlag = entity_lag(avruntime, se);
vlag = div_s64(vlag * old_weight, weight);
se->vruntime = avruntime - vlag;
}
@@ -3787,25 +3792,26 @@
unsigned long weight)
{
bool curr = cfs_rq->curr == se;
+ u64 avruntime;
if (se->on_rq) {
/* commit outstanding execution time */
- if (curr)
- update_curr(cfs_rq);
- else
+ update_curr(cfs_rq);
+ avruntime = avg_vruntime(cfs_rq);
+ if (!curr)
__dequeue_entity(cfs_rq, se);
update_load_sub(&cfs_rq->load, se->load.weight);
}
dequeue_load_avg(cfs_rq, se);
- if (!se->on_rq) {
+ if (se->on_rq) {
+ reweight_eevdf(se, avruntime, weight);
+ } else {
/*
* Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
* we need to scale se->vlag when w_i changes.
*/
se->vlag = div_s64(se->vlag * se->load.weight, weight);
- } else {
- reweight_eevdf(cfs_rq, se, weight);
}
update_load_set(&se->load, weight);
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 373d42c..5891e71 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -46,7 +46,16 @@
if (cpu < nr_cpu_ids)
return cpu;
- return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+ cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
+ if (likely(cpu < nr_cpu_ids))
+ return cpu;
+ /*
+ * Unless we have another problem this can only happen
+ * at boot time before start_secondary() brings the 1st
+ * housekeeping CPU up.
+ */
+ WARN_ON_ONCE(system_state == SYSTEM_RUNNING ||
+ type != HK_TYPE_TIMER);
}
}
return smp_processor_id();
@@ -109,6 +118,7 @@
static int __init housekeeping_setup(char *str, unsigned long flags)
{
cpumask_var_t non_housekeeping_mask, housekeeping_staging;
+ unsigned int first_cpu;
int err = 0;
if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) {
@@ -129,7 +139,8 @@
cpumask_andnot(housekeeping_staging,
cpu_possible_mask, non_housekeeping_mask);
- if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) {
+ first_cpu = cpumask_first_and(cpu_present_mask, housekeeping_staging);
+ if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) {
__cpumask_set_cpu(smp_processor_id(), housekeeping_staging);
__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
if (!housekeeping.flags) {
@@ -138,6 +149,9 @@
}
}
+ if (cpumask_empty(non_housekeeping_mask))
+ goto free_housekeeping_staging;
+
if (!housekeeping.flags) {
/* First setup call ("nohz_full=" or "isolcpus=") */
enum hk_type type;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d2242679..ae50f21 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -79,6 +79,8 @@
# include <asm/paravirt_api_clock.h>
#endif
+#include <asm/barrier.h>
+
#include "cpupri.h"
#include "cpudeadline.h"
@@ -3445,13 +3447,19 @@
* between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
* Provide it here.
*/
- if (!prev->mm) // from kernel
+ if (!prev->mm) { // from kernel
smp_mb();
- /*
- * user -> user transition guarantees a memory barrier through
- * switch_mm() when current->mm changes. If current->mm is
- * unchanged, no barrier is needed.
- */
+ } else { // from user
+ /*
+ * user->user transition relies on an implicit
+ * memory barrier in switch_mm() when
+ * current->mm changes. If the architecture
+ * switch_mm() does not have an implicit memory
+ * barrier, it is emitted here. If current->mm
+ * is unchanged, no barrier is needed.
+ */
+ smp_mb__after_switch_mm();
+ }
}
if (prev->mm_cid_active) {
mm_cid_snapshot_time(rq, prev->mm);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b315b21..0258201 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -508,7 +508,7 @@
static inline void lockdep_softirq_end(bool in_hardirq) { }
#endif
-asmlinkage __visible void __softirq_entry __do_softirq(void)
+static void handle_softirqs(bool ksirqd)
{
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
unsigned long old_flags = current->flags;
@@ -563,8 +563,7 @@
pending >>= softirq_bit;
}
- if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
- __this_cpu_read(ksoftirqd) == current)
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && ksirqd)
rcu_softirq_qs();
local_irq_disable();
@@ -584,6 +583,11 @@
current_restore_flags(old_flags, PF_MEMALLOC);
}
+asmlinkage __visible void __softirq_entry __do_softirq(void)
+{
+ handle_softirqs(false);
+}
+
/**
* irq_enter_rcu - Enter an interrupt context with RCU watching
*/
@@ -921,7 +925,7 @@
* We can safely run softirq on inline stack, as we are not deep
* in the task stack here.
*/
- __do_softirq();
+ handle_softirqs(true);
ksoftirqd_run_end();
cond_resched();
return;
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index fb0fdec..d88b130 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -7,6 +7,7 @@
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
*/
+#include <linux/compiler.h>
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
@@ -84,7 +85,7 @@
*/
static void tick_periodic(int cpu)
{
- if (tick_do_timer_cpu == cpu) {
+ if (READ_ONCE(tick_do_timer_cpu) == cpu) {
raw_spin_lock(&jiffies_lock);
write_seqcount_begin(&jiffies_seq);
@@ -215,8 +216,8 @@
* If no cpu took the do_timer update, assign it to
* this cpu:
*/
- if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
- tick_do_timer_cpu = cpu;
+ if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) {
+ WRITE_ONCE(tick_do_timer_cpu, cpu);
tick_next_period = ktime_get();
#ifdef CONFIG_NO_HZ_FULL
/*
@@ -232,7 +233,7 @@
!tick_nohz_full_cpu(cpu)) {
tick_take_do_timer_from_boot();
tick_do_timer_boot_cpu = -1;
- WARN_ON(tick_do_timer_cpu != cpu);
+ WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu);
#endif
}
@@ -406,10 +407,10 @@
int tick_cpu_dying(unsigned int dying_cpu)
{
/*
- * If the current CPU is the timekeeper, it's the only one that
- * can safely hand over its duty. Also all online CPUs are in
- * stop machine, guaranteed not to be idle, therefore it's safe
- * to pick any online successor.
+ * If the current CPU is the timekeeper, it's the only one that can
+ * safely hand over its duty. Also all online CPUs are in stop
+ * machine, guaranteed not to be idle, therefore there is no
+ * concurrency and it's safe to pick any online successor.
*/
if (tick_do_timer_cpu == dying_cpu)
tick_do_timer_cpu = cpumask_first(cpu_online_mask);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1331216..71a792c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -8,6 +8,7 @@
*
* Started by: Thomas Gleixner and Ingo Molnar
*/
+#include <linux/compiler.h>
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
@@ -204,7 +205,7 @@
static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
{
- int cpu = smp_processor_id();
+ int tick_cpu, cpu = smp_processor_id();
/*
* Check if the do_timer duty was dropped. We don't care about
@@ -216,16 +217,18 @@
* If nohz_full is enabled, this should not happen because the
* 'tick_do_timer_cpu' CPU never relinquishes.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) &&
- unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+ tick_cpu = READ_ONCE(tick_do_timer_cpu);
+
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) {
#ifdef CONFIG_NO_HZ_FULL
WARN_ON_ONCE(tick_nohz_full_running);
#endif
- tick_do_timer_cpu = cpu;
+ WRITE_ONCE(tick_do_timer_cpu, cpu);
+ tick_cpu = cpu;
}
/* Check if jiffies need an update */
- if (tick_do_timer_cpu == cpu)
+ if (tick_cpu == cpu)
tick_do_update_jiffies64(now);
/*
@@ -610,7 +613,7 @@
* timers, workqueues, timekeeping, ...) on behalf of full dynticks
* CPUs. It must remain online when nohz full is enabled.
*/
- if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
+ if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu)
return false;
return true;
}
@@ -891,6 +894,7 @@
{
u64 basemono, next_tick, delta, expires;
unsigned long basejiff;
+ int tick_cpu;
basemono = get_jiffies_update(&basejiff);
ts->last_jiffies = basejiff;
@@ -947,9 +951,9 @@
* Otherwise we can sleep as long as we want.
*/
delta = timekeeping_max_deferment();
- if (cpu != tick_do_timer_cpu &&
- (tick_do_timer_cpu != TICK_DO_TIMER_NONE ||
- !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST)))
+ tick_cpu = READ_ONCE(tick_do_timer_cpu);
+ if (tick_cpu != cpu &&
+ (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST)))
delta = KTIME_MAX;
/* Calculate the next expiry time */
@@ -970,6 +974,7 @@
unsigned long basejiff = ts->last_jiffies;
u64 basemono = ts->timer_expires_base;
bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED);
+ int tick_cpu;
u64 expires;
/* Make sure we won't be trying to stop it twice in a row. */
@@ -1007,10 +1012,11 @@
* do_timer() never gets invoked. Keep track of the fact that it
* was the one which had the do_timer() duty last.
*/
- if (cpu == tick_do_timer_cpu) {
- tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+ tick_cpu = READ_ONCE(tick_do_timer_cpu);
+ if (tick_cpu == cpu) {
+ WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE);
tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST);
- } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
+ } else if (tick_cpu != TICK_DO_TIMER_NONE) {
tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST);
}
@@ -1173,15 +1179,17 @@
return false;
if (tick_nohz_full_enabled()) {
+ int tick_cpu = READ_ONCE(tick_do_timer_cpu);
+
/*
* Keep the tick alive to guarantee timekeeping progression
* if there are full dynticks CPUs around
*/
- if (tick_do_timer_cpu == cpu)
+ if (tick_cpu == cpu)
return false;
/* Should not happen for nohz-full */
- if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
+ if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE))
return false;
}
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 61c541c..47345bf 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -965,7 +965,7 @@
config FTRACE_RECORD_RECURSION_SIZE
int "Max number of recursed functions to record"
- default 128
+ default 128
depends on FTRACE_RECORD_RECURSION
help
This defines the limit of number of functions that can be
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 25476ea..6511dc3 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1393,7 +1393,6 @@
old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
- local_inc(&cpu_buffer->pages_touched);
/*
* Just make sure we have seen our old_write and synchronize
* with any interrupts that come in.
@@ -1430,8 +1429,9 @@
*/
local_set(&next_page->page->commit, 0);
- /* Again, either we update tail_page or an interrupt does */
- (void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page);
+ /* Either we update tail_page or an interrupt does */
+ if (try_cmpxchg(&cpu_buffer->tail_page, &tail_page, next_page))
+ local_inc(&cpu_buffer->pages_touched);
}
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7c364b8..6ef29eb 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1670,6 +1670,7 @@
return 0;
}
+#ifdef CONFIG_PERF_EVENTS
static ssize_t
event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
{
@@ -1684,6 +1685,7 @@
return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
}
+#endif
static ssize_t
event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
@@ -2152,10 +2154,12 @@
.release = seq_release,
};
+#ifdef CONFIG_PERF_EVENTS
static const struct file_operations ftrace_event_id_fops = {
.read = event_id_read,
.llseek = default_llseek,
};
+#endif
static const struct file_operations ftrace_event_filter_fops = {
.open = tracing_open_file_tr,
@@ -2548,6 +2552,14 @@
return 0;
}
+/* The file is incremented on creation and freeing the enable file decrements it */
+static void event_release(const char *name, void *data)
+{
+ struct trace_event_file *file = data;
+
+ event_file_put(file);
+}
+
static int
event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file)
{
@@ -2562,6 +2574,7 @@
{
.name = "enable",
.callback = event_callback,
+ .release = event_release,
},
{
.name = "filter",
@@ -2630,6 +2643,9 @@
return ret;
}
+ /* Gets decremented on freeing of the "enable" file */
+ event_file_get(file);
+
return 0;
}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index dfe3ee6..42bc0f36 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1466,7 +1466,7 @@
parg->fmt = kmalloc(len, GFP_KERNEL);
if (!parg->fmt) {
ret = -ENOMEM;
- goto out;
+ goto fail;
}
snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype,
parg->count);
diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c
index f95516c..23c125c 100644
--- a/kernel/vmcore_info.c
+++ b/kernel/vmcore_info.c
@@ -205,11 +205,10 @@
VMCOREINFO_NUMBER(PG_head_mask);
#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy)
VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
-#ifdef CONFIG_HUGETLB_PAGE
- VMCOREINFO_NUMBER(PG_hugetlb);
+#define PAGE_HUGETLB_MAPCOUNT_VALUE (~PG_hugetlb)
+ VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE);
#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline)
VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE);
-#endif
#ifdef CONFIG_KALLSYMS
VMCOREINFO_SYMBOL(kallsyms_names);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0066c8f..d2dbe09 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1277,8 +1277,12 @@
!cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) {
struct work_struct *work = list_first_entry(&pool->worklist,
struct work_struct, entry);
- p->wake_cpu = cpumask_any_distribute(pool->attrs->__pod_cpumask);
- get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++;
+ int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask,
+ cpu_online_mask);
+ if (wake_cpu < nr_cpu_ids) {
+ p->wake_cpu = wake_cpu;
+ get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++;
+ }
}
#endif
wake_up_process(p);
@@ -1594,6 +1598,15 @@
if (off_cpu >= 0)
total_cpus--;
+ /* If all CPUs of the wq get offline, use the default values */
+ if (unlikely(!total_cpus)) {
+ for_each_node(node)
+ wq_node_nr_active(wq, node)->max = min_active;
+
+ wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
+ return;
+ }
+
for_each_node(node) {
int node_cpus;
@@ -1606,7 +1619,7 @@
min_active, max_active);
}
- wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active;
+ wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active;
}
/**
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c63a5fb..291185f5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -375,7 +375,7 @@
Incompatible with older versions of ccache.
config DEBUG_INFO_BTF
- bool "Generate BTF typeinfo"
+ bool "Generate BTF type information"
depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED
depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST
depends on BPF_SYSCALL
@@ -408,7 +408,8 @@
using DEBUG_INFO_BTF_MODULES.
config DEBUG_INFO_BTF_MODULES
- def_bool y
+ bool "Generate BTF type information for kernel modules"
+ default y
depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF
help
Generate compact split BTF type information for kernel modules.
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index c59d2606..97f8911 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -61,9 +61,12 @@
return memblock_alloc(size, SMP_CACHE_BYTES);
}
-static inline void __init xbc_free_mem(void *addr, size_t size)
+static inline void __init xbc_free_mem(void *addr, size_t size, bool early)
{
- memblock_free(addr, size);
+ if (early)
+ memblock_free(addr, size);
+ else if (addr)
+ memblock_free_late(__pa(addr), size);
}
#else /* !__KERNEL__ */
@@ -73,7 +76,7 @@
return malloc(size);
}
-static inline void xbc_free_mem(void *addr, size_t size)
+static inline void xbc_free_mem(void *addr, size_t size, bool early)
{
free(addr);
}
@@ -898,19 +901,20 @@
}
/**
- * xbc_exit() - Clean up all parsed bootconfig
+ * _xbc_exit() - Clean up all parsed bootconfig
+ * @early: Set true if this is called before budy system is initialized.
*
* This clears all data structures of parsed bootconfig on memory.
* If you need to reuse xbc_init() with new boot config, you can
* use this.
*/
-void __init xbc_exit(void)
+void __init _xbc_exit(bool early)
{
- xbc_free_mem(xbc_data, xbc_data_size);
+ xbc_free_mem(xbc_data, xbc_data_size, early);
xbc_data = NULL;
xbc_data_size = 0;
xbc_node_num = 0;
- xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX);
+ xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX, early);
xbc_nodes = NULL;
brace_index = 0;
}
@@ -963,7 +967,7 @@
if (!xbc_nodes) {
if (emsg)
*emsg = "Failed to allocate bootconfig nodes";
- xbc_exit();
+ _xbc_exit(true);
return -ENOMEM;
}
memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX);
@@ -977,7 +981,7 @@
*epos = xbc_err_pos;
if (emsg)
*emsg = xbc_err_msg;
- xbc_exit();
+ _xbc_exit(true);
} else
ret = xbc_node_num;
diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c
index bf70850..404dba3 100644
--- a/lib/checksum_kunit.c
+++ b/lib/checksum_kunit.c
@@ -594,13 +594,15 @@
static void test_csum_ipv6_magic(struct kunit *test)
{
-#if defined(CONFIG_NET)
const struct in6_addr *saddr;
const struct in6_addr *daddr;
unsigned int len;
unsigned char proto;
__wsum csum;
+ if (!IS_ENABLED(CONFIG_NET))
+ return;
+
const int daddr_offset = sizeof(struct in6_addr);
const int len_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr);
const int proto_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr) +
@@ -618,7 +620,6 @@
CHECK_EQ(to_sum16(expected_csum_ipv6_magic[i]),
csum_ipv6_magic(saddr, daddr, len, proto, csum));
}
-#endif /* !CONFIG_NET */
}
static struct kunit_case __refdata checksum_test_cases[] = {
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index c78f335..f2c5e79 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -302,7 +302,11 @@
} else {
for (end = buf; *end && !isspace(*end); end++)
;
- BUG_ON(end == buf);
+ if (end == buf) {
+ pr_err("parse err after word:%d=%s\n", nwords,
+ nwords ? words[nwords - 1] : "<none>");
+ return -EINVAL;
+ }
}
/* `buf' is start of word, `end' is one past its end */
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 68b45c8..7bc2220 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -1124,7 +1124,7 @@
do {
res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max,
extraction_flags, &off);
- if (res < 0)
+ if (res <= 0)
goto failed;
len = res;
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index 68c9738..cd8f234 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -627,10 +627,10 @@
/*
* Zero out zone modifiers, as we don't have specific zone
* requirements. Keep the flags related to allocation in atomic
- * contexts and I/O.
+ * contexts, I/O, nolockdep.
*/
alloc_flags &= ~GFP_ZONEMASK;
- alloc_flags &= (GFP_ATOMIC | GFP_KERNEL);
+ alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP);
alloc_flags |= __GFP_NOWARN;
page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER);
if (page)
diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c
index 276c121..c288df9 100644
--- a/lib/test_ubsan.c
+++ b/lib/test_ubsan.c
@@ -134,7 +134,7 @@
};
/* Excluded because they Oops the module. */
-static const test_ubsan_fp skip_ubsan_array[] = {
+static __used const test_ubsan_fp skip_ubsan_array[] = {
test_ubsan_divrem_overflow,
};
diff --git a/lib/ubsan.c b/lib/ubsan.c
index 5fc107f..a1c983d 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -44,9 +44,10 @@
case ubsan_shift_out_of_bounds:
return "UBSAN: shift out of bounds";
#endif
-#ifdef CONFIG_UBSAN_DIV_ZERO
+#if defined(CONFIG_UBSAN_DIV_ZERO) || defined(CONFIG_UBSAN_SIGNED_WRAP)
/*
- * SanitizerKind::IntegerDivideByZero emits
+ * SanitizerKind::IntegerDivideByZero and
+ * SanitizerKind::SignedIntegerOverflow emit
* SanitizerHandler::DivremOverflow.
*/
case ubsan_divrem_overflow:
@@ -78,6 +79,19 @@
case ubsan_type_mismatch:
return "UBSAN: type mismatch";
#endif
+#ifdef CONFIG_UBSAN_SIGNED_WRAP
+ /*
+ * SanitizerKind::SignedIntegerOverflow emits
+ * SanitizerHandler::AddOverflow, SanitizerHandler::SubOverflow,
+ * or SanitizerHandler::MulOverflow.
+ */
+ case ubsan_add_overflow:
+ return "UBSAN: integer addition overflow";
+ case ubsan_sub_overflow:
+ return "UBSAN: integer subtraction overflow";
+ case ubsan_mul_overflow:
+ return "UBSAN: integer multiplication overflow";
+#endif
default:
return "UBSAN: unrecognized failure code";
}
diff --git a/mm/gup.c b/mm/gup.c
index af8edad..1611e73 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1206,6 +1206,22 @@
/* first iteration or cross vma bound */
if (!vma || start >= vma->vm_end) {
+ /*
+ * MADV_POPULATE_(READ|WRITE) wants to handle VMA
+ * lookups+error reporting differently.
+ */
+ if (gup_flags & FOLL_MADV_POPULATE) {
+ vma = vma_lookup(mm, start);
+ if (!vma) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ if (check_vma_flags(vma, gup_flags)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ goto retry;
+ }
vma = gup_vma_lookup(mm, start);
if (!vma && in_gate_area(mm, start)) {
ret = get_gate_page(mm, start & PAGE_MASK,
@@ -1685,35 +1701,35 @@
}
/*
- * faultin_vma_page_range() - populate (prefault) page tables inside the
- * given VMA range readable/writable
+ * faultin_page_range() - populate (prefault) page tables inside the
+ * given range readable/writable
*
* This takes care of mlocking the pages, too, if VM_LOCKED is set.
*
- * @vma: target vma
+ * @mm: the mm to populate page tables in
* @start: start address
* @end: end address
* @write: whether to prefault readable or writable
* @locked: whether the mmap_lock is still held
*
- * Returns either number of processed pages in the vma, or a negative error
- * code on error (see __get_user_pages()).
+ * Returns either number of processed pages in the MM, or a negative error
+ * code on error (see __get_user_pages()). Note that this function reports
+ * errors related to VMAs, such as incompatible mappings, as expected by
+ * MADV_POPULATE_(READ|WRITE).
*
- * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and
- * covered by the VMA. If it's released, *@locked will be set to 0.
+ * The range must be page-aligned.
+ *
+ * mm->mmap_lock must be held. If it's released, *@locked will be set to 0.
*/
-long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end, bool write, int *locked)
+long faultin_page_range(struct mm_struct *mm, unsigned long start,
+ unsigned long end, bool write, int *locked)
{
- struct mm_struct *mm = vma->vm_mm;
unsigned long nr_pages = (end - start) / PAGE_SIZE;
int gup_flags;
long ret;
VM_BUG_ON(!PAGE_ALIGNED(start));
VM_BUG_ON(!PAGE_ALIGNED(end));
- VM_BUG_ON_VMA(start < vma->vm_start, vma);
- VM_BUG_ON_VMA(end > vma->vm_end, vma);
mmap_assert_locked(mm);
/*
@@ -1725,19 +1741,13 @@
* a poisoned page.
* !FOLL_FORCE: Require proper access permissions.
*/
- gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE;
+ gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE |
+ FOLL_MADV_POPULATE;
if (write)
gup_flags |= FOLL_WRITE;
- /*
- * We want to report -EINVAL instead of -EFAULT for any permission
- * problems or incompatible mappings.
- */
- if (check_vma_flags(vma, gup_flags))
- return -EINVAL;
-
- ret = __get_user_pages(mm, start, nr_pages, gup_flags,
- NULL, locked);
+ ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked,
+ gup_flags);
lru_add_drain();
return ret;
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9859aa4..89f58c7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2259,9 +2259,6 @@
goto unlock_ptls;
}
- folio_move_anon_rmap(src_folio, dst_vma);
- WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
-
src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd);
/* Folio got pinned from under us. Put it back and fail the move. */
if (folio_maybe_dma_pinned(src_folio)) {
@@ -2270,6 +2267,9 @@
goto unlock_ptls;
}
+ folio_move_anon_rmap(src_folio, dst_vma);
+ WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr));
+
_dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot);
/* Follow mremap() behavior and treat the entry dirty after the move */
_dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 23ef240..ce7be5c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1624,7 +1624,7 @@
{
lockdep_assert_held(&hugetlb_lock);
- folio_clear_hugetlb(folio);
+ __folio_clear_hugetlb(folio);
}
/*
@@ -1711,7 +1711,7 @@
h->surplus_huge_pages_node[nid]++;
}
- folio_set_hugetlb(folio);
+ __folio_set_hugetlb(folio);
folio_change_private(folio, NULL);
/*
* We have to set hugetlb_vmemmap_optimized again as above
@@ -1781,7 +1781,7 @@
* If vmemmap pages were allocated above, then we need to clear the
* hugetlb destructor under the hugetlb lock.
*/
- if (clear_dtor) {
+ if (folio_test_hugetlb(folio)) {
spin_lock_irq(&hugetlb_lock);
__clear_hugetlb_destructor(h, folio);
spin_unlock_irq(&hugetlb_lock);
@@ -2049,7 +2049,7 @@
static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio)
{
- folio_set_hugetlb(folio);
+ __folio_set_hugetlb(folio);
INIT_LIST_HEAD(&folio->lru);
hugetlb_set_folio_subpool(folio, NULL);
set_hugetlb_cgroup(folio, NULL);
@@ -2160,22 +2160,6 @@
}
/*
- * PageHuge() only returns true for hugetlbfs pages, but not for normal or
- * transparent huge pages. See the PageTransHuge() documentation for more
- * details.
- */
-int PageHuge(const struct page *page)
-{
- const struct folio *folio;
-
- if (!PageCompound(page))
- return 0;
- folio = page_folio(page);
- return folio_test_hugetlb(folio);
-}
-EXPORT_SYMBOL_GPL(PageHuge);
-
-/*
* Find and lock address space (mapping) in write mode.
*
* Upon entry, the page is locked which means that page_mapping() is
@@ -3268,9 +3252,12 @@
rsv_adjust = hugepage_subpool_put_pages(spool, 1);
hugetlb_acct_memory(h, -rsv_adjust);
- if (deferred_reserve)
+ if (deferred_reserve) {
+ spin_lock_irq(&hugetlb_lock);
hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h),
pages_per_huge_page(h), folio);
+ spin_unlock_irq(&hugetlb_lock);
+ }
}
if (!memcg_charge_ret)
@@ -6274,6 +6261,12 @@
VM_UFFD_MISSING);
}
+ if (!(vma->vm_flags & VM_MAYSHARE)) {
+ ret = vmf_anon_prepare(vmf);
+ if (unlikely(ret))
+ goto out;
+ }
+
folio = alloc_hugetlb_folio(vma, haddr, 0);
if (IS_ERR(folio)) {
/*
@@ -6310,15 +6303,12 @@
*/
restore_reserve_on_error(h, vma, haddr, folio);
folio_put(folio);
+ ret = VM_FAULT_SIGBUS;
goto out;
}
new_pagecache_folio = true;
} else {
folio_lock(folio);
-
- ret = vmf_anon_prepare(vmf);
- if (unlikely(ret))
- goto backout_unlocked;
anon_rmap = 1;
}
} else {
@@ -7044,9 +7034,13 @@
if (!pte_same(pte, newpte))
set_huge_pte_at(mm, address, ptep, newpte, psize);
} 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)
+ /*
+ * Do nothing on a poison marker; page is
+ * corrupted, permissons do not apply. Here
+ * pte_marker_uffd_wp()==true implies !poison
+ * because they're mutual exclusive.
+ */
+ if (pte_marker_uffd_wp(pte) && uffd_wp_resolve)
/* Safe to modify directly (non-present->none). */
huge_pte_clear(mm, address, ptep, psize);
} else if (!huge_pte_none(pte)) {
diff --git a/mm/internal.h b/mm/internal.h
index 7e486f2..07ad267 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -686,9 +686,8 @@
void unmap_mapping_folio(struct folio *folio);
extern long populate_vma_page_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, int *locked);
-extern long faultin_vma_page_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end,
- bool write, int *locked);
+extern long faultin_page_range(struct mm_struct *mm, unsigned long start,
+ unsigned long end, bool write, int *locked);
extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
unsigned long bytes);
@@ -1127,10 +1126,13 @@
FOLL_FAST_ONLY = 1 << 20,
/* allow unlocking the mmap lock */
FOLL_UNLOCKABLE = 1 << 21,
+ /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */
+ FOLL_MADV_POPULATE = 1 << 22,
};
#define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \
- FOLL_FAST_ONLY | FOLL_UNLOCKABLE)
+ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \
+ FOLL_MADV_POPULATE)
/*
* Indicates for which pages that are write-protected in the page table,
diff --git a/mm/madvise.c b/mm/madvise.c
index 44a498c..1a073fc 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -908,27 +908,14 @@
{
const bool write = behavior == MADV_POPULATE_WRITE;
struct mm_struct *mm = vma->vm_mm;
- unsigned long tmp_end;
int locked = 1;
long pages;
*prev = vma;
while (start < end) {
- /*
- * We might have temporarily dropped the lock. For example,
- * our VMA might have been split.
- */
- if (!vma || start >= vma->vm_end) {
- vma = vma_lookup(mm, start);
- if (!vma)
- return -ENOMEM;
- }
-
- tmp_end = min_t(unsigned long, end, vma->vm_end);
/* Populate (prefault) page tables readable/writable. */
- pages = faultin_vma_page_range(vma, start, tmp_end, write,
- &locked);
+ pages = faultin_page_range(mm, start, end, write, &locked);
if (!locked) {
mmap_read_lock(mm);
locked = 1;
@@ -949,7 +936,7 @@
pr_warn_once("%s: unhandled return value: %ld\n",
__func__, pages);
fallthrough;
- case -ENOMEM:
+ case -ENOMEM: /* No VMA or out of memory. */
return -ENOMEM;
}
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 9349948..9e62a00 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -154,11 +154,23 @@
{
int ret;
- zone_pcp_disable(page_zone(page));
+ /*
+ * zone_pcp_disable() can't be used here. It will
+ * hold pcp_batch_high_lock and dissolve_free_huge_page() might hold
+ * cpu_hotplug_lock via static_key_slow_dec() when hugetlb vmemmap
+ * optimization is enabled. This will break current lock dependency
+ * chain and leads to deadlock.
+ * Disabling pcp before dissolving the page was a deterministic
+ * approach because we made sure that those pages cannot end up in any
+ * PCP list. Draining PCP lists expels those pages to the buddy system,
+ * but nothing guarantees that those pages do not get back to a PCP
+ * queue if we need to refill those.
+ */
ret = dissolve_free_huge_page(page);
- if (!ret)
+ if (!ret) {
+ drain_all_pages(page_zone(page));
ret = take_page_off_buddy(page);
- zone_pcp_enable(page_zone(page));
+ }
return ret;
}
diff --git a/mm/page_owner.c b/mm/page_owner.c
index d17d135..742f432 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -118,7 +118,6 @@
register_dummy_stack();
register_failure_stack();
register_early_stack();
- static_branch_enable(&page_owner_inited);
init_early_allocated_pages();
/* Initialize dummy and failure stacks and link them to stack_list */
dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle);
@@ -129,6 +128,7 @@
refcount_set(&failure_stack.stack_record->count, 1);
dummy_stack.next = &failure_stack;
stack_list = &dummy_stack;
+ static_branch_enable(&page_owner_inited);
}
struct page_ext_operations page_owner_ops = {
@@ -196,7 +196,8 @@
spin_unlock_irqrestore(&stack_list_lock, flags);
}
-static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask)
+static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask,
+ int nr_base_pages)
{
struct stack_record *stack_record = __stack_depot_get_stack_record(handle);
@@ -217,20 +218,74 @@
/* Add the new stack_record to our list */
add_stack_record_to_list(stack_record, gfp_mask);
}
- refcount_inc(&stack_record->count);
+ refcount_add(nr_base_pages, &stack_record->count);
}
-static void dec_stack_record_count(depot_stack_handle_t handle)
+static void dec_stack_record_count(depot_stack_handle_t handle,
+ int nr_base_pages)
{
struct stack_record *stack_record = __stack_depot_get_stack_record(handle);
- if (stack_record)
- refcount_dec(&stack_record->count);
+ if (!stack_record)
+ return;
+
+ if (refcount_sub_and_test(nr_base_pages, &stack_record->count))
+ pr_warn("%s: refcount went to 0 for %u handle\n", __func__,
+ handle);
+}
+
+static inline void __update_page_owner_handle(struct page_ext *page_ext,
+ depot_stack_handle_t handle,
+ unsigned short order,
+ gfp_t gfp_mask,
+ short last_migrate_reason, u64 ts_nsec,
+ pid_t pid, pid_t tgid, char *comm)
+{
+ int i;
+ struct page_owner *page_owner;
+
+ for (i = 0; i < (1 << order); i++) {
+ page_owner = get_page_owner(page_ext);
+ page_owner->handle = handle;
+ page_owner->order = order;
+ page_owner->gfp_mask = gfp_mask;
+ page_owner->last_migrate_reason = last_migrate_reason;
+ page_owner->pid = pid;
+ page_owner->tgid = tgid;
+ page_owner->ts_nsec = ts_nsec;
+ strscpy(page_owner->comm, comm,
+ sizeof(page_owner->comm));
+ __set_bit(PAGE_EXT_OWNER, &page_ext->flags);
+ __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
+ page_ext = page_ext_next(page_ext);
+ }
+}
+
+static inline void __update_page_owner_free_handle(struct page_ext *page_ext,
+ depot_stack_handle_t handle,
+ unsigned short order,
+ pid_t pid, pid_t tgid,
+ u64 free_ts_nsec)
+{
+ int i;
+ struct page_owner *page_owner;
+
+ for (i = 0; i < (1 << order); i++) {
+ page_owner = get_page_owner(page_ext);
+ /* Only __reset_page_owner() wants to clear the bit */
+ if (handle) {
+ __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
+ page_owner->free_handle = handle;
+ }
+ page_owner->free_ts_nsec = free_ts_nsec;
+ page_owner->free_pid = current->pid;
+ page_owner->free_tgid = current->tgid;
+ page_ext = page_ext_next(page_ext);
+ }
}
void __reset_page_owner(struct page *page, unsigned short order)
{
- int i;
struct page_ext *page_ext;
depot_stack_handle_t handle;
depot_stack_handle_t alloc_handle;
@@ -245,16 +300,10 @@
alloc_handle = page_owner->handle;
handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
- for (i = 0; i < (1 << order); i++) {
- __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
- page_owner->free_handle = handle;
- page_owner->free_ts_nsec = free_ts_nsec;
- page_owner->free_pid = current->pid;
- page_owner->free_tgid = current->tgid;
- page_ext = page_ext_next(page_ext);
- page_owner = get_page_owner(page_ext);
- }
+ __update_page_owner_free_handle(page_ext, handle, order, current->pid,
+ current->tgid, free_ts_nsec);
page_ext_put(page_ext);
+
if (alloc_handle != early_handle)
/*
* early_handle is being set as a handle for all those
@@ -263,39 +312,14 @@
* the machinery is not ready yet, we cannot decrement
* their refcount either.
*/
- dec_stack_record_count(alloc_handle);
-}
-
-static inline void __set_page_owner_handle(struct page_ext *page_ext,
- depot_stack_handle_t handle,
- unsigned short order, gfp_t gfp_mask)
-{
- struct page_owner *page_owner;
- int i;
- u64 ts_nsec = local_clock();
-
- for (i = 0; i < (1 << order); i++) {
- page_owner = get_page_owner(page_ext);
- page_owner->handle = handle;
- page_owner->order = order;
- page_owner->gfp_mask = gfp_mask;
- page_owner->last_migrate_reason = -1;
- page_owner->pid = current->pid;
- page_owner->tgid = current->tgid;
- page_owner->ts_nsec = ts_nsec;
- strscpy(page_owner->comm, current->comm,
- sizeof(page_owner->comm));
- __set_bit(PAGE_EXT_OWNER, &page_ext->flags);
- __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
-
- page_ext = page_ext_next(page_ext);
- }
+ dec_stack_record_count(alloc_handle, 1 << order);
}
noinline void __set_page_owner(struct page *page, unsigned short order,
gfp_t gfp_mask)
{
struct page_ext *page_ext;
+ u64 ts_nsec = local_clock();
depot_stack_handle_t handle;
handle = save_stack(gfp_mask);
@@ -303,9 +327,11 @@
page_ext = page_ext_get(page);
if (unlikely(!page_ext))
return;
- __set_page_owner_handle(page_ext, handle, order, gfp_mask);
+ __update_page_owner_handle(page_ext, handle, order, gfp_mask, -1,
+ current->pid, current->tgid, ts_nsec,
+ current->comm);
page_ext_put(page_ext);
- inc_stack_record_count(handle, gfp_mask);
+ inc_stack_record_count(handle, gfp_mask, 1 << order);
}
void __set_page_owner_migrate_reason(struct page *page, int reason)
@@ -340,9 +366,12 @@
void __folio_copy_owner(struct folio *newfolio, struct folio *old)
{
+ int i;
struct page_ext *old_ext;
struct page_ext *new_ext;
- struct page_owner *old_page_owner, *new_page_owner;
+ struct page_owner *old_page_owner;
+ struct page_owner *new_page_owner;
+ depot_stack_handle_t migrate_handle;
old_ext = page_ext_get(&old->page);
if (unlikely(!old_ext))
@@ -356,30 +385,32 @@
old_page_owner = get_page_owner(old_ext);
new_page_owner = get_page_owner(new_ext);
- new_page_owner->order = old_page_owner->order;
- new_page_owner->gfp_mask = old_page_owner->gfp_mask;
- new_page_owner->last_migrate_reason =
- old_page_owner->last_migrate_reason;
- new_page_owner->handle = old_page_owner->handle;
- new_page_owner->pid = old_page_owner->pid;
- new_page_owner->tgid = old_page_owner->tgid;
- new_page_owner->free_pid = old_page_owner->free_pid;
- new_page_owner->free_tgid = old_page_owner->free_tgid;
- new_page_owner->ts_nsec = old_page_owner->ts_nsec;
- new_page_owner->free_ts_nsec = old_page_owner->ts_nsec;
- strcpy(new_page_owner->comm, old_page_owner->comm);
-
+ migrate_handle = new_page_owner->handle;
+ __update_page_owner_handle(new_ext, old_page_owner->handle,
+ old_page_owner->order, old_page_owner->gfp_mask,
+ old_page_owner->last_migrate_reason,
+ old_page_owner->ts_nsec, old_page_owner->pid,
+ old_page_owner->tgid, old_page_owner->comm);
/*
- * We don't clear the bit on the old folio as it's going to be freed
- * after migration. Until then, the info can be useful in case of
- * a bug, and the overall stats will be off a bit only temporarily.
- * Also, migrate_misplaced_transhuge_page() can still fail the
- * migration and then we want the old folio to retain the info. But
- * in that case we also don't need to explicitly clear the info from
- * the new page, which will be freed.
+ * Do not proactively clear PAGE_EXT_OWNER{_ALLOCATED} bits as the folio
+ * will be freed after migration. Keep them until then as they may be
+ * useful.
*/
- __set_bit(PAGE_EXT_OWNER, &new_ext->flags);
- __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags);
+ __update_page_owner_free_handle(new_ext, 0, old_page_owner->order,
+ old_page_owner->free_pid,
+ old_page_owner->free_tgid,
+ old_page_owner->free_ts_nsec);
+ /*
+ * We linked the original stack to the new folio, we need to do the same
+ * for the new one and the old folio otherwise there will be an imbalance
+ * when subtracting those pages from the stack.
+ */
+ for (i = 0; i < (1 << new_page_owner->order); i++) {
+ old_page_owner->handle = migrate_handle;
+ old_ext = page_ext_next(old_ext);
+ old_page_owner = get_page_owner(old_ext);
+ }
+
page_ext_put(new_ext);
page_ext_put(old_ext);
}
@@ -787,8 +818,9 @@
goto ext_put_continue;
/* Found early allocated page */
- __set_page_owner_handle(page_ext, early_handle,
- 0, 0);
+ __update_page_owner_handle(page_ext, early_handle, 0, 0,
+ -1, local_clock(), current->pid,
+ current->tgid, current->comm);
count++;
ext_put_continue:
page_ext_put(page_ext);
@@ -840,13 +872,11 @@
* value of stack_list.
*/
stack = smp_load_acquire(&stack_list);
+ m->private = stack;
} else {
stack = m->private;
- stack = stack->next;
}
- m->private = stack;
-
return stack;
}
@@ -861,11 +891,11 @@
return stack;
}
-static unsigned long page_owner_stack_threshold;
+static unsigned long page_owner_pages_threshold;
static int stack_print(struct seq_file *m, void *v)
{
- int i, stack_count;
+ int i, nr_base_pages;
struct stack *stack = v;
unsigned long *entries;
unsigned long nr_entries;
@@ -876,14 +906,14 @@
nr_entries = stack_record->size;
entries = stack_record->entries;
- stack_count = refcount_read(&stack_record->count) - 1;
+ nr_base_pages = refcount_read(&stack_record->count) - 1;
- if (stack_count < 1 || stack_count < page_owner_stack_threshold)
+ if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold)
return 0;
for (i = 0; i < nr_entries; i++)
seq_printf(m, " %pS\n", (void *)entries[i]);
- seq_printf(m, "stack_count: %d\n\n", stack_count);
+ seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages);
return 0;
}
@@ -913,13 +943,13 @@
static int page_owner_threshold_get(void *data, u64 *val)
{
- *val = READ_ONCE(page_owner_stack_threshold);
+ *val = READ_ONCE(page_owner_pages_threshold);
return 0;
}
static int page_owner_threshold_set(void *data, u64 val)
{
- WRITE_ONCE(page_owner_stack_threshold, val);
+ WRITE_ONCE(page_owner_pages_threshold, val);
return 0;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index 0aad0d9..94ab99b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -748,12 +748,6 @@
#define shmem_huge SHMEM_HUGE_DENY
-bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force,
- struct mm_struct *mm, unsigned long vm_flags)
-{
- return false;
-}
-
static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
struct shrink_control *sc, unsigned long nr_to_split)
{
diff --git a/mm/zswap.c b/mm/zswap.c
index caed028..6f8850c4 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1331,15 +1331,22 @@
if (!gfp_has_io_fs(sc->gfp_mask))
return 0;
-#ifdef CONFIG_MEMCG_KMEM
- mem_cgroup_flush_stats(memcg);
- nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
- nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
-#else
- /* use pool stats instead of memcg stats */
- nr_backing = zswap_pool_total_size >> PAGE_SHIFT;
- nr_stored = atomic_read(&zswap_nr_stored);
-#endif
+ /*
+ * For memcg, use the cgroup-wide ZSWAP stats since we don't
+ * have them per-node and thus per-lruvec. Careful if memcg is
+ * runtime-disabled: we can get sc->memcg == NULL, which is ok
+ * for the lruvec, but not for memcg_page_state().
+ *
+ * Without memcg, use the zswap pool-wide metrics.
+ */
+ if (!mem_cgroup_disabled()) {
+ mem_cgroup_flush_stats(memcg);
+ nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
+ nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
+ } else {
+ nr_backing = zswap_pool_total_size >> PAGE_SHIFT;
+ nr_stored = atomic_read(&zswap_nr_stored);
+ }
if (!nr_stored)
return 0;
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index f001582..9404dd5 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -478,6 +478,8 @@
if (unlikely(!vhdr))
goto out;
+ NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = hlen;
+
type = vhdr->h_vlan_encapsulated_proto;
ptype = gro_find_receive_by_type(type);
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 558e158..9169efb 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -103,7 +103,7 @@
s->ax25_dev = NULL;
if (sk->sk_socket) {
netdev_put(ax25_dev->dev,
- &ax25_dev->dev_tracker);
+ &s->dev_tracker);
ax25_dev_put(ax25_dev);
}
ax25_cb_del(s);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index b95c367..2243cec 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -3948,7 +3948,7 @@
spin_lock_bh(&bat_priv->tt.commit_lock);
- while (true) {
+ while (timeout) {
table_size = batadv_tt_local_table_transmit_size(bat_priv);
if (packet_size_max >= table_size)
break;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 3ad74f7..0534625 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1263,7 +1263,7 @@
struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
u8 dst_type, bool dst_resolved, u8 sec_level,
- u16 conn_timeout, u8 role)
+ u16 conn_timeout, u8 role, u8 phy, u8 sec_phy)
{
struct hci_conn *conn;
struct smp_irk *irk;
@@ -1326,6 +1326,8 @@
conn->dst_type = dst_type;
conn->sec_level = BT_SECURITY_LOW;
conn->conn_timeout = conn_timeout;
+ conn->le_adv_phy = phy;
+ conn->le_adv_sec_phy = sec_phy;
err = hci_connect_le_sync(hdev, conn);
if (err) {
@@ -2273,7 +2275,7 @@
le = hci_connect_le(hdev, dst, dst_type, false,
BT_SECURITY_LOW,
HCI_LE_CONN_TIMEOUT,
- HCI_ROLE_SLAVE);
+ HCI_ROLE_SLAVE, 0, 0);
else
le = hci_connect_le_scan(hdev, dst, dst_type,
BT_SECURITY_LOW,
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a8b8cfe..4a27e4a 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3218,7 +3218,7 @@
if (key) {
set_bit(HCI_CONN_ENCRYPT, &conn->flags);
- if (!(hdev->commands[20] & 0x10)) {
+ if (!read_key_size_capable(hdev)) {
conn->enc_key_size = HCI_LINK_KEY_SIZE;
} else {
cp.handle = cpu_to_le16(conn->handle);
@@ -3666,8 +3666,7 @@
* controller really supports it. If it doesn't, assume
* the default size (16).
*/
- if (!(hdev->commands[20] & 0x10) ||
- test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) {
+ if (!read_key_size_capable(hdev)) {
conn->enc_key_size = HCI_LINK_KEY_SIZE;
goto notify;
}
@@ -6038,7 +6037,7 @@
static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev,
bdaddr_t *addr,
u8 addr_type, bool addr_resolved,
- u8 adv_type)
+ u8 adv_type, u8 phy, u8 sec_phy)
{
struct hci_conn *conn;
struct hci_conn_params *params;
@@ -6093,7 +6092,7 @@
conn = hci_connect_le(hdev, addr, addr_type, addr_resolved,
BT_SECURITY_LOW, hdev->def_le_autoconnect_timeout,
- HCI_ROLE_MASTER);
+ HCI_ROLE_MASTER, phy, sec_phy);
if (!IS_ERR(conn)) {
/* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned
* by higher layer that tried to connect, if no then
@@ -6128,8 +6127,9 @@
static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
u8 bdaddr_type, bdaddr_t *direct_addr,
- u8 direct_addr_type, s8 rssi, u8 *data, u8 len,
- bool ext_adv, bool ctl_time, u64 instant)
+ u8 direct_addr_type, u8 phy, u8 sec_phy, s8 rssi,
+ u8 *data, u8 len, bool ext_adv, bool ctl_time,
+ u64 instant)
{
struct discovery_state *d = &hdev->discovery;
struct smp_irk *irk;
@@ -6217,7 +6217,7 @@
* for advertising reports) and is already verified to be RPA above.
*/
conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved,
- type);
+ type, phy, sec_phy);
if (!ext_adv && conn && type == LE_ADV_IND &&
len <= max_adv_len(hdev)) {
/* Store report for later inclusion by
@@ -6363,7 +6363,8 @@
if (info->length <= max_adv_len(hdev)) {
rssi = info->data[info->length];
process_adv_report(hdev, info->type, &info->bdaddr,
- info->bdaddr_type, NULL, 0, rssi,
+ info->bdaddr_type, NULL, 0,
+ HCI_ADV_PHY_1M, 0, rssi,
info->data, info->length, false,
false, instant);
} else {
@@ -6448,6 +6449,8 @@
if (legacy_evt_type != LE_ADV_INVALID) {
process_adv_report(hdev, legacy_evt_type, &info->bdaddr,
info->bdaddr_type, NULL, 0,
+ info->primary_phy,
+ info->secondary_phy,
info->rssi, info->data, info->length,
!(evt_type & LE_EXT_ADV_LEGACY_PDU),
false, instant);
@@ -6730,8 +6733,8 @@
process_adv_report(hdev, info->type, &info->bdaddr,
info->bdaddr_type, &info->direct_addr,
- info->direct_addr_type, info->rssi, NULL, 0,
- false, false, instant);
+ info->direct_addr_type, HCI_ADV_PHY_1M, 0,
+ info->rssi, NULL, 0, false, false, instant);
}
hci_dev_unlock(hdev);
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 00e0213..efea25e 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -105,8 +105,10 @@
if (hdev->req_status == HCI_REQ_PEND) {
hdev->req_result = result;
hdev->req_status = HCI_REQ_DONE;
- if (skb)
+ if (skb) {
+ kfree_skb(hdev->req_skb);
hdev->req_skb = skb_get(skb);
+ }
wake_up_interruptible(&hdev->req_wait_q);
}
}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 4ee1b97..703b84b 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1946,10 +1946,9 @@
switch (optname) {
case HCI_DATA_DIR:
- if (copy_from_sockptr(&opt, optval, sizeof(opt))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len);
+ if (err)
break;
- }
if (opt)
hci_pi(sk)->cmsg_mask |= HCI_CMSG_DIR;
@@ -1958,10 +1957,9 @@
break;
case HCI_TIME_STAMP:
- if (copy_from_sockptr(&opt, optval, sizeof(opt))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len);
+ if (err)
break;
- }
if (opt)
hci_pi(sk)->cmsg_mask |= HCI_CMSG_TSTAMP;
@@ -1979,11 +1977,9 @@
uf.event_mask[1] = *((u32 *) f->event_mask + 1);
}
- len = min_t(unsigned int, len, sizeof(uf));
- if (copy_from_sockptr(&uf, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&uf, sizeof(uf), optval, len);
+ if (err)
break;
- }
if (!capable(CAP_NET_RAW)) {
uf.type_mask &= hci_sec_filter.type_mask;
@@ -2042,10 +2038,9 @@
goto done;
}
- if (copy_from_sockptr(&opt, optval, sizeof(opt))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len);
+ if (err)
break;
- }
hci_pi(sk)->mtu = opt;
break;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 8fe0292..4c707eb6 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2814,8 +2814,8 @@
if (qos->bcast.in.phy & BT_ISO_PHY_CODED) {
cp->scanning_phys |= LE_SCAN_PHY_CODED;
hci_le_scan_phy_params(phy, type,
- interval,
- window);
+ interval * 3,
+ window * 3);
num_phy++;
phy++;
}
@@ -2835,7 +2835,7 @@
if (scan_coded(hdev)) {
cp->scanning_phys |= LE_SCAN_PHY_CODED;
- hci_le_scan_phy_params(phy, type, interval, window);
+ hci_le_scan_phy_params(phy, type, interval * 3, window * 3);
num_phy++;
phy++;
}
@@ -6346,7 +6346,8 @@
plen = sizeof(*cp);
- if (scan_1m(hdev)) {
+ if (scan_1m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_1M ||
+ conn->le_adv_sec_phy == HCI_ADV_PHY_1M)) {
cp->phys |= LE_SCAN_PHY_1M;
set_ext_conn_params(conn, p);
@@ -6354,7 +6355,8 @@
plen += sizeof(*p);
}
- if (scan_2m(hdev)) {
+ if (scan_2m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_2M ||
+ conn->le_adv_sec_phy == HCI_ADV_PHY_2M)) {
cp->phys |= LE_SCAN_PHY_2M;
set_ext_conn_params(conn, p);
@@ -6362,7 +6364,8 @@
plen += sizeof(*p);
}
- if (scan_coded(hdev)) {
+ if (scan_coded(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_CODED ||
+ conn->le_adv_sec_phy == HCI_ADV_PHY_CODED)) {
cp->phys |= LE_SCAN_PHY_CODED;
set_ext_conn_params(conn, p);
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index c8793e5..ef0cc80 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1451,8 +1451,8 @@
static bool check_bcast_qos(struct bt_iso_qos *qos)
{
- if (qos->bcast.sync_factor == 0x00)
- return false;
+ if (!qos->bcast.sync_factor)
+ qos->bcast.sync_factor = 0x01;
if (qos->bcast.packing > 0x01)
return false;
@@ -1475,6 +1475,9 @@
if (qos->bcast.skip > 0x01f3)
return false;
+ if (!qos->bcast.sync_timeout)
+ qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT;
+
if (qos->bcast.sync_timeout < 0x000a || qos->bcast.sync_timeout > 0x4000)
return false;
@@ -1484,6 +1487,9 @@
if (qos->bcast.mse > 0x1f)
return false;
+ if (!qos->bcast.timeout)
+ qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT;
+
if (qos->bcast.timeout < 0x000a || qos->bcast.timeout > 0x4000)
return false;
@@ -1494,7 +1500,7 @@
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
- int len, err = 0;
+ int err = 0;
struct bt_iso_qos qos = default_qos;
u32 opt;
@@ -1509,10 +1515,9 @@
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
@@ -1521,10 +1526,9 @@
break;
case BT_PKT_STATUS:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags);
@@ -1539,17 +1543,9 @@
break;
}
- len = min_t(unsigned int, sizeof(qos), optlen);
-
- if (copy_from_sockptr(&qos, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&qos, sizeof(qos), optval, optlen);
+ if (err)
break;
- }
-
- if (len == sizeof(qos.ucast) && !check_ucast_qos(&qos)) {
- err = -EINVAL;
- break;
- }
iso_pi(sk)->qos = qos;
iso_pi(sk)->qos_user_set = true;
@@ -1564,18 +1560,16 @@
}
if (optlen > sizeof(iso_pi(sk)->base)) {
- err = -EOVERFLOW;
+ err = -EINVAL;
break;
}
- len = min_t(unsigned int, sizeof(iso_pi(sk)->base), optlen);
-
- if (copy_from_sockptr(iso_pi(sk)->base, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(iso_pi(sk)->base, optlen, optval,
+ optlen);
+ if (err)
break;
- }
- iso_pi(sk)->base_len = len;
+ iso_pi(sk)->base_len = optlen;
break;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 467b242..84fc708 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4054,8 +4054,7 @@
return -EPROTO;
hci_dev_lock(hdev);
- if (hci_dev_test_flag(hdev, HCI_MGMT) &&
- !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags))
+ if (hci_dev_test_flag(hdev, HCI_MGMT))
mgmt_device_connected(hdev, hcon, NULL, 0);
hci_dev_unlock(hdev);
@@ -7019,7 +7018,7 @@
if (hci_dev_test_flag(hdev, HCI_ADVERTISING))
hcon = hci_connect_le(hdev, dst, dst_type, false,
chan->sec_level, timeout,
- HCI_ROLE_SLAVE);
+ HCI_ROLE_SLAVE, 0, 0);
else
hcon = hci_connect_le_scan(hdev, dst, dst_type,
chan->sec_level, timeout,
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 4287aa6..5cc83f9 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -439,7 +439,8 @@
struct l2cap_chan *chan = l2cap_pi(sk)->chan;
struct l2cap_options opts;
struct l2cap_conninfo cinfo;
- int len, err = 0;
+ int err = 0;
+ size_t len;
u32 opt;
BT_DBG("sk %p", sk);
@@ -486,7 +487,7 @@
BT_DBG("mode 0x%2.2x", chan->mode);
- len = min_t(unsigned int, len, sizeof(opts));
+ len = min(len, sizeof(opts));
if (copy_to_user(optval, (char *) &opts, len))
err = -EFAULT;
@@ -536,7 +537,7 @@
cinfo.hci_handle = chan->conn->hcon->handle;
memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3);
- len = min_t(unsigned int, len, sizeof(cinfo));
+ len = min(len, sizeof(cinfo));
if (copy_to_user(optval, (char *) &cinfo, len))
err = -EFAULT;
@@ -727,7 +728,7 @@
struct sock *sk = sock->sk;
struct l2cap_chan *chan = l2cap_pi(sk)->chan;
struct l2cap_options opts;
- int len, err = 0;
+ int err = 0;
u32 opt;
BT_DBG("sk %p", sk);
@@ -754,11 +755,9 @@
opts.max_tx = chan->max_tx;
opts.txwin_size = chan->tx_win;
- len = min_t(unsigned int, sizeof(opts), optlen);
- if (copy_from_sockptr(&opts, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen);
+ if (err)
break;
- }
if (opts.txwin_size > L2CAP_DEFAULT_EXT_WINDOW) {
err = -EINVAL;
@@ -801,10 +800,9 @@
break;
case L2CAP_LM:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt & L2CAP_LM_FIPS) {
err = -EINVAL;
@@ -885,7 +883,7 @@
struct bt_security sec;
struct bt_power pwr;
struct l2cap_conn *conn;
- int len, err = 0;
+ int err = 0;
u32 opt;
u16 mtu;
u8 mode;
@@ -911,11 +909,9 @@
sec.level = BT_SECURITY_LOW;
- len = min_t(unsigned int, sizeof(sec), optlen);
- if (copy_from_sockptr(&sec, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen);
+ if (err)
break;
- }
if (sec.level < BT_SECURITY_LOW ||
sec.level > BT_SECURITY_FIPS) {
@@ -960,10 +956,9 @@
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt) {
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
@@ -975,10 +970,9 @@
break;
case BT_FLUSHABLE:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt > BT_FLUSHABLE_ON) {
err = -EINVAL;
@@ -1010,11 +1004,9 @@
pwr.force_active = BT_POWER_FORCE_ACTIVE_ON;
- len = min_t(unsigned int, sizeof(pwr), optlen);
- if (copy_from_sockptr(&pwr, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen);
+ if (err)
break;
- }
if (pwr.force_active)
set_bit(FLAG_FORCE_ACTIVE, &chan->flags);
@@ -1023,10 +1015,9 @@
break;
case BT_CHANNEL_POLICY:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
err = -EOPNOTSUPP;
break;
@@ -1055,10 +1046,9 @@
break;
}
- if (copy_from_sockptr(&mtu, optval, sizeof(u16))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen);
+ if (err)
break;
- }
if (chan->mode == L2CAP_MODE_EXT_FLOWCTL &&
sk->sk_state == BT_CONNECTED)
@@ -1086,10 +1076,9 @@
break;
}
- if (copy_from_sockptr(&mode, optval, sizeof(u8))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen);
+ if (err)
break;
- }
BT_DBG("mode %u", mode);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 32ed6e9..965f621e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2623,7 +2623,11 @@
goto failed;
}
- err = hci_cmd_sync_queue(hdev, add_uuid_sync, cmd, mgmt_class_complete);
+ /* MGMT_OP_ADD_UUID don't require adapter the UP/Running so use
+ * hci_cmd_sync_submit instead of hci_cmd_sync_queue.
+ */
+ err = hci_cmd_sync_submit(hdev, add_uuid_sync, cmd,
+ mgmt_class_complete);
if (err < 0) {
mgmt_pending_free(cmd);
goto failed;
@@ -2717,8 +2721,11 @@
goto unlock;
}
- err = hci_cmd_sync_queue(hdev, remove_uuid_sync, cmd,
- mgmt_class_complete);
+ /* MGMT_OP_REMOVE_UUID don't require adapter the UP/Running so use
+ * hci_cmd_sync_submit instead of hci_cmd_sync_queue.
+ */
+ err = hci_cmd_sync_submit(hdev, remove_uuid_sync, cmd,
+ mgmt_class_complete);
if (err < 0)
mgmt_pending_free(cmd);
@@ -2784,8 +2791,11 @@
goto unlock;
}
- err = hci_cmd_sync_queue(hdev, set_class_sync, cmd,
- mgmt_class_complete);
+ /* MGMT_OP_SET_DEV_CLASS don't require adapter the UP/Running so use
+ * hci_cmd_sync_submit instead of hci_cmd_sync_queue.
+ */
+ err = hci_cmd_sync_submit(hdev, set_class_sync, cmd,
+ mgmt_class_complete);
if (err < 0)
mgmt_pending_free(cmd);
@@ -5475,8 +5485,8 @@
goto unlock;
}
- err = hci_cmd_sync_queue(hdev, mgmt_remove_adv_monitor_sync, cmd,
- mgmt_remove_adv_monitor_complete);
+ err = hci_cmd_sync_submit(hdev, mgmt_remove_adv_monitor_sync, cmd,
+ mgmt_remove_adv_monitor_complete);
if (err) {
mgmt_pending_remove(cmd);
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index b54e8a5..29aa07e 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -629,7 +629,7 @@
switch (optname) {
case RFCOMM_LM:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
+ if (bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen)) {
err = -EFAULT;
break;
}
@@ -664,7 +664,6 @@
struct sock *sk = sock->sk;
struct bt_security sec;
int err = 0;
- size_t len;
u32 opt;
BT_DBG("sk %p", sk);
@@ -686,11 +685,9 @@
sec.level = BT_SECURITY_LOW;
- len = min_t(unsigned int, sizeof(sec), optlen);
- if (copy_from_sockptr(&sec, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen);
+ if (err)
break;
- }
if (sec.level > BT_SECURITY_HIGH) {
err = -EINVAL;
@@ -706,10 +703,9 @@
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 43daf96..5d03c54 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -824,7 +824,7 @@
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
- int len, err = 0;
+ int err = 0;
struct bt_voice voice;
u32 opt;
struct bt_codecs *codecs;
@@ -843,10 +843,9 @@
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
@@ -863,11 +862,10 @@
voice.setting = sco_pi(sk)->setting;
- len = min_t(unsigned int, sizeof(voice), optlen);
- if (copy_from_sockptr(&voice, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&voice, sizeof(voice), optval,
+ optlen);
+ if (err)
break;
- }
/* Explicitly check for these values */
if (voice.setting != BT_VOICE_TRANSPARENT &&
@@ -890,10 +888,9 @@
break;
case BT_PKT_STATUS:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags);
@@ -934,9 +931,9 @@
break;
}
- if (copy_from_sockptr(buffer, optval, optlen)) {
+ err = bt_copy_from_sockptr(buffer, optlen, optval, optlen);
+ if (err) {
hci_dev_put(hdev);
- err = -EFAULT;
break;
}
@@ -967,7 +964,8 @@
struct sock *sk = sock->sk;
struct sco_options opts;
struct sco_conninfo cinfo;
- int len, err = 0;
+ int err = 0;
+ size_t len;
BT_DBG("sk %p", sk);
@@ -989,7 +987,7 @@
BT_DBG("mtu %u", opts.mtu);
- len = min_t(unsigned int, len, sizeof(opts));
+ len = min(len, sizeof(opts));
if (copy_to_user(optval, (char *)&opts, len))
err = -EFAULT;
@@ -1007,7 +1005,7 @@
cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle;
memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3);
- len = min_t(unsigned int, len, sizeof(cinfo));
+ len = min(len, sizeof(cinfo));
if (copy_to_user(optval, (char *)&cinfo, len))
err = -EFAULT;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 7431f89..d7c35f5 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -266,7 +266,7 @@
if (skb->dev == p->dev && ether_addr_equal(src, addr))
return;
- skb = skb_copy(skb, GFP_ATOMIC);
+ skb = pskb_copy(skb, GFP_ATOMIC);
if (!skb) {
DEV_STATS_INC(dev, tx_dropped);
return;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index f21097e..ceaa5a8 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -30,7 +30,7 @@
return netif_receive_skb(skb);
}
-static int br_pass_frame_up(struct sk_buff *skb)
+static int br_pass_frame_up(struct sk_buff *skb, bool promisc)
{
struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(brdev);
@@ -65,6 +65,8 @@
br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb),
BR_MCAST_DIR_TX);
+ BR_INPUT_SKB_CB(skb)->promisc = promisc;
+
return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
dev_net(indev), NULL, skb, indev, NULL,
br_netif_receive_skb);
@@ -82,6 +84,7 @@
struct net_bridge_mcast *brmctx;
struct net_bridge_vlan *vlan;
struct net_bridge *br;
+ bool promisc;
u16 vid = 0;
u8 state;
@@ -137,7 +140,9 @@
if (p->flags & BR_LEARNING)
br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0);
- local_rcv = !!(br->dev->flags & IFF_PROMISC);
+ promisc = !!(br->dev->flags & IFF_PROMISC);
+ local_rcv = promisc;
+
if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
/* by definition the broadcast is also a multicast address */
if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
@@ -200,7 +205,7 @@
unsigned long now = jiffies;
if (test_bit(BR_FDB_LOCAL, &dst->flags))
- return br_pass_frame_up(skb);
+ return br_pass_frame_up(skb, false);
if (now != dst->used)
dst->used = now;
@@ -213,7 +218,7 @@
}
if (local_rcv)
- return br_pass_frame_up(skb);
+ return br_pass_frame_up(skb, promisc);
out:
return 0;
@@ -386,6 +391,8 @@
goto forward;
}
+ BR_INPUT_SKB_CB(skb)->promisc = false;
+
/* The else clause should be hit when nf_hook():
* - returns < 0 (drop/error)
* - returns = 0 (stolen/nf_queue)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 35e10c5..22e3562 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -600,11 +600,17 @@
struct sk_buff *skb,
const struct nf_hook_state *state)
{
+ bool promisc = BR_INPUT_SKB_CB(skb)->promisc;
struct nf_conntrack *nfct = skb_nfct(skb);
const struct nf_ct_hook *ct_hook;
struct nf_conn *ct;
int ret;
+ if (promisc) {
+ nf_reset_ct(skb);
+ return NF_ACCEPT;
+ }
+
if (!nfct || skb->pkt_type == PACKET_HOST)
return NF_ACCEPT;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 2cf4fc7..f17dbac 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -667,7 +667,7 @@
{
u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
- return br_info_notify(event, br, port, filter);
+ br_info_notify(event, br, port, filter);
}
/*
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 86ea5e66..d4bedc8 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -589,6 +589,7 @@
#endif
u8 proxyarp_replied:1;
u8 src_port_isolated:1;
+ u8 promisc:1;
#ifdef CONFIG_BRIDGE_VLAN_FILTERING
u8 vlan_filtered:1;
#endif
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 6f877e3..c3c51b9 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -294,18 +294,24 @@
static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
- enum ip_conntrack_info ctinfo;
+ bool promisc = BR_INPUT_SKB_CB(skb)->promisc;
+ struct nf_conntrack *nfct = skb_nfct(skb);
struct nf_conn *ct;
- if (skb->pkt_type == PACKET_HOST)
+ if (promisc) {
+ nf_reset_ct(skb);
+ return NF_ACCEPT;
+ }
+
+ if (!nfct || skb->pkt_type == PACKET_HOST)
return NF_ACCEPT;
/* nf_conntrack_confirm() cannot handle concurrent clones,
* this happens for broad/multicast frames with e.g. macvlan on top
* of the bridge device.
*/
- ct = nf_ct_get(skb, &ctinfo);
- if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct))
+ ct = container_of(nfct, struct nf_conn, ct_general);
+ if (nf_ct_is_confirmed(ct) || nf_ct_is_template(ct))
return NF_ACCEPT;
/* let inet prerouting call conntrack again */
diff --git a/net/core/dev.c b/net/core/dev.c
index 984ff8b9..331848e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3775,6 +3775,10 @@
return rc;
}
+ if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) {
+ kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP);
+ return NET_XMIT_DROP;
+ }
/*
* Heuristic to force contended enqueues to serialize on a
* separate lock before trying to get qdisc main lock.
@@ -3814,7 +3818,9 @@
qdisc_run_end(q);
rc = NET_XMIT_SUCCESS;
} else {
+ WRITE_ONCE(q->owner, smp_processor_id());
rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
+ WRITE_ONCE(q->owner, -1);
if (qdisc_run_begin(q)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
diff --git a/net/core/filter.c b/net/core/filter.c
index 8adf957..ae5254f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4360,10 +4360,12 @@
enum bpf_map_type map_type = ri->map_type;
void *fwd = ri->tgt_value;
u32 map_id = ri->map_id;
+ u32 flags = ri->flags;
struct bpf_map *map;
int err;
ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
+ ri->flags = 0;
ri->map_type = BPF_MAP_TYPE_UNSPEC;
if (unlikely(!xdpf)) {
@@ -4375,11 +4377,20 @@
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
- map = READ_ONCE(ri->map);
- if (unlikely(map)) {
+ if (unlikely(flags & BPF_F_BROADCAST)) {
+ map = READ_ONCE(ri->map);
+
+ /* The map pointer is cleared when the map is being torn
+ * down by bpf_clear_redirect_map()
+ */
+ if (unlikely(!map)) {
+ err = -ENOENT;
+ break;
+ }
+
WRITE_ONCE(ri->map, NULL);
err = dev_map_enqueue_multi(xdpf, dev, map,
- ri->flags & BPF_F_EXCLUDE_INGRESS);
+ flags & BPF_F_EXCLUDE_INGRESS);
} else {
err = dev_map_enqueue(fwd, xdpf, dev);
}
@@ -4442,9 +4453,9 @@
static int xdp_do_generic_redirect_map(struct net_device *dev,
struct sk_buff *skb,
struct xdp_buff *xdp,
- struct bpf_prog *xdp_prog,
- void *fwd,
- enum bpf_map_type map_type, u32 map_id)
+ struct bpf_prog *xdp_prog, void *fwd,
+ enum bpf_map_type map_type, u32 map_id,
+ u32 flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
struct bpf_map *map;
@@ -4454,11 +4465,20 @@
case BPF_MAP_TYPE_DEVMAP:
fallthrough;
case BPF_MAP_TYPE_DEVMAP_HASH:
- map = READ_ONCE(ri->map);
- if (unlikely(map)) {
+ if (unlikely(flags & BPF_F_BROADCAST)) {
+ map = READ_ONCE(ri->map);
+
+ /* The map pointer is cleared when the map is being torn
+ * down by bpf_clear_redirect_map()
+ */
+ if (unlikely(!map)) {
+ err = -ENOENT;
+ break;
+ }
+
WRITE_ONCE(ri->map, NULL);
err = dev_map_redirect_multi(dev, skb, xdp_prog, map,
- ri->flags & BPF_F_EXCLUDE_INGRESS);
+ flags & BPF_F_EXCLUDE_INGRESS);
} else {
err = dev_map_generic_redirect(fwd, skb, xdp_prog);
}
@@ -4495,9 +4515,11 @@
enum bpf_map_type map_type = ri->map_type;
void *fwd = ri->tgt_value;
u32 map_id = ri->map_id;
+ u32 flags = ri->flags;
int err;
ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */
+ ri->flags = 0;
ri->map_type = BPF_MAP_TYPE_UNSPEC;
if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) {
@@ -4517,7 +4539,7 @@
return 0;
}
- return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id);
+ return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags);
err:
_trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err);
return err;
diff --git a/net/core/gro.c b/net/core/gro.c
index 83f35d9..c790125 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -371,6 +371,7 @@
const skb_frag_t *frag0;
unsigned int headlen;
+ NAPI_GRO_CB(skb)->network_offset = 0;
NAPI_GRO_CB(skb)->data_offset = 0;
headlen = skb_headlen(skb);
NAPI_GRO_CB(skb)->frag0 = skb->data;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b991277..4096e67 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2123,11 +2123,17 @@
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
- int headerlen = skb_headroom(skb);
- unsigned int size = skb_end_offset(skb) + skb->data_len;
- struct sk_buff *n = __alloc_skb(size, gfp_mask,
- skb_alloc_rx_flag(skb), NUMA_NO_NODE);
+ struct sk_buff *n;
+ unsigned int size;
+ int headerlen;
+ if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST))
+ return NULL;
+
+ headerlen = skb_headroom(skb);
+ size = skb_end_offset(skb) + skb->data_len;
+ n = __alloc_skb(size, gfp_mask,
+ skb_alloc_rx_flag(skb), NUMA_NO_NODE);
if (!n)
return NULL;
@@ -2455,12 +2461,17 @@
/*
* Allocate the copy buffer
*/
- struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom,
- gfp_mask, skb_alloc_rx_flag(skb),
- NUMA_NO_NODE);
- int oldheadroom = skb_headroom(skb);
int head_copy_len, head_copy_off;
+ struct sk_buff *n;
+ int oldheadroom;
+ if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST))
+ return NULL;
+
+ oldheadroom = skb_headroom(skb);
+ n = __alloc_skb(newheadroom + skb->len + newtailroom,
+ gfp_mask, skb_alloc_rx_flag(skb),
+ NUMA_NO_NODE);
if (!n)
return NULL;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 4d75ef9..fd20aae 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1226,11 +1226,8 @@
rcu_read_lock();
psock = sk_psock(sk);
- if (psock) {
- read_lock_bh(&sk->sk_callback_lock);
+ if (psock)
sk_psock_data_ready(sk, psock);
- read_unlock_bh(&sk->sk_callback_lock);
- }
rcu_read_unlock();
}
}
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 2edc8b7..049c3ad 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -164,17 +164,7 @@
eth = (struct ethhdr *)skb->data;
skb_pull_inline(skb, ETH_HLEN);
- if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
- dev->dev_addr))) {
- if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
- if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
- skb->pkt_type = PACKET_BROADCAST;
- else
- skb->pkt_type = PACKET_MULTICAST;
- } else {
- skb->pkt_type = PACKET_OTHERHOST;
- }
- }
+ eth_skb_pkt_type(skb, dev);
/*
* Some variants of DSA tagging don't have an ethertype field
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 55bd729..fafb123 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1572,6 +1572,7 @@
/* The above will be needed by the transport layer if there is one
* immediately following this IP hdr.
*/
+ NAPI_GRO_CB(skb)->inner_network_offset = off;
/* Note : No need to call skb_gro_postpull_rcsum() here,
* as we already checked checksum over ipv4 header was 0
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 4874135..c484b1c0 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1050,6 +1050,11 @@
e++;
}
}
+
+ /* Don't let NLM_DONE coalesce into a message, even if it could.
+ * Some user space expects NLM_DONE in a separate recv().
+ */
+ err = skb->len;
out:
cb->args[1] = e;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e63a3bf..437e782 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -92,6 +92,7 @@
#include <net/inet_common.h>
#include <net/ip_fib.h>
#include <net/l3mdev.h>
+#include <net/addrconf.h>
/*
* Build xmit assembly blocks
@@ -1032,6 +1033,8 @@
struct icmp_ext_hdr *ext_hdr, _ext_hdr;
struct icmp_ext_echo_iio *iio, _iio;
struct net *net = dev_net(skb->dev);
+ struct inet6_dev *in6_dev;
+ struct in_device *in_dev;
struct net_device *dev;
char buff[IFNAMSIZ];
u16 ident_len;
@@ -1115,10 +1118,15 @@
/* Fill bits in reply message */
if (dev->flags & IFF_UP)
status |= ICMP_EXT_ECHOREPLY_ACTIVE;
- if (__in_dev_get_rcu(dev) && __in_dev_get_rcu(dev)->ifa_list)
+
+ in_dev = __in_dev_get_rcu(dev);
+ if (in_dev && rcu_access_pointer(in_dev->ifa_list))
status |= ICMP_EXT_ECHOREPLY_IPV4;
- if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list))
+
+ in6_dev = __in6_dev_get(dev);
+ if (in6_dev && !list_empty(&in6_dev->addr_list))
status |= ICMP_EXT_ECHOREPLY_IPV6;
+
dev_put(dev);
icmphdr->un.echo.sequence |= htons(status);
return true;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1fe7949..39229fd 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1473,7 +1473,7 @@
* by icmp_hdr(skb)->type.
*/
if (sk->sk_type == SOCK_RAW &&
- !inet_test_bit(HDRINCL, sk))
+ !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH))
icmp_type = fl4->fl4_icmp_type;
else
icmp_type = icmp_hdr(skb)->type;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index b150c99..14365b2 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -966,6 +966,8 @@
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1266,6 +1268,8 @@
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 4876707..fe89a05 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1118,6 +1118,8 @@
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1504,6 +1506,8 @@
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index dcb11f2..4cb4340 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -612,6 +612,9 @@
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
+ fl4.fl4_icmp_type = 0;
+ fl4.fl4_icmp_code = 0;
+
if (!hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c8f76f5..b814fda 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -926,13 +926,11 @@
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->n_redirects;
-#ifdef CONFIG_IP_ROUTE_VERBOSE
- if (log_martians &&
+ if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians &&
peer->n_redirects == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, inet_iif(skb),
&ip_hdr(skb)->daddr, &gw);
-#endif
}
out_put_peer:
inet_putpeer(peer);
@@ -2168,6 +2166,9 @@
int err = -EINVAL;
u32 tag = 0;
+ if (!in_dev)
+ return -EINVAL;
+
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
goto martian_source;
diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
index 3afeeb6..781b67a 100644
--- a/net/ipv4/tcp_ao.c
+++ b/net/ipv4/tcp_ao.c
@@ -1068,6 +1068,7 @@
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_ao_info *ao_info;
+ struct hlist_node *next;
union tcp_ao_addr *addr;
struct tcp_ao_key *key;
int family, l3index;
@@ -1090,7 +1091,7 @@
l3index = l3mdev_master_ifindex_by_index(sock_net(sk),
sk->sk_bound_dev_if);
- hlist_for_each_entry_rcu(key, &ao_info->head, node) {
+ hlist_for_each_entry_safe(key, next, &ao_info->head, node) {
if (!tcp_ao_key_cmp(key, l3index, addr, key->prefixlen, family, -1, -1))
continue;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c02bf01..b32cf2e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -532,7 +532,8 @@
struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
- const struct iphdr *iph = ip_hdr(skb);
+ const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+ const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
struct net *net = dev_net(skb->dev);
int iif, sdif;
@@ -1123,16 +1124,17 @@
if (msg->msg_controllen) {
err = udp_cmsg_send(sk, msg, &ipc.gso_size);
- if (err > 0)
+ if (err > 0) {
err = ip_cmsg_send(sk, msg, &ipc,
sk->sk_family == AF_INET6);
+ connected = 0;
+ }
if (unlikely(err < 0)) {
kfree(ipc.opt);
return err;
}
if (ipc.opt)
free = 1;
- connected = 0;
}
if (!ipc.opt) {
struct ip_options_rcu *inet_opt;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 3498dd1..8721fe5 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -471,6 +471,7 @@
struct sk_buff *p;
unsigned int ulen;
int ret = 0;
+ int flush;
/* requires non zero csum, for symmetry with GSO */
if (!uh->check) {
@@ -504,13 +505,22 @@
return p;
}
+ flush = NAPI_GRO_CB(p)->flush;
+
+ if (NAPI_GRO_CB(p)->flush_id != 1 ||
+ NAPI_GRO_CB(p)->count != 1 ||
+ !NAPI_GRO_CB(p)->is_atomic)
+ flush |= NAPI_GRO_CB(p)->flush_id;
+ else
+ NAPI_GRO_CB(p)->is_atomic = false;
+
/* Terminate the flow on len mismatch or if it grow "too much".
* Under small packet flood GRO count could elsewhere grow a lot
* leading to excessive truesize values.
* On len mismatch merge the first packet shorter than gso_size,
* otherwise complete the GRO packet.
*/
- if (ulen > ntohs(uh2->len)) {
+ if (ulen > ntohs(uh2->len) || flush) {
pp = p;
} else {
if (NAPI_GRO_CB(skb)->is_flist) {
@@ -718,7 +728,8 @@
INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
{
- const struct iphdr *iph = ip_hdr(skb);
+ const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+ const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
/* do fraglist only if there is no outer UDP encap (or we already processed it) */
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 92db9b4..779aa6e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2091,9 +2091,10 @@
if (ipv6_addr_equal(&ifp->addr, addr)) {
if (!dev || ifp->idev->dev == dev ||
!(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) {
- result = ifp;
- in6_ifa_hold(ifp);
- break;
+ if (in6_ifa_hold_safe(ifp)) {
+ result = ifp;
+ break;
+ }
}
}
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 7209419..c1f6235 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1385,7 +1385,10 @@
struct nl_info *info, struct netlink_ext_ack *extack)
{
struct fib6_table *table = rt->fib6_table;
- struct fib6_node *fn, *pn = NULL;
+ struct fib6_node *fn;
+#ifdef CONFIG_IPV6_SUBTREES
+ struct fib6_node *pn = NULL;
+#endif
int err = -ENOMEM;
int allow_create = 1;
int replace_required = 0;
@@ -1409,9 +1412,9 @@
goto out;
}
+#ifdef CONFIG_IPV6_SUBTREES
pn = fn;
-#ifdef CONFIG_IPV6_SUBTREES
if (rt->fib6_src.plen) {
struct fib6_node *sn;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index b41e35a..c8b909a 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -237,6 +237,7 @@
goto out;
skb_set_network_header(skb, off);
+ NAPI_GRO_CB(skb)->inner_network_offset = off;
flush += ntohs(iph->payload_len) != skb->len - hlen;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 636b360..131f7bb 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1135,6 +1135,8 @@
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1513,6 +1515,8 @@
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 8b1dd7f..8f7aa8b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -272,7 +272,8 @@
struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
- const struct ipv6hdr *iph = ipv6_hdr(skb);
+ const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+ const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset);
struct net *net = dev_net(skb->dev);
int iif, sdif;
@@ -1474,9 +1475,11 @@
ipc6.opt = opt;
err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
- if (err > 0)
+ if (err > 0) {
err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6,
&ipc6);
+ connected = false;
+ }
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
@@ -1488,7 +1491,6 @@
}
if (!(opt->opt_nflen|opt->opt_flen))
opt = NULL;
- connected = false;
}
if (!opt) {
opt = txopt_get(np);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index bbd347d..b41152d 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -164,7 +164,8 @@
INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff)
{
- const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+ const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset);
struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
/* do fraglist only if there is no outer UDP encap (or we already processed it) */
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 39e487c..8ba00ad 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -127,6 +127,9 @@
/* checksums verified by L2TP */
skb->ip_summed = CHECKSUM_NONE;
+ /* drop outer flow-hash */
+ skb_clear_hash(skb);
+
skb_dst_drop(skb);
nf_reset_ct(skb);
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 80e4b97..ccacaed 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -797,6 +797,7 @@
struct ieee80211_local *local = sdata->local;
struct ieee80211_chanctx_conf *conf;
struct ieee80211_chanctx *curr_ctx = NULL;
+ bool new_idle;
int ret = 0;
if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_NAN))
@@ -829,8 +830,6 @@
out:
rcu_assign_pointer(link->conf->chanctx_conf, conf);
- sdata->vif.cfg.idle = !conf;
-
if (curr_ctx && ieee80211_chanctx_num_assigned(local, curr_ctx) > 0) {
ieee80211_recalc_chanctx_chantype(local, curr_ctx);
ieee80211_recalc_smps_chanctx(local, curr_ctx);
@@ -843,9 +842,27 @@
ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL);
}
- if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
- sdata->vif.type != NL80211_IFTYPE_MONITOR)
- ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_IDLE);
+ if (conf) {
+ new_idle = false;
+ } else {
+ struct ieee80211_link_data *tmp;
+
+ new_idle = true;
+ for_each_sdata_link(local, tmp) {
+ if (rcu_access_pointer(tmp->conf->chanctx_conf)) {
+ new_idle = false;
+ break;
+ }
+ }
+ }
+
+ if (new_idle != sdata->vif.cfg.idle) {
+ sdata->vif.cfg.idle = new_idle;
+
+ if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
+ sdata->vif.type != NL80211_IFTYPE_MONITOR)
+ ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_IDLE);
+ }
ieee80211_check_fast_xmit_iface(sdata);
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 32475da..cbc9b5e 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -747,6 +747,9 @@
struct sk_buff *skb, u32 ctrl_flags)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
+ struct ieee80211_mesh_fast_tx_key key = {
+ .type = MESH_FAST_TX_TYPE_LOCAL
+ };
struct ieee80211_mesh_fast_tx *entry;
struct ieee80211s_hdr *meshhdr;
u8 sa[ETH_ALEN] __aligned(2);
@@ -782,7 +785,10 @@
return false;
}
- entry = mesh_fast_tx_get(sdata, skb->data);
+ ether_addr_copy(key.addr, skb->data);
+ if (!ether_addr_equal(skb->data + ETH_ALEN, sdata->vif.addr))
+ key.type = MESH_FAST_TX_TYPE_PROXIED;
+ entry = mesh_fast_tx_get(sdata, &key);
if (!entry)
return false;
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index d913ce7..3f9664e 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -135,9 +135,38 @@
#define MESH_FAST_TX_CACHE_TIMEOUT 8000 /* msecs */
/**
+ * enum ieee80211_mesh_fast_tx_type - cached mesh fast tx entry type
+ *
+ * @MESH_FAST_TX_TYPE_LOCAL: tx from the local vif address as SA
+ * @MESH_FAST_TX_TYPE_PROXIED: local tx with a different SA (e.g. bridged)
+ * @MESH_FAST_TX_TYPE_FORWARDED: forwarded from a different mesh point
+ * @NUM_MESH_FAST_TX_TYPE: number of entry types
+ */
+enum ieee80211_mesh_fast_tx_type {
+ MESH_FAST_TX_TYPE_LOCAL,
+ MESH_FAST_TX_TYPE_PROXIED,
+ MESH_FAST_TX_TYPE_FORWARDED,
+
+ /* must be last */
+ NUM_MESH_FAST_TX_TYPE
+};
+
+
+/**
+ * struct ieee80211_mesh_fast_tx_key - cached mesh fast tx entry key
+ *
+ * @addr: The Ethernet DA for this entry
+ * @type: cache entry type
+ */
+struct ieee80211_mesh_fast_tx_key {
+ u8 addr[ETH_ALEN] __aligned(2);
+ u16 type;
+};
+
+/**
* struct ieee80211_mesh_fast_tx - cached mesh fast tx entry
* @rhash: rhashtable pointer
- * @addr_key: The Ethernet DA which is the key for this entry
+ * @key: the lookup key for this cache entry
* @fast_tx: base fast_tx data
* @hdr: cached mesh and rfc1042 headers
* @hdrlen: length of mesh + rfc1042
@@ -148,7 +177,7 @@
*/
struct ieee80211_mesh_fast_tx {
struct rhash_head rhash;
- u8 addr_key[ETH_ALEN] __aligned(2);
+ struct ieee80211_mesh_fast_tx_key key;
struct ieee80211_fast_tx fast_tx;
u8 hdr[sizeof(struct ieee80211s_hdr) + sizeof(rfc1042_header)];
@@ -334,7 +363,8 @@
bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt);
struct ieee80211_mesh_fast_tx *
-mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, const u8 *addr);
+mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_mesh_fast_tx_key *key);
bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata,
struct sk_buff *skb, u32 ctrl_flags);
void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 91b55d6..a6b6216 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -37,8 +37,8 @@
static const struct rhashtable_params fast_tx_rht_params = {
.nelem_hint = 10,
.automatic_shrinking = true,
- .key_len = ETH_ALEN,
- .key_offset = offsetof(struct ieee80211_mesh_fast_tx, addr_key),
+ .key_len = sizeof_field(struct ieee80211_mesh_fast_tx, key),
+ .key_offset = offsetof(struct ieee80211_mesh_fast_tx, key),
.head_offset = offsetof(struct ieee80211_mesh_fast_tx, rhash),
.hashfn = mesh_table_hash,
};
@@ -431,20 +431,21 @@
}
struct ieee80211_mesh_fast_tx *
-mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, const u8 *addr)
+mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata,
+ struct ieee80211_mesh_fast_tx_key *key)
{
struct ieee80211_mesh_fast_tx *entry;
struct mesh_tx_cache *cache;
cache = &sdata->u.mesh.tx_cache;
- entry = rhashtable_lookup(&cache->rht, addr, fast_tx_rht_params);
+ entry = rhashtable_lookup(&cache->rht, key, fast_tx_rht_params);
if (!entry)
return NULL;
if (!(entry->mpath->flags & MESH_PATH_ACTIVE) ||
mpath_expired(entry->mpath)) {
spin_lock_bh(&cache->walk_lock);
- entry = rhashtable_lookup(&cache->rht, addr, fast_tx_rht_params);
+ entry = rhashtable_lookup(&cache->rht, key, fast_tx_rht_params);
if (entry)
mesh_fast_tx_entry_free(cache, entry);
spin_unlock_bh(&cache->walk_lock);
@@ -489,18 +490,24 @@
if (!sta)
return;
+ build.key.type = MESH_FAST_TX_TYPE_LOCAL;
if ((meshhdr->flags & MESH_FLAGS_AE) == MESH_FLAGS_AE_A5_A6) {
/* This is required to keep the mppath alive */
mppath = mpp_path_lookup(sdata, meshhdr->eaddr1);
if (!mppath)
return;
build.mppath = mppath;
+ if (!ether_addr_equal(meshhdr->eaddr2, sdata->vif.addr))
+ build.key.type = MESH_FAST_TX_TYPE_PROXIED;
} else if (ieee80211_has_a4(hdr->frame_control)) {
mppath = mpath;
} else {
return;
}
+ if (!ether_addr_equal(hdr->addr4, sdata->vif.addr))
+ build.key.type = MESH_FAST_TX_TYPE_FORWARDED;
+
/* rate limit, in case fast xmit can't be enabled */
if (mppath->fast_tx_check == jiffies)
return;
@@ -547,7 +554,7 @@
}
}
- memcpy(build.addr_key, mppath->dst, ETH_ALEN);
+ memcpy(build.key.addr, mppath->dst, ETH_ALEN);
build.timestamp = jiffies;
build.fast_tx.band = info->band;
build.fast_tx.da_offs = offsetof(struct ieee80211_hdr, addr3);
@@ -646,12 +653,18 @@
const u8 *addr)
{
struct mesh_tx_cache *cache = &sdata->u.mesh.tx_cache;
+ struct ieee80211_mesh_fast_tx_key key = {};
struct ieee80211_mesh_fast_tx *entry;
+ int i;
+ ether_addr_copy(key.addr, addr);
spin_lock_bh(&cache->walk_lock);
- entry = rhashtable_lookup_fast(&cache->rht, addr, fast_tx_rht_params);
- if (entry)
- mesh_fast_tx_entry_free(cache, entry);
+ for (i = 0; i < NUM_MESH_FAST_TX_TYPE; i++) {
+ key.type = i;
+ entry = rhashtable_lookup_fast(&cache->rht, &key, fast_tx_rht_params);
+ if (entry)
+ mesh_fast_tx_entry_free(cache, entry);
+ }
spin_unlock_bh(&cache->walk_lock);
}
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 96b7000..3bbb216 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -616,7 +616,6 @@
.from_ap = true,
.start = ies->data,
.len = ies->len,
- .mode = conn->mode,
};
struct ieee802_11_elems *elems;
struct ieee80211_supported_band *sband;
@@ -625,6 +624,7 @@
int ret;
again:
+ parse_params.mode = conn->mode;
elems = ieee802_11_parse_elems_full(&parse_params);
if (!elems)
return ERR_PTR(-ENOMEM);
@@ -632,15 +632,21 @@
ap_mode = ieee80211_determine_ap_chan(sdata, channel, bss->vht_cap_info,
elems, false, conn, &ap_chandef);
- mlme_link_id_dbg(sdata, link_id, "determined AP %pM to be %s\n",
- cbss->bssid, ieee80211_conn_mode_str(ap_mode));
-
/* this should be impossible since parsing depends on our mode */
if (WARN_ON(ap_mode > conn->mode)) {
ret = -EINVAL;
goto free;
}
+ if (conn->mode != ap_mode) {
+ conn->mode = ap_mode;
+ kfree(elems);
+ goto again;
+ }
+
+ mlme_link_id_dbg(sdata, link_id, "determined AP %pM to be %s\n",
+ cbss->bssid, ieee80211_conn_mode_str(ap_mode));
+
sband = sdata->local->hw.wiphy->bands[channel->band];
switch (channel->band) {
@@ -691,7 +697,6 @@
break;
}
- conn->mode = ap_mode;
chanreq->oper = ap_chandef;
/* wider-bandwidth OFDMA is only done in EHT */
@@ -753,8 +758,10 @@
}
/* the mode can only decrease, so this must terminate */
- if (ap_mode != conn->mode)
+ if (ap_mode != conn->mode) {
+ kfree(elems);
goto again;
+ }
mlme_link_id_dbg(sdata, link_id,
"connecting with %s mode, max bandwidth %d MHz\n",
@@ -5812,7 +5819,7 @@
*/
if (control &
IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT)
- link_removal_timeout[link_id] = le16_to_cpu(*(__le16 *)pos);
+ link_removal_timeout[link_id] = get_unaligned_le16(pos);
}
removed_links &= sdata->vif.valid_links;
@@ -5837,8 +5844,11 @@
continue;
}
- link_delay = link_conf->beacon_int *
- link_removal_timeout[link_id];
+ if (link_removal_timeout[link_id] < 1)
+ link_delay = 0;
+ else
+ link_delay = link_conf->beacon_int *
+ (link_removal_timeout[link_id] - 1);
if (!delay)
delay = link_delay;
@@ -6193,7 +6203,8 @@
link->u.mgd.dtim_period = elems->dtim_period;
link->u.mgd.have_beacon = true;
ifmgd->assoc_data->need_beacon = false;
- if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY)) {
+ if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY) &&
+ !ieee80211_is_s1g_beacon(hdr->frame_control)) {
link->conf->sync_tsf =
le64_to_cpu(mgmt->u.beacon.timestamp);
link->conf->sync_device_ts =
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 23404b2..4dc1def 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -877,6 +877,7 @@
struct ieee80211_sub_if_data *sdata;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
struct ieee80211_supported_band *sband;
+ u32 mask = ~0;
rate_control_fill_sta_table(sta, info, dest, max_rates);
@@ -889,9 +890,12 @@
if (ieee80211_is_tx_data(skb))
rate_control_apply_mask(sdata, sta, sband, dest, max_rates);
+ if (!(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX))
+ mask = sdata->rc_rateidx_mask[info->band];
+
if (dest[0].idx < 0)
__rate_control_send_low(&sdata->local->hw, sband, sta, info,
- sdata->rc_rateidx_mask[info->band]);
+ mask);
if (sta)
rate_fixup_ratelist(vif, sband, info, dest, max_rates);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index c1f8501..6e24864 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2763,7 +2763,10 @@
struct sk_buff *skb, int hdrlen)
{
struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh;
- struct ieee80211_mesh_fast_tx *entry = NULL;
+ struct ieee80211_mesh_fast_tx_key key = {
+ .type = MESH_FAST_TX_TYPE_FORWARDED
+ };
+ struct ieee80211_mesh_fast_tx *entry;
struct ieee80211s_hdr *mesh_hdr;
struct tid_ampdu_tx *tid_tx;
struct sta_info *sta;
@@ -2772,9 +2775,13 @@
mesh_hdr = (struct ieee80211s_hdr *)(skb->data + sizeof(eth));
if ((mesh_hdr->flags & MESH_FLAGS_AE) == MESH_FLAGS_AE_A5_A6)
- entry = mesh_fast_tx_get(sdata, mesh_hdr->eaddr1);
+ ether_addr_copy(key.addr, mesh_hdr->eaddr1);
else if (!(mesh_hdr->flags & MESH_FLAGS_AE))
- entry = mesh_fast_tx_get(sdata, skb->data);
+ ether_addr_copy(key.addr, skb->data);
+ else
+ return false;
+
+ entry = mesh_fast_tx_get(sdata, &key);
if (!entry)
return false;
@@ -3780,6 +3787,10 @@
}
break;
case WLAN_CATEGORY_PROTECTED_EHT:
+ if (len < offsetofend(typeof(*mgmt),
+ u.action.u.ttlm_req.action_code))
+ break;
+
switch (mgmt->u.action.u.ttlm_req.action_code) {
case WLAN_PROTECTED_EHT_ACTION_TTLM_REQ:
if (sdata->vif.type != NL80211_IFTYPE_STATION)
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 0429e59..73850312 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -648,6 +648,7 @@
cpu_to_le16(IEEE80211_SN_TO_SEQ(sn));
}
IEEE80211_SKB_CB(skb)->flags |= tx_flags;
+ IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_SCAN_TX;
ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band);
}
}
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 6bf223e..cfd0a62 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -698,11 +698,16 @@
txrc.bss_conf = &tx->sdata->vif.bss_conf;
txrc.skb = tx->skb;
txrc.reported_rate.idx = -1;
- txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band];
- if (tx->sdata->rc_has_mcs_mask[info->band])
- txrc.rate_idx_mcs_mask =
- tx->sdata->rc_rateidx_mcs_mask[info->band];
+ if (unlikely(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX)) {
+ txrc.rate_idx_mask = ~0;
+ } else {
+ txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band];
+
+ if (tx->sdata->rc_has_mcs_mask[info->band])
+ txrc.rate_idx_mcs_mask =
+ tx->sdata->rc_rateidx_mcs_mask[info->band];
+ }
txrc.bss = (tx->sdata->vif.type == NL80211_IFTYPE_AP ||
tx->sdata->vif.type == NL80211_IFTYPE_MESH_POINT ||
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 7e74b81..965eb69 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3723,6 +3723,9 @@
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT);
mptcp_subflow_early_fallback(msk, subflow);
}
+
+ WRITE_ONCE(msk->write_seq, subflow->idsn);
+ WRITE_ONCE(msk->snd_nxt, subflow->idsn);
if (likely(!__mptcp_check_fallback(msk)))
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE);
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index a0921ad..1e689c7 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -126,7 +126,8 @@
if (sctph->source != cp->vport || payload_csum ||
skb->ip_summed == CHECKSUM_PARTIAL) {
sctph->source = cp->vport;
- sctp_nat_csum(skb, sctph, sctphoff);
+ if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
+ sctp_nat_csum(skb, sctph, sctphoff);
} else {
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
@@ -174,7 +175,8 @@
(skb->ip_summed == CHECKSUM_PARTIAL &&
!(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) {
sctph->dest = cp->dport;
- sctp_nat_csum(skb, sctph, sctphoff);
+ if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
+ sctp_nat_csum(skb, sctph, sctphoff);
} else if (skb->ip_summed != CHECKSUM_PARTIAL) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 9505f9d..6eef156 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -21,7 +21,8 @@
proto = veth->h_vlan_encapsulated_proto;
break;
case htons(ETH_P_PPP_SES):
- proto = nf_flow_pppoe_proto(skb);
+ if (!nf_flow_pppoe_proto(skb, &proto))
+ return NF_ACCEPT;
break;
default:
proto = skb->protocol;
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index e45fade..5383bed 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -157,7 +157,7 @@
tuple->encap[i].proto = skb->protocol;
break;
case htons(ETH_P_PPP_SES):
- phdr = (struct pppoe_hdr *)skb_mac_header(skb);
+ phdr = (struct pppoe_hdr *)skb_network_header(skb);
tuple->encap[i].id = ntohs(phdr->sid);
tuple->encap[i].proto = skb->protocol;
break;
@@ -273,10 +273,11 @@
return NF_STOLEN;
}
-static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto,
+static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
u32 *offset)
{
struct vlan_ethhdr *veth;
+ __be16 inner_proto;
switch (skb->protocol) {
case htons(ETH_P_8021Q):
@@ -287,7 +288,8 @@
}
break;
case htons(ETH_P_PPP_SES):
- if (nf_flow_pppoe_proto(skb) == proto) {
+ if (nf_flow_pppoe_proto(skb, &inner_proto) &&
+ inner_proto == proto) {
*offset += PPPOE_SES_HLEN;
return true;
}
@@ -316,7 +318,7 @@
skb_reset_network_header(skb);
break;
case htons(ETH_P_PPP_SES):
- skb->protocol = nf_flow_pppoe_proto(skb);
+ skb->protocol = __nf_flow_pppoe_proto(skb);
skb_pull(skb, PPPOE_SES_HLEN);
skb_reset_network_header(skb);
break;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d89d7794..1670742 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -594,6 +594,12 @@
const struct nft_set_iter *iter,
struct nft_elem_priv *elem_priv)
{
+ struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+
+ if (!nft_set_elem_active(ext, iter->genmask))
+ return 0;
+
+ nft_set_elem_change_active(ctx->net, set, ext);
nft_setelem_data_deactivate(ctx->net, set, elem_priv);
return 0;
@@ -617,6 +623,7 @@
if (!nft_set_elem_active(ext, genmask))
continue;
+ nft_set_elem_change_active(ctx->net, set, ext);
nft_setelem_data_deactivate(ctx->net, set, catchall->elem);
break;
}
@@ -626,6 +633,7 @@
{
struct nft_set_iter iter = {
.genmask = nft_genmask_next(ctx->net),
+ .type = NFT_ITER_UPDATE,
.fn = nft_mapelem_deactivate,
};
@@ -3060,7 +3068,7 @@
{
const struct nft_expr_type *type, *candidate = NULL;
- list_for_each_entry(type, &nf_tables_expressions, list) {
+ list_for_each_entry_rcu(type, &nf_tables_expressions, list) {
if (!nla_strcmp(nla, type->name)) {
if (!type->family && !candidate)
candidate = type;
@@ -3092,9 +3100,13 @@
if (nla == NULL)
return ERR_PTR(-EINVAL);
+ rcu_read_lock();
type = __nft_expr_type_get(family, nla);
- if (type != NULL && try_module_get(type->owner))
+ if (type != NULL && try_module_get(type->owner)) {
+ rcu_read_unlock();
return type;
+ }
+ rcu_read_unlock();
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
@@ -3875,6 +3887,9 @@
const struct nft_data *data;
int err;
+ if (!nft_set_elem_active(ext, iter->genmask))
+ return 0;
+
if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
*nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
return 0;
@@ -3898,17 +3913,20 @@
int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set)
{
- u8 genmask = nft_genmask_next(ctx->net);
+ struct nft_set_iter dummy_iter = {
+ .genmask = nft_genmask_next(ctx->net),
+ };
struct nft_set_elem_catchall *catchall;
+
struct nft_set_ext *ext;
int ret = 0;
list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
ext = nft_set_elem_ext(set, catchall->elem);
- if (!nft_set_elem_active(ext, genmask))
+ if (!nft_set_elem_active(ext, dummy_iter.genmask))
continue;
- ret = nft_setelem_validate(ctx, set, NULL, catchall->elem);
+ ret = nft_setelem_validate(ctx, set, &dummy_iter, catchall->elem);
if (ret < 0)
return ret;
}
@@ -5397,6 +5415,11 @@
const struct nft_set_iter *iter,
struct nft_elem_priv *elem_priv)
{
+ const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+
+ if (!nft_set_elem_active(ext, iter->genmask))
+ return 0;
+
return nft_setelem_data_validate(ctx, set, elem_priv);
}
@@ -5441,6 +5464,7 @@
}
iter.genmask = nft_genmask_next(ctx->net);
+ iter.type = NFT_ITER_UPDATE;
iter.skip = 0;
iter.count = 0;
iter.err = 0;
@@ -5488,6 +5512,13 @@
const struct nft_set_iter *iter,
struct nft_elem_priv *elem_priv)
{
+ struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+
+ /* called from abort path, reverse check to undo changes. */
+ if (nft_set_elem_active(ext, iter->genmask))
+ return 0;
+
+ nft_clear(ctx->net, ext);
nft_setelem_data_activate(ctx->net, set, elem_priv);
return 0;
@@ -5505,6 +5536,7 @@
if (!nft_set_elem_active(ext, genmask))
continue;
+ nft_clear(ctx->net, ext);
nft_setelem_data_activate(ctx->net, set, catchall->elem);
break;
}
@@ -5514,6 +5546,7 @@
{
struct nft_set_iter iter = {
.genmask = nft_genmask_next(ctx->net),
+ .type = NFT_ITER_UPDATE,
.fn = nft_mapelem_activate,
};
@@ -5778,6 +5811,9 @@
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
struct nft_set_dump_args *args;
+ if (!nft_set_elem_active(ext, iter->genmask))
+ return 0;
+
if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext))
return 0;
@@ -5888,6 +5924,7 @@
args.skb = skb;
args.reset = dump_ctx->reset;
args.iter.genmask = nft_genmask_cur(net);
+ args.iter.type = NFT_ITER_READ;
args.iter.skip = cb->args[0];
args.iter.count = 0;
args.iter.err = 0;
@@ -6627,7 +6664,7 @@
struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
if (nft_setelem_is_catchall(set, elem_priv)) {
- nft_set_elem_change_active(net, set, ext);
+ nft_clear(net, ext);
} else {
set->ops->activate(net, set, elem_priv);
}
@@ -7186,6 +7223,16 @@
}
}
+static int nft_setelem_active_next(const struct net *net,
+ const struct nft_set *set,
+ struct nft_elem_priv *elem_priv)
+{
+ const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+ u8 genmask = nft_genmask_next(net);
+
+ return nft_set_elem_active(ext, genmask);
+}
+
static void nft_setelem_data_activate(const struct net *net,
const struct nft_set *set,
struct nft_elem_priv *elem_priv)
@@ -7309,8 +7356,12 @@
const struct nft_set_iter *iter,
struct nft_elem_priv *elem_priv)
{
+ const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
struct nft_trans *trans;
+ if (!nft_set_elem_active(ext, iter->genmask))
+ return 0;
+
trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM,
sizeof(struct nft_trans_elem), GFP_ATOMIC);
if (!trans)
@@ -7372,6 +7423,7 @@
{
struct nft_set_iter iter = {
.genmask = genmask,
+ .type = NFT_ITER_UPDATE,
.fn = nft_setelem_flush,
};
@@ -7607,7 +7659,7 @@
{
const struct nft_object_type *type;
- list_for_each_entry(type, &nf_tables_objects, list) {
+ list_for_each_entry_rcu(type, &nf_tables_objects, list) {
if (type->family != NFPROTO_UNSPEC &&
type->family != family)
continue;
@@ -7623,9 +7675,13 @@
{
const struct nft_object_type *type;
+ rcu_read_lock();
type = __nft_obj_type_get(objtype, family);
- if (type != NULL && try_module_get(type->owner))
+ if (type != NULL && try_module_get(type->owner)) {
+ rcu_read_unlock();
return type;
+ }
+ rcu_read_unlock();
lockdep_nfnl_nft_mutex_not_held();
#ifdef CONFIG_MODULES
@@ -10598,8 +10654,10 @@
case NFT_MSG_DESTROYSETELEM:
te = (struct nft_trans_elem *)trans->data;
- nft_setelem_data_activate(net, te->set, te->elem_priv);
- nft_setelem_activate(net, te->set, te->elem_priv);
+ if (!nft_setelem_active_next(net, te->set, te->elem_priv)) {
+ nft_setelem_data_activate(net, te->set, te->elem_priv);
+ nft_setelem_activate(net, te->set, te->elem_priv);
+ }
if (!nft_setelem_is_catchall(te->set, te->elem_priv))
te->set->ndeact--;
@@ -10787,6 +10845,9 @@
{
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv);
+ if (!nft_set_elem_active(ext, iter->genmask))
+ return 0;
+
if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
*nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
return 0;
@@ -10871,6 +10932,7 @@
continue;
iter.genmask = nft_genmask_next(ctx->net);
+ iter.type = NFT_ITER_UPDATE;
iter.skip = 0;
iter.count = 0;
iter.err = 0;
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 274b6f7..d170758 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -338,7 +338,9 @@
return;
if (n > 1) {
- nf_unregister_net_hook(ctx->net, &found->ops);
+ if (!(ctx->chain->table->flags & NFT_TABLE_F_DORMANT))
+ nf_unregister_net_hook(ctx->net, &found->ops);
+
list_del_rcu(&found->list);
kfree_rcu(found, rcu);
return;
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index a0055f5..b314ca7 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -216,6 +216,7 @@
return 0;
iter.genmask = nft_genmask_next(ctx->net);
+ iter.type = NFT_ITER_UPDATE;
iter.skip = 0;
iter.count = 0;
iter.err = 0;
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index 32df7a1..1caa046 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -172,7 +172,7 @@
nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off);
/* Enter 11 state. */
priv->bitmap[idx] |= (genmask << off);
- nft_set_elem_change_active(net, set, &be->ext);
+ nft_clear(net, &be->ext);
}
static void nft_bitmap_flush(const struct net *net,
@@ -222,8 +222,6 @@
list_for_each_entry_rcu(be, &priv->list, head) {
if (iter->count < iter->skip)
goto cont;
- if (!nft_set_elem_active(&be->ext, iter->genmask))
- goto cont;
iter->err = iter->fn(ctx, set, iter, &be->priv);
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 6968a3b..daa56dd 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -199,7 +199,7 @@
{
struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv);
- nft_set_elem_change_active(net, set, &he->ext);
+ nft_clear(net, &he->ext);
}
static void nft_rhash_flush(const struct net *net,
@@ -286,8 +286,6 @@
if (iter->count < iter->skip)
goto cont;
- if (!nft_set_elem_active(&he->ext, iter->genmask))
- goto cont;
iter->err = iter->fn(ctx, set, iter, &he->priv);
if (iter->err < 0)
@@ -599,7 +597,7 @@
{
struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv);
- nft_set_elem_change_active(net, set, &he->ext);
+ nft_clear(net, &he->ext);
}
static void nft_hash_flush(const struct net *net,
@@ -652,8 +650,6 @@
hlist_for_each_entry_rcu(he, &priv->table[i], node) {
if (iter->count < iter->skip)
goto cont;
- if (!nft_set_elem_active(&he->ext, iter->genmask))
- goto cont;
iter->err = iter->fn(ctx, set, iter, &he->priv);
if (iter->err < 0)
diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index df8de50..187138a 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1847,7 +1847,7 @@
{
struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv);
- nft_set_elem_change_active(net, set, &e->ext);
+ nft_clear(net, &e->ext);
}
/**
@@ -2077,6 +2077,8 @@
rules_fx = rules_f0;
nft_pipapo_for_each_field(f, i, m) {
+ bool last = i == m->field_count - 1;
+
if (!pipapo_match_field(f, start, rules_fx,
match_start, match_end))
break;
@@ -2089,16 +2091,18 @@
match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f);
match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f);
- }
- if (i == m->field_count) {
- priv->dirty = true;
- pipapo_drop(m, rulemap);
- return;
+ if (last && f->mt[rulemap[i].to].e == e) {
+ priv->dirty = true;
+ pipapo_drop(m, rulemap);
+ return;
+ }
}
first_rule += rules_f0;
}
+
+ WARN_ON_ONCE(1); /* elem_priv not found */
}
/**
@@ -2115,13 +2119,15 @@
struct nft_set_iter *iter)
{
struct nft_pipapo *priv = nft_set_priv(set);
- struct net *net = read_pnet(&set->net);
const struct nft_pipapo_match *m;
const struct nft_pipapo_field *f;
unsigned int i, r;
+ WARN_ON_ONCE(iter->type != NFT_ITER_READ &&
+ iter->type != NFT_ITER_UPDATE);
+
rcu_read_lock();
- if (iter->genmask == nft_genmask_cur(net))
+ if (iter->type == NFT_ITER_READ)
m = rcu_dereference(priv->match);
else
m = priv->clone;
@@ -2143,9 +2149,6 @@
e = f->mt[r].e;
- if (!nft_set_elem_active(&e->ext, iter->genmask))
- goto cont;
-
iter->err = iter->fn(ctx, set, iter, &e->priv);
if (iter->err < 0)
goto out;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 9944fe4..b7ea213 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -532,7 +532,7 @@
{
struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv);
- nft_set_elem_change_active(net, set, &rbe->ext);
+ nft_clear(net, &rbe->ext);
}
static void nft_rbtree_flush(const struct net *net,
@@ -600,8 +600,6 @@
if (iter->count < iter->skip)
goto cont;
- if (!nft_set_elem_active(&rbe->ext, iter->genmask))
- goto cont;
iter->err = iter->fn(ctx, set, iter, &rbe->priv);
if (iter->err < 0) {
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 819157b..d534456 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -252,10 +252,10 @@
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = copy_safe_from_sockptr(&opt, sizeof(opt),
+ optval, optlen);
+ if (err)
break;
- }
if (opt > LLCP_MAX_RW) {
err = -EINVAL;
@@ -274,10 +274,10 @@
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = copy_safe_from_sockptr(&opt, sizeof(opt),
+ optval, optlen);
+ if (err)
break;
- }
if (opt > LLCP_MAX_MIUX) {
err = -EINVAL;
diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c
index f4a38bd..bfb7758 100644
--- a/net/nsh/nsh.c
+++ b/net/nsh/nsh.c
@@ -77,13 +77,15 @@
static struct sk_buff *nsh_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
+ unsigned int outer_hlen, mac_len, nsh_len;
struct sk_buff *segs = ERR_PTR(-EINVAL);
u16 mac_offset = skb->mac_header;
- unsigned int nsh_len, mac_len;
- __be16 proto;
+ __be16 outer_proto, proto;
skb_reset_network_header(skb);
+ outer_proto = skb->protocol;
+ outer_hlen = skb_mac_header_len(skb);
mac_len = skb->mac_len;
if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN)))
@@ -113,10 +115,10 @@
}
for (skb = segs; skb; skb = skb->next) {
- skb->protocol = htons(ETH_P_NSH);
- __skb_push(skb, nsh_len);
- skb->mac_header = mac_offset;
- skb->network_header = skb->mac_header + mac_len;
+ skb->protocol = outer_proto;
+ __skb_push(skb, nsh_len + outer_hlen);
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, outer_hlen);
skb->mac_len = mac_len;
}
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 3019a440..2928c14 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1380,8 +1380,9 @@
if (ct_info.timeout[0]) {
if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto,
ct_info.timeout))
- pr_info_ratelimited("Failed to associated timeout "
- "policy `%s'\n", ct_info.timeout);
+ OVS_NLERR(log,
+ "Failed to associated timeout policy '%s'",
+ ct_info.timeout);
else
ct_info.nf_ct_timeout = rcu_dereference(
nf_ct_timeout_find(ct_info.ct)->timeout);
@@ -1592,9 +1593,9 @@
for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) {
struct hlist_head *head = &info->limits[i];
struct ovs_ct_limit *ct_limit;
+ struct hlist_node *next;
- hlist_for_each_entry_rcu(ct_limit, head, hlist_node,
- lockdep_ovsl_is_held())
+ hlist_for_each_entry_safe(ct_limit, next, head, hlist_node)
kfree_rcu(ct_limit, rcu);
}
kfree(info->limits);
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 0af4642..1539d31 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -119,18 +119,13 @@
switch (srx->transport.family) {
case AF_INET:
if (peer->srx.transport.sin.sin_port !=
- srx->transport.sin.sin_port ||
- peer->srx.transport.sin.sin_addr.s_addr !=
- srx->transport.sin.sin_addr.s_addr)
+ srx->transport.sin.sin_port)
goto not_found;
break;
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
if (peer->srx.transport.sin6.sin6_port !=
- srx->transport.sin6.sin6_port ||
- memcmp(&peer->srx.transport.sin6.sin6_addr,
- &srx->transport.sin6.sin6_addr,
- sizeof(struct in6_addr)) != 0)
+ srx->transport.sin6.sin6_port)
goto not_found;
break;
#endif
diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
index f270106..6716c02 100644
--- a/net/rxrpc/insecure.c
+++ b/net/rxrpc/insecure.c
@@ -19,7 +19,7 @@
*/
static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp)
{
- return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 0, gfp);
+ return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 1, gfp);
}
static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index f1a6827..48a1475 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -155,7 +155,7 @@
switch (call->conn->security_level) {
default:
space = min_t(size_t, remain, RXRPC_JUMBO_DATALEN);
- return rxrpc_alloc_data_txbuf(call, space, 0, gfp);
+ return rxrpc_alloc_data_txbuf(call, space, 1, gfp);
case RXRPC_SECURITY_AUTH:
shdr = sizeof(struct rxkad_level1_hdr);
break;
diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c
index e067965..c3913d8 100644
--- a/net/rxrpc/txbuf.c
+++ b/net/rxrpc/txbuf.c
@@ -21,20 +21,20 @@
{
struct rxrpc_wire_header *whdr;
struct rxrpc_txbuf *txb;
- size_t total, hoff = 0;
+ size_t total, hoff;
void *buf;
txb = kmalloc(sizeof(*txb), gfp);
if (!txb)
return NULL;
- if (data_align)
- hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr);
+ hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr);
total = hoff + sizeof(*whdr) + data_size;
+ data_align = umax(data_align, L1_CACHE_BYTES);
mutex_lock(&call->conn->tx_data_alloc_lock);
- buf = __page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp,
- ~(data_align - 1) & ~(L1_CACHE_BYTES - 1));
+ buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp,
+ data_align);
mutex_unlock(&call->conn->tx_data_alloc_lock);
if (!buf) {
kfree(txb);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index ff53364..4a2c763 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -974,6 +974,7 @@
sch->enqueue = ops->enqueue;
sch->dequeue = ops->dequeue;
sch->dev_queue = dev_queue;
+ sch->owner = -1;
netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL);
refcount_set(&sch->refcnt, 1);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index f2a100c..4079711 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -231,28 +231,6 @@
}
/**
- * svc_rdma_write_chunk_release - Release Write chunk I/O resources
- * @rdma: controlling transport
- * @ctxt: Send context that is being released
- */
-void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma,
- struct svc_rdma_send_ctxt *ctxt)
-{
- struct svc_rdma_write_info *info;
- struct svc_rdma_chunk_ctxt *cc;
-
- while (!list_empty(&ctxt->sc_write_info_list)) {
- info = list_first_entry(&ctxt->sc_write_info_list,
- struct svc_rdma_write_info, wi_list);
- list_del(&info->wi_list);
-
- cc = &info->wi_cc;
- svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
- svc_rdma_write_info_free(info);
- }
-}
-
-/**
* svc_rdma_reply_chunk_release - Release Reply chunk I/O resources
* @rdma: controlling transport
* @ctxt: Send context that is being released
@@ -308,11 +286,13 @@
struct ib_cqe *cqe = wc->wr_cqe;
struct svc_rdma_chunk_ctxt *cc =
container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
+ struct svc_rdma_write_info *info =
+ container_of(cc, struct svc_rdma_write_info, wi_cc);
switch (wc->status) {
case IB_WC_SUCCESS:
trace_svcrdma_wc_write(&cc->cc_cid);
- return;
+ break;
case IB_WC_WR_FLUSH_ERR:
trace_svcrdma_wc_write_flush(wc, &cc->cc_cid);
break;
@@ -320,11 +300,12 @@
trace_svcrdma_wc_write_err(wc, &cc->cc_cid);
}
- /* The RDMA Write has flushed, so the client won't get
- * some of the outgoing RPC message. Signal the loss
- * to the client by closing the connection.
- */
- svc_xprt_deferred_close(&rdma->sc_xprt);
+ svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount);
+
+ if (unlikely(wc->status != IB_WC_SUCCESS))
+ svc_xprt_deferred_close(&rdma->sc_xprt);
+
+ svc_rdma_write_info_free(info);
}
/**
@@ -620,19 +601,13 @@
return xdr->len;
}
-/* Link Write WRs for @chunk onto @sctxt's WR chain.
- */
-static int svc_rdma_prepare_write_chunk(struct svcxprt_rdma *rdma,
- struct svc_rdma_send_ctxt *sctxt,
- const struct svc_rdma_chunk *chunk,
- const struct xdr_buf *xdr)
+static int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
+ const struct svc_rdma_chunk *chunk,
+ const struct xdr_buf *xdr)
{
struct svc_rdma_write_info *info;
struct svc_rdma_chunk_ctxt *cc;
- struct ib_send_wr *first_wr;
struct xdr_buf payload;
- struct list_head *pos;
- struct ib_cqe *cqe;
int ret;
if (xdr_buf_subsegment(xdr, &payload, chunk->ch_position,
@@ -648,25 +623,10 @@
if (ret != payload.len)
goto out_err;
- ret = -EINVAL;
- if (unlikely(cc->cc_sqecount > rdma->sc_sq_depth))
- goto out_err;
-
- first_wr = sctxt->sc_wr_chain;
- cqe = &cc->cc_cqe;
- list_for_each(pos, &cc->cc_rwctxts) {
- struct svc_rdma_rw_ctxt *rwc;
-
- rwc = list_entry(pos, struct svc_rdma_rw_ctxt, rw_list);
- first_wr = rdma_rw_ctx_wrs(&rwc->rw_ctx, rdma->sc_qp,
- rdma->sc_port_num, cqe, first_wr);
- cqe = NULL;
- }
- sctxt->sc_wr_chain = first_wr;
- sctxt->sc_sqecount += cc->cc_sqecount;
- list_add(&info->wi_list, &sctxt->sc_write_info_list);
-
trace_svcrdma_post_write_chunk(&cc->cc_cid, cc->cc_sqecount);
+ ret = svc_rdma_post_chunk_ctxt(rdma, cc);
+ if (ret < 0)
+ goto out_err;
return 0;
out_err:
@@ -675,27 +635,25 @@
}
/**
- * svc_rdma_prepare_write_list - Construct WR chain for sending Write list
+ * svc_rdma_send_write_list - Send all chunks on the Write list
* @rdma: controlling RDMA transport
- * @write_pcl: Write list provisioned by the client
- * @sctxt: Send WR resources
+ * @rctxt: Write list provisioned by the client
* @xdr: xdr_buf containing an RPC Reply message
*
* Returns zero on success, or a negative errno if one or more
* Write chunks could not be sent.
*/
-int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma,
- const struct svc_rdma_pcl *write_pcl,
- struct svc_rdma_send_ctxt *sctxt,
- const struct xdr_buf *xdr)
+int svc_rdma_send_write_list(struct svcxprt_rdma *rdma,
+ const struct svc_rdma_recv_ctxt *rctxt,
+ const struct xdr_buf *xdr)
{
struct svc_rdma_chunk *chunk;
int ret;
- pcl_for_each_chunk(chunk, write_pcl) {
+ pcl_for_each_chunk(chunk, &rctxt->rc_write_pcl) {
if (!chunk->ch_payload_length)
break;
- ret = svc_rdma_prepare_write_chunk(rdma, sctxt, chunk, xdr);
+ ret = svc_rdma_send_write_chunk(rdma, chunk, xdr);
if (ret < 0)
return ret;
}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index dfca39a..bb5436b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -142,7 +142,6 @@
ctxt->sc_send_wr.sg_list = ctxt->sc_sges;
ctxt->sc_send_wr.send_flags = IB_SEND_SIGNALED;
ctxt->sc_cqe.done = svc_rdma_wc_send;
- INIT_LIST_HEAD(&ctxt->sc_write_info_list);
ctxt->sc_xprt_buf = buffer;
xdr_buf_init(&ctxt->sc_hdrbuf, ctxt->sc_xprt_buf,
rdma->sc_max_req_size);
@@ -228,7 +227,6 @@
struct ib_device *device = rdma->sc_cm_id->device;
unsigned int i;
- svc_rdma_write_chunk_release(rdma, ctxt);
svc_rdma_reply_chunk_release(rdma, ctxt);
if (ctxt->sc_page_count)
@@ -1015,8 +1013,7 @@
if (!p)
goto put_ctxt;
- ret = svc_rdma_prepare_write_list(rdma, &rctxt->rc_write_pcl, sctxt,
- &rqstp->rq_res);
+ ret = svc_rdma_send_write_list(rdma, rctxt, &rqstp->rq_res);
if (ret < 0)
goto put_ctxt;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index bb9b747..ce18716 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2664,6 +2664,7 @@
.xprtsec = {
.policy = RPC_XPRTSEC_NONE,
},
+ .stats = upper_clnt->cl_stats,
};
unsigned int pflags = current->flags;
struct rpc_clnt *lower_clnt;
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 5c9fd47..76284fc 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -142,9 +142,9 @@
if (fragid == FIRST_FRAGMENT) {
if (unlikely(head))
goto err;
- *buf = NULL;
if (skb_has_frag_list(frag) && __skb_linearize(frag))
goto err;
+ *buf = NULL;
frag = skb_unshare(frag, GFP_ATOMIC);
if (unlikely(!frag))
goto err;
@@ -156,6 +156,11 @@
if (!head)
goto err;
+ /* Either the input skb ownership is transferred to headskb
+ * or the input skb is freed, clear the reference to avoid
+ * bad access on error path.
+ */
+ *buf = NULL;
if (skb_try_coalesce(head, frag, &headstolen, &delta)) {
kfree_skb_partial(frag, headstolen);
} else {
@@ -179,7 +184,6 @@
*headbuf = NULL;
return 1;
}
- *buf = NULL;
return 0;
err:
kfree_skb(*buf);
diff --git a/net/tls/tls.h b/net/tls/tls.h
index 762f424..e5e4745 100644
--- a/net/tls/tls.h
+++ b/net/tls/tls.h
@@ -215,7 +215,7 @@
static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx)
{
- return ctx->strp.msg_ready;
+ return READ_ONCE(ctx->strp.msg_ready);
}
static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx)
diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c
index ca1e0e1..5df08d8 100644
--- a/net/tls/tls_strp.c
+++ b/net/tls/tls_strp.c
@@ -360,7 +360,7 @@
if (strp->stm.full_len && strp->stm.full_len == skb->len) {
desc->count = 0;
- strp->msg_ready = 1;
+ WRITE_ONCE(strp->msg_ready, 1);
tls_rx_msg_ready(strp);
}
@@ -528,7 +528,7 @@
if (!tls_strp_check_queue_ok(strp))
return tls_strp_read_copy(strp, false);
- strp->msg_ready = 1;
+ WRITE_ONCE(strp->msg_ready, 1);
tls_rx_msg_ready(strp);
return 0;
@@ -580,7 +580,7 @@
else
tls_strp_flush_anchor_copy(strp);
- strp->msg_ready = 0;
+ WRITE_ONCE(strp->msg_ready, 0);
memset(&strp->stm, 0, sizeof(strp->stm));
tls_strp_check_rcv(strp);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5b41e23..9a6ad59 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2663,9 +2663,13 @@
WRITE_ONCE(u->oob_skb, NULL);
consume_skb(skb);
}
- } else if (!(flags & MSG_PEEK)) {
+ } else if (flags & MSG_PEEK) {
+ skb = NULL;
+ } else {
skb_unlink(skb, &sk->sk_receive_queue);
- consume_skb(skb);
+ WRITE_ONCE(u->oob_skb, NULL);
+ if (!WARN_ON_ONCE(skb_unref(skb)))
+ kfree_skb(skb);
skb = skb_peek(&sk->sk_receive_queue);
}
}
@@ -2739,18 +2743,16 @@
last = skb = skb_peek(&sk->sk_receive_queue);
last_len = last ? last->len : 0;
+again:
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
if (skb) {
skb = manage_oob(skb, sk, flags, copied);
- if (!skb) {
+ if (!skb && copied) {
unix_state_unlock(sk);
- if (copied)
- break;
- goto redo;
+ break;
}
}
#endif
-again:
if (skb == NULL) {
if (copied >= target)
goto unlock;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index fa39b62..0104be9 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -274,11 +274,22 @@
* receive queues. Other, non candidate sockets _can_ be
* added to queue, so we must make sure only to touch
* candidates.
+ *
+ * Embryos, though never candidates themselves, affect which
+ * candidates are reachable by the garbage collector. Before
+ * being added to a listener's queue, an embryo may already
+ * receive data carrying SCM_RIGHTS, potentially making the
+ * passed socket a candidate that is not yet reachable by the
+ * collector. It becomes reachable once the embryo is
+ * enqueued. Therefore, we must ensure that no SCM-laden
+ * embryo appears in a (candidate) listener's queue between
+ * consecutive scan_children() calls.
*/
list_for_each_entry_safe(u, next, &gc_inflight_list, link) {
+ struct sock *sk = &u->sk;
long total_refs;
- total_refs = file_count(u->sk.sk_socket->file);
+ total_refs = file_count(sk->sk_socket->file);
WARN_ON_ONCE(!u->inflight);
WARN_ON_ONCE(total_refs < u->inflight);
@@ -286,6 +297,11 @@
list_move_tail(&u->link, &gc_candidates);
__set_bit(UNIX_GC_CANDIDATE, &u->gc_flags);
__set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags);
+
+ if (sk->sk_state == TCP_LISTEN) {
+ unix_state_lock_nested(sk, U_LOCK_GC_LISTENER);
+ unix_state_unlock(sk);
+ }
}
}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index b4edba6..30ff9a4 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -14030,6 +14030,8 @@
error:
for (i = 0; i < new_coalesce.n_rules; i++) {
tmp_rule = &new_coalesce.rules[i];
+ if (!tmp_rule)
+ continue;
for (j = 0; j < tmp_rule->n_patterns; j++)
kfree(tmp_rule->patterns[j].mask);
kfree(tmp_rule->patterns);
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index cbbf347..df013c9 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1758,7 +1758,7 @@
DECLARE_EVENT_CLASS(tx_rx_evt,
TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx),
- TP_ARGS(wiphy, rx, tx),
+ TP_ARGS(wiphy, tx, rx),
TP_STRUCT__entry(
WIPHY_ENTRY
__field(u32, tx)
@@ -1775,7 +1775,7 @@
DEFINE_EVENT(tx_rx_evt, rdev_set_antenna,
TP_PROTO(struct wiphy *wiphy, u32 tx, u32 rx),
- TP_ARGS(wiphy, rx, tx)
+ TP_ARGS(wiphy, tx, rx)
);
DECLARE_EVENT_CLASS(wiphy_netdev_id_evt,
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 3404d07..727aa20 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1417,6 +1417,8 @@
struct xsk_queue **q;
int entries;
+ if (optlen < sizeof(entries))
+ return -EINVAL;
if (copy_from_sockptr(&entries, optval, sizeof(entries)))
return -EFAULT;
diff --git a/rust/Makefile b/rust/Makefile
index 846e6ab..86a125c 100644
--- a/rust/Makefile
+++ b/rust/Makefile
@@ -175,7 +175,6 @@
mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \
OBJTREE=$(abspath $(objtree)) \
$(RUSTDOC) --test $(rust_flags) \
- @$(objtree)/include/generated/rustc_cfg \
-L$(objtree)/$(obj) --extern alloc --extern kernel \
--extern build_error --extern macros \
--extern bindings --extern uapi \
diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 4242572..09004b5 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -1292,8 +1292,15 @@
i8, i16, i32, i64, i128, isize,
f32, f64,
- // SAFETY: These are ZSTs, there is nothing to zero.
- {<T: ?Sized>} PhantomData<T>, core::marker::PhantomPinned, Infallible, (),
+ // Note: do not add uninhabited types (such as `!` or `core::convert::Infallible`) to this list;
+ // creating an instance of an uninhabited type is immediate undefined behavior. For more on
+ // uninhabited/empty types, consult The Rustonomicon:
+ // <https://doc.rust-lang.org/stable/nomicon/exotic-sizes.html#empty-types>. The Rust Reference
+ // also has information on undefined behavior:
+ // <https://doc.rust-lang.org/stable/reference/behavior-considered-undefined.html>.
+ //
+ // SAFETY: These are inhabited ZSTs; there is nothing to zero and a valid value exists.
+ {<T: ?Sized>} PhantomData<T>, core::marker::PhantomPinned, (),
// SAFETY: Type is allowed to take any value, including all zeros.
{<T>} MaybeUninit<T>,
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index be68d5e..6858e2f 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -65,7 +65,7 @@
/// The top level entrypoint to implementing a kernel module.
///
/// For any teardown or cleanup operations, your type may implement [`Drop`].
-pub trait Module: Sized + Sync {
+pub trait Module: Sized + Sync + Send {
/// Called at module initialization time.
///
/// Use this method to perform whatever setup or registration your module
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 96e09c6..265d0e1 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -640,6 +640,10 @@
drivers: Pin<&'static mut [DriverVTable]>,
}
+// SAFETY: The only action allowed in a `Registration` instance is dropping it, which is safe to do
+// from any thread because `phy_drivers_unregister` can be called from any thread context.
+unsafe impl Send for Registration {}
+
impl Registration {
/// Registers a PHY driver.
pub fn register(
diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs
index f489f31..520eae5 100644
--- a/rust/macros/lib.rs
+++ b/rust/macros/lib.rs
@@ -35,18 +35,6 @@
/// author: "Rust for Linux Contributors",
/// description: "My very own kernel module!",
/// license: "GPL",
-/// params: {
-/// my_i32: i32 {
-/// default: 42,
-/// permissions: 0o000,
-/// description: "Example of i32",
-/// },
-/// writeable_i32: i32 {
-/// default: 42,
-/// permissions: 0o644,
-/// description: "Example of i32",
-/// },
-/// },
/// }
///
/// struct MyModule;
diff --git a/rust/macros/module.rs b/rust/macros/module.rs
index 27979e5..acd0393b 100644
--- a/rust/macros/module.rs
+++ b/rust/macros/module.rs
@@ -199,17 +199,6 @@
/// Used by the printing macros, e.g. [`info!`].
const __LOG_PREFIX: &[u8] = b\"{name}\\0\";
- /// The \"Rust loadable module\" mark.
- //
- // This may be best done another way later on, e.g. as a new modinfo
- // key or a new section. For the moment, keep it simple.
- #[cfg(MODULE)]
- #[doc(hidden)]
- #[used]
- static __IS_RUST_MODULE: () = ();
-
- static mut __MOD: Option<{type_}> = None;
-
// SAFETY: `__this_module` is constructed by the kernel at load time and will not be
// freed until the module is unloaded.
#[cfg(MODULE)]
@@ -221,81 +210,132 @@
kernel::ThisModule::from_ptr(core::ptr::null_mut())
}};
- // Loadable modules need to export the `{{init,cleanup}}_module` identifiers.
- /// # Safety
- ///
- /// This function must not be called after module initialization, because it may be
- /// freed after that completes.
- #[cfg(MODULE)]
- #[doc(hidden)]
- #[no_mangle]
- #[link_section = \".init.text\"]
- pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{
- __init()
- }}
+ // Double nested modules, since then nobody can access the public items inside.
+ mod __module_init {{
+ mod __module_init {{
+ use super::super::{type_};
- #[cfg(MODULE)]
- #[doc(hidden)]
- #[no_mangle]
- pub extern \"C\" fn cleanup_module() {{
- __exit()
- }}
+ /// The \"Rust loadable module\" mark.
+ //
+ // This may be best done another way later on, e.g. as a new modinfo
+ // key or a new section. For the moment, keep it simple.
+ #[cfg(MODULE)]
+ #[doc(hidden)]
+ #[used]
+ static __IS_RUST_MODULE: () = ();
- // Built-in modules are initialized through an initcall pointer
- // and the identifiers need to be unique.
- #[cfg(not(MODULE))]
- #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))]
- #[doc(hidden)]
- #[link_section = \"{initcall_section}\"]
- #[used]
- pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init;
+ static mut __MOD: Option<{type_}> = None;
- #[cfg(not(MODULE))]
- #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)]
- core::arch::global_asm!(
- r#\".section \"{initcall_section}\", \"a\"
- __{name}_initcall:
- .long __{name}_init - .
- .previous
- \"#
- );
+ // Loadable modules need to export the `{{init,cleanup}}_module` identifiers.
+ /// # Safety
+ ///
+ /// This function must not be called after module initialization, because it may be
+ /// freed after that completes.
+ #[cfg(MODULE)]
+ #[doc(hidden)]
+ #[no_mangle]
+ #[link_section = \".init.text\"]
+ pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{
+ // SAFETY: This function is inaccessible to the outside due to the double
+ // module wrapping it. It is called exactly once by the C side via its
+ // unique name.
+ unsafe {{ __init() }}
+ }}
- #[cfg(not(MODULE))]
- #[doc(hidden)]
- #[no_mangle]
- pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{
- __init()
- }}
+ #[cfg(MODULE)]
+ #[doc(hidden)]
+ #[no_mangle]
+ pub extern \"C\" fn cleanup_module() {{
+ // SAFETY:
+ // - This function is inaccessible to the outside due to the double
+ // module wrapping it. It is called exactly once by the C side via its
+ // unique name,
+ // - furthermore it is only called after `init_module` has returned `0`
+ // (which delegates to `__init`).
+ unsafe {{ __exit() }}
+ }}
- #[cfg(not(MODULE))]
- #[doc(hidden)]
- #[no_mangle]
- pub extern \"C\" fn __{name}_exit() {{
- __exit()
- }}
+ // Built-in modules are initialized through an initcall pointer
+ // and the identifiers need to be unique.
+ #[cfg(not(MODULE))]
+ #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))]
+ #[doc(hidden)]
+ #[link_section = \"{initcall_section}\"]
+ #[used]
+ pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init;
- fn __init() -> core::ffi::c_int {{
- match <{type_} as kernel::Module>::init(&THIS_MODULE) {{
- Ok(m) => {{
- unsafe {{
- __MOD = Some(m);
+ #[cfg(not(MODULE))]
+ #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)]
+ core::arch::global_asm!(
+ r#\".section \"{initcall_section}\", \"a\"
+ __{name}_initcall:
+ .long __{name}_init - .
+ .previous
+ \"#
+ );
+
+ #[cfg(not(MODULE))]
+ #[doc(hidden)]
+ #[no_mangle]
+ pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{
+ // SAFETY: This function is inaccessible to the outside due to the double
+ // module wrapping it. It is called exactly once by the C side via its
+ // placement above in the initcall section.
+ unsafe {{ __init() }}
+ }}
+
+ #[cfg(not(MODULE))]
+ #[doc(hidden)]
+ #[no_mangle]
+ pub extern \"C\" fn __{name}_exit() {{
+ // SAFETY:
+ // - This function is inaccessible to the outside due to the double
+ // module wrapping it. It is called exactly once by the C side via its
+ // unique name,
+ // - furthermore it is only called after `__{name}_init` has returned `0`
+ // (which delegates to `__init`).
+ unsafe {{ __exit() }}
+ }}
+
+ /// # Safety
+ ///
+ /// This function must only be called once.
+ unsafe fn __init() -> core::ffi::c_int {{
+ match <{type_} as kernel::Module>::init(&super::super::THIS_MODULE) {{
+ Ok(m) => {{
+ // SAFETY: No data race, since `__MOD` can only be accessed by this
+ // module and there only `__init` and `__exit` access it. These
+ // functions are only called once and `__exit` cannot be called
+ // before or during `__init`.
+ unsafe {{
+ __MOD = Some(m);
+ }}
+ return 0;
+ }}
+ Err(e) => {{
+ return e.to_errno();
+ }}
}}
- return 0;
}}
- Err(e) => {{
- return e.to_errno();
+
+ /// # Safety
+ ///
+ /// This function must
+ /// - only be called once,
+ /// - be called after `__init` has been called and returned `0`.
+ unsafe fn __exit() {{
+ // SAFETY: No data race, since `__MOD` can only be accessed by this module
+ // and there only `__init` and `__exit` access it. These functions are only
+ // called once and `__init` was already called.
+ unsafe {{
+ // Invokes `drop()` on `__MOD`, which should be used for cleanup.
+ __MOD = None;
+ }}
}}
+
+ {modinfo}
}}
}}
-
- fn __exit() {{
- unsafe {{
- // Invokes `drop()` on `__MOD`, which should be used for cleanup.
- __MOD = None;
- }}
- }}
-
- {modinfo}
",
type_ = info.type_,
name = info.name,
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index baf86c0..533a779 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -273,7 +273,7 @@
-Zallow-features=$(rust_allowed_features) \
-Zcrate-attr=no_std \
-Zcrate-attr='feature($(rust_allowed_features))' \
- --extern alloc --extern kernel \
+ -Zunstable-options --extern force:alloc --extern kernel \
--crate-type rlib -L $(objtree)/rust/ \
--crate-name $(basename $(notdir $@)) \
--sysroot=/dev/null \
diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c
index c5c2ce1..d20c47d 100644
--- a/scripts/gcc-plugins/stackleak_plugin.c
+++ b/scripts/gcc-plugins/stackleak_plugin.c
@@ -467,6 +467,8 @@
return false;
if (STRING_EQUAL(section, ".entry.text"))
return false;
+ if (STRING_EQUAL(section, ".head.text"))
+ return false;
}
return track_frame_size >= 0;
diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
index b141024..ee6ac64 100644
--- a/sound/core/seq/seq_ump_convert.c
+++ b/sound/core/seq/seq_ump_convert.c
@@ -428,7 +428,7 @@
midi1->note.group = midi2->note.group;
midi1->note.status = midi2->note.status;
midi1->note.channel = midi2->note.channel;
- switch (midi2->note.status << 4) {
+ switch (midi2->note.status) {
case UMP_MSG_STATUS_NOTE_ON:
case UMP_MSG_STATUS_NOTE_OFF:
midi1->note.note = midi2->note.note;
diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
index 6a384b9..d1f6cdc 100644
--- a/sound/hda/intel-dsp-config.c
+++ b/sound/hda/intel-dsp-config.c
@@ -557,9 +557,32 @@
if (table->codec_hid) {
int i;
- for (i = 0; i < table->codec_hid->num_codecs; i++)
- if (acpi_dev_present(table->codec_hid->codecs[i], NULL, -1))
+ for (i = 0; i < table->codec_hid->num_codecs; i++) {
+ struct nhlt_acpi_table *nhlt;
+ bool ssp_found = false;
+
+ if (!acpi_dev_present(table->codec_hid->codecs[i], NULL, -1))
+ continue;
+
+ nhlt = intel_nhlt_init(&pci->dev);
+ if (!nhlt) {
+ dev_warn(&pci->dev, "%s: NHLT table not found, skipped HID %s\n",
+ __func__, table->codec_hid->codecs[i]);
+ continue;
+ }
+
+ if (intel_nhlt_has_endpoint_type(nhlt, NHLT_LINK_SSP) &&
+ intel_nhlt_ssp_endpoint_mask(nhlt, NHLT_DEVICE_I2S))
+ ssp_found = true;
+
+ intel_nhlt_free(nhlt);
+
+ if (ssp_found)
break;
+
+ dev_warn(&pci->dev, "%s: no valid SSP found for HID %s, skipped\n",
+ __func__, table->codec_hid->codecs[i]);
+ }
if (i == table->codec_hid->num_codecs)
continue;
}
diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c
index 5f60658..d7417a4 100644
--- a/sound/hda/intel-sdw-acpi.c
+++ b/sound/hda/intel-sdw-acpi.c
@@ -45,6 +45,8 @@
"intel-quirk-mask",
&quirk_mask);
+ fwnode_handle_put(link);
+
if (quirk_mask & SDW_INTEL_QUIRK_MASK_BUS_DISABLE)
return false;
diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c
index fe72e7d..dadeda7 100644
--- a/sound/pci/emu10k1/emu10k1.c
+++ b/sound/pci/emu10k1/emu10k1.c
@@ -189,8 +189,7 @@
emu->suspend = 1;
- cancel_work_sync(&emu->emu1010.firmware_work);
- cancel_work_sync(&emu->emu1010.clock_work);
+ cancel_work_sync(&emu->emu1010.work);
snd_ac97_suspend(emu->ac97);
diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c
index de5c41e..8ccc017 100644
--- a/sound/pci/emu10k1/emu10k1_main.c
+++ b/sound/pci/emu10k1/emu10k1_main.c
@@ -732,69 +732,67 @@
return snd_emu1010_load_firmware_entry(emu, *fw);
}
-static void emu1010_firmware_work(struct work_struct *work)
+static void snd_emu1010_load_dock_firmware(struct snd_emu10k1 *emu)
{
- struct snd_emu10k1 *emu;
- u32 tmp, tmp2, reg;
+ u32 tmp, tmp2;
int err;
- emu = container_of(work, struct snd_emu10k1,
- emu1010.firmware_work);
- if (emu->card->shutdown)
+ // The docking events clearly arrive prematurely - while the
+ // Dock's FPGA seems to be successfully programmed, the Dock
+ // fails to initialize subsequently if we don't give it some
+ // time to "warm up" here.
+ msleep(200);
+
+ dev_info(emu->card->dev, "emu1010: Loading Audio Dock Firmware\n");
+ /* Return to Audio Dock programming mode */
+ snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG,
+ EMU_HANA_FPGA_CONFIG_AUDIODOCK);
+ err = snd_emu1010_load_firmware(emu, 1, &emu->dock_fw);
+ if (err < 0)
return;
-#ifdef CONFIG_PM_SLEEP
- if (emu->suspend)
+ snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, 0);
+
+ snd_emu1010_fpga_read(emu, EMU_HANA_ID, &tmp);
+ dev_dbg(emu->card->dev, "emu1010: EMU_HANA+DOCK_ID = 0x%x\n", tmp);
+ if ((tmp & 0x1f) != 0x15) {
+ /* FPGA failed to be programmed */
+ dev_err(emu->card->dev,
+ "emu1010: Loading Audio Dock Firmware failed, reg = 0x%x\n",
+ tmp);
return;
-#endif
+ }
+ dev_info(emu->card->dev, "emu1010: Audio Dock Firmware loaded\n");
+
+ snd_emu1010_fpga_read(emu, EMU_DOCK_MAJOR_REV, &tmp);
+ snd_emu1010_fpga_read(emu, EMU_DOCK_MINOR_REV, &tmp2);
+ dev_info(emu->card->dev, "Audio Dock ver: %u.%u\n", tmp, tmp2);
+
+ /* Allow DLL to settle, to sync clocking between 1010 and Dock */
+ msleep(10);
+}
+
+static void emu1010_dock_event(struct snd_emu10k1 *emu)
+{
+ u32 reg;
+
snd_emu1010_fpga_read(emu, EMU_HANA_OPTION_CARDS, ®); /* OPTIONS: Which cards are attached to the EMU */
if (reg & EMU_HANA_OPTION_DOCK_OFFLINE) {
/* Audio Dock attached */
- /* Return to Audio Dock programming mode */
- dev_info(emu->card->dev,
- "emu1010: Loading Audio Dock Firmware\n");
- snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG,
- EMU_HANA_FPGA_CONFIG_AUDIODOCK);
- err = snd_emu1010_load_firmware(emu, 1, &emu->dock_fw);
- if (err < 0)
- return;
- snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, 0);
- snd_emu1010_fpga_read(emu, EMU_HANA_ID, &tmp);
- dev_info(emu->card->dev,
- "emu1010: EMU_HANA+DOCK_ID = 0x%x\n", tmp);
- if ((tmp & 0x1f) != 0x15) {
- /* FPGA failed to be programmed */
- dev_info(emu->card->dev,
- "emu1010: Loading Audio Dock Firmware file failed, reg = 0x%x\n",
- tmp);
- return;
- }
- dev_info(emu->card->dev,
- "emu1010: Audio Dock Firmware loaded\n");
- snd_emu1010_fpga_read(emu, EMU_DOCK_MAJOR_REV, &tmp);
- snd_emu1010_fpga_read(emu, EMU_DOCK_MINOR_REV, &tmp2);
- dev_info(emu->card->dev, "Audio Dock ver: %u.%u\n", tmp, tmp2);
- /* Sync clocking between 1010 and Dock */
- /* Allow DLL to settle */
- msleep(10);
+ snd_emu1010_load_dock_firmware(emu);
/* Unmute all. Default is muted after a firmware load */
snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE);
+ } else if (!(reg & EMU_HANA_OPTION_DOCK_ONLINE)) {
+ /* Audio Dock removed */
+ dev_info(emu->card->dev, "emu1010: Audio Dock detached\n");
+ /* The hardware auto-mutes all, so we unmute again */
+ snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE);
}
}
-static void emu1010_clock_work(struct work_struct *work)
+static void emu1010_clock_event(struct snd_emu10k1 *emu)
{
- struct snd_emu10k1 *emu;
struct snd_ctl_elem_id id;
- emu = container_of(work, struct snd_emu10k1,
- emu1010.clock_work);
- if (emu->card->shutdown)
- return;
-#ifdef CONFIG_PM_SLEEP
- if (emu->suspend)
- return;
-#endif
-
spin_lock_irq(&emu->reg_lock);
// This is the only thing that can actually happen.
emu->emu1010.clock_source = emu->emu1010.clock_fallback;
@@ -805,21 +803,44 @@
snd_ctl_notify(emu->card, SNDRV_CTL_EVENT_MASK_VALUE, &id);
}
-static void emu1010_interrupt(struct snd_emu10k1 *emu)
+static void emu1010_work(struct work_struct *work)
{
+ struct snd_emu10k1 *emu;
u32 sts;
+ emu = container_of(work, struct snd_emu10k1, emu1010.work);
+ if (emu->card->shutdown)
+ return;
+#ifdef CONFIG_PM_SLEEP
+ if (emu->suspend)
+ return;
+#endif
+
+ snd_emu1010_fpga_lock(emu);
+
snd_emu1010_fpga_read(emu, EMU_HANA_IRQ_STATUS, &sts);
- if (sts & EMU_HANA_IRQ_DOCK_LOST) {
- /* Audio Dock removed */
- dev_info(emu->card->dev, "emu1010: Audio Dock detached\n");
- /* The hardware auto-mutes all, so we unmute again */
- snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE);
- } else if (sts & EMU_HANA_IRQ_DOCK) {
- schedule_work(&emu->emu1010.firmware_work);
- }
+
+ // The distinction of the IRQ status bits is unreliable,
+ // so we dispatch later based on option card status.
+ if (sts & (EMU_HANA_IRQ_DOCK | EMU_HANA_IRQ_DOCK_LOST))
+ emu1010_dock_event(emu);
+
if (sts & EMU_HANA_IRQ_WCLK_CHANGED)
- schedule_work(&emu->emu1010.clock_work);
+ emu1010_clock_event(emu);
+
+ snd_emu1010_fpga_unlock(emu);
+}
+
+static void emu1010_interrupt(struct snd_emu10k1 *emu)
+{
+ // We get an interrupt on each GPIO input pin change, but we
+ // care only about the ones triggered by the dedicated pin.
+ u16 sts = inw(emu->port + A_GPIO);
+ u16 bit = emu->card_capabilities->ca0108_chip ? 0x2000 : 0x8000;
+ if (!(sts & bit))
+ return;
+
+ schedule_work(&emu->emu1010.work);
}
/*
@@ -841,6 +862,8 @@
* Proper init follows in snd_emu10k1_init(). */
outl(HCFG_LOCKSOUNDCACHE | HCFG_LOCKTANKCACHE_MASK, emu->port + HCFG);
+ snd_emu1010_fpga_lock(emu);
+
/* Disable 48Volt power to Audio Dock */
snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_PWR, 0);
@@ -866,7 +889,7 @@
err = snd_emu1010_load_firmware(emu, 0, &emu->firmware);
if (err < 0) {
dev_info(emu->card->dev, "emu1010: Loading Firmware failed\n");
- return err;
+ goto fail;
}
/* ID, should read & 0x7f = 0x55 when FPGA programmed. */
@@ -876,7 +899,8 @@
dev_info(emu->card->dev,
"emu1010: Loading Hana Firmware file failed, reg = 0x%x\n",
reg);
- return -ENODEV;
+ err = -ENODEV;
+ goto fail;
}
dev_info(emu->card->dev, "emu1010: Hana Firmware loaded\n");
@@ -889,7 +913,7 @@
snd_emu1010_fpga_read(emu, EMU_HANA_OPTION_CARDS, ®);
dev_info(emu->card->dev, "emu1010: Card options = 0x%x\n", reg);
if (reg & EMU_HANA_OPTION_DOCK_OFFLINE)
- schedule_work(&emu->emu1010.firmware_work);
+ snd_emu1010_load_dock_firmware(emu);
if (emu->card_capabilities->no_adat) {
emu->emu1010.optical_in = 0; /* IN_SPDIF */
emu->emu1010.optical_out = 0; /* OUT_SPDIF */
@@ -936,7 +960,9 @@
// so it is safe to simply enable the outputs.
snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE);
- return 0;
+fail:
+ snd_emu1010_fpga_unlock(emu);
+ return err;
}
/*
* Create the EMU10K1 instance
@@ -958,10 +984,10 @@
}
if (emu->card_capabilities->emu_model == EMU_MODEL_EMU1010) {
/* Disable 48Volt power to Audio Dock */
- snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_PWR, 0);
+ snd_emu1010_fpga_write_lock(emu, EMU_HANA_DOCK_PWR, 0);
}
- cancel_work_sync(&emu->emu1010.firmware_work);
- cancel_work_sync(&emu->emu1010.clock_work);
+ cancel_work_sync(&emu->emu1010.work);
+ mutex_destroy(&emu->emu1010.lock);
release_firmware(emu->firmware);
release_firmware(emu->dock_fw);
snd_util_memhdr_free(emu->memhdr);
@@ -1540,8 +1566,8 @@
emu->irq = -1;
emu->synth = NULL;
emu->get_synth_voice = NULL;
- INIT_WORK(&emu->emu1010.firmware_work, emu1010_firmware_work);
- INIT_WORK(&emu->emu1010.clock_work, emu1010_clock_work);
+ INIT_WORK(&emu->emu1010.work, emu1010_work);
+ mutex_init(&emu->emu1010.lock);
/* read revision & serial */
emu->revision = pci->revision;
pci_read_config_dword(pci, PCI_SUBSYSTEM_VENDOR_ID, &emu->serial);
diff --git a/sound/pci/emu10k1/emumixer.c b/sound/pci/emu10k1/emumixer.c
index 0a32ea5..05b98d9 100644
--- a/sound/pci/emu10k1/emumixer.c
+++ b/sound/pci/emu10k1/emumixer.c
@@ -661,7 +661,9 @@
change = (emu->emu1010.output_source[channel] != val);
if (change) {
emu->emu1010.output_source[channel] = val;
+ snd_emu1010_fpga_lock(emu);
snd_emu1010_output_source_apply(emu, channel, val);
+ snd_emu1010_fpga_unlock(emu);
}
return change;
}
@@ -705,7 +707,9 @@
change = (emu->emu1010.input_source[channel] != val);
if (change) {
emu->emu1010.input_source[channel] = val;
+ snd_emu1010_fpga_lock(emu);
snd_emu1010_input_source_apply(emu, channel, val);
+ snd_emu1010_fpga_unlock(emu);
}
return change;
}
@@ -774,7 +778,7 @@
cache = cache & ~mask;
change = (cache != emu->emu1010.adc_pads);
if (change) {
- snd_emu1010_fpga_write(emu, EMU_HANA_ADC_PADS, cache );
+ snd_emu1010_fpga_write_lock(emu, EMU_HANA_ADC_PADS, cache );
emu->emu1010.adc_pads = cache;
}
@@ -832,7 +836,7 @@
cache = cache & ~mask;
change = (cache != emu->emu1010.dac_pads);
if (change) {
- snd_emu1010_fpga_write(emu, EMU_HANA_DAC_PADS, cache );
+ snd_emu1010_fpga_write_lock(emu, EMU_HANA_DAC_PADS, cache );
emu->emu1010.dac_pads = cache;
}
@@ -980,6 +984,7 @@
val = ucontrol->value.enumerated.item[0] ;
if (val >= emu_ci->num)
return -EINVAL;
+ snd_emu1010_fpga_lock(emu);
spin_lock_irq(&emu->reg_lock);
change = (emu->emu1010.clock_source != val);
if (change) {
@@ -996,6 +1001,7 @@
} else {
spin_unlock_irq(&emu->reg_lock);
}
+ snd_emu1010_fpga_unlock(emu);
return change;
}
@@ -1041,7 +1047,7 @@
change = (emu->emu1010.clock_fallback != val);
if (change) {
emu->emu1010.clock_fallback = val;
- snd_emu1010_fpga_write(emu, EMU_HANA_DEFCLOCK, 1 - val);
+ snd_emu1010_fpga_write_lock(emu, EMU_HANA_DEFCLOCK, 1 - val);
}
return change;
}
@@ -1093,7 +1099,7 @@
emu->emu1010.optical_out = val;
tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : EMU_HANA_OPTICAL_IN_SPDIF) |
(emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : EMU_HANA_OPTICAL_OUT_SPDIF);
- snd_emu1010_fpga_write(emu, EMU_HANA_OPTICAL_TYPE, tmp);
+ snd_emu1010_fpga_write_lock(emu, EMU_HANA_OPTICAL_TYPE, tmp);
}
return change;
}
@@ -1144,7 +1150,7 @@
emu->emu1010.optical_in = val;
tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : EMU_HANA_OPTICAL_IN_SPDIF) |
(emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : EMU_HANA_OPTICAL_OUT_SPDIF);
- snd_emu1010_fpga_write(emu, EMU_HANA_OPTICAL_TYPE, tmp);
+ snd_emu1010_fpga_write_lock(emu, EMU_HANA_OPTICAL_TYPE, tmp);
}
return change;
}
@@ -2323,7 +2329,9 @@
for (i = 0; i < emu_ri->n_outs; i++)
emu->emu1010.output_source[i] =
emu1010_map_source(emu_ri, emu_ri->out_dflts[i]);
+ snd_emu1010_fpga_lock(emu);
snd_emu1010_apply_sources(emu);
+ snd_emu1010_fpga_unlock(emu);
kctl = emu->ctl_clock_source = snd_ctl_new1(&snd_emu1010_clock_source, emu);
err = snd_ctl_add(card, kctl);
diff --git a/sound/pci/emu10k1/emuproc.c b/sound/pci/emu10k1/emuproc.c
index 2f80fd9..737c28d 100644
--- a/sound/pci/emu10k1/emuproc.c
+++ b/sound/pci/emu10k1/emuproc.c
@@ -165,6 +165,8 @@
u32 value2;
if (emu->card_capabilities->emu_model) {
+ snd_emu1010_fpga_lock(emu);
+
// This represents the S/PDIF lock status on 0404b, which is
// kinda weird and unhelpful, because monitoring it via IRQ is
// impractical (one gets an IRQ flood as long as it is desynced).
@@ -197,6 +199,8 @@
snd_iprintf(buffer, "\nS/PDIF mode: %s%s\n",
value & EMU_HANA_SPDIF_MODE_RX_PRO ? "professional" : "consumer",
value & EMU_HANA_SPDIF_MODE_RX_NOCOPY ? ", no copy" : "");
+
+ snd_emu1010_fpga_unlock(emu);
} else {
snd_emu10k1_proc_spdif_status(emu, buffer, "CD-ROM S/PDIF In", CDCS, CDSRCS);
snd_emu10k1_proc_spdif_status(emu, buffer, "Optical or Coax S/PDIF In", GPSCS, GPSRCS);
@@ -458,6 +462,9 @@
struct snd_emu10k1 *emu = entry->private_data;
u32 value;
int i;
+
+ snd_emu1010_fpga_lock(emu);
+
snd_iprintf(buffer, "EMU1010 Registers:\n\n");
for(i = 0; i < 0x40; i+=1) {
@@ -496,6 +503,8 @@
snd_emu_proc_emu1010_link_read(emu, buffer, 0x701);
}
}
+
+ snd_emu1010_fpga_unlock(emu);
}
static void snd_emu_proc_io_reg_read(struct snd_info_entry *entry,
diff --git a/sound/pci/emu10k1/io.c b/sound/pci/emu10k1/io.c
index 74df233..f4a1c2d 100644
--- a/sound/pci/emu10k1/io.c
+++ b/sound/pci/emu10k1/io.c
@@ -285,24 +285,33 @@
outw(value, emu->port + A_GPIO);
udelay(10);
outw(value | 0x80 , emu->port + A_GPIO); /* High bit clocks the value into the fpga. */
+ udelay(10);
}
void snd_emu1010_fpga_write(struct snd_emu10k1 *emu, u32 reg, u32 value)
{
- unsigned long flags;
-
- spin_lock_irqsave(&emu->emu_lock, flags);
+ if (snd_BUG_ON(!mutex_is_locked(&emu->emu1010.lock)))
+ return;
snd_emu1010_fpga_write_locked(emu, reg, value);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
}
-static void snd_emu1010_fpga_read_locked(struct snd_emu10k1 *emu, u32 reg, u32 *value)
+void snd_emu1010_fpga_write_lock(struct snd_emu10k1 *emu, u32 reg, u32 value)
+{
+ snd_emu1010_fpga_lock(emu);
+ snd_emu1010_fpga_write_locked(emu, reg, value);
+ snd_emu1010_fpga_unlock(emu);
+}
+
+void snd_emu1010_fpga_read(struct snd_emu10k1 *emu, u32 reg, u32 *value)
{
// The higest input pin is used as the designated interrupt trigger,
// so it needs to be masked out.
// But note that any other input pin change will also cause an IRQ,
// so using this function often causes an IRQ as a side effect.
u32 mask = emu->card_capabilities->ca0108_chip ? 0x1f : 0x7f;
+
+ if (snd_BUG_ON(!mutex_is_locked(&emu->emu1010.lock)))
+ return;
if (snd_BUG_ON(reg > 0x3f))
return;
reg += 0x40; /* 0x40 upwards are registers. */
@@ -313,47 +322,31 @@
*value = ((inw(emu->port + A_GPIO) >> 8) & mask);
}
-void snd_emu1010_fpga_read(struct snd_emu10k1 *emu, u32 reg, u32 *value)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&emu->emu_lock, flags);
- snd_emu1010_fpga_read_locked(emu, reg, value);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
-}
-
/* Each Destination has one and only one Source,
* but one Source can feed any number of Destinations simultaneously.
*/
void snd_emu1010_fpga_link_dst_src_write(struct snd_emu10k1 *emu, u32 dst, u32 src)
{
- unsigned long flags;
-
if (snd_BUG_ON(dst & ~0x71f))
return;
if (snd_BUG_ON(src & ~0x71f))
return;
- spin_lock_irqsave(&emu->emu_lock, flags);
- snd_emu1010_fpga_write_locked(emu, EMU_HANA_DESTHI, dst >> 8);
- snd_emu1010_fpga_write_locked(emu, EMU_HANA_DESTLO, dst & 0x1f);
- snd_emu1010_fpga_write_locked(emu, EMU_HANA_SRCHI, src >> 8);
- snd_emu1010_fpga_write_locked(emu, EMU_HANA_SRCLO, src & 0x1f);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
+ snd_emu1010_fpga_write(emu, EMU_HANA_DESTHI, dst >> 8);
+ snd_emu1010_fpga_write(emu, EMU_HANA_DESTLO, dst & 0x1f);
+ snd_emu1010_fpga_write(emu, EMU_HANA_SRCHI, src >> 8);
+ snd_emu1010_fpga_write(emu, EMU_HANA_SRCLO, src & 0x1f);
}
u32 snd_emu1010_fpga_link_dst_src_read(struct snd_emu10k1 *emu, u32 dst)
{
- unsigned long flags;
u32 hi, lo;
if (snd_BUG_ON(dst & ~0x71f))
return 0;
- spin_lock_irqsave(&emu->emu_lock, flags);
- snd_emu1010_fpga_write_locked(emu, EMU_HANA_DESTHI, dst >> 8);
- snd_emu1010_fpga_write_locked(emu, EMU_HANA_DESTLO, dst & 0x1f);
- snd_emu1010_fpga_read_locked(emu, EMU_HANA_SRCHI, &hi);
- snd_emu1010_fpga_read_locked(emu, EMU_HANA_SRCLO, &lo);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
+ snd_emu1010_fpga_write(emu, EMU_HANA_DESTHI, dst >> 8);
+ snd_emu1010_fpga_write(emu, EMU_HANA_DESTLO, dst & 0x1f);
+ snd_emu1010_fpga_read(emu, EMU_HANA_SRCHI, &hi);
+ snd_emu1010_fpga_read(emu, EMU_HANA_SRCLO, &lo);
return (hi << 8) | lo;
}
diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
index 1a3f845..558c1f3 100644
--- a/sound/pci/hda/cs35l56_hda.c
+++ b/sound/pci/hda/cs35l56_hda.c
@@ -644,6 +644,8 @@
ret = cs35l56_wait_for_firmware_boot(&cs35l56->base);
if (ret)
goto err_powered_up;
+
+ regcache_cache_only(cs35l56->base.regmap, false);
}
/* Disable auto-hibernate so that runtime_pm has control */
@@ -1002,6 +1004,8 @@
if (ret)
goto err;
+ regcache_cache_only(cs35l56->base.regmap, false);
+
ret = cs35l56_set_patch(&cs35l56->base);
if (ret)
goto err;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index cdcb28a..b29739b 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -920,6 +920,8 @@
((codec)->core.dev.power.power_state.event == PM_EVENT_RESUME)
#define is_s4_resume(codec) \
((codec)->core.dev.power.power_state.event == PM_EVENT_RESTORE)
+#define is_s4_suspend(codec) \
+ ((codec)->core.dev.power.power_state.event == PM_EVENT_FREEZE)
static int alc_init(struct hda_codec *codec)
{
@@ -7183,6 +7185,46 @@
alc245_fixup_hp_gpio_led(codec, fix, action);
}
+/*
+ * ALC287 PCM hooks
+ */
+static void alc287_alc1318_playback_pcm_hook(struct hda_pcm_stream *hinfo,
+ struct hda_codec *codec,
+ struct snd_pcm_substream *substream,
+ int action)
+{
+ alc_write_coef_idx(codec, 0x10, 0x8806); /* Change MLK to GPIO3 */
+ switch (action) {
+ case HDA_GEN_PCM_ACT_OPEN:
+ alc_write_coefex_idx(codec, 0x5a, 0x00, 0x954f); /* write gpio3 to high */
+ break;
+ case HDA_GEN_PCM_ACT_CLOSE:
+ alc_write_coefex_idx(codec, 0x5a, 0x00, 0x554f); /* write gpio3 as default value */
+ break;
+ }
+}
+
+static void __maybe_unused alc287_s4_power_gpio3_default(struct hda_codec *codec)
+{
+ if (is_s4_suspend(codec)) {
+ alc_write_coef_idx(codec, 0x10, 0x8806); /* Change MLK to GPIO3 */
+ alc_write_coefex_idx(codec, 0x5a, 0x00, 0x554f); /* write gpio3 as default value */
+ }
+}
+
+static void alc287_fixup_lenovo_thinkpad_with_alc1318(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct alc_spec *spec = codec->spec;
+
+ if (action != HDA_FIXUP_ACT_PRE_PROBE)
+ return;
+#ifdef CONFIG_PM
+ spec->power_hook = alc287_s4_power_gpio3_default;
+#endif
+ spec->gen.pcm_playback_hook = alc287_alc1318_playback_pcm_hook;
+}
+
enum {
ALC269_FIXUP_GPIO2,
@@ -7426,6 +7468,7 @@
ALC287_FIXUP_YOGA7_14ITL_SPEAKERS,
ALC298_FIXUP_LENOVO_C940_DUET7,
ALC287_FIXUP_LENOVO_14IRP8_DUETITL,
+ ALC287_FIXUP_LENOVO_LEGION_7,
ALC287_FIXUP_13S_GEN2_SPEAKERS,
ALC256_FIXUP_SET_COEF_DEFAULTS,
ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE,
@@ -7467,6 +7510,11 @@
ALC285_FIXUP_CS35L56_I2C_2,
ALC285_FIXUP_CS35L56_I2C_4,
ALC285_FIXUP_ASUS_GA403U,
+ ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC,
+ ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1,
+ ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC,
+ ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1,
+ ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318,
};
/* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -7506,6 +7554,23 @@
__snd_hda_apply_fixup(codec, id, action, 0);
}
+/* Another hilarious PCI SSID conflict with Lenovo Legion Pro 7 16ARX8H (with
+ * TAS2781 codec) and Legion 7i 16IAX7 (with CS35L41 codec);
+ * we apply a corresponding fixup depending on the codec SSID instead
+ */
+static void alc287_fixup_lenovo_legion_7(struct hda_codec *codec,
+ const struct hda_fixup *fix,
+ int action)
+{
+ int id;
+
+ if (codec->core.subsystem_id == 0x17aa38a8)
+ id = ALC287_FIXUP_TAS2781_I2C; /* Legion Pro 7 16ARX8H */
+ else
+ id = ALC287_FIXUP_CS35L41_I2C_2; /* Legion 7i 16IAX7 */
+ __snd_hda_apply_fixup(codec, id, action, 0);
+}
+
static const struct hda_fixup alc269_fixups[] = {
[ALC269_FIXUP_GPIO2] = {
.type = HDA_FIXUP_FUNC,
@@ -9400,6 +9465,10 @@
.type = HDA_FIXUP_FUNC,
.v.func = alc287_fixup_lenovo_14irp8_duetitl,
},
+ [ALC287_FIXUP_LENOVO_LEGION_7] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc287_fixup_lenovo_legion_7,
+ },
[ALC287_FIXUP_13S_GEN2_SPEAKERS] = {
.type = HDA_FIXUP_VERBS,
.v.verbs = (const struct hda_verb[]) {
@@ -9690,6 +9759,44 @@
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_asus_ga403u,
},
+ [ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x19, 0x03a11050 },
+ { 0x1b, 0x03a11c30 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1
+ },
+ [ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_speaker2_to_dac1,
+ .chained = true,
+ .chain_id = ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC,
+ },
+ [ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x19, 0x03a11050 },
+ { 0x1b, 0x03a11c30 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC285_FIXUP_CS35L56_SPI_2
+ },
+ [ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_speaker2_to_dac1,
+ .chained = true,
+ .chain_id = ALC285_FIXUP_ASUS_GA403U,
+ },
+ [ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc287_fixup_lenovo_thinkpad_with_alc1318,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_THINKPAD_ACPI
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -9901,6 +10008,7 @@
SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
+ SND_PCI_QUIRK(0x103c, 0x86c1, "HP Laptop 15-da3001TU", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
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),
@@ -10084,6 +10192,8 @@
SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_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),
@@ -10143,7 +10253,7 @@
SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B),
- SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U),
+ SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10151,7 +10261,7 @@
SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
- SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_CS35L56_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1),
SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
@@ -10228,6 +10338,7 @@
SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x152d, 0x1082, "Quanta NL3", ALC269_FIXUP_LIFEBOOK),
+ SND_PCI_QUIRK(0x152d, 0x1262, "Huawei NBLB-WAX9N", ALC2XX_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1558, 0x0353, "Clevo V35[05]SN[CDE]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1558, 0x1325, "Clevo N15[01][CW]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -10333,6 +10444,7 @@
SND_PCI_QUIRK(0x17aa, 0x222e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460),
SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460),
+ SND_PCI_QUIRK(0x17aa, 0x2234, "Thinkpad ICE-1", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x2245, "Thinkpad T470", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x2246, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
SND_PCI_QUIRK(0x17aa, 0x2247, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
@@ -10353,6 +10465,8 @@
SND_PCI_QUIRK(0x17aa, 0x2318, "Thinkpad Z13 Gen2", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
SND_PCI_QUIRK(0x17aa, 0x2319, "Thinkpad Z16 Gen2", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
SND_PCI_QUIRK(0x17aa, 0x231a, "Thinkpad Z16 Gen2", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
+ SND_PCI_QUIRK(0x17aa, 0x231e, "Thinkpad", ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318),
+ SND_PCI_QUIRK(0x17aa, 0x231f, "Thinkpad", ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318),
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
@@ -10382,7 +10496,7 @@
SND_PCI_QUIRK(0x17aa, 0x3853, "Lenovo Yoga 7 15ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
SND_PCI_QUIRK(0x17aa, 0x3855, "Legion 7 16ITHG6", ALC287_FIXUP_LEGION_16ITHG6),
SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
- SND_PCI_QUIRK(0x17aa, 0x386f, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7/7i", ALC287_FIXUP_LENOVO_LEGION_7),
SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C),
SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x17aa, 0x3878, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10394,8 +10508,8 @@
SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x38a8, "Y780P AMD VECO dual", ALC287_FIXUP_TAS2781_I2C),
- SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2),
- SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
+ SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10457,6 +10571,7 @@
SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
index 48dae33..75f7674 100644
--- a/sound/pci/hda/tas2781_hda_i2c.c
+++ b/sound/pci/hda/tas2781_hda_i2c.c
@@ -514,10 +514,10 @@
static void tas2781_apply_calib(struct tasdevice_priv *tas_priv)
{
static const unsigned char page_array[CALIB_MAX] = {
- 0x17, 0x18, 0x18, 0x0d, 0x18
+ 0x17, 0x18, 0x18, 0x13, 0x18,
};
static const unsigned char rgno_array[CALIB_MAX] = {
- 0x74, 0x0c, 0x14, 0x3c, 0x7c
+ 0x74, 0x0c, 0x14, 0x70, 0x7c,
};
unsigned char *data;
int i, j, rc;
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 69c68d8..1760b5d 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -433,6 +433,13 @@
{
.driver_data = &acp6x_card,
.matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "MDC"),
+ DMI_MATCH(DMI_BOARD_NAME, "Herbag_MDU"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "System76"),
DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"),
}
diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c
index dfb4ce5..f8e57a2 100644
--- a/sound/soc/codecs/cs35l41.c
+++ b/sound/soc/codecs/cs35l41.c
@@ -1094,6 +1094,7 @@
static int cs35l41_dsp_init(struct cs35l41_private *cs35l41)
{
struct wm_adsp *dsp;
+ uint32_t dsp1rx5_src;
int ret;
dsp = &cs35l41->dsp;
@@ -1113,16 +1114,29 @@
return ret;
}
- ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC,
- CS35L41_INPUT_SRC_VPMON);
- if (ret < 0) {
- dev_err(cs35l41->dev, "Write INPUT_SRC_VPMON failed: %d\n", ret);
+ switch (cs35l41->hw_cfg.bst_type) {
+ case CS35L41_INT_BOOST:
+ case CS35L41_SHD_BOOST_ACTV:
+ dsp1rx5_src = CS35L41_INPUT_SRC_VPMON;
+ break;
+ case CS35L41_EXT_BOOST:
+ case CS35L41_SHD_BOOST_PASS:
+ dsp1rx5_src = CS35L41_INPUT_SRC_VBSTMON;
+ break;
+ default:
+ dev_err(cs35l41->dev, "wm_halo_init failed - Invalid Boost Type: %d\n",
+ cs35l41->hw_cfg.bst_type);
goto err_dsp;
}
- ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC,
- CS35L41_INPUT_SRC_CLASSH);
+
+ ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC, dsp1rx5_src);
if (ret < 0) {
- dev_err(cs35l41->dev, "Write INPUT_SRC_CLASSH failed: %d\n", ret);
+ dev_err(cs35l41->dev, "Write DSP1RX5_SRC: %d failed: %d\n", dsp1rx5_src, ret);
+ goto err_dsp;
+ }
+ ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC, CS35L41_INPUT_SRC_VBSTMON);
+ if (ret < 0) {
+ dev_err(cs35l41->dev, "Write CS35L41_INPUT_SRC_VBSTMON failed: %d\n", ret);
goto err_dsp;
}
ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX7_SRC,
diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c
index 14a5f86..70ff55c 100644
--- a/sound/soc/codecs/cs35l56-sdw.c
+++ b/sound/soc/codecs/cs35l56-sdw.c
@@ -188,8 +188,6 @@
goto out;
}
- regcache_cache_only(cs35l56->base.regmap, false);
-
ret = cs35l56_init(cs35l56);
if (ret < 0) {
regcache_cache_only(cs35l56->base.regmap, true);
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index 08cac58..fd02b62 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -40,16 +40,11 @@
static const struct reg_default cs35l56_reg_defaults[] = {
/* no defaults for OTP_MEM - first read populates cache */
- { CS35L56_ASP1_ENABLES1, 0x00000000 },
- { CS35L56_ASP1_CONTROL1, 0x00000028 },
- { CS35L56_ASP1_CONTROL2, 0x18180200 },
- { CS35L56_ASP1_CONTROL3, 0x00000002 },
- { CS35L56_ASP1_FRAME_CONTROL1, 0x03020100 },
- { CS35L56_ASP1_FRAME_CONTROL5, 0x00020100 },
- { CS35L56_ASP1_DATA_CONTROL1, 0x00000018 },
- { CS35L56_ASP1_DATA_CONTROL5, 0x00000018 },
-
- /* no defaults for ASP1TX mixer */
+ /*
+ * No defaults for ASP1 control or ASP1TX mixer. See
+ * cs35l56_populate_asp1_register_defaults() and
+ * cs35l56_sync_asp1_mixer_widgets_with_firmware().
+ */
{ CS35L56_SWIRE_DP3_CH1_INPUT, 0x00000018 },
{ CS35L56_SWIRE_DP3_CH2_INPUT, 0x00000019 },
@@ -210,6 +205,36 @@
}
}
+static const struct reg_sequence cs35l56_asp1_defaults[] = {
+ REG_SEQ0(CS35L56_ASP1_ENABLES1, 0x00000000),
+ REG_SEQ0(CS35L56_ASP1_CONTROL1, 0x00000028),
+ REG_SEQ0(CS35L56_ASP1_CONTROL2, 0x18180200),
+ REG_SEQ0(CS35L56_ASP1_CONTROL3, 0x00000002),
+ REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL1, 0x03020100),
+ REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL5, 0x00020100),
+ REG_SEQ0(CS35L56_ASP1_DATA_CONTROL1, 0x00000018),
+ REG_SEQ0(CS35L56_ASP1_DATA_CONTROL5, 0x00000018),
+};
+
+/*
+ * The firmware can have control of the ASP so we don't provide regmap
+ * with defaults for these registers, to prevent a regcache_sync() from
+ * overwriting the firmware settings. But if the machine driver hooks up
+ * the ASP it means the driver is taking control of the ASP, so then the
+ * registers are populated with the defaults.
+ */
+int cs35l56_init_asp1_regs_for_driver_control(struct cs35l56_base *cs35l56_base)
+{
+ if (!cs35l56_base->fw_owns_asp1)
+ return 0;
+
+ cs35l56_base->fw_owns_asp1 = false;
+
+ return regmap_multi_reg_write(cs35l56_base->regmap, cs35l56_asp1_defaults,
+ ARRAY_SIZE(cs35l56_asp1_defaults));
+}
+EXPORT_SYMBOL_NS_GPL(cs35l56_init_asp1_regs_for_driver_control, SND_SOC_CS35L56_SHARED);
+
/*
* The firmware boot sequence can overwrite the ASP1 config registers so that
* they don't match regmap's view of their values. Rewrite the values from the
@@ -217,19 +242,15 @@
*/
int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base)
{
- struct reg_sequence asp1_regs[] = {
- { .reg = CS35L56_ASP1_ENABLES1 },
- { .reg = CS35L56_ASP1_CONTROL1 },
- { .reg = CS35L56_ASP1_CONTROL2 },
- { .reg = CS35L56_ASP1_CONTROL3 },
- { .reg = CS35L56_ASP1_FRAME_CONTROL1 },
- { .reg = CS35L56_ASP1_FRAME_CONTROL5 },
- { .reg = CS35L56_ASP1_DATA_CONTROL1 },
- { .reg = CS35L56_ASP1_DATA_CONTROL5 },
- };
+ struct reg_sequence asp1_regs[ARRAY_SIZE(cs35l56_asp1_defaults)];
int i, ret;
- /* Read values from regmap cache into a write sequence */
+ if (cs35l56_base->fw_owns_asp1)
+ return 0;
+
+ memcpy(asp1_regs, cs35l56_asp1_defaults, sizeof(asp1_regs));
+
+ /* Read current values from regmap cache into the write sequence */
for (i = 0; i < ARRAY_SIZE(asp1_regs); ++i) {
ret = regmap_read(cs35l56_base->regmap, asp1_regs[i].reg, &asp1_regs[i].def);
if (ret)
@@ -307,10 +328,10 @@
reg = CS35L56_DSP1_HALO_STATE;
/*
- * This can't be a regmap_read_poll_timeout() because cs35l56 will NAK
- * I2C until it has booted which would terminate the poll
+ * The regmap must remain in cache-only until the chip has
+ * booted, so use a bypassed read of the status register.
*/
- poll_ret = read_poll_timeout(regmap_read, read_ret,
+ poll_ret = read_poll_timeout(regmap_read_bypassed, read_ret,
(val < 0xFFFF) && (val >= CS35L56_HALO_STATE_BOOT_DONE),
CS35L56_HALO_STATE_POLL_US,
CS35L56_HALO_STATE_TIMEOUT_US,
@@ -362,7 +383,8 @@
return;
cs35l56_wait_control_port_ready();
- regcache_cache_only(cs35l56_base->regmap, false);
+
+ /* Leave in cache-only. This will be revoked when the chip has rebooted. */
}
EXPORT_SYMBOL_NS_GPL(cs35l56_system_reset, SND_SOC_CS35L56_SHARED);
@@ -577,14 +599,14 @@
cs35l56_issue_wake_event(cs35l56_base);
out_sync:
- regcache_cache_only(cs35l56_base->regmap, false);
-
ret = cs35l56_wait_for_firmware_boot(cs35l56_base);
if (ret) {
dev_err(cs35l56_base->dev, "Hibernate wake failed: %d\n", ret);
goto err;
}
+ regcache_cache_only(cs35l56_base->regmap, false);
+
ret = cs35l56_mbox_send(cs35l56_base, CS35L56_MBOX_CMD_PREVENT_AUTO_HIBERNATE);
if (ret)
goto err;
@@ -684,7 +706,7 @@
int cs35l56_get_calibration(struct cs35l56_base *cs35l56_base)
{
- u64 silicon_uid;
+ u64 silicon_uid = 0;
int ret;
/* Driver can't apply calibration to a secured part, so skip */
@@ -757,7 +779,7 @@
* devices so the REVID needs to be determined before waiting for the
* firmware to boot.
*/
- ret = regmap_read(cs35l56_base->regmap, CS35L56_REVID, &revid);
+ ret = regmap_read_bypassed(cs35l56_base->regmap, CS35L56_REVID, &revid);
if (ret < 0) {
dev_err(cs35l56_base->dev, "Get Revision ID failed\n");
return ret;
@@ -768,7 +790,7 @@
if (ret)
return ret;
- ret = regmap_read(cs35l56_base->regmap, CS35L56_DEVID, &devid);
+ ret = regmap_read_bypassed(cs35l56_base->regmap, CS35L56_DEVID, &devid);
if (ret < 0) {
dev_err(cs35l56_base->dev, "Get Device ID failed\n");
return ret;
@@ -787,6 +809,9 @@
cs35l56_base->type = devid & 0xFF;
+ /* Silicon is now identified and booted so exit cache-only */
+ regcache_cache_only(cs35l56_base->regmap, false);
+
ret = regmap_read(cs35l56_base->regmap, CS35L56_DSP_RESTRICT_STS1, &secured);
if (ret) {
dev_err(cs35l56_base->dev, "Get Secure status failed\n");
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 8d2f021..4986e78 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -454,9 +454,14 @@
{
struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component);
unsigned int val;
+ int ret;
dev_dbg(cs35l56->base.dev, "%s: %#x\n", __func__, fmt);
+ ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base);
+ if (ret)
+ return ret;
+
switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
case SND_SOC_DAIFMT_CBC_CFC:
break;
@@ -530,6 +535,11 @@
unsigned int rx_mask, int slots, int slot_width)
{
struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component);
+ int ret;
+
+ ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base);
+ if (ret)
+ return ret;
if ((slots == 0) || (slot_width == 0)) {
dev_dbg(cs35l56->base.dev, "tdm config cleared\n");
@@ -578,6 +588,11 @@
struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component);
unsigned int rate = params_rate(params);
u8 asp_width, asp_wl;
+ int ret;
+
+ ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base);
+ if (ret)
+ return ret;
asp_wl = params_width(params);
if (cs35l56->asp_slot_width)
@@ -634,7 +649,11 @@
int clk_id, unsigned int freq, int dir)
{
struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component);
- int freq_id;
+ int freq_id, ret;
+
+ ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base);
+ if (ret)
+ return ret;
if (freq == 0) {
cs35l56->sysclk_set = false;
@@ -1341,6 +1360,7 @@
"spk-id-gpios", ACPI_TYPE_PACKAGE, &obj);
if (ret) {
dev_dbg(cs35l56->base.dev, "Could not get spk-id-gpios package: %d\n", ret);
+ fwnode_handle_put(af01_fwnode);
return -ENOENT;
}
@@ -1348,6 +1368,7 @@
if (obj->package.count != 4) {
dev_warn(cs35l56->base.dev, "Unexpected spk-id element count %d\n",
obj->package.count);
+ fwnode_handle_put(af01_fwnode);
return -ENOENT;
}
@@ -1362,6 +1383,7 @@
*/
ret = acpi_dev_add_driver_gpios(adev, cs35l56_af01_spkid_gpios_mapping);
if (ret) {
+ fwnode_handle_put(af01_fwnode);
return dev_err_probe(cs35l56->base.dev, ret,
"Failed to add gpio mapping to AF01\n");
}
@@ -1369,14 +1391,17 @@
ret = devm_add_action_or_reset(cs35l56->base.dev,
cs35l56_acpi_dev_release_driver_gpios,
adev);
- if (ret)
+ if (ret) {
+ fwnode_handle_put(af01_fwnode);
return ret;
+ }
dev_dbg(cs35l56->base.dev, "Added spk-id-gpios mapping to AF01\n");
}
desc = fwnode_gpiod_get_index(af01_fwnode, "spk-id", 0, GPIOD_IN, NULL);
if (IS_ERR(desc)) {
+ fwnode_handle_put(af01_fwnode);
ret = PTR_ERR(desc);
return dev_err_probe(cs35l56->base.dev, ret, "Get GPIO from AF01 failed\n");
}
@@ -1385,9 +1410,12 @@
gpiod_put(desc);
if (ret < 0) {
+ fwnode_handle_put(af01_fwnode);
dev_err_probe(cs35l56->base.dev, ret, "Error reading spk-id GPIO\n");
return ret;
- }
+ }
+
+ fwnode_handle_put(af01_fwnode);
dev_info(cs35l56->base.dev, "Got spk-id from AF01\n");
@@ -1403,6 +1431,9 @@
cs35l56->base.cal_index = -1;
cs35l56->speaker_id = -ENOENT;
+ /* Assume that the firmware owns ASP1 until we know different */
+ cs35l56->base.fw_owns_asp1 = true;
+
dev_set_drvdata(cs35l56->base.dev, cs35l56);
cs35l56_fill_supply_names(cs35l56->supplies);
@@ -1531,6 +1562,8 @@
return ret;
dev_dbg(cs35l56->base.dev, "Firmware rebooted after soft reset\n");
+
+ regcache_cache_only(cs35l56->base.regmap, false);
}
/* Disable auto-hibernate so that runtime_pm has control */
diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c
index 6bc068c..15e5e3e 100644
--- a/sound/soc/codecs/da7219-aad.c
+++ b/sound/soc/codecs/da7219-aad.c
@@ -671,8 +671,10 @@
return NULL;
aad_pdata = devm_kzalloc(dev, sizeof(*aad_pdata), GFP_KERNEL);
- if (!aad_pdata)
+ if (!aad_pdata) {
+ fwnode_handle_put(aad_np);
return NULL;
+ }
aad_pdata->irq = i2c->irq;
@@ -753,6 +755,8 @@
else
aad_pdata->adc_1bit_rpt = DA7219_AAD_ADC_1BIT_RPT_1;
+ fwnode_handle_put(aad_np);
+
return aad_pdata;
}
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index e3ba044..d0d24a5 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -444,6 +444,7 @@
struct regmap *regmap;
struct i2c_client *i2c;
struct gpio_desc *gpiod_hp_det;
+ struct gpio_desc *gpiod_cbj_sleeve;
struct snd_soc_jack *hp_jack;
struct snd_soc_jack *mic_jack;
struct snd_soc_jack *btn_jack;
@@ -3186,6 +3187,9 @@
regmap_update_bits(rt5645->regmap, RT5645_IN1_CTRL2,
RT5645_CBJ_MN_JD, 0);
+ if (rt5645->gpiod_cbj_sleeve)
+ gpiod_set_value(rt5645->gpiod_cbj_sleeve, 1);
+
msleep(600);
regmap_read(rt5645->regmap, RT5645_IN1_CTRL3, &val);
val &= 0x7;
@@ -3202,6 +3206,8 @@
snd_soc_dapm_disable_pin(dapm, "Mic Det Power");
snd_soc_dapm_sync(dapm);
rt5645->jack_type = SND_JACK_HEADPHONE;
+ if (rt5645->gpiod_cbj_sleeve)
+ gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0);
}
if (rt5645->pdata.level_trigger_irq)
regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2,
@@ -3229,6 +3235,9 @@
if (rt5645->pdata.level_trigger_irq)
regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2,
RT5645_JD_1_1_MASK, RT5645_JD_1_1_INV);
+
+ if (rt5645->gpiod_cbj_sleeve)
+ gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0);
}
return rt5645->jack_type;
@@ -4012,6 +4021,16 @@
return ret;
}
+ rt5645->gpiod_cbj_sleeve = devm_gpiod_get_optional(&i2c->dev, "cbj-sleeve",
+ GPIOD_OUT_LOW);
+
+ if (IS_ERR(rt5645->gpiod_cbj_sleeve)) {
+ ret = PTR_ERR(rt5645->gpiod_cbj_sleeve);
+ dev_info(&i2c->dev, "failed to initialize gpiod, ret=%d\n", ret);
+ if (ret != -ENOENT)
+ return ret;
+ }
+
for (i = 0; i < ARRAY_SIZE(rt5645->supplies); i++)
rt5645->supplies[i].supply = rt5645_supply_names[i];
@@ -4259,6 +4278,9 @@
cancel_delayed_work_sync(&rt5645->jack_detect_work);
cancel_delayed_work_sync(&rt5645->rcclock_work);
+ if (rt5645->gpiod_cbj_sleeve)
+ gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0);
+
regulator_bulk_disable(ARRAY_SIZE(rt5645->supplies), rt5645->supplies);
}
@@ -4274,6 +4296,9 @@
0);
msleep(20);
regmap_write(rt5645->regmap, RT5645_RESET, 0);
+
+ if (rt5645->gpiod_cbj_sleeve)
+ gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0);
}
static int __maybe_unused rt5645_sys_suspend(struct device *dev)
diff --git a/sound/soc/codecs/rt715-sdca.c b/sound/soc/codecs/rt715-sdca.c
index 3fb7b9a..bc35792 100644
--- a/sound/soc/codecs/rt715-sdca.c
+++ b/sound/soc/codecs/rt715-sdca.c
@@ -316,7 +316,7 @@
return 0;
}
-static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -1725, 75, 0);
static const DECLARE_TLV_DB_SCALE(mic_vol_tlv, 0, 1000, 0);
static int rt715_sdca_get_volsw(struct snd_kcontrol *kcontrol,
@@ -477,7 +477,7 @@
RT715_SDCA_FU_VOL_CTRL, CH_01),
SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_ADC7_27_VOL,
RT715_SDCA_FU_VOL_CTRL, CH_02),
- 0x2f, 0x7f, 0,
+ 0x2f, 0x3f, 0,
rt715_sdca_set_amp_gain_get, rt715_sdca_set_amp_gain_put,
in_vol_tlv),
RT715_SDCA_EXT_TLV("FU02 Capture Volume",
@@ -485,13 +485,13 @@
RT715_SDCA_FU_VOL_CTRL, CH_01),
rt715_sdca_set_amp_gain_4ch_get,
rt715_sdca_set_amp_gain_4ch_put,
- in_vol_tlv, 4, 0x7f),
+ in_vol_tlv, 4, 0x3f),
RT715_SDCA_EXT_TLV("FU06 Capture Volume",
SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_ADC10_11_VOL,
RT715_SDCA_FU_VOL_CTRL, CH_01),
rt715_sdca_set_amp_gain_4ch_get,
rt715_sdca_set_amp_gain_4ch_put,
- in_vol_tlv, 4, 0x7f),
+ in_vol_tlv, 4, 0x3f),
/* MIC Boost Control */
RT715_SDCA_BOOST_EXT_TLV("FU0E Boost",
SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_DMIC_GAIN_EN,
diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c
index 7e13868..f012fe0 100644
--- a/sound/soc/codecs/rt715-sdw.c
+++ b/sound/soc/codecs/rt715-sdw.c
@@ -111,6 +111,7 @@
case 0x839d:
case 0x83a7:
case 0x83a9:
+ case 0x752001:
case 0x752039:
return true;
default:
diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c
index e0ea3a23..e5bd9ef 100644
--- a/sound/soc/codecs/rt722-sdca.c
+++ b/sound/soc/codecs/rt722-sdca.c
@@ -1330,7 +1330,7 @@
.capture = {
.stream_name = "DP6 DMic Capture",
.channels_min = 1,
- .channels_max = 2,
+ .channels_max = 4,
.rates = RT722_STEREO_RATES,
.formats = RT722_FORMATS,
},
@@ -1439,9 +1439,12 @@
int loop_check, chk_cnt = 100, ret;
unsigned int calib_status = 0;
- /* Read eFuse */
- rt722_sdca_index_write(rt722, RT722_VENDOR_SPK_EFUSE, RT722_DC_CALIB_CTRL,
- 0x4808);
+ /* Config analog bias */
+ rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_ANALOG_BIAS_CTL3,
+ 0xa081);
+ /* GE related settings */
+ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_GE_RELATED_CTL2,
+ 0xa009);
/* Button A, B, C, D bypass mode */
rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_UMP_HID_CTL4,
0xcf00);
@@ -1475,9 +1478,6 @@
if ((calib_status & 0x0040) == 0x0)
break;
}
- /* Release HP-JD, EN_CBJ_TIE_GL/R open, en_osw gating auto done bit */
- rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4,
- 0x0010);
/* Set ADC09 power entity floating control */
rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ADC0A_08_PDE_FLOAT_CTL,
0x2a12);
@@ -1490,8 +1490,21 @@
/* Set DAC03 and HP power entity floating control */
rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_DAC03_HP_PDE_FLOAT_CTL,
0x4040);
+ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ENT_FLOAT_CTRL_1,
+ 0x4141);
+ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_FLOAT_CTRL_1,
+ 0x0101);
/* Fine tune PDE40 latency */
regmap_write(rt722->regmap, 0x2f58, 0x07);
+ regmap_write(rt722->regmap, 0x2f03, 0x06);
+ /* MIC VRefo */
+ rt722_sdca_index_update_bits(rt722, RT722_VENDOR_REG,
+ RT722_COMBO_JACK_AUTO_CTL1, 0x0200, 0x0200);
+ rt722_sdca_index_update_bits(rt722, RT722_VENDOR_REG,
+ RT722_VREFO_GAT, 0x4000, 0x4000);
+ /* Release HP-JD, EN_CBJ_TIE_GL/R open, en_osw gating auto done bit */
+ rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4,
+ 0x0010);
}
int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave)
diff --git a/sound/soc/codecs/rt722-sdca.h b/sound/soc/codecs/rt722-sdca.h
index 44af890..2464361 100644
--- a/sound/soc/codecs/rt722-sdca.h
+++ b/sound/soc/codecs/rt722-sdca.h
@@ -69,6 +69,7 @@
#define RT722_COMBO_JACK_AUTO_CTL2 0x46
#define RT722_COMBO_JACK_AUTO_CTL3 0x47
#define RT722_DIGITAL_MISC_CTRL4 0x4a
+#define RT722_VREFO_GAT 0x63
#define RT722_FSM_CTL 0x67
#define RT722_SDCA_INTR_REC 0x82
#define RT722_SW_CONFIG1 0x8a
@@ -127,6 +128,8 @@
#define RT722_UMP_HID_CTL6 0x66
#define RT722_UMP_HID_CTL7 0x67
#define RT722_UMP_HID_CTL8 0x68
+#define RT722_FLOAT_CTRL_1 0x70
+#define RT722_ENT_FLOAT_CTRL_1 0x76
/* Parameter & Verb control 01 (0x1a)(NID:20h) */
#define RT722_HIDDEN_REG_SW_RESET (0x1 << 14)
diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c
index 3c025da..1253695 100644
--- a/sound/soc/codecs/wsa881x.c
+++ b/sound/soc/codecs/wsa881x.c
@@ -1155,6 +1155,7 @@
pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS, 0);
pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop;
pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
+ pdev->prop.clk_stop_mode1 = true;
gpiod_direction_output(wsa881x->sd_n, !wsa881x->sd_n_val);
wsa881x->regmap = devm_regmap_init_sdw(pdev, &wsa881x_regmap_config);
diff --git a/sound/soc/intel/avs/icl.c b/sound/soc/intel/avs/icl.c
index 9d9921e1..d2554c8 100644
--- a/sound/soc/intel/avs/icl.c
+++ b/sound/soc/intel/avs/icl.c
@@ -64,7 +64,7 @@
struct avs_icl_memwnd2 {
union {
struct avs_icl_memwnd2_desc slot_desc[AVS_ICL_MEMWND2_SLOTS_COUNT];
- u8 rsvd[PAGE_SIZE];
+ u8 rsvd[SZ_4K];
};
u8 slot_array[AVS_ICL_MEMWND2_SLOTS_COUNT][PAGE_SIZE];
} __packed;
diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c
index 13061bd..42b4290 100644
--- a/sound/soc/intel/avs/topology.c
+++ b/sound/soc/intel/avs/topology.c
@@ -1582,6 +1582,8 @@
if (!le32_to_cpu(dw->priv.size))
return 0;
+ w->no_wname_in_kcontrol_name = true;
+
if (w->ignore_suspend && !AVS_S0IX_SUPPORTED) {
dev_info_once(comp->dev, "Device does not support S0IX, check BIOS settings\n");
w->ignore_suspend = false;
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 05f38d1..b41a1147 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -636,17 +636,7 @@
BYT_RT5640_USE_AMCR0F28),
},
{
- .matches = {
- DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
- DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"),
- },
- .driver_data = (void *)(BYT_RT5640_IN1_MAP |
- BYT_RT5640_JD_SRC_JD2_IN4N |
- BYT_RT5640_OVCD_TH_2000UA |
- BYT_RT5640_OVCD_SF_0P75 |
- BYT_RT5640_MCLK_EN),
- },
- {
+ /* Asus T100TAF, unlike other T100TA* models this one has a mono speaker */
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"),
@@ -661,6 +651,18 @@
BYT_RT5640_MCLK_EN),
},
{
+ /* Asus T100TA and T100TAM, must come after T100TAF (mono spk) match */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "T100TA"),
+ },
+ .driver_data = (void *)(BYT_RT5640_IN1_MAP |
+ BYT_RT5640_JD_SRC_JD2_IN4N |
+ BYT_RT5640_OVCD_TH_2000UA |
+ BYT_RT5640_OVCD_SF_0P75 |
+ BYT_RT5640_MCLK_EN),
+ },
+ {
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
DMI_MATCH(DMI_PRODUCT_NAME, "TF103C"),
diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index b93ea337..6458d5d 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -99,6 +99,7 @@
config SND_MESON_CARD_UTILS
tristate
+ select SND_DYNAMIC_MINORS
config SND_MESON_CODEC_GLUE
tristate
diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c
index 3180aa4..8c5605c 100644
--- a/sound/soc/meson/axg-card.c
+++ b/sound/soc/meson/axg-card.c
@@ -318,6 +318,7 @@
dai_link->cpus = cpu;
dai_link->num_cpus = 1;
+ dai_link->nonatomic = true;
ret = meson_card_parse_dai(card, np, dai_link->cpus);
if (ret)
diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c
index bebee0c..ecb3eb7 100644
--- a/sound/soc/meson/axg-fifo.c
+++ b/sound/soc/meson/axg-fifo.c
@@ -204,18 +204,26 @@
unsigned int status;
regmap_read(fifo->map, FIFO_STATUS1, &status);
-
status = FIELD_GET(STATUS1_INT_STS, status);
- if (status & FIFO_INT_COUNT_REPEAT)
- snd_pcm_period_elapsed(ss);
- else
- dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n",
- status);
-
- /* Ack irqs */
axg_fifo_ack_irq(fifo, status);
- return IRQ_RETVAL(status);
+ /* Use the thread to call period elapsed on nonatomic links */
+ if (status & FIFO_INT_COUNT_REPEAT)
+ return IRQ_WAKE_THREAD;
+
+ dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n",
+ status);
+
+ return IRQ_NONE;
+}
+
+static irqreturn_t axg_fifo_pcm_irq_block_thread(int irq, void *dev_id)
+{
+ struct snd_pcm_substream *ss = dev_id;
+
+ snd_pcm_period_elapsed(ss);
+
+ return IRQ_HANDLED;
}
int axg_fifo_pcm_open(struct snd_soc_component *component,
@@ -243,8 +251,9 @@
if (ret)
return ret;
- ret = request_irq(fifo->irq, axg_fifo_pcm_irq_block, 0,
- dev_name(dev), ss);
+ ret = request_threaded_irq(fifo->irq, axg_fifo_pcm_irq_block,
+ axg_fifo_pcm_irq_block_thread,
+ IRQF_ONESHOT, dev_name(dev), ss);
if (ret)
return ret;
diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c
index 63333a2..a6579ef 100644
--- a/sound/soc/meson/axg-tdm-formatter.c
+++ b/sound/soc/meson/axg-tdm-formatter.c
@@ -392,6 +392,46 @@
}
EXPORT_SYMBOL_GPL(axg_tdm_stream_free);
+int axg_tdm_stream_set_cont_clocks(struct axg_tdm_stream *ts,
+ unsigned int fmt)
+{
+ int ret = 0;
+
+ if (fmt & SND_SOC_DAIFMT_CONT) {
+ /* Clock are already enabled - skipping */
+ if (ts->clk_enabled)
+ return 0;
+
+ ret = clk_prepare_enable(ts->iface->mclk);
+ if (ret)
+ return ret;
+
+ ret = clk_prepare_enable(ts->iface->sclk);
+ if (ret)
+ goto err_sclk;
+
+ ret = clk_prepare_enable(ts->iface->lrclk);
+ if (ret)
+ goto err_lrclk;
+
+ ts->clk_enabled = true;
+ return 0;
+ }
+
+ /* Clocks are already disabled - skipping */
+ if (!ts->clk_enabled)
+ return 0;
+
+ clk_disable_unprepare(ts->iface->lrclk);
+err_lrclk:
+ clk_disable_unprepare(ts->iface->sclk);
+err_sclk:
+ clk_disable_unprepare(ts->iface->mclk);
+ ts->clk_enabled = false;
+ return ret;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_set_cont_clocks);
+
MODULE_DESCRIPTION("Amlogic AXG TDM formatter driver");
MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c
index bf70871..62057c7 100644
--- a/sound/soc/meson/axg-tdm-interface.c
+++ b/sound/soc/meson/axg-tdm-interface.c
@@ -309,6 +309,7 @@
struct snd_soc_dai *dai)
{
struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+ struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
int ret;
switch (iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
@@ -346,7 +347,11 @@
return ret;
}
- return 0;
+ ret = axg_tdm_stream_set_cont_clocks(ts, iface->fmt);
+ if (ret)
+ dev_err(dai->dev, "failed to apply continuous clock setting\n");
+
+ return ret;
}
static int axg_tdm_iface_hw_free(struct snd_pcm_substream *substream,
@@ -354,19 +359,32 @@
{
struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
- /* Stop all attached formatters */
- axg_tdm_stream_stop(ts);
-
- return 0;
+ return axg_tdm_stream_set_cont_clocks(ts, 0);
}
-static int axg_tdm_iface_prepare(struct snd_pcm_substream *substream,
+static int axg_tdm_iface_trigger(struct snd_pcm_substream *substream,
+ int cmd,
struct snd_soc_dai *dai)
{
- struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
+ struct axg_tdm_stream *ts =
+ snd_soc_dai_get_dma_data(dai, substream);
- /* Force all attached formatters to update */
- return axg_tdm_stream_reset(ts);
+ switch (cmd) {
+ case SNDRV_PCM_TRIGGER_START:
+ case SNDRV_PCM_TRIGGER_RESUME:
+ case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+ axg_tdm_stream_start(ts);
+ break;
+ case SNDRV_PCM_TRIGGER_SUSPEND:
+ case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+ case SNDRV_PCM_TRIGGER_STOP:
+ axg_tdm_stream_stop(ts);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
}
static int axg_tdm_iface_remove_dai(struct snd_soc_dai *dai)
@@ -412,8 +430,8 @@
.set_fmt = axg_tdm_iface_set_fmt,
.startup = axg_tdm_iface_startup,
.hw_params = axg_tdm_iface_hw_params,
- .prepare = axg_tdm_iface_prepare,
.hw_free = axg_tdm_iface_hw_free,
+ .trigger = axg_tdm_iface_trigger,
};
/* TDM Backend DAIs */
diff --git a/sound/soc/meson/axg-tdm.h b/sound/soc/meson/axg-tdm.h
index 42f7470..daaca10 100644
--- a/sound/soc/meson/axg-tdm.h
+++ b/sound/soc/meson/axg-tdm.h
@@ -58,12 +58,17 @@
unsigned int physical_width;
u32 *mask;
bool ready;
+
+ /* For continuous clock tracking */
+ bool clk_enabled;
};
struct axg_tdm_stream *axg_tdm_stream_alloc(struct axg_tdm_iface *iface);
void axg_tdm_stream_free(struct axg_tdm_stream *ts);
int axg_tdm_stream_start(struct axg_tdm_stream *ts);
void axg_tdm_stream_stop(struct axg_tdm_stream *ts);
+int axg_tdm_stream_set_cont_clocks(struct axg_tdm_stream *ts,
+ unsigned int fmt);
static inline int axg_tdm_stream_reset(struct axg_tdm_stream *ts)
{
diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c
index cc84d4c..238bda5 100644
--- a/sound/soc/sof/core.c
+++ b/sound/soc/sof/core.c
@@ -350,7 +350,9 @@
}
ret = sof_select_ipc_and_paths(sdev);
- if (!ret && plat_data->ipc_type != base_profile->ipc_type) {
+ if (ret) {
+ goto err_machine_check;
+ } else if (plat_data->ipc_type != base_profile->ipc_type) {
/* IPC type changed, re-initialize the ops */
sof_ops_free(sdev);
diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c
index 7c8aafc..7275437 100644
--- a/sound/soc/sof/debug.c
+++ b/sound/soc/sof/debug.c
@@ -330,14 +330,32 @@
int snd_sof_dbg_init(struct snd_sof_dev *sdev)
{
+ struct snd_sof_pdata *plat_data = sdev->pdata;
struct snd_sof_dsp_ops *ops = sof_ops(sdev);
const struct snd_sof_debugfs_map *map;
+ struct dentry *fw_profile;
int i;
int err;
/* use "sof" as top level debugFS dir */
sdev->debugfs_root = debugfs_create_dir("sof", NULL);
+ /* expose firmware/topology prefix/names for test purposes */
+ fw_profile = debugfs_create_dir("fw_profile", sdev->debugfs_root);
+
+ debugfs_create_str("fw_path", 0444, fw_profile,
+ (char **)&plat_data->fw_filename_prefix);
+ debugfs_create_str("fw_lib_path", 0444, fw_profile,
+ (char **)&plat_data->fw_lib_prefix);
+ debugfs_create_str("tplg_path", 0444, fw_profile,
+ (char **)&plat_data->tplg_filename_prefix);
+ debugfs_create_str("fw_name", 0444, fw_profile,
+ (char **)&plat_data->fw_filename);
+ debugfs_create_str("tplg_name", 0444, fw_profile,
+ (char **)&plat_data->tplg_filename);
+ debugfs_create_u32("ipc_type", 0444, fw_profile,
+ (u32 *)&plat_data->ipc_type);
+
/* init dfsentry list */
INIT_LIST_HEAD(&sdev->dfsentry_list);
diff --git a/sound/soc/sof/intel/pci-lnl.c b/sound/soc/sof/intel/pci-lnl.c
index b26ffe7..b14e508f 100644
--- a/sound/soc/sof/intel/pci-lnl.c
+++ b/sound/soc/sof/intel/pci-lnl.c
@@ -35,6 +35,9 @@
.default_fw_path = {
[SOF_IPC_TYPE_4] = "intel/sof-ipc4/lnl",
},
+ .default_lib_path = {
+ [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/lnl",
+ },
.default_tplg_path = {
[SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg",
},
diff --git a/sound/soc/sof/ipc3-pcm.c b/sound/soc/sof/ipc3-pcm.c
index 35769dd..af0bf35 100644
--- a/sound/soc/sof/ipc3-pcm.c
+++ b/sound/soc/sof/ipc3-pcm.c
@@ -434,4 +434,5 @@
.trigger = sof_ipc3_pcm_trigger,
.dai_link_fixup = sof_ipc3_pcm_dai_link_fixup,
.reset_hw_params_during_stop = true,
+ .d0i3_supported_in_s0ix = true,
};
diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index e915f9f..4594470 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -37,6 +37,25 @@
snd_pcm_sframes_t delay;
};
+/**
+ * struct sof_ipc4_pcm_stream_priv - IPC4 specific private data
+ * @time_info: pointer to time info struct if it is supported, otherwise NULL
+ * @chain_dma_allocated: indicates the ChainDMA allocation state
+ */
+struct sof_ipc4_pcm_stream_priv {
+ struct sof_ipc4_timestamp_info *time_info;
+
+ bool chain_dma_allocated;
+};
+
+static inline struct sof_ipc4_timestamp_info *
+sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps)
+{
+ struct sof_ipc4_pcm_stream_priv *stream_priv = sps->private;
+
+ return stream_priv->time_info;
+}
+
static int sof_ipc4_set_multi_pipeline_state(struct snd_sof_dev *sdev, u32 state,
struct ipc4_pipeline_set_state_data *trigger_list)
{
@@ -253,14 +272,17 @@
*/
static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev,
- int direction,
+ struct snd_sof_pcm *spcm, int direction,
struct snd_sof_pcm_stream_pipeline_list *pipeline_list,
int state, int cmd)
{
struct sof_ipc4_fw_data *ipc4_data = sdev->private;
+ struct sof_ipc4_pcm_stream_priv *stream_priv;
bool allocate, enable, set_fifo_size;
struct sof_ipc4_msg msg = {{ 0 }};
- int i;
+ int ret, i;
+
+ stream_priv = spcm->stream[direction].private;
switch (state) {
case SOF_IPC4_PIPE_RUNNING: /* Allocate and start chained dma */
@@ -281,6 +303,11 @@
set_fifo_size = false;
break;
case SOF_IPC4_PIPE_RESET: /* Disable and free chained DMA. */
+
+ /* ChainDMA can only be reset if it has been allocated */
+ if (!stream_priv->chain_dma_allocated)
+ return 0;
+
allocate = false;
enable = false;
set_fifo_size = false;
@@ -338,7 +365,12 @@
if (enable)
msg.primary |= SOF_IPC4_GLB_CHAIN_DMA_ENABLE_MASK;
- return sof_ipc_tx_message_no_reply(sdev->ipc, &msg, 0);
+ ret = sof_ipc_tx_message_no_reply(sdev->ipc, &msg, 0);
+ /* Update the ChainDMA allocation state */
+ if (!ret)
+ stream_priv->chain_dma_allocated = allocate;
+
+ return ret;
}
static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component,
@@ -378,7 +410,7 @@
* trigger function that handles the rest for the substream.
*/
if (pipeline->use_chain_dma)
- return sof_ipc4_chain_dma_trigger(sdev, substream->stream,
+ return sof_ipc4_chain_dma_trigger(sdev, spcm, substream->stream,
pipeline_list, state, cmd);
/* allocate memory for the pipeline data */
@@ -452,7 +484,7 @@
* Invalidate the stream_start_offset to make sure that it is
* going to be updated if the stream resumes
*/
- time_info = spcm->stream[substream->stream].private;
+ time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]);
if (time_info)
time_info->stream_start_offset = SOF_IPC4_INVALID_STREAM_POSITION;
@@ -706,12 +738,16 @@
static void sof_ipc4_pcm_free(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm)
{
struct snd_sof_pcm_stream_pipeline_list *pipeline_list;
+ struct sof_ipc4_pcm_stream_priv *stream_priv;
int stream;
for_each_pcm_streams(stream) {
pipeline_list = &spcm->stream[stream].pipeline_list;
kfree(pipeline_list->pipelines);
pipeline_list->pipelines = NULL;
+
+ stream_priv = spcm->stream[stream].private;
+ kfree(stream_priv->time_info);
kfree(spcm->stream[stream].private);
spcm->stream[stream].private = NULL;
}
@@ -721,7 +757,8 @@
{
struct snd_sof_pcm_stream_pipeline_list *pipeline_list;
struct sof_ipc4_fw_data *ipc4_data = sdev->private;
- struct sof_ipc4_timestamp_info *stream_info;
+ struct sof_ipc4_pcm_stream_priv *stream_priv;
+ struct sof_ipc4_timestamp_info *time_info;
bool support_info = true;
u32 abi_version;
u32 abi_offset;
@@ -749,33 +786,41 @@
return -ENOMEM;
}
- if (!support_info)
- continue;
-
- stream_info = kzalloc(sizeof(*stream_info), GFP_KERNEL);
- if (!stream_info) {
+ stream_priv = kzalloc(sizeof(*stream_priv), GFP_KERNEL);
+ if (!stream_priv) {
sof_ipc4_pcm_free(sdev, spcm);
return -ENOMEM;
}
- spcm->stream[stream].private = stream_info;
+ spcm->stream[stream].private = stream_priv;
+
+ if (!support_info)
+ continue;
+
+ time_info = kzalloc(sizeof(*time_info), GFP_KERNEL);
+ if (!time_info) {
+ sof_ipc4_pcm_free(sdev, spcm);
+ return -ENOMEM;
+ }
+
+ stream_priv->time_info = time_info;
}
return 0;
}
-static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *spcm)
+static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *sps)
{
struct sof_ipc4_copier *host_copier = NULL;
struct sof_ipc4_copier *dai_copier = NULL;
struct sof_ipc4_llp_reading_slot llp_slot;
- struct sof_ipc4_timestamp_info *info;
+ struct sof_ipc4_timestamp_info *time_info;
struct snd_soc_dapm_widget *widget;
struct snd_sof_dai *dai;
int i;
/* find host & dai to locate info in memory window */
- for_each_dapm_widgets(spcm->list, i, widget) {
+ for_each_dapm_widgets(sps->list, i, widget) {
struct snd_sof_widget *swidget = widget->dobj.private;
if (!swidget)
@@ -795,44 +840,44 @@
return;
}
- info = spcm->private;
- info->host_copier = host_copier;
- info->dai_copier = dai_copier;
- info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_gpdma_reading_slots) +
- sdev->fw_info_box.offset;
+ time_info = sof_ipc4_sps_to_time_info(sps);
+ time_info->host_copier = host_copier;
+ time_info->dai_copier = dai_copier;
+ time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers,
+ llp_gpdma_reading_slots) + sdev->fw_info_box.offset;
/* find llp slot used by current dai */
for (i = 0; i < SOF_IPC4_MAX_LLP_GPDMA_READING_SLOTS; i++) {
- sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot));
+ sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot));
if (llp_slot.node_id == dai_copier->data.gtw_cfg.node_id)
break;
- info->llp_offset += sizeof(llp_slot);
+ time_info->llp_offset += sizeof(llp_slot);
}
if (i < SOF_IPC4_MAX_LLP_GPDMA_READING_SLOTS)
return;
/* if no llp gpdma slot is used, check aggregated sdw slot */
- info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_sndw_reading_slots) +
- sdev->fw_info_box.offset;
+ time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers,
+ llp_sndw_reading_slots) + sdev->fw_info_box.offset;
for (i = 0; i < SOF_IPC4_MAX_LLP_SNDW_READING_SLOTS; i++) {
- sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot));
+ sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot));
if (llp_slot.node_id == dai_copier->data.gtw_cfg.node_id)
break;
- info->llp_offset += sizeof(llp_slot);
+ time_info->llp_offset += sizeof(llp_slot);
}
if (i < SOF_IPC4_MAX_LLP_SNDW_READING_SLOTS)
return;
/* check EVAD slot */
- info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_evad_reading_slot) +
- sdev->fw_info_box.offset;
- sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot));
+ time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers,
+ llp_evad_reading_slot) + sdev->fw_info_box.offset;
+ sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot));
if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id)
- info->llp_offset = 0;
+ time_info->llp_offset = 0;
}
static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component,
@@ -849,7 +894,7 @@
if (!spcm)
return -EINVAL;
- time_info = spcm->stream[substream->stream].private;
+ time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]);
/* delay calculation is not supported by current fw_reg ABI */
if (!time_info)
return 0;
@@ -864,7 +909,7 @@
static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
struct snd_pcm_substream *substream,
- struct snd_sof_pcm_stream *stream,
+ struct snd_sof_pcm_stream *sps,
struct sof_ipc4_timestamp_info *time_info)
{
struct sof_ipc4_copier *host_copier = time_info->host_copier;
@@ -918,7 +963,7 @@
struct sof_ipc4_timestamp_info *time_info;
struct sof_ipc4_llp_reading_slot llp;
snd_pcm_uframes_t head_cnt, tail_cnt;
- struct snd_sof_pcm_stream *stream;
+ struct snd_sof_pcm_stream *sps;
u64 dai_cnt, host_cnt, host_ptr;
struct snd_sof_pcm *spcm;
int ret;
@@ -927,8 +972,8 @@
if (!spcm)
return -EOPNOTSUPP;
- stream = &spcm->stream[substream->stream];
- time_info = stream->private;
+ sps = &spcm->stream[substream->stream];
+ time_info = sof_ipc4_sps_to_time_info(sps);
if (!time_info)
return -EOPNOTSUPP;
@@ -938,7 +983,7 @@
* the statistics is complete. And it will not change after the first initiailization.
*/
if (time_info->stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION) {
- ret = sof_ipc4_get_stream_start_offset(sdev, substream, stream, time_info);
+ ret = sof_ipc4_get_stream_start_offset(sdev, substream, sps, time_info);
if (ret < 0)
return -EOPNOTSUPP;
}
@@ -1030,15 +1075,13 @@
{
struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
struct sof_ipc4_timestamp_info *time_info;
- struct snd_sof_pcm_stream *stream;
struct snd_sof_pcm *spcm;
spcm = snd_sof_find_spcm_dai(component, rtd);
if (!spcm)
return 0;
- stream = &spcm->stream[substream->stream];
- time_info = stream->private;
+ time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]);
/*
* Report the stored delay value calculated in the pointer callback.
* In the unlikely event that the calculation was skipped/aborted, the
diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c
index f03cee9..8804e00 100644
--- a/sound/soc/sof/pcm.c
+++ b/sound/soc/sof/pcm.c
@@ -325,14 +325,13 @@
ipc_first = true;
break;
case SNDRV_PCM_TRIGGER_SUSPEND:
- if (sdev->system_suspend_target == SOF_SUSPEND_S0IX &&
+ /*
+ * If DSP D0I3 is allowed during S0iX, set the suspend_ignored flag for
+ * D0I3-compatible streams to keep the firmware pipeline running
+ */
+ if (pcm_ops && pcm_ops->d0i3_supported_in_s0ix &&
+ sdev->system_suspend_target == SOF_SUSPEND_S0IX &&
spcm->stream[substream->stream].d0i3_compatible) {
- /*
- * trap the event, not sending trigger stop to
- * prevent the FW pipelines from being stopped,
- * and mark the flag to ignore the upcoming DAPM
- * PM events.
- */
spcm->stream[substream->stream].suspend_ignored = true;
return 0;
}
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 86bbb53..499b608 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -116,6 +116,7 @@
* triggers. The FW keeps the host DMA running in this case and
* therefore the host must do the same and should stop the DMA during
* hw_free.
+ * @d0i3_supported_in_s0ix: Allow DSP D0I3 during S0iX
*/
struct sof_ipc_pcm_ops {
int (*hw_params)(struct snd_soc_component *component, struct snd_pcm_substream *substream,
@@ -135,6 +136,7 @@
bool reset_hw_params_during_stop;
bool ipc_first_on_start;
bool platform_stop_during_hw_free;
+ bool d0i3_supported_in_s0ix;
};
/**
diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c
index aa37c4a..21cd41f 100644
--- a/sound/soc/tegra/tegra186_dspk.c
+++ b/sound/soc/tegra/tegra186_dspk.c
@@ -1,8 +1,7 @@
// SPDX-License-Identifier: GPL-2.0-only
+// SPDX-FileCopyrightText: Copyright (c) 2020-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
//
// tegra186_dspk.c - Tegra186 DSPK driver
-//
-// Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved.
#include <linux/clk.h>
#include <linux/device.h>
@@ -241,14 +240,14 @@
return -EINVAL;
}
- cif_conf.client_bits = TEGRA_ACIF_BITS_24;
-
switch (params_format(params)) {
case SNDRV_PCM_FORMAT_S16_LE:
cif_conf.audio_bits = TEGRA_ACIF_BITS_16;
+ cif_conf.client_bits = TEGRA_ACIF_BITS_16;
break;
case SNDRV_PCM_FORMAT_S32_LE:
cif_conf.audio_bits = TEGRA_ACIF_BITS_32;
+ cif_conf.client_bits = TEGRA_ACIF_BITS_24;
break;
default:
dev_err(dev, "unsupported format!\n");
diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c
index b892d66..1e760c3 100644
--- a/sound/soc/ti/davinci-mcasp.c
+++ b/sound/soc/ti/davinci-mcasp.c
@@ -2417,12 +2417,6 @@
mcasp_reparent_fck(pdev);
- ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component,
- &davinci_mcasp_dai[mcasp->op_mode], 1);
-
- if (ret != 0)
- goto err;
-
ret = davinci_mcasp_get_dma_type(mcasp);
switch (ret) {
case PCM_EDMA:
@@ -2449,6 +2443,12 @@
goto err;
}
+ ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component,
+ &davinci_mcasp_dai[mcasp->op_mode], 1);
+
+ if (ret != 0)
+ goto err;
+
no_audio:
ret = davinci_mcasp_init_gpiochip(mcasp);
if (ret) {
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 7c7493c..52f076a 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -61,6 +61,7 @@
#define ARM_CPU_IMP_HISI 0x48
#define ARM_CPU_IMP_APPLE 0x61
#define ARM_CPU_IMP_AMPERE 0xC0
+#define ARM_CPU_IMP_MICROSOFT 0x6D
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
@@ -135,6 +136,8 @@
#define AMPERE_CPU_PART_AMPERE1 0xAC3
+#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -193,6 +196,7 @@
#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
#define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 89d2fc8..964df31 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -37,9 +37,7 @@
#include <asm/ptrace.h>
#include <asm/sve_context.h>
-#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_READONLY_MEM
#define __KVM_HAVE_VCPU_EVENTS
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -76,11 +74,11 @@
/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
#define KVM_ARM_DEVICE_TYPE_SHIFT 0
-#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
- KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_TYPE_MASK __GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
+ KVM_ARM_DEVICE_TYPE_SHIFT)
#define KVM_ARM_DEVICE_ID_SHIFT 16
-#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
- KVM_ARM_DEVICE_ID_SHIFT)
+#define KVM_ARM_DEVICE_ID_MASK __GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
+ KVM_ARM_DEVICE_ID_SHIFT)
/* Supported device IDs */
#define KVM_ARM_DEVICE_VGIC_V2 0
@@ -162,6 +160,11 @@
__u64 device_irq_level;
};
+/* Bits for run->s.regs.device_irq_level */
+#define KVM_ARM_DEV_EL1_VTIMER (1 << 0)
+#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
+#define KVM_ARM_DEV_PMU (1 << 2)
+
/*
* PMU filter structure. Describe a range of events with a particular
* action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 9f18fa0..1691297 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -28,7 +28,6 @@
#define __KVM_HAVE_PPC_SMT
#define __KVM_HAVE_IRQCHIP
#define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_GUEST_DEBUG
/* Not always available, but if it is, this is the correct offset. */
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -733,4 +732,48 @@
#define KVM_XIVE_TIMA_PAGE_OFFSET 0
#define KVM_XIVE_ESB_PAGE_OFFSET 4
+/* for KVM_PPC_GET_PVINFO */
+
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
+
+struct kvm_ppc_pvinfo {
+ /* out */
+ __u32 flags;
+ __u32 hcall[4];
+ __u8 pad[108];
+};
+
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ 8
+
+struct kvm_ppc_one_page_size {
+ __u32 page_shift; /* Page shift (or 0) */
+ __u32 pte_enc; /* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+ __u32 page_shift; /* Base page shift of segment (or 0) */
+ __u32 slb_enc; /* SLB encoding for BookS */
+ struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
+#define KVM_PPC_1T_SEGMENTS 0x00000002
+#define KVM_PPC_NO_HASH 0x00000004
+
+struct kvm_ppc_smmu_info {
+ __u64 flags;
+ __u32 slb_size;
+ __u16 data_keys; /* # storage keys supported for data */
+ __u16 instr_keys; /* # storage keys supported for instructions */
+ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
+struct kvm_ppc_resize_hpt {
+ __u64 flags;
+ __u32 shift;
+ __u32 pad;
+};
+
#endif /* __LINUX_KVM_POWERPC_H */
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index abe926d..05eaf6d 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -12,7 +12,320 @@
#include <linux/types.h>
#define __KVM_S390
-#define __KVM_HAVE_GUEST_DEBUG
+
+struct kvm_s390_skeys {
+ __u64 start_gfn;
+ __u64 count;
+ __u64 skeydata_addr;
+ __u32 flags;
+ __u32 reserved[9];
+};
+
+#define KVM_S390_CMMA_PEEK (1 << 0)
+
+/**
+ * kvm_s390_cmma_log - Used for CMMA migration.
+ *
+ * Used both for input and output.
+ *
+ * @start_gfn: Guest page number to start from.
+ * @count: Size of the result buffer.
+ * @flags: Control operation mode via KVM_S390_CMMA_* flags
+ * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
+ * pages are still remaining.
+ * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
+ * in the PGSTE.
+ * @values: Pointer to the values buffer.
+ *
+ * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
+ */
+struct kvm_s390_cmma_log {
+ __u64 start_gfn;
+ __u32 count;
+ __u32 flags;
+ union {
+ __u64 remaining;
+ __u64 mask;
+ };
+ __u64 values;
+};
+
+#define KVM_S390_RESET_POR 1
+#define KVM_S390_RESET_CLEAR 2
+#define KVM_S390_RESET_SUBSYSTEM 4
+#define KVM_S390_RESET_CPU_INIT 8
+#define KVM_S390_RESET_IPL 16
+
+/* for KVM_S390_MEM_OP */
+struct kvm_s390_mem_op {
+ /* in */
+ __u64 gaddr; /* the guest address */
+ __u64 flags; /* flags */
+ __u32 size; /* amount of bytes */
+ __u32 op; /* type of operation */
+ __u64 buf; /* buffer in userspace */
+ union {
+ struct {
+ __u8 ar; /* the access register number */
+ __u8 key; /* access key, ignored if flag unset */
+ __u8 pad1[6]; /* ignored */
+ __u64 old_addr; /* ignored if cmpxchg flag unset */
+ };
+ __u32 sida_offset; /* offset into the sida */
+ __u8 reserved[32]; /* ignored */
+ };
+};
+/* types for kvm_s390_mem_op->op */
+#define KVM_S390_MEMOP_LOGICAL_READ 0
+#define KVM_S390_MEMOP_LOGICAL_WRITE 1
+#define KVM_S390_MEMOP_SIDA_READ 2
+#define KVM_S390_MEMOP_SIDA_WRITE 3
+#define KVM_S390_MEMOP_ABSOLUTE_READ 4
+#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5
+#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6
+
+/* flags for kvm_s390_mem_op->flags */
+#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
+#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
+#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2)
+
+/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */
+#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0)
+#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1)
+
+struct kvm_s390_psw {
+ __u64 mask;
+ __u64 addr;
+};
+
+/* valid values for type in kvm_s390_interrupt */
+#define KVM_S390_SIGP_STOP 0xfffe0000u
+#define KVM_S390_PROGRAM_INT 0xfffe0001u
+#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u
+#define KVM_S390_RESTART 0xfffe0003u
+#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u
+#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u
+#define KVM_S390_MCHK 0xfffe1000u
+#define KVM_S390_INT_CLOCK_COMP 0xffff1004u
+#define KVM_S390_INT_CPU_TIMER 0xffff1005u
+#define KVM_S390_INT_VIRTIO 0xffff2603u
+#define KVM_S390_INT_SERVICE 0xffff2401u
+#define KVM_S390_INT_EMERGENCY 0xffff1201u
+#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u
+/* Anything below 0xfffe0000u is taken by INT_IO */
+#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \
+ (((schid)) | \
+ ((ssid) << 16) | \
+ ((cssid) << 18) | \
+ ((ai) << 26))
+#define KVM_S390_INT_IO_MIN 0x00000000u
+#define KVM_S390_INT_IO_MAX 0xfffdffffu
+#define KVM_S390_INT_IO_AI_MASK 0x04000000u
+
+
+struct kvm_s390_interrupt {
+ __u32 type;
+ __u32 parm;
+ __u64 parm64;
+};
+
+struct kvm_s390_io_info {
+ __u16 subchannel_id;
+ __u16 subchannel_nr;
+ __u32 io_int_parm;
+ __u32 io_int_word;
+};
+
+struct kvm_s390_ext_info {
+ __u32 ext_params;
+ __u32 pad;
+ __u64 ext_params2;
+};
+
+struct kvm_s390_pgm_info {
+ __u64 trans_exc_code;
+ __u64 mon_code;
+ __u64 per_address;
+ __u32 data_exc_code;
+ __u16 code;
+ __u16 mon_class_nr;
+ __u8 per_code;
+ __u8 per_atmid;
+ __u8 exc_access_id;
+ __u8 per_access_id;
+ __u8 op_access_id;
+#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01
+#define KVM_S390_PGM_FLAGS_ILC_0 0x02
+#define KVM_S390_PGM_FLAGS_ILC_1 0x04
+#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06
+#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08
+ __u8 flags;
+ __u8 pad[2];
+};
+
+struct kvm_s390_prefix_info {
+ __u32 address;
+};
+
+struct kvm_s390_extcall_info {
+ __u16 code;
+};
+
+struct kvm_s390_emerg_info {
+ __u16 code;
+};
+
+#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01
+struct kvm_s390_stop_info {
+ __u32 flags;
+};
+
+struct kvm_s390_mchk_info {
+ __u64 cr14;
+ __u64 mcic;
+ __u64 failing_storage_address;
+ __u32 ext_damage_code;
+ __u32 pad;
+ __u8 fixed_logout[16];
+};
+
+struct kvm_s390_irq {
+ __u64 type;
+ union {
+ struct kvm_s390_io_info io;
+ struct kvm_s390_ext_info ext;
+ struct kvm_s390_pgm_info pgm;
+ struct kvm_s390_emerg_info emerg;
+ struct kvm_s390_extcall_info extcall;
+ struct kvm_s390_prefix_info prefix;
+ struct kvm_s390_stop_info stop;
+ struct kvm_s390_mchk_info mchk;
+ char reserved[64];
+ } u;
+};
+
+struct kvm_s390_irq_state {
+ __u64 buf;
+ __u32 flags; /* will stay unused for compatibility reasons */
+ __u32 len;
+ __u32 reserved[4]; /* will stay unused for compatibility reasons */
+};
+
+struct kvm_s390_ucas_mapping {
+ __u64 user_addr;
+ __u64 vcpu_addr;
+ __u64 length;
+};
+
+struct kvm_s390_pv_sec_parm {
+ __u64 origin;
+ __u64 length;
+};
+
+struct kvm_s390_pv_unp {
+ __u64 addr;
+ __u64 size;
+ __u64 tweak;
+};
+
+enum pv_cmd_dmp_id {
+ KVM_PV_DUMP_INIT,
+ KVM_PV_DUMP_CONFIG_STOR_STATE,
+ KVM_PV_DUMP_COMPLETE,
+ KVM_PV_DUMP_CPU,
+};
+
+struct kvm_s390_pv_dmp {
+ __u64 subcmd;
+ __u64 buff_addr;
+ __u64 buff_len;
+ __u64 gaddr; /* For dump storage state */
+ __u64 reserved[4];
+};
+
+enum pv_cmd_info_id {
+ KVM_PV_INFO_VM,
+ KVM_PV_INFO_DUMP,
+};
+
+struct kvm_s390_pv_info_dump {
+ __u64 dump_cpu_buffer_len;
+ __u64 dump_config_mem_buffer_per_1m;
+ __u64 dump_config_finalize_len;
+};
+
+struct kvm_s390_pv_info_vm {
+ __u64 inst_calls_list[4];
+ __u64 max_cpus;
+ __u64 max_guests;
+ __u64 max_guest_addr;
+ __u64 feature_indication;
+};
+
+struct kvm_s390_pv_info_header {
+ __u32 id;
+ __u32 len_max;
+ __u32 len_written;
+ __u32 reserved;
+};
+
+struct kvm_s390_pv_info {
+ struct kvm_s390_pv_info_header header;
+ union {
+ struct kvm_s390_pv_info_dump dump;
+ struct kvm_s390_pv_info_vm vm;
+ };
+};
+
+enum pv_cmd_id {
+ KVM_PV_ENABLE,
+ KVM_PV_DISABLE,
+ KVM_PV_SET_SEC_PARMS,
+ KVM_PV_UNPACK,
+ KVM_PV_VERIFY,
+ KVM_PV_PREP_RESET,
+ KVM_PV_UNSHARE_ALL,
+ KVM_PV_INFO,
+ KVM_PV_DUMP,
+ KVM_PV_ASYNC_CLEANUP_PREPARE,
+ KVM_PV_ASYNC_CLEANUP_PERFORM,
+};
+
+struct kvm_pv_cmd {
+ __u32 cmd; /* Command to be executed */
+ __u16 rc; /* Ultravisor return code */
+ __u16 rrc; /* Ultravisor return reason code */
+ __u64 data; /* Data or address */
+ __u32 flags; /* flags for future extensions. Must be 0 for now */
+ __u32 reserved[3];
+};
+
+struct kvm_s390_zpci_op {
+ /* in */
+ __u32 fh; /* target device */
+ __u8 op; /* operation to perform */
+ __u8 pad[3];
+ union {
+ /* for KVM_S390_ZPCIOP_REG_AEN */
+ struct {
+ __u64 ibv; /* Guest addr of interrupt bit vector */
+ __u64 sb; /* Guest addr of summary bit */
+ __u32 flags;
+ __u32 noi; /* Number of interrupts */
+ __u8 isc; /* Guest interrupt subclass */
+ __u8 sbo; /* Offset of guest summary bit vector */
+ __u16 pad;
+ } reg_aen;
+ __u64 reserved[8];
+ } u;
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_REG_AEN 0
+#define KVM_S390_ZPCIOP_DEREG_AEN 1
+
+/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
+#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0)
/* Device control API: s390-specific devices */
#define KVM_DEV_FLIC_GET_ALL_IRQS 1
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 25160d2..a38f8f9 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 21 /* N 32-bit words worth of info */
+#define NCAPINTS 22 /* N 32-bit words worth of info */
#define NBUGINTS 2 /* N 32-bit bug flags */
/*
@@ -81,10 +81,8 @@
#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-
-/* CPU types for specific tunings: */
#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */
-/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */
+#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */
#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */
#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */
#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
@@ -97,7 +95,7 @@
#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
-/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */
#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */
@@ -462,6 +460,14 @@
#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */
/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0x80000022, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
+
+/*
* BUG word(s)
*/
#define X86_BUG(x) (NCAPINTS*32 + (x))
@@ -508,4 +514,5 @@
/* BUG word 2 */
#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */
#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
+#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 1f23960..c492bdc 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -123,6 +123,12 @@
# define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31))
#endif
+#ifdef CONFIG_KVM_AMD_SEV
+#define DISABLE_SEV_SNP 0
+#else
+#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -147,8 +153,9 @@
DISABLE_ENQCMD)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 (DISABLE_IBT)
-#define DISABLED_MASK19 0
+#define DISABLED_MASK19 (DISABLE_SEV_SNP)
#define DISABLED_MASK20 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define DISABLED_MASK21 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h
index 3f73ac3..d18bfb2 100644
--- a/tools/arch/x86/include/asm/irq_vectors.h
+++ b/tools/arch/x86/include/asm/irq_vectors.h
@@ -84,11 +84,9 @@
#define HYPERVISOR_CALLBACK_VECTOR 0xf3
/* Vector for KVM to deliver posted interrupt IPI */
-#if IS_ENABLED(CONFIG_KVM)
#define POSTED_INTR_VECTOR 0xf2
#define POSTED_INTR_WAKEUP_VECTOR 0xf1
#define POSTED_INTR_NESTED_VECTOR 0xf0
-#endif
#define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 1f9dc9b..05956bd 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -176,6 +176,14 @@
* CPU is not vulnerable to Gather
* Data Sampling (GDS).
*/
+#define ARCH_CAP_RFDS_NO BIT(27) /*
+ * Not susceptible to Register
+ * File Data Sampling.
+ */
+#define ARCH_CAP_RFDS_CLEAR BIT(28) /*
+ * VERW clears CPU Register
+ * File.
+ */
#define ARCH_CAP_XAPIC_DISABLE BIT(21) /*
* IA32_XAPIC_DISABLE_STATUS MSR
@@ -605,34 +613,47 @@
#define MSR_AMD64_SEV_ES_GHCB 0xc0010130
#define MSR_AMD64_SEV 0xc0010131
#define MSR_AMD64_SEV_ENABLED_BIT 0
-#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
-#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2
#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+#define MSR_AMD64_SEV_ES_ENABLED_BIT 1
#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
+#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2
#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
-
-/* SNP feature bits enabled by the hypervisor */
-#define MSR_AMD64_SNP_VTOM BIT_ULL(3)
-#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4)
-#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5)
-#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6)
-#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7)
-#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8)
-#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9)
-#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10)
-#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11)
-#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12)
-#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14)
-#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16)
-#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17)
-
-/* SNP feature bits reserved for future use. */
-#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13)
-#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15)
-#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18)
+#define MSR_AMD64_SNP_VTOM_BIT 3
+#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT)
+#define MSR_AMD64_SNP_REFLECT_VC_BIT 4
+#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT)
+#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5
+#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT)
+#define MSR_AMD64_SNP_ALT_INJ_BIT 6
+#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT)
+#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7
+#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT)
+#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9
+#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT)
+#define MSR_AMD64_SNP_VMPL_SSS_BIT 10
+#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT)
+#define MSR_AMD64_SNP_SECURE_TSC_BIT 11
+#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12
+#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT)
+#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13)
+#define MSR_AMD64_SNP_IBS_VIRT_BIT 14
+#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT)
+#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15)
+#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16
+#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT)
+#define MSR_AMD64_SNP_SMT_PROT_BIT 17
+#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
+#define MSR_AMD64_SNP_RESV_BIT 18
+#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
+#define MSR_AMD64_RMP_BASE 0xc0010132
+#define MSR_AMD64_RMP_END 0xc0010133
+
/* AMD Collaborative Processor Performance Control MSRs */
#define MSR_AMD_CPPC_CAP1 0xc00102b0
#define MSR_AMD_CPPC_ENABLE 0xc00102b1
@@ -719,8 +740,15 @@
#define MSR_K8_TOP_MEM1 0xc001001a
#define MSR_K8_TOP_MEM2 0xc001001d
#define MSR_AMD64_SYSCFG 0xc0010010
-#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23
+#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23
#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24
+#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT)
+#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25
+#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT)
+#define MSR_AMD64_SYSCFG_MFDM_BIT 19
+#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT)
+
#define MSR_K8_INT_PENDING_MSG 0xc0010055
/* C1E active bits in int pending message */
#define K8_INTP_C1E_ACTIVE_MASK 0x18000000
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 7ba1726..e9187dd 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -99,6 +99,7 @@
#define REQUIRED_MASK18 0
#define REQUIRED_MASK19 0
#define REQUIRED_MASK20 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define REQUIRED_MASK21 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index a448d09..ef11aa4 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -7,6 +7,8 @@
*
*/
+#include <linux/const.h>
+#include <linux/bits.h>
#include <linux/types.h>
#include <linux/ioctl.h>
#include <linux/stddef.h>
@@ -40,7 +42,6 @@
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_MSI
#define __KVM_HAVE_USER_NMI
-#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_MSIX
#define __KVM_HAVE_MCE
#define __KVM_HAVE_PIT_STATE2
@@ -49,7 +50,6 @@
#define __KVM_HAVE_DEBUGREGS
#define __KVM_HAVE_XSAVE
#define __KVM_HAVE_XCRS
-#define __KVM_HAVE_READONLY_MEM
/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
@@ -526,9 +526,301 @@
#define KVM_PMU_EVENT_ALLOW 0
#define KVM_PMU_EVENT_DENY 1
-#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0)
+#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0)
#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS)
+/* for KVM_CAP_MCE */
+struct kvm_x86_mce {
+ __u64 status;
+ __u64 addr;
+ __u64 misc;
+ __u64 mcg_status;
+ __u8 bank;
+ __u8 pad1[7];
+ __u64 pad2[3];
+};
+
+/* for KVM_CAP_XEN_HVM */
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
+#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8)
+
+struct kvm_xen_hvm_config {
+ __u32 flags;
+ __u32 msr;
+ __u64 blob_addr_32;
+ __u64 blob_addr_64;
+ __u8 blob_size_32;
+ __u8 blob_size_64;
+ __u8 pad2[30];
+};
+
+struct kvm_xen_hvm_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u8 long_mode;
+ __u8 vector;
+ __u8 runstate_update_flag;
+ union {
+ __u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
+ __u64 hva;
+ } shared_info;
+ struct {
+ __u32 send_port;
+ __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+ __u32 flags;
+#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0)
+#define KVM_XEN_EVTCHN_UPDATE (1 << 1)
+#define KVM_XEN_EVTCHN_RESET (1 << 2)
+ /*
+ * Events sent by the guest are either looped back to
+ * the guest itself (potentially on a different port#)
+ * or signalled via an eventfd.
+ */
+ union {
+ struct {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+ } port;
+ struct {
+ __u32 port; /* Zero for eventfd */
+ __s32 fd;
+ } eventfd;
+ __u32 padding[4];
+ } deliver;
+ } evtchn;
+ __u32 xen_version;
+ __u64 pad[8];
+ } u;
+};
+
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3
+#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
+#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6
+
+struct kvm_xen_vcpu_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
+ __u64 hva;
+ __u64 pad[8];
+ struct {
+ __u64 state;
+ __u64 state_entry_time;
+ __u64 time_running;
+ __u64 time_runnable;
+ __u64 time_blocked;
+ __u64 time_offline;
+ } runstate;
+ __u32 vcpu_id;
+ struct {
+ __u32 port;
+ __u32 priority;
+ __u64 expires_ns;
+ } timer;
+ __u8 vector;
+ } u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6
+#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7
+#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+ /* Guest initialization commands */
+ KVM_SEV_INIT = 0,
+ KVM_SEV_ES_INIT,
+ /* Guest launch commands */
+ KVM_SEV_LAUNCH_START,
+ KVM_SEV_LAUNCH_UPDATE_DATA,
+ KVM_SEV_LAUNCH_UPDATE_VMSA,
+ KVM_SEV_LAUNCH_SECRET,
+ KVM_SEV_LAUNCH_MEASURE,
+ KVM_SEV_LAUNCH_FINISH,
+ /* Guest migration commands (outgoing) */
+ KVM_SEV_SEND_START,
+ KVM_SEV_SEND_UPDATE_DATA,
+ KVM_SEV_SEND_UPDATE_VMSA,
+ KVM_SEV_SEND_FINISH,
+ /* Guest migration commands (incoming) */
+ KVM_SEV_RECEIVE_START,
+ KVM_SEV_RECEIVE_UPDATE_DATA,
+ KVM_SEV_RECEIVE_UPDATE_VMSA,
+ KVM_SEV_RECEIVE_FINISH,
+ /* Guest status and debug commands */
+ KVM_SEV_GUEST_STATUS,
+ KVM_SEV_DBG_DECRYPT,
+ KVM_SEV_DBG_ENCRYPT,
+ /* Guest certificates commands */
+ KVM_SEV_CERT_EXPORT,
+ /* Attestation report */
+ KVM_SEV_GET_ATTESTATION_REPORT,
+ /* Guest Migration Extension */
+ KVM_SEV_SEND_CANCEL,
+
+ KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+ __u32 id;
+ __u32 pad0;
+ __u64 data;
+ __u32 error;
+ __u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 dh_uaddr;
+ __u32 dh_len;
+ __u32 pad0;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad1;
+};
+
+struct kvm_sev_launch_update_data {
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+
+struct kvm_sev_launch_secret {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+struct kvm_sev_launch_measure {
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_guest_status {
+ __u32 handle;
+ __u32 policy;
+ __u32 state;
+};
+
+struct kvm_sev_dbg {
+ __u64 src_uaddr;
+ __u64 dst_uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_attestation_report {
+ __u8 mnonce[16];
+ __u64 uaddr;
+ __u32 len;
+ __u32 pad0;
+};
+
+struct kvm_sev_send_start {
+ __u32 policy;
+ __u32 pad0;
+ __u64 pdh_cert_uaddr;
+ __u32 pdh_cert_len;
+ __u32 pad1;
+ __u64 plat_certs_uaddr;
+ __u32 plat_certs_len;
+ __u32 pad2;
+ __u64 amd_certs_uaddr;
+ __u32 amd_certs_len;
+ __u32 pad3;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad4;
+};
+
+struct kvm_sev_send_update_data {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+struct kvm_sev_receive_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 pdh_uaddr;
+ __u32 pdh_len;
+ __u32 pad0;
+ __u64 session_uaddr;
+ __u32 session_len;
+ __u32 pad1;
+};
+
+struct kvm_sev_receive_update_data {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u32 pad0;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u32 pad1;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+ __u32 pad2;
+};
+
+#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
+
+struct kvm_hyperv_eventfd {
+ __u32 conn_id;
+ __s32 fd;
+ __u32 flags;
+ __u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+
/*
* Masked event layout.
* Bits Description
@@ -549,10 +841,10 @@
((__u64)(!!(exclude)) << 55))
#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \
- (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32))
-#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56))
-#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8))
-#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55))
+ (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56))
+#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8))
+#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55))
#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56)
/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
@@ -560,7 +852,7 @@
#define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
/* x86-specific KVM_EXIT_HYPERCALL flags. */
-#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0)
+#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0)
#define KVM_X86_DEFAULT_VM 0
#define KVM_X86_SW_PROTECTED_VM 1
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 318e2da..ae57bf6 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -76,6 +76,12 @@
DNS
};
+enum {
+ IPV4 = 1,
+ IPV6,
+ IP_TYPE_MAX
+};
+
static int in_hand_shake;
static char *os_name = "";
@@ -102,6 +108,11 @@
#define MAX_FILE_NAME 100
#define ENTRIES_PER_BLOCK 50
+/*
+ * Change this entry if the number of addresses increases in future
+ */
+#define MAX_IP_ENTRIES 64
+#define OUTSTR_BUF_SIZE ((INET6_ADDRSTRLEN + 1) * MAX_IP_ENTRIES)
struct kvp_record {
char key[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
@@ -1171,6 +1182,18 @@
return 0;
}
+int ip_version_check(const char *input_addr)
+{
+ struct in6_addr addr;
+
+ if (inet_pton(AF_INET, input_addr, &addr))
+ return IPV4;
+ else if (inet_pton(AF_INET6, input_addr, &addr))
+ return IPV6;
+
+ return -EINVAL;
+}
+
/*
* Only IPv4 subnet strings needs to be converted to plen
* For IPv6 the subnet is already privided in plen format
@@ -1197,14 +1220,75 @@
return plen;
}
+static int process_dns_gateway_nm(FILE *f, char *ip_string, int type,
+ int ip_sec)
+{
+ char addr[INET6_ADDRSTRLEN], *output_str;
+ int ip_offset = 0, error = 0, ip_ver;
+ char *param_name;
+
+ if (type == DNS)
+ param_name = "dns";
+ else if (type == GATEWAY)
+ param_name = "gateway";
+ else
+ return -EINVAL;
+
+ output_str = (char *)calloc(OUTSTR_BUF_SIZE, sizeof(char));
+ if (!output_str)
+ return -ENOMEM;
+
+ while (1) {
+ memset(addr, 0, sizeof(addr));
+
+ if (!parse_ip_val_buffer(ip_string, &ip_offset, addr,
+ (MAX_IP_ADDR_SIZE * 2)))
+ break;
+
+ ip_ver = ip_version_check(addr);
+ if (ip_ver < 0)
+ continue;
+
+ if ((ip_ver == IPV4 && ip_sec == IPV4) ||
+ (ip_ver == IPV6 && ip_sec == IPV6)) {
+ /*
+ * do a bound check to avoid out-of bound writes
+ */
+ if ((OUTSTR_BUF_SIZE - strlen(output_str)) >
+ (strlen(addr) + 1)) {
+ strncat(output_str, addr,
+ OUTSTR_BUF_SIZE -
+ strlen(output_str) - 1);
+ strncat(output_str, ",",
+ OUTSTR_BUF_SIZE -
+ strlen(output_str) - 1);
+ }
+ } else {
+ continue;
+ }
+ }
+
+ if (strlen(output_str)) {
+ /*
+ * This is to get rid of that extra comma character
+ * in the end of the string
+ */
+ output_str[strlen(output_str) - 1] = '\0';
+ error = fprintf(f, "%s=%s\n", param_name, output_str);
+ }
+
+ free(output_str);
+ return error;
+}
+
static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet,
- int is_ipv6)
+ int ip_sec)
{
char addr[INET6_ADDRSTRLEN];
char subnet_addr[INET6_ADDRSTRLEN];
- int error, i = 0;
+ int error = 0, i = 0;
int ip_offset = 0, subnet_offset = 0;
- int plen;
+ int plen, ip_ver;
memset(addr, 0, sizeof(addr));
memset(subnet_addr, 0, sizeof(subnet_addr));
@@ -1216,10 +1300,16 @@
subnet_addr,
(MAX_IP_ADDR_SIZE *
2))) {
- if (!is_ipv6)
+ ip_ver = ip_version_check(addr);
+ if (ip_ver < 0)
+ continue;
+
+ if (ip_ver == IPV4 && ip_sec == IPV4)
plen = kvp_subnet_to_plen((char *)subnet_addr);
- else
+ else if (ip_ver == IPV6 && ip_sec == IPV6)
plen = atoi(subnet_addr);
+ else
+ continue;
if (plen < 0)
return plen;
@@ -1233,17 +1323,16 @@
memset(subnet_addr, 0, sizeof(subnet_addr));
}
- return 0;
+ return error;
}
static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
{
- int error = 0;
+ int error = 0, ip_ver;
char if_filename[PATH_MAX];
char nm_filename[PATH_MAX];
FILE *ifcfg_file, *nmfile;
char cmd[PATH_MAX];
- int is_ipv6 = 0;
char *mac_addr;
int str_len;
@@ -1421,52 +1510,94 @@
if (error)
goto setval_error;
- if (new_val->addr_family & ADDR_FAMILY_IPV6) {
- error = fprintf(nmfile, "\n[ipv6]\n");
- if (error < 0)
- goto setval_error;
- is_ipv6 = 1;
- } else {
- error = fprintf(nmfile, "\n[ipv4]\n");
- if (error < 0)
- goto setval_error;
- }
-
/*
* Now we populate the keyfile format
+ *
+ * The keyfile format expects the IPv6 and IPv4 configuration in
+ * different sections. Therefore we iterate through the list twice,
+ * once to populate the IPv4 section and the next time for IPv6
*/
+ ip_ver = IPV4;
+ do {
+ if (ip_ver == IPV4) {
+ error = fprintf(nmfile, "\n[ipv4]\n");
+ if (error < 0)
+ goto setval_error;
+ } else {
+ error = fprintf(nmfile, "\n[ipv6]\n");
+ if (error < 0)
+ goto setval_error;
+ }
- if (new_val->dhcp_enabled) {
- error = kvp_write_file(nmfile, "method", "", "auto");
+ /*
+ * Write the configuration for ipaddress, netmask, gateway and
+ * name services
+ */
+ error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr,
+ (char *)new_val->sub_net,
+ ip_ver);
if (error < 0)
goto setval_error;
- } else {
- error = kvp_write_file(nmfile, "method", "", "manual");
+
+ /*
+ * As dhcp_enabled is only valid for ipv4, we do not set dhcp
+ * methods for ipv6 based on dhcp_enabled flag.
+ *
+ * For ipv4, set method to manual only when dhcp_enabled is
+ * false and specific ipv4 addresses are configured. If neither
+ * dhcp_enabled is true and no ipv4 addresses are configured,
+ * set method to 'disabled'.
+ *
+ * For ipv6, set method to manual when we configure ipv6
+ * addresses. Otherwise set method to 'auto' so that SLAAC from
+ * RA may be used.
+ */
+ if (ip_ver == IPV4) {
+ if (new_val->dhcp_enabled) {
+ error = kvp_write_file(nmfile, "method", "",
+ "auto");
+ if (error < 0)
+ goto setval_error;
+ } else if (error) {
+ error = kvp_write_file(nmfile, "method", "",
+ "manual");
+ if (error < 0)
+ goto setval_error;
+ } else {
+ error = kvp_write_file(nmfile, "method", "",
+ "disabled");
+ if (error < 0)
+ goto setval_error;
+ }
+ } else if (ip_ver == IPV6) {
+ if (error) {
+ error = kvp_write_file(nmfile, "method", "",
+ "manual");
+ if (error < 0)
+ goto setval_error;
+ } else {
+ error = kvp_write_file(nmfile, "method", "",
+ "auto");
+ if (error < 0)
+ goto setval_error;
+ }
+ }
+
+ error = process_dns_gateway_nm(nmfile,
+ (char *)new_val->gate_way,
+ GATEWAY, ip_ver);
if (error < 0)
goto setval_error;
- }
- /*
- * Write the configuration for ipaddress, netmask, gateway and
- * name services
- */
- error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr,
- (char *)new_val->sub_net, is_ipv6);
- if (error < 0)
- goto setval_error;
-
- /* we do not want ipv4 addresses in ipv6 section and vice versa */
- if (is_ipv6 != is_ipv4((char *)new_val->gate_way)) {
- error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way);
+ error = process_dns_gateway_nm(nmfile,
+ (char *)new_val->dns_addr, DNS,
+ ip_ver);
if (error < 0)
goto setval_error;
- }
- if (is_ipv6 != is_ipv4((char *)new_val->dns_addr)) {
- error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr);
- if (error < 0)
- goto setval_error;
- }
+ ip_ver++;
+ } while (ip_ver < IP_TYPE_MAX);
+
fclose(nmfile);
fclose(ifcfg_file);
diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index 03f721a..54ccccf 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -5,12 +5,12 @@
#include <asm/types.h>
/**
- * __fls - find last (most-significant) set bit in a long word
+ * generic___fls - find last (most-significant) set bit in a long word
* @word: the word to search
*
* Undefined if no set bit exists, so code should check against 0 first.
*/
-static __always_inline unsigned long __fls(unsigned long word)
+static __always_inline unsigned long generic___fls(unsigned long word)
{
int num = BITS_PER_LONG - 1;
@@ -41,4 +41,8 @@
return num;
}
+#ifndef __HAVE_ARCH___FLS
+#define __fls(word) generic___fls(word)
+#endif
+
#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index b168bb1..26f3ce1 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -3,14 +3,14 @@
#define _ASM_GENERIC_BITOPS_FLS_H_
/**
- * fls - find last (most-significant) bit set
+ * generic_fls - find last (most-significant) bit set
* @x: the word to search
*
* This is defined the same way as ffs.
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
*/
-static __always_inline int fls(unsigned int x)
+static __always_inline int generic_fls(unsigned int x)
{
int r = 32;
@@ -39,4 +39,8 @@
return r;
}
+#ifndef __HAVE_ARCH_FLS
+#define fls(x) generic_fls(x)
+#endif
+
#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 4b0673bf..07cfad8 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -8,6 +8,7 @@
#include <linux/build_bug.h>
#include <linux/compiler.h>
#include <linux/math.h>
+#include <linux/panic.h>
#include <endian.h>
#include <byteswap.h>
diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h
index f3c82ab..7d73da0 100644
--- a/tools/include/linux/mm.h
+++ b/tools/include/linux/mm.h
@@ -37,4 +37,9 @@
{
}
+static inline int early_pfn_to_nid(unsigned long pfn)
+{
+ return 0;
+}
+
#endif
diff --git a/tools/include/linux/panic.h b/tools/include/linux/panic.h
new file mode 100644
index 0000000..9c8f17a
--- /dev/null
+++ b/tools/include/linux/panic.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_PANIC_H
+#define _TOOLS_LINUX_PANIC_H
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+static inline void panic(const char *fmt, ...)
+{
+ va_list argp;
+
+ va_start(argp, fmt);
+ vfprintf(stderr, fmt, argp);
+ va_end(argp);
+ exit(-1);
+}
+
+#endif
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index fd4f957..2ee3388 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -3013,6 +3013,7 @@
* - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions)
* - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`)
* - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info)
+ * - %DRM_I915_QUERY_GUC_SUBMISSION_VERSION (see struct drm_i915_query_guc_submission_version)
*/
__u64 query_id;
#define DRM_I915_QUERY_TOPOLOGY_INFO 1
@@ -3021,6 +3022,7 @@
#define DRM_I915_QUERY_MEMORY_REGIONS 4
#define DRM_I915_QUERY_HWCONFIG_BLOB 5
#define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6
+#define DRM_I915_QUERY_GUC_SUBMISSION_VERSION 7
/* Must be kept compact -- no holes and well documented */
/**
@@ -3567,6 +3569,20 @@
};
/**
+ * struct drm_i915_query_guc_submission_version - query GuC submission interface version
+ */
+struct drm_i915_query_guc_submission_version {
+ /** @branch: Firmware branch version. */
+ __u32 branch;
+ /** @major: Firmware major version. */
+ __u32 major;
+ /** @minor: Firmware minor version. */
+ __u32 minor;
+ /** @patch: Firmware patch version. */
+ __u32 patch;
+};
+
+/**
* DOC: GuC HWCONFIG blob uAPI
*
* The GuC produces a blob with information about the current device.
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 48ad69f..45e4e64 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -64,6 +64,24 @@
__u64 minlen;
};
+/*
+ * We include a length field because some filesystems (vfat) have an identifier
+ * that we do want to expose as a UUID, but doesn't have the standard length.
+ *
+ * We use a fixed size buffer beacuse this interface will, by fiat, never
+ * support "UUIDs" longer than 16 bytes; we don't want to force all downstream
+ * users to have to deal with that.
+ */
+struct fsuuid2 {
+ __u8 len;
+ __u8 uuid[16];
+};
+
+struct fs_sysfs_path {
+ __u8 len;
+ __u8 name[128];
+};
+
/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
#define FILE_DEDUPE_RANGE_SAME 0
#define FILE_DEDUPE_RANGE_DIFFERS 1
@@ -215,6 +233,13 @@
#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr)
#define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX])
#define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX])
+/* Returns the external filesystem UUID, the same one blkid returns */
+#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2)
+/*
+ * Returns the path component under /sys/fs/ that refers to this filesystem;
+ * also /sys/kernel/debug/ for filesystems with debugfs exports
+ */
+#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path)
/*
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
@@ -301,9 +326,12 @@
/* per-IO O_APPEND */
#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010)
+/* per-IO negation of O_APPEND */
+#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
- RWF_APPEND)
+ RWF_APPEND | RWF_NOAPPEND)
/* Pagemap ioctl */
#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index c330853..2190adb 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -16,6 +16,11 @@
#define KVM_API_VERSION 12
+/*
+ * Backwards-compatible definitions.
+ */
+#define __KVM_HAVE_GUEST_DEBUG
+
/* for KVM_SET_USER_MEMORY_REGION */
struct kvm_userspace_memory_region {
__u32 slot;
@@ -85,43 +90,6 @@
#define KVM_PIT_SPEAKER_DUMMY 1
-struct kvm_s390_skeys {
- __u64 start_gfn;
- __u64 count;
- __u64 skeydata_addr;
- __u32 flags;
- __u32 reserved[9];
-};
-
-#define KVM_S390_CMMA_PEEK (1 << 0)
-
-/**
- * kvm_s390_cmma_log - Used for CMMA migration.
- *
- * Used both for input and output.
- *
- * @start_gfn: Guest page number to start from.
- * @count: Size of the result buffer.
- * @flags: Control operation mode via KVM_S390_CMMA_* flags
- * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
- * pages are still remaining.
- * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
- * in the PGSTE.
- * @values: Pointer to the values buffer.
- *
- * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
- */
-struct kvm_s390_cmma_log {
- __u64 start_gfn;
- __u32 count;
- __u32 flags;
- union {
- __u64 remaining;
- __u64 mask;
- };
- __u64 values;
-};
-
struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
@@ -315,11 +283,6 @@
__u32 ipb;
} s390_sieic;
/* KVM_EXIT_S390_RESET */
-#define KVM_S390_RESET_POR 1
-#define KVM_S390_RESET_CLEAR 2
-#define KVM_S390_RESET_SUBSYSTEM 4
-#define KVM_S390_RESET_CPU_INIT 8
-#define KVM_S390_RESET_IPL 16
__u64 s390_reset_flags;
/* KVM_EXIT_S390_UCONTROL */
struct {
@@ -536,43 +499,6 @@
__u8 pad[5];
};
-/* for KVM_S390_MEM_OP */
-struct kvm_s390_mem_op {
- /* in */
- __u64 gaddr; /* the guest address */
- __u64 flags; /* flags */
- __u32 size; /* amount of bytes */
- __u32 op; /* type of operation */
- __u64 buf; /* buffer in userspace */
- union {
- struct {
- __u8 ar; /* the access register number */
- __u8 key; /* access key, ignored if flag unset */
- __u8 pad1[6]; /* ignored */
- __u64 old_addr; /* ignored if cmpxchg flag unset */
- };
- __u32 sida_offset; /* offset into the sida */
- __u8 reserved[32]; /* ignored */
- };
-};
-/* types for kvm_s390_mem_op->op */
-#define KVM_S390_MEMOP_LOGICAL_READ 0
-#define KVM_S390_MEMOP_LOGICAL_WRITE 1
-#define KVM_S390_MEMOP_SIDA_READ 2
-#define KVM_S390_MEMOP_SIDA_WRITE 3
-#define KVM_S390_MEMOP_ABSOLUTE_READ 4
-#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5
-#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6
-
-/* flags for kvm_s390_mem_op->flags */
-#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
-#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
-#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2)
-
-/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */
-#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0)
-#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1)
-
/* for KVM_INTERRUPT */
struct kvm_interrupt {
/* in */
@@ -637,124 +563,6 @@
__u32 mp_state;
};
-struct kvm_s390_psw {
- __u64 mask;
- __u64 addr;
-};
-
-/* valid values for type in kvm_s390_interrupt */
-#define KVM_S390_SIGP_STOP 0xfffe0000u
-#define KVM_S390_PROGRAM_INT 0xfffe0001u
-#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u
-#define KVM_S390_RESTART 0xfffe0003u
-#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u
-#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u
-#define KVM_S390_MCHK 0xfffe1000u
-#define KVM_S390_INT_CLOCK_COMP 0xffff1004u
-#define KVM_S390_INT_CPU_TIMER 0xffff1005u
-#define KVM_S390_INT_VIRTIO 0xffff2603u
-#define KVM_S390_INT_SERVICE 0xffff2401u
-#define KVM_S390_INT_EMERGENCY 0xffff1201u
-#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u
-/* Anything below 0xfffe0000u is taken by INT_IO */
-#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \
- (((schid)) | \
- ((ssid) << 16) | \
- ((cssid) << 18) | \
- ((ai) << 26))
-#define KVM_S390_INT_IO_MIN 0x00000000u
-#define KVM_S390_INT_IO_MAX 0xfffdffffu
-#define KVM_S390_INT_IO_AI_MASK 0x04000000u
-
-
-struct kvm_s390_interrupt {
- __u32 type;
- __u32 parm;
- __u64 parm64;
-};
-
-struct kvm_s390_io_info {
- __u16 subchannel_id;
- __u16 subchannel_nr;
- __u32 io_int_parm;
- __u32 io_int_word;
-};
-
-struct kvm_s390_ext_info {
- __u32 ext_params;
- __u32 pad;
- __u64 ext_params2;
-};
-
-struct kvm_s390_pgm_info {
- __u64 trans_exc_code;
- __u64 mon_code;
- __u64 per_address;
- __u32 data_exc_code;
- __u16 code;
- __u16 mon_class_nr;
- __u8 per_code;
- __u8 per_atmid;
- __u8 exc_access_id;
- __u8 per_access_id;
- __u8 op_access_id;
-#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01
-#define KVM_S390_PGM_FLAGS_ILC_0 0x02
-#define KVM_S390_PGM_FLAGS_ILC_1 0x04
-#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06
-#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08
- __u8 flags;
- __u8 pad[2];
-};
-
-struct kvm_s390_prefix_info {
- __u32 address;
-};
-
-struct kvm_s390_extcall_info {
- __u16 code;
-};
-
-struct kvm_s390_emerg_info {
- __u16 code;
-};
-
-#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01
-struct kvm_s390_stop_info {
- __u32 flags;
-};
-
-struct kvm_s390_mchk_info {
- __u64 cr14;
- __u64 mcic;
- __u64 failing_storage_address;
- __u32 ext_damage_code;
- __u32 pad;
- __u8 fixed_logout[16];
-};
-
-struct kvm_s390_irq {
- __u64 type;
- union {
- struct kvm_s390_io_info io;
- struct kvm_s390_ext_info ext;
- struct kvm_s390_pgm_info pgm;
- struct kvm_s390_emerg_info emerg;
- struct kvm_s390_extcall_info extcall;
- struct kvm_s390_prefix_info prefix;
- struct kvm_s390_stop_info stop;
- struct kvm_s390_mchk_info mchk;
- char reserved[64];
- } u;
-};
-
-struct kvm_s390_irq_state {
- __u64 buf;
- __u32 flags; /* will stay unused for compatibility reasons */
- __u32 len;
- __u32 reserved[4]; /* will stay unused for compatibility reasons */
-};
-
/* for KVM_SET_GUEST_DEBUG */
#define KVM_GUESTDBG_ENABLE 0x00000001
@@ -810,50 +618,6 @@
__u8 pad[64];
};
-/* for KVM_PPC_GET_PVINFO */
-
-#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
-
-struct kvm_ppc_pvinfo {
- /* out */
- __u32 flags;
- __u32 hcall[4];
- __u8 pad[108];
-};
-
-/* for KVM_PPC_GET_SMMU_INFO */
-#define KVM_PPC_PAGE_SIZES_MAX_SZ 8
-
-struct kvm_ppc_one_page_size {
- __u32 page_shift; /* Page shift (or 0) */
- __u32 pte_enc; /* Encoding in the HPTE (>>12) */
-};
-
-struct kvm_ppc_one_seg_page_size {
- __u32 page_shift; /* Base page shift of segment (or 0) */
- __u32 slb_enc; /* SLB encoding for BookS */
- struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
-};
-
-#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
-#define KVM_PPC_1T_SEGMENTS 0x00000002
-#define KVM_PPC_NO_HASH 0x00000004
-
-struct kvm_ppc_smmu_info {
- __u64 flags;
- __u32 slb_size;
- __u16 data_keys; /* # storage keys supported for data */
- __u16 instr_keys; /* # storage keys supported for instructions */
- struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
-};
-
-/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
-struct kvm_ppc_resize_hpt {
- __u64 flags;
- __u32 shift;
- __u32 pad;
-};
-
#define KVMIO 0xAE
/* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -923,9 +687,7 @@
/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
#define KVM_CAP_USER_NMI 22
-#ifdef __KVM_HAVE_GUEST_DEBUG
#define KVM_CAP_SET_GUEST_DEBUG 23
-#endif
#ifdef __KVM_HAVE_PIT
#define KVM_CAP_REINJECT_CONTROL 24
#endif
@@ -1156,8 +918,6 @@
#define KVM_CAP_GUEST_MEMFD 234
#define KVM_CAP_VM_TYPES 235
-#ifdef KVM_CAP_IRQ_ROUTING
-
struct kvm_irq_routing_irqchip {
__u32 irqchip;
__u32 pin;
@@ -1222,42 +982,6 @@
struct kvm_irq_routing_entry entries[];
};
-#endif
-
-#ifdef KVM_CAP_MCE
-/* x86 MCE */
-struct kvm_x86_mce {
- __u64 status;
- __u64 addr;
- __u64 misc;
- __u64 mcg_status;
- __u8 bank;
- __u8 pad1[7];
- __u64 pad2[3];
-};
-#endif
-
-#ifdef KVM_CAP_XEN_HVM
-#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
-#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
-#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
-#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
-#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
-#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
-#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6)
-#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7)
-
-struct kvm_xen_hvm_config {
- __u32 flags;
- __u32 msr;
- __u64 blob_addr_32;
- __u64 blob_addr_64;
- __u8 blob_size_32;
- __u8 blob_size_64;
- __u8 pad2[30];
-};
-#endif
-
#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
/*
* Available with KVM_CAP_IRQFD_RESAMPLE
@@ -1442,11 +1166,6 @@
struct kvm_userspace_memory_region2)
/* enable ucontrol for s390 */
-struct kvm_s390_ucas_mapping {
- __u64 user_addr;
- __u64 vcpu_addr;
- __u64 length;
-};
#define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
#define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
#define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long)
@@ -1641,89 +1360,6 @@
#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3)
#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4)
-struct kvm_s390_pv_sec_parm {
- __u64 origin;
- __u64 length;
-};
-
-struct kvm_s390_pv_unp {
- __u64 addr;
- __u64 size;
- __u64 tweak;
-};
-
-enum pv_cmd_dmp_id {
- KVM_PV_DUMP_INIT,
- KVM_PV_DUMP_CONFIG_STOR_STATE,
- KVM_PV_DUMP_COMPLETE,
- KVM_PV_DUMP_CPU,
-};
-
-struct kvm_s390_pv_dmp {
- __u64 subcmd;
- __u64 buff_addr;
- __u64 buff_len;
- __u64 gaddr; /* For dump storage state */
- __u64 reserved[4];
-};
-
-enum pv_cmd_info_id {
- KVM_PV_INFO_VM,
- KVM_PV_INFO_DUMP,
-};
-
-struct kvm_s390_pv_info_dump {
- __u64 dump_cpu_buffer_len;
- __u64 dump_config_mem_buffer_per_1m;
- __u64 dump_config_finalize_len;
-};
-
-struct kvm_s390_pv_info_vm {
- __u64 inst_calls_list[4];
- __u64 max_cpus;
- __u64 max_guests;
- __u64 max_guest_addr;
- __u64 feature_indication;
-};
-
-struct kvm_s390_pv_info_header {
- __u32 id;
- __u32 len_max;
- __u32 len_written;
- __u32 reserved;
-};
-
-struct kvm_s390_pv_info {
- struct kvm_s390_pv_info_header header;
- union {
- struct kvm_s390_pv_info_dump dump;
- struct kvm_s390_pv_info_vm vm;
- };
-};
-
-enum pv_cmd_id {
- KVM_PV_ENABLE,
- KVM_PV_DISABLE,
- KVM_PV_SET_SEC_PARMS,
- KVM_PV_UNPACK,
- KVM_PV_VERIFY,
- KVM_PV_PREP_RESET,
- KVM_PV_UNSHARE_ALL,
- KVM_PV_INFO,
- KVM_PV_DUMP,
- KVM_PV_ASYNC_CLEANUP_PREPARE,
- KVM_PV_ASYNC_CLEANUP_PERFORM,
-};
-
-struct kvm_pv_cmd {
- __u32 cmd; /* Command to be executed */
- __u16 rc; /* Ultravisor return code */
- __u16 rrc; /* Ultravisor return reason code */
- __u64 data; /* Data or address */
- __u32 flags; /* flags for future extensions. Must be 0 for now */
- __u32 reserved[3];
-};
-
/* Available with KVM_CAP_S390_PROTECTED */
#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
@@ -1737,58 +1373,6 @@
#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr)
#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr)
-struct kvm_xen_hvm_attr {
- __u16 type;
- __u16 pad[3];
- union {
- __u8 long_mode;
- __u8 vector;
- __u8 runstate_update_flag;
- struct {
- __u64 gfn;
-#define KVM_XEN_INVALID_GFN ((__u64)-1)
- } shared_info;
- struct {
- __u32 send_port;
- __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
- __u32 flags;
-#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0)
-#define KVM_XEN_EVTCHN_UPDATE (1 << 1)
-#define KVM_XEN_EVTCHN_RESET (1 << 2)
- /*
- * Events sent by the guest are either looped back to
- * the guest itself (potentially on a different port#)
- * or signalled via an eventfd.
- */
- union {
- struct {
- __u32 port;
- __u32 vcpu;
- __u32 priority;
- } port;
- struct {
- __u32 port; /* Zero for eventfd */
- __s32 fd;
- } eventfd;
- __u32 padding[4];
- } deliver;
- } evtchn;
- __u32 xen_version;
- __u64 pad[8];
- } u;
-};
-
-
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
-#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
-#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
-#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
-#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3
-#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */
-#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5
-
/* Per-vCPU Xen attributes */
#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr)
@@ -1799,242 +1383,6 @@
#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2)
#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2)
-struct kvm_xen_vcpu_attr {
- __u16 type;
- __u16 pad[3];
- union {
- __u64 gpa;
-#define KVM_XEN_INVALID_GPA ((__u64)-1)
- __u64 pad[8];
- struct {
- __u64 state;
- __u64 state_entry_time;
- __u64 time_running;
- __u64 time_runnable;
- __u64 time_blocked;
- __u64 time_offline;
- } runstate;
- __u32 vcpu_id;
- struct {
- __u32 port;
- __u32 priority;
- __u64 expires_ns;
- } timer;
- __u8 vector;
- } u;
-};
-
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
-#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0
-#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1
-#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2
-#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3
-#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4
-#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5
-/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */
-#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6
-#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7
-#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8
-
-/* Secure Encrypted Virtualization command */
-enum sev_cmd_id {
- /* Guest initialization commands */
- KVM_SEV_INIT = 0,
- KVM_SEV_ES_INIT,
- /* Guest launch commands */
- KVM_SEV_LAUNCH_START,
- KVM_SEV_LAUNCH_UPDATE_DATA,
- KVM_SEV_LAUNCH_UPDATE_VMSA,
- KVM_SEV_LAUNCH_SECRET,
- KVM_SEV_LAUNCH_MEASURE,
- KVM_SEV_LAUNCH_FINISH,
- /* Guest migration commands (outgoing) */
- KVM_SEV_SEND_START,
- KVM_SEV_SEND_UPDATE_DATA,
- KVM_SEV_SEND_UPDATE_VMSA,
- KVM_SEV_SEND_FINISH,
- /* Guest migration commands (incoming) */
- KVM_SEV_RECEIVE_START,
- KVM_SEV_RECEIVE_UPDATE_DATA,
- KVM_SEV_RECEIVE_UPDATE_VMSA,
- KVM_SEV_RECEIVE_FINISH,
- /* Guest status and debug commands */
- KVM_SEV_GUEST_STATUS,
- KVM_SEV_DBG_DECRYPT,
- KVM_SEV_DBG_ENCRYPT,
- /* Guest certificates commands */
- KVM_SEV_CERT_EXPORT,
- /* Attestation report */
- KVM_SEV_GET_ATTESTATION_REPORT,
- /* Guest Migration Extension */
- KVM_SEV_SEND_CANCEL,
-
- KVM_SEV_NR_MAX,
-};
-
-struct kvm_sev_cmd {
- __u32 id;
- __u64 data;
- __u32 error;
- __u32 sev_fd;
-};
-
-struct kvm_sev_launch_start {
- __u32 handle;
- __u32 policy;
- __u64 dh_uaddr;
- __u32 dh_len;
- __u64 session_uaddr;
- __u32 session_len;
-};
-
-struct kvm_sev_launch_update_data {
- __u64 uaddr;
- __u32 len;
-};
-
-
-struct kvm_sev_launch_secret {
- __u64 hdr_uaddr;
- __u32 hdr_len;
- __u64 guest_uaddr;
- __u32 guest_len;
- __u64 trans_uaddr;
- __u32 trans_len;
-};
-
-struct kvm_sev_launch_measure {
- __u64 uaddr;
- __u32 len;
-};
-
-struct kvm_sev_guest_status {
- __u32 handle;
- __u32 policy;
- __u32 state;
-};
-
-struct kvm_sev_dbg {
- __u64 src_uaddr;
- __u64 dst_uaddr;
- __u32 len;
-};
-
-struct kvm_sev_attestation_report {
- __u8 mnonce[16];
- __u64 uaddr;
- __u32 len;
-};
-
-struct kvm_sev_send_start {
- __u32 policy;
- __u64 pdh_cert_uaddr;
- __u32 pdh_cert_len;
- __u64 plat_certs_uaddr;
- __u32 plat_certs_len;
- __u64 amd_certs_uaddr;
- __u32 amd_certs_len;
- __u64 session_uaddr;
- __u32 session_len;
-};
-
-struct kvm_sev_send_update_data {
- __u64 hdr_uaddr;
- __u32 hdr_len;
- __u64 guest_uaddr;
- __u32 guest_len;
- __u64 trans_uaddr;
- __u32 trans_len;
-};
-
-struct kvm_sev_receive_start {
- __u32 handle;
- __u32 policy;
- __u64 pdh_uaddr;
- __u32 pdh_len;
- __u64 session_uaddr;
- __u32 session_len;
-};
-
-struct kvm_sev_receive_update_data {
- __u64 hdr_uaddr;
- __u32 hdr_len;
- __u64 guest_uaddr;
- __u32 guest_len;
- __u64 trans_uaddr;
- __u32 trans_len;
-};
-
-#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
-#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
-#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2)
-
-struct kvm_assigned_pci_dev {
- __u32 assigned_dev_id;
- __u32 busnr;
- __u32 devfn;
- __u32 flags;
- __u32 segnr;
- union {
- __u32 reserved[11];
- };
-};
-
-#define KVM_DEV_IRQ_HOST_INTX (1 << 0)
-#define KVM_DEV_IRQ_HOST_MSI (1 << 1)
-#define KVM_DEV_IRQ_HOST_MSIX (1 << 2)
-
-#define KVM_DEV_IRQ_GUEST_INTX (1 << 8)
-#define KVM_DEV_IRQ_GUEST_MSI (1 << 9)
-#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10)
-
-#define KVM_DEV_IRQ_HOST_MASK 0x00ff
-#define KVM_DEV_IRQ_GUEST_MASK 0xff00
-
-struct kvm_assigned_irq {
- __u32 assigned_dev_id;
- __u32 host_irq; /* ignored (legacy field) */
- __u32 guest_irq;
- __u32 flags;
- union {
- __u32 reserved[12];
- };
-};
-
-struct kvm_assigned_msix_nr {
- __u32 assigned_dev_id;
- __u16 entry_nr;
- __u16 padding;
-};
-
-#define KVM_MAX_MSIX_PER_DEV 256
-struct kvm_assigned_msix_entry {
- __u32 assigned_dev_id;
- __u32 gsi;
- __u16 entry; /* The index of entry in the MSI-X table */
- __u16 padding[3];
-};
-
-#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
-#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
-
-/* Available with KVM_CAP_ARM_USER_IRQ */
-
-/* Bits for run->s.regs.device_irq_level */
-#define KVM_ARM_DEV_EL1_VTIMER (1 << 0)
-#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
-#define KVM_ARM_DEV_PMU (1 << 2)
-
-struct kvm_hyperv_eventfd {
- __u32 conn_id;
- __s32 fd;
- __u32 flags;
- __u32 padding[3];
-};
-
-#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
-#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
-
#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1)
@@ -2180,33 +1528,6 @@
/* Available with KVM_CAP_S390_ZPCI_OP */
#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op)
-struct kvm_s390_zpci_op {
- /* in */
- __u32 fh; /* target device */
- __u8 op; /* operation to perform */
- __u8 pad[3];
- union {
- /* for KVM_S390_ZPCIOP_REG_AEN */
- struct {
- __u64 ibv; /* Guest addr of interrupt bit vector */
- __u64 sb; /* Guest addr of summary bit */
- __u32 flags;
- __u32 noi; /* Number of interrupts */
- __u8 isc; /* Guest interrupt subclass */
- __u8 sbo; /* Offset of guest summary bit vector */
- __u16 pad;
- } reg_aen;
- __u64 reserved[8];
- } u;
-};
-
-/* types for kvm_s390_zpci_op->op */
-#define KVM_S390_ZPCIOP_REG_AEN 0
-#define KVM_S390_ZPCIOP_DEREG_AEN 1
-
-/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
-#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0)
-
/* Available with KVM_CAP_MEMORY_ATTRIBUTES */
#define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes)
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index d5b9cfb..628d46a 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -142,7 +142,7 @@
* *
*****************************************************************************/
-#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16)
+#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17)
typedef unsigned long snd_pcm_uframes_t;
typedef signed long snd_pcm_sframes_t;
@@ -416,7 +416,7 @@
unsigned int rmask; /* W: requested masks */
unsigned int cmask; /* R: changed masks */
unsigned int info; /* R: Info flags for returned setup */
- unsigned int msbits; /* R: used most significant bits */
+ unsigned int msbits; /* R: used most significant bits (in sample bit-width) */
unsigned int rate_num; /* R: rate numerator */
unsigned int rate_den; /* R: rate denominator */
snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 5fa7957..25810e1 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -182,6 +182,7 @@
self.done = 1
extack_off = 20
elif self.nl_type == Netlink.NLMSG_DONE:
+ self.error = struct.unpack("i", self.raw[0:4])[0]
self.done = 1
extack_off = 4
diff --git a/tools/perf/arch/riscv/util/header.c b/tools/perf/arch/riscv/util/header.c
index 4a41856..1b29030 100644
--- a/tools/perf/arch/riscv/util/header.c
+++ b/tools/perf/arch/riscv/util/header.c
@@ -41,7 +41,7 @@
char *mimpid = NULL;
char *cpuid = NULL;
int read;
- unsigned long line_sz;
+ size_t line_sz;
FILE *cpuinfo;
cpuinfo = fopen(CPUINFO, "r");
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ec5e219..4790c73 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -970,7 +970,7 @@
if (dso->annotate_warned)
return -1;
- if (not_annotated) {
+ if (not_annotated || !sym->annotate2) {
err = symbol__annotate2(ms, evsel, &browser.arch);
if (err) {
char msg[BUFSIZ];
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac002d9..50ca922 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2461,6 +2461,9 @@
if (parch)
*parch = arch;
+ if (!list_empty(¬es->src->source))
+ return 0;
+
args.arch = arch;
args.ms = *ms;
if (annotate_opts.full_addr)
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index fb54bd3..d931a89 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -284,6 +284,7 @@
struct task_struct *curr;
struct mm_struct___old *mm_old;
struct mm_struct___new *mm_new;
+ struct sighand_struct *sighand;
switch (flags) {
case LCB_F_READ: /* rwsem */
@@ -305,7 +306,9 @@
break;
case LCB_F_SPIN: /* spinlock */
curr = bpf_get_current_task_btf();
- if (&curr->sighand->siglock == (void *)lock)
+ sighand = curr->sighand;
+
+ if (sighand && &sighand->siglock == (void *)lock)
return LCD_F_SIGHAND_LOCK;
break;
default:
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 8f08c3f..0d3672e 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -67,6 +67,10 @@
.PP
\fB--quiet\fP Do not decode and print the system configuration header information.
.PP
++\fB--no-msr\fP Disable all the uses of the MSR driver.
++.PP
++\fB--no-perf\fP Disable all the uses of the perf API.
++.PP
\fB--interval seconds\fP overrides the default 5.0 second measurement interval.
.PP
\fB--num_iterations num\fP number of the measurement iterations.
@@ -125,9 +129,17 @@
.PP
\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
.PP
-\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
+\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms or /sys/class/drm/card0/gt/gt0/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used.
.PP
-\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
+\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used.
+.PP
+\fBGFXAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used.
+.PP
+\fBSAM%mc6\fP The percentage of time the SA Media is in the "module C6" state, mc6, during the measurement interval. From /sys/class/drm/card0/gt/gt1/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used.
+.PP
+\fBSAMMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used.
+.PP
+\fBSAMAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used.
.PP
\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters.
.PP
@@ -370,7 +382,7 @@
Busy% = MPERF_delta/TSC_delta
-Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval
+Bzy_MHz = TSC_delta*APERF_delta/MPERF_delta/measurement_interval
Note that these calculations depend on TSC_delta, so they
are not reliable during intervals when TSC_MHz is not running at the base frequency.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 7a33437..9825646 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3,7 +3,7 @@
* turbostat -- show CPU frequency and C-state residency
* on modern Intel and AMD processors.
*
- * Copyright (c) 2023 Intel Corporation.
+ * Copyright (c) 2024 Intel Corporation.
* Len Brown <len.brown@intel.com>
*/
@@ -36,6 +36,8 @@
#include <linux/perf_event.h>
#include <asm/unistd.h>
#include <stdbool.h>
+#include <assert.h>
+#include <linux/kernel.h>
#define UNUSED(x) (void)(x)
@@ -53,9 +55,13 @@
#define NAME_BYTES 20
#define PATH_BYTES 128
+#define MAX_NOFILE 0x8000
+
enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC };
enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT };
+enum amperf_source { AMPERF_SOURCE_PERF, AMPERF_SOURCE_MSR };
+enum rapl_source { RAPL_SOURCE_NONE, RAPL_SOURCE_PERF, RAPL_SOURCE_MSR };
struct msr_counter {
unsigned int msr_num;
@@ -127,6 +133,9 @@
{ 0x0, "IPC", "", 0, 0, 0, NULL, 0 },
{ 0x0, "CoreThr", "", 0, 0, 0, NULL, 0 },
{ 0x0, "UncMHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAM%mc6", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAMMHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAMAMHz", "", 0, 0, 0, NULL, 0 },
};
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -185,11 +194,14 @@
#define BIC_IPC (1ULL << 52)
#define BIC_CORE_THROT_CNT (1ULL << 53)
#define BIC_UNCORE_MHZ (1ULL << 54)
+#define BIC_SAM_mc6 (1ULL << 55)
+#define BIC_SAMMHz (1ULL << 56)
+#define BIC_SAMACTMHz (1ULL << 57)
#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die )
#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__)
-#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_UNCORE_MHZ)
-#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX)
+#define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ)
+#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6)
#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
@@ -204,10 +216,13 @@
#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT)
+struct amperf_group_fd;
+
char *proc_stat = "/proc/stat";
FILE *outf;
int *fd_percpu;
int *fd_instr_count_percpu;
+struct amperf_group_fd *fd_amperf_percpu; /* File descriptors for perf group with APERF and MPERF counters. */
struct timeval interval_tv = { 5, 0 };
struct timespec interval_ts = { 5, 0 };
@@ -242,11 +257,8 @@
unsigned int do_dts;
unsigned int do_ptm;
unsigned int do_ipc;
-unsigned long long gfx_cur_rc6_ms;
unsigned long long cpuidle_cur_cpu_lpi_us;
unsigned long long cpuidle_cur_sys_lpi_us;
-unsigned int gfx_cur_mhz;
-unsigned int gfx_act_mhz;
unsigned int tj_max;
unsigned int tj_max_override;
double rapl_power_units, rapl_time_units;
@@ -263,6 +275,28 @@
unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */
unsigned int first_counter_read = 1;
int ignore_stdin;
+bool no_msr;
+bool no_perf;
+enum amperf_source amperf_source;
+
+enum gfx_sysfs_idx {
+ GFX_rc6,
+ GFX_MHz,
+ GFX_ACTMHz,
+ SAM_mc6,
+ SAM_MHz,
+ SAM_ACTMHz,
+ GFX_MAX
+};
+
+struct gfx_sysfs_info {
+ const char *path;
+ FILE *fp;
+ unsigned int val;
+ unsigned long long val_ull;
+};
+
+static struct gfx_sysfs_info gfx_info[GFX_MAX];
int get_msr(int cpu, off_t offset, unsigned long long *msr);
@@ -652,6 +686,7 @@
.bclk_freq = BCLK_100MHZ,
.supported_cstates = CC1 | CC6 | PC2 | PC6,
.cst_limit = CST_LIMIT_ICX,
+ .has_msr_core_c1_res = 1,
.has_irtl_msrs = 1,
.has_cst_prewake_bit = 1,
.trl_msrs = TRL_BASE | TRL_CORECOUNT,
@@ -948,6 +983,175 @@
#define MAX_ADDED_THREAD_COUNTERS 24
#define BITMASK_SIZE 32
+/* Indexes used to map data read from perf and MSRs into global variables */
+enum rapl_rci_index {
+ RAPL_RCI_INDEX_ENERGY_PKG = 0,
+ RAPL_RCI_INDEX_ENERGY_CORES = 1,
+ RAPL_RCI_INDEX_DRAM = 2,
+ RAPL_RCI_INDEX_GFX = 3,
+ RAPL_RCI_INDEX_PKG_PERF_STATUS = 4,
+ RAPL_RCI_INDEX_DRAM_PERF_STATUS = 5,
+ RAPL_RCI_INDEX_CORE_ENERGY = 6,
+ NUM_RAPL_COUNTERS,
+};
+
+enum rapl_unit {
+ RAPL_UNIT_INVALID,
+ RAPL_UNIT_JOULES,
+ RAPL_UNIT_WATTS,
+};
+
+struct rapl_counter_info_t {
+ unsigned long long data[NUM_RAPL_COUNTERS];
+ enum rapl_source source[NUM_RAPL_COUNTERS];
+ unsigned long long flags[NUM_RAPL_COUNTERS];
+ double scale[NUM_RAPL_COUNTERS];
+ enum rapl_unit unit[NUM_RAPL_COUNTERS];
+
+ union {
+ /* Active when source == RAPL_SOURCE_MSR */
+ struct {
+ unsigned long long msr[NUM_RAPL_COUNTERS];
+ unsigned long long msr_mask[NUM_RAPL_COUNTERS];
+ int msr_shift[NUM_RAPL_COUNTERS];
+ };
+ };
+
+ int fd_perf;
+};
+
+/* struct rapl_counter_info_t for each RAPL domain */
+struct rapl_counter_info_t *rapl_counter_info_perdomain;
+
+#define RAPL_COUNTER_FLAG_USE_MSR_SUM (1u << 1)
+
+struct rapl_counter_arch_info {
+ int feature_mask; /* Mask for testing if the counter is supported on host */
+ const char *perf_subsys;
+ const char *perf_name;
+ unsigned long long msr;
+ unsigned long long msr_mask;
+ int msr_shift; /* Positive mean shift right, negative mean shift left */
+ double *platform_rapl_msr_scale; /* Scale applied to values read by MSR (platform dependent, filled at runtime) */
+ unsigned int rci_index; /* Maps data from perf counters to global variables */
+ unsigned long long bic;
+ double compat_scale; /* Some counters require constant scaling to be in the same range as other, similar ones */
+ unsigned long long flags;
+};
+
+static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = {
+ {
+ .feature_mask = RAPL_PKG,
+ .perf_subsys = "power",
+ .perf_name = "energy-pkg",
+ .msr = MSR_PKG_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_PKG,
+ .bic = BIC_PkgWatt | BIC_Pkg_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_AMD_F17H,
+ .perf_subsys = "power",
+ .perf_name = "energy-pkg",
+ .msr = MSR_PKG_ENERGY_STAT,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_PKG,
+ .bic = BIC_PkgWatt | BIC_Pkg_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_CORE_ENERGY_STATUS,
+ .perf_subsys = "power",
+ .perf_name = "energy-cores",
+ .msr = MSR_PP0_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_CORES,
+ .bic = BIC_CorWatt | BIC_Cor_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_DRAM,
+ .perf_subsys = "power",
+ .perf_name = "energy-ram",
+ .msr = MSR_DRAM_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_dram_energy_units,
+ .rci_index = RAPL_RCI_INDEX_DRAM,
+ .bic = BIC_RAMWatt | BIC_RAM_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_GFX,
+ .perf_subsys = "power",
+ .perf_name = "energy-gpu",
+ .msr = MSR_PP1_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_GFX,
+ .bic = BIC_GFXWatt | BIC_GFX_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_PKG_PERF_STATUS,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_PKG_PERF_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_time_units,
+ .rci_index = RAPL_RCI_INDEX_PKG_PERF_STATUS,
+ .bic = BIC_PKG__,
+ .compat_scale = 100.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_DRAM_PERF_STATUS,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_DRAM_PERF_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_time_units,
+ .rci_index = RAPL_RCI_INDEX_DRAM_PERF_STATUS,
+ .bic = BIC_RAM__,
+ .compat_scale = 100.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_AMD_F17H,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_CORE_ENERGY_STAT,
+ .msr_mask = 0xFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_CORE_ENERGY,
+ .bic = BIC_CorWatt | BIC_Cor_J,
+ .compat_scale = 1.0,
+ .flags = 0,
+ },
+};
+
+struct rapl_counter {
+ unsigned long long raw_value;
+ enum rapl_unit unit;
+ double scale;
+};
+
struct thread_data {
struct timeval tv_begin;
struct timeval tv_end;
@@ -974,7 +1178,7 @@
unsigned long long c7;
unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */
unsigned int core_temp_c;
- unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */
+ struct rapl_counter core_energy; /* MSR_CORE_ENERGY_STAT */
unsigned int core_id;
unsigned long long core_throt_cnt;
unsigned long long counter[MAX_ADDED_COUNTERS];
@@ -989,8 +1193,8 @@
unsigned long long pc8;
unsigned long long pc9;
unsigned long long pc10;
- unsigned long long cpu_lpi;
- unsigned long long sys_lpi;
+ long long cpu_lpi;
+ long long sys_lpi;
unsigned long long pkg_wtd_core_c0;
unsigned long long pkg_any_core_c0;
unsigned long long pkg_any_gfxe_c0;
@@ -998,13 +1202,16 @@
long long gfx_rc6_ms;
unsigned int gfx_mhz;
unsigned int gfx_act_mhz;
+ long long sam_mc6_ms;
+ unsigned int sam_mhz;
+ unsigned int sam_act_mhz;
unsigned int package_id;
- unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */
- unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */
- unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */
- unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */
- unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
- unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
+ struct rapl_counter energy_pkg; /* MSR_PKG_ENERGY_STATUS */
+ struct rapl_counter energy_dram; /* MSR_DRAM_ENERGY_STATUS */
+ struct rapl_counter energy_cores; /* MSR_PP0_ENERGY_STATUS */
+ struct rapl_counter energy_gfx; /* MSR_PP1_ENERGY_STATUS */
+ struct rapl_counter rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
+ struct rapl_counter rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
unsigned int pkg_temp_c;
unsigned int uncore_mhz;
unsigned long long counter[MAX_ADDED_COUNTERS];
@@ -1150,6 +1357,38 @@
struct msr_counter *pp;
} sys;
+void free_sys_counters(void)
+{
+ struct msr_counter *p = sys.tp, *pnext = NULL;
+
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ p = sys.cp, pnext = NULL;
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ p = sys.pp, pnext = NULL;
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ sys.added_thread_counters = 0;
+ sys.added_core_counters = 0;
+ sys.added_package_counters = 0;
+ sys.tp = NULL;
+ sys.cp = NULL;
+ sys.pp = NULL;
+}
+
struct system_summary {
struct thread_data threads;
struct core_data cores;
@@ -1280,34 +1519,60 @@
sprintf(pathname, "/dev/cpu/%d/msr", cpu);
fd = open(pathname, O_RDONLY);
if (fd < 0)
- err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
+ err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, "
+ "or run with --no-msr, or run as root", pathname);
fd_percpu[cpu] = fd;
return fd;
}
+static void bic_disable_msr_access(void)
+{
+ const unsigned long bic_msrs =
+ BIC_SMI |
+ BIC_CPU_c1 |
+ BIC_CPU_c3 |
+ BIC_CPU_c6 |
+ BIC_CPU_c7 |
+ BIC_Mod_c6 |
+ BIC_CoreTmp |
+ BIC_Totl_c0 |
+ BIC_Any_c0 |
+ BIC_GFX_c0 |
+ BIC_CPUGFX |
+ BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_PkgTmp;
+
+ bic_enabled &= ~bic_msrs;
+
+ free_sys_counters();
+}
+
static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags)
{
+ assert(!no_perf);
+
return syscall(__NR_perf_event_open, hw_event, pid, cpu, group_fd, flags);
}
-static int perf_instr_count_open(int cpu_num)
+static long open_perf_counter(int cpu, unsigned int type, unsigned int config, int group_fd, __u64 read_format)
{
- struct perf_event_attr pea;
- int fd;
+ struct perf_event_attr attr;
+ const pid_t pid = -1;
+ const unsigned long flags = 0;
- memset(&pea, 0, sizeof(struct perf_event_attr));
- pea.type = PERF_TYPE_HARDWARE;
- pea.size = sizeof(struct perf_event_attr);
- pea.config = PERF_COUNT_HW_INSTRUCTIONS;
+ assert(!no_perf);
- /* counter for cpu_num, including user + kernel and all processes */
- fd = perf_event_open(&pea, -1, cpu_num, -1, 0);
- if (fd == -1) {
- warnx("capget(CAP_PERFMON) failed, try \"# setcap cap_sys_admin=ep %s\"", progname);
- BIC_NOT_PRESENT(BIC_IPC);
- }
+ memset(&attr, 0, sizeof(struct perf_event_attr));
+
+ attr.type = type;
+ attr.size = sizeof(struct perf_event_attr);
+ attr.config = config;
+ attr.disabled = 0;
+ attr.sample_type = PERF_SAMPLE_IDENTIFIER;
+ attr.read_format = read_format;
+
+ const int fd = perf_event_open(&attr, pid, cpu, group_fd, flags);
return fd;
}
@@ -1317,7 +1582,7 @@
if (fd_instr_count_percpu[cpu])
return fd_instr_count_percpu[cpu];
- fd_instr_count_percpu[cpu] = perf_instr_count_open(cpu);
+ fd_instr_count_percpu[cpu] = open_perf_counter(cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0);
return fd_instr_count_percpu[cpu];
}
@@ -1326,6 +1591,8 @@
{
ssize_t retval;
+ assert(!no_msr);
+
retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset);
if (retval != sizeof *msr)
@@ -1334,6 +1601,21 @@
return 0;
}
+int probe_msr(int cpu, off_t offset)
+{
+ ssize_t retval;
+ unsigned long long dummy;
+
+ assert(!no_msr);
+
+ retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset);
+
+ if (retval != sizeof(dummy))
+ return 1;
+
+ return 0;
+}
+
#define MAX_DEFERRED 16
char *deferred_add_names[MAX_DEFERRED];
char *deferred_skip_names[MAX_DEFERRED];
@@ -1369,6 +1651,8 @@
" Override default 5-second measurement interval\n"
" -J, --Joules displays energy in Joules instead of Watts\n"
" -l, --list list column headers only\n"
+ " -M, --no-msr Disable all uses of the MSR driver\n"
+ " -P, --no-perf Disable all uses of the perf API\n"
" -n, --num_iterations num\n"
" number of the measurement iterations\n"
" -N, --header_iterations num\n"
@@ -1573,6 +1857,15 @@
if (DO_BIC(BIC_GFXACTMHz))
outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_SAM_mc6))
+ outp += sprintf(outp, "%sSAM%%mc6", (printed++ ? delim : ""));
+
+ if (DO_BIC(BIC_SAMMHz))
+ outp += sprintf(outp, "%sSAMMHz", (printed++ ? delim : ""));
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ outp += sprintf(outp, "%sSAMAMHz", (printed++ ? delim : ""));
+
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
if (DO_BIC(BIC_Any_c0))
@@ -1671,26 +1964,35 @@
outp += sprintf(outp, "SMI: %d\n", t->smi_count);
for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, t->counter[i]);
+ outp +=
+ sprintf(outp, "tADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ t->counter[i], mp->path);
}
}
- if (c) {
+ if (c && is_cpu_first_thread_in_core(t, c, p)) {
outp += sprintf(outp, "core: %d\n", c->core_id);
outp += sprintf(outp, "c3: %016llX\n", c->c3);
outp += sprintf(outp, "c6: %016llX\n", c->c6);
outp += sprintf(outp, "c7: %016llX\n", c->c7);
outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
outp += sprintf(outp, "cpu_throt_count: %016llX\n", c->core_throt_cnt);
- outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
+
+ const unsigned long long energy_value = c->core_energy.raw_value * c->core_energy.scale;
+ const double energy_scale = c->core_energy.scale;
+
+ if (c->core_energy.unit == RAPL_UNIT_JOULES)
+ outp += sprintf(outp, "Joules: %0llX (scale: %lf)\n", energy_value, energy_scale);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, c->counter[i]);
+ outp +=
+ sprintf(outp, "cADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ c->counter[i], mp->path);
}
outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us);
}
- if (p) {
+ if (p && is_cpu_first_core_in_package(t, c, p)) {
outp += sprintf(outp, "package: %d\n", p->package_id);
outp += sprintf(outp, "Weighted cores: %016llX\n", p->pkg_wtd_core_c0);
@@ -1710,16 +2012,18 @@
outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
- outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg);
- outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores);
- outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx);
- outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram);
- outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status);
- outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status);
+ outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg.raw_value);
+ outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores.raw_value);
+ outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx.raw_value);
+ outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram.raw_value);
+ outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status.raw_value);
+ outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status.raw_value);
outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "pADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, p->counter[i]);
+ outp +=
+ sprintf(outp, "pADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ p->counter[i], mp->path);
}
}
@@ -1728,6 +2032,23 @@
return 0;
}
+double rapl_counter_get_value(const struct rapl_counter *c, enum rapl_unit desired_unit, double interval)
+{
+ assert(desired_unit != RAPL_UNIT_INVALID);
+
+ /*
+ * For now we don't expect anything other than joules,
+ * so just simplify the logic.
+ */
+ assert(c->unit == RAPL_UNIT_JOULES);
+
+ const double scaled = c->raw_value * c->scale;
+
+ if (desired_unit == RAPL_UNIT_WATTS)
+ return scaled / interval;
+ return scaled;
+}
+
/*
* column formatting convention & formats
*/
@@ -1921,9 +2242,11 @@
if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl)
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&c->core_energy, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl)
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&c->core_energy, RAPL_UNIT_JOULES, interval_float));
/* print per-package data only for 1st core in package */
if (!is_cpu_first_core_in_package(t, c, p))
@@ -1951,6 +2274,24 @@
if (DO_BIC(BIC_GFXACTMHz))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz);
+ /* SAMmc6 */
+ if (DO_BIC(BIC_SAM_mc6)) {
+ if (p->sam_mc6_ms == -1) { /* detect GFX counter reset */
+ outp += sprintf(outp, "%s**.**", (printed++ ? delim : ""));
+ } else {
+ outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ p->sam_mc6_ms / 10.0 / interval_float);
+ }
+ }
+
+ /* SAMMHz */
+ if (DO_BIC(BIC_SAMMHz))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_mhz);
+
+ /* SAMACTMHz */
+ if (DO_BIC(BIC_SAMACTMHz))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_act_mhz);
+
/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0 / tsc);
@@ -1976,43 +2317,59 @@
if (DO_BIC(BIC_Pkgpc10))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10 / tsc);
- if (DO_BIC(BIC_CPU_LPI))
- outp +=
- sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
- if (DO_BIC(BIC_SYS_LPI))
- outp +=
- sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+ if (DO_BIC(BIC_CPU_LPI)) {
+ if (p->cpu_lpi >= 0)
+ outp +=
+ sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
+ else
+ outp += sprintf(outp, "%s(neg)", (printed++ ? delim : ""));
+ }
+ if (DO_BIC(BIC_SYS_LPI)) {
+ if (p->sys_lpi >= 0)
+ outp +=
+ sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+ else
+ outp += sprintf(outp, "%s(neg)", (printed++ ? delim : ""));
+ }
if (DO_BIC(BIC_PkgWatt))
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
-
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl)
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_GFXWatt))
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_RAMWatt))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- p->energy_dram * rapl_dram_energy_units / interval_float);
+ rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_Pkg_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl)
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_GFX_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_RAM_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_PKG__))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+ rapl_counter_get_value(&p->rapl_pkg_perf_status, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_RAM__))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+ rapl_counter_get_value(&p->rapl_dram_perf_status, RAPL_UNIT_WATTS, interval_float));
/* UncMHz */
if (DO_BIC(BIC_UNCORE_MHZ))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->uncore_mhz);
@@ -2121,12 +2478,22 @@
old->gfx_mhz = new->gfx_mhz;
old->gfx_act_mhz = new->gfx_act_mhz;
- old->energy_pkg = new->energy_pkg - old->energy_pkg;
- old->energy_cores = new->energy_cores - old->energy_cores;
- old->energy_gfx = new->energy_gfx - old->energy_gfx;
- old->energy_dram = new->energy_dram - old->energy_dram;
- old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status;
- old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status;
+ /* flag an error when mc6 counter resets/wraps */
+ if (old->sam_mc6_ms > new->sam_mc6_ms)
+ old->sam_mc6_ms = -1;
+ else
+ old->sam_mc6_ms = new->sam_mc6_ms - old->sam_mc6_ms;
+
+ old->sam_mhz = new->sam_mhz;
+ old->sam_act_mhz = new->sam_act_mhz;
+
+ old->energy_pkg.raw_value = new->energy_pkg.raw_value - old->energy_pkg.raw_value;
+ old->energy_cores.raw_value = new->energy_cores.raw_value - old->energy_cores.raw_value;
+ old->energy_gfx.raw_value = new->energy_gfx.raw_value - old->energy_gfx.raw_value;
+ old->energy_dram.raw_value = new->energy_dram.raw_value - old->energy_dram.raw_value;
+ old->rapl_pkg_perf_status.raw_value = new->rapl_pkg_perf_status.raw_value - old->rapl_pkg_perf_status.raw_value;
+ old->rapl_dram_perf_status.raw_value =
+ new->rapl_dram_perf_status.raw_value - old->rapl_dram_perf_status.raw_value;
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2150,7 +2517,7 @@
old->core_throt_cnt = new->core_throt_cnt;
old->mc6_us = new->mc6_us - old->mc6_us;
- DELTA_WRAP32(new->core_energy, old->core_energy);
+ DELTA_WRAP32(new->core_energy.raw_value, old->core_energy.raw_value);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2277,6 +2644,13 @@
return retval;
}
+void rapl_counter_clear(struct rapl_counter *c)
+{
+ c->raw_value = 0;
+ c->scale = 0.0;
+ c->unit = RAPL_UNIT_INVALID;
+}
+
void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int i;
@@ -2304,7 +2678,7 @@
c->c7 = 0;
c->mc6_us = 0;
c->core_temp_c = 0;
- c->core_energy = 0;
+ rapl_counter_clear(&c->core_energy);
c->core_throt_cnt = 0;
p->pkg_wtd_core_c0 = 0;
@@ -2325,18 +2699,21 @@
p->cpu_lpi = 0;
p->sys_lpi = 0;
- p->energy_pkg = 0;
- p->energy_dram = 0;
- p->energy_cores = 0;
- p->energy_gfx = 0;
- p->rapl_pkg_perf_status = 0;
- p->rapl_dram_perf_status = 0;
+ rapl_counter_clear(&p->energy_pkg);
+ rapl_counter_clear(&p->energy_dram);
+ rapl_counter_clear(&p->energy_cores);
+ rapl_counter_clear(&p->energy_gfx);
+ rapl_counter_clear(&p->rapl_pkg_perf_status);
+ rapl_counter_clear(&p->rapl_dram_perf_status);
p->pkg_temp_c = 0;
p->gfx_rc6_ms = 0;
p->uncore_mhz = 0;
p->gfx_mhz = 0;
p->gfx_act_mhz = 0;
+ p->sam_mc6_ms = 0;
+ p->sam_mhz = 0;
+ p->sam_act_mhz = 0;
for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
t->counter[i] = 0;
@@ -2347,6 +2724,20 @@
p->counter[i] = 0;
}
+void rapl_counter_accumulate(struct rapl_counter *dst, const struct rapl_counter *src)
+{
+ /* Copy unit and scale from src if dst is not initialized */
+ if (dst->unit == RAPL_UNIT_INVALID) {
+ dst->unit = src->unit;
+ dst->scale = src->scale;
+ }
+
+ assert(dst->unit == src->unit);
+ assert(dst->scale == src->scale);
+
+ dst->raw_value += src->raw_value;
+}
+
int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int i;
@@ -2393,7 +2784,7 @@
average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
average.cores.core_throt_cnt = MAX(average.cores.core_throt_cnt, c->core_throt_cnt);
- average.cores.core_energy += c->core_energy;
+ rapl_counter_accumulate(&average.cores.core_energy, &c->core_energy);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2428,25 +2819,29 @@
average.packages.cpu_lpi = p->cpu_lpi;
average.packages.sys_lpi = p->sys_lpi;
- average.packages.energy_pkg += p->energy_pkg;
- average.packages.energy_dram += p->energy_dram;
- average.packages.energy_cores += p->energy_cores;
- average.packages.energy_gfx += p->energy_gfx;
+ rapl_counter_accumulate(&average.packages.energy_pkg, &p->energy_pkg);
+ rapl_counter_accumulate(&average.packages.energy_dram, &p->energy_dram);
+ rapl_counter_accumulate(&average.packages.energy_cores, &p->energy_cores);
+ rapl_counter_accumulate(&average.packages.energy_gfx, &p->energy_gfx);
average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
average.packages.uncore_mhz = p->uncore_mhz;
average.packages.gfx_mhz = p->gfx_mhz;
average.packages.gfx_act_mhz = p->gfx_act_mhz;
+ average.packages.sam_mc6_ms = p->sam_mc6_ms;
+ average.packages.sam_mhz = p->sam_mhz;
+ average.packages.sam_act_mhz = p->sam_act_mhz;
average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
- average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status;
- average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status;
+ rapl_counter_accumulate(&average.packages.rapl_pkg_perf_status, &p->rapl_pkg_perf_status);
+ rapl_counter_accumulate(&average.packages.rapl_dram_perf_status, &p->rapl_dram_perf_status);
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
- if (mp->format == FORMAT_RAW)
- continue;
- average.packages.counter[i] += p->counter[i];
+ if ((mp->format == FORMAT_RAW) && (topo.num_packages == 0))
+ average.packages.counter[i] = p->counter[i];
+ else
+ average.packages.counter[i] += p->counter[i];
}
return 0;
}
@@ -2578,6 +2973,7 @@
int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
{
if (mp->msr_num != 0) {
+ assert(!no_msr);
if (get_msr(cpu, mp->msr_num, counterp))
return -1;
} else {
@@ -2599,7 +2995,7 @@
{
char path[128];
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/current_freq_khz", package,
+ sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d/current_freq_khz", package,
die);
return (snapshot_sysfs_counter(path) / 1000);
@@ -2627,6 +3023,9 @@
return epb;
msr_fallback:
+ if (no_msr)
+ return -1;
+
get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr);
return msr & 0xf;
@@ -2700,6 +3099,351 @@
return 0;
}
+struct amperf_group_fd {
+ int aperf; /* Also the group descriptor */
+ int mperf;
+};
+
+static int read_perf_counter_info(const char *const path, const char *const parse_format, void *value_ptr)
+{
+ int fdmt;
+ int bytes_read;
+ char buf[64];
+ int ret = -1;
+
+ fdmt = open(path, O_RDONLY, 0);
+ if (fdmt == -1) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ bytes_read = read(fdmt, buf, sizeof(buf) - 1);
+ if (bytes_read <= 0 || bytes_read >= (int)sizeof(buf)) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ buf[bytes_read] = '\0';
+
+ if (sscanf(buf, parse_format, value_ptr) != 1) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ ret = 0;
+
+cleanup_and_exit:
+ close(fdmt);
+ return ret;
+}
+
+static unsigned int read_perf_counter_info_n(const char *const path, const char *const parse_format)
+{
+ unsigned int v;
+ int status;
+
+ status = read_perf_counter_info(path, parse_format, &v);
+ if (status)
+ v = -1;
+
+ return v;
+}
+
+static unsigned int read_msr_type(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/type";
+ const char *const format = "%u";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_aperf_config(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/events/aperf";
+ const char *const format = "event=%x";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_mperf_config(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/events/mperf";
+ const char *const format = "event=%x";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_perf_type(const char *subsys)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/type";
+ const char *const format = "%u";
+ char path[128];
+
+ snprintf(path, sizeof(path), path_format, subsys);
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_rapl_config(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s";
+ const char *const format = "event=%x";
+ char path[128];
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.unit";
+ const char *const format = "%s";
+ char path[128];
+ char unit_buffer[16];
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ read_perf_counter_info(path, format, &unit_buffer);
+ if (strcmp("Joules", unit_buffer) == 0)
+ return RAPL_UNIT_JOULES;
+
+ return RAPL_UNIT_INVALID;
+}
+
+static double read_perf_rapl_scale(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.scale";
+ const char *const format = "%lf";
+ char path[128];
+ double scale;
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ if (read_perf_counter_info(path, format, &scale))
+ return 0.0;
+
+ return scale;
+}
+
+static struct amperf_group_fd open_amperf_fd(int cpu)
+{
+ const unsigned int msr_type = read_msr_type();
+ const unsigned int aperf_config = read_aperf_config();
+ const unsigned int mperf_config = read_mperf_config();
+ struct amperf_group_fd fds = {.aperf = -1, .mperf = -1 };
+
+ fds.aperf = open_perf_counter(cpu, msr_type, aperf_config, -1, PERF_FORMAT_GROUP);
+ fds.mperf = open_perf_counter(cpu, msr_type, mperf_config, fds.aperf, PERF_FORMAT_GROUP);
+
+ return fds;
+}
+
+static int get_amperf_fd(int cpu)
+{
+ assert(fd_amperf_percpu);
+
+ if (fd_amperf_percpu[cpu].aperf)
+ return fd_amperf_percpu[cpu].aperf;
+
+ fd_amperf_percpu[cpu] = open_amperf_fd(cpu);
+
+ return fd_amperf_percpu[cpu].aperf;
+}
+
+/* Read APERF, MPERF and TSC using the perf API. */
+static int read_aperf_mperf_tsc_perf(struct thread_data *t, int cpu)
+{
+ union {
+ struct {
+ unsigned long nr_entries;
+ unsigned long aperf;
+ unsigned long mperf;
+ };
+
+ unsigned long as_array[3];
+ } cnt;
+
+ const int fd_amperf = get_amperf_fd(cpu);
+
+ /*
+ * Read the TSC with rdtsc, because we want the absolute value and not
+ * the offset from the start of the counter.
+ */
+ t->tsc = rdtsc();
+
+ const int n = read(fd_amperf, &cnt.as_array[0], sizeof(cnt.as_array));
+
+ if (n != sizeof(cnt.as_array))
+ return -2;
+
+ t->aperf = cnt.aperf * aperf_mperf_multiplier;
+ t->mperf = cnt.mperf * aperf_mperf_multiplier;
+
+ return 0;
+}
+
+/* Read APERF, MPERF and TSC using the MSR driver and rdtsc instruction. */
+static int read_aperf_mperf_tsc_msr(struct thread_data *t, int cpu)
+{
+ unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
+ int aperf_mperf_retry_count = 0;
+
+ /*
+ * The TSC, APERF and MPERF must be read together for
+ * APERF/MPERF and MPERF/TSC to give accurate results.
+ *
+ * Unfortunately, APERF and MPERF are read by
+ * individual system call, so delays may occur
+ * between them. If the time to read them
+ * varies by a large amount, we re-read them.
+ */
+
+ /*
+ * This initial dummy APERF read has been seen to
+ * reduce jitter in the subsequent reads.
+ */
+
+ if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+ return -3;
+
+retry:
+ t->tsc = rdtsc(); /* re-read close to APERF */
+
+ tsc_before = t->tsc;
+
+ if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+ return -3;
+
+ tsc_between = rdtsc();
+
+ if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
+ return -4;
+
+ tsc_after = rdtsc();
+
+ aperf_time = tsc_between - tsc_before;
+ mperf_time = tsc_after - tsc_between;
+
+ /*
+ * If the system call latency to read APERF and MPERF
+ * differ by more than 2x, then try again.
+ */
+ if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
+ aperf_mperf_retry_count++;
+ if (aperf_mperf_retry_count < 5)
+ goto retry;
+ else
+ warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time);
+ }
+ aperf_mperf_retry_count = 0;
+
+ t->aperf = t->aperf * aperf_mperf_multiplier;
+ t->mperf = t->mperf * aperf_mperf_multiplier;
+
+ return 0;
+}
+
+size_t rapl_counter_info_count_perf(const struct rapl_counter_info_t *rci)
+{
+ size_t ret = 0;
+
+ for (int i = 0; i < NUM_RAPL_COUNTERS; ++i)
+ if (rci->source[i] == RAPL_SOURCE_PERF)
+ ++ret;
+
+ return ret;
+}
+
+void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci, unsigned int idx)
+{
+ rc->raw_value = rci->data[idx];
+ rc->unit = rci->unit[idx];
+ rc->scale = rci->scale[idx];
+}
+
+int get_rapl_counters(int cpu, int domain, struct core_data *c, struct pkg_data *p)
+{
+ unsigned long long perf_data[NUM_RAPL_COUNTERS + 1];
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain];
+
+ if (debug)
+ fprintf(stderr, "%s: cpu%d domain%d\n", __func__, cpu, domain);
+
+ assert(rapl_counter_info_perdomain);
+
+ /*
+ * If we have any perf counters to read, read them all now, in bulk
+ */
+ if (rci->fd_perf != -1) {
+ size_t num_perf_counters = rapl_counter_info_count_perf(rci);
+ const ssize_t expected_read_size = (num_perf_counters + 1) * sizeof(unsigned long long);
+ const ssize_t actual_read_size = read(rci->fd_perf, &perf_data[0], sizeof(perf_data));
+
+ if (actual_read_size != expected_read_size)
+ err(-1, "%s: failed to read perf_data (%zu %zu)", __func__, expected_read_size,
+ actual_read_size);
+ }
+
+ for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) {
+ switch (rci->source[i]) {
+ case RAPL_SOURCE_NONE:
+ break;
+
+ case RAPL_SOURCE_PERF:
+ assert(pi < ARRAY_SIZE(perf_data));
+ assert(rci->fd_perf != -1);
+
+ if (debug)
+ fprintf(stderr, "Reading rapl counter via perf at %u (%llu %e %lf)\n",
+ i, perf_data[pi], rci->scale[i], perf_data[pi] * rci->scale[i]);
+
+ rci->data[i] = perf_data[pi];
+
+ ++pi;
+ break;
+
+ case RAPL_SOURCE_MSR:
+ if (debug)
+ fprintf(stderr, "Reading rapl counter via msr at %u\n", i);
+
+ assert(!no_msr);
+ if (rci->flags[i] & RAPL_COUNTER_FLAG_USE_MSR_SUM) {
+ if (get_msr_sum(cpu, rci->msr[i], &rci->data[i]))
+ return -13 - i;
+ } else {
+ if (get_msr(cpu, rci->msr[i], &rci->data[i]))
+ return -13 - i;
+ }
+
+ rci->data[i] &= rci->msr_mask[i];
+ if (rci->msr_shift[i] >= 0)
+ rci->data[i] >>= abs(rci->msr_shift[i]);
+ else
+ rci->data[i] <<= abs(rci->msr_shift[i]);
+
+ break;
+ }
+ }
+
+ _Static_assert(NUM_RAPL_COUNTERS == 7);
+ write_rapl_counter(&p->energy_pkg, rci, RAPL_RCI_INDEX_ENERGY_PKG);
+ write_rapl_counter(&p->energy_cores, rci, RAPL_RCI_INDEX_ENERGY_CORES);
+ write_rapl_counter(&p->energy_dram, rci, RAPL_RCI_INDEX_DRAM);
+ write_rapl_counter(&p->energy_gfx, rci, RAPL_RCI_INDEX_GFX);
+ write_rapl_counter(&p->rapl_pkg_perf_status, rci, RAPL_RCI_INDEX_PKG_PERF_STATUS);
+ write_rapl_counter(&p->rapl_dram_perf_status, rci, RAPL_RCI_INDEX_DRAM_PERF_STATUS);
+ write_rapl_counter(&c->core_energy, rci, RAPL_RCI_INDEX_CORE_ENERGY);
+
+ return 0;
+}
+
/*
* get_counters(...)
* migrate to cpu
@@ -2709,12 +3453,12 @@
{
int cpu = t->cpu_id;
unsigned long long msr;
- int aperf_mperf_retry_count = 0;
struct msr_counter *mp;
int i;
+ int status;
if (cpu_migrate(cpu)) {
- fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "%s: Could not migrate to CPU %d\n", __func__, cpu);
return -1;
}
@@ -2722,63 +3466,26 @@
if (first_counter_read)
get_apic_id(t);
-retry:
+
t->tsc = rdtsc(); /* we are running on local CPU of interest */
if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC)
|| soft_c1_residency_display(BIC_Avg_MHz)) {
- unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
+ int status = -1;
- /*
- * The TSC, APERF and MPERF must be read together for
- * APERF/MPERF and MPERF/TSC to give accurate results.
- *
- * Unfortunately, APERF and MPERF are read by
- * individual system call, so delays may occur
- * between them. If the time to read them
- * varies by a large amount, we re-read them.
- */
+ assert(!no_perf || !no_msr);
- /*
- * This initial dummy APERF read has been seen to
- * reduce jitter in the subsequent reads.
- */
-
- if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
- return -3;
-
- t->tsc = rdtsc(); /* re-read close to APERF */
-
- tsc_before = t->tsc;
-
- if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
- return -3;
-
- tsc_between = rdtsc();
-
- if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
- return -4;
-
- tsc_after = rdtsc();
-
- aperf_time = tsc_between - tsc_before;
- mperf_time = tsc_after - tsc_between;
-
- /*
- * If the system call latency to read APERF and MPERF
- * differ by more than 2x, then try again.
- */
- if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
- aperf_mperf_retry_count++;
- if (aperf_mperf_retry_count < 5)
- goto retry;
- else
- warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time);
+ switch (amperf_source) {
+ case AMPERF_SOURCE_PERF:
+ status = read_aperf_mperf_tsc_perf(t, cpu);
+ break;
+ case AMPERF_SOURCE_MSR:
+ status = read_aperf_mperf_tsc_msr(t, cpu);
+ break;
}
- aperf_mperf_retry_count = 0;
- t->aperf = t->aperf * aperf_mperf_multiplier;
- t->mperf = t->mperf * aperf_mperf_multiplier;
+ if (status != 0)
+ return status;
}
if (DO_BIC(BIC_IPC))
@@ -2806,6 +3513,12 @@
if (!is_cpu_first_thread_in_core(t, c, p))
goto done;
+ if (platform->has_per_core_rapl) {
+ status = get_rapl_counters(cpu, c->core_id, c, p);
+ if (status != 0)
+ return status;
+ }
+
if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) {
if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
return -6;
@@ -2846,12 +3559,6 @@
if (DO_BIC(BIC_CORE_THROT_CNT))
get_core_throt_cnt(cpu, &c->core_throt_cnt);
- if (platform->rapl_msrs & RAPL_AMD_F17H) {
- if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
- return -14;
- c->core_energy = msr & 0xFFFFFFFF;
- }
-
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &c->counter[i]))
return -10;
@@ -2911,59 +3618,39 @@
if (DO_BIC(BIC_SYS_LPI))
p->sys_lpi = cpuidle_cur_sys_lpi_us;
- if (platform->rapl_msrs & RAPL_PKG) {
- if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr))
- return -13;
- p->energy_pkg = msr;
+ if (!platform->has_per_core_rapl) {
+ status = get_rapl_counters(cpu, p->package_id, c, p);
+ if (status != 0)
+ return status;
}
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) {
- if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr))
- return -14;
- p->energy_cores = msr;
- }
- if (platform->rapl_msrs & RAPL_DRAM) {
- if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
- return -15;
- p->energy_dram = msr;
- }
- if (platform->rapl_msrs & RAPL_GFX) {
- if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr))
- return -16;
- p->energy_gfx = msr;
- }
- if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) {
- if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr))
- return -16;
- p->rapl_pkg_perf_status = msr;
- }
- if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) {
- if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr))
- return -16;
- p->rapl_dram_perf_status = msr;
- }
- if (platform->rapl_msrs & RAPL_AMD_F17H) {
- if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr))
- return -13;
- p->energy_pkg = msr;
- }
+
if (DO_BIC(BIC_PkgTmp)) {
if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
return -17;
p->pkg_temp_c = tj_max - ((msr >> 16) & 0x7F);
}
- if (DO_BIC(BIC_GFX_rc6))
- p->gfx_rc6_ms = gfx_cur_rc6_ms;
-
/* n.b. assume die0 uncore frequency applies to whole package */
if (DO_BIC(BIC_UNCORE_MHZ))
p->uncore_mhz = get_uncore_mhz(p->package_id, 0);
+ if (DO_BIC(BIC_GFX_rc6))
+ p->gfx_rc6_ms = gfx_info[GFX_rc6].val_ull;
+
if (DO_BIC(BIC_GFXMHz))
- p->gfx_mhz = gfx_cur_mhz;
+ p->gfx_mhz = gfx_info[GFX_MHz].val;
if (DO_BIC(BIC_GFXACTMHz))
- p->gfx_act_mhz = gfx_act_mhz;
+ p->gfx_act_mhz = gfx_info[GFX_ACTMHz].val;
+
+ if (DO_BIC(BIC_SAM_mc6))
+ p->sam_mc6_ms = gfx_info[SAM_mc6].val_ull;
+
+ if (DO_BIC(BIC_SAMMHz))
+ p->sam_mhz = gfx_info[SAM_MHz].val;
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ p->sam_act_mhz = gfx_info[SAM_ACTMHz].val;
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &p->counter[i]))
@@ -3053,7 +3740,7 @@
unsigned long long msr;
int *pkg_cstate_limits;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
switch (platform->cst_limit) {
@@ -3097,7 +3784,7 @@
unsigned long long msr;
unsigned int ratio;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
@@ -3115,7 +3802,7 @@
{
unsigned long long msr;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
@@ -3321,7 +4008,7 @@
{
unsigned long long msr;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
@@ -3393,7 +4080,7 @@
{
unsigned long long msr;
- if (!platform->has_irtl_msrs)
+ if (!platform->has_irtl_msrs || no_msr)
return;
if (platform->supported_cstates & PC3) {
@@ -3443,12 +4130,64 @@
{
int i;
+ if (!fd_percpu)
+ return;
+
for (i = 0; i < topo.max_cpu_num + 1; ++i) {
if (fd_percpu[i] != 0)
close(fd_percpu[i]);
}
free(fd_percpu);
+ fd_percpu = NULL;
+}
+
+void free_fd_amperf_percpu(void)
+{
+ int i;
+
+ if (!fd_amperf_percpu)
+ return;
+
+ for (i = 0; i < topo.max_cpu_num + 1; ++i) {
+ if (fd_amperf_percpu[i].mperf != 0)
+ close(fd_amperf_percpu[i].mperf);
+
+ if (fd_amperf_percpu[i].aperf != 0)
+ close(fd_amperf_percpu[i].aperf);
+ }
+
+ free(fd_amperf_percpu);
+ fd_amperf_percpu = NULL;
+}
+
+void free_fd_instr_count_percpu(void)
+{
+ if (!fd_instr_count_percpu)
+ return;
+
+ for (int i = 0; i < topo.max_cpu_num + 1; ++i) {
+ if (fd_instr_count_percpu[i] != 0)
+ close(fd_instr_count_percpu[i]);
+ }
+
+ free(fd_instr_count_percpu);
+ fd_instr_count_percpu = NULL;
+}
+
+void free_fd_rapl_percpu(void)
+{
+ if (!rapl_counter_info_perdomain)
+ return;
+
+ const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages;
+
+ for (int domain_id = 0; domain_id < num_domains; ++domain_id) {
+ if (rapl_counter_info_perdomain[domain_id].fd_perf != -1)
+ close(rapl_counter_info_perdomain[domain_id].fd_perf);
+ }
+
+ free(rapl_counter_info_perdomain);
}
void free_all_buffers(void)
@@ -3492,6 +4231,9 @@
outp = NULL;
free_fd_percpu();
+ free_fd_instr_count_percpu();
+ free_fd_amperf_percpu();
+ free_fd_rapl_percpu();
free(irq_column_2_cpu);
free(irqs_per_cpu);
@@ -3825,11 +4567,17 @@
err(1, "%s: cpu str malformat %s\n", PATH_EFFECTIVE_CPUS, cpu_effective_str);
}
+void linux_perf_init(void);
+void rapl_perf_init(void);
+
void re_initialize(void)
{
free_all_buffers();
setup_all_buffers(false);
- fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus);
+ linux_perf_init();
+ rapl_perf_init();
+ fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus,
+ topo.allowed_cpus);
}
void set_max_cpu_num(void)
@@ -3940,85 +4688,43 @@
}
/*
- * snapshot_gfx_rc6_ms()
+ * snapshot_graphics()
*
- * record snapshot of
- * /sys/class/drm/card0/power/rc6_residency_ms
+ * record snapshot of specified graphics sysfs knob
*
* return 1 if config change requires a restart, else return 0
*/
-int snapshot_gfx_rc6_ms(void)
+int snapshot_graphics(int idx)
{
FILE *fp;
int retval;
- fp = fopen_or_die("/sys/class/drm/card0/power/rc6_residency_ms", "r");
-
- retval = fscanf(fp, "%lld", &gfx_cur_rc6_ms);
- if (retval != 1)
- err(1, "GFX rc6");
-
- fclose(fp);
-
- return 0;
-}
-
-/*
- * snapshot_gfx_mhz()
- *
- * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
- * when /sys/class/drm/card0/gt_cur_freq_mhz is not available.
- *
- * return 1 if config change requires a restart, else return 0
- */
-int snapshot_gfx_mhz(void)
-{
- static FILE *fp;
- int retval;
-
- if (fp == NULL) {
- fp = fopen("/sys/class/drm/card0/gt_cur_freq_mhz", "r");
- if (!fp)
- fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
- } else {
- rewind(fp);
- fflush(fp);
+ switch (idx) {
+ case GFX_rc6:
+ case SAM_mc6:
+ fp = fopen_or_die(gfx_info[idx].path, "r");
+ retval = fscanf(fp, "%lld", &gfx_info[idx].val_ull);
+ if (retval != 1)
+ err(1, "rc6");
+ fclose(fp);
+ return 0;
+ case GFX_MHz:
+ case GFX_ACTMHz:
+ case SAM_MHz:
+ case SAM_ACTMHz:
+ if (gfx_info[idx].fp == NULL) {
+ gfx_info[idx].fp = fopen_or_die(gfx_info[idx].path, "r");
+ } else {
+ rewind(gfx_info[idx].fp);
+ fflush(gfx_info[idx].fp);
+ }
+ retval = fscanf(gfx_info[idx].fp, "%d", &gfx_info[idx].val);
+ if (retval != 1)
+ err(1, "MHz");
+ return 0;
+ default:
+ return -EINVAL;
}
-
- retval = fscanf(fp, "%d", &gfx_cur_mhz);
- if (retval != 1)
- err(1, "GFX MHz");
-
- return 0;
-}
-
-/*
- * snapshot_gfx_cur_mhz()
- *
- * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
- * when /sys/class/drm/card0/gt_act_freq_mhz is not available.
- *
- * return 1 if config change requires a restart, else return 0
- */
-int snapshot_gfx_act_mhz(void)
-{
- static FILE *fp;
- int retval;
-
- if (fp == NULL) {
- fp = fopen("/sys/class/drm/card0/gt_act_freq_mhz", "r");
- if (!fp)
- fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
- } else {
- rewind(fp);
- fflush(fp);
- }
-
- retval = fscanf(fp, "%d", &gfx_act_mhz);
- if (retval != 1)
- err(1, "GFX ACT MHz");
-
- return 0;
}
/*
@@ -4083,13 +4789,22 @@
return 1;
if (DO_BIC(BIC_GFX_rc6))
- snapshot_gfx_rc6_ms();
+ snapshot_graphics(GFX_rc6);
if (DO_BIC(BIC_GFXMHz))
- snapshot_gfx_mhz();
+ snapshot_graphics(GFX_MHz);
if (DO_BIC(BIC_GFXACTMHz))
- snapshot_gfx_act_mhz();
+ snapshot_graphics(GFX_ACTMHz);
+
+ if (DO_BIC(BIC_SAM_mc6))
+ snapshot_graphics(SAM_mc6);
+
+ if (DO_BIC(BIC_SAMMHz))
+ snapshot_graphics(SAM_MHz);
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ snapshot_graphics(SAM_ACTMHz);
if (DO_BIC(BIC_CPU_LPI))
snapshot_cpu_lpi_us();
@@ -4173,6 +4888,8 @@
int ret, idx;
unsigned long long msr_cur, msr_last;
+ assert(!no_msr);
+
if (!per_cpu_msr_sum)
return 1;
@@ -4201,6 +4918,8 @@
UNUSED(c);
UNUSED(p);
+ assert(!no_msr);
+
for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) {
unsigned long long msr_cur, msr_last;
off_t offset;
@@ -4280,7 +4999,8 @@
/*
* set_my_sched_priority(pri)
- * return previous
+ * return previous priority on success
+ * return value < -20 on failure
*/
int set_my_sched_priority(int priority)
{
@@ -4290,16 +5010,16 @@
errno = 0;
original_priority = getpriority(PRIO_PROCESS, 0);
if (errno && (original_priority == -1))
- err(errno, "getpriority");
+ return -21;
retval = setpriority(PRIO_PROCESS, 0, priority);
if (retval)
- errx(retval, "capget(CAP_SYS_NICE) failed,try \"# setcap cap_sys_nice=ep %s\"", progname);
+ return -21;
errno = 0;
retval = getpriority(PRIO_PROCESS, 0);
if (retval != priority)
- err(retval, "getpriority(%d) != setpriority(%d)", retval, priority);
+ return -21;
return original_priority;
}
@@ -4314,6 +5034,9 @@
/*
* elevate own priority for interval mode
+ *
+ * ignore on error - we probably don't have permission to set it, but
+ * it's not a big deal
*/
set_my_sched_priority(-20);
@@ -4399,10 +5122,13 @@
struct stat sb;
char pathname[32];
+ if (no_msr)
+ return;
+
sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
if (stat(pathname, &sb))
if (system("/sbin/modprobe msr > /dev/null 2>&1"))
- err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
+ no_msr = 1;
}
/*
@@ -4414,47 +5140,51 @@
{
cap_t caps;
cap_flag_value_t cap_flag_value;
+ int ret = 0;
caps = cap_get_proc();
if (caps == NULL)
- err(-6, "cap_get_proc\n");
-
- if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value))
- err(-6, "cap_get\n");
-
- if (cap_flag_value != CAP_SET) {
- warnx("capget(CAP_SYS_RAWIO) failed," " try \"# setcap cap_sys_rawio=ep %s\"", progname);
return 1;
+
+ if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) {
+ ret = 1;
+ goto free_and_exit;
}
+ if (cap_flag_value != CAP_SET) {
+ ret = 1;
+ goto free_and_exit;
+ }
+
+free_and_exit:
if (cap_free(caps) == -1)
err(-6, "cap_free\n");
- return 0;
+ return ret;
}
-void check_permissions(void)
+void check_msr_permission(void)
{
- int do_exit = 0;
+ int failed = 0;
char pathname[32];
+ if (no_msr)
+ return;
+
/* check for CAP_SYS_RAWIO */
- do_exit += check_for_cap_sys_rawio();
+ failed += check_for_cap_sys_rawio();
/* test file permissions */
sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
if (euidaccess(pathname, R_OK)) {
- do_exit++;
- warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr");
+ failed++;
}
- /* if all else fails, thell them to be root */
- if (do_exit)
- if (getuid() != 0)
- warnx("... or simply run as root");
-
- if (do_exit)
- exit(-6);
+ if (failed) {
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly", pathname, "--no-msr");
+ no_msr = 1;
+ }
}
void probe_bclk(void)
@@ -4462,7 +5192,7 @@
unsigned long long msr;
unsigned int base_ratio;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
if (platform->bclk_freq == BCLK_100MHZ)
@@ -4502,7 +5232,7 @@
if (!has_turbo)
return;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
if (platform->trl_msrs & TRL_LIMIT2)
@@ -4567,20 +5297,15 @@
static void probe_intel_uncore_frequency(void)
{
int i, j;
- char path[128];
+ char path[256];
if (!genuine_intel)
return;
- if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK))
- return;
+ if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK))
+ goto probe_cluster;
- /* Cluster level sysfs not supported yet. */
- if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK))
- return;
-
- if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK))
- BIC_PRESENT(BIC_UNCORE_MHZ);
+ BIC_PRESENT(BIC_UNCORE_MHZ);
if (quiet)
return;
@@ -4588,40 +5313,178 @@
for (i = 0; i < topo.num_packages; ++i) {
for (j = 0; j < topo.num_die; ++j) {
int k, l;
+ char path_base[128];
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/min_freq_khz",
- i, j);
- k = read_sysfs_int(path);
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/max_freq_khz",
- i, j);
- l = read_sysfs_int(path);
- fprintf(outf, "Uncore Frequency pkg%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000);
+ sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d", i,
+ j);
- sprintf(path,
- "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_min_freq_khz",
- i, j);
+ sprintf(path, "%s/min_freq_khz", path_base);
k = read_sysfs_int(path);
- sprintf(path,
- "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_max_freq_khz",
- i, j);
+ sprintf(path, "%s/max_freq_khz", path_base);
l = read_sysfs_int(path);
- fprintf(outf, "(%d - %d MHz)\n", k / 1000, l / 1000);
+ fprintf(outf, "Uncore Frequency package%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000);
+
+ sprintf(path, "%s/initial_min_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ sprintf(path, "%s/initial_max_freq_khz", path_base);
+ l = read_sysfs_int(path);
+ fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000);
+
+ sprintf(path, "%s/current_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ fprintf(outf, " %d MHz\n", k / 1000);
}
}
+ return;
+
+probe_cluster:
+ if (access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00/current_freq_khz", R_OK))
+ return;
+
+ if (quiet)
+ return;
+
+ for (i = 0;; ++i) {
+ int k, l;
+ char path_base[128];
+ int package_id, domain_id, cluster_id;
+
+ sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/uncore%02d", i);
+
+ if (access(path_base, R_OK))
+ break;
+
+ sprintf(path, "%s/package_id", path_base);
+ package_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/domain_id", path_base);
+ domain_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/fabric_cluster_id", path_base);
+ cluster_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/min_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ sprintf(path, "%s/max_freq_khz", path_base);
+ l = read_sysfs_int(path);
+ fprintf(outf, "Uncore Frequency package%d domain%d cluster%d: %d - %d MHz ", package_id, domain_id,
+ cluster_id, k / 1000, l / 1000);
+
+ sprintf(path, "%s/initial_min_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ sprintf(path, "%s/initial_max_freq_khz", path_base);
+ l = read_sysfs_int(path);
+ fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000);
+
+ sprintf(path, "%s/current_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ fprintf(outf, " %d MHz\n", k / 1000);
+ }
}
static void probe_graphics(void)
{
+ /* Xe graphics sysfs knobs */
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", R_OK)) {
+ FILE *fp;
+ char buf[8];
+ bool gt0_is_gt;
+ int idx;
+
+ fp = fopen("/sys/class/drm/card0/device/tile0/gt0/gtidle/name", "r");
+ if (!fp)
+ goto next;
+
+ if (!fread(buf, sizeof(char), 7, fp)) {
+ fclose(fp);
+ goto next;
+ }
+ fclose(fp);
+
+ if (!strncmp(buf, "gt0-rc", strlen("gt0-rc")))
+ gt0_is_gt = true;
+ else if (!strncmp(buf, "gt0-mc", strlen("gt0-mc")))
+ gt0_is_gt = false;
+ else
+ goto next;
+
+ idx = gt0_is_gt ? GFX_rc6 : SAM_mc6;
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms";
+
+ idx = gt0_is_gt ? GFX_MHz : SAM_MHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq";
+
+ idx = gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq";
+
+ idx = gt0_is_gt ? SAM_mc6 : GFX_rc6;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms";
+
+ idx = gt0_is_gt ? SAM_MHz : GFX_MHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq";
+
+ idx = gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq";
+
+ goto end;
+ }
+
+next:
+ /* New i915 graphics sysfs knobs */
+ if (!access("/sys/class/drm/card0/gt/gt0/rc6_residency_ms", R_OK)) {
+ gfx_info[GFX_rc6].path = "/sys/class/drm/card0/gt/gt0/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rc6_residency_ms", R_OK))
+ gfx_info[SAM_mc6].path = "/sys/class/drm/card0/gt/gt1/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz", R_OK))
+ gfx_info[SAM_MHz].path = "/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz", R_OK))
+ gfx_info[SAM_ACTMHz].path = "/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz";
+
+ goto end;
+ }
+
+ /* Fall back to traditional i915 graphics sysfs knobs */
if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
+ gfx_info[GFX_rc6].path = "/sys/class/drm/card0/power/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt_cur_freq_mhz";
+ else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz";
+
+
+ if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt_act_freq_mhz";
+ else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz";
+
+end:
+ if (gfx_info[GFX_rc6].path)
BIC_PRESENT(BIC_GFX_rc6);
-
- if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK) ||
- !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
+ if (gfx_info[GFX_MHz].path)
BIC_PRESENT(BIC_GFXMHz);
-
- if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK) ||
- !access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+ if (gfx_info[GFX_ACTMHz].path)
BIC_PRESENT(BIC_GFXACTMHz);
+ if (gfx_info[SAM_mc6].path)
+ BIC_PRESENT(BIC_SAM_mc6);
+ if (gfx_info[SAM_MHz].path)
+ BIC_PRESENT(BIC_SAMMHz);
+ if (gfx_info[SAM_ACTMHz].path)
+ BIC_PRESENT(BIC_SAMACTMHz);
}
static void dump_sysfs_cstate_config(void)
@@ -4783,6 +5646,9 @@
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
if (!has_hwp)
return 0;
@@ -4869,6 +5735,9 @@
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
cpu = t->cpu_id;
/* per-package */
@@ -4983,31 +5852,18 @@
unsigned long long msr;
unsigned int time_unit;
double tdp;
+ const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt;
+ const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J;
- if (rapl_joules) {
- if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
- BIC_PRESENT(BIC_Pkg_J);
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
- BIC_PRESENT(BIC_Cor_J);
- if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
- BIC_PRESENT(BIC_RAM_J);
- if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
- BIC_PRESENT(BIC_GFX_J);
- } else {
- if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
- BIC_PRESENT(BIC_PkgWatt);
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
- BIC_PRESENT(BIC_CorWatt);
- if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
- BIC_PRESENT(BIC_RAMWatt);
- if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
- BIC_PRESENT(BIC_GFXWatt);
- }
+ if (rapl_joules)
+ bic_enabled &= ~bic_watt_bits;
+ else
+ bic_enabled &= ~bic_joules_bits;
- if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS)
- BIC_PRESENT(BIC_PKG__);
- if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS)
- BIC_PRESENT(BIC_RAM__);
+ if (!(platform->rapl_msrs & RAPL_PKG_PERF_STATUS))
+ bic_enabled &= ~BIC_PKG__;
+ if (!(platform->rapl_msrs & RAPL_DRAM_PERF_STATUS))
+ bic_enabled &= ~BIC_RAM__;
/* units on package 0, verify later other packages match */
if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr))
@@ -5041,14 +5897,13 @@
{
unsigned long long msr;
double tdp;
+ const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt;
+ const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J;
- if (rapl_joules) {
- BIC_PRESENT(BIC_Pkg_J);
- BIC_PRESENT(BIC_Cor_J);
- } else {
- BIC_PRESENT(BIC_PkgWatt);
- BIC_PRESENT(BIC_CorWatt);
- }
+ if (rapl_joules)
+ bic_enabled &= ~bic_watt_bits;
+ else
+ bic_enabled &= ~bic_joules_bits;
if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
return;
@@ -5202,7 +6057,7 @@
*/
void probe_rapl(void)
{
- if (!platform->rapl_msrs)
+ if (!platform->rapl_msrs || no_msr)
return;
if (genuine_intel)
@@ -5258,7 +6113,7 @@
}
/* Temperature Target MSR is Nehalem and newer only */
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
goto guess;
if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
@@ -5305,6 +6160,9 @@
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
if (!(do_dts || do_ptm))
return 0;
@@ -5402,6 +6260,9 @@
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!get_msr(base_cpu, MSR_IA32_FEAT_CTL, &msr))
fprintf(outf, "cpu%d: MSR_IA32_FEATURE_CONTROL: 0x%08llx (%sLocked %s)\n",
base_cpu, msr, msr & FEAT_CTL_LOCKED ? "" : "UN-", msr & (1 << 18) ? "SGX" : "");
@@ -5411,6 +6272,9 @@
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!genuine_intel)
return;
@@ -5428,6 +6292,9 @@
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_misc_feature_control)
return;
@@ -5449,6 +6316,9 @@
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_misc_pwr_mgmt)
return;
@@ -5468,6 +6338,9 @@
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_c6_demotion_policy_config)
return;
@@ -5489,7 +6362,8 @@
fd = open(path, O_RDONLY);
if (fd < 0) {
- warnx("capget(CAP_SYS_ADMIN) failed, try \"# setcap cap_sys_admin=ep %s\"", progname);
+ if (debug)
+ warnx("Read %s failed", path);
return;
}
@@ -5504,23 +6378,260 @@
close(fd);
}
+static int has_instr_count_access(void)
+{
+ int fd;
+ int has_access;
+
+ if (no_perf)
+ return 0;
+
+ fd = open_perf_counter(base_cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0);
+ has_access = fd != -1;
+
+ if (fd != -1)
+ close(fd);
+
+ if (!has_access)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "instructions retired perf counter", "--no-perf");
+
+ return has_access;
+}
+
+bool is_aperf_access_required(void)
+{
+ return BIC_IS_ENABLED(BIC_Avg_MHz)
+ || BIC_IS_ENABLED(BIC_Busy)
+ || BIC_IS_ENABLED(BIC_Bzy_MHz)
+ || BIC_IS_ENABLED(BIC_IPC);
+}
+
+int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai,
+ double *scale_, enum rapl_unit *unit_)
+{
+ if (no_perf)
+ return -1;
+
+ const double scale = read_perf_rapl_scale(cai->perf_subsys, cai->perf_name);
+
+ if (scale == 0.0)
+ return -1;
+
+ const enum rapl_unit unit = read_perf_rapl_unit(cai->perf_subsys, cai->perf_name);
+
+ if (unit == RAPL_UNIT_INVALID)
+ return -1;
+
+ const unsigned int rapl_type = read_perf_type(cai->perf_subsys);
+ const unsigned int rapl_energy_pkg_config = read_rapl_config(cai->perf_subsys, cai->perf_name);
+
+ const int fd_counter =
+ open_perf_counter(cpu, rapl_type, rapl_energy_pkg_config, rci->fd_perf, PERF_FORMAT_GROUP);
+ if (fd_counter == -1)
+ return -1;
+
+ /* If it's the first counter opened, make it a group descriptor */
+ if (rci->fd_perf == -1)
+ rci->fd_perf = fd_counter;
+
+ *scale_ = scale;
+ *unit_ = unit;
+ return fd_counter;
+}
+
+int add_rapl_perf_counter(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai,
+ double *scale, enum rapl_unit *unit)
+{
+ int ret = add_rapl_perf_counter_(cpu, rci, cai, scale, unit);
+
+ if (debug)
+ fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu);
+
+ return ret;
+}
+
/*
* Linux-perf manages the HW instructions-retired counter
* by enabling when requested, and hiding rollover
*/
void linux_perf_init(void)
{
- if (!BIC_IS_ENABLED(BIC_IPC))
- return;
-
if (access("/proc/sys/kernel/perf_event_paranoid", F_OK))
return;
- fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int));
- if (fd_instr_count_percpu == NULL)
- err(-1, "calloc fd_instr_count_percpu");
+ if (BIC_IS_ENABLED(BIC_IPC) && has_aperf) {
+ fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int));
+ if (fd_instr_count_percpu == NULL)
+ err(-1, "calloc fd_instr_count_percpu");
+ }
- BIC_PRESENT(BIC_IPC);
+ const bool aperf_required = is_aperf_access_required();
+
+ if (aperf_required && has_aperf && amperf_source == AMPERF_SOURCE_PERF) {
+ fd_amperf_percpu = calloc(topo.max_cpu_num + 1, sizeof(*fd_amperf_percpu));
+ if (fd_amperf_percpu == NULL)
+ err(-1, "calloc fd_amperf_percpu");
+ }
+}
+
+void rapl_perf_init(void)
+{
+ const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages;
+ bool *domain_visited = calloc(num_domains, sizeof(bool));
+
+ rapl_counter_info_perdomain = calloc(num_domains, sizeof(*rapl_counter_info_perdomain));
+ if (rapl_counter_info_perdomain == NULL)
+ err(-1, "calloc rapl_counter_info_percpu");
+
+ /*
+ * Initialize rapl_counter_info_percpu
+ */
+ for (int domain_id = 0; domain_id < num_domains; ++domain_id) {
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain_id];
+
+ rci->fd_perf = -1;
+ for (size_t i = 0; i < NUM_RAPL_COUNTERS; ++i) {
+ rci->data[i] = 0;
+ rci->source[i] = RAPL_SOURCE_NONE;
+ }
+ }
+
+ /*
+ * Open/probe the counters
+ * If can't get it via perf, fallback to MSR
+ */
+ for (size_t i = 0; i < ARRAY_SIZE(rapl_counter_arch_infos); ++i) {
+
+ const struct rapl_counter_arch_info *const cai = &rapl_counter_arch_infos[i];
+ bool has_counter = 0;
+ double scale;
+ enum rapl_unit unit;
+ int next_domain;
+
+ memset(domain_visited, 0, num_domains * sizeof(*domain_visited));
+
+ for (int cpu = 0; cpu < topo.max_cpu_num + 1; ++cpu) {
+
+ if (cpu_is_not_allowed(cpu))
+ continue;
+
+ /* Skip already seen and handled RAPL domains */
+ next_domain =
+ platform->has_per_core_rapl ? cpus[cpu].physical_core_id : cpus[cpu].physical_package_id;
+
+ if (domain_visited[next_domain])
+ continue;
+
+ domain_visited[next_domain] = 1;
+
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[next_domain];
+
+ /* Check if the counter is enabled and accessible */
+ if (BIC_IS_ENABLED(cai->bic) && (platform->rapl_msrs & cai->feature_mask)) {
+
+ /* Use perf API for this counter */
+ if (!no_perf && cai->perf_name
+ && add_rapl_perf_counter(cpu, rci, cai, &scale, &unit) != -1) {
+ rci->source[cai->rci_index] = RAPL_SOURCE_PERF;
+ rci->scale[cai->rci_index] = scale * cai->compat_scale;
+ rci->unit[cai->rci_index] = unit;
+ rci->flags[cai->rci_index] = cai->flags;
+
+ /* Use MSR for this counter */
+ } else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
+ rci->source[cai->rci_index] = RAPL_SOURCE_MSR;
+ rci->msr[cai->rci_index] = cai->msr;
+ rci->msr_mask[cai->rci_index] = cai->msr_mask;
+ rci->msr_shift[cai->rci_index] = cai->msr_shift;
+ rci->unit[cai->rci_index] = RAPL_UNIT_JOULES;
+ rci->scale[cai->rci_index] = *cai->platform_rapl_msr_scale * cai->compat_scale;
+ rci->flags[cai->rci_index] = cai->flags;
+ }
+ }
+
+ if (rci->source[cai->rci_index] != RAPL_SOURCE_NONE)
+ has_counter = 1;
+ }
+
+ /* If any CPU has access to the counter, make it present */
+ if (has_counter)
+ BIC_PRESENT(cai->bic);
+ }
+
+ free(domain_visited);
+}
+
+static int has_amperf_access_via_msr(void)
+{
+ if (no_msr)
+ return 0;
+
+ if (probe_msr(base_cpu, MSR_IA32_APERF))
+ return 0;
+
+ if (probe_msr(base_cpu, MSR_IA32_MPERF))
+ return 0;
+
+ return 1;
+}
+
+static int has_amperf_access_via_perf(void)
+{
+ struct amperf_group_fd fds;
+
+ /*
+ * Cache the last result, so we don't warn the user multiple times
+ *
+ * Negative means cached, no access
+ * Zero means not cached
+ * Positive means cached, has access
+ */
+ static int has_access_cached;
+
+ if (no_perf)
+ return 0;
+
+ if (has_access_cached != 0)
+ return has_access_cached > 0;
+
+ fds = open_amperf_fd(base_cpu);
+ has_access_cached = (fds.aperf != -1) && (fds.mperf != -1);
+
+ if (fds.aperf == -1)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "APERF perf counter", "--no-perf");
+ else
+ close(fds.aperf);
+
+ if (fds.mperf == -1)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "MPERF perf counter", "--no-perf");
+ else
+ close(fds.mperf);
+
+ if (has_access_cached == 0)
+ has_access_cached = -1;
+
+ return has_access_cached > 0;
+}
+
+/* Check if we can access APERF and MPERF */
+static int has_amperf_access(void)
+{
+ if (!is_aperf_access_required())
+ return 0;
+
+ if (!no_msr && has_amperf_access_via_msr())
+ return 1;
+
+ if (!no_perf && has_amperf_access_via_perf())
+ return 1;
+
+ return 0;
}
void probe_cstates(void)
@@ -5563,7 +6674,7 @@
if (platform->has_msr_module_c6_res_ms)
BIC_PRESENT(BIC_Mod_c6);
- if (platform->has_ext_cst_msrs) {
+ if (platform->has_ext_cst_msrs && !no_msr) {
BIC_PRESENT(BIC_Totl_c0);
BIC_PRESENT(BIC_Any_c0);
BIC_PRESENT(BIC_GFX_c0);
@@ -5623,6 +6734,7 @@
unsigned int eax, ebx, ecx, edx;
unsigned int fms, family, model, stepping, ecx_flags, edx_flags;
unsigned long long ucode_patch = 0;
+ bool ucode_patch_valid = false;
eax = ebx = ecx = edx = 0;
@@ -5650,8 +6762,12 @@
ecx_flags = ecx;
edx_flags = edx;
- if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch))
- warnx("get_msr(UCODE)");
+ if (!no_msr) {
+ if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch))
+ warnx("get_msr(UCODE)");
+ else
+ ucode_patch_valid = true;
+ }
/*
* check max extended function levels of CPUID.
@@ -5662,9 +6778,12 @@
__cpuid(0x80000000, max_extended_level, ebx, ecx, edx);
if (!quiet) {
- fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d) microcode 0x%x\n",
- family, model, stepping, family, model, stepping,
- (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF));
+ fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)",
+ family, model, stepping, family, model, stepping);
+ if (ucode_patch_valid)
+ fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF));
+ fputc('\n', outf);
+
fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level);
fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n",
ecx_flags & (1 << 0) ? "SSE3" : "-",
@@ -5700,10 +6819,11 @@
__cpuid(0x6, eax, ebx, ecx, edx);
has_aperf = ecx & (1 << 0);
- if (has_aperf) {
+ if (has_aperf && has_amperf_access()) {
BIC_PRESENT(BIC_Avg_MHz);
BIC_PRESENT(BIC_Busy);
BIC_PRESENT(BIC_Bzy_MHz);
+ BIC_PRESENT(BIC_IPC);
}
do_dts = eax & (1 << 0);
if (do_dts)
@@ -5786,6 +6906,15 @@
base_mhz = max_mhz = bus_mhz = edx = 0;
__cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx);
+
+ bclk = bus_mhz;
+
+ base_hz = base_mhz * 1000000;
+ has_base_hz = 1;
+
+ if (platform->enable_tsc_tweak)
+ tsc_tweak = base_hz / tsc_hz;
+
if (!quiet)
fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n",
base_mhz, max_mhz, bus_mhz);
@@ -5814,7 +6943,7 @@
probe_thermal();
- if (platform->has_nhm_msrs)
+ if (platform->has_nhm_msrs && !no_msr)
BIC_PRESENT(BIC_SMI);
if (!quiet)
@@ -6142,6 +7271,7 @@
topo.allowed_packages = 0;
for_all_cpus(update_topo, ODD_COUNTERS);
}
+
void setup_all_buffers(bool startup)
{
topology_probe(startup);
@@ -6169,21 +7299,129 @@
err(-ENODEV, "No valid cpus found");
}
+static void set_amperf_source(void)
+{
+ amperf_source = AMPERF_SOURCE_PERF;
+
+ const bool aperf_required = is_aperf_access_required();
+
+ if (no_perf || !aperf_required || !has_amperf_access_via_perf())
+ amperf_source = AMPERF_SOURCE_MSR;
+
+ if (quiet || !debug)
+ return;
+
+ fprintf(outf, "aperf/mperf source preference: %s\n", amperf_source == AMPERF_SOURCE_MSR ? "msr" : "perf");
+}
+
+bool has_added_counters(void)
+{
+ /*
+ * It only makes sense to call this after the command line is parsed,
+ * otherwise sys structure is not populated.
+ */
+
+ return sys.added_core_counters | sys.added_thread_counters | sys.added_package_counters;
+}
+
+bool is_msr_access_required(void)
+{
+ if (no_msr)
+ return false;
+
+ if (has_added_counters())
+ return true;
+
+ return BIC_IS_ENABLED(BIC_SMI)
+ || BIC_IS_ENABLED(BIC_CPU_c1)
+ || BIC_IS_ENABLED(BIC_CPU_c3)
+ || BIC_IS_ENABLED(BIC_CPU_c6)
+ || BIC_IS_ENABLED(BIC_CPU_c7)
+ || BIC_IS_ENABLED(BIC_Mod_c6)
+ || BIC_IS_ENABLED(BIC_CoreTmp)
+ || BIC_IS_ENABLED(BIC_Totl_c0)
+ || BIC_IS_ENABLED(BIC_Any_c0)
+ || BIC_IS_ENABLED(BIC_GFX_c0)
+ || BIC_IS_ENABLED(BIC_CPUGFX)
+ || BIC_IS_ENABLED(BIC_Pkgpc3)
+ || BIC_IS_ENABLED(BIC_Pkgpc6)
+ || BIC_IS_ENABLED(BIC_Pkgpc2)
+ || BIC_IS_ENABLED(BIC_Pkgpc7)
+ || BIC_IS_ENABLED(BIC_Pkgpc8)
+ || BIC_IS_ENABLED(BIC_Pkgpc9)
+ || BIC_IS_ENABLED(BIC_Pkgpc10)
+ /* TODO: Multiplex access with perf */
+ || BIC_IS_ENABLED(BIC_CorWatt)
+ || BIC_IS_ENABLED(BIC_Cor_J)
+ || BIC_IS_ENABLED(BIC_PkgWatt)
+ || BIC_IS_ENABLED(BIC_CorWatt)
+ || BIC_IS_ENABLED(BIC_GFXWatt)
+ || BIC_IS_ENABLED(BIC_RAMWatt)
+ || BIC_IS_ENABLED(BIC_Pkg_J)
+ || BIC_IS_ENABLED(BIC_Cor_J)
+ || BIC_IS_ENABLED(BIC_GFX_J)
+ || BIC_IS_ENABLED(BIC_RAM_J)
+ || BIC_IS_ENABLED(BIC_PKG__)
+ || BIC_IS_ENABLED(BIC_RAM__)
+ || BIC_IS_ENABLED(BIC_PkgTmp)
+ || (is_aperf_access_required() && !has_amperf_access_via_perf());
+}
+
+void check_msr_access(void)
+{
+ if (!is_msr_access_required())
+ no_msr = 1;
+
+ check_dev_msr();
+ check_msr_permission();
+
+ if (no_msr)
+ bic_disable_msr_access();
+}
+
+void check_perf_access(void)
+{
+ const bool intrcount_required = BIC_IS_ENABLED(BIC_IPC);
+
+ if (no_perf || !intrcount_required || !has_instr_count_access())
+ bic_enabled &= ~BIC_IPC;
+
+ const bool aperf_required = is_aperf_access_required();
+
+ if (!aperf_required || !has_amperf_access()) {
+ bic_enabled &= ~BIC_Avg_MHz;
+ bic_enabled &= ~BIC_Busy;
+ bic_enabled &= ~BIC_Bzy_MHz;
+ bic_enabled &= ~BIC_IPC;
+ }
+}
+
void turbostat_init()
{
setup_all_buffers(true);
set_base_cpu();
- check_dev_msr();
- check_permissions();
+ check_msr_access();
+ check_perf_access();
process_cpuid();
probe_pm_features();
+ set_amperf_source();
linux_perf_init();
+ rapl_perf_init();
for_all_cpus(get_cpu_type, ODD_COUNTERS);
for_all_cpus(get_cpu_type, EVEN_COUNTERS);
if (DO_BIC(BIC_IPC))
(void)get_instr_count_fd(base_cpu);
+
+ /*
+ * If TSC tweak is needed, but couldn't get it,
+ * disable more BICs, since it can't be reported accurately.
+ */
+ if (platform->enable_tsc_tweak && !has_base_hz) {
+ bic_enabled &= ~BIC_Busy;
+ bic_enabled &= ~BIC_Bzy_MHz;
+ }
}
int fork_it(char **argv)
@@ -6259,7 +7497,7 @@
void print_version()
{
- fprintf(outf, "turbostat version 2023.11.07 - Len Brown <lenb@kernel.org>\n");
+ fprintf(outf, "turbostat version 2024.04.08 - Len Brown <lenb@kernel.org>\n");
}
#define COMMAND_LINE_SIZE 2048
@@ -6291,6 +7529,9 @@
{
struct msr_counter *msrp;
+ if (no_msr && msr_num)
+ errx(1, "Requested MSR counter 0x%x, but in --no-msr mode", msr_num);
+
msrp = calloc(1, sizeof(struct msr_counter));
if (msrp == NULL) {
perror("calloc");
@@ -6595,6 +7836,8 @@
{ "list", no_argument, 0, 'l' },
{ "out", required_argument, 0, 'o' },
{ "quiet", no_argument, 0, 'q' },
+ { "no-msr", no_argument, 0, 'M' },
+ { "no-perf", no_argument, 0, 'P' },
{ "show", required_argument, 0, 's' },
{ "Summary", no_argument, 0, 'S' },
{ "TCC", required_argument, 0, 'T' },
@@ -6604,7 +7847,25 @@
progname = argv[0];
- while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v", long_options, &option_index)) != -1) {
+ /*
+ * Parse some options early, because they may make other options invalid,
+ * like adding the MSR counter with --add and at the same time using --no-msr.
+ */
+ while ((opt = getopt_long_only(argc, argv, "MP", long_options, &option_index)) != -1) {
+ switch (opt) {
+ case 'M':
+ no_msr = 1;
+ break;
+ case 'P':
+ no_perf = 1;
+ break;
+ default:
+ break;
+ }
+ }
+ optind = 0;
+
+ while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qMST:v", long_options, &option_index)) != -1) {
switch (opt) {
case 'a':
parse_add_command(optarg);
@@ -6662,6 +7923,10 @@
case 'q':
quiet = 1;
break;
+ case 'M':
+ case 'P':
+ /* Parsed earlier */
+ break;
case 'n':
num_iterations = strtod(optarg, NULL);
@@ -6704,6 +7969,22 @@
}
}
+void set_rlimit(void)
+{
+ struct rlimit limit;
+
+ if (getrlimit(RLIMIT_NOFILE, &limit) < 0)
+ err(1, "Failed to get rlimit");
+
+ if (limit.rlim_max < MAX_NOFILE)
+ limit.rlim_max = MAX_NOFILE;
+ if (limit.rlim_cur < MAX_NOFILE)
+ limit.rlim_cur = MAX_NOFILE;
+
+ if (setrlimit(RLIMIT_NOFILE, &limit) < 0)
+ err(1, "Failed to set rlimit");
+}
+
int main(int argc, char **argv)
{
int fd, ret;
@@ -6729,9 +8010,13 @@
probe_sysfs();
+ if (!getuid())
+ set_rlimit();
+
turbostat_init();
- msr_sum_record();
+ if (!no_msr)
+ msr_sum_record();
/* dump counters and exit */
if (dump_only)
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index 908e0d0..3482248 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -986,10 +986,12 @@
{
dpa_perf->qos_class = FAKE_QTG_ID;
dpa_perf->dpa_range = *range;
- dpa_perf->coord.read_latency = 500;
- dpa_perf->coord.write_latency = 500;
- dpa_perf->coord.read_bandwidth = 1000;
- dpa_perf->coord.write_bandwidth = 1000;
+ for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) {
+ dpa_perf->coord[i].read_latency = 500;
+ dpa_perf->coord[i].write_latency = 500;
+ dpa_perf->coord[i].read_bandwidth = 1000;
+ dpa_perf->coord[i].write_bandwidth = 1000;
+ }
}
static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port)
@@ -999,6 +1001,7 @@
struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
struct cxl_dev_state *cxlds = cxlmd->cxlds;
struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
+ struct access_coordinate ep_c[ACCESS_COORDINATE_MAX];
struct range pmem_range = {
.start = cxlds->pmem_res.start,
.end = cxlds->pmem_res.end,
@@ -1018,6 +1021,12 @@
dpa_perf_setup(port, &pmem_range, &mds->pmem_perf);
cxl_memdev_update_perf(cxlmd);
+
+ /*
+ * This function is here to only test the topology iterator. It serves
+ * no other purpose.
+ */
+ cxl_endpoint_get_perf_coordinates(port, ep_c);
}
static struct cxl_mock_ops cxl_mock_ops = {
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 39ad96a..edcd261 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -205,6 +205,9 @@
case 5: return (void *)~(1ull << 30); /* trigger extable */
case 6: return &f; /* valid addr */
case 7: return (void *)((long)&f | 1); /* kernel tricks */
+#ifdef CONFIG_X86_64
+ case 8: return (void *)VSYSCALL_ADDR; /* vsyscall page address */
+#endif
default: return NULL;
}
}
diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
index b1ede62..b7c8f29 100644
--- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
+++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc
@@ -18,7 +18,7 @@
yield
-count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
if [ $count -lt 3 ]; then
fail "at least fork, exec and exit events should be recorded"
fi
@@ -29,7 +29,7 @@
yield
-count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
if [ $count -lt 3 ]; then
fail "at least fork, exec and exit events should be recorded"
fi
@@ -40,7 +40,7 @@
yield
-count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
+count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l`
if [ $count -ne 0 ]; then
fail "any of scheduler events should not be recorded"
fi
diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config
index 110d739..02a2a1b 100644
--- a/tools/testing/selftests/iommu/config
+++ b/tools/testing/selftests/iommu/config
@@ -1,3 +1,5 @@
CONFIG_IOMMUFD=y
+CONFIG_FAULT_INJECTION_DEBUG_FS=y
CONFIG_FAULT_INJECTION=y
CONFIG_IOMMUFD_TEST=y
+CONFIG_FAILSLAB=y
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index 541bf19..14bbab0 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -51,6 +51,7 @@
#include <stdarg.h>
#include <string.h>
#include <stdio.h>
+#include <sys/utsname.h>
#endif
#ifndef ARRAY_SIZE
@@ -79,6 +80,9 @@
#define KSFT_XPASS 3
#define KSFT_SKIP 4
+#ifndef __noreturn
+#define __noreturn __attribute__((__noreturn__))
+#endif
#define __printf(a, b) __attribute__((format(printf, a, b)))
/* counters */
@@ -288,24 +292,26 @@
}
/* Docs seem to call for double space if directive is absent */
- if (!directive[0] && msg[0])
+ if (!directive[0] && msg)
directive = " # ";
- va_start(args, msg);
printf("%s %u %s%s", tap_code, ksft_test_num(), test_name, directive);
errno = saved_errno;
- vprintf(msg, args);
+ if (msg) {
+ va_start(args, msg);
+ vprintf(msg, args);
+ va_end(args);
+ }
printf("\n");
- va_end(args);
}
-static inline int ksft_exit_pass(void)
+static inline __noreturn int ksft_exit_pass(void)
{
ksft_print_cnts();
exit(KSFT_PASS);
}
-static inline int ksft_exit_fail(void)
+static inline __noreturn int ksft_exit_fail(void)
{
ksft_print_cnts();
exit(KSFT_FAIL);
@@ -332,7 +338,7 @@
ksft_cnt.ksft_xfail + \
ksft_cnt.ksft_xskip)
-static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...)
+static inline __noreturn __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...)
{
int saved_errno = errno;
va_list args;
@@ -347,19 +353,19 @@
exit(KSFT_FAIL);
}
-static inline int ksft_exit_xfail(void)
+static inline __noreturn int ksft_exit_xfail(void)
{
ksft_print_cnts();
exit(KSFT_XFAIL);
}
-static inline int ksft_exit_xpass(void)
+static inline __noreturn int ksft_exit_xpass(void)
{
ksft_print_cnts();
exit(KSFT_XPASS);
}
-static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...)
+static inline __noreturn __printf(1, 2) int ksft_exit_skip(const char *msg, ...)
{
int saved_errno = errno;
va_list args;
@@ -388,4 +394,21 @@
exit(KSFT_SKIP);
}
+static inline int ksft_min_kernel_version(unsigned int min_major,
+ unsigned int min_minor)
+{
+#ifdef NOLIBC
+ ksft_print_msg("NOLIBC: Can't check kernel version: Function not implemented\n");
+ return 0;
+#else
+ unsigned int major, minor;
+ struct utsname info;
+
+ if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2)
+ ksft_exit_fail_msg("Can't parse kernel version\n");
+
+ return major > min_major || (major == min_major && minor >= min_minor);
+#endif
+}
+
#endif /* __KSELFTEST_H */
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 4fd735e..d98702b 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -56,7 +56,6 @@
#include <asm/types.h>
#include <ctype.h>
#include <errno.h>
-#include <limits.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
@@ -383,6 +382,7 @@
FIXTURE_DATA(fixture_name) self; \
pid_t child = 1; \
int status = 0; \
+ bool jmp = false; \
memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \
if (setjmp(_metadata->env) == 0) { \
/* Use the same _metadata. */ \
@@ -399,8 +399,10 @@
_metadata->exit_code = KSFT_FAIL; \
} \
} \
+ else \
+ jmp = true; \
if (child == 0) { \
- if (_metadata->setup_completed && !_metadata->teardown_parent) \
+ if (_metadata->setup_completed && !_metadata->teardown_parent && !jmp) \
fixture_name##_teardown(_metadata, &self, variant->data); \
_exit(0); \
} \
@@ -1156,7 +1158,7 @@
struct __test_metadata *t)
{
struct __test_xfail *xfail;
- char test_name[LINE_MAX];
+ char *test_name;
const char *diagnostic;
/* reset test struct */
@@ -1164,8 +1166,12 @@
t->trigger = 0;
memset(t->results->reason, 0, sizeof(t->results->reason));
- snprintf(test_name, sizeof(test_name), "%s%s%s.%s",
- f->name, variant->name[0] ? "." : "", variant->name, t->name);
+ if (asprintf(&test_name, "%s%s%s.%s", f->name,
+ variant->name[0] ? "." : "", variant->name, t->name) == -1) {
+ ksft_print_msg("ERROR ALLOCATING MEMORY\n");
+ t->exit_code = KSFT_FAIL;
+ _exit(t->exit_code);
+ }
ksft_print_msg(" RUN %s ...\n", test_name);
@@ -1202,7 +1208,8 @@
diagnostic = "unknown";
ksft_test_result_code(t->exit_code, test_name,
- diagnostic ? "%s" : "", diagnostic);
+ diagnostic ? "%s" : NULL, diagnostic);
+ free(test_name);
}
static int test_harness_run(int argc, char **argv)
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c
index eef816b..ca917c7 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_init.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c
@@ -84,6 +84,18 @@
return v;
}
+static struct vm_gic vm_gic_create_barebones(uint32_t gic_dev_type)
+{
+ struct vm_gic v;
+
+ v.gic_dev_type = gic_dev_type;
+ v.vm = vm_create_barebones();
+ v.gic_fd = kvm_create_device(v.vm, gic_dev_type);
+
+ return v;
+}
+
+
static void vm_gic_destroy(struct vm_gic *v)
{
close(v->gic_fd);
@@ -357,6 +369,40 @@
vm_gic_destroy(&v);
}
+#define KVM_VGIC_V2_ATTR(offset, cpu) \
+ (FIELD_PREP(KVM_DEV_ARM_VGIC_OFFSET_MASK, offset) | \
+ FIELD_PREP(KVM_DEV_ARM_VGIC_CPUID_MASK, cpu))
+
+#define GIC_CPU_CTRL 0x00
+
+static void test_v2_uaccess_cpuif_no_vcpus(void)
+{
+ struct vm_gic v;
+ u64 val = 0;
+ int ret;
+
+ v = vm_gic_create_barebones(KVM_DEV_TYPE_ARM_VGIC_V2);
+ subtest_dist_rdist(&v);
+
+ ret = __kvm_has_device_attr(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS,
+ KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0));
+ TEST_ASSERT(ret && errno == EINVAL,
+ "accessed non-existent CPU interface, want errno: %i",
+ EINVAL);
+ ret = __kvm_device_attr_get(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS,
+ KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0), &val);
+ TEST_ASSERT(ret && errno == EINVAL,
+ "accessed non-existent CPU interface, want errno: %i",
+ EINVAL);
+ ret = __kvm_device_attr_set(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CPU_REGS,
+ KVM_VGIC_V2_ATTR(GIC_CPU_CTRL, 0), &val);
+ TEST_ASSERT(ret && errno == EINVAL,
+ "accessed non-existent CPU interface, want errno: %i",
+ EINVAL);
+
+ vm_gic_destroy(&v);
+}
+
static void test_v3_new_redist_regions(void)
{
struct kvm_vcpu *vcpus[NR_VCPUS];
@@ -675,6 +721,9 @@
test_vcpus_then_vgic(gic_dev_type);
test_vgic_then_vcpus(gic_dev_type);
+ if (VGIC_DEV_IS_V2(gic_dev_type))
+ test_v2_uaccess_cpuif_no_vcpus();
+
if (VGIC_DEV_IS_V3(gic_dev_type)) {
test_v3_new_redist_regions();
test_v3_typer_accesses();
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 6628dc4..1a6da73 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -22,10 +22,11 @@
{
uint64_t gpa;
- for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
- *((volatile uint64_t *)gpa) = gpa;
-
- GUEST_DONE();
+ for (;;) {
+ for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
+ *((volatile uint64_t *)gpa) = gpa;
+ GUEST_SYNC(0);
+ }
}
struct vcpu_info {
@@ -55,7 +56,7 @@
static void run_vcpu(struct kvm_vcpu *vcpu)
{
vcpu_run(vcpu);
- TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+ TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
}
static void *vcpu_worker(void *data)
@@ -64,17 +65,13 @@
struct kvm_vcpu *vcpu = info->vcpu;
struct kvm_vm *vm = vcpu->vm;
struct kvm_sregs sregs;
- struct kvm_regs regs;
vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size);
- /* Snapshot regs before the first run. */
- vcpu_regs_get(vcpu, ®s);
rendezvous_with_boss();
run_vcpu(vcpu);
rendezvous_with_boss();
- vcpu_regs_set(vcpu, ®s);
vcpu_sregs_get(vcpu, &sregs);
#ifdef __x86_64__
/* Toggle CR0.WP to trigger a MMU context reset. */
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 06b43ed..bd57d99 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -333,7 +333,7 @@
struct kvm_vm *vm;
int r, i;
-#if defined __aarch64__ || defined __x86_64__
+#if defined __aarch64__ || defined __riscv || defined __x86_64__
supported_flags |= KVM_MEM_READONLY;
#endif
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
index 29609b5..26c8581 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
@@ -416,12 +416,30 @@
static void guest_test_gp_counters(void)
{
+ uint8_t pmu_version = guest_get_pmu_version();
uint8_t nr_gp_counters = 0;
uint32_t base_msr;
- if (guest_get_pmu_version())
+ if (pmu_version)
nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
+ /*
+ * For v2+ PMUs, PERF_GLOBAL_CTRL's architectural post-RESET value is
+ * "Sets bits n-1:0 and clears the upper bits", where 'n' is the number
+ * of GP counters. If there are no GP counters, require KVM to leave
+ * PERF_GLOBAL_CTRL '0'. This edge case isn't covered by the SDM, but
+ * follow the spirit of the architecture and only globally enable GP
+ * counters, of which there are none.
+ */
+ if (pmu_version > 1) {
+ uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL);
+
+ if (nr_gp_counters)
+ GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0));
+ else
+ GUEST_ASSERT_EQ(global_ctrl, 0);
+ }
+
if (this_cpu_has(X86_FEATURE_PDCM) &&
rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES)
base_msr = MSR_IA32_PMC0;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index 7f6f5f2..977948f 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -28,16 +28,16 @@
#define NESTED_TEST_MEM1 0xc0001000
#define NESTED_TEST_MEM2 0xc0002000
-static void l2_guest_code(void)
+static void l2_guest_code(u64 *a, u64 *b)
{
- *(volatile uint64_t *)NESTED_TEST_MEM1;
- *(volatile uint64_t *)NESTED_TEST_MEM1 = 1;
+ READ_ONCE(*a);
+ WRITE_ONCE(*a, 1);
GUEST_SYNC(true);
GUEST_SYNC(false);
- *(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+ WRITE_ONCE(*b, 1);
GUEST_SYNC(true);
- *(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+ WRITE_ONCE(*b, 1);
GUEST_SYNC(true);
GUEST_SYNC(false);
@@ -45,17 +45,33 @@
vmcall();
}
+static void l2_guest_code_ept_enabled(void)
+{
+ l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2);
+}
+
+static void l2_guest_code_ept_disabled(void)
+{
+ /* Access the same L1 GPAs as l2_guest_code_ept_enabled() */
+ l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM);
+}
+
void l1_guest_code(struct vmx_pages *vmx)
{
#define L2_GUEST_STACK_SIZE 64
unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ void *l2_rip;
GUEST_ASSERT(vmx->vmcs_gpa);
GUEST_ASSERT(prepare_for_vmx_operation(vmx));
GUEST_ASSERT(load_vmcs(vmx));
- prepare_vmcs(vmx, l2_guest_code,
- &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ if (vmx->eptp_gpa)
+ l2_rip = l2_guest_code_ept_enabled;
+ else
+ l2_rip = l2_guest_code_ept_disabled;
+
+ prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
GUEST_SYNC(false);
GUEST_ASSERT(!vmlaunch());
@@ -64,7 +80,7 @@
GUEST_DONE();
}
-int main(int argc, char *argv[])
+static void test_vmx_dirty_log(bool enable_ept)
{
vm_vaddr_t vmx_pages_gva = 0;
struct vmx_pages *vmx;
@@ -76,8 +92,7 @@
struct ucall uc;
bool done = false;
- TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
- TEST_REQUIRE(kvm_cpu_has_ept());
+ pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled");
/* Create VM */
vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
@@ -103,11 +118,16 @@
*
* Note that prepare_eptp should be called only L1's GPA map is done,
* meaning after the last call to virt_map.
+ *
+ * When EPT is disabled, the L2 guest code will still access the same L1
+ * GPAs as the EPT enabled case.
*/
- prepare_eptp(vmx, vm, 0);
- nested_map_memslot(vmx, vm, 0);
- nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
- nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+ if (enable_ept) {
+ prepare_eptp(vmx, vm, 0);
+ nested_map_memslot(vmx, vm, 0);
+ nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
+ nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+ }
bmap = bitmap_zalloc(TEST_MEM_PAGES);
host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
@@ -148,3 +168,15 @@
}
}
}
+
+int main(int argc, char *argv[])
+{
+ TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+
+ test_vmx_dirty_log(/*enable_ept=*/false);
+
+ if (kvm_cpu_has_ept())
+ test_vmx_dirty_log(/*enable_ept=*/true);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c
index 200bedc..1e01d3d 100644
--- a/tools/testing/selftests/mm/mdwe_test.c
+++ b/tools/testing/selftests/mm/mdwe_test.c
@@ -7,6 +7,7 @@
#include <linux/mman.h>
#include <linux/prctl.h>
+#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <sys/auxv.h>
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index 374a308..48dc151 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -54,7 +54,6 @@
u64 shadow_pkey_reg;
int dprint_in_signal;
char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
-char buf[256];
void cat_into_file(char *str, char *file)
{
@@ -1745,42 +1744,6 @@
shadow_pkey_reg = __read_pkey_reg();
}
-pid_t parent_pid;
-
-void restore_settings_atexit(void)
-{
- if (parent_pid == getpid())
- cat_into_file(buf, "/proc/sys/vm/nr_hugepages");
-}
-
-void save_settings(void)
-{
- int fd;
- int err;
-
- if (geteuid())
- return;
-
- fd = open("/proc/sys/vm/nr_hugepages", O_RDONLY);
- if (fd < 0) {
- fprintf(stderr, "error opening\n");
- perror("error: ");
- exit(__LINE__);
- }
-
- /* -1 to guarantee leaving the trailing \0 */
- err = read(fd, buf, sizeof(buf)-1);
- if (err < 0) {
- fprintf(stderr, "error reading\n");
- perror("error: ");
- exit(__LINE__);
- }
-
- parent_pid = getpid();
- atexit(restore_settings_atexit);
- close(fd);
-}
-
int main(void)
{
int nr_iterations = 22;
@@ -1788,7 +1751,6 @@
srand((unsigned int)time(NULL));
- save_settings();
setup_handlers();
printf("has pkeys: %d\n", pkeys_supported);
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index c2c542f..4bdb3a0 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -385,6 +385,7 @@
CATEGORY="ksm" run_test ./ksm_functional_tests
# protection_keys tests
+nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages)
if [ -x ./protection_keys_32 ]
then
CATEGORY="pkey" run_test ./protection_keys_32
@@ -394,6 +395,7 @@
then
CATEGORY="pkey" run_test ./protection_keys_64
fi
+echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
if [ -x ./soft-dirty ]
then
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 6c988bd..d3c7f5f 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -300,7 +300,7 @@
char **addr)
{
size_t i;
- int dummy;
+ int __attribute__((unused)) dummy = 0;
srand(time(NULL));
diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c
index 2fb6dd8..8b984fa 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/proc.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c
@@ -86,7 +86,7 @@
pos = strchr(line, ' ') + 1;
- if (fscanf(fnetstat, type->header_name) == EOF)
+ if (fscanf(fnetstat, "%[^ :]", type->header_name) == EOF)
test_error("fscanf(%s)", type->header_name);
if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != ':')
test_error("Unexpected netstat format (%c)", tmp);
diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c
index 92276f9..e408b92 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/setup.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c
@@ -17,37 +17,37 @@
void __test_msg(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_print_msg(buf);
+ ksft_print_msg("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_ok(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_pass(buf);
+ ksft_test_result_pass("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_fail(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_fail(buf);
+ ksft_test_result_fail("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_xfail(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_xfail(buf);
+ ksft_test_result_xfail("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_error(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_error(buf);
+ ksft_test_result_error("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
void __test_skip(const char *buf)
{
pthread_mutex_lock(&ksft_print_lock);
- ksft_test_result_skip(buf);
+ ksft_test_result_skip("%s", buf);
pthread_mutex_unlock(&ksft_print_lock);
}
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index 7df8b87..a2fe88d 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -256,8 +256,6 @@
static void test_client_active_rst(unsigned int port)
{
- /* one in queue, another accept()ed */
- unsigned int wait_for = backlog + 2;
int i, sk[3], err;
bool is_writable[ARRAY_SIZE(sk)] = {false};
unsigned int last = ARRAY_SIZE(sk) - 1;
@@ -275,16 +273,20 @@
for (i = 0; i < last; i++) {
err = _test_connect_socket(sk[i], this_ip_dest, port,
(i == 0) ? TEST_TIMEOUT_SEC : -1);
-
if (err < 0)
test_error("failed to connect()");
}
- synchronize_threads(); /* 2: connection accept()ed, another queued */
- err = test_wait_fds(sk, last, is_writable, wait_for, TEST_TIMEOUT_SEC);
+ synchronize_threads(); /* 2: two connections: one accept()ed, another queued */
+ err = test_wait_fds(sk, last, is_writable, last, TEST_TIMEOUT_SEC);
if (err < 0)
test_error("test_wait_fds(): %d", err);
+ /* async connect() with third sk to get into request_sock_queue */
+ err = _test_connect_socket(sk[last], this_ip_dest, port, -1);
+ if (err < 0)
+ test_error("failed to connect()");
+
synchronize_threads(); /* 3: close listen socket */
if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
test_fail("Failed to send data on connected socket");
@@ -292,13 +294,14 @@
test_ok("Verified established tcp connection");
synchronize_threads(); /* 4: finishing up */
- err = _test_connect_socket(sk[last], this_ip_dest, port, -1);
- if (err < 0)
- test_error("failed to connect()");
synchronize_threads(); /* 5: closed active sk */
- err = test_wait_fds(sk, ARRAY_SIZE(sk), NULL,
- wait_for, TEST_TIMEOUT_SEC);
+ /*
+ * Wait for 2 connections: one accepted, another in the accept queue,
+ * the one in request_sock_queue won't get fully established, so
+ * doesn't receive an active RST, see inet_csk_listen_stop().
+ */
+ err = test_wait_fds(sk, last, NULL, last, TEST_TIMEOUT_SEC);
if (err < 0)
test_error("select(): %d", err);
diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
index 452de13..517930f 100644
--- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
+++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
@@ -21,7 +21,7 @@
static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info,
const char *tst)
{
- struct tcp_ao_info_opt tmp;
+ struct tcp_ao_info_opt tmp = {};
socklen_t len = sizeof(tmp);
if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, &tmp, &len))
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index 1d975bf..85b3baa 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -34,7 +34,7 @@
#endif
#ifndef UDP_MAX_SEGMENTS
-#define UDP_MAX_SEGMENTS (1 << 6UL)
+#define UDP_MAX_SEGMENTS (1 << 7UL)
#endif
#define CONST_MTU_TEST 1500
diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
index 505294d..d6f99eb 100644
--- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
+++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c
@@ -154,7 +154,7 @@
static int papr_vpd_close_handle_without_reading(void)
{
const int devfd = open(DEVPATH, O_RDONLY);
- struct papr_location_code lc;
+ struct papr_location_code lc = { .str = "", };
int fd;
SKIP_IF_MSG(devfd < 0 && errno == ENOENT,
diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c
index c537d52..a40541b 100644
--- a/tools/testing/selftests/riscv/hwprobe/cbo.c
+++ b/tools/testing/selftests/riscv/hwprobe/cbo.c
@@ -19,7 +19,7 @@
#include "hwprobe.h"
#include "../../kselftest.h"
-#define MK_CBO(fn) cpu_to_le32((fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15)
+#define MK_CBO(fn) le32_bswap((uint32_t)(fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15)
static char mem[4096] __aligned(4096) = { [0 ... 4095] = 0xa5 };
diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.h b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
index e3fccb3..f3de970 100644
--- a/tools/testing/selftests/riscv/hwprobe/hwprobe.h
+++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h
@@ -4,6 +4,16 @@
#include <stddef.h>
#include <asm/hwprobe.h>
+#if __BYTE_ORDER == __BIG_ENDIAN
+# define le32_bswap(_x) \
+ ((((_x) & 0x000000ffU) << 24) | \
+ (((_x) & 0x0000ff00U) << 8) | \
+ (((_x) & 0x00ff0000U) >> 8) | \
+ (((_x) & 0xff000000U) >> 24))
+#else
+# define le32_bswap(_x) (_x)
+#endif
+
/*
* Rather than relying on having a new enough libc to define this, just do it
* ourselves. This way we don't need to be coupled to a new-enough libc to
diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
index b5d592d..d975a67 100644
--- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c
+++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
@@ -158,6 +158,20 @@
/* In preparation for sigreturn. */
SYSCALL_DISPATCH_OFF(glob_sel);
+
+ /*
+ * The tests for argument handling assume that `syscall(x) == x`. This
+ * is a NOP on x86 because the syscall number is passed in %rax, which
+ * happens to also be the function ABI return register. Other
+ * architectures may need to swizzle the arguments around.
+ */
+#if defined(__riscv)
+/* REG_A7 is not defined in libc headers */
+# define REG_A7 (REG_A0 + 7)
+
+ ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A0] =
+ ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A7];
+#endif
}
TEST(dispatch_and_return)
diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
index d49dd3f..c001dd7 100644
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -66,7 +66,7 @@
diff = end.tv_usec - start.tv_usec;
diff += (end.tv_sec - start.tv_sec) * USECS_PER_SEC;
- if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) {
+ if (llabs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) {
printf("Diff too high: %lld..", diff);
return -1;
}
@@ -184,80 +184,71 @@
return 0;
}
-int remain;
-__thread int got_signal;
+static pthread_t ctd_thread;
+static volatile int ctd_count, ctd_failed;
-static void *distribution_thread(void *arg)
+static void ctd_sighandler(int sig)
{
- while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
- return NULL;
+ if (pthread_self() != ctd_thread)
+ ctd_failed = 1;
+ ctd_count--;
}
-static void distribution_handler(int nr)
+static void *ctd_thread_func(void *arg)
{
- if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED))
- __atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED);
-}
-
-/*
- * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID
- * timer signals. This primarily tests that the kernel does not favour any one.
- */
-static int check_timer_distribution(void)
-{
- int err, i;
- timer_t id;
- const int nthreads = 10;
- pthread_t threads[nthreads];
struct itimerspec val = {
.it_value.tv_sec = 0,
.it_value.tv_nsec = 1000 * 1000,
.it_interval.tv_sec = 0,
.it_interval.tv_nsec = 1000 * 1000,
};
+ timer_t id;
- remain = nthreads + 1; /* worker threads + this thread */
- signal(SIGALRM, distribution_handler);
- err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id);
- if (err < 0) {
- ksft_perror("Can't create timer");
- return -1;
- }
- err = timer_settime(id, 0, &val, NULL);
- if (err < 0) {
- ksft_perror("Can't set timer");
- return -1;
- }
+ /* 1/10 seconds to ensure the leader sleeps */
+ usleep(10000);
- for (i = 0; i < nthreads; i++) {
- err = pthread_create(&threads[i], NULL, distribution_thread,
- NULL);
- if (err) {
- ksft_print_msg("Can't create thread: %s (%d)\n",
- strerror(errno), errno);
- return -1;
- }
- }
+ ctd_count = 100;
+ if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id))
+ return "Can't create timer\n";
+ if (timer_settime(id, 0, &val, NULL))
+ return "Can't set timer\n";
- /* Wait for all threads to receive the signal. */
- while (__atomic_load_n(&remain, __ATOMIC_RELAXED));
+ while (ctd_count > 0 && !ctd_failed)
+ ;
- for (i = 0; i < nthreads; i++) {
- err = pthread_join(threads[i], NULL);
- if (err) {
- ksft_print_msg("Can't join thread: %s (%d)\n",
- strerror(errno), errno);
- return -1;
- }
- }
+ if (timer_delete(id))
+ return "Can't delete timer\n";
- if (timer_delete(id)) {
- ksft_perror("Can't delete timer");
- return -1;
- }
+ return NULL;
+}
- ksft_test_result_pass("check_timer_distribution\n");
+/*
+ * Test that only the running thread receives the timer signal.
+ */
+static int check_timer_distribution(void)
+{
+ const char *errmsg;
+
+ signal(SIGALRM, ctd_sighandler);
+
+ errmsg = "Can't create thread\n";
+ if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL))
+ goto err;
+
+ errmsg = "Can't join thread\n";
+ if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg)
+ goto err;
+
+ if (!ctd_failed)
+ ksft_test_result_pass("check signal distribution\n");
+ else if (ksft_min_kernel_version(6, 3))
+ ksft_test_result_fail("check signal distribution\n");
+ else
+ ksft_test_result_skip("check signal distribution (old kernel)\n");
return 0;
+err:
+ ksft_print_msg("%s", errmsg);
+ return -1;
}
int main(int argc, char **argv)
diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c
index 48b9a80..d13ebde 100644
--- a/tools/testing/selftests/timers/valid-adjtimex.c
+++ b/tools/testing/selftests/timers/valid-adjtimex.c
@@ -21,9 +21,6 @@
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
-
-
-
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
@@ -62,45 +59,47 @@
#define NUM_FREQ_OUTOFRANGE 4
#define NUM_FREQ_INVALID 2
+#define SHIFTED_PPM (1 << 16)
+
long valid_freq[NUM_FREQ_VALID] = {
- -499<<16,
- -450<<16,
- -400<<16,
- -350<<16,
- -300<<16,
- -250<<16,
- -200<<16,
- -150<<16,
- -100<<16,
- -75<<16,
- -50<<16,
- -25<<16,
- -10<<16,
- -5<<16,
- -1<<16,
+ -499 * SHIFTED_PPM,
+ -450 * SHIFTED_PPM,
+ -400 * SHIFTED_PPM,
+ -350 * SHIFTED_PPM,
+ -300 * SHIFTED_PPM,
+ -250 * SHIFTED_PPM,
+ -200 * SHIFTED_PPM,
+ -150 * SHIFTED_PPM,
+ -100 * SHIFTED_PPM,
+ -75 * SHIFTED_PPM,
+ -50 * SHIFTED_PPM,
+ -25 * SHIFTED_PPM,
+ -10 * SHIFTED_PPM,
+ -5 * SHIFTED_PPM,
+ -1 * SHIFTED_PPM,
-1000,
- 1<<16,
- 5<<16,
- 10<<16,
- 25<<16,
- 50<<16,
- 75<<16,
- 100<<16,
- 150<<16,
- 200<<16,
- 250<<16,
- 300<<16,
- 350<<16,
- 400<<16,
- 450<<16,
- 499<<16,
+ 1 * SHIFTED_PPM,
+ 5 * SHIFTED_PPM,
+ 10 * SHIFTED_PPM,
+ 25 * SHIFTED_PPM,
+ 50 * SHIFTED_PPM,
+ 75 * SHIFTED_PPM,
+ 100 * SHIFTED_PPM,
+ 150 * SHIFTED_PPM,
+ 200 * SHIFTED_PPM,
+ 250 * SHIFTED_PPM,
+ 300 * SHIFTED_PPM,
+ 350 * SHIFTED_PPM,
+ 400 * SHIFTED_PPM,
+ 450 * SHIFTED_PPM,
+ 499 * SHIFTED_PPM,
};
long outofrange_freq[NUM_FREQ_OUTOFRANGE] = {
- -1000<<16,
- -550<<16,
- 550<<16,
- 1000<<16,
+ -1000 * SHIFTED_PPM,
+ -550 * SHIFTED_PPM,
+ 550 * SHIFTED_PPM,
+ 1000 * SHIFTED_PPM,
};
#define LONG_MAX (~0UL>>1)
diff --git a/tools/testing/selftests/turbostat/defcolumns.py b/tools/testing/selftests/turbostat/defcolumns.py
new file mode 100755
index 0000000..d9b0420
--- /dev/null
+++ b/tools/testing/selftests/turbostat/defcolumns.py
@@ -0,0 +1,60 @@
+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+from shutil import which
+
+turbostat = which('turbostat')
+if turbostat is None:
+ print('Could not find turbostat binary')
+ exit(1)
+
+timeout = which('timeout')
+if timeout is None:
+ print('Could not find timeout binary')
+ exit(1)
+
+proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+
+#
+# By default --list reports also "usec" and "Time_Of_Day_Seconds" columns
+# which are only visible when running with --debug.
+#
+expected_columns_debug = proc_turbostat.stdout.replace(b',', b'\t').strip()
+expected_columns = expected_columns_debug.replace(b'usec\t', b'').replace(b'Time_Of_Day_Seconds\t', b'').replace(b'X2APIC\t', b'').replace(b'APIC\t', b'')
+
+#
+# Run turbostat with no options for 10 seconds and send SIGINT
+#
+timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '1s']
+turbostat_argv = [turbostat, '-i', '0.250']
+
+print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True)
+proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+actual_columns = proc_turbostat.stdout.split(b'\n')[0]
+if expected_columns != actual_columns:
+ print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}')
+ exit(1)
+print('OK')
+
+#
+# Same, but with --debug
+#
+turbostat_argv.append('--debug')
+
+print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True)
+proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+actual_columns = proc_turbostat.stdout.split(b'\n')[0]
+if expected_columns_debug != actual_columns:
+ print(f'turbostat column check failed\n{expected_columns_debug=}\n{actual_columns=}')
+ exit(1)
+print('OK')
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fb49c2a..ff0a205 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -832,8 +832,7 @@
* mn_active_invalidate_count (see above) instead of
* mmu_invalidate_in_progress.
*/
- gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
- hva_range.may_block);
+ gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end);
/*
* If one or more memslots were found and thus zapped, notify arch code
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index ecefc7e..715f196 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -26,13 +26,11 @@
#ifdef CONFIG_HAVE_KVM_PFNCACHE
void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
unsigned long start,
- unsigned long end,
- bool may_block);
+ unsigned long end);
#else
static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
unsigned long start,
- unsigned long end,
- bool may_block)
+ unsigned long end)
{
}
#endif /* HAVE_KVM_PFNCACHE */
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index 4e07112..e3453e8 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -23,7 +23,7 @@
* MMU notifier 'invalidate_range_start' hook.
*/
void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
- unsigned long end, bool may_block)
+ unsigned long end)
{
struct gfn_to_pfn_cache *gpc;
@@ -57,6 +57,19 @@
spin_unlock(&kvm->gpc_lock);
}
+static bool kvm_gpc_is_valid_len(gpa_t gpa, unsigned long uhva,
+ unsigned long len)
+{
+ unsigned long offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) :
+ offset_in_page(gpa);
+
+ /*
+ * The cached access must fit within a single page. The 'len' argument
+ * to activate() and refresh() exists only to enforce that.
+ */
+ return offset + len <= PAGE_SIZE;
+}
+
bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len)
{
struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
@@ -74,7 +87,7 @@
if (kvm_is_error_hva(gpc->uhva))
return false;
- if (offset_in_page(gpc->uhva) + len > PAGE_SIZE)
+ if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len))
return false;
if (!gpc->valid)
@@ -232,8 +245,7 @@
return -EFAULT;
}
-static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva,
- unsigned long len)
+static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva)
{
unsigned long page_offset;
bool unmap_old = false;
@@ -247,15 +259,6 @@
if (WARN_ON_ONCE(kvm_is_error_gpa(gpa) == kvm_is_error_hva(uhva)))
return -EINVAL;
- /*
- * The cached acces must fit within a single page. The 'len' argument
- * exists only to enforce that.
- */
- page_offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) :
- offset_in_page(gpa);
- if (page_offset + len > PAGE_SIZE)
- return -EINVAL;
-
lockdep_assert_held(&gpc->refresh_lock);
write_lock_irq(&gpc->lock);
@@ -270,6 +273,8 @@
old_uhva = PAGE_ALIGN_DOWN(gpc->uhva);
if (kvm_is_error_gpa(gpa)) {
+ page_offset = offset_in_page(uhva);
+
gpc->gpa = INVALID_GPA;
gpc->memslot = NULL;
gpc->uhva = PAGE_ALIGN_DOWN(uhva);
@@ -279,6 +284,8 @@
} else {
struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
+ page_offset = offset_in_page(gpa);
+
if (gpc->gpa != gpa || gpc->generation != slots->generation ||
kvm_is_error_hva(gpc->uhva)) {
gfn_t gfn = gpa_to_gfn(gpa);
@@ -354,6 +361,9 @@
guard(mutex)(&gpc->refresh_lock);
+ if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len))
+ return -EINVAL;
+
/*
* If the GPA is valid then ignore the HVA, as a cache can be GPA-based
* or HVA-based, not both. For GPA-based caches, the HVA will be
@@ -361,7 +371,7 @@
*/
uhva = kvm_is_error_gpa(gpc->gpa) ? gpc->uhva : KVM_HVA_ERR_BAD;
- return __kvm_gpc_refresh(gpc, gpc->gpa, uhva, len);
+ return __kvm_gpc_refresh(gpc, gpc->gpa, uhva);
}
void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm)
@@ -381,6 +391,9 @@
{
struct kvm *kvm = gpc->kvm;
+ if (!kvm_gpc_is_valid_len(gpa, uhva, len))
+ return -EINVAL;
+
guard(mutex)(&gpc->refresh_lock);
if (!gpc->active) {
@@ -400,11 +413,18 @@
gpc->active = true;
write_unlock_irq(&gpc->lock);
}
- return __kvm_gpc_refresh(gpc, gpa, uhva, len);
+ return __kvm_gpc_refresh(gpc, gpa, uhva);
}
int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len)
{
+ /*
+ * Explicitly disallow INVALID_GPA so that the magic value can be used
+ * by KVM to differentiate between GPA-based and HVA-based caches.
+ */
+ if (WARN_ON_ONCE(kvm_is_error_gpa(gpa)))
+ return -EINVAL;
+
return __kvm_gpc_activate(gpc, gpa, KVM_HVA_ERR_BAD, len);
}
