diff --git a/.github/workflows/run-schedulers b/.github/workflows/run-schedulers index 0aa3ffea3bff7..fc1f92270f597 100755 --- a/.github/workflows/run-schedulers +++ b/.github/workflows/run-schedulers @@ -16,6 +16,26 @@ if [ ! -x `which vng` ]; then exit 1 fi +function runtest() { + local bin="${1}" + + if [ -z "${bin}" ]; then + echo "No binary passed to runtest" + exit 1 + fi + + if ! [ -f "${bin}" ]; then + echo "Binary ${bin} was not a regular file" + exit 1 + fi + + rm -f /tmp/output + (timeout --foreground --preserve-status ${GUEST_TIMEOUT} \ + vng --force-9p --verbose -- \ + "timeout --foreground --preserve-status ${TEST_TIMEOUT} ${bin}" \ + 2>&1 &1 Alexei Starovoitov Alexei Starovoitov Alexey Makhalov +Alex Elder +Alex Elder +Alex Elder +Alex Elder +Alex Elder +Alex Elder +Alex Elder +Alex Elder +Alex Elder +Alex Elder Alex Hung Alex Shi Alex Shi @@ -98,6 +108,8 @@ Ben Widawsky Ben Widawsky Ben Widawsky Benjamin Poirier +Benjamin Tissoires +Benjamin Tissoires Bjorn Andersson Bjorn Andersson Bjorn Andersson @@ -500,6 +512,7 @@ Praveen BP Pradeep Kumar Chitrapu Prasad Sodagudi Punit Agrawal +Puranjay Mohan Qais Yousef Qais Yousef Quentin Monnet diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 902ecd92a29fb..213d0719e2b7a 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3423,6 +3423,9 @@ 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 diff --git a/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst b/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst index d3504826f4015..c389d4fd7599d 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 @@ The essence of the process (aka 'TL;DR') ======================================== *[If you are new to building or bisecting Linux, ignore this section and head -over to the* ":ref:`step-by-step guide`" *below. It utilizes +over to the* ':ref:`step-by-step guide `' *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 @@ aspects, all of which might be essential in your present case.]* **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 @@ will be considered the 'good' release and used to prepare the .config file. 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 @@ will be considered the 'good' release and used to prepare the .config file. 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 @@ will be considered the 'good' release and used to prepare the .config file. 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 @@ will be considered the 'good' release and used to prepare the .config file. * **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 @@ will be considered the 'good' release and used to prepare the .config file. 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 @@ will be considered the 'good' release and used to prepare the .config file. 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 @@ will be considered the 'good' release and used to prepare the .config file. 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 @@ report; instead of the latter your could also head straight on and follow *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.` + :ref:`Preparations: set up everything to build your own kernels `. - :ref:`Segment 1: try to reproduce the problem with the latest codebase.` + :ref:`Segment 1: try to reproduce the problem with the latest codebase `. - :ref:`Segment 2: check if the kernels you build work fine.` + :ref:`Segment 2: check if the kernels you build work fine `. - :ref:`Segment 3: perform a bisection and validate the result.` + :ref:`Segment 3: perform a bisection and validate the result `. - :ref:`Supplementary tasks: cleanup during and after following this guide.` + :ref:`Complementary tasks: cleanup during and after following this guide `. + + :ref:`Optional tasks: test reverts, patches, or later versions `. 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 @@ to get things rolling again. 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 `. .. _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 ` 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`] + [:ref:`details `] .. _vanilla_bissbs: @@ -265,7 +293,7 @@ Preparations: set up everything to build your own kernels 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`] + [:ref:`details `] .. _secureboot_bissbs: @@ -276,48 +304,49 @@ Preparations: set up everything to build your own kernels their restrictions through a process initiated by ``mokutil --disable-validation``. - [:ref:`details`] + [:ref:`details `] .. _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`] + [:ref:`details `] .. _bootworking_bissbs: * Boot into the 'working' kernel and briefly use the apparently broken feature. - [:ref:`details`] + [:ref:`details `] .. _diskspace_bissbs: @@ -327,7 +356,7 @@ Preparations: set up everything to build your own kernels 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`] + [:ref:`details `] .. _buildrequires_bissbs: @@ -337,7 +366,7 @@ Preparations: set up everything to build your own kernels reference section shows how to quickly install those on various popular Linux distributions. - [:ref:`details`] + [:ref:`details `] .. _sources_bissbs: @@ -360,14 +389,23 @@ Preparations: set up everything to build your own kernels git remote add -t master stable \ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git - [:ref:`details`] + [:ref:`details `] + +.. _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 @@ Preparations: set up everything to build your own kernels 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 @@ Preparations: set up everything to build your own kernels 'make olddefconfig' again and check if it now picked up the right config file as base. - [:ref:`details`] + [:ref:`details `] .. _localmodconfig_bissbs: @@ -432,7 +470,7 @@ Preparations: set up everything to build your own kernels spending much effort on, as long as it boots and allows to properly test the feature that causes trouble. - [:ref:`details`] + [:ref:`details `] .. _tagging_bissbs: @@ -442,7 +480,7 @@ Preparations: set up everything to build your own kernels ./scripts/config --set-str CONFIG_LOCALVERSION '-local' ./scripts/config -e CONFIG_LOCALVERSION_AUTO - [:ref:`details`] + [:ref:`details `] .. _debugsymbols_bissbs: @@ -461,7 +499,7 @@ Preparations: set up everything to build your own kernels ./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`] + [:ref:`details `] .. _configmods_bissbs: @@ -471,14 +509,14 @@ Preparations: set up everything to build your own kernels * Are you running Debian? Then you want to avoid known problems by performing additional adjustments explained in the reference section. - [:ref:`details`]. + [:ref:`details `]. * 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`]. + [:ref:`details `]. .. _saveconfig_bissbs: @@ -488,7 +526,7 @@ Preparations: set up everything to build your own kernels make olddefconfig cp .config ~/kernel-config-working - [:ref:`details`] + [:ref:`details `] .. _introlatestcheck_bissbs: @@ -498,16 +536,30 @@ Segment 1: try to reproduce the problem with the latest codebase 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`] +be a waste of time. [:ref:`details `] .. _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 `_: 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):: + + 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. - [:ref:`details`] + * In all other cases, run:: + + cd ~/linux/ + git switch --discard-changes --detach mainline/master + + [:ref:`details `] .. _build_bissbs: @@ -522,7 +574,7 @@ be a waste of time. [:ref:`details`] reference section for alternatives, which obviously will require other steps to install as well. - [:ref:`details`] + [:ref:`details `] .. _install_bissbs: @@ -555,7 +607,7 @@ be a waste of time. [:ref:`details`] 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`] + [:ref:`details `] .. _storagespace_bissbs: @@ -568,7 +620,7 @@ be a waste of time. [:ref:`details`] 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`] + [:ref:`details `] .. _kernelrelease_bissbs: @@ -595,7 +647,7 @@ be a waste of time. [:ref:`details`] If that command does not return '0', check the reference section, as the cause for this might interfere with your testing. - [:ref:`details`] + [:ref:`details `] .. _recheckbroken_bissbs: @@ -603,21 +655,19 @@ be a waste of time. [:ref:`details`] out the instructions in the reference section to ensure nothing went sideways during your tests. - [:ref:`details`] + [:ref:`details `] .. _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 `_ 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 @@ be a waste of time. [:ref:`details`] 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`] + [:ref:`details `] 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`. +:ref:`Complementary tasks: cleanup during and after following this guide `. In case you face a regression, move on and execute at least the next segment as well. @@ -658,7 +710,7 @@ Segment 2: check if the kernels you build work fine 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`] +otherwise would be a waste of time. [:ref:`details `] .. _recheckworking_bissbs: @@ -669,7 +721,7 @@ otherwise would be a waste of time. [:ref:`details`] '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 @@ otherwise would be a waste of time. [:ref:`details`] Now check if this kernel works as expected; if not, consult the reference section for further instructions. - [:ref:`details`] + [:ref:`details `] .. _introbisect_bissbs: @@ -703,18 +755,11 @@ Segment 3: perform the bisection and validate the result 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 @@ each kernel on commodity x86 machines. git bisect good v6.0 git bisect bad v6.1.5 - [:ref:`details`] + [:ref:`details `] .. _bisectbuild_bissbs: @@ -745,7 +790,7 @@ each kernel on commodity x86 machines. 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 @@ each kernel on commodity x86 machines. 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`] + [:ref:`details `] .. _bisecttest_bissbs: @@ -794,7 +839,7 @@ each kernel on commodity x86 machines. might need to scroll up to see the message mentioning the culprit; alternatively, run ``git bisect log > ~/bisection-log``. - [:ref:`details`] + [:ref:`details `] .. _bisectlog_bissbs: @@ -806,7 +851,7 @@ each kernel on commodity x86 machines. cp .config ~/bisection-config-culprit git bisect reset - [:ref:`details`] + [:ref:`details `] .. _revert_bissbs: @@ -823,16 +868,16 @@ each kernel on commodity x86 machines. 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 @@ each kernel on commodity x86 machines. 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`] + [:ref:`details `] .. _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 @@ space might run out. kernel image and related files behind; in that case remove them as described in the reference section. - [:ref:`details`] + [:ref:`details `] .. _finishingtouch_bissbs: @@ -926,18 +977,99 @@ space might run out. the version considered 'good', and the last three or four you compiled during the actual bisection process. - [:ref:`details`] + [:ref:`details `] + +.. _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 `] .. _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 ), 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 @@ Reference section for the step-by-step guide 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:`... `] + +The steps in all later sections of this guide depend on those described here. + +[:ref:`back to step-by-step guide `]. + .. _backup_bisref: Prepare for emergencies ------------------------ +~~~~~~~~~~~~~~~~~~~~~~~ *Create a fresh backup and put system repair and restore tools at hand.* [:ref:`... `] @@ -966,7 +1108,7 @@ for something going sideways, even if that should not happen. .. _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:`...`] @@ -984,7 +1126,7 @@ explains in more detail. .. _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 @@ Afterwards, permit MokManager to reboot the machine. .. _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:`...`] @@ -1034,7 +1176,7 @@ the right thing. .. _diskspace_bisref: Space requirements ------------------- +~~~~~~~~~~~~~~~~~~ *Ensure to have enough free space for building Linux.* [:ref:`... `] @@ -1052,32 +1194,32 @@ space by quite a few gigabytes. .. _rangecheck_bisref: Bisection range ---------------- +~~~~~~~~~~~~~~~ *Determine the kernel versions considered 'good' and 'bad' throughout this guide.* [:ref:`...`] 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 `] .. _buildrequires_bisref: Install build requirements --------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~ *Install all software required to build a Linux kernel.* [:ref:`...`] @@ -1117,7 +1259,7 @@ These commands install a few packages that are often, but not always needed. You 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 @@ the kernel's tools/ directory. .. _sources_bisref: Download the sources using Git ------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Retrieve the Linux mainline sources.* [:ref:`...`] @@ -1148,7 +1290,7 @@ work better for you: .. _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 @@ First, execute the following command to retrieve the latest mainline codebase:: 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 @@ Note, shallow clones have a few peculiar characteristics: .. _oldconfig_bisref: Start defining the build configuration for your kernel ------------------------------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Start preparing a kernel build configuration (the '.config' file).* [:ref:`... `] @@ -1279,7 +1421,7 @@ that file to the build machine and store it as ~/linux/.config; afterwards run .. _localmodconfig_bisref: Trim the build configuration for your kernel --------------------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Disable any kernel modules apparently superfluous for your setup.* [:ref:`... `] @@ -1328,7 +1470,7 @@ step-by-step guide mentions:: .. _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:`... `] @@ -1344,7 +1486,7 @@ confusing during the bisection. .. _debugsymbols_bisref: Decide to enable or disable debug symbols ------------------------------------------ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Decide how to handle debug symbols.* [:ref:`... `] @@ -1373,7 +1515,7 @@ explains this process in more detail. .. _configmods_bisref: Adjust build configuration --------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~ *Check if you may want or need to adjust some other kernel configuration options:* @@ -1384,7 +1526,7 @@ kernel configuration options. .. _configmods_distros_bisref: Distro specific adjustments -~~~~~~~~~~~~~~~~~~~~~~~~~~~ +""""""""""""""""""""""""""" *Are you running* [:ref:`... `] @@ -1409,7 +1551,7 @@ when following this guide on a few commodity distributions. .. _configmods_individual_bisref: Individual adjustments -~~~~~~~~~~~~~~~~~~~~~~ +"""""""""""""""""""""" *If you want to influence the other aspects of the configuration, do so now.* [:ref:`... `] @@ -1426,13 +1568,13 @@ is missing. .. _saveconfig_bisref: Put the .config file aside --------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~ *Reprocess the .config after the latest changes and store it in a safe place.* [:ref:`... `] 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 @@ meaningless. .. _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:`... `] @@ -1490,28 +1632,28 @@ highly recommended for these reasons: 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 `] .. _checkoutmaster_bisref: Check out the latest Linux codebase ------------------------------------ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Check out the latest Linux codebase.* - [:ref:`... `] + [:ref:`... `] 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 `] +[:ref:`back to step-by-step guide `] .. _build_bisref: Build your kernel ------------------ +~~~~~~~~~~~~~~~~~ *Build the image and the modules of your first kernel using the config file you prepared.* [:ref:`... `] @@ -1521,7 +1663,7 @@ yourself. Another subsection explains how to directly package your kernel up as 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 @@ by modifying your search terms or using another line from the error messages. 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 @@ distribution's kernel packages. .. _install_bisref: Put the kernel in place ------------------------ +~~~~~~~~~~~~~~~~~~~~~~~ *Install the kernel you just built.* [:ref:`... `] @@ -1630,7 +1772,7 @@ process. Afterwards add your kernel to your bootloader configuration and reboot. .. _storagespace_bisref: Storage requirements per kernel -------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Check how much storage space the kernel, its modules, and other related files like the initramfs consume.* [:ref:`... `] @@ -1651,7 +1793,7 @@ need to look in different places. .. _tainted_bisref: Check if your newly built kernel considers itself 'tainted' ------------------------------------------------------------ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Check if the kernel marked itself as 'tainted'.* [:ref:`... `] @@ -1670,7 +1812,7 @@ interest, as your testing might be flawed otherwise. .. _recheckbroken_bisref: Check the kernel built from a recent mainline codebase ------------------------------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Verify if your bug occurs with the newly built kernel.* [:ref:`... `] @@ -1696,7 +1838,7 @@ the kernel you built from the latest codebase. These are the most frequent: .. _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 @@ ensure the kernel version you assumed to be 'good' earlier in the process (e.g. .. _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:`... `] @@ -1767,15 +1909,25 @@ multitude of reasons why this might happen. Some ideas where to look: 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 `] +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:`... `] + +The steps in this segment perform and validate the bisection. + +[:ref:`back to step-by-step guide `]. + .. _bisectstart_bisref: Start the bisection -------------------- +~~~~~~~~~~~~~~~~~~~ *Start the bisection and tell Git about the versions earlier established as 'good' and 'bad'.* [:ref:`... `] @@ -1789,7 +1941,7 @@ for you to test. .. _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:`... `] @@ -1817,7 +1969,7 @@ There are two things worth of note here: .. _bisecttest_bisref: Bisection checkpoint --------------------- +~~~~~~~~~~~~~~~~~~~~ *Check if the feature that regressed works in the kernel you just built.* [:ref:`... `] @@ -1831,7 +1983,7 @@ will be for nothing. .. _bisectlog_bisref: Put the bisection log away --------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~ *Store Git's bisection log and the current .config file in a safe place.* [:ref:`... `] @@ -1851,7 +2003,7 @@ ask for it after you report the regression. .. _revert_bisref: Try reverting the culprit -------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~ *Try reverting the culprit on top of the latest codebase to see if this fixes your regression.* [:ref:`... `] @@ -1869,14 +2021,20 @@ succeeds, test that kernel version instead. [:ref:`back to step-by-step guide `] +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:`... `] + +The steps in this section describe clean-up procedures. + +[:ref:`back to step-by-step guide `]. .. _makeroom_bisref: Cleaning up during the bisection --------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *To remove one of the kernels you installed, look up its 'kernelrelease' identifier.* [:ref:`... `] @@ -1911,13 +2069,13 @@ Now remove the boot entry for the kernel from your bootloader's configuration; 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 `] Cleaning up after the bisection -------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ .. _finishingtouch_bisref: @@ -1932,26 +2090,105 @@ build artifacts and the Linux sources, but will leave the Git repository (~/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 -`` or ``git am `` 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 `. 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 `] +.. _introoptional_bisref: -Additional reading material -=========================== +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:`... `] + +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 `]. + + +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 `', 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 `' 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 [...] `'). + +* When you reach ':ref:`Start preparing a kernel build configuration[...] + `': 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 `' use the following command instead:: -Further sources ---------------- + 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 `; 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 +--------------------------- * The `man page for 'git bisect' `_ and `fighting regressions with 'git bisect' `_ diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index ed73c612174d4..bcc370c876be9 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -671,7 +671,7 @@ configuration, worker pools and how workqueues map to the pools: :: 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 @@ Use tools/workqueue/wq_monitor.py to monitor workqueue operations: :: 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 @@ Use tools/workqueue/wq_monitor.py to monitor workqueue operations: :: 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/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml index 1812ef31d5f1e..3c36cd0510de8 100644 --- a/Documentation/devicetree/bindings/eeprom/at24.yaml +++ b/Documentation/devicetree/bindings/eeprom/at24.yaml @@ -68,14 +68,10 @@ properties: pattern: cs16$ - items: pattern: c32$ - - items: - pattern: c32d-wl$ - items: pattern: cs32$ - items: pattern: c64$ - - items: - pattern: c64d-wl$ - items: pattern: cs64$ - items: @@ -136,6 +132,7 @@ properties: - 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 c13c10c8d65da..eed0df9d3a232 100644 --- a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml +++ b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml @@ -42,7 +42,7 @@ allOf: 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 d476de82e5c3f..4d5a957fa232e 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml @@ -120,7 +120,9 @@ additionalProperties: 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/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml index 0b87c266760c6..79798c7474768 100644 --- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml +++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml @@ -171,6 +171,7 @@ allOf: 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 41a62fd2ae1ff..c1fa379f5f3ea 100644 --- a/Documentation/devicetree/bindings/sound/rt5645.txt +++ b/Documentation/devicetree/bindings/sound/rt5645.txt @@ -20,6 +20,11 @@ Optional properties: 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 @@ codec: rt5650@1a { 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/rust/arch-support.rst b/Documentation/rust/arch-support.rst index 5c4fa9f5d1cdb..c9137710633a3 100644 --- a/Documentation/rust/arch-support.rst +++ b/Documentation/rust/arch-support.rst @@ -16,7 +16,7 @@ support corresponds to ``S`` values in the ``MAINTAINERS`` file. 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 f8786be15183c..7fe8ef9718d8e 100644 --- a/Documentation/timers/no_hz.rst +++ b/Documentation/timers/no_hz.rst @@ -129,11 +129,8 @@ adaptive-tick CPUs: At least one non-adaptive-tick CPU must remain 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 7fac6f75d0782..fe0ff5a127f3f 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 周彬彬 Binbin Zhou + 陈兴友 Xingyou Chen .. _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 @@ -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 @@ 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 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 @@ 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 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 @@ workqueue将自动创建与属性相匹配的后备工作者池。调节并发 ``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 @@ workqueue将自动创建与属性相匹配的后备工作者池。调节并发 -------------- ``@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 @@ And with cmwq with ``@max_active`` >= 3, :: * 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 @@ And with cmwq with ``@max_active`` >= 3, :: 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 @@ And with cmwq with ``@max_active`` >= 3, :: 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 9b197a5e53a98..25ffaf595ec25 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -553,7 +553,7 @@ F: Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml F: drivers/input/misc/adxl34x.c ADXL355 THREE-AXIS DIGITAL ACCELEROMETER DRIVER -M: Puranjay Mohan +M: Puranjay Mohan L: linux-iio@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/iio/accel/adi,adxl355.yaml @@ -3714,7 +3714,7 @@ F: drivers/iio/imu/bmi323/ BPF JIT for ARM M: Russell King -M: Puranjay Mohan +M: Puranjay Mohan L: bpf@vger.kernel.org S: Maintained F: arch/arm/net/ @@ -3764,6 +3764,8 @@ X: arch/riscv/net/bpf_jit_comp64.c BPF JIT for RISC-V (64-bit) M: Björn Töpel +R: Pu Lehui +R: Puranjay Mohan L: bpf@vger.kernel.org S: Maintained F: arch/riscv/net/ @@ -4191,7 +4193,6 @@ S: Supported F: drivers/scsi/bnx2i/ BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER -M: Ariel Elior M: Sudarsana Kalluru M: Manish Chopra L: netdev@vger.kernel.org @@ -7829,9 +7830,8 @@ W: http://aeschi.ch.eu.org/efs/ F: fs/efs/ EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER -M: Douglas Miller L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/ethernet/ibm/ehea/ ELM327 CAN NETWORK DRIVER @@ -9576,7 +9576,7 @@ F: kernel/power/ HID CORE LAYER M: Jiri Kosina -M: Benjamin Tissoires +M: Benjamin Tissoires L: linux-input@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git @@ -15161,9 +15161,8 @@ F: drivers/scsi/myrb.* F: drivers/scsi/myrs.* MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE) -M: Chris Lee L: netdev@vger.kernel.org -S: Supported +S: Orphan W: https://www.cspi.com/ethernet-products/support/downloads/ F: drivers/net/ethernet/myricom/myri10ge/ @@ -16799,12 +16798,6 @@ S: Maintained F: drivers/leds/leds-pca9532.c F: include/linux/leds-pca9532.h -PCA9541 I2C BUS MASTER SELECTOR DRIVER -M: Guenter Roeck -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 M: Pali Rohár @@ -17873,7 +17866,7 @@ F: Documentation/devicetree/bindings/leds/irled/pwm-ir-tx.yaml F: drivers/media/rc/pwm-ir-tx.c PWM SUBSYSTEM -M: Uwe Kleine-König +M: Uwe Kleine-König L: linux-pwm@vger.kernel.org S: Maintained Q: https://patchwork.ozlabs.org/project/linux-pwm/list/ @@ -17997,7 +17990,6 @@ S: Supported F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER -M: Ariel Elior M: Manish Chopra L: netdev@vger.kernel.org S: Supported @@ -18007,7 +17999,6 @@ F: include/linux/qed/ QLOGIC QL4xxx RDMA DRIVER M: Michal Kalderon -M: Ariel Elior L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/hw/qedr/ @@ -19623,8 +19614,6 @@ R: Ben Segall (CONFIG_CFS_BANDWIDTH) R: Mel Gorman (CONFIG_NUMA_BALANCING) R: Daniel Bristot de Oliveira (SCHED_DEADLINE) R: Valentin Schneider (TOPOLOGY) -R: Tejun Heo (SCHED_EXT) -R: David Vernet (SCHED_EXT) L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core @@ -19633,7 +19622,19 @@ F: include/linux/sched.h F: include/linux/wait.h F: include/uapi/linux/sched.h F: kernel/sched/ + +SCHEDULER - SCHED_EXT +R: Tejun Heo +R: David Vernet +L: linux-kernel@vger.kernel.org +S: Maintained +W: https://github.com/sched-ext/scx +T: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git +F: include/linux/sched/ext.h +F: kernel/sched/ext.h +F: kernel/sched/ext.c F: tools/sched_ext/ +F: tools/testing/selftests/sched_ext SCSI LIBSAS SUBSYSTEM R: John Garry @@ -20180,7 +20181,6 @@ F: include/linux/platform_data/simplefb.h SIOX M: Thorsten Scherer -M: Uwe Kleine-König R: Pengutronix Kernel Team S: Supported F: drivers/gpio/gpio-siox.c @@ -21929,7 +21929,7 @@ F: include/linux/soc/ti/ti_sci_inta_msi.h F: include/linux/soc/ti/ti_sci_protocol.h TEXAS INSTRUMENTS' TMP117 TEMPERATURE SENSOR DRIVER -M: Puranjay Mohan +M: Puranjay Mohan L: linux-iio@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml @@ -22842,7 +22842,7 @@ F: drivers/usb/host/ehci* USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...) M: Jiri Kosina -M: Benjamin Tissoires +M: Benjamin Tissoires L: linux-usb@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git @@ -24470,6 +24470,14 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har F: Documentation/admin-guide/LSM/Yama.rst F: security/yama/ +YAML NETLINK (YNL) +M: Donald Hunter +M: Jakub Kicinski +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 L: usbb2k-api-dev@nongnu.org diff --git a/Makefile b/Makefile index ba73e2c6f3191..f8278d07aeab4 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -scx1-rc5 +EXTRAVERSION = -scx1-rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 65afb1de48b36..30f7930275d83 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 diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 99d2845f3feb9..4092bec198bec 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 5648748c285f5..5a8550124b73e 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 3434c8131ecd5..c0a812674ce9e 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 6691f42550778..41b980df862b1 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 90a412026e643..0e0e2d337bf87 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 05fc7ed597125..0000000000000 --- 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 - -#define cpu_dcache_is_aliasing() true - -#endif diff --git a/arch/arc/include/asm/dsp.h b/arch/arc/include/asm/dsp.h index 202c78e567045..f496dbc4640b2 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 92c3e9f132521..00946fe04c9b2 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 cf1ba376e992c..38c35722cebf0 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 /* For NR_syscalls defination */ +#include /* For NR_syscalls definition */ #include #include #include /* 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 c574712ad8658..9cd79263acba8 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 0d63e568d64cb..936a2f21f315e 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 dda471f5f05bb..9963bb1a5733f 100644 --- a/arch/arc/include/asm/mmu_context.h +++ b/arch/arc/include/asm/mmu_context.h @@ -165,7 +165,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * 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 f3eea3f30b2e2..8ebec1b21d246 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 00b9318e551e7..cf79df0b25705 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -169,7 +169,7 @@ static inline unsigned long regs_get_register(struct pt_regs *regs, 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 8b0251464ffd4..719112af0f41a 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 e0913f52c2cdd..990f834909f08 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -77,7 +77,7 @@ static inline const char *arc_platform_smp_cpuinfo(void) /* * 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 @@ static inline const char *arc_platform_smp_cpuinfo(void) * 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 4c530cf131f33..12daaf3a61eaf 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 02109cd48ee12..8d1f1ef44ba75 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 2e49c81c8086b..e238b5fd3c8cf 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 /* ARC_{EXTRY,EXIT} */ +#include /* ARC_{ENTRY,EXIT} */ #include /* SAVE_ALL_{INT1,INT2,TRAP...} */ #include #include @@ -31,7 +31,7 @@ VECTOR res_service ; Reset Vector 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 @@ ENTRY(handle_interrupt) # 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 089f6680518f8..3c7e74aba6794 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -95,7 +95,7 @@ ENTRY(EV_MachineCheck) 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 @@ trap_with_param: ; --------------------------------------------- ; 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 9152782444b55..8d541f53fae3e 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -165,7 +165,7 @@ ENTRY(first_lines_of_secondary) ; 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 678898757e473..f324f0e3341a3 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -56,7 +56,7 @@ void arc_init_IRQ(void) 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 e71d64119d71a..f8e2960832d94 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -190,7 +190,8 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs) } } -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 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) 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 adff957962da8..6e5a651cd75cf 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 d08a5092c2b4d..7b6a9beba9db6 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -390,7 +390,7 @@ static void arc_chk_core_config(struct cpuinfo_arc *info) #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 8f6f4a5429646..fefa705a86385 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 9b9570b79362e..a19751e824fb4 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -89,7 +89,7 @@ int do_misaligned_access(unsigned long address, struct pt_regs *regs, /* * 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 549c3f4079186..61a1b2b96e1d8 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -41,8 +41,8 @@ SECTIONS #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 ad702b49aeb3b..cae4a7aae0ed4 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -212,7 +212,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, 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 @@ static void create_tlb(struct vm_area_struct *vma, unsigned long vaddr, pte_t *p * -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 e054780a8fe0c..dc65e87a531fd 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 4f609e9e510ef..009d2c8324210 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 217e9b96c61e5..20b2497657ae4 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 3fdece5bd31f9..5248a058230c8 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/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 01516f83a95ac..deeb8f292454b 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -871,16 +871,11 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[], } /* 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 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], 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_mov_r64(const bool is64, const s8 dst[], 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] */ + + /* 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); - emit_a32_mov_r(dst_lo, src_lo, off, 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/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index bfc5c81a5bd4e..8141926e4ef14 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/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index 0c38f7b517637..234e3b23d7a8d 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 = , , @@ -156,7 +156,7 @@ }; }; - eth_sleep: eth_sleep { + eth_sleep: eth-sleep-pins { tx_pins { pinmux = , , @@ -182,14 +182,14 @@ }; }; - usb0_id_pins_float: usb0_iddig { + usb0_id_pins_float: usb0-iddig-pins { pins_iddig { pinmux = ; bias-pull-up; }; }; - usb1_id_pins_float: usb1_iddig { + usb1_id_pins_float: usb1-iddig-pins { pins_iddig { pinmux = ; bias-pull-up; diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi index 6d218caa198cf..082672efba0a3 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 3ee9266fa8e98..917fa39a74f8d 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 = ; @@ -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 = , , 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 e04b1c0c0ebbf..ed79ad1ae8716 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 b3f416b9a7a4d..559990dcd1d17 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 = ; 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 6bd7424ef66c5..100191c6453ba 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 93dfbf1302315..774ae5d9143f1 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 3dea28f1d8061..1807e9d6cb0e4 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 9b738f6a5d213..7a704246678f0 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 05e401670bced..84cbdf6e9eb0c 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 = ; clocks = <&mmsys CLK_MM_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; mediatek,gce-events = , ; 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 f94c07f8b9334..4a11918da3704 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 ea6dc220e1cce..5d8b68f86ce44 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 = ; 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 = ; }; @@ -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 = ; }; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 7e7f0f0fb41ba..41f51d3261110 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 32afc78d5b769..053f7861c3cec 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 a5b194813079e..d0f82e12289e1 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 24bcec3366efd..0be053555602c 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 4386f8a9c636c..f40509d91bbda 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 39bd8f0eba1e6..7f2333c9d17d6 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 b86be34a912b9..024d2653cc307 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 = , , @@ -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 = , , diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index 3904348075f67..3348bc06db488 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 ba72d8f384207..eb117866e59ff 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 8e517f76189e1..6b40082bac68c 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 5846a11f0e848..d5e035823eb5e 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 @@ camera: &i2c7 { port@1 { reg = <1>; - mipi1_in_panel: endpoint@1 { + mipi1_in_panel: endpoint { remote-endpoint = <&mipi1_out_panel>; }; }; @@ -689,7 +689,6 @@ camera: &i2c7 { 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 dfb2a0bdea5b7..9586bb12a5d8f 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 054c6a4d1a45f..294eb2de263de 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 2c3984a880af6..f6f15946579eb 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 c08e69391c015..ccbe3a7a1d2c2 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 6ecdf5d283390..c1194d1e438d0 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 7b5f3904ef610..c87fad2c34cba 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 a8a4cc190eb32..a3112d5df2008 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 cce1c8e835877..94ecb9b4f98f8 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 1b606ea5b6cf2..1a604429fb266 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 67414d72e2b6e..22bbfbe729c11 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/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index f48b8dab8b3d2..1d26bb5b02f4b 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -338,12 +338,12 @@ int kvm_register_vgic_device(unsigned long type) 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/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 82d6c562e8c7e..320cb10ca93dd 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1844,15 +1844,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, 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 a5f300ec6f280..54ad04dacdee9 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -595,7 +595,7 @@ config ARCH_SELECTS_CRASH_DUMP 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/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 218bdbfa527ba..a1d9b84b1c7d5 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/perf_event.h b/arch/loongarch/include/asm/perf_event.h index 2a35a0bc2aaab..52b638059e40b 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 + #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 da7a3b5b9374a..e071f5e9e8580 100644 --- a/arch/loongarch/include/asm/tlb.h +++ b/arch/loongarch/include/asm/tlb.h @@ -132,8 +132,6 @@ static __always_inline void invtlb_all(u32 op, u32 info, u64 addr) ); } -#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 0491bf453cd49..cac7cba81b65f 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -884,4 +884,4 @@ static int __init init_hw_perf_events(void) 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 1fc2f6813ea02..97b40defde060 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -202,10 +202,10 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, 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/powerpc/include/asm/plpks.h b/arch/powerpc/include/asm/plpks.h index 23b77027c9163..7a84069759b03 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/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index e8c4129697b14..b1e6d275cda9e 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -786,8 +786,16 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) * 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 febe18f251d0c..4a595493d28ae 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -415,8 +415,7 @@ static int plpks_confirm_object_flushed(struct label *label, 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 @@ int plpks_signed_update_var(struct plpks_var *var, u64 flags) 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 910ba8837add8..2acc7d876e1fb 100644 --- a/arch/riscv/Kconfig.errata +++ b/arch/riscv/Kconfig.errata @@ -82,14 +82,14 @@ config ERRATA_THEAD 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 b1c410bbc1aec..bf6a0a6318ee3 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -19,20 +19,26 @@ #include #include -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; + + if (!(csr_read(CSR_TH_SXSTATUS) & SXSTATUS_MAEE)) + return false; - return false; + return true; } /* @@ -140,8 +146,8 @@ static u32 thead_errata_probe(unsigned int stage, { 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 1f2dbfb8a8bfc..efd851e1b4832 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 @@ asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID, \ * 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 @@ asm volatile(ALTERNATIVE( \ "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 2947423b5082e..115ac98b8d729 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -89,7 +89,7 @@ typedef struct page *pgtable_t; #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 9f8ea0e33eb10..6afd6bb4882eb 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -896,7 +896,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) #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 9f2a8e3ff2048..2902f68dc913a 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -54,7 +54,7 @@ struct riscv_hwprobe { #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 fe8e159394d8e..9687618432031 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -231,7 +231,7 @@ static void __init setup_bootmem(void) * 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 1adf2f39ce59c..ec9d692838fca 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -722,6 +722,9 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of 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 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of /* 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 99f7e1f2b70af..99ea3f12c5d2a 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -125,8 +125,19 @@ struct s390_pxts_ctx { 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 4f21ae561e4dd..390906b8e386e 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/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index 57f62596e53b9..85247ef5a41b8 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -24,8 +24,10 @@ __kernel_\func: 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 094b43b121cd5..12d22a7fa32fd 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2661,7 +2661,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, 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 c2e8242bd15dd..dc3db86e13ffb 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -139,7 +139,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) } 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 4474bf32d0a49..928820e61cb50 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -62,6 +62,7 @@ config X86 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 @@ config PREFIX_SYMBOLS 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" diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index a3c0df11d0e6d..2fb7d53cf3338 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -98,11 +98,6 @@ static int addr_to_vsyscall_nr(unsigned long addr) 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 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size) 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 @@ bool emulate_vsyscall(unsigned long error_code, goto sigsegv; } - tsk = current; - /* * Check for access_ok violations and find the syscall nr. * @@ -234,12 +225,8 @@ bool emulate_vsyscall(unsigned long error_code, 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 @@ bool emulate_vsyscall(unsigned long error_code, 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/include/asm/coco.h b/arch/x86/include/asm/coco.h index c086699b0d0c5..aa6c8f8ca9588 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -25,6 +25,7 @@ u64 cc_mkdec(u64 val); 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/e820/api.h b/arch/x86/include/asm/e820/api.h index e8f58ddd06d97..2e74a7f0e9357 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -17,6 +17,7 @@ extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type); extern void e820__range_add (u64 start, u64 size, enum e820_type type); extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type); +extern 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/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0b748ee16b3d9..9abb8cc4cd474 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 @@ enum page_cache_mode { }; #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 811548f131f4e..78e51b0d6433d 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -472,7 +472,6 @@ struct thread_struct { 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 7f57382afee41..93ed60080cfe7 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -269,6 +269,7 @@ int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immut 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_private(u64 pfn, u64 gpa, enum pg_level level, u32 as 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/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c342c4aa9c684..803dcfb0e3469 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1771,7 +1771,7 @@ void x2apic_setup(void) __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 @@ static __init void x2apic_disable(void) } __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 @@ void __init init_apic_mappings(void) } } -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 @@ void __init register_lapic_address(unsigned long address) 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 cb9eece55904d..307302af0aeee 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -459,8 +459,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) 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); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 6f1b379e3b385..68b09f718f10e 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -532,9 +532,10 @@ u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum 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 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) 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 7062b84dd467d..6d3d20e3e43a9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -139,7 +139,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, 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 8b04958da5e7d..b4f8fa0f722cd 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -1203,12 +1203,14 @@ static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt, 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/mm/fault.c b/arch/x86/mm/fault.c index 622d12ec7f085..bba4e020dd646 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -723,39 +723,8 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, 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 6f3b3e0287185..0a120d85d7bba 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -102,6 +102,13 @@ void __init mem_encrypt_setup_arch(void) 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 788a3d6f62765..fedff8ae7069c 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1806,36 +1806,41 @@ st: if (is_imm8(insn->off)) 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)); + + /* 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_JAE, 0); + /* if unsigned '>', goto load */ + EMIT2(X86_JA, 0); end_of_jmp = prog; /* xor dst_reg, dst_reg */ @@ -1861,18 +1866,6 @@ st: if (is_imm8(insn->off)) /* 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; @@ -3469,3 +3462,9 @@ bool bpf_jit_supports_ptr_xchg(void) { 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 ab0e8448bb6eb..0ae10535c6999 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -163,6 +163,42 @@ bool snp_probe_rmptable_info(void) 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 ace2eb054053f..9ba53814ed6a9 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -219,13 +219,21 @@ static __read_mostly unsigned int cpuid_leaf5_edx_val; 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 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, : "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 27d1a5b7f571a..ac41d83b38d3c 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -154,9 +154,9 @@ static void __init xen_pv_smp_config(void) 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 38bcecb0e457d..a2b6bb5429f5c 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -100,6 +100,10 @@ void flush_cache_range(struct vm_area_struct*, ulong, ulong); 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 @@ void local_flush_cache_page(struct vm_area_struct *vma, #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 @@ void local_flush_cache_page(struct vm_area_struct *vma, __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 @@ extern void copy_from_user_page(struct vm_area_struct*, struct page*, #endif +#include + #endif /* _XTENSA_CACHEFLUSH_H */ diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index d008a153a2b9f..7ed1a2085bd72 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 a270467556dc8..86c70117371bb 100644 --- a/arch/xtensa/include/asm/ptrace.h +++ b/arch/xtensa/include/asm/ptrace.h @@ -87,7 +87,7 @@ struct pt_regs { # 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 a815577d25fd0..7bd66677f7b6d 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -47,6 +47,7 @@ #include #include #include +#include #include extern void ret_from_fork(void); @@ -380,7 +381,7 @@ unsigned long __get_wchan(struct task_struct *p) 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 @@ unsigned long __get_wchan(struct task_struct *p) /* 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 831ffb648bda7..ed324fdf2a2f9 100644 --- a/arch/xtensa/kernel/stacktrace.c +++ b/arch/xtensa/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include #include +#include #include #include #include @@ -189,7 +190,7 @@ void walk_stackframe(unsigned long *sp, 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 8896e691c051e..abec44b687dff 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -166,10 +166,8 @@ late_initcall(rs_init); 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 4dc94145eb533..da2a167a4d08b 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -882,7 +882,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, 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/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 4bfbe55553f41..a40b6f3946efe 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -170,8 +170,8 @@ show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time); #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 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) } *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 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *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 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *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 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) 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 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) } 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 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) 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/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index cd84af23f7eac..dd0b40b9bbe8b 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -492,16 +492,14 @@ static int lps0_device_attach(struct acpi_device *adev, 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/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 5cb425f6f02d4..0a34dd3c4f38d 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -2838,6 +2838,43 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) } 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 * diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index bea3d5cf8a834..374e4efa8759f 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2177,7 +2177,8 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) .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 ac8ebccd35075..812fd2a8f853e 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -380,8 +380,10 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) 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 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) 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 19cfc342fc7bb..216826c31ee34 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 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) } 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 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, 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 06e915b57283f..e3946f7b736e3 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -542,6 +542,8 @@ static const struct usb_device_id quirks_table[] = { /* 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_dump_hdr_qca(struct hci_dev *hdev, struct sk_buff *skb) 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 ecbc52eaf1010..0c9c9ee56592d 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1672,6 +1672,9 @@ static bool qca_wakeup(struct hci_dev *hdev) 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 @@ static int qca_setup(struct hci_uart *hu) 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 @@ static int qca_setup(struct hci_uart *hu) 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 @@ static int qca_serdev_probe(struct serdev_device *serdev) (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 @@ static int qca_serdev_probe(struct serdev_device *serdev) 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/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 8602c02047d04..45c5255bcd11b 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -768,6 +768,7 @@ static struct clk_smd_rpm *msm8976_clks[] = { 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 e7a4068b9f390..df9618ab7eea1 100644 --- a/drivers/clk/qcom/gdsc.c +++ b/drivers/clk/qcom/gdsc.c @@ -487,9 +487,14 @@ int gdsc_register(struct gdsc_desc *desc, 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 3484e6cc80ad1..503c6f5b20d5c 100644 --- a/drivers/clk/samsung/clk-exynos-clkout.c +++ b/drivers/clk/samsung/clk-exynos-clkout.c @@ -13,9 +13,9 @@ #include #include #include +#include #include #include -#include #define EXYNOS_CLKOUT_NR_CLKS 1 #define EXYNOS_CLKOUT_PARENTS 32 @@ -84,17 +84,24 @@ MODULE_DEVICE_TABLE(of, exynos_clkout_ids); 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 8951ffc14ff52..6a4b2b9ef30a8 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c @@ -182,6 +182,8 @@ static struct ccu_nkm pll_mipi_clk = { &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 42568c6161814..892df807275c8 100644 --- a/drivers/clk/sunxi-ng/ccu-sun50i-h6.c +++ b/drivers/clk/sunxi-ng/ccu-sun50i-h6.c @@ -1181,11 +1181,18 @@ static const u32 usb2_clk_regs[] = { 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 @@ static int sun50i_h6_ccu_probe(struct platform_device *pdev) 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 8babce55302f5..ac0091b4ce242 100644 --- a/drivers/clk/sunxi-ng/ccu_common.c +++ b/drivers/clk/sunxi-ng/ccu_common.c @@ -44,6 +44,16 @@ bool ccu_is_better_rate(struct ccu_common *common, 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 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev, 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 @@ static int sunxi_ccu_probe(struct sunxi_ccu *ccu, struct device *dev, 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 942a72c094374..329734f8cf42b 100644 --- a/drivers/clk/sunxi-ng/ccu_common.h +++ b/drivers/clk/sunxi-ng/ccu_common.h @@ -31,6 +31,9 @@ struct ccu_common { 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/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index f0f54aeccc872..65185c9fa0013 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -946,25 +946,22 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, 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, - .min_out = struct_size(payload, records, 0), - }; - do { int rc, i; - - mbox_cmd.size_out = mds->payload_size; + 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) { @@ -1297,7 +1294,6 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, 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; @@ -1309,16 +1305,16 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, 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 762783bb091af..887ed6e358fb9 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -2184,6 +2184,7 @@ static bool parent_port_is_cxl_root(struct cxl_port *port) int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, struct access_coordinate *coord) { + struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev); struct access_coordinate c[] = { { .read_bandwidth = UINT_MAX, @@ -2197,12 +2198,20 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, 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; + /* + * 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 iter port is cxl * root. The iterative loop starts at the endpoint and gathers the @@ -2232,8 +2241,12 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, 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; diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c index 78a938969d7d7..1398814d8fbb6 100644 --- a/drivers/dma/idma64.c +++ b/drivers/dma/idma64.c @@ -171,6 +171,10 @@ static irqreturn_t idma64_irq(int irq, void *dev) 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 8078ab9acfbc3..c095a2c8f6595 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -342,7 +342,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) 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 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) 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 f3f25ee676f30..ad4245cb301d5 100644 --- a/drivers/dma/idxd/debugfs.c +++ b/drivers/dma/idxd/debugfs.c @@ -66,7 +66,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d) 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 @@ static int debugfs_evl_show(struct seq_file *s, void *d) 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 ecfdf4a8f1f83..c41ef195eeb9f 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -775,7 +775,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) 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 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) 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 @@ static void idxd_device_evl_free(struct idxd_device *idxd) 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 @@ static void idxd_device_evl_free(struct idxd_device *idxd) 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 a4099a1e2340f..7b98944135eb4 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -293,7 +293,7 @@ struct idxd_driver_data { 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 4954adc6bb609..264c4e47d7cca 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -354,7 +354,7 @@ static int idxd_init_evl(struct idxd_device *idxd) 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 348aa21389a9f..8dc029c865515 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -363,7 +363,7 @@ static void process_evl_entries(struct idxd_device *idxd) 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 @@ static void process_evl_entries(struct idxd_device *idxd) 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 fdda6d6042629..5e94247e1ea70 100644 --- a/drivers/dma/idxd/perfmon.c +++ b/drivers/dma/idxd/perfmon.c @@ -528,14 +528,11 @@ static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node) 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 4e76c4ec2d396..e001f4f7aa640 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -250,7 +250,7 @@ static void pchan_update(struct owl_dma_pchan *pchan, u32 reg, 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 @@ static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state) 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 5f6d7f1e095f9..ad8e3da1b2cd2 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1053,9 +1053,6 @@ static bool _trigger(struct pl330_thread *thrd) 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 88547a23825b1..3642508e88bb2 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -746,6 +746,9 @@ static int tegra_dma_get_residual(struct tegra_dma_channel *tdc) 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 98f5f6fb9ff9c..6ad08878e9386 100644 --- a/drivers/dma/xilinx/xdma-regs.h +++ b/drivers/dma/xilinx/xdma-regs.h @@ -117,6 +117,9 @@ struct xdma_hw_desc { 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 170017ff2aad6..313b217388fe9 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -71,6 +71,8 @@ struct xdma_chan { enum dma_transfer_direction dir; struct dma_slave_config cfg; u32 irq; + struct completion last_interrupt; + bool stop_requested; }; /** @@ -376,6 +378,8 @@ static int xdma_xfer_start(struct xdma_chan *xchan) return ret; xchan->busy = true; + xchan->stop_requested = false; + reinit_completion(&xchan->last_interrupt); return 0; } @@ -387,7 +391,6 @@ static int xdma_xfer_start(struct xdma_chan *xchan) 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 @@ static int xdma_xfer_stop(struct xdma_chan *xchan) 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 @@ static int xdma_alloc_channels(struct xdma_device *xdev, 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 @@ static int xdma_terminate_all(struct dma_chan *chan) 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 int xdma_terminate_all(struct dma_chan *chan) 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 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address, 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 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id) 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 b82815e64d24e..eb0637d90342a 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -214,7 +214,8 @@ struct xilinx_dpdma_tx_desc { * @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 @@ static void xilinx_dpdma_chan_vsync_irq(struct xilinx_dpdma_chan *chan) * 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 @@ static void xilinx_dpdma_issue_pending(struct dma_chan *dchan) 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 @@ static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t) 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 64eaca80d736c..d0f6693ca1426 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -42,6 +42,7 @@ struct dpll_pin_registration { 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 @@ struct dpll_device *dpll_device_get_by_id(int id) 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 @@ dpll_pin_registration_find(struct dpll_pin_ref *ref, 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 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, 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 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, } 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 @@ dpll_xa_ref_pin_add(struct xarray *xa_pins, struct dpll_pin *pin, } 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 @@ static int dpll_xa_ref_pin_del(struct xarray *xa_pins, struct dpll_pin *pin, 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_pin_del(struct xarray *xa_pins, struct dpll_pin *pin, 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 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, 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 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, } 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 @@ dpll_xa_ref_dpll_add(struct xarray *xa_dplls, struct dpll_device *dpll, 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 @@ dpll_xa_ref_dpll_del(struct xarray *xa_dplls, struct dpll_device *dpll, 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 @@ EXPORT_SYMBOL_GPL(dpll_pin_put); 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 @@ __dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, 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_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, 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 @@ EXPORT_SYMBOL_GPL(dpll_pin_register); 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 @@ void dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin, 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 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, 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 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, 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 @@ void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin, 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 1688a5050f63a..a556d23e8261c 100644 --- a/drivers/edac/versal_edac.c +++ b/drivers/edac/versal_edac.c @@ -425,7 +425,7 @@ static void handle_error(struct mem_ctl_info *mci, struct ecc_status *stat) 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 @@ static void handle_error(struct mem_ctl_info *mci, struct ecc_status *stat) 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 @@ static ssize_t inject_data_ue_store(struct file *file, const char __user *data, 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 @@ static int mc_probe(struct platform_device *pdev) } 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 @@ static void mc_remove(struct platform_device *pdev) 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 b0d671db178a8..ea31ac7ac1ca9 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -148,10 +148,12 @@ packet_buffer_get(struct client *client, char __user *data, size_t user_length) 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 38d19410a2be6..b9ae0340b8a70 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -1556,6 +1556,8 @@ static int handle_at_packet(struct context *context, #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 @@ static void handle_local_rom(struct fw_ohci *ohci, (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 @@ static void handle_local_lock(struct fw_ohci *ohci, 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 void handle_local_request(struct context *ctx, struct fw_packet *packet) } } -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/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c index 5b439d04079c8..50f6503fe49f5 100644 --- a/drivers/firmware/efi/unaccepted_memory.c +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -4,6 +4,7 @@ #include #include #include +#include #include /* Protects unaccepted memory bitmap and accepting_list */ @@ -149,6 +150,9 @@ void accept_memory(phys_addr_t start, phys_addr_t end) } 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 32188f098ef34..bc550ad0dbe0c 100644 --- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c +++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c @@ -221,6 +221,19 @@ struct qsee_rsp_uefi_query_variable_info { * 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 @@ struct qsee_rsp_uefi_query_variable_info { #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 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e 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 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e __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 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e 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 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e 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 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e 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 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e __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 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e 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 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e } 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 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, 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 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, __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 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, 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 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, } 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 @@ static efi_status_t qsee_uefi_query_variable_info(struct qcuefi_client *qcuefi, 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 @@ static efi_status_t qsee_uefi_query_variable_info(struct qcuefi_client *qcuefi, *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 520de9b5633ab..90283f160a228 100644 --- a/drivers/firmware/qcom/qcom_scm.c +++ b/drivers/firmware/qcom/qcom_scm.c @@ -1576,9 +1576,9 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_get_id); /** * 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 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_get_id); * * 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 @@ int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, 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 98b8fd16183e4..80cac3a5f9767 100644 --- a/drivers/fpga/dfl-pci.c +++ b/drivers/fpga/dfl-pci.c @@ -78,6 +78,7 @@ static void cci_pci_free_irq(struct pci_dev *pcidev) #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 @@ -101,6 +102,8 @@ static struct pci_device_id cci_pcie_id_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_PAC_D5005_VF),}, {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, diff --git a/drivers/gpio/gpio-tangier.c b/drivers/gpio/gpio-tangier.c index b75e0b12087ac..4b29abafecf6a 100644 --- a/drivers/gpio/gpio-tangier.c +++ b/drivers/gpio/gpio-tangier.c @@ -195,7 +195,8 @@ static int tng_gpio_set_config(struct gpio_chip *chip, unsigned int offset, 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_unmask_mask(struct tng_gpio *priv, u32 gpio, bool unmask) 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_mask(struct irq_data *d) 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 d87dd06db40d0..9130c691a2dd3 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 @@ static inline bool tegra186_gpio_is_accessible(struct tegra_gpio *gpio, unsigned 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/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index df58a6a1a67ec..e4d4e55c08ad5 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 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, (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 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( 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 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * 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 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * 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 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * } } - 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_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index a00cf4756ad0e..1569bef030eac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1132,6 +1132,7 @@ void amdgpu_mes_remove_ring(struct amdgpu_device *adev, 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); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 2099159a693fa..f6d503432a9ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -605,6 +605,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev, 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) @@ -1241,14 +1243,18 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, * 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)) @@ -1260,12 +1266,12 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) 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, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index fa03d9e4874cc..bc42ccbde659a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -328,7 +328,9 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, 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 1d71729e3f6bc..109fe557a02bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -419,7 +419,7 @@ bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, 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_PREEMPT || res->mem_type == AMDGPU_PL_DOORBELL) return true; if (res->mem_type != TTM_PL_VRAM) @@ -481,14 +481,16 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 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) && @@ -498,9 +500,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 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 || @@ -512,8 +515,9 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 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 && @@ -525,22 +529,23 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 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; - } + 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 { + else r = -ENODEV; - } if (r) { /* Check that all memory is CPU accessible */ @@ -555,11 +560,10 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, 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; } @@ -1559,7 +1563,7 @@ static int amdgpu_ttm_access_memory(struct ttm_buffer_object *bo, 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_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c index 0df97c3e3a700..f7c73533e336f 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 @@ static int umsch_mm_late_init(void *handle) { 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_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c index 6695481f870f8..c23d97d34b7ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c @@ -205,7 +205,7 @@ int amdgpu_vpe_configure_dpm(struct amdgpu_vpe *vpe) 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/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f90905ef32c76..701146d649c35 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 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { 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 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = { 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 f7325b02a191f..f00e05aba46a4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -6192,7 +6192,7 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_gfx = { 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 */ @@ -6278,7 +6278,6 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_kiq = { 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 6f97a6d0e6d05..99dbd2341120d 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 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = { 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 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = { 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/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 82eab49be82bb..e708468ac54dd 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 @@ static void sdma_v4_4_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) 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), diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 42f4bd250def6..da01b524b9f2a 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 @@ static void sdma_v5_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) 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; - - 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 */ + 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 */ + } } /** diff --git a/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c b/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c index 769eb8f7bb3c5..09315dd5a1ec9 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 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe) 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 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe) 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 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe) } 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_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index bdc01ca9609a7..5c8d81bfce7ab 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -509,10 +509,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, 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_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, 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 b79986412cd83..451bb058cc620 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -829,6 +829,14 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) 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 @@ static int signal_eviction_fence(struct kfd_process *p) 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 @@ static void evict_process_worker(struct work_struct *work) * 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 @@ static void restore_process_worker(struct work_struct *work) 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 f0f7f48af4137..386875e6eb96b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -3426,7 +3426,7 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, 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 6d2f60c61decc..d6e71aa808d88 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3029,6 +3029,7 @@ static int dm_resume(void *handle) 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) { @@ -4536,15 +4537,18 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) /* 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; 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 eee4945653e2d..c7715a17f388b 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 @@ static ssize_t dp_dsc_clock_en_read(struct file *f, char __user *buf, 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 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf, 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 @@ static ssize_t dp_dsc_slice_width_read(struct file *f, char __user *buf, 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 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf, 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 @@ static ssize_t dp_dsc_slice_height_read(struct file *f, char __user *buf, 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 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf, 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 @@ static ssize_t dp_dsc_bits_per_pixel_read(struct file *f, char __user *buf, 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 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu 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 @@ static ssize_t dp_dsc_pic_width_read(struct file *f, char __user *buf, 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 @@ static ssize_t dp_dsc_pic_height_read(struct file *f, char __user *buf, 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 @@ static ssize_t dp_dsc_chunk_size_read(struct file *f, char __user *buf, 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 @@ static ssize_t dp_dsc_slice_bpg_offset_read(struct file *f, char __user *buf, 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/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 05f392501c0ae..ab31643b10969 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 @@ static enum bp_result construct_integrated_info( 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 644da46373209..5506cf9b3672f 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 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, */ 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 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, } } } 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/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index bec252e1dd27a..e506e4f969ca9 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 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, * 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 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, /* 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/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 03b554e912a20..d68c83e40d4d6 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 @@ bool dc_validate_boot_timing(const struct dc *dc, 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/dcn31/dcn31_hpo_dp_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_link_encoder.c index 5b7ad38f85e08..65e45a0b4ff34 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 @@ void dcn31_hpo_dp_link_enc_set_throttled_vcp_size( 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/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index deb6d162a2d5c..7307b7b8d8ad7 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 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = { .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 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_16_soc = { .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 5491b707cec88..5a965c26bf209 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 @@ static void set_usb4_req_bw_req(struct dc_link *link, int req_bw) /* 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 @@ bool link_dp_dpia_set_dptx_usb4_bw_alloc_support(struct dc_link *link) 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/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c index a2387cea1af9a..622214b365a25 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 @@ static bool dcn20_resource_construct( 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 f09b9d49297e8..bbd0169010c2d 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -4261,6 +4261,13 @@ static int amdgpu_od_set_init(struct amdgpu_device *adev) } } + /* + * 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/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 3957af057d54f..c977ebe88001d 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 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table 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 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu) /* 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/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index e440f458b6633..93337543aac32 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -224,8 +224,8 @@ __drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane, __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 734412aae94dd..a9bf426f69b36 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -164,26 +164,6 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) *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 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) /* 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 7d5e9158e13c1..197e0037732ec 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -54,18 +54,6 @@ struct etnaviv_chip_identity { /* 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 d8e7334de8cea..8665f2658d51b 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -17,10 +17,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .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 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .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 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .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 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .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 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .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 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .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 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .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 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .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 4f302cd5e1a6c..58fed80c7392a 100644 --- a/drivers/gpu/drm/gma500/Makefile +++ b/drivers/gpu/drm/gma500/Makefile @@ -34,7 +34,6 @@ gma500_gfx-y += \ 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 dcfcd7b89d4a1..6dece8f0e380f 100644 --- a/drivers/gpu/drm/gma500/psb_device.c +++ b/drivers/gpu/drm/gma500/psb_device.c @@ -73,8 +73,7 @@ static int psb_backlight_setup(struct drm_device *dev) } 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 int psb_chip_setup(struct drm_device *dev) 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 c5edfa4aa4ccd..83c17689c454f 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 @@ struct drm_psb_private { /* 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 @@ struct psb_ops { 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 58a7fe3926360..0000000000000 --- 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 - **************************************************************************/ - -#include - -#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/imagination/pvr_fw_mips.h b/drivers/gpu/drm/imagination/pvr_fw_mips.h index 408dbe63a90cf..a0c5c41c8aa24 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 +#include #include /* 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/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h index 6f5d376d8fcc1..a11d16a16c3b2 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_mem { }; 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/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c index adc60b25f8e6c..141b0a513bf52 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c @@ -205,7 +205,9 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw) 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 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name, 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/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index 9858c1438aa7f..abe41f7a34045 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -1624,7 +1624,7 @@ r535_gsp_wpr_meta_init(struct nvkm_gsp *gsp) 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 @@ nvkm_gsp_sg(struct nvkm_device *device, u64 size, struct sg_table *sgt) 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 @@ static int 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; + if (ret) { +lvl2_fail: + nvkm_gsp_mem_dtor(gsp, &rx3->lvl1); +lvl1_fail: + nvkm_gsp_mem_dtor(gsp, &rx3->lvl0); } - return 0; + return ret; } int @@ -2021,7 +2046,7 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend) 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/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index d037b3b8b9993..5b15d02948367 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -177,7 +177,7 @@ config DRM_PANEL_ILITEK_IL9322 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 3574681891e81..b933380b7eb78 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -22,8 +22,9 @@ #include #include #include +#include #include -#include +#include #include #include @@ -421,7 +422,7 @@ static int ili9341_dpi_prepare(struct drm_panel *panel) ili9341_dpi_init(ili); - return ret; + return 0; } static int ili9341_dpi_enable(struct drm_panel *panel) @@ -691,7 +692,7 @@ static int ili9341_dpi_probe(struct spi_device *spi, struct gpio_desc *dc, * 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 @@ static int ili9341_probe(struct spi_device *spi) 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/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 578a7c37f00bd..d776e3f87064f 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -92,7 +92,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) */ 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/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index e5eb21a471a60..00144632c600e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -204,6 +204,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, 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 */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 2a0cda3247031..5efc6a766f64e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -991,7 +991,7 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv, } 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/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h index 420eba0e4be00..854a7bb535674 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 @@ static inline struct drm_i915_private *kdev_to_i915(struct device *kdev) #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/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index a0afe1ba6dd5c..f9705430ada93 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -378,7 +378,9 @@ static int gt_fw_domain_init(struct xe_gt *gt) 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 529fc286cd06c..396aeb5b99242 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 @@ static void xe_gt_ccs_mode_sysfs_fini(struct drm_device *drm, void *arg) * 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 f39975aaaab0d..f8779852cf0d2 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 355edd4d758af..7f32547f94b26 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -1054,10 +1054,10 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len) 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 b545f850087cd..6b9b1cbedd379 100644 --- a/drivers/gpu/drm/xe/xe_huc.c +++ b/drivers/gpu/drm/xe/xe_huc.c @@ -53,7 +53,6 @@ static int huc_alloc_gsc_pkt(struct xe_huc *huc) 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 @@ static int huc_alloc_gsc_pkt(struct xe_huc *huc) 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_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 3d4c8f342e215..32cd0c978aa28 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1606,6 +1606,9 @@ static void vm_destroy_work_func(struct work_struct *w) /* 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)) diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index e6a8b6d8eab70..3c3c497b6b911 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -965,9 +965,7 @@ static void logi_hidpp_dev_conn_notif_equad(struct hid_device *hdev, } 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 f9cceaeffd081..da5ea5a23b087 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -944,9 +944,11 @@ static void mcp2221_hid_unregister(void *ptr) /* 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 ab5953fc24367..80e0f23c1c33e 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -481,10 +481,10 @@ static const struct joycon_ctlr_button_mapping n64con_button_mappings[] = { { 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 2df1ab3c31cc5..d965382196c69 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 @@ static int i2c_hid_xfer(struct i2c_hid *ihid, 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 @@ static irqreturn_t i2c_hid_irq(int irq, void *dev_id) { 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 @@ static int i2c_hid_parse(struct hid_device *hid) 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 @@ static int i2c_hid_parse(struct hid_device *hid) 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 @@ static int i2c_hid_parse(struct hid_device *hid) 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 a49c6affd7c4c..dd5fc60874ba1 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -948,6 +948,7 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev) if (!dev) return NULL; + dev->devc = &pdev->dev; ishtp_device_init(dev); init_waitqueue_head(&dev->wait_hw_ready); @@ -983,7 +984,6 @@ struct ishtp_device *ish_dev_init(struct pci_dev *pdev) } 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/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index ff5c486a1dbb1..db0d1ac82910e 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2200,13 +2200,18 @@ static int i2c_check_for_quirks(struct i2c_adapter *adap, struct i2c_msg *msgs, * 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 i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { 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 61839be501c21..63c3566a533bd 100644 --- a/drivers/iio/accel/mxc4005.c +++ b/drivers/iio/accel/mxc4005.c @@ -5,6 +5,7 @@ * Copyright (c) 2014, Intel Corporation. */ +#include #include #include #include @@ -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 @@ struct mxc4005_data { s64 timestamp __aligned(8); } scan; bool trigger_enabled; + unsigned int control; + unsigned int int_mask1; }; /* @@ -113,7 +124,9 @@ static bool mxc4005_is_readable_reg(struct device *dev, unsigned int reg) 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 @@ static int mxc4005_set_trigger_state(struct iio_trigger *trig, { 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 @@ static int mxc4005_chip_init(struct mxc4005_data *data) 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 @@ static int mxc4005_probe(struct i2c_client *client) 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 @@ static struct i2c_driver mxc4005_driver = { .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 01f55cc902faa..060a21c70460d 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -1289,6 +1289,7 @@ static int adis16475_config_sync_mode(struct adis16475 *st) 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 @@ static int adis16475_config_sync_mode(struct adis16475 *st) * 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 fe8734468ed35..62e9e93d915dc 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1233,6 +1233,7 @@ const struct bmp280_chip_info bmp380_chip_info = { .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 a444d4b2978b5..4e19ea0b4d398 100644 --- a/drivers/iio/pressure/bmp280-spi.c +++ b/drivers/iio/pressure/bmp280-spi.c @@ -96,15 +96,10 @@ static int bmp280_spi_probe(struct spi_device *spi) 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 @@ static const struct of_device_id bmp280_of_spi_match[] = { { .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 @@ static const struct spi_device_id bmp280_spi_id[] = { { "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 4012387d79565..5812a344ed8e8 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -423,6 +423,7 @@ struct bmp280_chip_info { 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/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index f50848ed5575d..6fadaddb2b908 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -208,6 +208,7 @@ static const struct xpad_device { { 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 @@ static const struct usb_device_id xpad_table[] = { { 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 cda0c3ff5a288..2fbbaeb76d708 100644 --- a/drivers/input/mouse/amimouse.c +++ b/drivers/input/mouse/amimouse.c @@ -132,7 +132,13 @@ static void __exit amimouse_remove(struct platform_device *pdev) 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/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 2a537cbfcb077..5f7d3db3afd82 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -4567,13 +4567,8 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq 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/md/dm-vdo/murmurhash3.c b/drivers/md/dm-vdo/murmurhash3.c index 01d2743444ec6..3a989efae1420 100644 --- a/drivers/md/dm-vdo/murmurhash3.c +++ b/drivers/md/dm-vdo/murmurhash3.c @@ -137,7 +137,7 @@ void murmurhash3_128(const void *key, const int len, const u32 seed, void *out) break; default: break; - }; + } } /* finalization */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 56aa2a8b9d715..7d0746b37c8ec 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -765,7 +765,7 @@ static struct table_device *open_table_device(struct mapped_device *md, 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 @@ static void close_table_device(struct table_device *td, struct mapped_device *md { 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/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 572333ead5fb8..4bd4f32bcdabb 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -758,15 +758,6 @@ static int at24_probe(struct i2c_client *client) } 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 @@ static int at24_probe(struct i2c_client *client) } } + 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 aac36750d2c54..c3a6657dcd4a2 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 c39718042e2e0..7f59dd38c32f5 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -122,6 +122,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {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/pxp/mei_pxp.c b/drivers/misc/mei/pxp/mei_pxp.c index b1e4c23b31a32..49abc95677cda 100644 --- a/drivers/misc/mei/pxp/mei_pxp.c +++ b/drivers/misc/mei/pxp/mei_pxp.c @@ -236,8 +236,11 @@ static int mei_pxp_component_match(struct device *dev, int subcomponent, 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/pvpanic/pvpanic-pci.c b/drivers/misc/pvpanic/pvpanic-pci.c index 9ad20e82785bc..b21598a18f6da 100644 --- a/drivers/misc/pvpanic/pvpanic-pci.c +++ b/drivers/misc/pvpanic/pvpanic-pci.c @@ -44,8 +44,6 @@ static struct pci_driver pvpanic_pci_driver = { .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 b88d6dec209f5..9a5f75163acae 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -300,6 +300,7 @@ static void moxart_transfer_pio(struct moxart_host *host) 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/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 668e0aceeebac..e113b99a3eab5 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2694,6 +2694,11 @@ static __maybe_unused int sdhci_msm_runtime_suspend(struct device *dev) 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 @@ static __maybe_unused int sdhci_msm_runtime_resume(struct device *dev) 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 @@ static __maybe_unused int sdhci_msm_runtime_resume(struct device *dev) 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 1d8f5a76096ae..f2e4a93ed1d61 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -626,6 +626,7 @@ static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode) /* 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 5887feb347a4e..0de87bc638405 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -900,7 +900,7 @@ static struct nvmem_device *mtd_otp_nvmem_register(struct mtd_info *mtd, 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 a8d12c71f987b..1b2ec0fec60c7 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -857,7 +857,7 @@ static inline void brcmnand_read_data_bus(struct brcmnand_controller *ctrl, 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 5243fab9face0..8db7fc4245711 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -53,7 +53,7 @@ static unsigned long doc_locations[] __initdata = { 0xe8000, 0xea000, 0xec000, 0xee000, #endif #endif - 0xffffffff }; +}; static struct mtd_info *doclist = NULL; @@ -1554,7 +1554,7 @@ static int __init init_nanddoc(void) 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 b079605c84d38..b8cff9240b286 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -2815,7 +2815,7 @@ static int qcom_misc_cmd_type_exec(struct nand_chip *chip, const struct nand_sub 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 @@ static int qcom_misc_cmd_type_exec(struct nand_chip *chip, const struct nand_sub 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/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c95787cb90867..14daf432f30b5 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -566,13 +566,61 @@ static void mv88e6xxx_translate_cmode(u8 cmode, unsigned long *supported) phy_interface_set_rgmii(supported); } -static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, - struct phylink_config *config) +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; - /* Translate the default cmode */ - mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + 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) +{ + 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 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .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 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .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 86deeb347cbc1..ddadeb9bfdaee 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/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index 72ea97c5d5d42..82768b0e90262 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -436,10 +436,8 @@ static void umac_init(struct bcmasp_intf *intf) 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 @@ static int bcmasp_tx_poll(struct napi_struct *napi, int budget) 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 @@ static void bcmasp_init_tx(struct bcmasp_intf *intf) 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 @@ static void bcmasp_netif_deinit(struct net_device *dev) } 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 3e4fb3c3e8342..1be6d14030bcf 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -2009,12 +2009,14 @@ static int b44_set_pauseparam(struct net_device *dev, 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 57e61f9631678..2c2ee79c4d779 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1778,7 +1778,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, 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 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, 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 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, 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 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, 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 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, 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 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, 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 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, 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 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, *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 @@ static int bnxt_force_rx_discard(struct bnxt *bp, } 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 @@ static void bnxt_try_map_fw_health_reg(struct bnxt *bp) 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 | @@ -13037,6 +13029,16 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) 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); @@ -13050,12 +13052,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp) 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); @@ -15373,6 +15370,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, { 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"); @@ -15381,16 +15379,27 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, 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); @@ -15474,6 +15483,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) } 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/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index b1f84b37032a7..c7e7dac057a33 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 @@ static void umac_enable_set(struct bcmgenet_priv *priv, u32 mask, bool enable) { 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 @@ static void reset_umac(struct bcmgenet_priv *priv) 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 @@ static void bcmgenet_netif_start(struct net_device *dev) 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 @@ static void bcmgenet_set_rx_mode(struct net_device *dev) * 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 @@ static int bcmgenet_probe(struct platform_device *pdev) 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 7523b60b3c1c0..43b923c48b14f 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 @@ struct bcmgenet_rxnfc_rule { /* 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 7a41cad5788f4..1248792d7fd4d 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 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, } /* 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 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, /* 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 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, } /* 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 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, /* 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 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, } /* 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 9ada893557475..c4a3698cef66f 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 @@ -76,6 +76,7 @@ static void bcmgenet_mac_config(struct net_device *dev) 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 @@ static void bcmgenet_mac_config(struct net_device *dev) 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 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) * 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 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) 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 7246e13dd559f..97291bfbeea58 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c +++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c @@ -312,7 +312,7 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf, 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 @@ bnad_debugfs_write_regwr(struct file *file, const char __user *buf, 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 49d5808b7d11d..de52bcb884c41 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2670,12 +2670,12 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) 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 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) 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 93544f1cc2a51..f7ae0e0aa4a4f 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -157,7 +157,7 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) * 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 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) * 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 @@ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) * 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 @@ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) * 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 48b9ddb2b1b38..ffb9f9f15c523 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16107,8 +16107,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) 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 @@ static int __init i40e_init_module(void) * 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 ef2440f3abf8b..166832a4213a2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3502,6 +3502,34 @@ static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) spin_unlock_bh(&adapter->cloud_filter_list_lock); } +/** + * 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 @@ -3559,7 +3587,7 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data) 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 d252d98218d08..9fc0fd95a13d8 100644 --- a/drivers/net/ethernet/intel/ice/ice_debugfs.c +++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c @@ -171,7 +171,7 @@ ice_debugfs_module_write(struct file *filp, const char __user *buf, 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 @@ ice_debugfs_nr_messages_write(struct file *filp, const char __user *buf, 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 @@ ice_debugfs_enable_write(struct file *filp, const char __user *buf, 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 @@ ice_debugfs_log_size_write(struct file *filp, const char __user *buf, 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_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 21d26e19338a6..d10a4be965b59 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 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) 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 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) 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 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) 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 90316dc586308..6bc56c7c181e4 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -298,6 +298,7 @@ struct igc_adapter { /* LEDs */ struct mutex led_mutex; + struct igc_led_classdev *leds; }; void igc_up(struct igc_adapter *adapter); @@ -723,6 +724,7 @@ void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts); 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 bf240c5daf865..3929b25b6ae6e 100644 --- a/drivers/net/ethernet/intel/igc/igc_leds.c +++ b/drivers/net/ethernet/intel/igc/igc_leds.c @@ -236,8 +236,8 @@ static void igc_led_get_name(struct igc_adapter *adapter, int index, char *buf, 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 @@ static void igc_setup_ldev(struct igc_led_classdev *ldev, 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 35ad40a803cb6..4d975d620a8e4 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7021,6 +7021,9 @@ static void igc_remove(struct pci_dev *pdev) 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 2500f5ba4f5a4..881d704644fbe 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 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, 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_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index be709f83f3318..e8b73b9d75e31 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 @@ void rvu_npc_freemem(struct rvu *rvu) 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/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index b2cabd6ab86cb..cc9bcc4200324 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 @@ static const struct macsec_ops macsec_offload_ops = { .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/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e4d7739bd7c88..4a79c0d7e7ad8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -849,7 +849,7 @@ static void mlxsw_emad_rx_listener_func(struct sk_buff *skb, u16 local_port, 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 53b150b7ae4e7..6c06b05927608 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -1357,24 +1357,20 @@ static struct mlxsw_linecards_event_ops mlxsw_env_event_ops = { .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 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, 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 af99bf17eb36d..f42a1b1c93687 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1530,7 +1530,7 @@ mlxsw_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id) { 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_pci_reset(struct mlxsw_pci *mlxsw_pci, const struct pci_device_id *id) 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 f20052776b3f2..92a406f02eae7 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 #include #include +#include #include #include @@ -58,41 +59,43 @@ int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, 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 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) 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. @@ -725,6 +730,17 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion); } +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) { @@ -747,7 +763,7 @@ mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(struct mlxsw_sp_acl_tcam_vregion *v * 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 @@ mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp, 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 @@ mlxsw_sp_acl_tcam_ventry_activity_get(struct mlxsw_sp *mlxsw_sp, 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 @@ mlxsw_sp_acl_tcam_vchunk_migrate_start(struct mlxsw_sp *mlxsw_sp, { 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_vchunk_migrate_end(struct mlxsw_sp *mlxsw_sp, { 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 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, 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 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, 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 @@ mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, } } +out: mlxsw_sp_acl_tcam_vchunk_migrate_end(mlxsw_sp, vchunk, ctx); return 0; } @@ -1292,6 +1326,9 @@ mlxsw_sp_acl_tcam_vchunk_migrate_all(struct mlxsw_sp *mlxsw_sp, 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 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, 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 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, /* 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 @@ mlxsw_sp_acl_tcam_vregion_rehash_start(struct mlxsw_sp *mlxsw_sp, 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 @@ mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, 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 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, 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 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, 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 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, 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 462bf448497d3..79a1d86065125 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 #include +#include #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/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index a5ac21a0ee33f..cb6b33a228ea2 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1868,8 +1868,8 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, 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 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, } /* 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 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, 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 @@ static int qede_flow_spec_to_rule(struct qede_dev *edev, 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/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index b621ddd4539cf..384ddad65aaf6 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2729,19 +2729,18 @@ static int ravb_setup_irq(struct ravb_private *priv, const char *irq_name, 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; } @@ -2751,9 +2750,9 @@ static int ravb_setup_irq(struct ravb_private *priv, const char *irq_name, 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/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index c66618d91c28f..f89716b1cfb64 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -784,6 +784,11 @@ static bool am65_cpts_match_tx_ts(struct am65_cpts *cpts, 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 cf7b73f8f4507..b69af69a1ccd3 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -421,12 +421,14 @@ static int prueth_init_rx_chns(struct prueth_emac *emac, 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 6dff2c85682d8..6fae161cbcb82 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -1598,7 +1598,7 @@ static void wx_set_num_queues(struct wx *wx) */ 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 2fa511227eac8..93295916b1d2b 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 @@ static int txgbe_clock_register(struct txgbe *txgbe) 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 @@ static int txgbe_i2c_register(struct txgbe *txgbe) 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/gtp.c b/drivers/net/gtp.c index ba4704c2c640b..e62d6cbdf9bc6 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1098,11 +1098,12 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, 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/macsec.c b/drivers/net/macsec.c index 0206b84284ab5..ff016c11b4a03 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -999,10 +999,12 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) 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 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) * 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 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) 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 fa8c6fdcf3018..d7aaefb5226b6 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -695,7 +695,8 @@ static int dp83869_configure_mode(struct phy_device *phydev, 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 0f3a1538a8b8e..f4f9412d0cd7e 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 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, 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 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, 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 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, 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 @@ static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index, 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 @@ static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index, 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/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 752f821a19901..df9d767cb5242 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1456,21 +1456,16 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* 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); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index edc34402e787f..a5469cf5cf670 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1368,6 +1368,9 @@ static const struct usb_device_id products[] = { {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 */ diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 3495591a5c29b..3a9148fb1422b 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1615,6 +1615,10 @@ static bool vxlan_set_mac(struct vxlan_dev *vxlan, 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 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) 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 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) 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 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) 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 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) 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 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) 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 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, 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 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, 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 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 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 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 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 @@ static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, 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 @@ static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, 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 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) !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 a6a37d67a50ad..9f4bf41a3d41e 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -9020,6 +9020,7 @@ static void ath11k_mac_op_ipv6_changed(struct ieee80211_hw *hw, 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 @@ static void ath11k_mac_op_ipv6_changed(struct ieee80211_hw *hw, } /* 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 072b0a5827d19..eca1457caa0ca 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 9b79279fd76ca..dbbcb2d0968c0 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 4863a3c746406..d84d7e955bb02 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 @@ int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, 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 9f69e04594e49..fe5bba8561d0c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c @@ -279,6 +279,7 @@ int iwl_mvm_unset_link_mapping(struct iwl_mvm *mvm, struct ieee80211_vif *vif, 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 @@ int iwl_mvm_remove_link(struct iwl_mvm *mvm, struct ieee80211_vif *vif, 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 f3e3986b4c72f..11559563ae381 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -2813,7 +2813,8 @@ static int iwl_mvm_build_scan_cmd(struct iwl_mvm *mvm, 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 b55fe320633c7..59e1fc0018df3 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -3899,7 +3899,7 @@ static int hwsim_pmsr_report_nl(struct sk_buff *msg, struct genl_info *info) } 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 7eb17f46a8153..9e1a34e23af26 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -424,7 +424,8 @@ struct trf7970a { 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 @@ static int trf7970a_power_up(struct trf7970a *trf) 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 @@ static int trf7970a_power_down(struct trf7970a *trf) 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 @@ static int trf7970a_probe(struct spi_device *spi) 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 @@ static int trf7970a_probe(struct spi_device *spi) 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 @@ static int trf7970a_probe(struct spi_device *spi) 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 @@ static void trf7970a_remove(struct spi_device *spi) 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 27281a9a8951d..095f59e7aa937 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -628,27 +628,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, } 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 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) "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 5397fb428b242..d16e976ae1a47 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -247,7 +247,8 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) 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 d0ed64dc7380e..b564c5f1450c6 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -741,6 +741,27 @@ static inline bool nvme_is_aen_req(u16 qid, __u16 command_id) 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 8e0bb9692685d..e393f6947ce49 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1286,6 +1286,9 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) 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 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) 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 fdbcdcedcee99..28bc2f373cfa0 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -360,12 +360,18 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue) } 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 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, 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 3ddbc3880cac8..fb518b00f71f6 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -285,9 +285,9 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, } 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 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, 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 a2325330bf221..89a001101a7fc 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -754,6 +754,19 @@ static struct configfs_attribute *nvmet_ns_attrs[] = { 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 8860a3eb71ec8..e06013c5dace9 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -437,10 +437,13 @@ void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl) 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 f460728e1df1f..c1306de1f4ddf 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -543,6 +543,7 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys, 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 a5422e2c979ad..380f22ee3ebba 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -348,6 +348,7 @@ static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu) 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 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue) 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/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index b700f52b7b679..11fcb1867118c 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -110,8 +110,10 @@ static int imx8_pcie_phy_power_on(struct phy *phy) /* 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 41162d7228c91..1d1db1737422a 100644 --- a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c @@ -603,7 +603,7 @@ static void comphy_gbe_phy_init(struct mvebu_a3700_comphy_lane *lane, 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 @@ static void comphy_gbe_phy_init(struct mvebu_a3700_comphy_lane *lane, * 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 03fb0d4b75d74..20d4c020a83c1 100644 --- a/drivers/phy/qualcomm/phy-qcom-m31.c +++ b/drivers/phy/qualcomm/phy-qcom-m31.c @@ -297,7 +297,7 @@ static int m31usb_phy_probe(struct platform_device *pdev) 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 7d585a4bbbba9..c21cdb8dbfe74 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -77,6 +77,7 @@ enum qphy_reg_layout { 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 @@ static const unsigned int qmp_v3_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [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 @@ static const unsigned int qmp_v45_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [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 @@ static const unsigned int qmp_v5_5nm_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [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 @@ static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [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 @@ static bool qmp_combo_configure_dp_mode(struct qmp_combo *qmp) 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 @@ static int qmp_combo_configure_dp_clocks(struct qmp_combo *qmp) 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 @@ static int qmp_combo_configure_dp_clocks(struct qmp_combo *qmp) /* 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 f5cfacf9be964..181057421c113 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 01a20d3be4b81..fa967a1af058f 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 a34f67bb7e61a..b60a4b60451e5 100644 --- a/drivers/phy/rockchip/Kconfig +++ b/drivers/phy/rockchip/Kconfig @@ -87,6 +87,7 @@ config PHY_ROCKCHIP_SAMSUNG_HDPTX 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 76b9cf417591d..bf74e429ff46e 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_grfcfg { }; 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 @@ static int rockchip_combphy_probe(struct platform_device *pdev) 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 @@ static int rockchip_combphy_probe(struct platform_device *pdev) 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_grfcfg rk3568_combphy_grfcfgs = { }; 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 @@ static int rk3588_combphy_cfg(struct rockchip_combphy_priv *priv) 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_grfcfg rk3588_combphy_grfcfgs = { }; 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 121e5961ce114..9857ee45b89e0 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 const struct rockchip_p3phy_ops rk3568_ops = { 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 @@ static int rockchip_p3phy_rk3588_init(struct rockchip_p3phy_priv *priv) /* 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); - } - - 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; + 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; } - 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 13cd614e12a1d..751fecd466e3e 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -69,7 +69,6 @@ struct tusb1210 { 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 const char * const tusb1210_chargers[] = { 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; + + power_supply_put(charger); - return val.intval; + return online; } static void tusb1210_chg_det_work(struct work_struct *work) @@ -473,9 +477,6 @@ static void tusb1210_remove_charger_detect(struct tusb1210 *tusb) 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 d376fa7114d1a..029efe16f8cc2 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 @@ static struct aspeed_pin_config aspeed_g6_configs[] = { 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 6649357637ff3..cffeb869130dd 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -2124,13 +2124,7 @@ int pinctrl_enable(struct pinctrl_dev *pctldev) 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 df1efc2e52025..6a94ecd6a8dea 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -220,14 +220,16 @@ int pinctrl_dt_to_map(struct pinctrl *p, struct pinctrl_dev *pctldev) 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 ac97724c59bae..4e87f5b875c0e 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -231,6 +231,7 @@ static const unsigned int byt_score_pins_map[BYT_NGPIO_SCORE] = { /* 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_plt_clk5_pins[] = { 101 }; 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_plt_clk_groups[] = { }; 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 @@ static const struct intel_pingroup byt_sus_groups[] = { 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_pmu_clk_groups[] = { }; 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 fde65e18cd145..6981e2fab93f3 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.h +++ b/drivers/pinctrl/intel/pinctrl-intel.h @@ -179,6 +179,10 @@ struct intel_community { .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 b6bc31abd2b06..b19bc391705ee 100644 --- a/drivers/pinctrl/mediatek/pinctrl-paris.c +++ b/drivers/pinctrl/mediatek/pinctrl-paris.c @@ -165,20 +165,21 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, 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 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, } 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 @@ static int mtk_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, 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 79f5d753d7e1a..50a87d9618a8e 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_dclk_x_pins[] = { GPIOX_10 }; 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 @@ static struct meson_pmx_group meson_a1_periphs_groups[] = { 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 spi_a_groups[] = { 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 eb5a8c6542606..20425afc6b331 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -2045,7 +2045,9 @@ static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl) 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 @@ static void rzg2l_gpio_irq_restore(struct rzg2l_pinctrl *pctrl) 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/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 30951f7131cd9..1accdaaf282c5 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 @@ -721,6 +721,7 @@ static struct miscdevice isst_if_char_driver = { 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/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index 1305cba61edd4..aca123783efcc 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -588,7 +588,7 @@ static const struct regulator_ops mt6360_chg_otg_ops = { }; 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 c345a77f9f78c..e4dbacd50a437 100644 --- a/drivers/power/supply/rt9455_charger.c +++ b/drivers/power/supply/rt9455_charger.c @@ -192,6 +192,7 @@ static const int rt9455_voreg_values[] = { 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 @@ static const int rt9455_boost_voltage_values[] = { 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/regulator/irq_helpers.c b/drivers/regulator/irq_helpers.c index fe7ae0f3f46af..5ab1a0befe12f 100644 --- a/drivers/regulator/irq_helpers.c +++ b/drivers/regulator/irq_helpers.c @@ -352,6 +352,9 @@ void *regulator_irq_helper(struct device *dev, 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 ad6587a378d09..24cc9fc94e900 100644 --- a/drivers/regulator/mt6360-regulator.c +++ b/drivers/regulator/mt6360-regulator.c @@ -319,15 +319,15 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } } -#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 unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } 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 656fe330d38f0..063e12c08e75f 100644 --- a/drivers/regulator/qcom-refgen-regulator.c +++ b/drivers/regulator/qcom-refgen-regulator.c @@ -140,6 +140,7 @@ static const struct of_device_id qcom_refgen_match_table[] = { { .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 086da36abc0b4..4955616517ce9 100644 --- a/drivers/regulator/vqmmc-ipq4019-regulator.c +++ b/drivers/regulator/vqmmc-ipq4019-regulator.c @@ -84,6 +84,7 @@ static const struct of_device_id regulator_ipq4019_of_match[] = { { .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 37173cb0f5f5a..c57694be9bd32 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -162,7 +162,8 @@ struct raw3270_request *raw3270_request_alloc(size_t size) /* * 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 @@ int raw3270_request_reset(struct raw3270_request *rq) 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 8613fa937237b..a2e771ebae8eb 100644 --- a/drivers/s390/cio/cio_inject.c +++ b/drivers/s390/cio/cio_inject.c @@ -95,7 +95,7 @@ static ssize_t crw_inject_write(struct file *file, const char __user *buf, return -EINVAL; } - buffer = vmemdup_user(buf, lbuf); + buffer = memdup_user_nul(buf, lbuf); if (IS_ERR(buffer)) return -ENOMEM; diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 0a3a678ffc7ee..6087547328ce9 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -658,7 +658,7 @@ int cca_sec2protkey(u16 cardnr, u16 domain, (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 cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, (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 cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, (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 eb7f5489ccf95..9bcf8fc69ebe4 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -556,13 +556,29 @@ static int check_reply_pl(const u8 *pl, const char *func) 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 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, 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 @@ static int _ep11_genaeskey(u16 card, u16 domain, 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 @@ static int ep11_cryptsingle(u16 card, u16 domain, 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 @@ static int _ep11_unwrapkey(u16 card, u16 domain, 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 @@ static int _ep11_wrapkey(u16 card, u16 domain, 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/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index f0b8b709649f2..a3adaec5504e4 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -364,30 +364,33 @@ static int qeth_cq_init(struct qeth_card *card) return rc; } +static void qeth_free_cq(struct qeth_card *card) +{ + if (card->qdio.c_q) { + qeth_free_qdio_queue(card->qdio.c_q); + card->qdio.c_q = NULL; + } +} + 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; + 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; + qeth_free_cq(card); } return 0; } -static void qeth_free_cq(struct qeth_card *card) -{ - if (card->qdio.c_q) { - qeth_free_qdio_queue(card->qdio.c_q); - card->qdio.c_q = NULL; - } -} - static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15, int delayed) { @@ -2628,6 +2631,10 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) 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 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT; } - /* completion */ - if (qeth_alloc_cq(card)) - goto out_freeoutq; - return 0; out_freeoutq: @@ -2677,6 +2680,8 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) 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 @@ static void qeth_free_qdio_queues(struct qeth_card *card) { 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 @@ static void qeth_qdio_poll(struct ccw_device *cdev, unsigned long card_ptr) int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) { - int rc; - - 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; + if (card->options.cq == QETH_CQ_NOTAVAILABLE) + return -1; + card->options.cq = cq; + return 0; } EXPORT_SYMBOL_GPL(qeth_configure_cq); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 58fdf679341dc..65cdc8b77e358 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3120,6 +3120,7 @@ static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer) { 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 @@ static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer) 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/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c index efeba8275a669..a09a26bf4988f 100644 --- a/drivers/slimbus/qcom-ngd-ctrl.c +++ b/drivers/slimbus/qcom-ngd-ctrl.c @@ -1451,7 +1451,11 @@ static void qcom_slim_ngd_up_worker(struct work_struct *work) 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 50c664b65f4d4..1b7afb19ccd63 100644 --- a/drivers/soc/mediatek/Kconfig +++ b/drivers/soc/mediatek/Kconfig @@ -72,6 +72,7 @@ config MTK_SOCINFO 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 c832f5c670bcf..9a91298c12539 100644 --- a/drivers/soc/mediatek/mtk-svs.c +++ b/drivers/soc/mediatek/mtk-svs.c @@ -1768,6 +1768,7 @@ static int svs_bank_resource_setup(struct svs_platform *svsp) 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 @@ static int svs_bank_resource_setup(struct svs_platform *svsp) } 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 7cd24bd8e2248..6bcf8e75273c4 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -130,6 +130,19 @@ static void amd_sdw_set_frameshape(struct amd_sdw_manager *amd_manager) 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 @@ static int __maybe_unused amd_suspend(struct device *dev) } 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 @@ static int __maybe_unused amd_suspend_runtime(struct device *dev) 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 418b679e0b1a6..707065468e05a 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 7cc219d78551a..e358ac5b45097 100644 --- a/drivers/spi/spi-axi-spi-engine.c +++ b/drivers/spi/spi-axi-spi-engine.c @@ -623,7 +623,7 @@ static int spi_engine_probe(struct platform_device *pdev) 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 35ef5e8e2ffd2..77e9738e42f60 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -151,8 +151,6 @@ static const struct debugfs_reg32 hisi_spi_regs[] = { 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 ff75838c1b5df..a2c467d9e92f5 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -4523,6 +4523,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message) wait_for_completion(&done); status = message->status; } + message->complete = NULL; message->context = NULL; return status; diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c index d78d54ae2605e..5693cc8b231aa 100644 --- a/drivers/thermal/thermal_debugfs.c +++ b/drivers/thermal/thermal_debugfs.c @@ -139,11 +139,13 @@ struct tz_episode { * 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_add(struct thermal_cooling_device *cdev) */ 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); @@ -716,8 +726,7 @@ void thermal_debug_update_temp(struct thermal_zone_device *tz) 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); @@ -727,8 +736,7 @@ static void *tze_seq_start(struct seq_file *s, loff_t *pos) 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); @@ -736,15 +744,15 @@ static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos) 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; @@ -810,6 +818,8 @@ void thermal_debug_tz_add(struct thermal_zone_device *tz) 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); @@ -818,23 +828,44 @@ void thermal_debug_tz_add(struct thermal_zone_device *tz) 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/usb/core/hub.c b/drivers/usb/core/hub.c index 9446660e231bb..008053039875a 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5110,9 +5110,10 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, } 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 0e1262a077aea..e7da2fca11a48 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -51,13 +51,15 @@ static ssize_t disable_show(struct device *dev, 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 @@ static ssize_t disable_store(struct device *dev, struct device_attribute *attr, 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; diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 31684cdaaae30..100041320e8dd 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -104,6 +104,27 @@ static int dwc3_get_dr_mode(struct dwc3 *dwc) 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_core_ulpi_init(struct dwc3 *dwc) */ 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 @@ static int dwc3_phy_setup(struct dwc3 *dwc) 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. - */ - 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. + * 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 (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 @@ static int dwc3_phy_setup(struct dwc3 *dwc) 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 @@ static int dwc3_phy_setup(struct dwc3 *dwc) } /* - * 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. - */ - 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. + * 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 (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 @@ static int dwc3_core_init(struct dwc3 *dwc) 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 7e80dd3d466b8..180dd8d29287c 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1580,6 +1580,7 @@ int dwc3_event_buffers_setup(struct dwc3 *dwc); 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/gadget.c b/drivers/usb/dwc3/gadget.c index 4df2661f66751..f94f68f1e7d2b 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2924,6 +2924,7 @@ static int __dwc3_gadget_start(struct dwc3 *dwc) dwc3_ep0_out_start(dwc); dwc3_gadget_enable_irq(dwc); + dwc3_enable_susphy(dwc, true); return 0; @@ -4690,6 +4691,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc) 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 0204787df81d5..a171b27a7845a 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -10,10 +10,13 @@ #include #include #include +#include +#include #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_power_off_all_roothub_ports(struct dwc3 *dwc) } } +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 @@ int dwc3_host_init(struct dwc3 *dwc) } } + 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 @@ void dwc3_host_exit(struct dwc3 *dwc) 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 0ace45b66a31c..0e151b54aae82 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2112,7 +2112,7 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) 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 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) } 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 f855f1fc8e5e1..a057cbedf3c9b 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -852,6 +852,7 @@ static void ffs_user_copy_worker(struct work_struct *work) 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); @@ -864,6 +865,11 @@ static void ffs_user_copy_worker(struct work_struct *work) 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); @@ -877,7 +883,6 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep, 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); @@ -3806,7 +3811,7 @@ static int ffs_func_setup(struct usb_function *f, __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/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 7e704b2bcfd1c..a4377df612f51 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -92,10 +92,10 @@ static int __uvcg_iter_item_entries(const char *page, size_t len, 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/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 4f9982ecfb583..5cec7640e913c 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -888,6 +888,7 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) /* 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 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd) } 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 2d15386f2c504..6475130eac4b3 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-rzv2m.c b/drivers/usb/host/xhci-rzv2m.c index ec65b24eafa86..4f59867d7117c 100644 --- a/drivers/usb/host/xhci-rzv2m.c +++ b/drivers/usb/host/xhci-rzv2m.c @@ -6,6 +6,7 @@ */ #include +#include "xhci.h" #include "xhci-plat.h" #include "xhci-rzv2m.h" diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c index e48412cdcb0fb..d3958c061a972 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 @@ static int qcom_pmic_typec_probe(struct platform_device *pdev) 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 6560f4fc98d5a..5b7f52b74a40a 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 @@ static int qcom_pmic_typec_pdphy_enable(struct pmic_typec_pdphy *pmic_typec_pdph 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 @@ static int qcom_pmic_typec_pdphy_start(struct pmic_typec *tcpm, 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 ab6ed6111ed05..8a1af08f71b64 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1564,8 +1564,12 @@ static void tcpm_queue_vdm(struct tcpm_port *port, const u32 header, 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 @@ static void svdm_consume_identity(struct tcpm_port *port, const u32 *p, int cnt) 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 @@ static void tcpm_register_partner_altmodes(struct tcpm_port *port) 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 @@ static int tcpm_register_source_caps(struct tcpm_port *port) { 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 @@ static int tcpm_register_source_caps(struct tcpm_port *port) 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 int tcpm_init_vconn(struct tcpm_port *port) 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 @@ static void tcpm_typec_connect(struct tcpm_port *port) 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 @@ static void tcpm_typec_disconnect(struct tcpm_port *port) 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 enum typec_cc_status tcpm_pwr_opmode_to_rp(enum typec_pwr_opmode opmode) 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 @@ static void run_state_machine(struct tcpm_port *port) break; case PORT_RESET: tcpm_reset_port(port); + port->pd_events = 0; if (port->self_powered) tcpm_set_cc(port, TYPEC_CC_OPEN); else diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index b246067e074bc..6cb96a1e8b7df 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -967,7 +967,7 @@ vdpa_dev_blk_seg_size_config_fill(struct sk_buff *msg, u64 features, 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 @@ static int vdpa_dev_blk_ro_config_fill(struct sk_buff *msg, u64 features) 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 @@ static int vdpa_dev_blk_flush_config_fill(struct sk_buff *msg, u64 features) 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/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index dae96c9f61cf8..806ecd32219b6 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_track_page(struct fb_info *info, unsigned long */ 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/fs/9p/v9fs.h b/fs/9p/v9fs.h index 9defa12208f98..1775fcc7f0e8e 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -179,13 +179,14 @@ extern int v9fs_vfs_rename(struct mnt_idmap *idmap, 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 int v9fs_proto_dotl(struct v9fs_session_info *v9ses) */ 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_inode.c b/fs/9p/vfs_inode.c index 47bd77199e20c..7a3308d776060 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -364,7 +364,8 @@ void v9fs_evict_inode(struct inode *inode) 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; @@ -376,8 +377,18 @@ struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid) 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 @@ -401,11 +412,11 @@ struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid) 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); - } /** @@ -437,8 +448,15 @@ static int v9fs_at_to_dotl_flags(int flags) */ 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); + } + } } /** @@ -489,6 +507,9 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags) } 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); @@ -554,7 +575,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, /* * 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, @@ -683,7 +704,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, 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 diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 55dde186041a3..c61b97bd13b9a 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -52,7 +52,10 @@ static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode) 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 @@ struct inode *v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid) 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 @@ struct inode *v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid) 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 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, 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 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, } /* 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 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir, 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 55e67e36ae682..f52fdf42945cf 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -139,7 +139,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, 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; diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index fadb1078903d2..a200442010025 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -470,7 +470,7 @@ static int check_extent_checksum(struct btree_trans *trans, 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/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 085987435a5ea..f7fbfccd2b1e4 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -1504,7 +1504,8 @@ enum btree_id_flags { 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, \ diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index ecbd9598f69fd..791470b0c6545 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -1587,7 +1587,7 @@ static int bch2_gc_write_reflink_key(struct btree_trans *trans, 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; @@ -1595,6 +1595,7 @@ static int bch2_gc_write_reflink_key(struct btree_trans *trans, *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 9678b2375bedd..debb0edc3455a 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -888,7 +888,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, -BCH_ERR_btree_node_read_err_fixable, c, NULL, b, i, btree_node_bkey_bad_u64s, - "bad k->u64s %u (min %u max %lu)", k->u64s, + "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; diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 88a3582a32757..e8c1c530cd95f 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -842,8 +842,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, * 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)) @@ -857,11 +855,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, 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)) @@ -875,9 +868,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, 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) @@ -893,12 +883,12 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, 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); } @@ -916,7 +906,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, } 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_node_scan.c b/fs/bcachefs/btree_node_scan.c index 866bd278439f8..45cb8149d374c 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -57,13 +57,14 @@ static void found_btree_node_to_key(struct bkey_i *k, const struct found_btree_n 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 @@ static bool found_btree_node_is_readable(struct btree_trans *trans, 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 @@ -302,6 +305,8 @@ static int handle_overwrites(struct bch_fs *c, start->max_key = bpos_predecessor(n->min_key); start->range_updated = true; + } else if (n->level) { + n->overwritten = true; } else { struct printbuf buf = PRINTBUF; diff --git a/fs/bcachefs/btree_node_scan_types.h b/fs/bcachefs/btree_node_scan_types.h index abb7b27d556a9..5cfaeb5ac831b 100644 --- a/fs/bcachefs/btree_node_scan_types.h +++ b/fs/bcachefs/btree_node_scan_types.h @@ -9,6 +9,7 @@ struct found_btree_node { bool overwritten:1; u8 btree_id; u8 level; + unsigned sectors_written; u32 seq; u64 cookie; diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index e0c982a4195c7..c69b233c41bb3 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -321,9 +321,9 @@ struct bkey_cached { 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; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index 6030c396754f6..b4efd8cc4d1a2 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -1960,7 +1960,11 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, if ((flags & BCH_WATERMARK_MASK) == BCH_WATERMARK_interior_updates) return 0; - flags &= ~BCH_WATERMARK_MASK; + 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; diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index 941401a210f56..82f179258867b 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -525,7 +525,6 @@ int bch2_mark_metadata_bucket(struct bch_fs *c, struct bch_dev *ca, "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 @@ int bch2_check_bucket_ref(struct btree_trans *trans, 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/chardev.c b/fs/bcachefs/chardev.c index 72781aad6ba70..4d14f19f51850 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -232,13 +232,15 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a /* 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, &bch2_offline_fsck_ops); + ret = __bch2_run_thread_with_stdio(&thr->thr); out: darray_for_each(devs, i) kfree(*i); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index b5ea9fa1259d1..fce690007edfc 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -188,7 +188,8 @@ static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_ino 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 @@ static struct bch_inode_info *bch2_new_inode(struct btree_trans *trans) 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 ca4a066e9a542..0f95d7fb5ec0b 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -606,7 +606,7 @@ int bch2_trigger_inode(struct btree_trans *trans, 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 9aa28b52ab926..eb1f9d6f5a196 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -1723,7 +1723,7 @@ static void journal_write_endio(struct bio *bio) 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]); @@ -1768,6 +1768,44 @@ static CLOSURE_CALLBACK(do_journal_write) 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); @@ -2033,23 +2071,9 @@ CLOSURE_CALLBACK(bch2_journal_write) 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/recovery.c b/fs/bcachefs/recovery.c index 0f328aba9760b..be5b476193270 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -249,7 +249,10 @@ int bch2_journal_replay(struct bch_fs *c) 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/sb-clean.c b/fs/bcachefs/sb-clean.c index 5980ba2563fe9..35ca3f138de6f 100644 --- a/fs/bcachefs/sb-clean.c +++ b/fs/bcachefs/sb-clean.c @@ -29,6 +29,14 @@ int bch2_sb_clean_validate_late(struct bch_fs *c, struct bch_sb_field_clean *cle 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-errors_types.h b/fs/bcachefs/sb-errors_types.h index 4ca6e7b0d8aae..06c7a644f4a44 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -271,7 +271,8 @@ x(btree_root_unreadable_and_scan_found_nothing, 263) \ x(snapshot_node_missing, 264) \ x(dup_backpointer_to_bad_csum_extent, 265) \ - x(btree_bitmap_not_marked, 266) + 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 522a969345e52..5b8e621ac5eb5 100644 --- a/fs/bcachefs/sb-members.c +++ b/fs/bcachefs/sb-members.c @@ -463,8 +463,8 @@ static void __bch2_dev_btree_bitmap_mark(struct bch_sb_field_members_v2 *mi, uns m->btree_bitmap_shift += resize; } - for (unsigned bit = sectors >> m->btree_bitmap_shift; - bit << m->btree_bitmap_shift < end; + for (unsigned bit = start >> m->btree_bitmap_shift; + (u64) bit << m->btree_bitmap_shift < end; bit++) bitmap |= BIT_ULL(bit); diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h index b27c3e4467cf2..5efa64eca5f85 100644 --- a/fs/bcachefs/sb-members.h +++ b/fs/bcachefs/sb-members.h @@ -235,11 +235,11 @@ static inline bool bch2_dev_btree_bitmap_marked_sectors(struct bch_dev *ca, u64 { u64 end = start + sectors; - if (end > 64 << ca->mi.btree_bitmap_shift) + if (end > 64ULL << ca->mi.btree_bitmap_shift) return false; - for (unsigned bit = sectors >> ca->mi.btree_bitmap_shift; - bit << ca->mi.btree_bitmap_shift < end; + 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; diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index 8daf80a38d60c..88e214c609bb2 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -544,6 +544,7 @@ static void __bch2_fs_free(struct bch_fs *c) 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/thread_with_file.c b/fs/bcachefs/thread_with_file.c index 940db15d6a939..b1af7ac430f66 100644 --- a/fs/bcachefs/thread_with_file.c +++ b/fs/bcachefs/thread_with_file.c @@ -294,16 +294,27 @@ static int thread_with_stdio_fn(void *arg) 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 af54ea8f5b0ff..1d63d14d7dcae 100644 --- a/fs/bcachefs/thread_with_file.h +++ b/fs/bcachefs/thread_with_file.h @@ -63,6 +63,9 @@ struct thread_with_stdio { 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/btrfs/backref.c b/fs/btrfs/backref.c index c1e6a5bbeeaff..58110c9686673 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2776,20 +2776,14 @@ struct btrfs_data_container *init_data_container(u32 total_bytes) 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/extent_map.c b/fs/btrfs/extent_map.c index 445f7716f1e2f..24a048210b157 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -817,7 +817,7 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, 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 c65fe5de40220..7fed887e700c4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1145,13 +1145,13 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, 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 @@ static void submit_one_async_extent(struct async_chunk *async_chunk, 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 | diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 55f3ba6a831ca..0493272a7668e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3758,15 +3758,43 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) 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; @@ -3774,7 +3802,6 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) } 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 c96dd66fd0f72..210d9c82e2ae0 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 b749ba45da2ba..c2a42bcde98e0 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -1188,6 +1188,7 @@ struct btrfs_ordered_extent *btrfs_split_ordered_extent( 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 cf8820ce7aa29..364acc9bbe730 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1342,16 +1342,10 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) 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 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) 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 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_end_transaction(trans); else if (trans) ret = btrfs_commit_transaction(trans); -out_unlock_cleaner: - mutex_unlock(&fs_info->cleaner_mutex); - return ret; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index fa25004ab04e7..4b22cfe9a98cb 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1012,6 +1012,7 @@ static void scrub_stripe_read_repair_worker(struct work_struct *work) 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 @@ static void scrub_stripe_read_repair_worker(struct work_struct *work) * 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 253cce7ffecfe..47b5d301038ee 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -847,6 +847,11 @@ static int test_case_7(struct btrfs_fs_info *fs_info) 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/volumes.c b/fs/btrfs/volumes.c index f15591f3e54fa..ef6bd2f4251b5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3455,6 +3455,7 @@ static int btrfs_relocate_sys_chunks(struct btrfs_fs_info *fs_info) * alignment and size). */ ret = -EUCLEAN; + mutex_unlock(&fs_info->reclaim_bgs_lock); goto error; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 8aff1a724805a..62da538d91cbd 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -151,7 +151,7 @@ static int erofs_fscache_read_io_async(struct fscache_cookie *cookie, 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 39c67119f43bf..d28ccfc0352b1 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -84,13 +84,6 @@ struct erofs_dev_context { 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 c0eb139adb07a..30b49b2eee534 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -370,18 +370,18 @@ static int erofs_read_superblock(struct super_block *sb) 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 const struct fs_parameter_spec erofs_fs_parameters[] = { 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 bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) 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 @@ static int erofs_fc_parse_param(struct fs_context *fc, 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 @@ static int erofs_fc_parse_param(struct fs_context *fc, 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 @@ static int erofs_fc_parse_param(struct fs_context *fc, 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 const struct export_operations erofs_export_ops = { 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 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) 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_fill_super(struct super_block *sb, struct fs_context *fc) 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 @@ static int erofs_fc_reconfigure(struct fs_context *fc) { 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_free_dev_context(struct erofs_dev_context *devs) 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 const struct fs_context_operations erofs_context_ops = { 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 882b89edc52ad..f53ca4f7fcedd 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -979,6 +979,34 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep return res; } +/* + * 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() @@ -987,14 +1015,22 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep 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/ioctl.c b/fs/ioctl.c index 1d5abfdf0f22a..fb0628e680c40 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -769,7 +769,7 @@ static int ioctl_getfsuuid(struct file *file, void __user *argp) 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 @@ static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp) 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/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 9a0d32e4b422a..267b622d923b1 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -164,7 +164,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, 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 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, 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 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, 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 c709c296ea9a4..acef52ecb1bb7 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2429,7 +2429,12 @@ static int nfs_net_init(struct net *net) 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 87c9547989f69..e88aca0c6e8ef 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -983,15 +983,7 @@ static struct workqueue_struct *callback_wq; 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 @@ static void 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 @@ nfsd4_run_cb_work(struct work_struct *work) 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 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, 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 1955481832e03..a644460f3a5e7 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3515,6 +3515,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, 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. @@ -3573,7 +3574,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, } else args.fhp = fhp; - args.acl = NULL; if (attrmask[0] & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 01c6f34456469..2ed0fcf879fd1 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -68,7 +68,7 @@ struct nfsd4_callback { 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/ntfs3/Kconfig b/fs/ntfs3/Kconfig index cdfdf51e55d79..7bc31d69f680d 100644 --- a/fs/ntfs3/Kconfig +++ b/fs/ntfs3/Kconfig @@ -46,3 +46,12 @@ config NTFS3_FS_POSIX_ACL 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 5cf3d9decf646..263635199b60d 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -616,4 +616,11 @@ const struct file_operations ntfs_dir_operations = { .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 5418662c80d88..b73969e05052a 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -1236,4 +1236,12 @@ const struct file_operations ntfs_file_operations = { .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 eb7a8c9fba018..d273eda1cf45d 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -440,7 +440,10 @@ static struct inode *ntfs_read_mft(struct inode *inode, * 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 @@ static struct inode *ntfs_read_mft(struct inode *inode, } 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 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, 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 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, 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 79356fd29a141..5f4d288c6adfb 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -493,6 +493,7 @@ struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni, 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 @@ long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg); 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 @@ static inline void le64_sub_cpu(__le64 *var, u64 val) *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 9df7c20d066f6..b26d95a8d3274 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -408,6 +408,12 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) 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 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) 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 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) return -EINVAL; } +out: + sync_filesystem(sb); swap(sbi->options, fc->fs_private); return 0; @@ -1613,6 +1619,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) } #endif + if (is_legacy_ntfs(sb)) + sb->s_flags |= SB_RDONLY; return 0; put_inode_out: @@ -1730,7 +1738,7 @@ static const struct fs_context_operations ntfs_context_ops = { * 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 @@ static int ntfs_init_fs_context(struct fs_context *fc) 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 @@ static struct file_system_type ntfs_fs_type = { .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 @@ static int __init init_ntfs_fs(void) goto out1; } + register_as_ntfs_legacy(); err = register_filesystem(&ntfs_fs_type); if (err) goto out; @@ -1849,6 +1907,7 @@ static void __exit exit_ntfs_fs(void) 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/page.c b/fs/proc/page.c index 195b077c0facb..9223856c934b4 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -67,7 +67,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, */ 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 @@ u64 stable_page_flags(struct page *page) /* * 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/cifsfs.c b/fs/smb/client/cifsfs.c index d41eedbff674a..39277c37185ca 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -389,6 +389,7 @@ cifs_alloc_inode(struct super_block *sb) * 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 @@ static void cifs_umount_begin(struct super_block *sb) 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 d6669ce4ae87f..6ff35570db813 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1190,6 +1190,7 @@ struct cifs_fattr { */ 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 */ @@ -1276,7 +1277,9 @@ struct cifs_tcon { __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 c0513fbb8a59d..c46d418c1c0c3 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -882,7 +882,7 @@ typedef struct smb_com_open_rsp { __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 @@ typedef struct { /* 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 8e0a348f1f660..fbc358c09da3b 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -303,7 +303,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, 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 int CIFSSMBLogoff(const unsigned int xid, struct cifs_ses *ses); 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 @@ static inline int cifs_create_options(struct cifs_sb_info *cifs_sb, int options) 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 4e35970681bf0..7a16e12f5da87 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1943,7 +1943,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) } /* 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 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) 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 @@ void __cifs_put_smb_ses(struct cifs_ses *ses) * 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); @@ -2432,6 +2432,8 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) 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; @@ -2441,7 +2443,7 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) } 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; @@ -2457,6 +2459,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) 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); @@ -2493,7 +2496,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) _free_xid(xid); cifs_fscache_release_super_cookie(tcon); - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free); cifs_put_smb_ses(ses); } @@ -2547,7 +2550,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) 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; @@ -2737,7 +2740,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) return tcon; out_fail: - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free_fail); return ERR_PTR(rc); } @@ -2754,7 +2757,7 @@ cifs_put_tlink(struct tcon_link *tlink) } 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); } @@ -3319,7 +3322,7 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx) 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 6c727d8c31e87..3bbac925d0766 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -748,6 +748,16 @@ static int smb3_fs_context_validate(struct fs_context *fc) /* 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"); @@ -1019,12 +1029,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, 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) diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index a947bddeba273..cf577ec0dd0ac 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -165,6 +165,8 @@ enum cifs_param { }; struct smb3_fs_context { + bool forceuid_specified; + bool forcegid_specified; bool uid_specified; bool cruid_specified; bool gid_specified; diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index 340efce8f0529..1a895e6243ee9 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -43,12 +43,23 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) 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 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) 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 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) } 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 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) kfree(key); out: kfree(sharename); + mutex_unlock(&tcon->fscache_lock); return ret; } @@ -102,6 +120,8 @@ void cifs_fscache_release_super_cookie(struct cifs_tcon *tcon) 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/misc.c b/fs/smb/client/misc.c index 7d15a1969b818..07c468ddb88a8 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -111,9 +111,10 @@ sesInfoFree(struct cifs_ses *buf_to_free) } 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) @@ -130,7 +131,8 @@ tcon_info_alloc(bool dir_leases_enabled) 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); @@ -139,17 +141,22 @@ tcon_info_alloc(bool dir_leases_enabled) 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 cc72be5a93a93..677ef6f99a5be 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -767,7 +767,7 @@ smb2_cancelled_close_fid(struct work_struct *work) 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 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, 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 @@ smb2_handle_cancelled_close(struct cifs_tcon *tcon, __u64 persistent_fid, 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 @@ smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *serve 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 78c94d0350fe9..28f0b7d19d534 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2915,8 +2915,11 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, 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 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, /* 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); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 86c647a947ccd..a5efce03cb58e 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4138,6 +4138,8 @@ void smb2_reconnect_server(struct work_struct *work) 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; } @@ -4176,14 +4178,14 @@ void smb2_reconnect_server(struct work_struct *work) 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) { @@ -4206,7 +4208,7 @@ void smb2_reconnect_server(struct work_struct *work) 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 c72a3b2886b7f..2fccf0d4f53d2 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -320,7 +320,7 @@ struct smb2_file_reparse_point_info { } __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 1d6e54f7879e6..02135a6053051 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -189,6 +189,8 @@ smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid) 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 5e83cb9da9028..604e52876cd2d 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 + * + * 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 /* - * 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(waitff_credits); 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 994d701934329..ddf1a3aafee5c 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -909,12 +909,15 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) 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 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) 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 1b594307c9d5a..202ff91281560 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -711,7 +711,7 @@ struct smb2_close_rsp { __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 686b321c5a8bb..f4e55199938d5 100644 --- a/fs/smb/server/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h @@ -340,23 +340,24 @@ enum KSMBD_TREE_CONN_STATUS { /* * 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 c0788188aa82f..c67fbc8d6683e 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -167,20 +167,17 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, 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 5723bbf372d7c..355824151c2d8 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -535,6 +535,10 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) 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 @@ int smb2_tree_connect(struct ksmbd_work *work) 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 @@ int smb2_open(struct ksmbd_work *work) 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 22f0f3db3ac92..51b1b0bed616e 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -754,10 +754,15 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, 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/tracefs/event_inode.c b/fs/tracefs/event_inode.c index 894c6ca1e5002..a878cea70f4c9 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -37,6 +37,7 @@ static DEFINE_MUTEX(eventfs_mutex); struct eventfs_root_inode { struct eventfs_inode ei; + struct inode *parent_inode; struct dentry *events_dir; }; @@ -68,11 +69,25 @@ enum { 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 @@ enum { 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 @@ static inline void free_ei(struct eventfs_inode *ei) } } +/* + * 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 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, * 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 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry, 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 @@ static void set_top_events_ownership(struct inode *inode) 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 @@ static int eventfs_permission(struct mnt_idmap *idmap, 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 @@ static const struct file_operations eventfs_file_operations = { .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 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry) // 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; } @@ -410,7 +458,7 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry, 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 */ @@ -734,7 +782,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode /* Was the parent freed? */ if (list_empty(&ei->list)) { - free_ei(ei); + cleanup_ei(ei); ei = NULL; } return ei; @@ -781,6 +829,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry // 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; @@ -790,29 +839,26 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry 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); @@ -835,7 +881,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry 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 5545e6bf7d26c..417c840e64033 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -30,20 +30,47 @@ static struct vfsmount *tracefs_mount; 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 @@ static void set_tracefs_inode_owner(struct inode *inode) { 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 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) 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 @@ static int tracefs_apply_options(struct super_block *sb, bool remount) 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 @@ static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags) 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 15c26f9aaad4d..f704d8348357e 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_end_creating(struct dentry *dentry); 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/include/linux/cpu.h b/include/linux/cpu.h index 272e4e79e15c4..861c3bfc5f170 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -221,7 +221,18 @@ void cpuhp_report_idle_dead(void); 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/etherdevice.h b/include/linux/etherdevice.h index 224645f17c333..297231854ada5 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -607,6 +607,31 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, eth_hw_addr_set(dev, addr); } +/** + * 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 44934b968b57d..42dbceb04ca6c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -975,6 +975,7 @@ bool bpf_jit_supports_far_kfunc_call(void); 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 5c28298a98bec..366243ee96096 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 +#include #include #include @@ -24,12 +25,57 @@ struct qseecom_client { u32 app_id; }; +/** + * 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 @@ struct qseecom_client { * * 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 ccaf288460546..aaa19f93ac430 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -118,8 +118,8 @@ bool qcom_scm_lmh_dcvsh_available(void); #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 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) 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/mm.h b/include/linux/mm.h index 7b0ee64225de9..b6bdaa18b9e9d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1223,14 +1223,16 @@ static inline void page_mapcount_reset(struct page *page) * 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)); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 652d77805e99d..4bf1c25fd1dc5 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,7 +190,6 @@ enum pageflags { /* 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 @@ static __always_inline int TestClearPage##uname(struct page *page) \ 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 @@ TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) #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 @@ -933,34 +930,23 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #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 @@ static inline int page_has_type(const struct page *page) return page_type_has_type(page->page_type); } +#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 __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 __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 int 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; \ -} \ +} /* * PageBuddy() indicates that the page is free and in the buddy system @@ -1052,6 +1041,37 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ 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 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #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/profile.h b/include/linux/profile.h index 11db1ec516e27..04ae5ebcb637a 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -18,13 +18,8 @@ struct proc_dir_entry; 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/regmap.h b/include/linux/regmap.h index b743241cfb7ca..d470303b1bbbb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1230,6 +1230,7 @@ int regmap_multi_reg_write_bypassed(struct regmap *map, 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 @@ static inline int regmap_read(struct regmap *map, unsigned int reg, 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 4660582a33022..ed180ca419dad 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -320,13 +320,13 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) 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/sched/ext.h b/include/linux/sched/ext.h index dd113d4a95ada..364ca827a45e7 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -51,14 +51,17 @@ enum scx_dsq_id_flags { }; /* - * Dispatch queue (dsq) is a simple FIFO which is used to buffer between the - * scheduler core and the BPF scheduler. See the documentation for more details. + * A dispatch queue (DSQ) can be either a FIFO or p->scx.dsq_vtime ordered + * queue. A built-in DSQ is always a FIFO. The built-in local DSQs are used to + * buffer between the scheduler core and the BPF scheduler. See the + * documentation for more details. */ struct scx_dispatch_q { raw_spinlock_t lock; - struct list_head fifo; /* processed in dispatching order */ - struct rb_root_cached priq; /* processed in p->scx.dsq_vtime order */ + struct list_head list; /* tasks in dispatch order */ + struct rb_root priq; /* used to order by p->scx.dsq_vtime */ u32 nr; + u64 seq; /* used by BPF iter */ u64 id; struct rhash_head hash_node; struct llist_node free_node; @@ -92,6 +95,8 @@ enum scx_task_state { /* scx_entity.dsq_flags */ enum scx_ent_dsq_flags { SCX_TASK_DSQ_ON_PRIQ = 1 << 0, /* task is queued on the priority queue of a dsq */ + + SCX_TASK_DSQ_CURSOR = 1 << 31, /* iteration cursor, not a task */ }; /* @@ -119,18 +124,21 @@ enum scx_kf_mask { __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, }; +struct scx_dsq_node { + struct list_head list; /* dispatch order */ + struct rb_node priq; /* p->scx.dsq_vtime order */ + u32 flags; /* SCX_TASK_DSQ_* flags */ +}; + /* * The following is embedded in task_struct and contains all fields necessary * for a task to be scheduled by SCX. */ struct sched_ext_entity { struct scx_dispatch_q *dsq; - struct { - struct list_head fifo; /* dispatch order */ - struct rb_node priq; /* p->scx.dsq_vtime order */ - } dsq_node; + struct scx_dsq_node dsq_node; /* protected by dsq lock */ + u64 dsq_seq; u32 flags; /* protected by rq lock */ - u32 dsq_flags; /* protected by dsq lock */ u32 weight; s32 sticky_cpu; s32 holding_cpu; @@ -183,10 +191,11 @@ struct sched_ext_entity { bool disallow; /* reject switching into SCX */ /* cold fields */ - struct list_head tasks_node; #ifdef CONFIG_EXT_GROUP_SCHED struct cgroup *cgrp_moving_from; #endif + /* must be the last field, see init_scx_entity() */ + struct list_head tasks_node; }; void sched_ext_free(struct task_struct *p); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd27998..a509caf823d61 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -461,10 +461,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) 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/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24cd199dd6f3a..d33bab33099ab 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -210,7 +210,6 @@ struct svc_rdma_recv_ctxt { */ 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 svc_rdma_send_ctxt { 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_init(struct svcxprt_rdma *rdma, 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/tracefs.h b/include/linux/tracefs.h index 7a5fe17b6bf9c..d03f746587167 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -62,6 +62,8 @@ struct eventfs_file; 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 @@ typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, struct eventfs_entry { const char *name; eventfs_callback callback; + eventfs_release release; }; struct eventfs_inode; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 627ea8e2d9159..3dee0b2721aa4 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -85,6 +85,9 @@ enum unix_socket_lock_class { 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/hci_core.h b/include/net/bluetooth/hci_core.h index 56fb42df44a33..e8f581f3f3ce6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -738,6 +738,8 @@ struct hci_conn { __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 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, 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 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #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 50f1e403dbbb3..c1d4ca0463a17 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -87,6 +87,15 @@ struct napi_gro_cb { /* 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/mac80211.h b/include/net/mac80211.h index 353488ab94a29..2d7f87bc5324b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -953,6 +953,8 @@ enum mac80211_tx_info_flags { * 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 @@ enum mac80211_tx_control_flags { 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 dbd22180cc5c3..de216cbc6b059 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -321,6 +321,7 @@ struct macsec_context { * 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 macsec_ops { 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/sock.h b/include/net/sock.h index f57bfd8a2ad2d..b4b553df7870c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1410,32 +1410,34 @@ sk_memory_allocated(const struct sock *sk) #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) extern int sysctl_mem_pcpu_rsv; +static inline void proto_memory_pcpu_drain(struct proto *proto) +{ + int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); + + if (val) + atomic_long_add(val, proto->memory_allocated); +} + static inline void -sk_memory_allocated_add(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_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(); + 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(struct sock *sk, int amt) +sk_memory_allocated_sub(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_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 340ad43971e47..33f657d3c0510 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -111,7 +111,8 @@ struct tls_strparser { 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 e0629699b5633..1a3c6f66f6205 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -267,6 +267,7 @@ struct cs35l56_base { 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 char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC]; 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 1af9e68193920..234b5baea69c8 100644 --- a/include/sound/emu10k1.h +++ b/include/sound/emu10k1.h @@ -1684,8 +1684,8 @@ struct snd_emu1010 { 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 @@ unsigned int snd_emu10k1_ptr20_read(struct snd_emu10k1 * emu, unsigned int reg, 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 d801409b33cfe..d55e53ac91bd2 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -135,6 +135,7 @@ IF_HAVE_PG_ARCH_X(arch_3) #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/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h index d87410a8443aa..af024d90453dd 100644 --- a/include/uapi/drm/etnaviv_drm.h +++ b/include/uapi/drm/etnaviv_drm.h @@ -77,11 +77,6 @@ struct drm_etnaviv_timespec { #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 43c51698195ce..842bf1201ac41 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -57,7 +57,7 @@ enum vdpa_attr { 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 @@ enum vdpa_attr { 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/init/Kconfig b/init/Kconfig index b8fde3e53a773..41db869257cd8 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1904,11 +1904,11 @@ config RUST 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/init_task.c b/init/init_task.c index a32c606cc81ba..6bac934219d8a 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -101,15 +101,12 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { #endif #ifdef CONFIG_SCHED_CLASS_EXT .scx = { - .dsq_node.fifo = LIST_HEAD_INIT(init_task.scx.dsq_node.fifo), - .flags = 0, + .dsq_node.list = LIST_HEAD_INIT(init_task.scx.dsq_node.list), .sticky_cpu = -1, .holding_cpu = -1, - .ops_state = ATOMIC_INIT(0), .runnable_node = LIST_HEAD_INIT(init_task.scx.runnable_node), .runnable_at = INITIAL_JIFFIES, .ddsp_dsq_id = SCX_DSQ_INVALID, - .ddsp_enq_flags = 0, .slice = SCX_SLICE_DFL, }, #endif diff --git a/kernel/bounds.c b/kernel/bounds.c index c5a9fcd2d6228..29b2cd00df2cc 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -19,7 +19,7 @@ int main(void) 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 5aacb1d3c4cc7..a04695ca82b92 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2958,6 +2958,15 @@ bool __weak bpf_jit_supports_arena(void) 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 58952f0407619..d09ddefdb7833 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18293,8 +18293,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) 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); } @@ -19685,6 +19684,36 @@ static int do_misc_fixups(struct bpf_verifier_env *env) 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/cpu.c b/kernel/cpu.c index 07ad53b7f1195..63447eb85dab6 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -3196,6 +3196,7 @@ void __init boot_cpu_hotplug_init(void) 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. @@ -3206,9 +3207,7 @@ enum cpu_mitigations { CPU_MITIGATIONS_AUTO_NOSMT, }; -static enum cpu_mitigations cpu_mitigations __ro_after_init = - IS_ENABLED(CONFIG_SPECULATION_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : - CPU_MITIGATIONS_OFF; +static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { @@ -3224,7 +3223,6 @@ static int __init mitigations_parse_cmdline(char *arg) return 0; } -early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) @@ -3239,3 +3237,11 @@ bool cpu_mitigations_auto_nosmt(void) 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 a5e0dfc44d24e..0de66f0ff43ab 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -1798,6 +1798,7 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, 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/profile.c b/kernel/profile.c index 8a77769bc4b4c..2b775cc5c28f9 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -344,49 +344,6 @@ void profile_tick(int type) #include #include -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/core.c b/kernel/sched/core.c index ae7039676d313..f3d210301e9f0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4585,20 +4585,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->rt.on_list = 0; #ifdef CONFIG_SCHED_CLASS_EXT - p->scx.dsq = NULL; - INIT_LIST_HEAD(&p->scx.dsq_node.fifo); - RB_CLEAR_NODE(&p->scx.dsq_node.priq); - p->scx.flags = 0; - p->scx.weight = 0; - p->scx.sticky_cpu = -1; - p->scx.holding_cpu = -1; - p->scx.kf_mask = 0; - atomic_long_set(&p->scx.ops_state, 0); - INIT_LIST_HEAD(&p->scx.runnable_node); - p->scx.runnable_at = jiffies; - p->scx.ddsp_dsq_id = SCX_DSQ_INVALID; - p->scx.ddsp_enq_flags = 0; - p->scx.slice = SCX_SLICE_DFL; + init_scx_entity(&p->scx); #endif #ifdef CONFIG_PREEMPT_NOTIFIERS diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index fc695b13efb05..f805b8ee6474b 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -121,10 +121,10 @@ enum scx_ops_flags { */ SCX_OPS_CGROUP_KNOB_WEIGHT = 1LLU << 16, /* cpu.weight */ - SCX_OPS_ALL_FLAGS = SCX_OPS_SWITCH_PARTIAL | - SCX_OPS_KEEP_BUILTIN_IDLE | + SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | SCX_OPS_ENQ_LAST | SCX_OPS_ENQ_EXITING | + SCX_OPS_SWITCH_PARTIAL | SCX_OPS_CGROUP_KNOB_WEIGHT, }; @@ -155,13 +155,13 @@ struct scx_cgroup_init_args { enum scx_cpu_preempt_reason { /* next task is being scheduled by &sched_class_rt */ - SCX_CPU_PREEMPT_RT, + SCX_CPU_PREEMPT_RT, /* next task is being scheduled by &sched_class_dl */ - SCX_CPU_PREEMPT_DL, + SCX_CPU_PREEMPT_DL, /* next task is being scheduled by &sched_class_stop */ - SCX_CPU_PREEMPT_STOP, + SCX_CPU_PREEMPT_STOP, /* unknown reason for SCX being preempted */ - SCX_CPU_PREEMPT_UNKNOWN, + SCX_CPU_PREEMPT_UNKNOWN, }; /* @@ -176,7 +176,18 @@ struct scx_cpu_release_args { enum scx_cpu_preempt_reason reason; /* the task that's going to be scheduled on the CPU */ - struct task_struct *task; + struct task_struct *task; +}; + +/* + * Informational context provided to dump operations. + */ +struct scx_dump_ctx { + enum scx_exit_kind kind; + s64 exit_code; + const char *reason; + u64 at_ns; + u64 at_jiffies; }; /** @@ -292,9 +303,10 @@ struct sched_ext_ops { * * This and ->enqueue() are related but not coupled. This operation * notifies @p's state transition and may not be followed by ->enqueue() - * e.g. when @p is being dispatched to a remote CPU. Likewise, a task - * may be ->enqueue()'d without being preceded by this operation e.g. - * after exhausting its slice. + * e.g. when @p is being dispatched to a remote CPU, or when @p is + * being enqueued on a CPU experiencing a hotplug event. Likewise, a + * task may be ->enqueue()'d without being preceded by this operation + * e.g. after exhausting its slice. */ void (*runnable)(struct task_struct *p, u64 enq_flags); @@ -475,6 +487,36 @@ struct sched_ext_ops { */ void (*disable)(struct task_struct *p); + /** + * dump - Dump BPF scheduler state on error + * @ctx: debug dump context + * + * Use scx_bpf_dump() to generate BPF scheduler specific debug dump. + */ + void (*dump)(struct scx_dump_ctx *ctx); + + /** + * dump_cpu - Dump BPF scheduler state for a CPU on error + * @ctx: debug dump context + * @cpu: CPU to generate debug dump for + * @idle: @cpu is currently idle without any runnable tasks + * + * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for + * @cpu. If @idle is %true and this operation doesn't produce any + * output, @cpu is skipped for dump. + */ + void (*dump_cpu)(struct scx_dump_ctx *ctx, s32 cpu, bool idle); + + /** + * dump_task - Dump BPF scheduler state for a runnable task on error + * @ctx: debug dump context + * @p: runnable task to generate debug dump for + * + * Use scx_bpf_dump() to generate BPF scheduler specific debug dump for + * @p. + */ + void (*dump_task)(struct scx_dump_ctx *ctx, struct task_struct *p); + #ifdef CONFIG_EXT_GROUP_SCHED /** * cgroup_init - Initialize a cgroup @@ -556,8 +598,8 @@ struct sched_ext_ops { * cpu_online - A CPU became online * @cpu: CPU which just came up * - * @cpu just came online. @cpu doesn't call ops.enqueue() or run tasks - * associated with other CPUs beforehand. + * @cpu just came online. @cpu will not call ops.enqueue() or + * ops.dispatch(), nor run tasks associated with other CPUs beforehand. */ void (*cpu_online)(s32 cpu); @@ -565,8 +607,8 @@ struct sched_ext_ops { * cpu_offline - A CPU is going offline * @cpu: CPU which is going offline * - * @cpu is going offline. @cpu doesn't call ops.enqueue() or run tasks - * associated with other CPUs afterwards. + * @cpu is going offline. @cpu will not call ops.enqueue() or + * ops.dispatch(), nor run tasks associated with other CPUs afterwards. */ void (*cpu_offline)(s32 cpu); @@ -879,6 +921,16 @@ static unsigned long __percpu *scx_kick_cpus_pnt_seqs; */ static DEFINE_PER_CPU(struct task_struct *, direct_dispatch_task); +/* + * Has the current CPU been onlined from the perspective of scx? + * + * A hotplugged CPU may begin scheduling tasks before the core scheduler will + * call into rq_online_scx(). Track whether we've had a chance to invoke + * ops.cpu_online() so we can skip invoking ops.enqueue() or ops.dispatch() on + * that CPU until the scheduler knows about the hotplug event. + */ +static DEFINE_PER_CPU(bool, scx_cpu_online); + /* dispatch queues */ static struct scx_dispatch_q __cacheline_aligned_in_smp scx_dsq_global; @@ -911,6 +963,12 @@ struct scx_dsp_ctx { static DEFINE_PER_CPU(struct scx_dsp_ctx, scx_dsp_ctx); +/* ops debug dump */ +static s32 scx_dump_cpu = -1; +static char scx_dump_last; +static struct seq_buf *scx_dump_seq_buf; +static const char *scx_dump_prefix; + /* /sys/kernel/sched_ext interface */ static struct kset *scx_kset; static struct kobject *scx_root_kobj; @@ -920,22 +978,15 @@ static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind, s64 exit_code, const char *fmt, ...); -#define scx_ops_error_kind(__err, fmt, args...) \ - scx_ops_exit_kind(__err, 0, fmt, ##args) +#define scx_ops_error_kind(err, fmt, args...) \ + scx_ops_exit_kind((err), 0, fmt, ##args) -#define scx_ops_exit(__code, fmt, args...) \ - scx_ops_exit_kind(SCX_EXIT_UNREG_KERN, __code, fmt, ##args) +#define scx_ops_exit(code, fmt, args...) \ + scx_ops_exit_kind(SCX_EXIT_UNREG_KERN, (code), fmt, ##args) #define scx_ops_error(fmt, args...) \ scx_ops_error_kind(SCX_EXIT_ERROR, fmt, ##args) -struct scx_task_iter { - struct sched_ext_entity cursor; - struct task_struct *locked; - struct rq *rq; - struct rq_flags rf; -}; - #define SCX_HAS_OP(op) static_branch_likely(&scx_has_op[SCX_OP_IDX(op)]) static long jiffies_delta_msecs(unsigned long at, unsigned long now) @@ -974,10 +1025,12 @@ static __always_inline void scx_kf_allow(u32 mask) "invalid nesting current->scx.kf_mask=0x%x mask=0x%x\n", current->scx.kf_mask, mask); current->scx.kf_mask |= mask; + barrier(); } static void scx_kf_disallow(u32 mask) { + barrier(); current->scx.kf_mask &= ~mask; } @@ -1085,7 +1138,7 @@ static __always_inline bool scx_kf_allowed(u32 mask) static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask, struct task_struct *p) { - if (!scx_kf_allowed(__SCX_KF_RQ_LOCKED)) + if (!scx_kf_allowed(mask)) return false; if (unlikely((p != current->scx.kf_tasks[0] && @@ -1097,6 +1150,89 @@ static __always_inline bool scx_kf_allowed_on_arg_tasks(u32 mask, return true; } +/** + * nldsq_next_task - Iterate to the next task in a non-local DSQ + * @dsq: user dsq being interated + * @cur: current position, %NULL to start iteration + * @rev: walk backwards + * + * Returns %NULL when iteration is finished. + */ +static struct task_struct *nldsq_next_task(struct scx_dispatch_q *dsq, + struct task_struct *cur, bool rev) +{ + struct list_head *list_node; + struct scx_dsq_node *dsq_node; + + lockdep_assert_held(&dsq->lock); + + if (cur) + list_node = &cur->scx.dsq_node.list; + else + list_node = &dsq->list; + + /* find the next task, need to skip BPF iteration cursors */ + do { + if (rev) + list_node = list_node->prev; + else + list_node = list_node->next; + + if (list_node == &dsq->list) + return NULL; + + dsq_node = container_of(list_node, struct scx_dsq_node, list); + } while (dsq_node->flags & SCX_TASK_DSQ_CURSOR); + + return container_of(dsq_node, struct task_struct, scx.dsq_node); +} + +#define nldsq_for_each_task(p, dsq) \ + for ((p) = nldsq_next_task((dsq), NULL, false); (p); \ + (p) = nldsq_next_task((dsq), (p), false)) + + +/* + * BPF DSQ iterator. Tasks in a non-local DSQ can be iterated in [reverse] + * dispatch order. BPF-visible iterator is opaque and larger to allow future + * changes without breaking backward compatibility. Can be used with + * bpf_for_each(). See bpf_iter_scx_dsq_*(). + */ +enum scx_dsq_iter_flags { + /* iterate in the reverse dispatch order */ + SCX_DSQ_ITER_REV = 1LLU << 0, + + __SCX_DSQ_ITER_ALL_FLAGS = SCX_DSQ_ITER_REV, +}; + +struct bpf_iter_scx_dsq_kern { + /* + * Must be the first field. Used to work around BPF restriction and pass + * in the iterator pointer to scx_bpf_consume_task(). + */ + struct bpf_iter_scx_dsq_kern *self; + + struct scx_dsq_node cursor; + struct scx_dispatch_q *dsq; + u64 dsq_seq; + u64 flags; +} __attribute__((aligned(8))); + +struct bpf_iter_scx_dsq { + u64 __opaque[12]; +} __attribute__((aligned(8))); + + +/* + * SCX task iterator. + */ +struct scx_task_iter { + struct sched_ext_entity cursor; + struct task_struct *locked; + struct rq *rq; + struct rq_flags rf; +}; + /** * scx_task_iter_init - Initialize a task iterator * @iter: iterator to init @@ -1379,13 +1515,19 @@ static bool scx_dsq_priq_less(struct rb_node *node_a, return time_before64(a->scx.dsq_vtime, b->scx.dsq_vtime); } +static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) +{ + /* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */ + WRITE_ONCE(dsq->nr, dsq->nr + delta); +} + static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, u64 enq_flags) { bool is_local = dsq->id == SCX_DSQ_LOCAL; - WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_node.fifo)); - WARN_ON_ONCE((p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) || + WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_node.list)); + WARN_ON_ONCE((p->scx.dsq_node.flags & SCX_TASK_DSQ_ON_PRIQ) || !RB_EMPTY_NODE(&p->scx.dsq_node.priq)); if (!is_local) { @@ -1413,25 +1555,52 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, } if (enq_flags & SCX_ENQ_DSQ_PRIQ) { - p->scx.dsq_flags |= SCX_TASK_DSQ_ON_PRIQ; - rb_add_cached(&p->scx.dsq_node.priq, &dsq->priq, - scx_dsq_priq_less); - /* A DSQ should only be using either FIFO or PRIQ enqueuing. */ - if (unlikely(!list_empty(&dsq->fifo))) + struct rb_node *rbp; + + /* + * A PRIQ DSQ shouldn't be using FIFO enqueueing. As tasks are + * linked to both the rbtree and list on PRIQs, this can only be + * tested easily when adding the first task. + */ + if (unlikely(RB_EMPTY_ROOT(&dsq->priq) && + nldsq_next_task(dsq, NULL, false))) scx_ops_error("DSQ ID 0x%016llx already had FIFO-enqueued tasks", dsq->id); + + p->scx.dsq_node.flags |= SCX_TASK_DSQ_ON_PRIQ; + rb_add(&p->scx.dsq_node.priq, &dsq->priq, scx_dsq_priq_less); + + /* + * Find the previous task and insert after it on the list so + * that @dsq->list is vtime ordered. + */ + rbp = rb_prev(&p->scx.dsq_node.priq); + if (rbp) { + struct task_struct *prev = + container_of(rbp, struct task_struct, + scx.dsq_node.priq); + list_add(&p->scx.dsq_node.list, &prev->scx.dsq_node.list); + } else { + list_add(&p->scx.dsq_node.list, &dsq->list); + } } else { - if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT)) - list_add(&p->scx.dsq_node.fifo, &dsq->fifo); - else - list_add_tail(&p->scx.dsq_node.fifo, &dsq->fifo); - /* A DSQ should only be using either FIFO or PRIQ enqueuing. */ - if (unlikely(rb_first_cached(&dsq->priq))) + /* a FIFO DSQ shouldn't be using PRIQ enqueuing */ + if (unlikely(!RB_EMPTY_ROOT(&dsq->priq))) scx_ops_error("DSQ ID 0x%016llx already had PRIQ-enqueued tasks", dsq->id); + + if (enq_flags & (SCX_ENQ_HEAD | SCX_ENQ_PREEMPT)) + list_add(&p->scx.dsq_node.list, &dsq->list); + else + list_add_tail(&p->scx.dsq_node.list, &dsq->list); } - dsq->nr++; - p->scx.dsq = dsq; + + /* seq records the order tasks are queued, used by BPF DSQ iterator */ + dsq->seq++; + p->scx.dsq_seq = dsq->seq; + + dsq_mod_nr(dsq, 1); + WRITE_ONCE(p->scx.dsq, dsq); /* * scx.ddsp_dsq_id and scx.ddsp_enq_flags are only relevant on the @@ -1470,19 +1639,18 @@ static void dispatch_enqueue(struct scx_dispatch_q *dsq, struct task_struct *p, static void task_unlink_from_dsq(struct task_struct *p, struct scx_dispatch_q *dsq) { - if (p->scx.dsq_flags & SCX_TASK_DSQ_ON_PRIQ) { - rb_erase_cached(&p->scx.dsq_node.priq, &dsq->priq); + if (p->scx.dsq_node.flags & SCX_TASK_DSQ_ON_PRIQ) { + rb_erase(&p->scx.dsq_node.priq, &dsq->priq); RB_CLEAR_NODE(&p->scx.dsq_node.priq); - p->scx.dsq_flags &= ~SCX_TASK_DSQ_ON_PRIQ; - } else { - list_del_init(&p->scx.dsq_node.fifo); + p->scx.dsq_node.flags &= ~SCX_TASK_DSQ_ON_PRIQ; } + + list_del_init(&p->scx.dsq_node.list); } static bool task_linked_on_dsq(struct task_struct *p) { - return !list_empty(&p->scx.dsq_node.fifo) || - !RB_EMPTY_NODE(&p->scx.dsq_node.priq); + return !list_empty(&p->scx.dsq_node.list); } static void dispatch_dequeue(struct scx_rq *scx_rq, struct task_struct *p) @@ -1514,7 +1682,7 @@ static void dispatch_dequeue(struct scx_rq *scx_rq, struct task_struct *p) /* @p must still be on @dsq, dequeue */ WARN_ON_ONCE(!task_linked_on_dsq(p)); task_unlink_from_dsq(p, dsq); - dsq->nr--; + dsq_mod_nr(dsq, -1); } else { /* * We're racing against dispatch_to_local_dsq() which already @@ -1525,12 +1693,17 @@ static void dispatch_dequeue(struct scx_rq *scx_rq, struct task_struct *p) WARN_ON_ONCE(task_linked_on_dsq(p)); p->scx.holding_cpu = -1; } - p->scx.dsq = NULL; + WRITE_ONCE(p->scx.dsq, NULL); if (!is_local) raw_spin_unlock(&dsq->lock); } +static struct scx_dispatch_q *find_user_dsq(u64 dsq_id) +{ + return rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params); +} + static struct scx_dispatch_q *find_non_local_dsq(u64 dsq_id) { lockdep_assert(rcu_read_lock_any_held()); @@ -1538,8 +1711,7 @@ static struct scx_dispatch_q *find_non_local_dsq(u64 dsq_id) if (dsq_id == SCX_DSQ_GLOBAL) return &scx_dsq_global; else - return rhashtable_lookup_fast(&dsq_hash, &dsq_id, - dsq_hash_params); + return find_user_dsq(dsq_id); } static struct scx_dispatch_q *find_dsq_for_dispatch(struct rq *rq, u64 dsq_id, @@ -1614,11 +1786,7 @@ static void direct_dispatch(struct task_struct *p, u64 enq_flags) static bool test_rq_online(struct rq *rq) { -#ifdef CONFIG_SMP - return rq->online; -#else - return true; -#endif + return per_cpu(scx_cpu_online, cpu_of(rq)); } static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, @@ -2012,61 +2180,51 @@ static void dispatch_to_local_dsq_unlock(struct rq *rq, struct rq_flags *rf, } #endif /* CONFIG_SMP */ - -static bool task_can_run_on_rq(struct task_struct *p, struct rq *rq) -{ - return likely(test_rq_online(rq)) && !is_migration_disabled(p) && - cpumask_test_cpu(cpu_of(rq), p->cpus_ptr); -} - -static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf, - struct scx_dispatch_q *dsq) +static void consume_local_task(struct rq *rq, struct scx_dispatch_q *dsq, + struct task_struct *p) { struct scx_rq *scx_rq = &rq->scx; - struct task_struct *p; - struct rb_node *rb_node; - struct rq *task_rq; - bool moved = false; -retry: - if (list_empty(&dsq->fifo) && !rb_first_cached(&dsq->priq)) - return false; - - raw_spin_lock(&dsq->lock); - - list_for_each_entry(p, &dsq->fifo, scx.dsq_node.fifo) { - task_rq = task_rq(p); - if (rq == task_rq) - goto this_rq; - if (task_can_run_on_rq(p, rq)) - goto remote_rq; - } - - for (rb_node = rb_first_cached(&dsq->priq); rb_node; - rb_node = rb_next(rb_node)) { - p = container_of(rb_node, struct task_struct, scx.dsq_node.priq); - task_rq = task_rq(p); - if (rq == task_rq) - goto this_rq; - if (task_can_run_on_rq(p, rq)) - goto remote_rq; - } - raw_spin_unlock(&dsq->lock); - return false; + lockdep_assert_held(&dsq->lock); /* released on return */ -this_rq: /* @dsq is locked and @p is on this rq */ WARN_ON_ONCE(p->scx.holding_cpu >= 0); task_unlink_from_dsq(p, dsq); - list_add_tail(&p->scx.dsq_node.fifo, &scx_rq->local_dsq.fifo); - dsq->nr--; - scx_rq->local_dsq.nr++; - p->scx.dsq = &scx_rq->local_dsq; + list_add_tail(&p->scx.dsq_node.list, &scx_rq->local_dsq.list); + dsq_mod_nr(dsq, -1); + dsq_mod_nr(&scx_rq->local_dsq, 1); + WRITE_ONCE(p->scx.dsq, &scx_rq->local_dsq); raw_spin_unlock(&dsq->lock); - return true; +} -remote_rq: #ifdef CONFIG_SMP +/* + * Similar to kernel/sched/core.c::is_cpu_allowed() but we're testing whether @p + * can be pulled to @rq. + */ +static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq) +{ + int cpu = cpu_of(rq); + + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + if (unlikely(is_migration_disabled(p))) + return false; + if (!(p->flags & PF_KTHREAD) && unlikely(!task_cpu_possible(cpu, p))) + return false; + if (unlikely(!test_rq_online(rq))) + return false; + return true; +} + +static bool consume_remote_task(struct rq *rq, struct rq_flags *rf, + struct scx_dispatch_q *dsq, + struct task_struct *p, struct rq *task_rq) +{ + bool moved = false; + + lockdep_assert_held(&dsq->lock); /* released on return */ + /* * @dsq is locked and @p is on a remote rq. @p is currently protected by * @dsq->lock. We want to pull @p to @rq but may deadlock if we grab @@ -2076,7 +2234,7 @@ static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf, */ WARN_ON_ONCE(p->scx.holding_cpu >= 0); task_unlink_from_dsq(p, dsq); - dsq->nr--; + dsq_mod_nr(dsq, -1); p->scx.holding_cpu = raw_smp_processor_id(); raw_spin_unlock(&dsq->lock); @@ -2087,10 +2245,43 @@ static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf, moved = move_task_to_local_dsq(rq, p, 0); double_unlock_balance(rq, task_rq); -#endif /* CONFIG_SMP */ - if (likely(moved)) - return true; - goto retry; + + return moved; +} +#else /* CONFIG_SMP */ +static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq) { return false; } +static bool consume_remote_task(struct rq *rq, struct rq_flags *rf, + struct scx_dispatch_q *dsq, + struct task_struct *p, struct rq *task_rq) { return false; } +#endif /* CONFIG_SMP */ + +static bool consume_dispatch_q(struct rq *rq, struct rq_flags *rf, + struct scx_dispatch_q *dsq) +{ + struct task_struct *p; +retry: + if (list_empty(&dsq->list)) + return false; + + raw_spin_lock(&dsq->lock); + + nldsq_for_each_task(p, dsq) { + struct rq *task_rq = task_rq(p); + + if (rq == task_rq) { + consume_local_task(rq, dsq, p); + return true; + } + + if (task_can_run_on_remote_rq(p, rq)) { + if (likely(consume_remote_task(rq, rf, dsq, p, task_rq))) + return true; + goto retry; + } + } + + raw_spin_unlock(&dsq->lock); + return false; } enum dispatch_to_local_dsq_ret { @@ -2204,7 +2395,7 @@ dispatch_to_local_dsq(struct rq *rq, struct rq_flags *rf, u64 dsq_id, return dsp ? DTL_DISPATCHED : DTL_LOST; } -#endif /* CONFIG_SMP */ +#endif /* CONFIG_SMP */ scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]", cpu_of(dst_rq), p->comm, p->pid); @@ -2377,7 +2568,8 @@ static int balance_one(struct rq *rq, struct task_struct *prev, if (consume_dispatch_q(rq, rf, &scx_dsq_global)) goto has_tasks; - if (!SCX_HAS_OP(dispatch) || scx_ops_bypassing()) + if (!SCX_HAS_OP(dispatch) || scx_ops_bypassing() || + unlikely(!test_rq_online(rq))) goto out; dspc->rq = rq; @@ -2584,7 +2776,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p) * can find the task unless it wants to trigger a separate * follow-up scheduling event. */ - if (list_empty(&rq->scx.local_dsq.fifo)) + if (list_empty(&rq->scx.local_dsq.list)) do_enqueue_task(rq, p, SCX_ENQ_LAST, -1); else do_enqueue_task(rq, p, 0, -1); @@ -2593,9 +2785,8 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p) static struct task_struct *first_local_task(struct rq *rq) { - WARN_ON_ONCE(rb_first_cached(&rq->scx.local_dsq.priq)); - return list_first_entry_or_null(&rq->scx.local_dsq.fifo, - struct task_struct, scx.dsq_node.fifo); + return list_first_entry_or_null(&rq->scx.local_dsq.list, + struct task_struct, scx.dsq_node.list); } static struct task_struct *pick_next_task_scx(struct rq *rq) @@ -2612,6 +2803,8 @@ static struct task_struct *pick_next_task_scx(struct rq *rq) if (!p) return NULL; + set_next_task_scx(rq, p, true); + if (unlikely(!p->scx.slice)) { if (!scx_ops_bypassing() && !scx_warned_zero_slice) { printk_deferred(KERN_WARNING "sched_ext: %s[%d] has zero slice in pick_next_task_scx()\n", @@ -2621,8 +2814,6 @@ static struct task_struct *pick_next_task_scx(struct rq *rq) p->scx.slice = SCX_SLICE_DFL; } - set_next_task_scx(rq, p, true); - return p; } @@ -3019,21 +3210,23 @@ static void rq_online_scx(struct rq *rq, enum rq_onoff_reason reason) { if (reason == RQ_ONOFF_HOTPLUG) handle_hotplug(rq, true); + per_cpu(scx_cpu_online, cpu_of(rq)) = true; } static void rq_offline_scx(struct rq *rq, enum rq_onoff_reason reason) { + per_cpu(scx_cpu_online, cpu_of(rq)) = false; if (reason == RQ_ONOFF_HOTPLUG) handle_hotplug(rq, false); } -#else /* !CONFIG_SMP */ +#else /* CONFIG_SMP */ static bool test_and_clear_cpu_idle(int cpu) { return false; } static s32 scx_pick_idle_cpu(const struct cpumask *cpus_allowed, u64 flags) { return -EBUSY; } static void reset_idle_masks(void) {} -#endif /* CONFIG_SMP */ +#endif /* CONFIG_SMP */ static bool check_rq_for_timeouts(struct rq *rq) { @@ -3284,6 +3477,24 @@ static void scx_ops_exit_task(struct task_struct *p) scx_set_task_state(p, SCX_TASK_NONE); } +void init_scx_entity(struct sched_ext_entity *scx) +{ + /* + * init_idle() calls this function again after fork sequence is + * complete. Don't touch ->tasks_node as it's already linked. + */ + memset(scx, 0, offsetof(struct sched_ext_entity, tasks_node)); + + INIT_LIST_HEAD(&scx->dsq_node.list); + RB_CLEAR_NODE(&scx->dsq_node.priq); + scx->sticky_cpu = -1; + scx->holding_cpu = -1; + INIT_LIST_HEAD(&scx->runnable_node); + scx->runnable_at = jiffies; + scx->ddsp_dsq_id = SCX_DSQ_INVALID; + scx->slice = SCX_SLICE_DFL; +} + void scx_pre_fork(struct task_struct *p) { /* @@ -3669,7 +3880,7 @@ static void init_dsq(struct scx_dispatch_q *dsq, u64 dsq_id) memset(dsq, 0, sizeof(*dsq)); raw_spin_lock_init(&dsq->lock); - INIT_LIST_HEAD(&dsq->fifo); + INIT_LIST_HEAD(&dsq->list); dsq->id = dsq_id; } @@ -3714,7 +3925,7 @@ static void destroy_dsq(u64 dsq_id) rcu_read_lock(); - dsq = rhashtable_lookup_fast(&dsq_hash, &dsq_id, dsq_hash_params); + dsq = find_user_dsq(dsq_id); if (!dsq) goto out_unlock_rcu; @@ -4012,9 +4223,13 @@ static void scx_ops_bypass(bool bypass) return; } - mutex_lock(&scx_ops_enable_mutex); + /* + * We need to guarantee that no tasks are on the BPF scheduler while + * bypassing. Either we see enabled or the enable path sees the + * increased bypass_depth before moving tasks to SCX. + */ if (!scx_enabled()) - goto out_unlock; + return; /* * No task property is changing. We just need to make sure all currently @@ -4053,9 +4268,6 @@ static void scx_ops_bypass(bool bypass) /* kick to restore ticks */ resched_cpu(cpu); } - -out_unlock: - mutex_unlock(&scx_ops_enable_mutex); } static void free_exit_info(struct scx_exit_info *ei) @@ -4285,8 +4497,29 @@ static void scx_ops_disable(enum scx_exit_kind kind) schedule_scx_ops_disable_work(); } -static void scx_dump_task(struct seq_buf *s, struct task_struct *p, char marker, - unsigned long now) +static void ops_dump_init(struct seq_buf *s, const char *prefix) +{ + lockdep_assert_irqs_disabled(); + + scx_dump_cpu = smp_processor_id(); /* allow scx_bpf_dump() */ + scx_dump_last = '\0'; /* nothing printed yet */ + scx_dump_seq_buf = s; + scx_dump_prefix = prefix; +} + +static void ops_dump_exit(void) +{ + /* + * If something was printed but the last line wasn't terminated, add a + * new line. + */ + if (scx_dump_last != '\0' && scx_dump_last != '\n') + seq_buf_putc(scx_dump_seq_buf, '\n'); + scx_dump_cpu = -1; +} + +static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, + struct task_struct *p, char marker) { static unsigned long bt[SCX_EXIT_BT_LEN]; char dsq_id_buf[19] = "(n/a)"; @@ -4301,28 +4534,42 @@ static void scx_dump_task(struct seq_buf *s, struct task_struct *p, char marker, seq_buf_printf(s, "\n %c%c %s[%d] %+ldms\n", marker, task_state_to_char(p), p->comm, p->pid, - jiffies_delta_msecs(p->scx.runnable_at, now)); + jiffies_delta_msecs(p->scx.runnable_at, dctx->at_jiffies)); seq_buf_printf(s, " scx_state/flags=%u/0x%x dsq_flags=0x%x ops_state/qseq=%lu/%lu\n", scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK, - p->scx.dsq_flags, + p->scx.dsq_node.flags, ops_state & SCX_OPSS_STATE_MASK, ops_state >> SCX_OPSS_QSEQ_SHIFT); seq_buf_printf(s, " sticky/holding_cpu=%d/%d dsq_id=%s\n", p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf); - seq_buf_printf(s, " cpus=%*pb\n\n", cpumask_pr_args(p->cpus_ptr)); + seq_buf_printf(s, " cpus=%*pb\n", cpumask_pr_args(p->cpus_ptr)); - bt_len = stack_trace_save_tsk(p, bt, SCX_EXIT_BT_LEN, 1); + if (SCX_HAS_OP(dump_task)) { + ops_dump_init(s, " "); + SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p); + ops_dump_exit(); + } - avail = seq_buf_get_buf(s, &buf); - used = stack_trace_snprint(buf, avail, bt, bt_len, 3); - seq_buf_commit(s, used < avail ? used : -1); + bt_len = stack_trace_save_tsk(p, bt, SCX_EXIT_BT_LEN, 1); + if (bt_len) { + seq_buf_putc(s, '\n'); + avail = seq_buf_get_buf(s, &buf); + used = stack_trace_snprint(buf, avail, bt, bt_len, 3); + seq_buf_commit(s, used < avail ? used : -1); + } } static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) { - const char trunc_marker[] = "\n\n~~~~ TRUNCATED ~~~~\n"; - unsigned long now = jiffies; + static const char trunc_marker[] = "\n\n~~~~ TRUNCATED ~~~~\n"; + struct scx_dump_ctx dctx = { + .kind = ei->kind, + .exit_code = ei->exit_code, + .reason = ei->reason, + .at_ns = ktime_get_ns(), + .at_jiffies = jiffies, + }; struct seq_buf s; size_t avail, used; char *buf; @@ -4340,45 +4587,82 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) used = stack_trace_snprint(buf, avail, ei->bt, ei->bt_len, 1); seq_buf_commit(&s, used < avail ? used : -1); - seq_buf_printf(&s, "\nRunqueue states\n"); - seq_buf_printf(&s, "---------------\n"); + if (SCX_HAS_OP(dump)) { + ops_dump_init(&s, ""); + SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx); + ops_dump_exit(); + } + + seq_buf_printf(&s, "\nCPU states\n"); + seq_buf_printf(&s, "----------\n"); for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); struct rq_flags rf; struct task_struct *p; + struct seq_buf ns; + bool idle; rq_lock(rq, &rf); - if (list_empty(&rq->scx.runnable_list) && - rq->curr->sched_class == &idle_sched_class) + idle = list_empty(&rq->scx.runnable_list) && + rq->curr->sched_class == &idle_sched_class; + + if (idle && !SCX_HAS_OP(dump_cpu)) goto next; - seq_buf_printf(&s, "\nCPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ops_qseq=%lu pnt_seq=%lu\n", + /* + * We don't yet know whether ops.dump_cpu() will produce output + * and we may want to skip the default CPU dump if it doesn't. + * Use a nested seq_buf to generate the standard dump so that we + * can decide whether to commit later. + */ + avail = seq_buf_get_buf(&s, &buf); + seq_buf_init(&ns, buf, avail); + + seq_buf_printf(&ns, "\nCPU %-4d: nr_run=%u flags=0x%x cpu_rel=%d ops_qseq=%lu pnt_seq=%lu\n", cpu, rq->scx.nr_running, rq->scx.flags, rq->scx.cpu_released, rq->scx.ops_qseq, rq->scx.pnt_seq); - seq_buf_printf(&s, " curr=%s[%d] class=%ps\n", + seq_buf_printf(&ns, " curr=%s[%d] class=%ps\n", rq->curr->comm, rq->curr->pid, rq->curr->sched_class); if (!cpumask_empty(rq->scx.cpus_to_kick)) - seq_buf_printf(&s, " cpus_to_kick : %*pb\n", + seq_buf_printf(&ns, " cpus_to_kick : %*pb\n", cpumask_pr_args(rq->scx.cpus_to_kick)); if (!cpumask_empty(rq->scx.cpus_to_kick_if_idle)) - seq_buf_printf(&s, " idle_to_kick : %*pb\n", + seq_buf_printf(&ns, " idle_to_kick : %*pb\n", cpumask_pr_args(rq->scx.cpus_to_kick_if_idle)); if (!cpumask_empty(rq->scx.cpus_to_preempt)) - seq_buf_printf(&s, " cpus_to_preempt: %*pb\n", + seq_buf_printf(&ns, " cpus_to_preempt: %*pb\n", cpumask_pr_args(rq->scx.cpus_to_preempt)); if (!cpumask_empty(rq->scx.cpus_to_wait)) - seq_buf_printf(&s, " cpus_to_wait : %*pb\n", + seq_buf_printf(&ns, " cpus_to_wait : %*pb\n", cpumask_pr_args(rq->scx.cpus_to_wait)); + used = seq_buf_used(&ns); + if (SCX_HAS_OP(dump_cpu)) { + ops_dump_init(&ns, " "); + SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle); + ops_dump_exit(); + } + + /* + * If idle && nothing generated by ops.dump_cpu(), there's + * nothing interesting. Skip. + */ + if (idle && used == seq_buf_used(&ns)) + goto next; + + seq_buf_commit(&s, seq_buf_used(&ns)); + if (seq_buf_has_overflowed(&ns)) + seq_buf_set_overflow(&s); + if (rq->curr->sched_class == &ext_sched_class) - scx_dump_task(&s, rq->curr, '*', now); + scx_dump_task(&s, &dctx, rq->curr, '*'); list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) - scx_dump_task(&s, p, ' ', now); + scx_dump_task(&s, &dctx, p, ' '); next: rq_unlock(rq, &rf); } @@ -4390,7 +4674,11 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) static void scx_ops_error_irq_workfn(struct irq_work *irq_work) { - scx_dump_state(scx_exit_info, scx_ops.exit_dump_len); + struct scx_exit_info *ei = scx_exit_info; + + if (ei->kind >= SCX_EXIT_ERROR) + scx_dump_state(ei, scx_ops.exit_dump_len); + schedule_scx_ops_disable_work(); } @@ -4407,6 +4695,8 @@ static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind, if (!atomic_try_cmpxchg(&scx_exit_kind, &none, kind)) return; + ei->exit_code = exit_code; + if (kind >= SCX_EXIT_ERROR) ei->bt_len = stack_trace_save(ei->bt, SCX_EXIT_BT_LEN, 1); @@ -4414,8 +4704,6 @@ static __printf(3, 4) void scx_ops_exit_kind(enum scx_exit_kind kind, vscnprintf(ei->msg, SCX_EXIT_MSG_LEN, fmt, args); va_end(args); - ei->exit_code = exit_code; - /* * Set ei->kind and ->reason for scx_dump_state(). They'll be set again * in scx_ops_disable_workfn(). @@ -5354,6 +5642,48 @@ static const struct btf_kfunc_id_set scx_kfunc_set_sleepable = { .set = &scx_kfunc_ids_sleepable, }; +__bpf_kfunc_start_defs(); + +/** + * scx_bpf_select_cpu_dfl - The default implementation of ops.select_cpu() + * @p: task_struct to select a CPU for + * @prev_cpu: CPU @p was on previously + * @wake_flags: %SCX_WAKE_* flags + * @is_idle: out parameter indicating whether the returned CPU is idle + * + * Can only be called from ops.select_cpu() if the built-in CPU selection is + * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set. + * @p, @prev_cpu and @wake_flags match ops.select_cpu(). + * + * Returns the picked CPU with *@is_idle indicating whether the picked CPU is + * currently idle and thus a good candidate for direct dispatching. + */ +__bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, + u64 wake_flags, bool *is_idle) +{ + if (!scx_kf_allowed(SCX_KF_SELECT_CPU)) { + *is_idle = false; + return prev_cpu; + } +#ifdef CONFIG_SMP + return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle); +#else + *is_idle = false; + return prev_cpu; +#endif +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_select_cpu) +BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU) +BTF_KFUNCS_END(scx_kfunc_ids_select_cpu) + +static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = { + .owner = THIS_MODULE, + .set = &scx_kfunc_ids_select_cpu, +}; + static bool scx_dispatch_preamble(struct task_struct *p, u64 enq_flags) { if (!scx_kf_allowed(SCX_KF_ENQUEUE | SCX_KF_DISPATCH)) @@ -5576,12 +5906,88 @@ __bpf_kfunc bool scx_bpf_consume(u64 dsq_id) } } -__bpf_kfunc_end_defs(); - -BTF_KFUNCS_START(scx_kfunc_ids_dispatch) -BTF_ID_FLAGS(func, scx_bpf_dispatch_nr_slots) -BTF_ID_FLAGS(func, scx_bpf_dispatch_cancel) -BTF_ID_FLAGS(func, scx_bpf_consume) +/** + * __scx_bpf_consume_task - Transfer a task from DSQ iteration to the local DSQ + * @it: DSQ iterator in progress + * @p: task to consume + * + * Transfer @p which is on the DSQ currently iterated by @it to the current + * CPU's local DSQ. For the transfer to be successful, @p must still be on the + * DSQ and have been queued before the DSQ iteration started. This function + * doesn't care whether @p was obtained from the DSQ iteration. @p just has to + * be on the DSQ and have been queued before the iteration started. + * + * Returns %true if @p has been consumed, %false if @p had already been consumed + * or dequeued. + */ +__bpf_kfunc bool __scx_bpf_consume_task(unsigned long it, struct task_struct *p) +{ + struct bpf_iter_scx_dsq_kern *kit = (void *)it; + struct scx_dispatch_q *dsq, *kit_dsq; + struct scx_dsp_ctx *dspc = this_cpu_ptr(&scx_dsp_ctx); + struct rq *task_rq; + u64 kit_dsq_seq; + + /* can't trust @kit, carefully fetch the values we need */ + if (get_kernel_nofault(kit_dsq, &kit->dsq) || + get_kernel_nofault(kit_dsq_seq, &kit->dsq_seq)) { + scx_ops_error("invalid @it 0x%lx", it); + return false; + } + + /* + * @kit can't be trusted and we can only get the DSQ from @p. As we + * don't know @p's rq is locked, use READ_ONCE() to access the field. + * Derefing is safe as DSQs are RCU protected. + */ + dsq = READ_ONCE(p->scx.dsq); + + if (unlikely(dsq->id == SCX_DSQ_LOCAL)) { + scx_ops_error("local DSQ not allowed"); + return false; + } + + if (unlikely(!dsq || dsq != kit_dsq)) + return false; + + if (!scx_kf_allowed(SCX_KF_DISPATCH)) + return false; + + flush_dispatch_buf(dspc->rq, dspc->rf); + + raw_spin_lock(&dsq->lock); + + /* + * Did someone else get to it? @p could have already left $dsq, got + * re-enqueud, or be in the process of being consumed by someone else. + */ + if (unlikely(p->scx.dsq != dsq || + time_after64(p->scx.dsq_seq, kit_dsq_seq) || + p->scx.holding_cpu >= 0)) + goto out_unlock; + + task_rq = task_rq(p); + + if (dspc->rq == task_rq) { + consume_local_task(dspc->rq, dsq, p); + return true; + } + + if (task_can_run_on_remote_rq(p, dspc->rq)) + return consume_remote_task(dspc->rq, dspc->rf, dsq, p, task_rq); + +out_unlock: + raw_spin_unlock(&dsq->lock); + return false; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(scx_kfunc_ids_dispatch) +BTF_ID_FLAGS(func, scx_bpf_dispatch_nr_slots) +BTF_ID_FLAGS(func, scx_bpf_dispatch_cancel) +BTF_ID_FLAGS(func, scx_bpf_consume) +BTF_ID_FLAGS(func, __scx_bpf_consume_task) BTF_KFUNCS_END(scx_kfunc_ids_dispatch) static const struct btf_kfunc_id_set scx_kfunc_set_dispatch = { @@ -5714,224 +6120,205 @@ __bpf_kfunc void scx_bpf_kick_cpu(s32 cpu, u64 flags) * @dsq_id: id of the DSQ * * Return the number of tasks in the DSQ matching @dsq_id. If not found, - * -%ENOENT is returned. Can be called from any non-sleepable online scx_ops - * operations. + * -%ENOENT is returned. */ __bpf_kfunc s32 scx_bpf_dsq_nr_queued(u64 dsq_id) { struct scx_dispatch_q *dsq; + s32 ret; - lockdep_assert(rcu_read_lock_any_held()); + preempt_disable(); if (dsq_id == SCX_DSQ_LOCAL) { - return this_rq()->scx.local_dsq.nr; + ret = READ_ONCE(this_rq()->scx.local_dsq.nr); + goto out; } else if ((dsq_id & SCX_DSQ_LOCAL_ON) == SCX_DSQ_LOCAL_ON) { s32 cpu = dsq_id & SCX_DSQ_LOCAL_CPU_MASK; - if (ops_cpu_valid(cpu, NULL)) - return cpu_rq(cpu)->scx.local_dsq.nr; + if (ops_cpu_valid(cpu, NULL)) { + ret = READ_ONCE(cpu_rq(cpu)->scx.local_dsq.nr); + goto out; + } } else { dsq = find_non_local_dsq(dsq_id); - if (dsq) - return dsq->nr; + if (dsq) { + ret = READ_ONCE(dsq->nr); + goto out; + } } - return -ENOENT; + ret = -ENOENT; +out: + preempt_enable(); + return ret; } /** - * scx_bpf_test_and_clear_cpu_idle - Test and clear @cpu's idle state - * @cpu: cpu to test and clear idle for - * - * Returns %true if @cpu was idle and its idle state was successfully cleared. - * %false otherwise. + * scx_bpf_destroy_dsq - Destroy a custom DSQ + * @dsq_id: DSQ to destroy * - * Unavailable if ops.update_idle() is implemented and - * %SCX_OPS_KEEP_BUILTIN_IDLE is not set. + * Destroy the custom DSQ identified by @dsq_id. Only DSQs created with + * scx_bpf_create_dsq() can be destroyed. The caller must ensure that the DSQ is + * empty and no further tasks are dispatched to it. Ignored if called on a DSQ + * which doesn't exist. Can be called from any online scx_ops operations. */ -__bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) +__bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id) { - if (!static_branch_likely(&scx_builtin_idle_enabled)) { - scx_ops_error("built-in idle tracking is disabled"); - return false; - } - - if (ops_cpu_valid(cpu, NULL)) - return test_and_clear_cpu_idle(cpu); - else - return false; + destroy_dsq(dsq_id); } /** - * scx_bpf_pick_idle_cpu - Pick and claim an idle cpu - * @cpus_allowed: Allowed cpumask - * @flags: %SCX_PICK_IDLE_CPU_* flags + * bpf_iter_scx_dsq_new - Create a DSQ iterator + * @it: iterator to initialize + * @dsq_id: DSQ to iterate + * @flags: %SCX_DSQ_ITER_* * - * Pick and claim an idle cpu in @cpus_allowed. Returns the picked idle cpu - * number on success. -%EBUSY if no matching cpu was found. - * - * Idle CPU tracking may race against CPU scheduling state transitions. For - * example, this function may return -%EBUSY as CPUs are transitioning into the - * idle state. If the caller then assumes that there will be dispatch events on - * the CPUs as they were all busy, the scheduler may end up stalling with CPUs - * idling while there are pending tasks. Use scx_bpf_pick_any_cpu() and - * scx_bpf_kick_cpu() to guarantee that there will be at least one dispatch - * event in the near future. - * - * Unavailable if ops.update_idle() is implemented and - * %SCX_OPS_KEEP_BUILTIN_IDLE is not set. + * Initialize BPF iterator @it which can be used with bpf_for_each() to walk + * tasks in the DSQ specified by @dsq_id. Iteration using @it only includes + * tasks which are already queued when this function is invoked. */ -__bpf_kfunc s32 scx_bpf_pick_idle_cpu(const struct cpumask *cpus_allowed, - u64 flags) +__bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, + u64 flags) { - if (!static_branch_likely(&scx_builtin_idle_enabled)) { - scx_ops_error("built-in idle tracking is disabled"); - return -EBUSY; - } + struct bpf_iter_scx_dsq_kern *kit = (void *)it; - return scx_pick_idle_cpu(cpus_allowed, flags); + BUILD_BUG_ON(sizeof(struct bpf_iter_scx_dsq_kern) > + sizeof(struct bpf_iter_scx_dsq)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) != + __alignof__(struct bpf_iter_scx_dsq)); + + if (flags & ~__SCX_DSQ_ITER_ALL_FLAGS) + return -EINVAL; + + kit->dsq = find_non_local_dsq(dsq_id); + if (!kit->dsq) + return -ENOENT; + + INIT_LIST_HEAD(&kit->cursor.list); + RB_CLEAR_NODE(&kit->cursor.priq); + kit->cursor.flags = SCX_TASK_DSQ_CURSOR; + kit->self = kit; + kit->dsq_seq = READ_ONCE(kit->dsq->seq); + kit->flags = flags; + + return 0; } /** - * scx_bpf_pick_any_cpu - Pick and claim an idle cpu if available or pick any CPU - * @cpus_allowed: Allowed cpumask - * @flags: %SCX_PICK_IDLE_CPU_* flags + * bpf_iter_scx_dsq_next - Progress a DSQ iterator + * @it: iterator to progress * - * Pick and claim an idle cpu in @cpus_allowed. If none is available, pick any - * CPU in @cpus_allowed. Guaranteed to succeed and returns the picked idle cpu - * number if @cpus_allowed is not empty. -%EBUSY is returned if @cpus_allowed is - * empty. - * - * If ops.update_idle() is implemented and %SCX_OPS_KEEP_BUILTIN_IDLE is not - * set, this function can't tell which CPUs are idle and will always pick any - * CPU. + * Return the next task. See bpf_iter_scx_dsq_new(). */ -__bpf_kfunc s32 scx_bpf_pick_any_cpu(const struct cpumask *cpus_allowed, - u64 flags) +__bpf_kfunc struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) { - s32 cpu; + struct bpf_iter_scx_dsq_kern *kit = (void *)it; + bool rev = kit->flags & SCX_DSQ_ITER_REV; + struct task_struct *p; + unsigned long flags; - if (static_branch_likely(&scx_builtin_idle_enabled)) { - cpu = scx_pick_idle_cpu(cpus_allowed, flags); - if (cpu >= 0) - return cpu; - } + if (!kit->dsq) + return NULL; - cpu = cpumask_any_distribute(cpus_allowed); - if (cpu < nr_cpu_ids) - return cpu; + raw_spin_lock_irqsave(&kit->dsq->lock, flags); + + if (list_empty(&kit->cursor.list)) + p = NULL; else - return -EBUSY; -} + p = container_of(&kit->cursor, struct task_struct, scx.dsq_node); -/** - * scx_bpf_destroy_dsq - Destroy a custom DSQ - * @dsq_id: DSQ to destroy - * - * Destroy the custom DSQ identified by @dsq_id. Only DSQs created with - * scx_bpf_create_dsq() can be destroyed. The caller must ensure that the DSQ is - * empty and no further tasks are dispatched to it. Ignored if called on a DSQ - * which doesn't exist. Can be called from any online scx_ops operations. - */ -__bpf_kfunc void scx_bpf_destroy_dsq(u64 dsq_id) -{ - destroy_dsq(dsq_id); + /* + * Only tasks which were queued before the iteration started are + * visible. This bounds BPF iterations and guarantees that vtime never + * jumps in the other direction while iterating. + */ + do { + p = nldsq_next_task(kit->dsq, p, rev); + } while (p && unlikely(time_after64(p->scx.dsq_seq, kit->dsq_seq))); + + if (p) { + if (rev) + list_move_tail(&kit->cursor.list, &p->scx.dsq_node.list); + else + list_move(&kit->cursor.list, &p->scx.dsq_node.list); + } else { + list_del_init(&kit->cursor.list); + } + + raw_spin_unlock_irqrestore(&kit->dsq->lock, flags); + + return p; } /** - * scx_bpf_select_cpu_dfl - The default implementation of ops.select_cpu() - * @p: task_struct to select a CPU for - * @prev_cpu: CPU @p was on previously - * @wake_flags: %SCX_WAKE_* flags - * @is_idle: out parameter indicating whether the returned CPU is idle - * - * Can only be called from ops.select_cpu() if the built-in CPU selection is - * enabled - ops.update_idle() is missing or %SCX_OPS_KEEP_BUILTIN_IDLE is set. - * @p, @prev_cpu and @wake_flags match ops.select_cpu(). + * bpf_iter_scx_dsq_destroy - Destroy a DSQ iterator + * @it: iterator to destroy * - * Returns the picked CPU with *@is_idle indicating whether the picked CPU is - * currently idle and thus a good candidate for direct dispatching. + * Undo scx_iter_scx_dsq_new(). */ -__bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, - u64 wake_flags, bool *is_idle) +__bpf_kfunc void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) { - if (!scx_kf_allowed(SCX_KF_SELECT_CPU)) { - *is_idle = false; - return prev_cpu; - } + struct bpf_iter_scx_dsq_kern *kit = (void *)it; - return scx_select_cpu_dfl(p, prev_cpu, wake_flags, is_idle); -} + if (!kit->dsq) + return; -__bpf_kfunc_end_defs(); + if (!list_empty(&kit->cursor.list)) { + unsigned long flags; -BTF_KFUNCS_START(scx_kfunc_ids_ops_only) -BTF_ID_FLAGS(func, scx_bpf_kick_cpu) -BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued) -BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle) -BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU) -BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU) -BTF_ID_FLAGS(func, scx_bpf_destroy_dsq) -BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU) -BTF_KFUNCS_END(scx_kfunc_ids_ops_only) + raw_spin_lock_irqsave(&kit->dsq->lock, flags); + list_del_init(&kit->cursor.list); + raw_spin_unlock_irqrestore(&kit->dsq->lock, flags); + } + kit->dsq = NULL; +} -static const struct btf_kfunc_id_set scx_kfunc_set_ops_only = { - .owner = THIS_MODULE, - .set = &scx_kfunc_ids_ops_only, -}; +__bpf_kfunc_end_defs(); -struct scx_bpf_error_bstr_bufs { +struct scx_bpf_bstr_bufs { u64 data[MAX_BPRINTF_VARARGS]; char msg[SCX_EXIT_MSG_LEN]; }; -static DEFINE_PER_CPU(struct scx_bpf_error_bstr_bufs, scx_bpf_error_bstr_bufs); +static DEFINE_PER_CPU(struct scx_bpf_bstr_bufs, scx_bpf_bstr_bufs); -static void bpf_exit_bstr_common(enum scx_exit_kind kind, s64 exit_code, - char *fmt, unsigned long long *data, - u32 data__sz) +static char *bstr_format(char *fmt, unsigned long long *data, u32 data__sz) { struct bpf_bprintf_data bprintf_data = { .get_bin_args = true }; - struct scx_bpf_error_bstr_bufs *bufs; - unsigned long flags; + struct scx_bpf_bstr_bufs *bufs = this_cpu_ptr(&scx_bpf_bstr_bufs); int ret; - BUILD_BUG_ON(sizeof(enum scx_exit_code) != sizeof_field(struct scx_exit_info, exit_code)); - local_irq_save(flags); - bufs = this_cpu_ptr(&scx_bpf_error_bstr_bufs); + lockdep_assert_irqs_disabled(); if (data__sz % 8 || data__sz > MAX_BPRINTF_VARARGS * 8 || (data__sz && !data)) { scx_ops_error("invalid data=%p and data__sz=%u", (void *)data, data__sz); - goto out_restore; + return ERR_PTR(-EINVAL); } ret = copy_from_kernel_nofault(bufs->data, data, data__sz); - if (ret) { + if (ret < 0) { scx_ops_error("failed to read data fields (%d)", ret); - goto out_restore; + return ERR_PTR(ret); } ret = bpf_bprintf_prepare(fmt, UINT_MAX, bufs->data, data__sz / 8, &bprintf_data); if (ret < 0) { - scx_ops_error("failed to format prepration (%d)", ret); - goto out_restore; + scx_ops_error("format preparation failed (%d)", ret); + return ERR_PTR(ret); } ret = bstr_printf(bufs->msg, sizeof(bufs->msg), fmt, bprintf_data.bin_args); bpf_bprintf_cleanup(&bprintf_data); if (ret < 0) { - scx_ops_error("scx_ops_error(\"%s\", %p, %u) failed to format", + scx_ops_error("(\"%s\", %p, %u) failed to format", fmt, data, data__sz); - goto out_restore; + return ERR_PTR(ret); } - scx_ops_exit_kind(kind, exit_code, "%s", bufs->msg); -out_restore: - local_irq_restore(flags); - + return bufs->msg; } __bpf_kfunc_start_defs(); @@ -5949,8 +6336,14 @@ __bpf_kfunc_start_defs(); __bpf_kfunc void scx_bpf_exit_bstr(s64 exit_code, char *fmt, unsigned long long *data, u32 data__sz) { - bpf_exit_bstr_common(SCX_EXIT_UNREG_BPF, exit_code, fmt, data, - data__sz); + unsigned long flags; + char *msg; + + local_irq_save(flags); + msg = bstr_format(fmt, data, data__sz); + if (!IS_ERR(msg)) + scx_ops_exit_kind(SCX_EXIT_UNREG_BPF, exit_code, "%s", msg); + local_irq_restore(flags); } /** @@ -5965,19 +6358,62 @@ __bpf_kfunc void scx_bpf_exit_bstr(s64 exit_code, char *fmt, __bpf_kfunc void scx_bpf_error_bstr(char *fmt, unsigned long long *data, u32 data__sz) { + unsigned long flags; + char *msg; - bpf_exit_bstr_common(SCX_EXIT_ERROR_BPF, 0, fmt, data, - data__sz); + local_irq_save(flags); + msg = bstr_format(fmt, data, data__sz); + if (!IS_ERR(msg)) + scx_ops_exit_kind(SCX_EXIT_ERROR_BPF, 0, "%s", msg); + local_irq_restore(flags); } /** - * scx_bpf_nr_cpu_ids - Return the number of possible CPU IDs + * scx_bpf_dump - Generate extra debug dump specific to the BPF scheduler + * @fmt: format string + * @data: format string parameters packaged using ___bpf_fill() macro + * @data__sz: @data len, must end in '__sz' for the verifier * - * All valid CPU IDs in the system are smaller than the returned value. + * To be called through scx_bpf_dump() helper from ops.dump(), dump_cpu() and + * dump_task() to generate extra debug dump specific to the BPF scheduler. + * + * The extra dump may be multiple lines. A single line may be split over + * multiple calls. The last line is automatically terminated. */ -__bpf_kfunc u32 scx_bpf_nr_cpu_ids(void) +__bpf_kfunc void scx_bpf_dump_bstr(char *fmt, unsigned long long *data, + u32 data__sz) { - return nr_cpu_ids; + struct seq_buf *s = scx_dump_seq_buf; + char *msg, *p; + + if (raw_smp_processor_id() != scx_dump_cpu) { + scx_ops_error("scx_bpf_dump() must only be called from ops.dump() and friends"); + return; + } + + lockdep_assert_irqs_disabled(); + + msg = bstr_format(fmt, data, data__sz); + if (IS_ERR(msg)) { + seq_buf_printf(s, "%s[!] (\"%s\", %p, %u) failed to format\n", + scx_dump_prefix, fmt, data, data__sz); + return; + } + + if (msg[0] == '\0') + return; + + if (scx_dump_last == '\0') { + seq_buf_putc(s, '\n'); + scx_dump_last = '\n'; + } + + for (p = msg; *p != '\0'; p++) { + if (scx_dump_last == '\n') + seq_buf_printf(s, "%s", scx_dump_prefix); + seq_buf_putc(s, *p); + scx_dump_last = *p; + } } /** @@ -6051,6 +6487,16 @@ __bpf_kfunc void scx_bpf_cpuperf_set(u32 cpu, u32 perf) } } +/** + * scx_bpf_nr_cpu_ids - Return the number of possible CPU IDs + * + * All valid CPU IDs in the system are smaller than the returned value. + */ +__bpf_kfunc u32 scx_bpf_nr_cpu_ids(void) +{ + return nr_cpu_ids; +} + /** * scx_bpf_get_possible_cpumask - Get a referenced kptr to cpu_possible_mask */ @@ -6132,14 +6578,98 @@ __bpf_kfunc const struct cpumask *scx_bpf_get_idle_smtmask(void) __bpf_kfunc void scx_bpf_put_idle_cpumask(const struct cpumask *idle_mask) { /* - * Empty function body because we aren't actually acquiring or - * releasing a reference to a global idle cpumask, which is read-only - * in the caller and is never released. The acquire / release semantics - * here are just used to make the cpumask a trusted pointer in the - * caller. + * Empty function body because we aren't actually acquiring or releasing + * a reference to a global idle cpumask, which is read-only in the + * caller and is never released. The acquire / release semantics here + * are just used to make the cpumask a trusted pointer in the caller. */ } +/** + * scx_bpf_test_and_clear_cpu_idle - Test and clear @cpu's idle state + * @cpu: cpu to test and clear idle for + * + * Returns %true if @cpu was idle and its idle state was successfully cleared. + * %false otherwise. + * + * Unavailable if ops.update_idle() is implemented and + * %SCX_OPS_KEEP_BUILTIN_IDLE is not set. + */ +__bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) +{ + if (!static_branch_likely(&scx_builtin_idle_enabled)) { + scx_ops_error("built-in idle tracking is disabled"); + return false; + } + + if (ops_cpu_valid(cpu, NULL)) + return test_and_clear_cpu_idle(cpu); + else + return false; +} + +/** + * scx_bpf_pick_idle_cpu - Pick and claim an idle cpu + * @cpus_allowed: Allowed cpumask + * @flags: %SCX_PICK_IDLE_CPU_* flags + * + * Pick and claim an idle cpu in @cpus_allowed. Returns the picked idle cpu + * number on success. -%EBUSY if no matching cpu was found. + * + * Idle CPU tracking may race against CPU scheduling state transitions. For + * example, this function may return -%EBUSY as CPUs are transitioning into the + * idle state. If the caller then assumes that there will be dispatch events on + * the CPUs as they were all busy, the scheduler may end up stalling with CPUs + * idling while there are pending tasks. Use scx_bpf_pick_any_cpu() and + * scx_bpf_kick_cpu() to guarantee that there will be at least one dispatch + * event in the near future. + * + * Unavailable if ops.update_idle() is implemented and + * %SCX_OPS_KEEP_BUILTIN_IDLE is not set. + */ +__bpf_kfunc s32 scx_bpf_pick_idle_cpu(const struct cpumask *cpus_allowed, + u64 flags) +{ + if (!static_branch_likely(&scx_builtin_idle_enabled)) { + scx_ops_error("built-in idle tracking is disabled"); + return -EBUSY; + } + + return scx_pick_idle_cpu(cpus_allowed, flags); +} + +/** + * scx_bpf_pick_any_cpu - Pick and claim an idle cpu if available or pick any CPU + * @cpus_allowed: Allowed cpumask + * @flags: %SCX_PICK_IDLE_CPU_* flags + * + * Pick and claim an idle cpu in @cpus_allowed. If none is available, pick any + * CPU in @cpus_allowed. Guaranteed to succeed and returns the picked idle cpu + * number if @cpus_allowed is not empty. -%EBUSY is returned if @cpus_allowed is + * empty. + * + * If ops.update_idle() is implemented and %SCX_OPS_KEEP_BUILTIN_IDLE is not + * set, this function can't tell which CPUs are idle and will always pick any + * CPU. + */ +__bpf_kfunc s32 scx_bpf_pick_any_cpu(const struct cpumask *cpus_allowed, + u64 flags) +{ + s32 cpu; + + if (static_branch_likely(&scx_builtin_idle_enabled)) { + cpu = scx_pick_idle_cpu(cpus_allowed, flags); + if (cpu >= 0) + return cpu; + } + + cpu = cpumask_any_distribute(cpus_allowed); + if (cpu < nr_cpu_ids) + return cpu; + else + return -EBUSY; +} + /** * scx_bpf_task_running - Is task currently running? * @p: task of interest @@ -6196,18 +6726,28 @@ __bpf_kfunc struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __bpf_kfunc_end_defs(); BTF_KFUNCS_START(scx_kfunc_ids_any) +BTF_ID_FLAGS(func, scx_bpf_kick_cpu) +BTF_ID_FLAGS(func, scx_bpf_dsq_nr_queued) +BTF_ID_FLAGS(func, scx_bpf_destroy_dsq) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_new, KF_ITER_NEW | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_scx_dsq_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, scx_bpf_exit_bstr, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, scx_bpf_error_bstr, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids) +BTF_ID_FLAGS(func, scx_bpf_dump_bstr, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, scx_bpf_cpuperf_cap) BTF_ID_FLAGS(func, scx_bpf_cpuperf_cur) BTF_ID_FLAGS(func, scx_bpf_cpuperf_set) +BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids) BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE) BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE) +BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle) +BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU) +BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU) #ifdef CONFIG_CGROUP_SCHED @@ -6237,14 +6777,14 @@ static int __init scx_init(void) */ if ((ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_sleepable)) || + (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, + &scx_kfunc_set_select_cpu)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_enqueue_dispatch)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_dispatch)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_cpu_release)) || - (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, - &scx_kfunc_set_ops_only)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_any)) || (ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index d572be7a43243..97064e53f2995 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -33,16 +33,17 @@ static inline bool task_on_scx(const struct task_struct *p) return scx_enabled() && p->sched_class == &ext_sched_class; } -bool task_should_scx(struct task_struct *p); +void scx_next_task_picked(struct rq *rq, struct task_struct *p, + const struct sched_class *active); +void scx_tick(struct rq *rq); +void init_scx_entity(struct sched_ext_entity *scx); void scx_pre_fork(struct task_struct *p); int scx_fork(struct task_struct *p); void scx_post_fork(struct task_struct *p); void scx_cancel_fork(struct task_struct *p); int scx_check_setscheduler(struct task_struct *p, int policy); bool scx_can_stop_tick(struct rq *rq); -void scx_tick(struct rq *rq); -void scx_next_task_picked(struct rq *rq, struct task_struct *p, - const struct sched_class *active); +bool task_should_scx(struct task_struct *p); void init_sched_ext_class(void); static inline u32 scx_cpuperf_target(s32 cpu) @@ -87,17 +88,16 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, #define scx_enabled() false #define scx_switched_all() false -static inline bool task_on_scx(const struct task_struct *p) { return false; } +static inline void scx_next_task_picked(struct rq *rq, struct task_struct *p, + const struct sched_class *active) {} +static inline void scx_tick(struct rq *rq) {} static inline void scx_pre_fork(struct task_struct *p) {} static inline int scx_fork(struct task_struct *p) { return 0; } static inline void scx_post_fork(struct task_struct *p) {} static inline void scx_cancel_fork(struct task_struct *p) {} -static inline int scx_check_setscheduler(struct task_struct *p, - int policy) { return 0; } +static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; } static inline bool scx_can_stop_tick(struct rq *rq) { return true; } -static inline void scx_tick(void) {} -static inline void scx_next_task_picked(struct rq *rq, struct task_struct *p, - const struct sched_class *active) {} +static inline bool task_on_scx(const struct task_struct *p) { return false; } static inline void init_sched_ext_class(void) {} static inline u32 scx_cpuperf_target(s32 cpu) { return 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8a9b2e95d06be..99e9236f8787a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -696,15 +696,21 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * * XXX could add max_slice to the augmented data to track this. */ -static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) +static s64 entity_lag(u64 avruntime, struct sched_entity *se) { - s64 lag, limit; + 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) +{ 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 @@ static inline void 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 @@ static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, * = 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 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, 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 373d42c707bc5..5891e715f00d0 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -46,7 +46,16 @@ int housekeeping_any_cpu(enum hk_type type) 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 void __init housekeeping_setup_type(enum hk_type type, 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 @@ static int __init housekeeping_setup(char *str, unsigned long flags) 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 @@ static int __init housekeeping_setup(char *str, unsigned long flags) } } + 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/softirq.c b/kernel/softirq.c index b315b21fb28cd..02582017759a2 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -508,7 +508,7 @@ static inline bool lockdep_softirq_start(void) { return false; } 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 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) 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 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) 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 @@ static void run_ksoftirqd(unsigned int cpu) * 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/trace/trace_events.c b/kernel/trace/trace_events.c index 52f75c36bbca4..6ef29eba90ceb 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2552,6 +2552,14 @@ static int event_callback(const char *name, umode_t *mode, void **data, 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) { @@ -2566,6 +2574,7 @@ event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) { .name = "enable", .callback = event_callback, + .release = event_release, }, { .name = "filter", @@ -2634,6 +2643,9 @@ event_create_dir(struct eventfs_inode *parent, struct trace_event_file *file) 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 dfe3ee6035ecc..42bc0f3622263 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -1466,7 +1466,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, 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 f95516cd45bbe..23c125c2e2436 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -205,11 +205,10 @@ static int __init crash_save_vmcoreinfo_init(void) 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 0066c8f6c1544..d2dbe099286b9 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1277,8 +1277,12 @@ static bool kick_pool(struct worker_pool *pool) !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 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) 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 @@ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) 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 c63a5fbf1f1c2..291185f54ee4c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -375,7 +375,7 @@ config DEBUG_INFO_SPLIT 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 @@ config PAHOLE_HAS_LANG_EXCLUDE 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/dynamic_debug.c b/lib/dynamic_debug.c index c78f335fa9813..f2c5e7910bb19 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -302,7 +302,11 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords) } 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] : ""); + return -EINVAL; + } } /* `buf' is start of word, `end' is one past its end */ diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 68b45c82c37a6..7bc2220fea805 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -1124,7 +1124,7 @@ static ssize_t extract_user_to_sg(struct iov_iter *iter, 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 68c97387aa54e..cd8f234552851 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -627,10 +627,10 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, /* * 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/mm/hugetlb.c b/mm/hugetlb.c index 31d00eee028f1..ce7be5c244429 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1624,7 +1624,7 @@ static inline void __clear_hugetlb_destructor(struct hstate *h, { lockdep_assert_held(&hugetlb_lock); - folio_clear_hugetlb(folio); + __folio_clear_hugetlb(folio); } /* @@ -1711,7 +1711,7 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, 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 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, * 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 __prep_account_new_huge_page(struct hstate *h, int nid) 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); @@ -2159,22 +2159,6 @@ static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, return __prep_compound_gigantic_folio(folio, order, true); } -/* - * 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. * @@ -3268,9 +3252,12 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, 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 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, 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 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, */ 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 { diff --git a/mm/zswap.c b/mm/zswap.c index caed028945b04..6f8850c44b616 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1331,15 +1331,22 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, 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 f001582345052..9404dd551dfd2 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -478,6 +478,8 @@ static struct sk_buff *vlan_gro_receive(struct list_head *head, 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 558e158c98d01..9169efb2f43aa 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -103,7 +103,7 @@ static void ax25_kill_by_device(struct net_device *dev) 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/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3ad74f76983b2..05346250f7195 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1263,7 +1263,7 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) 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 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, 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 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, 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 a8b8cfebe0180..4a27e4a17a674 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3218,7 +3218,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, 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 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, * 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 void hci_le_conn_update_complete_evt(struct hci_dev *hdev, void *data, 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 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, 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 struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, 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 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * 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 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, 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 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, 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 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data, 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_sync.c b/net/bluetooth/hci_sync.c index c5d8799046ccf..4c707eb64e6f6 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6346,7 +6346,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, 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 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, 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 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, 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/l2cap_core.c b/net/bluetooth/l2cap_core.c index dc08974087936..84fc70862d78a 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7018,7 +7018,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, 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 e7d810b23082f..5cc83f906c123 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -439,7 +439,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, 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 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, 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 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, 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; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 32ed6e9245a30..965f621ef865a 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2623,7 +2623,11 @@ static int add_uuid(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) 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 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, 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 @@ static int set_dev_class(struct sock *sk, struct hci_dev *hdev, void *data, 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 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, 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/sco.c b/net/bluetooth/sco.c index 368e026f4d15c..5d03c5440b06f 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -964,7 +964,8 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, 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); @@ -986,7 +987,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, 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; @@ -1004,7 +1005,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, 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 7431f89e897b9..d7c35f55bd69f 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -266,7 +266,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, 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_netlink.c b/net/bridge/br_netlink.c index 2cf4fc7562639..f17dbac7d8284 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -667,7 +667,7 @@ void br_ifinfo_notify(int event, const struct net_bridge *br, { 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/core/filter.c b/net/core/filter.c index 786d792ac8161..8120c3dddf5ed 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4363,10 +4363,12 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, 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)) { @@ -4378,11 +4380,20 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, 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); } @@ -4445,9 +4456,9 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); 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; @@ -4457,11 +4468,20 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, 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); } @@ -4498,9 +4518,11 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, 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) { @@ -4520,7 +4542,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, 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 83f35d99a682c..c7901253a1a8f 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -371,6 +371,7 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) 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 17617c29be2df..e03441de54b71 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2123,11 +2123,17 @@ static inline int skb_alloc_rx_flag(const struct sk_buff *skb) 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 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * 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 4d75ef9d24bfa..fd20aae30be23 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1226,11 +1226,8 @@ static void sk_psock_verdict_data_ready(struct sock *sk) 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 2edc8b796a4e7..049c3adeb8504 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -164,17 +164,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) 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 55bd72997b310..fafb123f798be 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1572,6 +1572,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) /* 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/icmp.c b/net/ipv4/icmp.c index e63a3bf996176..437e782b9663b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -92,6 +92,7 @@ #include #include #include +#include /* * Build xmit assembly blocks @@ -1032,6 +1033,8 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) 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 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) /* 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 1fe794967211e..39229fd0601a1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1473,7 +1473,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * 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/raw.c b/net/ipv4/raw.c index dcb11f22cbf2b..4cb43401e0e06 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -612,6 +612,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (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 d36ace160d426..b814fdab19f71 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2166,6 +2166,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, 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 3afeeb68e8a7e..781b67a525719 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1068,6 +1068,7 @@ void tcp_ao_connect_init(struct sock *sk) { 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 @@ void tcp_ao_connect_init(struct sock *sk) 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 c02bf011d4a6f..b32cf2eeeb41d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -532,7 +532,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, 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 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 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 3498dd1d0694d..8721fe5beca2b 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -471,6 +471,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, 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 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, 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 @@ EXPORT_SYMBOL(udp_gro_complete); 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/ip6_offload.c b/net/ipv6/ip6_offload.c index b41e35af69ea2..c8b909a9904f3 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -237,6 +237,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, 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/udp.c b/net/ipv6/udp.c index 8b1dd7f512491..8f7aa8bac1e7b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -272,7 +272,8 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, 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 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 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 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } 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 bbd347de00b45..b41152dd42469 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -164,7 +164,8 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) 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 39e487ccc4688..8ba00ad433c21 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -127,6 +127,9 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, /* 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 80e4b9784131d..ccacaed32817a 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -797,6 +797,7 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, 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 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, 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 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, 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 32475da98d739..cbc9b5e40cb35 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -747,6 +747,9 @@ bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata, 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 @@ bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata, 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 d913ce7ba72ef..3f9664e4e00c6 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -134,10 +134,39 @@ struct mesh_path { #define MESH_FAST_TX_CACHE_THRESHOLD_SIZE 384 #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 mesh_path { */ 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 @@ void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata); 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 91b55d6a68b97..a6b62169f0848 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -37,8 +37,8 @@ static const struct rhashtable_params mesh_rht_params = { 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 @@ static void mesh_fast_tx_entry_free(struct mesh_tx_cache *cache, } 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 @@ void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, 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 @@ void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, } } - 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 @@ void mesh_fast_tx_flush_addr(struct ieee80211_sub_if_data *sdata, 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 96b70006b7fc0..3bbb216a0fc8c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -616,7 +616,6 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, .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 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, 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 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, 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 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, break; } - conn->mode = ap_mode; chanreq->oper = ap_chandef; /* wider-bandwidth OFDMA is only done in EHT */ @@ -753,8 +758,10 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, } /* 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 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, */ 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 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, 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 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, 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 23404b275457a..4dc1def695486 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -877,6 +877,7 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, 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 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, 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 c1f8501384056..6e24864f9a40b 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2763,7 +2763,10 @@ ieee80211_rx_mesh_fast_forward(struct ieee80211_sub_if_data *sdata, 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 @@ ieee80211_rx_mesh_fast_forward(struct ieee80211_sub_if_data *sdata, 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 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) } 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 0429e59ba387c..73850312580f7 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -648,6 +648,7 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, 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 6bf223e6cd1a5..cfd0a62d0152b 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -698,11 +698,16 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) 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 7e74b812e366a..965eb69dc5de3 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3723,6 +3723,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) 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 a0921adc31a9f..1e689c7141271 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,8 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, 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 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (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/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 274b6f7e6bb57..d170758a1eb5d 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -338,7 +338,9 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, 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/nsh/nsh.c b/net/nsh/nsh.c index f4a38bd6a7e04..bfb7758063f31 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,15 @@ EXPORT_SYMBOL_GPL(nsh_pop); 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 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, } 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 74b63cdb59923..2928c142a2ddb 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1593,9 +1593,9 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) 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 0af4642aeec4b..1539d315afe74 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -119,18 +119,13 @@ struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *lo 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 f2701068ed9e4..6716c021a532e 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -19,7 +19,7 @@ static int none_init_connection_security(struct rxrpc_connection *conn, */ 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 f1a68270862db..48a1475e6b063 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -155,7 +155,7 @@ static struct rxrpc_txbuf *rxkad_alloc_txbuf(struct rxrpc_call *call, size_t rem 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 e0679658d9de0..c3913d8a50d34 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -21,20 +21,20 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ { 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/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index f2a100c4c81f1..40797114d50a4 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -230,28 +230,6 @@ static void svc_rdma_write_info_free(struct svc_rdma_write_info *info) queue_work(svcrdma_wq, &info->wi_work); } -/** - * 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 @@ -308,11 +286,13 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) 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 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) 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 @@ static int svc_rdma_xb_write(const struct xdr_buf *xdr, void *data) 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 @@ static int svc_rdma_prepare_write_chunk(struct svcxprt_rdma *rdma, 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 @@ static int svc_rdma_prepare_write_chunk(struct svcxprt_rdma *rdma, } /** - * 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 dfca39abd16c8..bb5436b719e05 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -142,7 +142,6 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma) 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 @@ static void svc_rdma_send_ctxt_release(struct svcxprt_rdma *rdma, 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 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) 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 bb9b747d58a1a..ce18716491c8f 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2664,6 +2664,7 @@ static void xs_tcp_tls_setup_socket(struct work_struct *work) .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 5c9fd4791c4ba..76284fc538ebd 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -142,9 +142,9 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) 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 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) 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 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) *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 762f424ff2d59..e5e47452308ab 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -215,7 +215,7 @@ static inline struct sk_buff *tls_strp_msg(struct tls_sw_context_rx *ctx) 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 ca1e0e198ceb4..5df08d848b5c9 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -360,7 +360,7 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, 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 @@ static int tls_strp_read_sock(struct tls_strparser *strp) 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 @@ void tls_strp_msg_done(struct tls_strparser *strp) 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/garbage.c b/net/unix/garbage.c index 6433a414acf86..0104be9d47045 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -299,7 +299,7 @@ static void __unix_gc(struct work_struct *work) __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); if (sk->sk_state == TCP_LISTEN) { - unix_state_lock(sk); + 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 b4edba6b0b7ba..30ff9a4708134 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14030,6 +14030,8 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info) 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 cbbf347c6b2e0..df013c98b80df 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1758,7 +1758,7 @@ TRACE_EVENT(rdev_return_void_tx_rx, 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 @@ DECLARE_EVENT_CLASS(tx_rx_evt, 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/rust/Makefile b/rust/Makefile index 846e6ab9d5a9b..86a125c4243cb 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -175,7 +175,6 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $< 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 424257284d167..09004b56fb65c 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -1292,8 +1292,15 @@ impl_zeroable! { i8, i16, i32, i64, i128, isize, f32, f64, - // SAFETY: These are ZSTs, there is nothing to zero. - {} PhantomData, 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: + // . The Rust Reference + // also has information on undefined behavior: + // . + // + // SAFETY: These are inhabited ZSTs; there is nothing to zero and a valid value exists. + {} PhantomData, core::marker::PhantomPinned, (), // SAFETY: Type is allowed to take any value, including all zeros. {} MaybeUninit, diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index be68d5e567b1a..6858e2f8a3ed9 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -65,7 +65,7 @@ const __LOG_PREFIX: &[u8] = b"rust_kernel\0"; /// 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 96e09c6e8530b..265d0e1c13710 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -640,6 +640,10 @@ pub struct Registration { 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 f489f31573832..520eae5fd7928 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -35,18 +35,6 @@ use proc_macro::TokenStream; /// 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 27979e582e4b9..acd0393b50957 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -199,17 +199,6 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { /// 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 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { 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() - }} - - #[cfg(MODULE)] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn cleanup_module() {{ - __exit() - }} + // Double nested modules, since then nobody can access the public items inside. + mod __module_init {{ + mod __module_init {{ + use super::super::{type_}; + + /// 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; + + // 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() }} + }} - // 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; + #[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))] - #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)] - core::arch::global_asm!( - r#\".section \"{initcall_section}\", \"a\" - __{name}_initcall: - .long __{name}_init - . - .previous - \"# - ); + // 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; + + #[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}_init() -> core::ffi::c_int {{ - __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() }} + }} - #[cfg(not(MODULE))] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn __{name}_exit() {{ - __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(); + }} + }} + }} - fn __init() -> core::ffi::c_int {{ - match <{type_} as kernel::Module>::init(&THIS_MODULE) {{ - Ok(m) => {{ + /// # 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 {{ - __MOD = Some(m); + // Invokes `drop()` on `__MOD`, which should be used for cleanup. + __MOD = None; }} - return 0; - }} - Err(e) => {{ - return e.to_errno(); }} - }} - }} - fn __exit() {{ - unsafe {{ - // Invokes `drop()` on `__MOD`, which should be used for cleanup. - __MOD = None; + {modinfo} }} }} - - {modinfo} ", type_ = info.type_, name = info.name, diff --git a/scripts/Makefile.build b/scripts/Makefile.build index baf86c0880b6d..533a7799fdfe6 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -273,7 +273,7 @@ rust_common_cmd = \ -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/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 6a384b922e4fa..d1f6cdcf1866e 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -557,9 +557,32 @@ static const struct config_entry *snd_intel_dsp_find_config 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 5f60658c6051c..d7417a40392b2 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -45,6 +45,8 @@ static bool is_link_enabled(struct fwnode_handle *fw_node, u8 idx) "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 fe72e7d772412..dadeda7758cee 100644 --- a/sound/pci/emu10k1/emu10k1.c +++ b/sound/pci/emu10k1/emu10k1.c @@ -189,8 +189,7 @@ static int snd_emu10k1_suspend(struct device *dev) 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 de5c41e578e1f..8ccc0178360ce 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -732,69 +732,67 @@ static int snd_emu1010_load_firmware(struct snd_emu10k1 *emu, int dock, 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 @@ static void emu1010_clock_work(struct work_struct *work) 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 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) * 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 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) 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 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) 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 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) 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 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) // 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 @@ static void snd_emu10k1_free(struct snd_card *card) } 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 @@ int snd_emu10k1_create(struct snd_card *card, 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 0a32ea53d8c64..05b98d9b547b2 100644 --- a/sound/pci/emu10k1/emumixer.c +++ b/sound/pci/emu10k1/emumixer.c @@ -661,7 +661,9 @@ static int snd_emu1010_output_source_put(struct snd_kcontrol *kcontrol, 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 @@ static int snd_emu1010_input_source_put(struct snd_kcontrol *kcontrol, 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 @@ static int snd_emu1010_adc_pads_put(struct snd_kcontrol *kcontrol, struct snd_ct 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 @@ static int snd_emu1010_dac_pads_put(struct snd_kcontrol *kcontrol, struct snd_ct 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 @@ static int snd_emu1010_clock_source_put(struct snd_kcontrol *kcontrol, 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 @@ static int snd_emu1010_clock_source_put(struct snd_kcontrol *kcontrol, } else { spin_unlock_irq(&emu->reg_lock); } + snd_emu1010_fpga_unlock(emu); return change; } @@ -1041,7 +1047,7 @@ static int snd_emu1010_clock_fallback_put(struct snd_kcontrol *kcontrol, 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 @@ static int snd_emu1010_optical_out_put(struct snd_kcontrol *kcontrol, 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 @@ static int snd_emu1010_optical_in_put(struct snd_kcontrol *kcontrol, 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 @@ int snd_emu10k1_mixer(struct snd_emu10k1 *emu, 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 2f80fd91017c3..737c28d31b41a 100644 --- a/sound/pci/emu10k1/emuproc.c +++ b/sound/pci/emu10k1/emuproc.c @@ -165,6 +165,8 @@ static void snd_emu10k1_proc_spdif_read(struct snd_info_entry *entry, 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 @@ static void snd_emu10k1_proc_spdif_read(struct snd_info_entry *entry, 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 @@ static void snd_emu_proc_emu1010_reg_read(struct snd_info_entry *entry, 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 @@ static void snd_emu_proc_emu1010_reg_read(struct snd_info_entry *entry, 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 74df2330015f6..f4a1c2d4b0787 100644 --- a/sound/pci/emu10k1/io.c +++ b/sound/pci/emu10k1/io.c @@ -285,24 +285,33 @@ static void snd_emu1010_fpga_write_locked(struct snd_emu10k1 *emu, u32 reg, u32 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; + if (snd_BUG_ON(!mutex_is_locked(&emu->emu1010.lock))) + return; + snd_emu1010_fpga_write_locked(emu, reg, value); +} - spin_lock_irqsave(&emu->emu_lock, flags); +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); - spin_unlock_irqrestore(&emu->emu_lock, flags); + snd_emu1010_fpga_unlock(emu); } -static void snd_emu1010_fpga_read_locked(struct snd_emu10k1 *emu, u32 reg, u32 *value) +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 @@ static void snd_emu1010_fpga_read_locked(struct snd_emu10k1 *emu, u32 reg, u32 * *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 1a3f84599cb58..558c1f38fe971 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -644,6 +644,8 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56) 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 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id) 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 70d80b6af3fe3..b29739bd330b1 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -920,6 +920,8 @@ static void alc_pre_init(struct hda_codec *codec) ((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 @@ static void alc245_fixup_hp_spectre_x360_eu0xxx(struct hda_codec *codec, 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 @@ enum { 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, @@ -7470,7 +7513,8 @@ enum { 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 + ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1, + ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -7510,6 +7554,23 @@ static void alc287_fixup_lenovo_14irp8_duetitl(struct hda_codec *codec, __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, @@ -9404,6 +9465,10 @@ static const struct hda_fixup alc269_fixups[] = { .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[]) { @@ -9726,6 +9791,12 @@ static const struct hda_fixup alc269_fixups[] = { .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[] = { @@ -9937,6 +10008,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { 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), @@ -10393,6 +10465,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { 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), @@ -10422,7 +10496,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { 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), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 69c68d8e7a6b5..1760b5d42460a 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -430,6 +430,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_BOARD_NAME, "MRID6"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "MDC"), + DMI_MATCH(DMI_BOARD_NAME, "Herbag_MDU"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index dfb4ce53491bb..f8e57a2fc3e32 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -1094,6 +1094,7 @@ static int cs35l41_handle_pdata(struct device *dev, struct cs35l41_hw_cfg *hw_cf 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 @@ static int cs35l41_dsp_init(struct cs35l41_private *cs35l41) return ret; } - ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC, - CS35L41_INPUT_SRC_VPMON); + 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_RX5_SRC, dsp1rx5_src); if (ret < 0) { - dev_err(cs35l41->dev, "Write INPUT_SRC_VPMON 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_CLASSH); + ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC, CS35L41_INPUT_SRC_VBSTMON); if (ret < 0) { - dev_err(cs35l41->dev, "Write INPUT_SRC_CLASSH failed: %d\n", ret); + 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 14a5f86019aad..70ff55c1517fe 100644 --- a/sound/soc/codecs/cs35l56-sdw.c +++ b/sound/soc/codecs/cs35l56-sdw.c @@ -188,8 +188,6 @@ static void cs35l56_sdw_init(struct sdw_slave *peripheral) 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 08cac58e3ab22..fd02b621da52c 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -40,16 +40,11 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_set_patch, SND_SOC_CS35L56_SHARED); 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 bool cs35l56_volatile_reg(struct device *dev, unsigned int reg) } } +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 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg) */ 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 @@ int cs35l56_wait_for_firmware_boot(struct cs35l56_base *cs35l56_base) 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 @@ void cs35l56_system_reset(struct cs35l56_base *cs35l56_base, bool is_soundwire) 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 @@ int cs35l56_runtime_resume_common(struct cs35l56_base *cs35l56_base, bool is_sou 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 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_calibration_controls, SND_SOC_CS35L56_SHARED); 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 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) * 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 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) 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 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) 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 8d2f021fb3628..4986e78105daf 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -454,9 +454,14 @@ static int cs35l56_asp_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int f { 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 @@ static int cs35l56_asp_dai_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx 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 @@ static int cs35l56_asp_dai_hw_params(struct snd_pcm_substream *substream, 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 @@ static int cs35l56_asp_dai_set_sysclk(struct snd_soc_dai *dai, 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 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 "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 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 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 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 */ 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 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 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 @@ static int cs35l56_try_get_broken_sdca_spkid_gpio(struct cs35l56_private *cs35l5 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 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56) 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 @@ int cs35l56_init(struct cs35l56_private *cs35l56) 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 6bc068cdcbe2a..15e5e3eb592b3 100644 --- a/sound/soc/codecs/da7219-aad.c +++ b/sound/soc/codecs/da7219-aad.c @@ -671,8 +671,10 @@ static struct da7219_aad_pdata *da7219_aad_fw_to_pdata(struct device *dev) 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 @@ static struct da7219_aad_pdata *da7219_aad_fw_to_pdata(struct device *dev) 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 e3ba04484813a..d0d24a53df746 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -444,6 +444,7 @@ struct rt5645_priv { 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 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse 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 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse 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 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse 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 @@ static int rt5645_i2c_probe(struct i2c_client *i2c) 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 @@ static void rt5645_i2c_remove(struct i2c_client *i2c) 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 @@ static void rt5645_i2c_shutdown(struct i2c_client *i2c) 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 3fb7b9adb61de..bc3579203c7a4 100644 --- a/sound/soc/codecs/rt715-sdca.c +++ b/sound/soc/codecs/rt715-sdca.c @@ -316,7 +316,7 @@ static int rt715_sdca_set_amp_gain_8ch_get(struct snd_kcontrol *kcontrol, 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 @@ static const struct snd_kcontrol_new rt715_sdca_snd_controls[] = { 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 @@ static const struct snd_kcontrol_new rt715_sdca_snd_controls[] = { 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 7e13868ff99f0..f012fe0ded6d2 100644 --- a/sound/soc/codecs/rt715-sdw.c +++ b/sound/soc/codecs/rt715-sdw.c @@ -111,6 +111,7 @@ static bool rt715_readable_register(struct device *dev, unsigned int reg) 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 e0ea3a23f7cc6..e5bd9ef812de1 100644 --- a/sound/soc/codecs/rt722-sdca.c +++ b/sound/soc/codecs/rt722-sdca.c @@ -1330,7 +1330,7 @@ static struct snd_soc_dai_driver rt722_sdca_dai[] = { .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 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) 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 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) 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 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) /* 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 44af8901352eb..2464361a7958c 100644 --- a/sound/soc/codecs/rt722-sdca.h +++ b/sound/soc/codecs/rt722-sdca.h @@ -69,6 +69,7 @@ struct rt722_sdca_dmic_kctrl_priv { #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 @@ struct rt722_sdca_dmic_kctrl_priv { #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 3c025dabaf7a4..1253695bebd86 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -1155,6 +1155,7 @@ static int wsa881x_probe(struct sdw_slave *pdev, 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 9d9921e1cd4de..d2554c8577326 100644 --- a/sound/soc/intel/avs/icl.c +++ b/sound/soc/intel/avs/icl.c @@ -64,7 +64,7 @@ struct avs_icl_memwnd2_desc { 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 13061bd1488bb..42b42903ae9de 100644 --- a/sound/soc/intel/avs/topology.c +++ b/sound/soc/intel/avs/topology.c @@ -1582,6 +1582,8 @@ static int avs_widget_load(struct snd_soc_component *comp, int index, 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 05f38d1f7d824..b41a1147f1c34 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -636,28 +636,30 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_USE_AMCR0F28), }, { + /* 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, "T100TA"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), }, .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_MONO_SPEAKER | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, { + /* Asus T100TA and T100TAM, must come after T100TAF (mono spk) match */ .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), + 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_MONO_SPEAKER | - BYT_RT5640_DIFF_MIC | - BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, { diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig index b93ea33739f29..6458d5dc4902f 100644 --- a/sound/soc/meson/Kconfig +++ b/sound/soc/meson/Kconfig @@ -99,6 +99,7 @@ config SND_MESON_AXG_PDM 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 3180aa4d3a157..8c5605c1e34e8 100644 --- a/sound/soc/meson/axg-card.c +++ b/sound/soc/meson/axg-card.c @@ -318,6 +318,7 @@ static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np, 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 bebee0ca8e388..ecb3eb7a9723d 100644 --- a/sound/soc/meson/axg-fifo.c +++ b/sound/soc/meson/axg-fifo.c @@ -204,18 +204,26 @@ static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id) unsigned int status; regmap_read(fifo->map, FIFO_STATUS1, &status); - status = FIELD_GET(STATUS1_INT_STS, status); + axg_fifo_ack_irq(fifo, status); + + /* Use the thread to call period elapsed on nonatomic links */ 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); + return IRQ_WAKE_THREAD; - /* Ack irqs */ - axg_fifo_ack_irq(fifo, status); + 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_RETVAL(status); + return IRQ_HANDLED; } int axg_fifo_pcm_open(struct snd_soc_component *component, @@ -243,8 +251,9 @@ int axg_fifo_pcm_open(struct snd_soc_component *component, 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 63333a2b0a9c3..a6579efd37750 100644 --- a/sound/soc/meson/axg-tdm-formatter.c +++ b/sound/soc/meson/axg-tdm-formatter.c @@ -392,6 +392,46 @@ void axg_tdm_stream_free(struct axg_tdm_stream *ts) } 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 "); MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c index bf708717635bf..62057c71f742e 100644 --- a/sound/soc/meson/axg-tdm-interface.c +++ b/sound/soc/meson/axg-tdm-interface.c @@ -309,6 +309,7 @@ static int axg_tdm_iface_hw_params(struct snd_pcm_substream *substream, 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 @@ static int axg_tdm_iface_hw_params(struct snd_pcm_substream *substream, 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 @@ static int axg_tdm_iface_hw_free(struct snd_pcm_substream *substream, { 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); + + 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; + } - /* Force all attached formatters to update */ - return axg_tdm_stream_reset(ts); + return 0; } static int axg_tdm_iface_remove_dai(struct snd_soc_dai *dai) @@ -412,8 +430,8 @@ static const struct snd_soc_dai_ops axg_tdm_iface_ops = { .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 42f7470b9a7f4..daaca10fec9e2 100644 --- a/sound/soc/meson/axg-tdm.h +++ b/sound/soc/meson/axg-tdm.h @@ -58,12 +58,17 @@ struct axg_tdm_stream { 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 cc84d4c81be9d..238bda5f6b76f 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -350,7 +350,9 @@ static int sof_init_environment(struct snd_sof_dev *sdev) } 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 7c8aafca8fdef..7275437ea8d8a 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -330,14 +330,32 @@ EXPORT_SYMBOL_GPL(snd_sof_dbg_memory_info_init); 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 b26ffe767fab5..b14e508f1f315 100644 --- a/sound/soc/sof/intel/pci-lnl.c +++ b/sound/soc/sof/intel/pci-lnl.c @@ -35,6 +35,9 @@ static const struct sof_dev_desc lnl_desc = { .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 35769dd7905eb..af0bf354cb209 100644 --- a/sound/soc/sof/ipc3-pcm.c +++ b/sound/soc/sof/ipc3-pcm.c @@ -434,4 +434,5 @@ const struct sof_ipc_pcm_ops ipc3_pcm_ops = { .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 e915f9f87a6c3..4594470ed08b1 100644 --- a/sound/soc/sof/ipc4-pcm.c +++ b/sound/soc/sof/ipc4-pcm.c @@ -37,6 +37,25 @@ struct sof_ipc4_timestamp_info { 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 @@ sof_ipc4_update_pipeline_state(struct snd_sof_dev *sdev, int state, int cmd, */ 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 @@ static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev, 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 @@ static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev, 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 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, * 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 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, * 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 int sof_ipc4_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd, 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 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm { 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 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm return -ENOMEM; } + stream_priv = kzalloc(sizeof(*stream_priv), GFP_KERNEL); + if (!stream_priv) { + sof_ipc4_pcm_free(sdev, spcm); + return -ENOMEM; + } + + spcm->stream[stream].private = stream_priv; + if (!support_info) continue; - stream_info = kzalloc(sizeof(*stream_info), GFP_KERNEL); - if (!stream_info) { + time_info = kzalloc(sizeof(*time_info), GFP_KERNEL); + if (!time_info) { sof_ipc4_pcm_free(sdev, spcm); return -ENOMEM; } - spcm->stream[stream].private = stream_info; + 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 @@ static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pc 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 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, 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_pcm_hw_params(struct snd_soc_component *component, 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 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, 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 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, 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 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, * 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 @@ static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component, { 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 f03cee94bce62..8804e00e7251b 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -325,14 +325,13 @@ static int sof_pcm_trigger(struct snd_soc_component *component, 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 86bbb531e142c..499b6084b5263 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -116,6 +116,7 @@ struct snd_sof_dai_config_data { * 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 @@ struct sof_ipc_pcm_ops { 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 aa37c4ab0adbd..21cd41fec7a9c 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 #include @@ -241,14 +240,14 @@ static int tegra186_dspk_hw_params(struct snd_pcm_substream *substream, 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 b892d66f78470..1e760c3155213 100644 --- a/sound/soc/ti/davinci-mcasp.c +++ b/sound/soc/ti/davinci-mcasp.c @@ -2417,12 +2417,6 @@ static int davinci_mcasp_probe(struct platform_device *pdev) 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 @@ static int davinci_mcasp_probe(struct platform_device *pdev) 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/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index e73b027c5624f..fd865a9137259 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -182,6 +182,7 @@ def __init__(self, msg, offset, attr_space=None): 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 4a41856938a88..1b29030021eeb 100644 --- a/tools/perf/arch/riscv/util/header.c +++ b/tools/perf/arch/riscv/util/header.c @@ -41,7 +41,7 @@ static char *_get_cpuid(void) 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/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 44eb4267d3ac2..2c2b53a080ac2 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -29,56 +29,75 @@ static inline void ___vmlinux_h_sanity_check___(void) } s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym; +s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym; void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym; void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym; u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; bool scx_bpf_consume(u64 dsq_id) __ksym; +bool __scx_bpf_consume_task(unsigned long it, struct task_struct *p) __ksym __weak; u32 scx_bpf_reenqueue_local(void) __ksym; void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym; s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym; -bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) __ksym; -s32 scx_bpf_pick_idle_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; -s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; void scx_bpf_destroy_dsq(u64 dsq_id) __ksym; -s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym; -void scx_bpf_exit_bstr(s64 exit_code, char *fmt, - unsigned long long *data, u32 data__sz) __ksym; +int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, bool rev) __ksym __weak; +struct task_struct *bpf_iter_scx_dsq_next(struct bpf_iter_scx_dsq *it) __ksym __weak; +void bpf_iter_scx_dsq_destroy(struct bpf_iter_scx_dsq *it) __ksym __weak; +void scx_bpf_exit_bstr(s64 exit_code, char *fmt, unsigned long long *data, u32 data__sz) __ksym __weak; void scx_bpf_error_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym; -u32 scx_bpf_nr_cpu_ids(void) __ksym; -u32 scx_bpf_cpuperf_cap(s32 cpu) __ksym; -u32 scx_bpf_cpuperf_cur(s32 cpu) __ksym; -void scx_bpf_cpuperf_set(s32 cpu, u32 perf) __ksym; -const struct cpumask *scx_bpf_get_possible_cpumask(void) __ksym; -const struct cpumask *scx_bpf_get_online_cpumask(void) __ksym; -void scx_bpf_put_cpumask(const struct cpumask *cpumask) __ksym; +void scx_bpf_dump_bstr(char *fmt, unsigned long long *data, u32 data_len) __ksym; +u32 scx_bpf_cpuperf_cap(s32 cpu) __ksym __weak; +u32 scx_bpf_cpuperf_cur(s32 cpu) __ksym __weak; +void scx_bpf_cpuperf_set(s32 cpu, u32 perf) __ksym __weak; +u32 scx_bpf_nr_cpu_ids(void) __ksym __weak; +const struct cpumask *scx_bpf_get_possible_cpumask(void) __ksym __weak; +const struct cpumask *scx_bpf_get_online_cpumask(void) __ksym __weak; +void scx_bpf_put_cpumask(const struct cpumask *cpumask) __ksym __weak; const struct cpumask *scx_bpf_get_idle_cpumask(void) __ksym; const struct cpumask *scx_bpf_get_idle_smtmask(void) __ksym; void scx_bpf_put_idle_cpumask(const struct cpumask *cpumask) __ksym; +bool scx_bpf_test_and_clear_cpu_idle(s32 cpu) __ksym; +s32 scx_bpf_pick_idle_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; +s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym; bool scx_bpf_task_running(const struct task_struct *p) __ksym; s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym; struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym; +/* + * Use the following as @it when calling scx_bpf_consume_task() from whitin + * bpf_for_each() loops. + */ +#define BPF_FOR_EACH_ITER (&___it) + +/* hopefully temporary wrapper to work around BPF restriction */ +static inline bool scx_bpf_consume_task(struct bpf_iter_scx_dsq *it, + struct task_struct *p) +{ + unsigned long ptr; + bpf_probe_read_kernel(&ptr, sizeof(ptr), it); + return __scx_bpf_consume_task(ptr, p); +} + static inline __attribute__((format(printf, 1, 2))) -void ___scx_bpf_exit_format_checker(const char *fmt, ...) {} +void ___scx_bpf_bstr_format_checker(const char *fmt, ...) {} /* * Helper macro for initializing the fmt and variadic argument inputs to both * bstr exit kfuncs. Callers to this function should use ___fmt and ___param to * refer to the initialized list of inputs to the bstr kfunc. */ -#define scx_bpf_exit_preamble(fmt, args...) \ - static char ___fmt[] = fmt; \ - /* \ - * Note that __param[] must have at least one \ - * element to keep the verifier happy. \ - */ \ - unsigned long long ___param[___bpf_narg(args) ?: 1] = {}; \ - \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - ___bpf_fill(___param, args); \ - _Pragma("GCC diagnostic pop") \ +#define scx_bpf_bstr_preamble(fmt, args...) \ + static char ___fmt[] = fmt; \ + /* \ + * Note that __param[] must have at least one \ + * element to keep the verifier happy. \ + */ \ + unsigned long long ___param[___bpf_narg(args) ?: 1] = {}; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ /* * scx_bpf_exit() wraps the scx_bpf_exit_bstr() kfunc with variadic arguments @@ -87,9 +106,9 @@ void ___scx_bpf_exit_format_checker(const char *fmt, ...) {} */ #define scx_bpf_exit(code, fmt, args...) \ ({ \ - scx_bpf_exit_preamble(fmt, args) \ + scx_bpf_bstr_preamble(fmt, args) \ scx_bpf_exit_bstr(code, ___fmt, ___param, sizeof(___param)); \ - ___scx_bpf_exit_format_checker(fmt, ##args); \ + ___scx_bpf_bstr_format_checker(fmt, ##args); \ }) /* @@ -100,9 +119,20 @@ void ___scx_bpf_exit_format_checker(const char *fmt, ...) {} */ #define scx_bpf_error(fmt, args...) \ ({ \ - scx_bpf_exit_preamble(fmt, args) \ + scx_bpf_bstr_preamble(fmt, args) \ scx_bpf_error_bstr(___fmt, ___param, sizeof(___param)); \ - ___scx_bpf_exit_format_checker(fmt, ##args); \ + ___scx_bpf_bstr_format_checker(fmt, ##args); \ +}) + +/* + * scx_bpf_dump() wraps the scx_bpf_dump_bstr() kfunc with variadic arguments + * instead of an array of u64. To be used from ops.dump() and friends. + */ +#define scx_bpf_dump(fmt, args...) \ +({ \ + scx_bpf_bstr_preamble(fmt, args) \ + scx_bpf_dump_bstr(___fmt, ___param, sizeof(___param)); \ + ___scx_bpf_bstr_format_checker(fmt, ##args); \ }) #define BPF_STRUCT_OPS(name, args...) \ @@ -159,7 +189,8 @@ BPF_PROG(name, ##args) * be a pointer to the area. Use `MEMBER_VPTR(*ptr, .member)` instead of * `MEMBER_VPTR(ptr, ->member)`. */ -#define MEMBER_VPTR(base, member) (typeof((base) member) *)({ \ +#define MEMBER_VPTR(base, member) (typeof((base) member) *) \ +({ \ u64 __base = (u64)&(base); \ u64 __addr = (u64)&((base) member) - __base; \ _Static_assert(sizeof(base) >= sizeof((base) member), \ @@ -189,18 +220,19 @@ BPF_PROG(name, ##args) * size of the array to compute the max, which will result in rejection by * the verifier. */ -#define ARRAY_ELEM_PTR(arr, i, n) (typeof(arr[i]) *)({ \ - u64 __base = (u64)arr; \ - u64 __addr = (u64)&(arr[i]) - __base; \ - asm volatile ( \ - "if %0 <= %[max] goto +2\n" \ - "%0 = 0\n" \ - "goto +1\n" \ - "%0 += %1\n" \ - : "+r"(__addr) \ - : "r"(__base), \ - [max]"r"(sizeof(arr[0]) * ((n) - 1))); \ - __addr; \ +#define ARRAY_ELEM_PTR(arr, i, n) (typeof(arr[i]) *) \ +({ \ + u64 __base = (u64)arr; \ + u64 __addr = (u64)&(arr[i]) - __base; \ + asm volatile ( \ + "if %0 <= %[max] goto +2\n" \ + "%0 = 0\n" \ + "goto +1\n" \ + "%0 += %1\n" \ + : "+r"(__addr) \ + : "r"(__base), \ + [max]"r"(sizeof(arr[0]) * ((n) - 1))); \ + __addr; \ }) /* @@ -230,7 +262,7 @@ int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node, struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) __ksym; -extern void *bpf_refcount_acquire_impl(void *kptr, void *meta) __ksym; +void *bpf_refcount_acquire_impl(void *kptr, void *meta) __ksym; #define bpf_refcount_acquire(kptr) bpf_refcount_acquire_impl(kptr, NULL) /* task */ diff --git a/tools/sched_ext/include/scx/compat.bpf.h b/tools/sched_ext/include/scx/compat.bpf.h index 5da12e378be34..8fcba2505ad53 100644 --- a/tools/sched_ext/include/scx/compat.bpf.h +++ b/tools/sched_ext/include/scx/compat.bpf.h @@ -18,13 +18,15 @@ /* * %SCX_KICK_IDLE is a later addition. To support both before and after, use * %__COMPAT_SCX_KICK_IDLE which becomes 0 on kernels which don't support it. + * Users can use %SCX_KICK_IDLE directly in the future. */ #define __COMPAT_SCX_KICK_IDLE \ __COMPAT_ENUM_OR_ZERO(enum scx_kick_flags, SCX_KICK_IDLE) /* * scx_switch_all() was replaced by %SCX_OPS_SWITCH_PARTIAL. See - * %__COMPAT_SCX_OPS_SWITCH_PARTIAL in compat.h. + * %__COMPAT_SCX_OPS_SWITCH_PARTIAL in compat.h. This can be dropped in the + * future. */ void scx_bpf_switch_all(void) __ksym __weak; @@ -34,6 +36,67 @@ static inline void __COMPAT_scx_bpf_switch_all(void) scx_bpf_switch_all(); } +/* + * scx_bpf_exit() is a new addition. Fall back to scx_bpf_error() if + * unavailable. Users can use scx_bpf_exit() directly in the future. + */ +#define __COMPAT_scx_bpf_exit(code, fmt, args...) \ +({ \ + if (bpf_ksym_exists(scx_bpf_exit_bstr)) \ + scx_bpf_exit((code), fmt, args); \ + else \ + scx_bpf_error(fmt, args); \ +}) + +/* + * scx_bpf_nr_cpu_ids(), scx_bpf_get_possible/online_cpumask() are new. No good + * way to noop these kfuncs. Provide a test macro. Users can assume existence in + * the future. + */ +#define __COMPAT_HAS_CPUMASKS \ + bpf_ksym_exists(scx_bpf_nr_cpu_ids) + +/* + * cpuperf is new. The followings become noop on older kernels. Callers can be + * updated to call cpuperf kfuncs directly in the future. + */ +static inline u32 __COMPAT_scx_bpf_cpuperf_cap(s32 cpu) +{ + if (bpf_ksym_exists(scx_bpf_cpuperf_cap)) + return scx_bpf_cpuperf_cap(cpu); + else + return 1024; +} + +static inline u32 __COMPAT_scx_bpf_cpuperf_cur(s32 cpu) +{ + if (bpf_ksym_exists(scx_bpf_cpuperf_cur)) + return scx_bpf_cpuperf_cur(cpu); + else + return 1024; +} + +static inline void __COMPAT_scx_bpf_cpuperf_set(s32 cpu, u32 perf) +{ + if (bpf_ksym_exists(scx_bpf_cpuperf_set)) + return scx_bpf_cpuperf_set(cpu, perf); +} + +/* + * Iteration and scx_bpf_consume_task() are new. The following become noop on + * older kernels. The users can switch to bpf_for_each(scx_dsq) and directly + * call scx_bpf_consume_task() in the future. + */ +#define __COMPAT_DSQ_FOR_EACH(p, dsq_id, flags) \ + if (bpf_ksym_exists(bpf_iter_scx_dsq_new)) \ + bpf_for_each(scx_dsq, (p), (dsq_id), (flags)) + +static inline bool __COMPAT_scx_bpf_consume_task(struct bpf_iter_scx_dsq *it, + struct task_struct *p) +{ + return false; +} + /* * Define sched_ext_ops. This may be expanded to define multiple variants for * backward compatibility. See compat.h::SCX_OPS_LOAD/ATTACH(). diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h index e2608ad6ec5cf..b6f30e012c617 100644 --- a/tools/sched_ext/include/scx/compat.h +++ b/tools/sched_ext/include/scx/compat.h @@ -72,6 +72,12 @@ static inline bool __COMPAT_read_enum(const char *type, const char *name, u64 *v __val; \ }) +static inline bool __COMPAT_has_ksym(const char *ksym) +{ + __COMPAT_load_vmlinux_btf(); + return btf__find_by_name(__COMPAT_vmlinux_btf, ksym) >= 0; +} + static inline bool __COMPAT_struct_has_field(const char *type, const char *field) { const struct btf_type *t; @@ -104,11 +110,25 @@ static inline bool __COMPAT_struct_has_field(const char *type, const char *field * An ops flag, %SCX_OPS_SWITCH_PARTIAL, replaced scx_bpf_switch_all() which had * to be called from ops.init(). To support both before and after, use both * %__COMPAT_SCX_OPS_SWITCH_PARTIAL and %__COMPAT_scx_bpf_switch_all() defined - * in compat.bpf.h. + * in compat.bpf.h. Users can switch to directly using %SCX_OPS_SWITCH_PARTIAL + * in the future. */ #define __COMPAT_SCX_OPS_SWITCH_PARTIAL \ __COMPAT_ENUM_OR_ZERO("scx_ops_flags", "SCX_OPS_SWITCH_PARTIAL") +/* + * scx_bpf_nr_cpu_ids(), scx_bpf_get_possible/online_cpumask() are new. Users + * will be able to assume existence in the future. + */ +#define __COMPAT_HAS_CPUMASKS \ + __COMPAT_has_ksym("scx_bpf_nr_cpu_ids") + +/* + * DSQ iterator is new. Users will be able to assume existence in the future. + */ +#define __COMPAT_HAS_DSQ_ITER \ + __COMPAT_has_ksym("bpf_iter_scx_dsq_new") + static inline long scx_hotplug_seq(void) { int fd; @@ -137,15 +157,10 @@ static inline long scx_hotplug_seq(void) * and attach it, backward compatibility is automatically maintained where * reasonable. * - * The following values were added in newer kernels: - * - * - sched_ext_ops.exit_dump_len - * o If nonzero and running on an older kernel, the value is set to zero - * and a warning is emitted - * - * - sched_ext_ops.hotplug_sqn - * o If nonzero and running on an older kernel, the scheduler will fail to - * load + * - ops.tick(): Ignored on older kernels with a warning. + * - ops.dump*(): Ignored on older kernels with a warning. + * - ops.exit_dump_len: Cleared to zero on older kernels with a warning. + * - ops.hotplug_seq: Ignored on older kernels. */ #define SCX_OPS_OPEN(__ops_name, __scx_name) ({ \ struct __scx_name *__skel; \ @@ -160,10 +175,24 @@ static inline long scx_hotplug_seq(void) #define SCX_OPS_LOAD(__skel, __ops_name, __scx_name, __uei_name) ({ \ UEI_SET_SIZE(__skel, __ops_name, __uei_name); \ - if (__COMPAT_struct_has_field("sched_ext_ops", "exit_dump_len") && \ + if (!__COMPAT_struct_has_field("sched_ext_ops", "exit_dump_len") && \ (__skel)->struct_ops.__ops_name->exit_dump_len) { \ fprintf(stderr, "WARNING: kernel doesn't support setting exit dump len\n"); \ - (__skel)->struct_ops.__ops_name->exit_dump_len = 0; \ + (__skel)->struct_ops.__ops_name->exit_dump_len = 0; \ + } \ + if (!__COMPAT_struct_has_field("sched_ext_ops", "tick") && \ + (__skel)->struct_ops.__ops_name->tick) { \ + fprintf(stderr, "WARNING: kernel doesn't support ops.tick()\n"); \ + (__skel)->struct_ops.__ops_name->tick = NULL; \ + } \ + if (!__COMPAT_struct_has_field("sched_ext_ops", "dump") && \ + ((__skel)->struct_ops.__ops_name->dump || \ + (__skel)->struct_ops.__ops_name->dump_cpu || \ + (__skel)->struct_ops.__ops_name->dump_task)) { \ + fprintf(stderr, "WARNING: kernel doesn't support ops.dump*()\n"); \ + (__skel)->struct_ops.__ops_name->dump = NULL; \ + (__skel)->struct_ops.__ops_name->dump_cpu = NULL; \ + (__skel)->struct_ops.__ops_name->dump_task = NULL; \ } \ SCX_BUG_ON(__scx_name##__load((__skel)), "Failed to load skel"); \ }) diff --git a/tools/sched_ext/include/scx/user_exit_info.h b/tools/sched_ext/include/scx/user_exit_info.h index 2705b81f8d2ed..2d86d01a95752 100644 --- a/tools/sched_ext/include/scx/user_exit_info.h +++ b/tools/sched_ext/include/scx/user_exit_info.h @@ -64,17 +64,6 @@ struct user_exit_info { __sync_val_compare_and_swap(&(__skel)->data->__uei_name.kind, -1, -1); \ }) -#define UEI_KIND(__skel, __uei_name) ((__skel)->data->__uei_name.kind) - -#define ECODE_USER_MASK ((1LLU << 32) - 1) -#define ECODE_SYS_ACT_MASK (((1LLU << 48) - 1) ^ ECODE_USER_MASK) -#define ECODE_SYS_RSN_MASK (~0LLU ^ (ECODE_SYS_ACT_MASK | ECODE_USER_MASK)) - -#define UEI_ECODE(__skel, __uei_name) (__skel)->data->__uei_name.exit_code -#define UEI_ECODE_SYS_ACT(__skel, __uei_name) (UEI_ECODE(__skel, __uei_name) & ECODE_SYS_ACT_MASK) -#define UEI_ECODE_SYS_RSN(__skel, __uei_name) (UEI_ECODE(__skel, __uei_name) & ECODE_SYS_RSN_MASK) -#define UEI_ECODE_USER(__skel, __uei_name) (UEI_ECODE(__skel, __uei_name) & ECODE_USER_MASK) - #define UEI_REPORT(__skel, __uei_name) ({ \ struct user_exit_info *__uei = &(__skel)->data->__uei_name; \ char *__uei_dump = (__skel)->data_##__uei_name##_dump->__uei_name##_dump; \ @@ -88,16 +77,35 @@ struct user_exit_info { if (__uei->msg[0] != '\0') \ fprintf(stderr, " (%s)", __uei->msg); \ fputs("\n", stderr); \ + __uei->exit_code; \ }) -#define UEI_RESET(__skel, __uei_name) ({ \ - struct user_exit_info *__uei = &(__skel)->data->__uei_name; \ - char *__uei_dump = (__skel)->data_##__uei_name##_dump->__uei_name##_dump; \ - size_t __uei_dump_len = (__skel)->rodata->__uei_name##_dump_len; \ - \ - memset(__uei, 0, sizeof(struct user_exit_info)); \ - memset(__uei_dump, 0, __uei_dump_len); \ -}) +/* + * We can't import vmlinux.h while compiling user C code. Let's duplicate + * scx_exit_code definition. + */ +enum scx_exit_code { + /* Reasons */ + SCX_ECODE_RSN_HOTPLUG = 1LLU << 32, + + /* Actions */ + SCX_ECODE_ACT_RESTART = 1LLU << 48, +}; + +enum uei_ecode_mask { + UEI_ECODE_USER_MASK = ((1LLU << 32) - 1), + UEI_ECODE_SYS_RSN_MASK = ((1LLU << 16) - 1) << 32, + UEI_ECODE_SYS_ACT_MASK = ((1LLU << 16) - 1) << 48, +}; + +/* + * These macro interpret the ecode returned from UEI_REPORT(). + */ +#define UEI_ECODE_USER(__ecode) ((__ecode) & UEI_ECODE_USER_MASK) +#define UEI_ECODE_SYS_RSN(__ecode) ((__ecode) & UEI_ECODE_SYS_RSN_MASK) +#define UEI_ECODE_SYS_ACT(__ecode) ((__ecode) & UEI_ECODE_SYS_ACT_MASK) + +#define UEI_ECODE_RESTART(__ecode) (UEI_ECODE_SYS_ACT((__ecode)) == SCX_ECODE_ACT_RESTART) #endif /* __bpf__ */ #endif /* __USER_EXIT_INFO_H */ diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index bc209ad6a6235..df692dc0ccb10 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -24,10 +24,19 @@ const char help_fmt[] = "\n" " -s SLICE_US Override slice duration\n" " -c CPU Override the central CPU (default: 0)\n" +" -v Print libbpf debug messages\n" " -h Display this help and exit\n"; +static bool verbose; static volatile int exit_req; +static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !verbose) + return 0; + return vfprintf(stderr, format, args); +} + static void sigint_handler(int dummy) { exit_req = 1; @@ -37,22 +46,20 @@ int main(int argc, char **argv) { struct scx_central *skel; struct bpf_link *link; - __u64 seq = 0; + __u64 seq = 0, ecode; __s32 opt; cpu_set_t *cpuset; + libbpf_set_print(libbpf_print_fn); signal(SIGINT, sigint_handler); signal(SIGTERM, sigint_handler); - - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - - skel = scx_central__open(); - SCX_BUG_ON(!skel, "Failed to open skel"); +restart: + skel = SCX_OPS_OPEN(central_ops, scx_central); skel->rodata->central_cpu = 0; skel->rodata->nr_cpu_ids = libbpf_num_possible_cpus(); - while ((opt = getopt(argc, argv, "s:c:ph")) != -1) { + while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) { switch (opt) { case 's': skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000; @@ -60,6 +67,9 @@ int main(int argc, char **argv) case 'c': skel->rodata->central_cpu = strtoul(optarg, NULL, 0); break; + case 'v': + verbose = true; + break; default: fprintf(stderr, help_fmt, basename(argv[0])); return opt != 'h'; @@ -116,7 +126,10 @@ int main(int argc, char **argv) } bpf_link__destroy(link); - UEI_REPORT(skel, uei); + ecode = UEI_REPORT(skel, uei); scx_central__destroy(skel); + + if (UEI_ECODE_RESTART(ecode)) + goto restart; return 0; } diff --git a/tools/sched_ext/scx_flatcg.c b/tools/sched_ext/scx_flatcg.c index b6f0184f106d2..1143d5eb389af 100644 --- a/tools/sched_ext/scx_flatcg.c +++ b/tools/sched_ext/scx_flatcg.c @@ -26,15 +26,24 @@ const char help_fmt[] = "\n" "See the top-level comment in .bpf.c for more details.\n" "\n" -"Usage: %s [-s SLICE_US] [-i INTERVAL] [-f]\n" +"Usage: %s [-s SLICE_US] [-i INTERVAL] [-f] [-v]\n" "\n" " -s SLICE_US Override slice duration\n" " -i INTERVAL Report interval\n" " -f Use FIFO scheduling instead of weighted vtime scheduling\n" +" -v Print libbpf debug messages\n" " -h Display this help and exit\n"; +static bool verbose; static volatile int exit_req; +static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !verbose) + return 0; + return vfprintf(stderr, format, args); +} + static void sigint_handler(int dummy) { exit_req = 1; @@ -119,18 +128,17 @@ int main(int argc, char **argv) __u64 last_stats[FCG_NR_STATS] = {}; unsigned long seq = 0; __s32 opt; + __u64 ecode; + libbpf_set_print(libbpf_print_fn); signal(SIGINT, sigint_handler); signal(SIGTERM, sigint_handler); - - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - - skel = scx_flatcg__open(); - SCX_BUG_ON(!skel, "Failed to open skel"); +restart: + skel = SCX_OPS_OPEN(flatcg_ops, scx_flatcg); skel->rodata->nr_cpus = libbpf_num_possible_cpus(); - while ((opt = getopt(argc, argv, "s:i:dfph")) != -1) { + while ((opt = getopt(argc, argv, "s:i:dfvh")) != -1) { double v; switch (opt) { @@ -149,6 +157,9 @@ int main(int argc, char **argv) case 'f': skel->rodata->fifo_sched = true; break; + case 'v': + verbose = true; + break; case 'h': default: fprintf(stderr, help_fmt, basename(argv[0])); @@ -213,7 +224,10 @@ int main(int argc, char **argv) } bpf_link__destroy(link); - UEI_REPORT(skel, uei); + ecode = UEI_REPORT(skel, uei); scx_flatcg__destroy(skel); + + if (UEI_ECODE_RESTART(ecode)) + goto restart; return 0; } diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c index dbca79a4d4237..2faff64306ba5 100644 --- a/tools/sched_ext/scx_qmap.bpf.c +++ b/tools/sched_ext/scx_qmap.bpf.c @@ -23,8 +23,12 @@ * Copyright (c) 2022 David Vernet */ #include +#include -#define ONE_SEC_IN_NS 1000000000 +enum consts { + ONE_SEC_IN_NS = 1000000000, + SHARED_DSQ = 0, +}; char _license[] SEC("license") = "GPL"; @@ -32,7 +36,11 @@ const volatile u64 slice_ns = SCX_SLICE_DFL; const volatile u32 stall_user_nth; const volatile u32 stall_kernel_nth; const volatile u32 dsp_inf_loop_after; +const volatile u32 dsp_batch; +const volatile bool print_shared_dsq; +const volatile char exp_prefix[17]; const volatile s32 disallow_tgid; +const volatile bool suppress_dump; const volatile bool switch_partial; u32 test_error_cnt; @@ -116,7 +124,7 @@ struct { /* Statistics */ u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_dequeued; -u64 nr_core_sched_execed; +u64 nr_core_sched_execed, nr_expedited; u32 cpuperf_min, cpuperf_avg, cpuperf_max; u32 cpuperf_target_min, cpuperf_target_avg, cpuperf_target_max; @@ -211,7 +219,7 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags) if (enq_flags & SCX_ENQ_REENQ) { s32 cpu; - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, 0, enq_flags); + scx_bpf_dispatch(p, SHARED_DSQ, 0, enq_flags); cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0); if (cpu >= 0) scx_bpf_kick_cpu(cpu, __COMPAT_SCX_KICK_IDLE); @@ -226,7 +234,7 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags) /* Queue on the selected FIFO. If the FIFO overflows, punt to global. */ if (bpf_map_push_elem(ring, &pid, 0)) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, slice_ns, enq_flags); + scx_bpf_dispatch(p, SHARED_DSQ, slice_ns, enq_flags); return; } @@ -255,16 +263,49 @@ static void update_core_sched_head_seq(struct task_struct *p) scx_bpf_error("task_ctx lookup failed"); } +static bool consume_shared_dsq(void) +{ + struct task_struct *p; + bool consumed; + + if (exp_prefix[0] == '\0') + return scx_bpf_consume(SHARED_DSQ); + + /* + * To demonstrate the use of scx_bpf_consume_task(), implement silly + * selective priority boosting mechanism by scanning SHARED_DSQ looking + * for matching comms and consume them first. This makes difference only + * when dsp_batch is larger than 1. + */ + consumed = false; + __COMPAT_DSQ_FOR_EACH(p, SHARED_DSQ, 0) { + char comm[sizeof(exp_prefix)]; + + memcpy(comm, p->comm, sizeof(exp_prefix) - 1); + + if (!bpf_strncmp(comm, sizeof(exp_prefix), + (const char *)exp_prefix) && + __COMPAT_scx_bpf_consume_task(BPF_FOR_EACH_ITER, p)) { + consumed = true; + __sync_fetch_and_add(&nr_expedited, 1); + } + } + + return consumed || scx_bpf_consume(SHARED_DSQ); +} + void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) { + struct task_struct *p; struct cpu_ctx *cpuc; - u32 zero = 0; + u32 zero = 0, batch = dsp_batch ?: 1; void *fifo; s32 i, pid; - if (dsp_inf_loop_after && nr_dispatched > dsp_inf_loop_after) { - struct task_struct *p; + if (consume_shared_dsq()) + return; + if (dsp_inf_loop_after && nr_dispatched > dsp_inf_loop_after) { /* * PID 2 should be kthreadd which should mostly be idle and off * the scheduler. Let's keep dispatching it to force the kernel @@ -272,7 +313,7 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) */ p = bpf_task_from_pid(2); if (p) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, slice_ns, 0); + scx_bpf_dispatch(p, SCX_DSQ_LOCAL, slice_ns, 0); bpf_task_release(p); return; } @@ -289,7 +330,6 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) cpuc->dsp_idx = (cpuc->dsp_idx + 1) % 5; cpuc->dsp_cnt = 1 << cpuc->dsp_idx; } - cpuc->dsp_cnt--; fifo = bpf_map_lookup_elem(&queue_arr, &cpuc->dsp_idx); if (!fifo) { @@ -298,17 +338,26 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev) } /* Dispatch or advance. */ - if (!bpf_map_pop_elem(fifo, &pid)) { - struct task_struct *p; + bpf_repeat(BPF_MAX_LOOPS) { + if (bpf_map_pop_elem(fifo, &pid)) + break; p = bpf_task_from_pid(pid); - if (p) { - update_core_sched_head_seq(p); - __sync_fetch_and_add(&nr_dispatched, 1); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, slice_ns, 0); - bpf_task_release(p); + if (!p) + continue; + + update_core_sched_head_seq(p); + __sync_fetch_and_add(&nr_dispatched, 1); + scx_bpf_dispatch(p, SHARED_DSQ, slice_ns, 0); + bpf_task_release(p); + batch--; + cpuc->dsp_cnt--; + if (!batch || !scx_bpf_dispatch_nr_slots()) { + consume_shared_dsq(); return; } + if (!cpuc->dsp_cnt) + break; } cpuc->dsp_cnt = 0; @@ -414,6 +463,57 @@ s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p, return -ENOMEM; } +void BPF_STRUCT_OPS(qmap_dump, struct scx_dump_ctx *dctx) +{ + s32 i, pid; + + if (suppress_dump) + return; + + bpf_for(i, 0, 5) { + void *fifo; + + if (!(fifo = bpf_map_lookup_elem(&queue_arr, &i))) + return; + + scx_bpf_dump("QMAP FIFO[%d]:", i); + bpf_repeat(4096) { + if (bpf_map_pop_elem(fifo, &pid)) + break; + scx_bpf_dump(" %d", pid); + } + scx_bpf_dump("\n"); + } +} + +void BPF_STRUCT_OPS(qmap_dump_cpu, struct scx_dump_ctx *dctx, s32 cpu, bool idle) +{ + u32 zero = 0; + struct cpu_ctx *cpuc; + + if (suppress_dump || idle) + return; + if (!(cpuc = bpf_map_lookup_percpu_elem(&cpu_ctx_stor, &zero, cpu))) + return; + + scx_bpf_dump("QMAP: dsp_idx=%llu dsp_cnt=%llu avg_weight=%u cpuperf_target=%u", + cpuc->dsp_idx, cpuc->dsp_cnt, cpuc->avg_weight, + cpuc->cpuperf_target); +} + +void BPF_STRUCT_OPS(qmap_dump_task, struct scx_dump_ctx *dctx, struct task_struct *p) +{ + struct task_ctx *taskc; + + if (suppress_dump) + return; + if (!(taskc = bpf_task_storage_get(&task_ctx_stor, p, 0, 0))) + return; + + scx_bpf_dump("QMAP: force_local=%d core_sched_seq=%llu", + taskc->force_local, taskc->core_sched_seq); +} + /* * Print out the online and possible CPU map using bpf_printk() as a * demonstration of using the cpumask kfuncs and ops.cpu_on/offline(). @@ -425,6 +525,9 @@ static void print_cpus(void) char buf[128] = "", *p; int idx; + if (!__COMPAT_HAS_CPUMASKS) + return; + possible = scx_bpf_get_possible_cpumask(); online = scx_bpf_get_online_cpumask(); @@ -467,7 +570,7 @@ void BPF_STRUCT_OPS(qmap_cpu_offline, s32 cpu) print_cpus(); } -struct cpu_mon_timer { +struct monitor_timer { struct bpf_timer timer; }; @@ -475,25 +578,26 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 1); __type(key, u32); - __type(value, struct cpu_mon_timer); + __type(value, struct monitor_timer); } central_timer SEC(".maps"); /* * Print out the min, avg and max performance levels of CPUs every second to * demonstrate the cpuperf interface. */ -static int cpu_mon_timerfn(void *map, int *key, struct bpf_timer *timer) +static void monitor_cpuperf(void) { - u32 zero = 0; - u32 nr_cpu_ids = scx_bpf_nr_cpu_ids(); + u32 zero = 0, nr_cpu_ids; u64 cap_sum = 0, cur_sum = 0, cur_min = SCX_CPUPERF_ONE, cur_max = 0; u64 target_sum = 0, target_min = SCX_CPUPERF_ONE, target_max = 0; const struct cpumask *online; int i, nr_online_cpus = 0; + if (!__COMPAT_HAS_CPUMASKS) + return; + + nr_cpu_ids = scx_bpf_nr_cpu_ids(); online = scx_bpf_get_online_cpumask(); - if (!online) - return -ENOMEM; bpf_for(i, 0, nr_cpu_ids) { struct cpu_ctx *cpuc; @@ -537,29 +641,63 @@ static int cpu_mon_timerfn(void *map, int *key, struct bpf_timer *timer) cpuperf_target_min = target_min; cpuperf_target_avg = target_sum / nr_online_cpus; cpuperf_target_max = target_max; - - bpf_timer_start(timer, ONE_SEC_IN_NS, 0); out: scx_bpf_put_cpumask(online); +} + +/* + * Dump the currently queued tasks in the shared DSQ to demonstrate the usage of + * scx_bpf_dsq_nr_queued() and DSQ iterator. Raise the dispatch batch count to + * see meaningful dumps in the trace pipe. + */ +static void dump_shared_dsq(void) +{ + struct task_struct *p; + s32 nr; + + if (!(nr = scx_bpf_dsq_nr_queued(SHARED_DSQ))) + return; + + bpf_printk("Dumping %d tasks in SHARED_DSQ in reverse order", nr); + + bpf_rcu_read_lock(); + __COMPAT_DSQ_FOR_EACH(p, SHARED_DSQ, SCX_DSQ_ITER_REV) + bpf_printk("%s[%d]", p->comm, p->pid); + bpf_rcu_read_unlock(); +} + +static int monitor_timerfn(void *map, int *key, struct bpf_timer *timer) +{ + monitor_cpuperf(); + + if (print_shared_dsq) + dump_shared_dsq(); + + bpf_timer_start(timer, ONE_SEC_IN_NS, 0); return 0; } -s32 BPF_STRUCT_OPS(qmap_init) +s32 BPF_STRUCT_OPS_SLEEPABLE(qmap_init) { u32 key = 0; struct bpf_timer *timer; + s32 ret; if (!switch_partial) __COMPAT_scx_bpf_switch_all(); print_cpus(); + ret = scx_bpf_create_dsq(SHARED_DSQ, -1); + if (ret) + return ret; + timer = bpf_map_lookup_elem(¢ral_timer, &key); if (!timer) return -ESRCH; bpf_timer_init(timer, ¢ral_timer, CLOCK_MONOTONIC); - bpf_timer_set_callback(timer, cpu_mon_timerfn); + bpf_timer_set_callback(timer, monitor_timerfn); return bpf_timer_start(timer, ONE_SEC_IN_NS, 0); } @@ -578,6 +716,9 @@ SCX_OPS_DEFINE(qmap_ops, .core_sched_before = (void *)qmap_core_sched_before, .cpu_release = (void *)qmap_cpu_release, .init_task = (void *)qmap_init_task, + .dump = (void *)qmap_dump, + .dump_cpu = (void *)qmap_dump_cpu, + .dump_task = (void *)qmap_dump_task, .cpu_online = (void *)qmap_cpu_online, .cpu_offline = (void *)qmap_cpu_offline, .init = (void *)qmap_init, diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c index 5cadc2e0b32db..91a2c294a0ac8 100644 --- a/tools/sched_ext/scx_qmap.c +++ b/tools/sched_ext/scx_qmap.c @@ -19,21 +19,35 @@ const char help_fmt[] = "\n" "See the top-level comment in .bpf.c for more details.\n" "\n" -"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-d PID]\n" -" [-D LEN] [-p]\n" +"Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n" +" [-P] [-E PREFIX] [-d PID] [-D LEN] [-p] [-v]\n" "\n" " -s SLICE_US Override slice duration\n" " -e COUNT Trigger scx_bpf_error() after COUNT enqueues\n" " -t COUNT Stall every COUNT'th user thread\n" " -T COUNT Stall every COUNT'th kernel thread\n" " -l COUNT Trigger dispatch infinite looping after COUNT dispatches\n" +" -b COUNT Dispatch upto COUNT tasks together\n" +" -P Print out DSQ content to trace_pipe every second, use with -b\n" +" -E PREFIX Expedite consumption of threads w/ matching comm, use with -b\n" +" (e.g. match shell on a loaded system)\n" " -d PID Disallow a process from switching into SCHED_EXT (-1 for self)\n" " -D LEN Set scx_exit_info.dump buffer length\n" +" -S Suppress qmap-specific debug dump\n" " -p Switch only tasks on SCHED_EXT policy intead of all\n" +" -v Print libbpf debug messages\n" " -h Display this help and exit\n"; +static bool verbose; static volatile int exit_req; +static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !verbose) + return 0; + return vfprintf(stderr, format, args); +} + static void sigint_handler(int dummy) { exit_req = 1; @@ -45,15 +59,13 @@ int main(int argc, char **argv) struct bpf_link *link; int opt; + libbpf_set_print(libbpf_print_fn); signal(SIGINT, sigint_handler); signal(SIGTERM, sigint_handler); - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + skel = SCX_OPS_OPEN(qmap_ops, scx_qmap); - skel = scx_qmap__open(); - SCX_BUG_ON(!skel, "Failed to open skel"); - - while ((opt = getopt(argc, argv, "s:e:t:T:l:d:D:ph")) != -1) { + while ((opt = getopt(argc, argv, "s:e:t:T:l:b:PE:d:D:Spvh")) != -1) { switch (opt) { case 's': skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000; @@ -70,6 +82,16 @@ int main(int argc, char **argv) case 'l': skel->rodata->dsp_inf_loop_after = strtoul(optarg, NULL, 0); break; + case 'b': + skel->rodata->dsp_batch = strtoul(optarg, NULL, 0); + break; + case 'P': + skel->rodata->print_shared_dsq = true; + break; + case 'E': + strncpy(skel->rodata->exp_prefix, optarg, + sizeof(skel->rodata->exp_prefix) - 1); + break; case 'd': skel->rodata->disallow_tgid = strtol(optarg, NULL, 0); if (skel->rodata->disallow_tgid < 0) @@ -78,16 +100,26 @@ int main(int argc, char **argv) case 'D': skel->struct_ops.qmap_ops->exit_dump_len = strtoul(optarg, NULL, 0); break; + case 'S': + skel->rodata->suppress_dump = true; + break; case 'p': skel->rodata->switch_partial = true; skel->struct_ops.qmap_ops->flags |= __COMPAT_SCX_OPS_SWITCH_PARTIAL; break; + case 'v': + verbose = true; + break; default: fprintf(stderr, help_fmt, basename(argv[0])); return opt != 'h'; } } + if (!__COMPAT_HAS_DSQ_ITER && + (skel->rodata->print_shared_dsq || strlen(skel->rodata->exp_prefix))) + fprintf(stderr, "kernel doesn't support DSQ iteration\n"); + SCX_OPS_LOAD(skel, qmap_ops, scx_qmap, uei); link = SCX_OPS_ATTACH(skel, qmap_ops); @@ -95,17 +127,18 @@ int main(int argc, char **argv) long nr_enqueued = skel->bss->nr_enqueued; long nr_dispatched = skel->bss->nr_dispatched; - printf("stats : enq=%lu dsp=%lu delta=%ld reenq=%" PRIu64 " deq=%" PRIu64 " core=%" PRIu64 "\n", + printf("stats : enq=%lu dsp=%lu delta=%ld reenq=%"PRIu64" deq=%"PRIu64" core=%"PRIu64" exp=%"PRIu64"\n", nr_enqueued, nr_dispatched, nr_enqueued - nr_dispatched, skel->bss->nr_reenqueued, skel->bss->nr_dequeued, - skel->bss->nr_core_sched_execed); - printf("cpuperf: cur min/avg/max=%u/%u/%u target min/avg/max=%u/%u/%u\n", - skel->bss->cpuperf_min, - skel->bss->cpuperf_avg, - skel->bss->cpuperf_max, - skel->bss->cpuperf_target_min, - skel->bss->cpuperf_target_avg, - skel->bss->cpuperf_target_max); + skel->bss->nr_core_sched_execed, skel->bss->nr_expedited); + if (__COMPAT_has_ksym("scx_bpf_cpuperf_cur")) + printf("cpuperf: cur min/avg/max=%u/%u/%u target min/avg/max=%u/%u/%u\n", + skel->bss->cpuperf_min, + skel->bss->cpuperf_avg, + skel->bss->cpuperf_max, + skel->bss->cpuperf_target_min, + skel->bss->cpuperf_target_avg, + skel->bss->cpuperf_target_max); fflush(stdout); sleep(1); } @@ -113,5 +146,9 @@ int main(int argc, char **argv) bpf_link__destroy(link); UEI_REPORT(skel, uei); scx_qmap__destroy(skel); + /* + * scx_qmap implements ops.cpu_on/offline() and doesn't need to restart + * on CPU hotplug events. + */ return 0; } diff --git a/tools/sched_ext/scx_simple.c b/tools/sched_ext/scx_simple.c index 006a2a5f35cc6..b88c058090b6c 100644 --- a/tools/sched_ext/scx_simple.c +++ b/tools/sched_ext/scx_simple.c @@ -17,13 +17,22 @@ const char help_fmt[] = "\n" "See the top-level comment in .bpf.c for more details.\n" "\n" -"Usage: %s [-f]\n" +"Usage: %s [-f] [-v]\n" "\n" " -f Use FIFO scheduling instead of weighted vtime scheduling\n" +" -v Print libbpf debug messages\n" " -h Display this help and exit\n"; +static bool verbose; static volatile int exit_req; +static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !verbose) + return 0; + return vfprintf(stderr, format, args); +} + static void sigint_handler(int simple) { exit_req = 1; @@ -54,20 +63,22 @@ int main(int argc, char **argv) struct scx_simple *skel; struct bpf_link *link; __u32 opt; + __u64 ecode; + libbpf_set_print(libbpf_print_fn); signal(SIGINT, sigint_handler); signal(SIGTERM, sigint_handler); +restart: + skel = SCX_OPS_OPEN(simple_ops, scx_simple); - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - - skel = scx_simple__open(); - SCX_BUG_ON(!skel, "Failed to open skel"); - - while ((opt = getopt(argc, argv, "fh")) != -1) { + while ((opt = getopt(argc, argv, "fvh")) != -1) { switch (opt) { case 'f': skel->rodata->fifo_sched = true; break; + case 'v': + verbose = true; + break; default: fprintf(stderr, help_fmt, basename(argv[0])); return opt != 'h'; @@ -87,7 +98,10 @@ int main(int argc, char **argv) } bpf_link__destroy(link); - UEI_REPORT(skel, uei); + ecode = UEI_REPORT(skel, uei); scx_simple__destroy(skel); + + if (UEI_ECODE_RESTART(ecode)) + goto restart; return 0; } diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 61c69297e7978..3482248aa3442 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -1001,6 +1001,7 @@ static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port) 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, @@ -1020,6 +1021,12 @@ static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port) 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 39ad96a18123f..edcd26106557b 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 @@ __weak noinline struct file *bpf_testmod_return_ptr(int arg) 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/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index ba3ddeda24bf5..d98702b6955df 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -56,7 +56,6 @@ #include #include #include -#include #include #include #include @@ -1159,7 +1158,7 @@ void __run_test(struct __fixture_metadata *f, struct __test_metadata *t) { struct __test_xfail *xfail; - char test_name[LINE_MAX]; + char *test_name; const char *diagnostic; /* reset test struct */ @@ -1167,8 +1166,12 @@ void __run_test(struct __fixture_metadata *f, 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); @@ -1206,6 +1209,7 @@ void __run_test(struct __fixture_metadata *f, ksft_test_result_code(t->exit_code, test_name, 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 eef816b80993f..ca917c71ff602 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_init.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c @@ -84,6 +84,18 @@ static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, 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 @@ static void test_vcpus_then_vgic(uint32_t gic_dev_type) 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 @@ void run_tests(uint32_t gic_dev_type) 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/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c index 200bedcdc32e9..1e01d3ddc11c5 100644 --- a/tools/testing/selftests/mm/mdwe_test.c +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -7,6 +7,7 @@ #include #include +#define _GNU_SOURCE #include #include #include diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 374a308174d2b..48dc151f8fca8 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -54,7 +54,6 @@ int test_nr; 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 @@ void pkey_setup_shadow(void) 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 @@ int main(void) 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 c2c542fe7b17b..4bdb3a0c7a606 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -385,6 +385,7 @@ CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 0 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 @@ if [ -x ./protection_keys_64 ] 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 6c988bd2f3356..d3c7f5fb3e7b7 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 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, char **addr) { size_t i; - int dummy; + int __attribute__((unused)) dummy = 0; srand(time(NULL)); diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c index c537d52fafc58..a40541bb7c7de 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 e3fccb390c4dc..f3de970c32227 100644 --- a/tools/testing/selftests/riscv/hwprobe/hwprobe.h +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h @@ -4,6 +4,16 @@ #include #include +#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/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c index ce23d797a6bb1..87bf220b1bcee 100644 --- a/tools/testing/selftests/sched_ext/hotplug.c +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -83,8 +83,8 @@ static enum scx_test_status test_hotplug(bool onlining, bool cbs_defined) while (!UEI_EXITED(skel, uei)) sched_yield(); - SCX_EQ(UEI_KIND(skel, uei), kind); - SCX_EQ(UEI_ECODE(skel, uei), code); + SCX_EQ(skel->data->uei.kind, kind); + SCX_EQ(UEI_REPORT(skel, uei), code); if (!onlining) toggle_online_status(1); @@ -126,8 +126,8 @@ static enum scx_test_status test_hotplug_attach(void) kind = SCX_KIND_VAL(SCX_EXIT_UNREG_KERN); code = SCX_ECODE_VAL(SCX_ECODE_ACT_RESTART) | SCX_ECODE_VAL(SCX_ECODE_RSN_HOTPLUG); - SCX_EQ(UEI_KIND(skel, uei), kind); - SCX_EQ(UEI_ECODE(skel, uei), code); + SCX_EQ(skel->data->uei.kind, kind); + SCX_EQ(UEI_REPORT(skel, uei), code); bpf_link__destroy(link); hotplug__destroy(skel); diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index b5d592d4099e8..d975a67673299 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 @@ static void handle_sigsys(int sig, siginfo_t *info, void *ucontext) /* 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)