diff options
737 files changed, 11693 insertions, 5318 deletions
@@ -38,6 +38,16 @@ Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com> Alexei Starovoitov <ast@kernel.org> <ast@fb.com> Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com> Alexey Makhalov <alexey.amakhalov@broadcom.com> <amakhalov@vmware.com> +Alex Elder <elder@kernel.org> +Alex Elder <elder@kernel.org> <aelder@sgi.com> +Alex Elder <elder@kernel.org> <alex.elder@linaro.org> +Alex Elder <elder@kernel.org> <alex.elder@linary.org> +Alex Elder <elder@kernel.org> <elder@dreamhost.com> +Alex Elder <elder@kernel.org> <elder@dreawmhost.com> +Alex Elder <elder@kernel.org> <elder@ieee.org> +Alex Elder <elder@kernel.org> <elder@inktank.com> +Alex Elder <elder@kernel.org> <elder@linaro.org> +Alex Elder <elder@kernel.org> <elder@newdream.net> Alex Hung <alexhung@gmail.com> <alex.hung@canonical.com> Alex Shi <alexs@kernel.org> <alex.shi@intel.com> Alex Shi <alexs@kernel.org> <alex.shi@linaro.org> @@ -98,6 +108,8 @@ Ben Widawsky <bwidawsk@kernel.org> <ben@bwidawsk.net> Ben Widawsky <bwidawsk@kernel.org> <ben.widawsky@intel.com> Ben Widawsky <bwidawsk@kernel.org> <benjamin.widawsky@intel.com> Benjamin Poirier <benjamin.poirier@gmail.com> <bpoirier@suse.de> +Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@gmail.com> +Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@redhat.com> Bjorn Andersson <andersson@kernel.org> <bjorn@kryo.se> Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@linaro.org> Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@sonymobile.com> @@ -446,7 +458,8 @@ Mythri P K <mythripk@ti.com> Nadav Amit <nadav.amit@gmail.com> <namit@vmware.com> Nadav Amit <nadav.amit@gmail.com> <namit@cs.technion.ac.il> Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com> -Naoya Horiguchi <naoya.horiguchi@nec.com> <n-horiguchi@ah.jp.nec.com> +Naoya Horiguchi <nao.horiguchi@gmail.com> <n-horiguchi@ah.jp.nec.com> +Naoya Horiguchi <nao.horiguchi@gmail.com> <naoya.horiguchi@nec.com> Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com> Neeraj Upadhyay <quic_neeraju@quicinc.com> <neeraju@codeaurora.org> Neil Armstrong <neil.armstrong@linaro.org> <narmstrong@baylibre.com> @@ -524,6 +537,7 @@ Rémi Denis-Courmont <rdenis@simphalempin.com> Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com> Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org> Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com> +Richard Genoud <richard.genoud@bootlin.com> <richard.genoud@gmail.com> Richard Leitner <richard.leitner@linux.dev> <dev@g0hl1n.net> Richard Leitner <richard.leitner@linux.dev> <me@g0hl1n.net> Richard Leitner <richard.leitner@linux.dev> <richard.leitner@skidata.com> @@ -3146,6 +3146,10 @@ S: Triftstra=DFe 55 S: 13353 Berlin S: Germany +N: Gustavo Pimental +E: gustavo.pimentel@synopsys.com +D: PCI driver for Synopsys DesignWare + N: Emanuel Pirker E: epirker@edu.uni-klu.ac.at D: AIC5800 IEEE 1394, RAW I/O on 1394 diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index cce768afec6b..25a04cda4c2c 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -138,11 +138,10 @@ associated with the source address of the indirect branch. Specifically, the BHB might be shared across privilege levels even in the presence of Enhanced IBRS. -Currently the only known real-world BHB attack vector is via -unprivileged eBPF. Therefore, it's highly recommended to not enable -unprivileged eBPF, especially when eIBRS is used (without retpolines). -For a full mitigation against BHB attacks, it's recommended to use -retpolines (or eIBRS combined with retpolines). +Previously the only known real-world BHB attack vector was via unprivileged +eBPF. Further research has found attacks that don't require unprivileged eBPF. +For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or +use the BHB clearing sequence. Attack scenarios ---------------- @@ -430,6 +429,23 @@ The possible values in this file are: 'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB =========================== ======================================================= + - Branch History Injection (BHI) protection status: + +.. list-table:: + + * - BHI: Not affected + - System is not affected + * - BHI: Retpoline + - System is protected by retpoline + * - BHI: BHI_DIS_S + - System is protected by BHI_DIS_S + * - BHI: SW loop, KVM SW loop + - System is protected by software clearing sequence + * - BHI: Vulnerable + - System is vulnerable to BHI + * - BHI: Vulnerable, KVM: SW loop + - System is vulnerable; KVM is protected by software clearing sequence + Full mitigation might require a microcode update from the CPU vendor. When the necessary microcode is not available, the kernel will report vulnerability. @@ -484,7 +500,11 @@ Spectre variant 2 Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at boot, by setting the IBRS bit, and they're automatically protected against - Spectre v2 variant attacks. + some Spectre v2 variant attacks. The BHB can still influence the choice of + indirect branch predictor entry, and although branch predictor entries are + isolated between modes when eIBRS is enabled, the BHB itself is not isolated + between modes. Systems which support BHI_DIS_S will set it to protect against + BHI attacks. On Intel's enhanced IBRS systems, this includes cross-thread branch target injections on SMT systems (STIBP). In other words, Intel eIBRS enables @@ -638,6 +658,18 @@ kernel command line. spectre_v2=off. Spectre variant 1 mitigations cannot be disabled. + spectre_bhi= + + [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. This setting affects the deployment + of the HW BHI control and the SW BHB clearing sequence. + + on + (default) Enable the HW or SW mitigation as + needed. + off + Disable the mitigation. + For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt Mitigation selection guide diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 623fce7d5fcd..902ecd92a29f 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3444,6 +3444,7 @@ retbleed=off [X86] spec_rstack_overflow=off [X86] spec_store_bypass_disable=off [X86,PPC] + spectre_bhi=off [X86] spectre_v2_user=off [X86] srbds=off [X86,INTEL] ssbd=force-off [ARM64] @@ -6063,6 +6064,15 @@ sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/admin-guide/laptops/sonypi.rst + spectre_bhi= [X86] Control mitigation of Branch History Injection + (BHI) vulnerability. This setting affects the + deployment of the HW BHI control and the SW BHB + clearing sequence. + + on - (default) Enable the HW or SW mitigation + as needed. + off - Disable the mitigation. + spectre_v2= [X86,EARLY] Control mitigation of Spectre variant 2 (indirect branch speculation) vulnerability. The default operation protects the kernel from diff --git a/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst b/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst index d3504826f401..c389d4fd7599 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<introguide_bissbs>`" *below. It utilizes +over to the* ':ref:`step-by-step guide <introguide_bissbs>`' *below. It utilizes the same commands as this section while describing them in brief fashion. The steps are nevertheless easy to follow and together with accompanying entries in a reference section mention many alternatives, pitfalls, and additional @@ -38,8 +38,8 @@ 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.<introprep_bissbs>` + :ref:`Preparations: set up everything to build your own kernels <introprep_bissbs>`. - :ref:`Segment 1: try to reproduce the problem with the latest codebase.<introlatestcheck_bissbs>` + :ref:`Segment 1: try to reproduce the problem with the latest codebase <introlatestcheck_bissbs>`. - :ref:`Segment 2: check if the kernels you build work fine.<introworkingcheck_bissbs>` + :ref:`Segment 2: check if the kernels you build work fine <introworkingcheck_bissbs>`. - :ref:`Segment 3: perform a bisection and validate the result.<introbisect_bissbs>` + :ref:`Segment 3: perform a bisection and validate the result <introbisect_bissbs>`. - :ref:`Supplementary tasks: cleanup during and after following this guide.<introclosure_bissbs>` + :ref:`Complementary tasks: cleanup during and after following this guide <introclosure_bissbs>`. + + :ref:`Optional tasks: test reverts, patches, or later versions <introoptional_bissbs>`. The steps in each segment illustrate the important aspects of the process, while a comprehensive reference section holds additional details for almost all of the @@ -240,24 +257,35 @@ 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 <submit_improvements>`. .. _introprep_bissbs: Preparations: set up everything to build your own kernels --------------------------------------------------------- +The following steps lay the groundwork for all further tasks. + +Note: the instructions assume you are building and testing on the same +machine; if you want to compile the kernel on another system, check +:ref:`Build kernels on a different machine <buildhost_bis>` below. + .. _backup_bissbs: * Create a fresh backup and put system repair and restore tools at hand, just to be prepared for the unlikely case of something going sideways. - [:ref:`details<backup_bisref>`] + [:ref:`details <backup_bisref>`] .. _vanilla_bissbs: @@ -265,7 +293,7 @@ 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<vanilla_bisref>`] + [:ref:`details <vanilla_bisref>`] .. _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<secureboot_bisref>`] + [:ref:`details <secureboot_bisref>`] .. _rangecheck_bissbs: * Determine the kernel versions considered 'good' and 'bad' throughout this - guide. + guide: - Do you follow this guide to verify if a bug is present in the code developers - care for? Then consider the mainline release your 'working' kernel (the newest - one you regularly use) is based on to be the 'good' version; if your 'working' - kernel for example is 6.0.11, then your 'good' kernel is 6.0. + * Do you follow this guide to verify if a bug is present in the code the + primary developers care for? Then consider the version of the newest kernel + you regularly use currently as 'good' (e.g. 6.0, 6.0.13, or 6.1-rc2). - In case you face a regression, it depends on the version range where the - regression was introduced: + * Do you face a regression, e.g. something broke or works worse after + switching to a newer kernel version? In that case it depends on the version + range during which the problem appeared: - * Something which used to work in Linux 6.0 broke when switching to Linux - 6.1-rc1? Then henceforth regard 6.0 as the last known 'good' version - and 6.1-rc1 as the first 'bad' one. + * Something regressed when updating from a stable/longterm release + (say 6.0.13) to a newer mainline series (like 6.1-rc7 or 6.1) or a + stable/longterm version based on one (say 6.1.5)? Then consider the + mainline release your working kernel is based on to be the 'good' + version (e.g. 6.0) and the first version to be broken as the 'bad' one + (e.g. 6.1-rc7, 6.1, or 6.1.5). Note, at this point it is merely assumed + that 6.0 is fine; this hypothesis will be checked in segment 2. - * Some function stopped working when updating from 6.0.11 to 6.1.4? Then for - the time being consider 6.0 as the last 'good' version and 6.1.4 as - the 'bad' one. Note, at this point it is merely assumed that 6.0 is fine; - this assumption will be checked in segment 2. + * Something regressed when switching from one mainline version (say 6.0) to + a later one (like 6.1-rc1) or a stable/longterm release based on it + (say 6.1.5)? Then regard the last working version (e.g. 6.0) as 'good' and + the first broken (e.g. 6.1-rc1 or 6.1.5) as 'bad'. - * A feature you used in 6.0.11 does not work at all or worse in 6.1.13? In - that case you want to bisect within a stable/longterm series: consider - 6.0.11 as the last known 'good' version and 6.0.13 as the first 'bad' - one. Note, in this case you still want to compile and test a mainline kernel - as explained in segment 1: the outcome will determine if you need to report - your issue to the regular developers or the stable team. + * Something regressed when updating within a stable/longterm series (say + from 6.0.13 to 6.0.15)? Then consider those versions as 'good' and 'bad' + (e.g. 6.0.13 and 6.0.15), as you need to bisect within that series. *Note, do not confuse 'good' version with 'working' kernel; the latter term throughout this guide will refer to the last kernel that has been working fine.* - [:ref:`details<rangecheck_bisref>`] + [:ref:`details <rangecheck_bisref>`] .. _bootworking_bissbs: * Boot into the 'working' kernel and briefly use the apparently broken feature. - [:ref:`details<bootworking_bisref>`] + [:ref:`details <bootworking_bisref>`] .. _diskspace_bissbs: @@ -327,7 +356,7 @@ 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<diskspace_bisref>`] + [:ref:`details <diskspace_bisref>`] .. _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<buildrequires_bisref>`] + [:ref:`details <buildrequires_bisref>`] .. _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<sources_bisref>`] + [:ref:`details <sources_bisref>`] + +.. _stablesources_bissbs: + +* Is one of the versions you earlier established as 'good' or 'bad' a stable or + longterm release (say 6.1.5)? Then download the code for the series it belongs + to ('linux-6.1.y' in this example):: + + git remote set-branches --add stable linux-6.1.y + git fetch stable .. _oldconfig_bissbs: * Start preparing a kernel build configuration (the '.config' file). Before doing so, ensure you are still running the 'working' kernel an earlier - step told you to boot; if you are unsure, check the current kernel release + step told you to boot; if you are unsure, check the current kernelrelease identifier using ``uname -r``. Afterwards check out the source code for the version earlier established as @@ -375,7 +413,7 @@ 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<oldconfig_bisref>`] + [:ref:`details <oldconfig_bisref>`] .. _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<localmodconfig_bisref>`] + [:ref:`details <localmodconfig_bisref>`] .. _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<tagging_bisref>`] + [:ref:`details <tagging_bisref>`] .. _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<debugsymbols_bisref>`] + [:ref:`details <debugsymbols_bisref>`] .. _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<configmods_distros_bisref>`]. + [:ref:`details <configmods_distros_bisref>`]. * If you want to influence other aspects of the configuration, do so now using your preferred tool. Note, to use make targets like 'menuconfig' or 'nconfig', you will need to install the development files of ncurses; for 'xconfig' you likewise need the Qt5 or Qt6 headers. - [:ref:`details<configmods_individual_bisref>`]. + [:ref:`details <configmods_individual_bisref>`]. .. _saveconfig_bissbs: @@ -488,7 +526,7 @@ Preparations: set up everything to build your own kernels make olddefconfig cp .config ~/kernel-config-working - [:ref:`details<saveconfig_bisref>`] + [:ref:`details <saveconfig_bisref>`] .. _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<introlatestcheck_bisref>`] +be a waste of time. [:ref:`details <introlatestcheck_bisref>`] .. _checkoutmaster_bissbs: -* Check out the latest Linux codebase:: +* Check out the latest Linux codebase. - cd ~/linux/ - git checkout --force --detach mainline/master + * Are your 'good' and 'bad' versions from the same stable or longterm series? + Then check the `front page of kernel.org <https://kernel.org/>`_: if it + lists a release from that series without an '[EOL]' tag, checkout the series + latest version ('linux-6.1.y' in the following example):: + + 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<checkoutmaster_bisref>`] + * In all other cases, run:: + + cd ~/linux/ + git switch --discard-changes --detach mainline/master + + [:ref:`details <checkoutmaster_bisref>`] .. _build_bissbs: @@ -522,7 +574,7 @@ be a waste of time. [:ref:`details<introlatestcheck_bisref>`] reference section for alternatives, which obviously will require other steps to install as well. - [:ref:`details<build_bisref>`] + [:ref:`details <build_bisref>`] .. _install_bissbs: @@ -555,7 +607,7 @@ be a waste of time. [:ref:`details<introlatestcheck_bisref>`] down: if you will build more kernels as described in segment 2 and 3, you will have to perform those again after executing ``command -v installkernel [...]``. - [:ref:`details<install_bisref>`] + [:ref:`details <install_bisref>`] .. _storagespace_bissbs: @@ -568,7 +620,7 @@ be a waste of time. [:ref:`details<introlatestcheck_bisref>`] Write down or remember those two values for later: they enable you to prevent running out of disk space accidentally during a bisection. - [:ref:`details<storagespace_bisref>`] + [:ref:`details <storagespace_bisref>`] .. _kernelrelease_bissbs: @@ -595,7 +647,7 @@ be a waste of time. [:ref:`details<introlatestcheck_bisref>`] If that command does not return '0', check the reference section, as the cause for this might interfere with your testing. - [:ref:`details<tainted_bisref>`] + [:ref:`details <tainted_bisref>`] .. _recheckbroken_bissbs: @@ -603,21 +655,19 @@ be a waste of time. [:ref:`details<introlatestcheck_bisref>`] out the instructions in the reference section to ensure nothing went sideways during your tests. - [:ref:`details<recheckbroken_bisref>`] + [:ref:`details <recheckbroken_bisref>`] .. _recheckstablebroken_bissbs: -* Are you facing a problem within a stable/longterm series, but failed to - reproduce it with the mainline kernel you just built? One that according to - the `front page of kernel.org <https://kernel.org/>`_ is still supported? Then - check if the latest codebase for the particular series might already fix the - problem. To do so, add the stable series Git branch for your 'good' kernel - (again, this here is assumed to be 6.0) and check out the latest version:: +* Did you just built a stable or longterm kernel? And were you able to reproduce + the regression with it? Then you should test the latest mainline codebase as + well, because the result determines which developers the bug must be submitted + to. + + To prepare that test, check out current mainline:: cd ~/linux/ - git remote set-branches --add stable linux-6.0.y - git fetch stable - git checkout --force --detach linux-6.0.y + git switch --discard-changes --detach mainline/master Now use the checked out code to build and install another kernel using the commands the earlier steps already described in more detail:: @@ -639,14 +689,16 @@ be a waste of time. [:ref:`details<introlatestcheck_bisref>`] uname -r cat /proc/sys/kernel/tainted - Now verify if this kernel is showing the problem. + Now verify if this kernel is showing the problem. If it does, then you need + to report the bug to the primary developers; if it does not, report it to the + stable team. See Documentation/admin-guide/reporting-issues.rst for details. - [:ref:`details<recheckstablebroken_bisref>`] + [:ref:`details <recheckstablebroken_bisref>`] Do you follow this guide to verify if a problem is present in the code currently supported by Linux kernel developers? Then you are done at this point. If you later want to remove the kernel you just built, check out -:ref:`Supplementary tasks: cleanup during and after following this guide<introclosure_bissbs>`. +:ref:`Complementary tasks: cleanup during and after following this guide <introclosure_bissbs>`. In case you face a regression, move on and execute at least the next segment as well. @@ -658,7 +710,7 @@ 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<introworkingcheck_bisref>`] +otherwise would be a waste of time. [:ref:`details <introworkingcheck_bisref>`] .. _recheckworking_bissbs: @@ -669,7 +721,7 @@ otherwise would be a waste of time. [:ref:`details<introworkingcheck_bisref>`] '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<introworkingcheck_bisref>`] Now check if this kernel works as expected; if not, consult the reference section for further instructions. - [:ref:`details<recheckworking_bisref>`] + [:ref:`details <recheckworking_bisref>`] .. _introbisect_bissbs: @@ -703,18 +755,11 @@ 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<bisectstart_bisref>`] + [:ref:`details <bisectstart_bisref>`] .. _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<bisectbuild_bisref>`] + [:ref:`details <bisectbuild_bisref>`] .. _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<bisecttest_bisref>`] + [:ref:`details <bisecttest_bisref>`] .. _bisectlog_bissbs: @@ -806,7 +851,7 @@ each kernel on commodity x86 machines. cp .config ~/bisection-config-culprit git bisect reset - [:ref:`details<bisectlog_bisref>`] + [:ref:`details <bisectlog_bisref>`] .. _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<revert_bisref>`] + [:ref:`details <revert_bisref>`] .. _introclosure_bissbs: -Supplementary tasks: cleanup during and after the bisection +Complementary tasks: cleanup during and after the bisection ----------------------------------------------------------- During and after following this guide you might want or need to remove some of @@ -903,7 +954,7 @@ space might run out. kernel image and related files behind; in that case remove them as described in the reference section. - [:ref:`details<makeroom_bisref>`] + [:ref:`details <makeroom_bisref>`] .. _finishingtouch_bissbs: @@ -926,18 +977,99 @@ space might run out. the version considered 'good', and the last three or four you compiled during the actual bisection process. - [:ref:`details<finishingtouch_bisref>`] + [:ref:`details <finishingtouch_bisref>`] + +.. _introoptional_bissbs: + +Optional: test reverts, patches, or later versions +-------------------------------------------------- + +While or after reporting a bug, you might want or potentially will be asked to +test reverts, debug patches, proposed fixes, or other versions. In that case +follow these instructions. + +* Update your Git clone and check out the latest code. + + * In case you want to test mainline, fetch its latest changes before checking + its code out:: + + git fetch mainline + git switch --discard-changes --detach mainline/master + + * In case you want to test a stable or longterm kernel, first add the branch + holding the series you are interested in (6.2 in the example), unless you + already did so earlier:: + + git remote set-branches --add stable linux-6.2.y + + Then fetch the latest changes and check out the latest version from the + series:: + + git fetch stable + git switch --discard-changes --detach stable/linux-6.2.y + +* Copy your kernel build configuration over:: + + cp ~/kernel-config-working .config + +* Your next step depends on what you want to do: + + * In case you just want to test the latest codebase, head to the next step, + you are already all set. + + * In case you want to test if a revert fixes an issue, revert one or multiple + changes by specifying their commit ids:: + + git revert --no-edit cafec0cacaca0 + + Now give that kernel a special tag to facilitates its identification and + prevent accidentally overwriting another kernel:: + + ./scripts/config --set-str CONFIG_LOCALVERSION '-local-cafec0cacaca0-reverted' + + * In case you want to test a patch, store the patch in a file like + '/tmp/foobars-proposed-fix-v1.patch' and apply it like this:: + + git apply /tmp/foobars-proposed-fix-v1.patch + + In case of multiple patches, repeat this step with the others. + + Now give that kernel a special tag to facilitates its identification and + prevent accidentally overwriting another kernel:: + + ./scripts/config --set-str CONFIG_LOCALVERSION '-local-foobars-fix-v1' + +* Build a kernel using the familiar commands, just without copying the kernel + build configuration over, as that has been taken care of already:: + + make olddefconfig && + make -j $(nproc --all) + # * Check if the free space suffices holding another kernel: + df -h /boot/ /lib/modules/ + sudo make modules_install + command -v installkernel && sudo make install + make -s kernelrelease | tee -a ~/kernels-built + reboot + +* Now verify you booted the newly built kernel and check it. + +[:ref:`details <introoptional_bisref>`] .. _submit_improvements: -This concludes the step-by-step guide. +Conclusion +---------- + +You have reached the end of the step-by-step guide. Did you run into trouble following any of the above steps not cleared up by the reference section below? Did you spot errors? Or do you have ideas how to -improve the guide? Then please take a moment and let the maintainer of this +improve the guide? + +If any of that applies, please take a moment and let the maintainer of this document know by email (Thorsten Leemhuis <linux@leemhuis.info>), ideally while CCing the Linux docs mailing list (linux-doc@vger.kernel.org). Such feedback is -vital to improve this document further, which is in everybody's interest, as it +vital to improve this text further, which is in everybody's interest, as it will enable more people to master the task described here -- and hopefully also improve similar guides inspired by this one. @@ -948,10 +1080,20 @@ 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:`... <introprep_bissbs>`] + +The steps in all later sections of this guide depend on those described here. + +[:ref:`back to step-by-step guide <introprep_bissbs>`]. + .. _backup_bisref: Prepare for emergencies ------------------------ +~~~~~~~~~~~~~~~~~~~~~~~ *Create a fresh backup and put system repair and restore tools at hand.* [:ref:`... <backup_bissbs>`] @@ -966,7 +1108,7 @@ 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:`...<vanilla_bissbs>`] @@ -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:`...<bootworking_bissbs>`] @@ -1034,7 +1176,7 @@ the right thing. .. _diskspace_bisref: Space requirements ------------------- +~~~~~~~~~~~~~~~~~~ *Ensure to have enough free space for building Linux.* [:ref:`... <diskspace_bissbs>`] @@ -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:`...<rangecheck_bissbs>`] Establishing the range of commits to be checked is mostly straightforward, except when a regression occurred when switching from a release of one stable -series to a release of a later series (e.g. from 6.0.11 to 6.1.4). In that case +series to a release of a later series (e.g. from 6.0.13 to 6.1.5). In that case Git will need some hand holding, as there is no straight line of descent. That's because with the release of 6.0 mainline carried on to 6.1 while the stable series 6.0.y branched to the side. It's therefore theoretically possible -that the issue you face with 6.1.4 only worked in 6.0.11, as it was fixed by a +that the issue you face with 6.1.5 only worked in 6.0.13, as it was fixed by a commit that went into one of the 6.0.y releases, but never hit mainline or the 6.1.y series. Thankfully that normally should not happen due to the way the stable/longterm maintainers maintain the code. It's thus pretty safe to assume 6.0 as a 'good' kernel. That assumption will be tested anyway, as that kernel will be built and tested in the segment '2' of this guide; Git would force you -to do this as well, if you tried bisecting between 6.0.11 and 6.1.13. +to do this as well, if you tried bisecting between 6.0.13 and 6.1.15. [:ref:`back to step-by-step guide <rangecheck_bissbs>`] .. _buildrequires_bisref: Install build requirements --------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~ *Install all software required to build a Linux kernel.* [:ref:`...<buildrequires_bissbs>`] @@ -1117,7 +1259,7 @@ 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:`...<sources_bissbs>`] @@ -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:`... <oldconfig_bissbs>`] @@ -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:`... <localmodconfig_bissbs>`] @@ -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:`... <tagging_bissbs>`] @@ -1344,7 +1486,7 @@ confusing during the bisection. .. _debugsymbols_bisref: Decide to enable or disable debug symbols ------------------------------------------ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Decide how to handle debug symbols.* [:ref:`... <debugsymbols_bissbs>`] @@ -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:`... <configmods_bissbs>`] @@ -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:`... <configmods_bissbs>`] @@ -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:`... <saveconfig_bissbs>`] Put the .config you prepared aside, as you want to copy it back to the build -directory every time during this guide before you start building another +directory every time during this guide before you start building another kernel. That's because going back and forth between different versions can alter .config files in odd ways; those occasionally cause side effects that could confuse testing or in some cases render the result of your bisection @@ -1442,8 +1584,8 @@ 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:`... <introlatestcheck_bissbs>`] @@ -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 <introlatestcheck_bissbs>`] .. _checkoutmaster_bisref: Check out the latest Linux codebase ------------------------------------ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *Check out the latest Linux codebase.* - [:ref:`... <introlatestcheck_bissbs>`] + [:ref:`... <checkoutmaster_bissbs>`] In case you later want to recheck if an ever newer codebase might fix the problem, remember to run that ``git fetch --shallow-exclude [...]`` command again mentioned earlier to update your local Git repository. -[:ref:`back to step-by-step guide <introlatestcheck_bissbs>`] +[:ref:`back to step-by-step guide <checkoutmaster_bissbs>`] .. _build_bisref: Build your kernel ------------------ +~~~~~~~~~~~~~~~~~ *Build the image and the modules of your first kernel using the config file you prepared.* [:ref:`... <build_bissbs>`] @@ -1521,7 +1663,7 @@ 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:`... <install_bissbs>`] @@ -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:`... <storagespace_bissbs>`] @@ -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:`... <tainted_bissbs>`] @@ -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:`... <recheckbroken_bissbs>`] @@ -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:`... <recheckworking_bissbs>`] @@ -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 <recheckworking_bissbs>`] +Perform a bisection and validate the result +------------------------------------------- + + *With all the preparations and precaution builds taken care of, you are now + ready to begin the bisection.* [:ref:`... <introbisect_bissbs>`] + +The steps in this segment perform and validate the bisection. + +[:ref:`back to step-by-step guide <introbisect_bissbs>`]. + .. _bisectstart_bisref: Start the bisection -------------------- +~~~~~~~~~~~~~~~~~~~ *Start the bisection and tell Git about the versions earlier established as 'good' and 'bad'.* [:ref:`... <bisectstart_bissbs>`] @@ -1789,7 +1941,7 @@ 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:`... <bisectbuild_bissbs>`] @@ -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:`... <bisecttest_bissbs>`] @@ -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:`... <bisectlog_bissbs>`] @@ -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:`... <revert_bissbs>`] @@ -1869,14 +2021,20 @@ succeeds, test that kernel version instead. [:ref:`back to step-by-step guide <revert_bissbs>`] +Cleanup steps during and after following this guide +--------------------------------------------------- -Supplementary tasks: cleanup during and after the bisection ------------------------------------------------------------ + *During and after following this guide you might want or need to remove some + of the kernels you installed.* [:ref:`... <introclosure_bissbs>`] + +The steps in this section describe clean-up procedures. + +[:ref:`back to step-by-step guide <introclosure_bissbs>`]. .. _makeroom_bisref: Cleaning up during the bisection --------------------------------- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ *To remove one of the kernels you installed, look up its 'kernelrelease' identifier.* [:ref:`... <makeroom_bissbs>`] @@ -1911,13 +2069,13 @@ 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 <makeroom_bissbs>`] 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 -<filename>`` or ``git am <filename>`` and build yet another kernel using the -familiar commands. +Removing the repository as well would likely be unwise at this point: there +is a decent chance developers will ask you to build another kernel to +perform additional tests -- like testing a debug patch or a proposed fix. +Details on how to perform those can be found in the section :ref:`Optional +tasks: test reverts, patches, or later versions <introoptional_bissbs>`. Additional tests are also the reason why you want to keep the ~/kernel-config-working file around for a few weeks. [:ref:`back to step-by-step guide <finishingtouch_bissbs>`] +.. _introoptional_bisref: -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:`... <introoptional_bissbs>`] + +All the commands used in this section should be pretty straight forward, so +there is not much to add except one thing: when setting a kernel tag as +instructed, ensure it is not much longer than the one used in the example, as +problems will arise if the kernelrelease identifier exceeds 63 characters. + +[:ref:`back to step-by-step guide <introoptional_bissbs>`]. + + +Additional information +====================== + +.. _buildhost_bis: + +Build kernels on a different machine +------------------------------------ + +To compile kernels on another system, slightly alter the step-by-step guide's +instructions: + +* Start following the guide on the machine where you want to install and test + the kernels later. + +* After executing ':ref:`Boot into the working kernel and briefly use the + apparently broken feature <bootworking_bissbs>`', save the list of loaded + modules to a file using ``lsmod > ~/test-machine-lsmod``. Then locate the + build configuration for the running kernel (see ':ref:`Start defining the + build configuration for your kernel <oldconfig_bisref>`' for hints on where + to find it) and store it as '~/test-machine-config-working'. Transfer both + files to the home directory of your build host. + +* Continue the guide on the build host (e.g. with ':ref:`Ensure to have enough + free space for building [...] <diskspace_bissbs>`'). + +* When you reach ':ref:`Start preparing a kernel build configuration[...] + <oldconfig_bissbs>`': before running ``make olddefconfig`` for the first time, + execute the following command to base your configuration on the one from the + test machine's 'working' kernel:: + + cp ~/test-machine-config-working ~/linux/.config + +* During the next step to ':ref:`disable any apparently superfluous kernel + modules <localmodconfig_bissbs>`' use the following command instead:: -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 $(nproc --all) targz-pkg + + This will generate a gzipped tar file whose name is printed in the last + line shown; for example, a kernel with the kernelrelease identifier + '6.0.0-rc1-local-g928a87efa423' built for x86 machines usually will + be stored as '~/linux/linux-6.0.0-rc1-local-g928a87efa423-x86.tar.gz'. + + Copy that file to your test machine's home directory. + +* Switch to the test machine to check if you have enough space to hold another + kernel. Then extract the file you transferred:: + + sudo tar -xvzf ~/linux-6.0.0-rc1-local-g928a87efa423-x86.tar.gz -C / + + Afterwards :ref:`generate the initramfs and add the kernel to your boot + loader's configuration <install_bisref>`; on some distributions the following + command will take care of both these tasks:: + + sudo /sbin/installkernel 6.0.0-rc1-local-g928a87efa423 /boot/vmlinuz-6.0.0-rc1-local-g928a87efa423 + + Now reboot and ensure you started the intended kernel. + +This approach even works when building for another architecture: just install +cross-compilers and add the appropriate parameters to every invocation of make +(e.g. ``make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- [...]``). + +Additional reading material +--------------------------- * The `man page for 'git bisect' <https://git-scm.com/docs/git-bisect>`_ and `fighting regressions with 'git bisect' <https://git-scm.com/docs/git-bisect-lk2009.html>`_ diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml index c0d6a4fdff97..e6dc5494baee 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm8150-mdss.yaml @@ -53,6 +53,15 @@ patternProperties: compatible: const: qcom,sm8150-dpu + "^displayport-controller@[0-9a-f]+$": + type: object + additionalProperties: true + + properties: + compatible: + contains: + const: qcom,sm8150-dp + "^dsi@[0-9a-f]+$": type: object additionalProperties: true diff --git a/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml b/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml index afcdeed4e88a..bc813fe74fab 100644 --- a/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml +++ b/Documentation/devicetree/bindings/pwm/mediatek,pwm-disp.yaml @@ -52,6 +52,9 @@ properties: - const: main - const: mm + power-domains: + maxItems: 1 + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml b/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml index 65cb2e5c5eee..eb2992a447d7 100644 --- a/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml +++ b/Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Universal Synchronous Asynchronous Receiver/Transmitter (USART) maintainers: - - Richard Genoud <richard.genoud@gmail.com> + - Richard Genoud <richard.genoud@bootlin.com> properties: compatible: diff --git a/Documentation/driver-api/virtio/writing_virtio_drivers.rst b/Documentation/driver-api/virtio/writing_virtio_drivers.rst index e14c58796d25..e5de6f5d061a 100644 --- a/Documentation/driver-api/virtio/writing_virtio_drivers.rst +++ b/Documentation/driver-api/virtio/writing_virtio_drivers.rst @@ -97,7 +97,6 @@ like this:: static struct virtio_driver virtio_dummy_driver = { .driver.name = KBUILD_MODNAME, - .driver.owner = THIS_MODULE, .id_table = id_table, .probe = virtio_dummy_probe, .remove = virtio_dummy_remove, diff --git a/Documentation/filesystems/bcachefs/index.rst b/Documentation/filesystems/bcachefs/index.rst new file mode 100644 index 000000000000..e2bd61ccd96f --- /dev/null +++ b/Documentation/filesystems/bcachefs/index.rst @@ -0,0 +1,11 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====================== +bcachefs Documentation +====================== + +.. toctree:: + :maxdepth: 2 + :numbered: + + errorcodes diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index 0ea1e44fa028..1f9b4c905a6a 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -69,6 +69,7 @@ Documentation for filesystem implementations. afs autofs autofs-mount-control + bcachefs/index befs bfs btrfs diff --git a/Documentation/mm/page_owner.rst b/Documentation/mm/page_owner.rst index 0d0334cd5179..3a45a20fc05a 100644 --- a/Documentation/mm/page_owner.rst +++ b/Documentation/mm/page_owner.rst @@ -24,10 +24,10 @@ fragmentation statistics can be obtained through gfp flag information of each page. It is already implemented and activated if page owner is enabled. Other usages are more than welcome. -It can also be used to show all the stacks and their outstanding -allocations, which gives us a quick overview of where the memory is going -without the need to screen through all the pages and match the allocation -and free operation. +It can also be used to show all the stacks and their current number of +allocated base pages, which gives us a quick overview of where the memory +is going without the need to screen through all the pages and match the +allocation and free operation. page owner is disabled by default. So, if you'd like to use it, you need to add "page_owner=on" to your boot cmdline. If the kernel is built @@ -75,42 +75,45 @@ Usage cat /sys/kernel/debug/page_owner_stacks/show_stacks > stacks.txt cat stacks.txt - prep_new_page+0xa9/0x120 - get_page_from_freelist+0x7e6/0x2140 - __alloc_pages+0x18a/0x370 - new_slab+0xc8/0x580 - ___slab_alloc+0x1f2/0xaf0 - __slab_alloc.isra.86+0x22/0x40 - kmem_cache_alloc+0x31b/0x350 - __khugepaged_enter+0x39/0x100 - dup_mmap+0x1c7/0x5ce - copy_process+0x1afe/0x1c90 - kernel_clone+0x9a/0x3c0 - __do_sys_clone+0x66/0x90 - do_syscall_64+0x7f/0x160 - entry_SYSCALL_64_after_hwframe+0x6c/0x74 - stack_count: 234 + post_alloc_hook+0x177/0x1a0 + get_page_from_freelist+0xd01/0xd80 + __alloc_pages+0x39e/0x7e0 + allocate_slab+0xbc/0x3f0 + ___slab_alloc+0x528/0x8a0 + kmem_cache_alloc+0x224/0x3b0 + sk_prot_alloc+0x58/0x1a0 + sk_alloc+0x32/0x4f0 + inet_create+0x427/0xb50 + __sock_create+0x2e4/0x650 + inet_ctl_sock_create+0x30/0x180 + igmp_net_init+0xc1/0x130 + ops_init+0x167/0x410 + setup_net+0x304/0xa60 + copy_net_ns+0x29b/0x4a0 + create_new_namespaces+0x4a1/0x820 + nr_base_pages: 16 ... ... echo 7000 > /sys/kernel/debug/page_owner_stacks/count_threshold cat /sys/kernel/debug/page_owner_stacks/show_stacks> stacks_7000.txt cat stacks_7000.txt - prep_new_page+0xa9/0x120 - get_page_from_freelist+0x7e6/0x2140 - __alloc_pages+0x18a/0x370 - alloc_pages_mpol+0xdf/0x1e0 - folio_alloc+0x14/0x50 - filemap_alloc_folio+0xb0/0x100 - page_cache_ra_unbounded+0x97/0x180 - filemap_fault+0x4b4/0x1200 - __do_fault+0x2d/0x110 - do_pte_missing+0x4b0/0xa30 - __handle_mm_fault+0x7fa/0xb70 - handle_mm_fault+0x125/0x300 - do_user_addr_fault+0x3c9/0x840 - exc_page_fault+0x68/0x150 - asm_exc_page_fault+0x22/0x30 - stack_count: 8248 + post_alloc_hook+0x177/0x1a0 + get_page_from_freelist+0xd01/0xd80 + __alloc_pages+0x39e/0x7e0 + alloc_pages_mpol+0x22e/0x490 + folio_alloc+0xd5/0x110 + filemap_alloc_folio+0x78/0x230 + page_cache_ra_order+0x287/0x6f0 + filemap_get_pages+0x517/0x1160 + filemap_read+0x304/0x9f0 + xfs_file_buffered_read+0xe6/0x1d0 [xfs] + xfs_file_read_iter+0x1f0/0x380 [xfs] + __kernel_read+0x3b9/0x730 + kernel_read_file+0x309/0x4d0 + __do_sys_finit_module+0x381/0x730 + do_syscall_64+0x8d/0x150 + entry_SYSCALL_64_after_hwframe+0x62/0x6a + nr_base_pages: 20824 ... cat /sys/kernel/debug/page_owner > page_owner_full.txt diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index bb2100228cc7..6e9a4597bf2c 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -252,7 +252,7 @@ an involved disclosed party. The current ambassadors list: AMD Tom Lendacky <thomas.lendacky@amd.com> Ampere Darren Hart <darren@os.amperecomputing.com> ARM Catalin Marinas <catalin.marinas@arm.com> - IBM Power Anton Blanchard <anton@linux.ibm.com> + IBM Power Michael Ellerman <ellerman@au.ibm.com> IBM Z Christian Borntraeger <borntraeger@de.ibm.com> Intel Tony Luck <tony.luck@intel.com> Qualcomm Trilok Soni <quic_tsoni@quicinc.com> diff --git a/Documentation/sound/soc/dapm-graph.svg b/Documentation/sound/soc/dapm-graph.svg new file mode 100644 index 000000000000..d783672db815 --- /dev/null +++ b/Documentation/sound/soc/dapm-graph.svg @@ -0,0 +1,375 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" + "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"> +<!-- Generated by graphviz version 2.43.0 (0) + --> +<!-- Title: G Pages: 1 --> +<svg width="900pt" height="630pt" + viewBox="0.00 0.00 900.00 630.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"> +<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 626)"> +<title>G</title> +<polygon fill="white" stroke="transparent" points="-4,4 -4,-626 896,-626 896,4 -4,4"/> +<g id="clust1" class="cluster"> +<title>ROOT</title> +<polygon fill="none" stroke="dodgerblue" points="8,-537 8,-614 102,-614 102,-537 8,-537"/> +<text text-anchor="middle" x="55" y="-598.8" font-family="sans-serif" font-size="14.00">ROOT</text> +</g> +<g id="clust2" class="cluster"> +<title>4000b000.audio-controller</title> +<polygon fill="none" stroke="dodgerblue" points="120,-378 120,-455 312,-455 312,-378 120,-378"/> +<text text-anchor="middle" x="216" y="-439.8" font-family="sans-serif" font-size="14.00">4000b000.audio-controller</text> +</g> +<g id="clust5" class="cluster"> +<title>cs42l51.0-004a</title> +<polygon fill="none" stroke="dodgerblue" points="330,-8 330,-614 884,-614 884,-8 330,-8"/> +<text text-anchor="middle" x="607" y="-598.8" font-family="sans-serif" font-size="14.00">cs42l51.0-004a</text> +</g> +<g id="clust9" class="cluster"> +<title>hdmi-audio-codec.1.auto</title> +<polygon fill="none" stroke="dodgerblue" points="110,-463 110,-614 314,-614 314,-463 110,-463"/> +<text text-anchor="middle" x="212" y="-598.8" font-family="sans-serif" font-size="14.00">hdmi-audio-codec.1.auto</text> +</g> +<!-- ROOT_Amplifier --> +<g id="node1" class="node"> +<title>ROOT_Amplifier</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="93.5,-583 16.5,-583 16.5,-545 93.5,-545 93.5,-583"/> +<text text-anchor="middle" x="55" y="-567.8" font-family="sans-serif" font-size="14.00">Amplifier</text> +<text text-anchor="middle" x="55" y="-552.8" font-family="sans-serif" font-size="14.00">[out_drv]</text> +</g> +<!-- 4000b000.audio-controller_capture --> +<g id="node2" class="node"> +<title>4000b000.audio-controller_capture</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="202,-424 128,-424 128,-386 202,-386 202,-424"/> +<text text-anchor="middle" x="165" y="-408.8" font-family="sans-serif" font-size="14.00">capture</text> +<text text-anchor="middle" x="165" y="-393.8" font-family="sans-serif" font-size="14.00">[dai_out]</text> +</g> +<!-- 4000b000.audio-controller_playback --> +<g id="node3" class="node"> +<title>4000b000.audio-controller_playback</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="304,-424 230,-424 230,-386 304,-386 304,-424"/> +<text text-anchor="middle" x="267" y="-408.8" font-family="sans-serif" font-size="14.00">playback</text> +<text text-anchor="middle" x="267" y="-393.8" font-family="sans-serif" font-size="14.00">[dai_in]</text> +</g> +<!-- hdmi-audio-codec.1.auto_I2S Playback --> +<g id="node28" class="node"> +<title>hdmi-audio-codec.1.auto_I2S Playback</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="306,-583 208,-583 208,-545 306,-545 306,-583"/> +<text text-anchor="middle" x="257" y="-567.8" font-family="sans-serif" font-size="14.00">I2S Playback</text> +<text text-anchor="middle" x="257" y="-552.8" font-family="sans-serif" font-size="14.00">[dai_in]</text> +</g> +<!-- 4000b000.audio-controller_playback->hdmi-audio-codec.1.auto_I2S Playback --> +<g id="edge21" class="edge"> +<title>4000b000.audio-controller_playback->hdmi-audio-codec.1.auto_I2S Playback</title> +<path fill="none" stroke="black" d="M276.84,-424.14C282.19,-435.06 288.26,-449.42 291,-463 295.05,-483.04 296.67,-489.36 291,-509 288.25,-518.54 283.26,-528.01 277.93,-536.3"/> +<polygon fill="black" stroke="black" points="274.89,-534.55 272.11,-544.78 280.66,-538.51 274.89,-534.55"/> +</g> +<!-- hdmi-audio-codec.1.auto_Capture --> +<g id="node4" class="node"> +<title>hdmi-audio-codec.1.auto_Capture</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="192,-509 118,-509 118,-471 192,-471 192,-509"/> +<text text-anchor="middle" x="155" y="-493.8" font-family="sans-serif" font-size="14.00">Capture</text> +<text text-anchor="middle" x="155" y="-478.8" font-family="sans-serif" font-size="14.00">[dai_out]</text> +</g> +<!-- hdmi-audio-codec.1.auto_Capture->4000b000.audio-controller_capture --> +<g id="edge1" class="edge"> +<title>hdmi-audio-codec.1.auto_Capture->4000b000.audio-controller_capture</title> +<path fill="none" stroke="black" d="M157.17,-470.99C158.46,-460.3 160.12,-446.5 161.58,-434.37"/> +<polygon fill="black" stroke="black" points="165.08,-434.61 162.8,-424.26 158.13,-433.77 165.08,-434.61"/> +</g> +<!-- cs42l51.0-004a_AIN1L --> +<g id="node5" class="node"> +<title>cs42l51.0-004a_AIN1L</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="836.5,-583 775.5,-583 775.5,-545 836.5,-545 836.5,-583"/> +<text text-anchor="middle" x="806" y="-567.8" font-family="sans-serif" font-size="14.00">AIN1L</text> +<text text-anchor="middle" x="806" y="-552.8" font-family="sans-serif" font-size="14.00">[input]</text> +</g> +<!-- cs42l51.0-004a_PGA-ADC Mux Left --> +<g id="node22" class="node"> +<title>cs42l51.0-004a_PGA-ADC Mux Left</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="876,-509 736,-509 736,-471 876,-471 876,-509"/> +<text text-anchor="middle" x="806" y="-493.8" font-family="sans-serif" font-size="14.00">PGA-ADC Mux Left</text> +<text text-anchor="middle" x="806" y="-478.8" font-family="sans-serif" font-size="14.00">[mux]</text> +</g> +<!-- cs42l51.0-004a_AIN1L->cs42l51.0-004a_PGA-ADC Mux Left --> +<g id="edge14" class="edge"> +<title>cs42l51.0-004a_AIN1L->cs42l51.0-004a_PGA-ADC Mux Left</title> +<path fill="none" stroke="black" d="M806,-544.83C806,-537.13 806,-527.97 806,-519.42"/> +<polygon fill="black" stroke="black" points="809.5,-519.41 806,-509.41 802.5,-519.41 809.5,-519.41"/> +</g> +<!-- cs42l51.0-004a_AIN1R --> +<g id="node6" class="node"> +<title>cs42l51.0-004a_AIN1R</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="738.5,-583 677.5,-583 677.5,-545 738.5,-545 738.5,-583"/> +<text text-anchor="middle" x="708" y="-567.8" font-family="sans-serif" font-size="14.00">AIN1R</text> +<text text-anchor="middle" x="708" y="-552.8" font-family="sans-serif" font-size="14.00">[input]</text> +</g> +<!-- cs42l51.0-004a_PGA-ADC Mux Right --> +<g id="node23" class="node"> +<title>cs42l51.0-004a_PGA-ADC Mux Right</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="717.5,-509 568.5,-509 568.5,-471 717.5,-471 717.5,-509"/> +<text text-anchor="middle" x="643" y="-493.8" font-family="sans-serif" font-size="14.00">PGA-ADC Mux Right</text> +<text text-anchor="middle" x="643" y="-478.8" font-family="sans-serif" font-size="14.00">[mux]</text> +</g> +<!-- cs42l51.0-004a_AIN1R->cs42l51.0-004a_PGA-ADC Mux Right --> +<g id="edge15" class="edge"> +<title>cs42l51.0-004a_AIN1R->cs42l51.0-004a_PGA-ADC Mux Right</title> +<path fill="none" stroke="black" d="M691.6,-544.83C683.96,-536.37 674.73,-526.15 666.38,-516.9"/> +<polygon fill="black" stroke="black" points="668.92,-514.49 659.62,-509.41 663.73,-519.18 668.92,-514.49"/> +</g> +<!-- cs42l51.0-004a_AIN2L --> +<g id="node7" class="node"> +<title>cs42l51.0-004a_AIN2L</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="659.5,-583 598.5,-583 598.5,-545 659.5,-545 659.5,-583"/> +<text text-anchor="middle" x="629" y="-567.8" font-family="sans-serif" font-size="14.00">AIN2L</text> +<text text-anchor="middle" x="629" y="-552.8" font-family="sans-serif" font-size="14.00">[input]</text> +</g> +<!-- cs42l51.0-004a_AIN2R --> +<g id="node8" class="node"> +<title>cs42l51.0-004a_AIN2R</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="580.5,-583 519.5,-583 519.5,-545 580.5,-545 580.5,-583"/> +<text text-anchor="middle" x="550" y="-567.8" font-family="sans-serif" font-size="14.00">AIN2R</text> +<text text-anchor="middle" x="550" y="-552.8" font-family="sans-serif" font-size="14.00">[input]</text> +</g> +<!-- cs42l51.0-004a_Capture --> +<g id="node9" class="node"> +<title>cs42l51.0-004a_Capture</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="692,-276 618,-276 618,-238 692,-238 692,-276"/> +<text text-anchor="middle" x="655" y="-260.8" font-family="sans-serif" font-size="14.00">Capture</text> +<text text-anchor="middle" x="655" y="-245.8" font-family="sans-serif" font-size="14.00">[dai_out]</text> +</g> +<!-- cs42l51.0-004a_DAC Mux --> +<g id="node10" class="node"> +<title>cs42l51.0-004a_DAC Mux</title> +<polygon fill="none" stroke="#008b00" stroke-width="2" points="598.5,-202 521.5,-202 521.5,-164 598.5,-164 598.5,-202"/> +<text text-anchor="middle" x="560" y="-186.8" font-family="sans-serif" font-size="14.00">DAC Mux</text> +<text text-anchor="middle" x="560" y="-171.8" font-family="sans-serif" font-size="14.00">[mux]</text> +</g> +<!-- cs42l51.0-004a_Left DAC --> +<g id="node14" class="node"> +<title>cs42l51.0-004a_Left DAC</title> +<polygon fill="none" stroke="#008b00" stroke-width="2" points="548,-128 474,-128 474,-90 548,-90 548,-128"/> +<text text-anchor="middle" x="511" y="-112.8" font-family="sans-serif" font-size="14.00">Left DAC</text> +<text text-anchor="middle" x="511" y="-97.8" font-family="sans-serif" font-size="14.00">[dac]</text> +</g> +<!-- cs42l51.0-004a_DAC Mux->cs42l51.0-004a_Left DAC --> +<g id="edge9" class="edge"> +<title>cs42l51.0-004a_DAC Mux->cs42l51.0-004a_Left DAC</title> +<path fill="none" stroke="black" d="M547.64,-163.83C542.05,-155.62 535.34,-145.76 529.19,-136.73"/> +<polygon fill="black" stroke="black" points="532.05,-134.71 523.53,-128.41 526.26,-138.65 532.05,-134.71"/> +</g> +<!-- cs42l51.0-004a_Right DAC --> +<g id="node26" class="node"> +<title>cs42l51.0-004a_Right DAC</title> +<polygon fill="none" stroke="#008b00" stroke-width="2" points="649.5,-128 566.5,-128 566.5,-90 649.5,-90 649.5,-128"/> +<text text-anchor="middle" x="608" y="-112.8" font-family="sans-serif" font-size="14.00">Right DAC</text> +<text text-anchor="middle" x="608" y="-97.8" font-family="sans-serif" font-size="14.00">[dac]</text> +</g> +<!-- cs42l51.0-004a_DAC Mux->cs42l51.0-004a_Right DAC --> +<g id="edge18" class="edge"> +<title>cs42l51.0-004a_DAC Mux->cs42l51.0-004a_Right DAC</title> +<path fill="none" stroke="black" d="M572.11,-163.83C577.53,-155.71 584.02,-145.96 589.99,-137.01"/> +<polygon fill="black" stroke="black" points="593.09,-138.68 595.72,-128.41 587.27,-134.79 593.09,-138.68"/> +</g> +<!-- cs42l51.0-004a_HPL --> +<g id="node11" class="node"> +<title>cs42l51.0-004a_HPL</title> +<polygon fill="none" stroke="#008b00" stroke-width="2" points="546.5,-54 475.5,-54 475.5,-16 546.5,-16 546.5,-54"/> +<text text-anchor="middle" x="511" y="-38.8" font-family="sans-serif" font-size="14.00">HPL</text> +<text text-anchor="middle" x="511" y="-23.8" font-family="sans-serif" font-size="14.00">[output]</text> +</g> +<!-- cs42l51.0-004a_HPR --> +<g id="node12" class="node"> +<title>cs42l51.0-004a_HPR</title> +<polygon fill="none" stroke="#008b00" stroke-width="2" points="643.5,-54 572.5,-54 572.5,-16 643.5,-16 643.5,-54"/> +<text text-anchor="middle" x="608" y="-38.8" font-family="sans-serif" font-size="14.00">HPR</text> +<text text-anchor="middle" x="608" y="-23.8" font-family="sans-serif" font-size="14.00">[output]</text> +</g> +<!-- cs42l51.0-004a_Left ADC --> +<g id="node13" class="node"> +<title>cs42l51.0-004a_Left ADC</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="822,-350 748,-350 748,-312 822,-312 822,-350"/> +<text text-anchor="middle" x="785" y="-334.8" font-family="sans-serif" font-size="14.00">Left ADC</text> +<text text-anchor="middle" x="785" y="-319.8" font-family="sans-serif" font-size="14.00">[adc]</text> +</g> +<!-- cs42l51.0-004a_Left ADC->cs42l51.0-004a_Capture --> +<g id="edge4" class="edge"> +<title>cs42l51.0-004a_Left ADC->cs42l51.0-004a_Capture</title> +<path fill="none" stroke="black" d="M752.2,-311.83C735.41,-302.54 714.8,-291.12 696.88,-281.2"/> +<polygon fill="black" stroke="black" points="698.24,-277.95 687.79,-276.16 694.85,-284.07 698.24,-277.95"/> +</g> +<!-- cs42l51.0-004a_Left DAC->cs42l51.0-004a_HPL --> +<g id="edge6" class="edge"> +<title>cs42l51.0-004a_Left DAC->cs42l51.0-004a_HPL</title> +<path fill="none" stroke="black" d="M511,-89.83C511,-82.13 511,-72.97 511,-64.42"/> +<polygon fill="black" stroke="black" points="514.5,-64.41 511,-54.41 507.5,-64.41 514.5,-64.41"/> +</g> +<!-- cs42l51.0-004a_Left PGA --> +<g id="node15" class="node"> +<title>cs42l51.0-004a_Left PGA</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="838,-424 764,-424 764,-386 838,-386 838,-424"/> +<text text-anchor="middle" x="801" y="-408.8" font-family="sans-serif" font-size="14.00">Left PGA</text> +<text text-anchor="middle" x="801" y="-393.8" font-family="sans-serif" font-size="14.00">[pga]</text> +</g> +<!-- cs42l51.0-004a_Left PGA->cs42l51.0-004a_Left ADC --> +<g id="edge8" class="edge"> +<title>cs42l51.0-004a_Left PGA->cs42l51.0-004a_Left ADC</title> +<path fill="none" stroke="black" d="M796.96,-385.83C795.25,-378.13 793.22,-368.97 791.31,-360.42"/> +<polygon fill="black" stroke="black" points="794.68,-359.42 789.09,-350.41 787.84,-360.93 794.68,-359.42"/> +</g> +<!-- cs42l51.0-004a_MCLK --> +<g id="node16" class="node"> +<title>cs42l51.0-004a_MCLK</title> +<polygon fill="none" stroke="#008b00" stroke-width="2" points="594.5,-350 525.5,-350 525.5,-312 594.5,-312 594.5,-350"/> +<text text-anchor="middle" x="560" y="-334.8" font-family="sans-serif" font-size="14.00">MCLK</text> +<text text-anchor="middle" x="560" y="-319.8" font-family="sans-serif" font-size="14.00">[supply]</text> +</g> +<!-- cs42l51.0-004a_MCLK->cs42l51.0-004a_Capture --> +<g id="edge2" class="edge"> +<title>cs42l51.0-004a_MCLK->cs42l51.0-004a_Capture</title> +<path fill="none" stroke="black" d="M583.97,-311.83C595.79,-302.88 610.2,-291.96 622.94,-282.3"/> +<polygon fill="black" stroke="black" points="625.18,-284.99 631.04,-276.16 620.95,-279.41 625.18,-284.99"/> +</g> +<!-- cs42l51.0-004a_Playback --> +<g id="node24" class="node"> +<title>cs42l51.0-004a_Playback</title> +<polygon fill="none" stroke="#008b00" stroke-width="2" points="597,-276 523,-276 523,-238 597,-238 597,-276"/> +<text text-anchor="middle" x="560" y="-260.8" font-family="sans-serif" font-size="14.00">Playback</text> +<text text-anchor="middle" x="560" y="-245.8" font-family="sans-serif" font-size="14.00">[dai_in]</text> +</g> +<!-- cs42l51.0-004a_MCLK->cs42l51.0-004a_Playback --> +<g id="edge16" class="edge"> +<title>cs42l51.0-004a_MCLK->cs42l51.0-004a_Playback</title> +<path fill="none" stroke="black" d="M560,-311.83C560,-304.13 560,-294.97 560,-286.42"/> +<polygon fill="black" stroke="black" points="563.5,-286.41 560,-276.41 556.5,-286.41 563.5,-286.41"/> +</g> +<!-- cs42l51.0-004a_MICL --> +<g id="node17" class="node"> +<title>cs42l51.0-004a_MICL</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="399.5,-509 338.5,-509 338.5,-471 399.5,-471 399.5,-509"/> +<text text-anchor="middle" x="369" y="-493.8" font-family="sans-serif" font-size="14.00">MICL</text> +<text text-anchor="middle" x="369" y="-478.8" font-family="sans-serif" font-size="14.00">[input]</text> +</g> +<!-- cs42l51.0-004a_Mic Preamp Left --> +<g id="node20" class="node"> +<title>cs42l51.0-004a_Mic Preamp Left</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="461.5,-424 338.5,-424 338.5,-386 461.5,-386 461.5,-424"/> +<text text-anchor="middle" x="400" y="-408.8" font-family="sans-serif" font-size="14.00">Mic Preamp Left</text> +<text text-anchor="middle" x="400" y="-393.8" font-family="sans-serif" font-size="14.00">[mixer]</text> +</g> +<!-- cs42l51.0-004a_MICL->cs42l51.0-004a_Mic Preamp Left --> +<g id="edge12" class="edge"> +<title>cs42l51.0-004a_MICL->cs42l51.0-004a_Mic Preamp Left</title> +<path fill="none" stroke="black" d="M375.73,-470.99C379.8,-460.08 385.08,-445.94 389.68,-433.64"/> +<polygon fill="black" stroke="black" points="392.96,-434.85 393.18,-424.26 386.4,-432.4 392.96,-434.85"/> +</g> +<!-- cs42l51.0-004a_MICR --> +<g id="node18" class="node"> +<title>cs42l51.0-004a_MICR</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="501.5,-583 440.5,-583 440.5,-545 501.5,-545 501.5,-583"/> +<text text-anchor="middle" x="471" y="-567.8" font-family="sans-serif" font-size="14.00">MICR</text> +<text text-anchor="middle" x="471" y="-552.8" font-family="sans-serif" font-size="14.00">[input]</text> +</g> +<!-- cs42l51.0-004a_Mic Preamp Right --> +<g id="node21" class="node"> +<title>cs42l51.0-004a_Mic Preamp Right</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="550.5,-509 417.5,-509 417.5,-471 550.5,-471 550.5,-509"/> +<text text-anchor="middle" x="484" y="-493.8" font-family="sans-serif" font-size="14.00">Mic Preamp Right</text> +<text text-anchor="middle" x="484" y="-478.8" font-family="sans-serif" font-size="14.00">[mixer]</text> +</g> +<!-- cs42l51.0-004a_MICR->cs42l51.0-004a_Mic Preamp Right --> +<g id="edge13" class="edge"> +<title>cs42l51.0-004a_MICR->cs42l51.0-004a_Mic Preamp Right</title> +<path fill="none" stroke="black" d="M474.28,-544.83C475.67,-537.13 477.32,-527.97 478.87,-519.42"/> +<polygon fill="black" stroke="black" points="482.34,-519.88 480.68,-509.41 475.45,-518.63 482.34,-519.88"/> +</g> +<!-- cs42l51.0-004a_Mic Bias --> +<g id="node19" class="node"> +<title>cs42l51.0-004a_Mic Bias</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="409.5,-583 338.5,-583 338.5,-545 409.5,-545 409.5,-583"/> +<text text-anchor="middle" x="374" y="-567.8" font-family="sans-serif" font-size="14.00">Mic Bias</text> +<text text-anchor="middle" x="374" y="-552.8" font-family="sans-serif" font-size="14.00">[supply]</text> +</g> +<!-- cs42l51.0-004a_Mic Bias->cs42l51.0-004a_MICL --> +<g id="edge11" class="edge"> +<title>cs42l51.0-004a_Mic Bias->cs42l51.0-004a_MICL</title> +<path fill="none" stroke="black" d="M372.74,-544.83C372.2,-537.13 371.57,-527.97 370.97,-519.42"/> +<polygon fill="black" stroke="black" points="374.46,-519.15 370.28,-509.41 367.48,-519.63 374.46,-519.15"/> +</g> +<!-- cs42l51.0-004a_PGA-ADC Mux Left->cs42l51.0-004a_Left PGA --> +<g id="edge10" class="edge"> +<title>cs42l51.0-004a_PGA-ADC Mux Left->cs42l51.0-004a_Left PGA</title> +<path fill="none" stroke="black" d="M804.92,-470.99C804.27,-460.3 803.44,-446.5 802.71,-434.37"/> +<polygon fill="black" stroke="black" points="806.2,-434.03 802.1,-424.26 799.21,-434.45 806.2,-434.03"/> +</g> +<!-- cs42l51.0-004a_Right PGA --> +<g id="node27" class="node"> +<title>cs42l51.0-004a_Right PGA</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="688.5,-424 605.5,-424 605.5,-386 688.5,-386 688.5,-424"/> +<text text-anchor="middle" x="647" y="-408.8" font-family="sans-serif" font-size="14.00">Right PGA</text> +<text text-anchor="middle" x="647" y="-393.8" font-family="sans-serif" font-size="14.00">[pga]</text> +</g> +<!-- cs42l51.0-004a_PGA-ADC Mux Right->cs42l51.0-004a_Right PGA --> +<g id="edge19" class="edge"> +<title>cs42l51.0-004a_PGA-ADC Mux Right->cs42l51.0-004a_Right PGA</title> +<path fill="none" stroke="black" d="M643.87,-470.99C644.38,-460.3 645.05,-446.5 645.63,-434.37"/> +<polygon fill="black" stroke="black" points="649.13,-434.42 646.12,-424.26 642.14,-434.08 649.13,-434.42"/> +</g> +<!-- cs42l51.0-004a_Playback->cs42l51.0-004a_DAC Mux --> +<g id="edge5" class="edge"> +<title>cs42l51.0-004a_Playback->cs42l51.0-004a_DAC Mux</title> +<path fill="none" stroke="black" d="M560,-237.83C560,-230.13 560,-220.97 560,-212.42"/> +<polygon fill="black" stroke="black" points="563.5,-212.41 560,-202.41 556.5,-212.41 563.5,-212.41"/> +</g> +<!-- cs42l51.0-004a_Right ADC --> +<g id="node25" class="node"> +<title>cs42l51.0-004a_Right ADC</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="697,-350 613,-350 613,-312 697,-312 697,-350"/> +<text text-anchor="middle" x="655" y="-334.8" font-family="sans-serif" font-size="14.00">Right ADC</text> +<text text-anchor="middle" x="655" y="-319.8" font-family="sans-serif" font-size="14.00">[adc]</text> +</g> +<!-- cs42l51.0-004a_Right ADC->cs42l51.0-004a_Capture --> +<g id="edge3" class="edge"> +<title>cs42l51.0-004a_Right ADC->cs42l51.0-004a_Capture</title> +<path fill="none" stroke="black" d="M655,-311.83C655,-304.13 655,-294.97 655,-286.42"/> +<polygon fill="black" stroke="black" points="658.5,-286.41 655,-276.41 651.5,-286.41 658.5,-286.41"/> +</g> +<!-- cs42l51.0-004a_Right DAC->cs42l51.0-004a_HPR --> +<g id="edge7" class="edge"> +<title>cs42l51.0-004a_Right DAC->cs42l51.0-004a_HPR</title> +<path fill="none" stroke="black" d="M608,-89.83C608,-82.13 608,-72.97 608,-64.42"/> +<polygon fill="black" stroke="black" points="611.5,-64.41 608,-54.41 604.5,-64.41 611.5,-64.41"/> +</g> +<!-- cs42l51.0-004a_Right PGA->cs42l51.0-004a_Right ADC --> +<g id="edge17" class="edge"> +<title>cs42l51.0-004a_Right PGA->cs42l51.0-004a_Right ADC</title> +<path fill="none" stroke="black" d="M649.02,-385.83C649.87,-378.13 650.89,-368.97 651.84,-360.42"/> +<polygon fill="black" stroke="black" points="655.33,-360.74 652.95,-350.41 648.37,-359.97 655.33,-360.74"/> +</g> +<!-- hdmi-audio-codec.1.auto_TX --> +<g id="node30" class="node"> +<title>hdmi-audio-codec.1.auto_TX</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="281.5,-509 210.5,-509 210.5,-471 281.5,-471 281.5,-509"/> +<text text-anchor="middle" x="246" y="-493.8" font-family="sans-serif" font-size="14.00">TX</text> +<text text-anchor="middle" x="246" y="-478.8" font-family="sans-serif" font-size="14.00">[output]</text> +</g> +<!-- hdmi-audio-codec.1.auto_I2S Playback->hdmi-audio-codec.1.auto_TX --> +<g id="edge22" class="edge"> +<title>hdmi-audio-codec.1.auto_I2S Playback->hdmi-audio-codec.1.auto_TX</title> +<path fill="none" stroke="black" d="M254.22,-544.83C253.05,-537.13 251.65,-527.97 250.34,-519.42"/> +<polygon fill="black" stroke="black" points="253.78,-518.77 248.81,-509.41 246.86,-519.83 253.78,-518.77"/> +</g> +<!-- hdmi-audio-codec.1.auto_RX --> +<g id="node29" class="node"> +<title>hdmi-audio-codec.1.auto_RX</title> +<polygon fill="#f2f2f2" stroke="#4d4d4d" points="189.5,-583 118.5,-583 118.5,-545 189.5,-545 189.5,-583"/> +<text text-anchor="middle" x="154" y="-567.8" font-family="sans-serif" font-size="14.00">RX</text> +<text text-anchor="middle" x="154" y="-552.8" font-family="sans-serif" font-size="14.00">[output]</text> +</g> +<!-- hdmi-audio-codec.1.auto_RX->hdmi-audio-codec.1.auto_Capture --> +<g id="edge20" class="edge"> +<title>hdmi-audio-codec.1.auto_RX->hdmi-audio-codec.1.auto_Capture</title> +<path fill="none" stroke="black" d="M154.25,-544.83C154.36,-537.13 154.49,-527.97 154.61,-519.42"/> +<polygon fill="black" stroke="black" points="158.1,-519.46 154.74,-509.41 151.11,-519.36 158.1,-519.46"/> +</g> +</g> +</svg> diff --git a/Documentation/sound/soc/dapm.rst b/Documentation/sound/soc/dapm.rst index c3154ce6e1b2..14c4dc026e6b 100644 --- a/Documentation/sound/soc/dapm.rst +++ b/Documentation/sound/soc/dapm.rst @@ -7,8 +7,8 @@ Description Dynamic Audio Power Management (DAPM) is designed to allow portable Linux devices to use the minimum amount of power within the audio -subsystem at all times. It is independent of other kernel PM and as -such, can easily co-exist with the other PM systems. +subsystem at all times. It is independent of other kernel power +management frameworks and, as such, can easily co-exist with them. DAPM is also completely transparent to all user space applications as all power switching is done within the ASoC core. No code changes or @@ -16,11 +16,29 @@ recompiling are required for user space applications. DAPM makes power switching decisions based upon any audio stream (capture/playback) activity and audio mixer settings within the device. -DAPM spans the whole machine. It covers power control within the entire -audio subsystem, this includes internal codec power blocks and machine -level power systems. +DAPM is based on two basic elements, called widgets and routes: -There are 4 power domains within DAPM + * a **widget** is every part of the audio hardware that can be enabled by + software when in use and disabled to save power when not in use + * a **route** is an interconnection between widgets that exists when sound + can flow from one widget to the other + +All DAPM power switching decisions are made automatically by consulting an +audio routing graph. This graph is specific to each sound card and spans +the whole sound card, so some DAPM routes connect two widgets belonging to +different components (e.g. the LINE OUT pin of a CODEC and the input pin of +an amplifier). + +The graph for the STM32MP1-DK1 sound card is shown in picture: + +.. kernel-figure:: dapm-graph.svg + :alt: Example DAPM graph + :align: center + +DAPM power domains +================== + +There are 4 power domains within DAPM: Codec bias domain VREF, VMID (core codec and audio power) @@ -47,17 +65,11 @@ Stream domain Enabled and disabled when stream playback/capture is started and stopped respectively. e.g. aplay, arecord. -All DAPM power switching decisions are made automatically by consulting an audio -routing map of the whole machine. This map is specific to each machine and -consists of the interconnections between every audio component (including -internal codec components). All audio components that effect power are called -widgets hereafter. - DAPM Widgets ============ -Audio DAPM widgets fall into a number of types:- +Audio DAPM widgets fall into a number of types: Mixer Mixes several analog signals into a single analog signal. @@ -141,14 +153,14 @@ Stream Widgets relate to the stream power domain and only consist of ADCs (analog to digital converters), DACs (digital to analog converters), AIF IN and AIF OUT. -Stream widgets have the following format:- +Stream widgets have the following format: :: SND_SOC_DAPM_DAC(name, stream name, reg, shift, invert), SND_SOC_DAPM_AIF_IN(name, stream, slot, reg, shift, invert) NOTE: the stream name must match the corresponding stream name in your codec -snd_soc_codec_dai. +snd_soc_dai_driver. e.g. stream widgets for HiFi playback and capture :: @@ -167,7 +179,7 @@ Path Domain Widgets ------------------- Path domain widgets have a ability to control or affect the audio signal or -audio paths within the audio subsystem. They have the following form:- +audio paths within the audio subsystem. They have the following form: :: SND_SOC_DAPM_PGA(name, reg, shift, invert, controls, num_controls) @@ -207,7 +219,7 @@ powered. e.g. A machine widget can have an optional call back. e.g. Jack connector widget for an external Mic that enables Mic Bias -when the Mic is inserted:-:: +when the Mic is inserted:: static int spitz_mic_bias(struct snd_soc_dapm_widget* w, int event) { @@ -221,7 +233,7 @@ when the Mic is inserted:-:: Codec (BIAS) Domain ------------------- -The codec bias power domain has no widgets and is handled by the codecs DAPM +The codec bias power domain has no widgets and is handled by the codec DAPM event handler. This handler is called when the codec powerstate is changed wrt to any stream event or by kernel PM events. @@ -229,17 +241,58 @@ to any stream event or by kernel PM events. Virtual Widgets --------------- -Sometimes widgets exist in the codec or machine audio map that don't have any +Sometimes widgets exist in the codec or machine audio graph that don't have any corresponding soft power control. In this case it is necessary to create a virtual widget - a widget with no control bits e.g. :: SND_SOC_DAPM_MIXER("AC97 Mixer", SND_SOC_NOPM, 0, 0, NULL, 0), -This can be used to merge to signal paths together in software. +This can be used to merge two signal paths together in software. -After all the widgets have been defined, they can then be added to the DAPM -subsystem individually with a call to snd_soc_dapm_new_control(). +Registering DAPM controls +========================= + +In many cases the DAPM widgets are implemented statically in a ``static +const struct snd_soc_dapm_widget`` array in a codec driver, and simply +declared via the ``dapm_widgets`` and ``num_dapm_widgets`` fields of the +``struct snd_soc_component_driver``. + +Similarly, routes connecting them are implemented statically in a ``static +const struct snd_soc_dapm_route`` array and declared via the +``dapm_routes`` and ``num_dapm_routes`` fields of the same struct. + +With the above declared, the driver registration will take care of +populating them:: + + static const struct snd_soc_dapm_widget wm2000_dapm_widgets[] = { + SND_SOC_DAPM_OUTPUT("SPKN"), + SND_SOC_DAPM_OUTPUT("SPKP"), + ... + }; + + /* Target, Path, Source */ + static const struct snd_soc_dapm_route wm2000_audio_map[] = { + { "SPKN", NULL, "ANC Engine" }, + { "SPKP", NULL, "ANC Engine" }, + ... + }; + + static const struct snd_soc_component_driver soc_component_dev_wm2000 = { + ... + .dapm_widgets = wm2000_dapm_widgets, + .num_dapm_widgets = ARRAY_SIZE(wm2000_dapm_widgets), + .dapm_routes = wm2000_audio_map, + .num_dapm_routes = ARRAY_SIZE(wm2000_audio_map), + ... + }; + +In more complex cases the list of DAPM widgets and/or routes can be only +known at probe time. This happens for example when a driver supports +different models having a different set of features. In those cases +separate widgets and routes arrays implementing the case-specific features +can be registered programmatically by calling snd_soc_dapm_new_controls() +and snd_soc_dapm_add_routes(). Codec/DSP Widget Interconnections @@ -247,31 +300,29 @@ Codec/DSP Widget Interconnections Widgets are connected to each other within the codec, platform and machine by audio paths (called interconnections). Each interconnection must be defined in -order to create a map of all audio paths between widgets. +order to create a graph of all audio paths between widgets. This is easiest with a diagram of the codec or DSP (and schematic of the machine audio system), as it requires joining widgets together via their audio signal paths. -e.g., from the WM8731 output mixer (wm8731.c) - -The WM8731 output mixer has 3 inputs (sources) +For example the WM8731 output mixer (wm8731.c) has 3 inputs (sources): 1. Line Bypass Input 2. DAC (HiFi playback) 3. Mic Sidetone Input -Each input in this example has a kcontrol associated with it (defined in example -above) and is connected to the output mixer via its kcontrol name. We can now -connect the destination widget (wrt audio signal) with its source widgets. -:: +Each input in this example has a kcontrol associated with it (defined in +the example above) and is connected to the output mixer via its kcontrol +name. We can now connect the destination widget (wrt audio signal) with its +source widgets. :: /* output mixer */ {"Output Mixer", "Line Bypass Switch", "Line Input"}, {"Output Mixer", "HiFi Playback Switch", "DAC"}, {"Output Mixer", "Mic Sidetone Switch", "Mic Bias"}, -So we have :- +So we have: * Destination Widget <=== Path Name <=== Source Widget, or * Sink, Path, Source, or @@ -280,12 +331,11 @@ So we have :- When there is no path name connecting widgets (e.g. a direct connection) we pass NULL for the path name. -Interconnections are created with a call to:- -:: +Interconnections are created with a call to:: snd_soc_dapm_connect_input(codec, sink, path, source); -Finally, snd_soc_dapm_new_widgets(codec) must be called after all widgets and +Finally, snd_soc_dapm_new_widgets() must be called after all widgets and interconnections have been registered with the core. This causes the core to scan the codec and machine so that the internal DAPM state matches the physical state of the machine. @@ -326,35 +376,44 @@ jacks can also be switched OFF. DAPM Widget Events ================== -Some widgets can register their interest with the DAPM core in PM events. -e.g. A Speaker with an amplifier registers a widget so the amplifier can be -powered only when the spk is in use. -:: +Widgets needing to implement a more complex behaviour than what DAPM can do +can set a custom "event handler" by setting a function pointer. An example +is a power supply needing to enable a GPIO:: - /* turn speaker amplifier on/off depending on use */ - static int corgi_amp_event(struct snd_soc_dapm_widget *w, int event) + static int sof_es8316_speaker_power_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, int event) { - gpio_set_value(CORGI_GPIO_APM_ON, SND_SOC_DAPM_EVENT_ON(event)); - return 0; + if (SND_SOC_DAPM_EVENT_ON(event)) + gpiod_set_value_cansleep(gpio_pa, true); + else + gpiod_set_value_cansleep(gpio_pa, false); + + return 0; } - /* corgi machine dapm widgets */ - static const struct snd_soc_dapm_widget wm8731_dapm_widgets = - SND_SOC_DAPM_SPK("Ext Spk", corgi_amp_event); + static const struct snd_soc_dapm_widget st_widgets[] = { + ... + SND_SOC_DAPM_SUPPLY("Speaker Power", SND_SOC_NOPM, 0, 0, + sof_es8316_speaker_power_event, + SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMU), + }; -Please see soc-dapm.h for all other widgets that support events. +See soc-dapm.h for all other widgets that support events. Event types ----------- -The following event types are supported by event widgets. -:: +The following event types are supported by event widgets:: /* dapm event types */ - #define SND_SOC_DAPM_PRE_PMU 0x1 /* before widget power up */ - #define SND_SOC_DAPM_POST_PMU 0x2 /* after widget power up */ - #define SND_SOC_DAPM_PRE_PMD 0x4 /* before widget power down */ - #define SND_SOC_DAPM_POST_PMD 0x8 /* after widget power down */ - #define SND_SOC_DAPM_PRE_REG 0x10 /* before audio path setup */ - #define SND_SOC_DAPM_POST_REG 0x20 /* after audio path setup */ + #define SND_SOC_DAPM_PRE_PMU 0x1 /* before widget power up */ + #define SND_SOC_DAPM_POST_PMU 0x2 /* after widget power up */ + #define SND_SOC_DAPM_PRE_PMD 0x4 /* before widget power down */ + #define SND_SOC_DAPM_POST_PMD 0x8 /* after widget power down */ + #define SND_SOC_DAPM_PRE_REG 0x10 /* before audio path setup */ + #define SND_SOC_DAPM_POST_REG 0x20 /* after audio path setup */ + #define SND_SOC_DAPM_WILL_PMU 0x40 /* called at start of sequence */ + #define SND_SOC_DAPM_WILL_PMD 0x80 /* called at start of sequence */ + #define SND_SOC_DAPM_PRE_POST_PMD (SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMD) + #define SND_SOC_DAPM_PRE_POST_PMU (SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU) diff --git a/MAINTAINERS b/MAINTAINERS index 2eda0f98adb5..dc6818d0938d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2191,7 +2191,6 @@ N: mxs ARM/FREESCALE LAYERSCAPE ARM ARCHITECTURE M: Shawn Guo <shawnguo@kernel.org> -M: Li Yang <leoyang.li@nxp.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git @@ -2708,7 +2707,7 @@ F: sound/soc/rockchip/ N: rockchip ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org @@ -3573,6 +3572,7 @@ S: Supported C: irc://irc.oftc.net/bcache T: git https://evilpiepirate.org/git/bcachefs.git F: fs/bcachefs/ +F: Documentation/filesystems/bcachefs/ BDISP ST MEDIA DRIVER M: Fabien Dessenne <fabien.dessenne@foss.st.com> @@ -4869,7 +4869,6 @@ F: drivers/power/supply/cw2015_battery.c CEPH COMMON CODE (LIBCEPH) M: Ilya Dryomov <idryomov@gmail.com> M: Xiubo Li <xiubli@redhat.com> -R: Jeff Layton <jlayton@kernel.org> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ @@ -4881,7 +4880,6 @@ F: net/ceph/ CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH) M: Xiubo Li <xiubli@redhat.com> M: Ilya Dryomov <idryomov@gmail.com> -R: Jeff Layton <jlayton@kernel.org> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ @@ -5557,7 +5555,7 @@ F: drivers/cpuidle/cpuidle-big_little.c CPUIDLE DRIVER - ARM EXYNOS M: Daniel Lezcano <daniel.lezcano@linaro.org> M: Kukjin Kim <kgene@kernel.org> -R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +R: Krzysztof Kozlowski <krzk@kernel.org> L: linux-pm@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -7831,9 +7829,8 @@ W: http://aeschi.ch.eu.org/efs/ F: fs/efs/ EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER -M: Douglas Miller <dougmill@linux.ibm.com> L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/ethernet/ibm/ehea/ ELM327 CAN NETWORK DRIVER @@ -8523,7 +8520,6 @@ S: Maintained F: drivers/video/fbdev/fsl-diu-fb.* FREESCALE DMA DRIVER -M: Li Yang <leoyang.li@nxp.com> M: Zhang Wei <zw@zh-kernel.org> L: linuxppc-dev@lists.ozlabs.org S: Maintained @@ -8688,10 +8684,9 @@ F: drivers/soc/fsl/qe/tsa.h F: include/dt-bindings/soc/cpm1-fsl,tsa.h FREESCALE QUICC ENGINE UCC ETHERNET DRIVER -M: Li Yang <leoyang.li@nxp.com> L: netdev@vger.kernel.org L: linuxppc-dev@lists.ozlabs.org -S: Maintained +S: Orphan F: drivers/net/ethernet/freescale/ucc_geth* FREESCALE QUICC ENGINE UCC HDLC DRIVER @@ -8708,10 +8703,9 @@ S: Maintained F: drivers/tty/serial/ucc_uart.c FREESCALE SOC DRIVERS -M: Li Yang <leoyang.li@nxp.com> L: linuxppc-dev@lists.ozlabs.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml F: Documentation/devicetree/bindings/soc/fsl/ F: drivers/soc/fsl/ @@ -8745,17 +8739,15 @@ F: Documentation/devicetree/bindings/sound/fsl,qmc-audio.yaml F: sound/soc/fsl/fsl_qmc_audio.c FREESCALE USB PERIPHERAL DRIVERS -M: Li Yang <leoyang.li@nxp.com> L: linux-usb@vger.kernel.org L: linuxppc-dev@lists.ozlabs.org -S: Maintained +S: Orphan F: drivers/usb/gadget/udc/fsl* FREESCALE USB PHY DRIVER -M: Ran Wang <ran.wang_1@nxp.com> L: linux-usb@vger.kernel.org L: linuxppc-dev@lists.ozlabs.org -S: Maintained +S: Orphan F: drivers/usb/phy/phy-fsl-usb* FREEVXFS FILESYSTEM @@ -9000,7 +8992,7 @@ F: drivers/i2c/muxes/i2c-mux-gpio.c F: include/linux/platform_data/i2c-mux-gpio.h GENERIC GPIO RESET DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> S: Maintained F: drivers/reset/reset-gpio.c @@ -9583,7 +9575,7 @@ F: kernel/power/ HID CORE LAYER M: Jiri Kosina <jikos@kernel.org> -M: Benjamin Tissoires <benjamin.tissoires@redhat.com> +M: Benjamin Tissoires <bentiss@kernel.org> L: linux-input@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git @@ -10030,7 +10022,7 @@ F: drivers/media/platform/st/sti/hva HWPOISON MEMORY FAILURE HANDLING M: Miaohe Lin <linmiaohe@huawei.com> -R: Naoya Horiguchi <naoya.horiguchi@nec.com> +R: Naoya Horiguchi <nao.horiguchi@gmail.com> L: linux-mm@kvack.org S: Maintained F: mm/hwpoison-inject.c @@ -12001,7 +11993,7 @@ F: include/keys/encrypted-type.h F: security/keys/encrypted-keys/ KEYS-TRUSTED -M: James Bottomley <jejb@linux.ibm.com> +M: James Bottomley <James.Bottomley@HansenPartnership.com> M: Jarkko Sakkinen <jarkko@kernel.org> M: Mimi Zohar <zohar@linux.ibm.com> L: linux-integrity@vger.kernel.org @@ -13295,7 +13287,7 @@ F: drivers/iio/adc/max11205.c MAXIM MAX17040 FAMILY FUEL GAUGE DRIVERS R: Iskren Chernev <iskren.chernev@gmail.com> -R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +R: Krzysztof Kozlowski <krzk@kernel.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Matheus Castello <matheus@castello.eng.br> L: linux-pm@vger.kernel.org @@ -13305,7 +13297,7 @@ F: drivers/power/supply/max17040_battery.c MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS R: Hans de Goede <hdegoede@redhat.com> -R: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +R: Krzysztof Kozlowski <krzk@kernel.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm> R: Purism Kernel Team <kernel@puri.sm> @@ -13363,7 +13355,7 @@ F: Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml F: drivers/power/supply/max77976_charger.c MAXIM MUIC CHARGER DRIVERS FOR EXYNOS BASED BOARDS -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-pm@vger.kernel.org S: Maintained B: mailto:linux-samsung-soc@vger.kernel.org @@ -13374,7 +13366,7 @@ F: drivers/power/supply/max77693_charger.c MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS M: Chanwoo Choi <cw00.choi@samsung.com> -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained B: mailto:linux-samsung-soc@vger.kernel.org @@ -14158,7 +14150,7 @@ F: mm/mm_init.c F: tools/testing/memblock/ MEMORY CONTROLLER DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained B: mailto:krzysztof.kozlowski@linaro.org @@ -14363,7 +14355,7 @@ F: drivers/dma/at_xdmac.c F: include/dt-bindings/dma/at91.h MICROCHIP AT91 SERIAL DRIVER -M: Richard Genoud <richard.genoud@gmail.com> +M: Richard Genoud <richard.genoud@bootlin.com> S: Maintained F: Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml F: drivers/tty/serial/atmel_serial.c @@ -15539,7 +15531,7 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/nfc/ @@ -15916,7 +15908,7 @@ F: Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml F: drivers/regulator/pf8x00-regulator.c NXP PTN5150A CC LOGIC AND EXTCON DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/extcon/extcon-ptn5150.yaml @@ -16527,7 +16519,7 @@ K: of_overlay_remove OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS M: Rob Herring <robh@kernel.org> -M: Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org> +M: Krzysztof Kozlowski <krzk+dt@kernel.org> M: Conor Dooley <conor+dt@kernel.org> L: devicetree@vger.kernel.org S: Maintained @@ -16974,7 +16966,6 @@ F: drivers/pci/controller/dwc/pci-exynos.c PCI DRIVER FOR SYNOPSYS DESIGNWARE M: Jingoo Han <jingoohan1@gmail.com> -M: Gustavo Pimentel <gustavo.pimentel@synopsys.com> M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> L: linux-pci@vger.kernel.org S: Maintained @@ -17485,7 +17476,7 @@ F: Documentation/devicetree/bindings/pinctrl/renesas,* F: drivers/pinctrl/renesas/ PIN CONTROLLER - SAMSUNG -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -19460,7 +19451,7 @@ F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -19495,7 +19486,7 @@ S: Maintained F: drivers/platform/x86/samsung-laptop.c SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-kernel@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -19521,7 +19512,7 @@ F: drivers/media/platform/samsung/s3c-camif/ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> S: Maintained F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml F: drivers/nfc/s3fwrn5 @@ -19542,7 +19533,7 @@ S: Supported F: drivers/media/i2c/s5k5baf.c SAMSUNG S5P Security SubSystem (SSS) DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Vladimir Zapolskiy <vz@mleia.com> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -19564,7 +19555,7 @@ F: Documentation/devicetree/bindings/media/samsung,fimc.yaml F: drivers/media/platform/samsung/exynos4-is/ SAMSUNG SOC CLOCK DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> M: Chanwoo Choi <cw00.choi@samsung.com> R: Alim Akhtar <alim.akhtar@samsung.com> @@ -19596,7 +19587,7 @@ F: drivers/net/ethernet/samsung/sxgbe/ SAMSUNG THERMAL DRIVER M: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-pm@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -19683,7 +19674,7 @@ F: drivers/scsi/sg.c F: include/scsi/sg.h SCSI SUBSYSTEM -M: "James E.J. Bottomley" <jejb@linux.ibm.com> +M: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> M: "Martin K. Petersen" <martin.petersen@oracle.com> L: linux-scsi@vger.kernel.org S: Maintained @@ -22590,6 +22581,7 @@ Q: https://patchwork.kernel.org/project/linux-pm/list/ B: https://bugzilla.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat F: tools/power/x86/turbostat/ +F: tools/testing/selftests/turbostat/ TW5864 VIDEO4LINUX DRIVER M: Bluecherry Maintainers <maintainers@bluecherrydvr.com> @@ -22859,7 +22851,7 @@ F: drivers/usb/host/ehci* USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...) M: Jiri Kosina <jikos@kernel.org> -M: Benjamin Tissoires <benjamin.tissoires@redhat.com> +M: Benjamin Tissoires <bentiss@kernel.org> L: linux-usb@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git @@ -23798,7 +23790,7 @@ S: Orphan F: drivers/mmc/host/vub300.c W1 DALLAS'S 1-WIRE BUS -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> S: Maintained F: Documentation/devicetree/bindings/w1/ F: Documentation/w1/ @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc5 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 9f066785bb71..65afb1de48b3 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1172,12 +1172,12 @@ config PAGE_SIZE_LESS_THAN_256KB config PAGE_SHIFT int - default 12 if PAGE_SIZE_4KB - default 13 if PAGE_SIZE_8KB - default 14 if PAGE_SIZE_16KB - default 15 if PAGE_SIZE_32KB - default 16 if PAGE_SIZE_64KB - default 18 if PAGE_SIZE_256KB + default 12 if PAGE_SIZE_4KB + default 13 if PAGE_SIZE_8KB + default 14 if PAGE_SIZE_16KB + default 15 if PAGE_SIZE_32KB + default 16 if PAGE_SIZE_64KB + default 18 if PAGE_SIZE_256KB # This allows to use a set of generic functions to determine mmap base # address by giving priority to top-down scheme only if the process diff --git a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi index 1235a71c6abe..52869e68f833 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7-mba7.dtsi @@ -666,7 +666,7 @@ bus-width = <4>; no-1-8-v; no-sdio; - no-emmc; + no-mmc; status = "okay"; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts b/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts index ba7231b364bb..7bab113ca6da 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts +++ b/arch/arm/boot/dts/nxp/imx/imx7s-warp.dts @@ -210,6 +210,7 @@ remote-endpoint = <&mipi_from_sensor>; clock-lanes = <0>; data-lanes = <1>; + link-frequencies = /bits/ 64 <330000000>; }; }; }; diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index 31755a378c73..ff2a4a4d8220 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -79,10 +79,8 @@ static struct musb_hdrc_platform_data tusb_data = { static struct gpiod_lookup_table tusb_gpio_table = { .dev_id = "musb-tusb", .table = { - GPIO_LOOKUP("gpio-0-15", 0, "enable", - GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("gpio-48-63", 10, "int", - GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-0-31", 0, "enable", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-32-63", 26, "int", GPIO_ACTIVE_HIGH), { } }, }; @@ -140,12 +138,11 @@ static int slot1_cover_open; static int slot2_cover_open; static struct device *mmc_device; -static struct gpiod_lookup_table nokia8xx_mmc_gpio_table = { +static struct gpiod_lookup_table nokia800_mmc_gpio_table = { .dev_id = "mmci-omap.0", .table = { /* Slot switch, GPIO 96 */ - GPIO_LOOKUP("gpio-80-111", 16, - "switch", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("gpio-96-127", 0, "switch", GPIO_ACTIVE_HIGH), { } }, }; @@ -153,12 +150,12 @@ static struct gpiod_lookup_table nokia8xx_mmc_gpio_table = { static struct gpiod_lookup_table nokia810_mmc_gpio_table = { .dev_id = "mmci-omap.0", .table = { + /* Slot switch, GPIO 96 */ + GPIO_LOOKUP("gpio-96-127", 0, "switch", GPIO_ACTIVE_HIGH), /* Slot index 1, VSD power, GPIO 23 */ - GPIO_LOOKUP_IDX("gpio-16-31", 7, - "vsd", 1, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP_IDX("gpio-0-31", 23, "vsd", 1, GPIO_ACTIVE_HIGH), /* Slot index 1, VIO power, GPIO 9 */ - GPIO_LOOKUP_IDX("gpio-0-15", 9, - "vio", 1, GPIO_ACTIVE_HIGH), + GPIO_LOOKUP_IDX("gpio-0-31", 9, "vio", 1, GPIO_ACTIVE_HIGH), { } }, }; @@ -415,8 +412,6 @@ static struct omap_mmc_platform_data *mmc_data[OMAP24XX_NR_MMC]; static void __init n8x0_mmc_init(void) { - gpiod_add_lookup_table(&nokia8xx_mmc_gpio_table); - if (board_is_n810()) { mmc1_data.slots[0].name = "external"; @@ -429,6 +424,8 @@ static void __init n8x0_mmc_init(void) mmc1_data.slots[1].name = "internal"; mmc1_data.slots[1].ban_openended = 1; gpiod_add_lookup_table(&nokia810_mmc_gpio_table); + } else { + gpiod_add_lookup_table(&nokia800_mmc_gpio_table); } mmc1_data.nr_slots = 2; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 3c42240e78e2..4aaf5a0c1ed8 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -41,7 +41,7 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 267 IRQ_TYPE_LEVEL_HIGH>; fsl,usbphy = <&usbphy1>; fsl,usbmisc = <&usbmisc1 0>; - clocks = <&usb2_lpcg 0>; + clocks = <&usb2_lpcg IMX_LPCG_CLK_6>; ahb-burst-config = <0x0>; tx-burst-size-dword = <0x10>; rx-burst-size-dword = <0x10>; @@ -58,7 +58,7 @@ conn_subsys: bus@5b000000 { usbphy1: usbphy@5b100000 { compatible = "fsl,imx7ulp-usbphy"; reg = <0x5b100000 0x1000>; - clocks = <&usb2_lpcg 1>; + clocks = <&usb2_lpcg IMX_LPCG_CLK_7>; power-domains = <&pd IMX_SC_R_USB_0_PHY>; status = "disabled"; }; @@ -67,8 +67,8 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b010000 0x10000>; clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>, - <&sdhc0_lpcg IMX_LPCG_CLK_0>, - <&sdhc0_lpcg IMX_LPCG_CLK_5>; + <&sdhc0_lpcg IMX_LPCG_CLK_5>, + <&sdhc0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_0>; status = "disabled"; @@ -78,8 +78,8 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 233 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b020000 0x10000>; clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>, - <&sdhc1_lpcg IMX_LPCG_CLK_0>, - <&sdhc1_lpcg IMX_LPCG_CLK_5>; + <&sdhc1_lpcg IMX_LPCG_CLK_5>, + <&sdhc1_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_1>; fsl,tuning-start-tap = <20>; @@ -91,8 +91,8 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 234 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b030000 0x10000>; clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>, - <&sdhc2_lpcg IMX_LPCG_CLK_0>, - <&sdhc2_lpcg IMX_LPCG_CLK_5>; + <&sdhc2_lpcg IMX_LPCG_CLK_5>, + <&sdhc2_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_2>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi index cab3468b1875..f7a91d43a0ff 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-dma.dtsi @@ -28,8 +28,8 @@ dma_subsys: bus@5a000000 { #size-cells = <0>; interrupts = <GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&spi0_lpcg 0>, - <&spi0_lpcg 1>; + clocks = <&spi0_lpcg IMX_LPCG_CLK_0>, + <&spi0_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -44,8 +44,8 @@ dma_subsys: bus@5a000000 { #size-cells = <0>; interrupts = <GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&spi1_lpcg 0>, - <&spi1_lpcg 1>; + clocks = <&spi1_lpcg IMX_LPCG_CLK_0>, + <&spi1_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -60,8 +60,8 @@ dma_subsys: bus@5a000000 { #size-cells = <0>; interrupts = <GIC_SPI 338 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&spi2_lpcg 0>, - <&spi2_lpcg 1>; + clocks = <&spi2_lpcg IMX_LPCG_CLK_0>, + <&spi2_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_2 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -76,8 +76,8 @@ dma_subsys: bus@5a000000 { #size-cells = <0>; interrupts = <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&spi3_lpcg 0>, - <&spi3_lpcg 1>; + clocks = <&spi3_lpcg IMX_LPCG_CLK_0>, + <&spi3_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_SPI_3 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <60000000>; @@ -145,8 +145,8 @@ dma_subsys: bus@5a000000 { compatible = "fsl,imx8qxp-pwm", "fsl,imx27-pwm"; reg = <0x5a190000 0x1000>; interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&adma_pwm_lpcg 1>, - <&adma_pwm_lpcg 0>; + clocks = <&adma_pwm_lpcg IMX_LPCG_CLK_4>, + <&adma_pwm_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_LCD_0_PWM_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; @@ -355,8 +355,8 @@ dma_subsys: bus@5a000000 { reg = <0x5a880000 0x10000>; interrupts = <GIC_SPI 240 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&adc0_lpcg 0>, - <&adc0_lpcg 1>; + clocks = <&adc0_lpcg IMX_LPCG_CLK_0>, + <&adc0_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_ADC_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; @@ -370,8 +370,8 @@ dma_subsys: bus@5a000000 { reg = <0x5a890000 0x10000>; interrupts = <GIC_SPI 241 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&adc1_lpcg 0>, - <&adc1_lpcg 1>; + clocks = <&adc1_lpcg IMX_LPCG_CLK_0>, + <&adc1_lpcg IMX_LPCG_CLK_4>; clock-names = "per", "ipg"; assigned-clocks = <&clk IMX_SC_R_ADC_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; @@ -384,8 +384,8 @@ dma_subsys: bus@5a000000 { reg = <0x5a8d0000 0x10000>; interrupts = <GIC_SPI 235 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; @@ -405,8 +405,8 @@ dma_subsys: bus@5a000000 { * CAN1 shares CAN0's clock and to enable CAN0's clock it * has to be powered on. */ - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; @@ -426,8 +426,8 @@ dma_subsys: bus@5a000000 { * CAN2 shares CAN0's clock and to enable CAN0's clock it * has to be powered on. */ - clocks = <&can0_lpcg 1>, - <&can0_lpcg 0>; + clocks = <&can0_lpcg IMX_LPCG_CLK_4>, + <&can0_lpcg IMX_LPCG_CLK_0>; clock-names = "ipg", "per"; assigned-clocks = <&clk IMX_SC_R_CAN_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <40000000>; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi index 7e510b21bbac..764c1a08e3b1 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi @@ -25,8 +25,8 @@ lsio_subsys: bus@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d000000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm0_lpcg 4>, - <&pwm0_lpcg 1>; + clocks = <&pwm0_lpcg IMX_LPCG_CLK_6>, + <&pwm0_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; #pwm-cells = <3>; @@ -38,8 +38,8 @@ lsio_subsys: bus@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d010000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm1_lpcg 4>, - <&pwm1_lpcg 1>; + clocks = <&pwm1_lpcg IMX_LPCG_CLK_6>, + <&pwm1_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; #pwm-cells = <3>; @@ -51,8 +51,8 @@ lsio_subsys: bus@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d020000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm2_lpcg 4>, - <&pwm2_lpcg 1>; + clocks = <&pwm2_lpcg IMX_LPCG_CLK_6>, + <&pwm2_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_2 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; #pwm-cells = <3>; @@ -64,8 +64,8 @@ lsio_subsys: bus@5d000000 { compatible = "fsl,imx27-pwm"; reg = <0x5d030000 0x10000>; clock-names = "ipg", "per"; - clocks = <&pwm3_lpcg 4>, - <&pwm3_lpcg 1>; + clocks = <&pwm3_lpcg IMX_LPCG_CLK_6>, + <&pwm3_lpcg IMX_LPCG_CLK_1>; assigned-clocks = <&clk IMX_SC_R_PWM_3 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; #pwm-cells = <3>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi index 41c79d2ebdd6..f24b14744799 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi @@ -14,6 +14,7 @@ pinctrl-0 = <&pinctrl_usbcon1>; type = "micro"; label = "otg"; + vbus-supply = <®_usb1_vbus>; id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; port { @@ -183,7 +184,6 @@ }; &usb3_phy0 { - vbus-supply = <®_usb1_vbus>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi index d5c400b355af..f5491a608b2f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi @@ -14,6 +14,7 @@ pinctrl-0 = <&pinctrl_usbcon1>; type = "micro"; label = "otg"; + vbus-supply = <®_usb1_vbus>; id-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; port { @@ -202,7 +203,6 @@ }; &usb3_phy0 { - vbus-supply = <®_usb1_vbus>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi index 11626fae5f97..aa9f28c4431d 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-dma.dtsi @@ -153,15 +153,15 @@ }; &flexcan2 { - clocks = <&can1_lpcg 1>, - <&can1_lpcg 0>; + clocks = <&can1_lpcg IMX_LPCG_CLK_4>, + <&can1_lpcg IMX_LPCG_CLK_0>; assigned-clocks = <&clk IMX_SC_R_CAN_1 IMX_SC_PM_CLK_PER>; fsl,clk-source = /bits/ 8 <1>; }; &flexcan3 { - clocks = <&can2_lpcg 1>, - <&can2_lpcg 0>; + clocks = <&can2_lpcg IMX_LPCG_CLK_4>, + <&can2_lpcg IMX_LPCG_CLK_0>; assigned-clocks = <&clk IMX_SC_R_CAN_2 IMX_SC_PM_CLK_PER>; fsl,clk-source = /bits/ 8 <1>; }; diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 3b0e8248e1a4..a75de2665d84 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -161,12 +161,18 @@ static inline unsigned long get_trans_granule(void) #define MAX_TLBI_RANGE_PAGES __TLBI_RANGE_PAGES(31, 3) /* - * Generate 'num' values from -1 to 30 with -1 rejected by the - * __flush_tlb_range() loop below. + * Generate 'num' values from -1 to 31 with -1 rejected by the + * __flush_tlb_range() loop below. Its return value is only + * significant for a maximum of MAX_TLBI_RANGE_PAGES pages. If + * 'pages' is more than that, you must iterate over the overall + * range. */ -#define TLBI_RANGE_MASK GENMASK_ULL(4, 0) -#define __TLBI_RANGE_NUM(pages, scale) \ - ((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1) +#define __TLBI_RANGE_NUM(pages, scale) \ + ({ \ + int __pages = min((pages), \ + __TLBI_RANGE_PAGES(31, (scale))); \ + (__pages >> (5 * (scale) + 1)) - 1; \ + }) /* * TLB Invalidation @@ -379,10 +385,6 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) * 3. If there is 1 page remaining, flush it through non-range operations. Range * operations can only span an even number of pages. We save this for last to * ensure 64KB start alignment is maintained for the LPA2 case. - * - * Note that certain ranges can be represented by either num = 31 and - * scale or num = 0 and scale + 1. The loop below favours the latter - * since num is limited to 30 by the __TLBI_RANGE_NUM() macro. */ #define __flush_tlb_range_op(op, start, pages, stride, \ asid, tlb_level, tlbi_user, lpa2) \ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 06234c3a15f3..cb68adcabe07 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -289,6 +289,11 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) adr_l x1, __hyp_text_end adr_l x2, dcache_clean_poc blr x2 + + mov_q x0, INIT_SCTLR_EL2_MMU_OFF + pre_disable_mmu_workaround + msr sctlr_el2, x0 + isb 0: mov_q x0, HCR_HOST_NVHE_FLAGS @@ -323,13 +328,11 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) cbz x0, 2f /* Set a sane SCTLR_EL1, the VHE way */ - pre_disable_mmu_workaround msr_s SYS_SCTLR_EL12, x1 mov x2, #BOOT_CPU_FLAG_E2H b 3f 2: - pre_disable_mmu_workaround msr sctlr_el1, x1 mov x2, xzr 3: diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 0f0e10bb0a95..b872b003a55f 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -276,7 +276,10 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, pte_t *ptep = NULL; pgdp = pgd_offset(mm, addr); - p4dp = p4d_offset(pgdp, addr); + p4dp = p4d_alloc(mm, pgdp, addr); + if (!p4dp) + return NULL; + pudp = pud_alloc(mm, p4dp, addr); if (!pudp) return NULL; diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 0c4e3ecf989d..0e270a1c51e6 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -219,9 +219,6 @@ bool kernel_page_present(struct page *page) pte_t *ptep; unsigned long addr = (unsigned long)page_address(page); - if (!can_set_direct_map()) - return true; - pgdp = pgd_offset_k(addr); if (pgd_none(READ_ONCE(*pgdp))) return false; diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi index 49a70f8c3cab..b6aeb1f70e2a 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi @@ -100,6 +100,13 @@ #size-cells = <2>; dma-coherent; + isa@18000000 { + compatible = "isa"; + #size-cells = <1>; + #address-cells = <2>; + ranges = <1 0x0 0x0 0x18000000 0x4000>; + }; + liointc0: interrupt-controller@1fe01400 { compatible = "loongson,liointc-2.0"; reg = <0x0 0x1fe01400 0x0 0x40>, diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts index dca91caf895e..74b99bd234cc 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts +++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts @@ -61,12 +61,45 @@ &gmac0 { status = "okay"; + + phy-mode = "gmii"; + phy-handle = <&phy0>; + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + phy0: ethernet-phy@0 { + reg = <2>; + }; + }; }; &gmac1 { status = "okay"; + + phy-mode = "gmii"; + phy-handle = <&phy1>; + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + phy1: ethernet-phy@1 { + reg = <2>; + }; + }; }; &gmac2 { status = "okay"; + + phy-mode = "rgmii"; + phy-handle = <&phy2>; + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + phy2: ethernet-phy@2 { + reg = <0>; + }; + }; }; diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi index a231949b5f55..9eab2d02cbe8 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi @@ -51,6 +51,13 @@ #address-cells = <2>; #size-cells = <2>; + isa@18400000 { + compatible = "isa"; + #size-cells = <1>; + #address-cells = <2>; + ranges = <1 0x0 0x0 0x18400000 0x4000>; + }; + pmc: power-management@100d0000 { compatible = "loongson,ls2k2000-pmc", "loongson,ls2k0500-pmc", "syscon"; reg = <0x0 0x100d0000 0x0 0x58>; @@ -109,6 +116,8 @@ msi: msi-controller@1fe01140 { compatible = "loongson,pch-msi-1.0"; reg = <0x0 0x1fe01140 0x0 0x8>; + interrupt-controller; + #interrupt-cells = <1>; msi-controller; loongson,msi-base-vec = <64>; loongson,msi-num-vecs = <192>; @@ -140,27 +149,34 @@ #address-cells = <3>; #size-cells = <2>; device_type = "pci"; + msi-parent = <&msi>; bus-range = <0x0 0xff>; - ranges = <0x01000000 0x0 0x00008000 0x0 0x18400000 0x0 0x00008000>, + ranges = <0x01000000 0x0 0x00008000 0x0 0x18408000 0x0 0x00008000>, <0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>; gmac0: ethernet@3,0 { reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupts = <12 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, + <13 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&pic>; status = "disabled"; }; gmac1: ethernet@3,1 { reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupts = <14 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, + <15 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&pic>; status = "disabled"; }; gmac2: ethernet@3,2 { reg = <0x1a00 0x0 0x0 0x0 0x0>; - interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>, + <18 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&pic>; status = "disabled"; }; diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index b24437e28c6e..7bd47d65bf7a 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -11,6 +11,7 @@ #define _ASM_ADDRSPACE_H #include <linux/const.h> +#include <linux/sizes.h> #include <asm/loongarch.h> diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index 4a8adcca329b..c2f9979b2979 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -14,11 +14,6 @@ #include <asm/pgtable-bits.h> #include <asm/string.h> -/* - * Change "struct page" to physical address. - */ -#define page_to_phys(page) ((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT) - extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size); extern void __init early_iounmap(void __iomem *addr, unsigned long size); @@ -73,6 +68,21 @@ extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t #define __io_aw() mmiowb() +#ifdef CONFIG_KFENCE +#define virt_to_phys(kaddr) \ +({ \ + (likely((unsigned long)kaddr < vm_map_base)) ? __pa((unsigned long)kaddr) : \ + page_to_phys(tlb_virt_to_page((unsigned long)kaddr)) + offset_in_page((unsigned long)kaddr);\ +}) + +#define phys_to_virt(paddr) \ +({ \ + extern char *__kfence_pool; \ + (unlikely(__kfence_pool == NULL)) ? __va((unsigned long)paddr) : \ + page_address(phys_to_page((unsigned long)paddr)) + offset_in_page((unsigned long)paddr);\ +}) +#endif + #include <asm-generic/io.h> #define ARCH_HAS_VALID_PHYS_ADDR_RANGE diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h index 6c82aea1c993..a6a5760da3a3 100644 --- a/arch/loongarch/include/asm/kfence.h +++ b/arch/loongarch/include/asm/kfence.h @@ -16,6 +16,7 @@ static inline bool arch_kfence_init_pool(void) { int err; + char *kaddr, *vaddr; char *kfence_pool = __kfence_pool; struct vm_struct *area; @@ -35,6 +36,14 @@ static inline bool arch_kfence_init_pool(void) return false; } + kaddr = kfence_pool; + vaddr = __kfence_pool; + while (kaddr < kfence_pool + KFENCE_POOL_SIZE) { + set_page_address(virt_to_page(kaddr), vaddr); + kaddr += PAGE_SIZE; + vaddr += PAGE_SIZE; + } + return true; } diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h index 44027060c54a..e85df33f11c7 100644 --- a/arch/loongarch/include/asm/page.h +++ b/arch/loongarch/include/asm/page.h @@ -78,7 +78,26 @@ typedef struct { unsigned long pgprot; } pgprot_t; struct page *dmw_virt_to_page(unsigned long kaddr); struct page *tlb_virt_to_page(unsigned long kaddr); -#define virt_to_pfn(kaddr) PFN_DOWN(PHYSADDR(kaddr)) +#define pfn_to_phys(pfn) __pfn_to_phys(pfn) +#define phys_to_pfn(paddr) __phys_to_pfn(paddr) + +#define page_to_phys(page) pfn_to_phys(page_to_pfn(page)) +#define phys_to_page(paddr) pfn_to_page(phys_to_pfn(paddr)) + +#ifndef CONFIG_KFENCE + +#define page_to_virt(page) __va(page_to_phys(page)) +#define virt_to_page(kaddr) phys_to_page(__pa(kaddr)) + +#else + +#define WANT_PAGE_VIRTUAL + +#define page_to_virt(page) \ +({ \ + extern char *__kfence_pool; \ + (__kfence_pool == NULL) ? __va(page_to_phys(page)) : page_address(page); \ +}) #define virt_to_page(kaddr) \ ({ \ @@ -86,6 +105,11 @@ struct page *tlb_virt_to_page(unsigned long kaddr); dmw_virt_to_page((unsigned long)kaddr) : tlb_virt_to_page((unsigned long)kaddr);\ }) +#endif + +#define pfn_to_virt(pfn) page_to_virt(pfn_to_page(pfn)) +#define virt_to_pfn(kaddr) page_to_pfn(virt_to_page(kaddr)) + extern int __virt_addr_valid(volatile void *kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((volatile void *)(kaddr)) diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c index a9630a81b38a..89af7c12e8c0 100644 --- a/arch/loongarch/mm/mmap.c +++ b/arch/loongarch/mm/mmap.c @@ -4,6 +4,7 @@ */ #include <linux/export.h> #include <linux/io.h> +#include <linux/kfence.h> #include <linux/memblock.h> #include <linux/mm.h> #include <linux/mman.h> @@ -111,6 +112,9 @@ int __virt_addr_valid(volatile void *kaddr) { unsigned long vaddr = (unsigned long)kaddr; + if (is_kfence_address((void *)kaddr)) + return 1; + if ((vaddr < PAGE_OFFSET) || (vaddr >= vm_map_base)) return 0; diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index 2aae72e63871..bda018150000 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -11,13 +11,13 @@ struct page *dmw_virt_to_page(unsigned long kaddr) { - return pfn_to_page(virt_to_pfn(kaddr)); + return phys_to_page(__pa(kaddr)); } EXPORT_SYMBOL(dmw_virt_to_page); struct page *tlb_virt_to_page(unsigned long kaddr) { - return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr))); + return phys_to_page(pfn_to_phys(pte_pfn(*virt_to_kpte(kaddr)))); } EXPORT_SYMBOL(tlb_virt_to_page); diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index d14d0e37ad02..4a2b40ce39e0 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -159,7 +159,7 @@ extern unsigned long exception_ip(struct pt_regs *regs); #define exception_ip(regs) exception_ip(regs) #define profile_pc(regs) instruction_pointer(regs) -extern asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall); +extern asmlinkage long syscall_trace_enter(struct pt_regs *regs); extern asmlinkage void syscall_trace_leave(struct pt_regs *regs); extern void die(const char *, struct pt_regs *) __noreturn; diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index d1b11f66f748..cb1045ebab06 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -101,6 +101,7 @@ void output_thread_info_defines(void) OFFSET(TI_CPU, thread_info, cpu); OFFSET(TI_PRE_COUNT, thread_info, preempt_count); OFFSET(TI_REGS, thread_info, regs); + OFFSET(TI_SYSCALL, thread_info, syscall); DEFINE(_THREAD_SIZE, THREAD_SIZE); DEFINE(_THREAD_MASK, THREAD_MASK); DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 59288c13b581..61503a36067e 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -1317,16 +1317,13 @@ long arch_ptrace(struct task_struct *child, long request, * Notification of system call entry/exit * - triggered by current->work.syscall_trace */ -asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) +asmlinkage long syscall_trace_enter(struct pt_regs *regs) { user_exit(); - current_thread_info()->syscall = syscall; - if (test_thread_flag(TIF_SYSCALL_TRACE)) { if (ptrace_report_syscall_entry(regs)) return -1; - syscall = current_thread_info()->syscall; } #ifdef CONFIG_SECCOMP @@ -1335,7 +1332,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) struct seccomp_data sd; unsigned long args[6]; - sd.nr = syscall; + sd.nr = current_thread_info()->syscall; sd.arch = syscall_get_arch(current); syscall_get_arguments(current, regs, args); for (i = 0; i < 6; i++) @@ -1345,23 +1342,23 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) ret = __secure_computing(&sd); if (ret == -1) return ret; - syscall = current_thread_info()->syscall; } #endif if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->regs[2]); - audit_syscall_entry(syscall, regs->regs[4], regs->regs[5], + audit_syscall_entry(current_thread_info()->syscall, + regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); /* * Negative syscall numbers are mistaken for rejected syscalls, but * won't have had the return value set appropriately, so we do so now. */ - if (syscall < 0) + if (current_thread_info()->syscall < 0) syscall_set_return_value(current, regs, -ENOSYS, 0); - return syscall; + return current_thread_info()->syscall; } /* diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 18dc9b345056..2c604717e630 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -77,6 +77,18 @@ loads_done: PTR_WD load_a7, bad_stack_a7 .previous + /* + * syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + */ + subu t2, v0, __NR_O32_Linux + bnez t2, 1f /* __NR_syscall at offset 0 */ + LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number + b 2f +1: + LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number +2: + lw t0, TI_FLAGS($28) # syscall tracing enabled? li t1, _TIF_WORK_SYSCALL_ENTRY and t0, t1 @@ -114,16 +126,7 @@ syscall_trace_entry: SAVE_STATIC move a0, sp - /* - * syscall number is in v0 unless we called syscall(__NR_###) - * where the real syscall number is in a0 - */ - move a1, v0 - subu t2, v0, __NR_O32_Linux - bnez t2, 1f /* __NR_syscall at offset 0 */ - lw a1, PT_R4(sp) - -1: jal syscall_trace_enter + jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 97456b2ca7dc..97788859238c 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -44,6 +44,8 @@ NESTED(handle_sysn32, PT_SIZE, sp) sd a3, PT_R26(sp) # save a3 for syscall restarting + LONG_S v0, TI_SYSCALL($28) # Store syscall number + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -72,7 +74,6 @@ syscall_common: n32_syscall_trace_entry: SAVE_STATIC move a0, sp - move a1, v0 jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S index e6264aa62e45..be11ea5cc67e 100644 --- a/arch/mips/kernel/scall64-n64.S +++ b/arch/mips/kernel/scall64-n64.S @@ -46,6 +46,8 @@ NESTED(handle_sys64, PT_SIZE, sp) sd a3, PT_R26(sp) # save a3 for syscall restarting + LONG_S v0, TI_SYSCALL($28) # Store syscall number + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -82,7 +84,6 @@ n64_syscall_exit: syscall_trace_entry: SAVE_STATIC move a0, sp - move a1, v0 jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index d3c2616cba22..7a5abb73e531 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -79,6 +79,22 @@ loads_done: PTR_WD load_a7, bad_stack_a7 .previous + /* + * absolute syscall number is in v0 unless we called syscall(__NR_###) + * where the real syscall number is in a0 + * note: NR_syscall is the first O32 syscall but the macro is + * only defined when compiling with -mabi=32 (CONFIG_32BIT) + * therefore __NR_O32_Linux is used (4000) + */ + + subu t2, v0, __NR_O32_Linux + bnez t2, 1f /* __NR_syscall at offset 0 */ + LONG_S a0, TI_SYSCALL($28) # Save a0 as syscall number + b 2f +1: + LONG_S v0, TI_SYSCALL($28) # Save v0 as syscall number +2: + li t1, _TIF_WORK_SYSCALL_ENTRY LONG_L t0, TI_FLAGS($28) # syscall tracing enabled? and t0, t1, t0 @@ -113,22 +129,7 @@ trace_a_syscall: sd a7, PT_R11(sp) # For indirect syscalls move a0, sp - /* - * absolute syscall number is in v0 unless we called syscall(__NR_###) - * where the real syscall number is in a0 - * note: NR_syscall is the first O32 syscall but the macro is - * only defined when compiling with -mabi=32 (CONFIG_32BIT) - * therefore __NR_O32_Linux is used (4000) - */ - .set push - .set reorder - subu t1, v0, __NR_O32_Linux - move a1, v0 - bnez t1, 1f /* __NR_syscall at offset 0 */ - ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ - .set pop - -1: jal syscall_trace_enter + jal syscall_trace_enter bltz v0, 1f # seccomp failed? Skip syscall diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c index 74fb86b0d209..7c728755852e 100644 --- a/arch/powerpc/crypto/chacha-p10-glue.c +++ b/arch/powerpc/crypto/chacha-p10-glue.c @@ -197,6 +197,9 @@ static struct skcipher_alg algs[] = { static int __init chacha_p10_init(void) { + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return 0; + static_branch_enable(&have_p10); return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); @@ -204,10 +207,13 @@ static int __init chacha_p10_init(void) static void __exit chacha_p10_exit(void) { + if (!static_branch_likely(&have_p10)) + return; + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); } -module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init); +module_init(chacha_p10_init); module_exit(chacha_p10_exit); MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)"); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 1185efebf032..29a8c8e18585 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1285,15 +1285,14 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain, struct device *dev) { struct iommu_domain *domain = iommu_get_domain_for_dev(dev); - struct iommu_group *grp = iommu_group_get(dev); struct iommu_table_group *table_group; + struct iommu_group *grp; /* At first attach the ownership is already set */ - if (!domain) { - iommu_group_put(grp); + if (!domain) return 0; - } + grp = iommu_group_get(dev); table_group = iommu_group_get_iommudata(grp); /* * The domain being set to PLATFORM from earlier diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 3dc85638bc63..6a1e0fbbaa15 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -340,7 +340,8 @@ SYM_CODE_START(pgm_check_handler) mvc __PT_LAST_BREAK(8,%r11),__LC_PGM_LAST_BREAK stctg %c1,%c1,__PT_CR1(%r11) #if IS_ENABLED(CONFIG_KVM) - lg %r12,__LC_GMAP + ltg %r12,__LC_GMAP + jz 5f clc __GMAP_ASCE(8,%r12), __PT_CR1(%r11) jne 5f BPENTER __SF_SIE_FLAGS(%r10),_TIF_ISOLATE_BP_GUEST diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4fff6ed46e90..4474bf32d0a4 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2633,6 +2633,16 @@ config MITIGATION_RFDS stored in floating point, vector and integer registers. See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst> +config MITIGATION_SPECTRE_BHI + bool "Mitigate Spectre-BHB (Branch History Injection)" + depends on CPU_SUP_INTEL + default y + help + Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks + where the branch history buffer is poisoned to speculatively steer + indirect branches. + See <file:Documentation/admin-guide/hw-vuln/spectre.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 6356060caaf3..51cc9c7cb9bd 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -49,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) if (likely(unr < NR_syscalls)) { unr = array_index_nospec(unr, NR_syscalls); - regs->ax = sys_call_table[unr](regs); + regs->ax = x64_sys_call(regs, unr); return true; } return false; @@ -66,7 +66,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { xnr = array_index_nospec(xnr, X32_NR_syscalls); - regs->ax = x32_sys_call_table[xnr](regs); + regs->ax = x32_sys_call(regs, xnr); return true; } return false; @@ -162,7 +162,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) if (likely(unr < IA32_NR_syscalls)) { unr = array_index_nospec(unr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[unr](regs); + regs->ax = ia32_sys_call(regs, unr); } else if (nr != -1) { regs->ax = __ia32_sys_ni_syscall(regs); } @@ -189,7 +189,7 @@ static __always_inline bool int80_is_external(void) } /** - * int80_emulation - 32-bit legacy syscall entry + * do_int80_emulation - 32-bit legacy syscall C entry from asm * * This entry point can be used by 32-bit and 64-bit programs to perform * 32-bit system calls. Instances of INT $0x80 can be found inline in @@ -207,7 +207,7 @@ static __always_inline bool int80_is_external(void) * eax: system call number * ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6 */ -DEFINE_IDTENTRY_RAW(int80_emulation) +__visible noinstr void do_int80_emulation(struct pt_regs *regs) { int nr; @@ -255,6 +255,71 @@ DEFINE_IDTENTRY_RAW(int80_emulation) instrumentation_end(); syscall_exit_to_user_mode(regs); } + +#ifdef CONFIG_X86_FRED +/* + * A FRED-specific INT80 handler is warranted for the follwing reasons: + * + * 1) As INT instructions and hardware interrupts are separate event + * types, FRED does not preclude the use of vector 0x80 for external + * interrupts. As a result, the FRED setup code does not reserve + * vector 0x80 and calling int80_is_external() is not merely + * suboptimal but actively incorrect: it could cause a system call + * to be incorrectly ignored. + * + * 2) It is called only for handling vector 0x80 of event type + * EVENT_TYPE_SWINT and will never be called to handle any external + * interrupt (event type EVENT_TYPE_EXTINT). + * + * 3) FRED has separate entry flows depending on if the event came from + * user space or kernel space, and because the kernel does not use + * INT insns, the FRED kernel entry handler fred_entry_from_kernel() + * falls through to fred_bad_type() if the event type is + * EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling + * an INT insn, it can only be from a user level. + * + * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will + * likely take a different approach if it is ever needed: it + * probably belongs in either fred_intx()/ fred_other() or + * asm_fred_entrypoint_user(), depending on if this ought to be done + * for all entries from userspace or only system + * calls. + * + * 5) INT $0x80 is the fast path for 32-bit system calls under FRED. + */ +DEFINE_FREDENTRY_RAW(int80_emulation) +{ + int nr; + + enter_from_user_mode(regs); + + instrumentation_begin(); + add_random_kstack_offset(); + + /* + * FRED pushed 0 into regs::orig_ax and regs::ax contains the + * syscall number. + * + * User tracing code (ptrace or signal handlers) might assume + * that the regs::orig_ax contains a 32-bit number on invoking + * a 32-bit syscall. + * + * Establish the syscall convention by saving the 32bit truncated + * syscall number in regs::orig_ax and by invalidating regs::ax. + */ + regs->orig_ax = regs->ax & GENMASK(31, 0); + regs->ax = -ENOSYS; + + nr = syscall_32_enter(regs); + + local_irq_enable(); + nr = syscall_enter_from_user_mode_work(regs, nr); + do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); + syscall_exit_to_user_mode(regs); +} +#endif #else /* CONFIG_IA32_EMULATION */ /* Handles int $0x80 on a 32bit kernel */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8af2a26b24f6..1b5be07f8669 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* clobbers %rax, make sure it is after saving the syscall nr */ IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY call do_syscall_64 /* returns with IRQs disabled */ @@ -1491,3 +1492,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead) call make_task_dead SYM_CODE_END(rewind_stack_and_make_dead) .popsection + +/* + * This sequence executes branches in order to remove user branch information + * from the branch history tracker in the Branch Predictor, therefore removing + * user influence on subsequent BTB lookups. + * + * It should be used on parts prior to Alder Lake. Newer parts should use the + * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being + * virtualized on newer hardware the VMM should protect against BHI attacks by + * setting BHI_DIS_S for the guests. + * + * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging + * and not clearing the branch history. The call tree looks like: + * + * call 1 + * call 2 + * call 2 + * call 2 + * call 2 + * call 2 + * ret + * ret + * ret + * ret + * ret + * ret + * + * This means that the stack is non-constant and ORC can't unwind it with %rsp + * alone. Therefore we unconditionally set up the frame pointer, which allows + * ORC to unwind properly. + * + * The alignment is for performance and not for safety, and may be safely + * refactored in the future if needed. + */ +SYM_FUNC_START(clear_bhb_loop) + push %rbp + mov %rsp, %rbp + movl $5, %ecx + ANNOTATE_INTRA_FUNCTION_CALL + call 1f + jmp 5f + .align 64, 0xcc + ANNOTATE_INTRA_FUNCTION_CALL +1: call 2f + RET + .align 64, 0xcc +2: movl $5, %eax +3: jmp 4f + nop +4: sub $1, %eax + jnz 3b + sub $1, %ecx + jnz 1b + RET +5: lfence + pop %rbp + RET +SYM_FUNC_END(clear_bhb_loop) +EXPORT_SYMBOL_GPL(clear_bhb_loop) +STACK_FRAME_NON_STANDARD(clear_bhb_loop) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index eabf48c4d4b4..c779046cc3fe 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY /* * SYSENTER doesn't filter flags, so we need to clear NT and AC @@ -206,6 +207,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_fast_syscall_32 @@ -276,3 +278,17 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR int3 SYM_CODE_END(entry_SYSCALL_compat) + +/* + * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries + * point to C routines, however since this is a system call interface the branch + * history needs to be scrubbed to protect against BHI attacks, and that + * scrubbing needs to take place in assembly code prior to entering any C + * routines. + */ +SYM_CODE_START(int80_emulation) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + CLEAR_BRANCH_HISTORY + jmp do_int80_emulation +SYM_CODE_END(int80_emulation) diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c index ac120cbdaaf2..89c1476fcdd9 100644 --- a/arch/x86/entry/entry_fred.c +++ b/arch/x86/entry/entry_fred.c @@ -28,9 +28,9 @@ static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code if (regs->fred_cs.sl > 0) { pr_emerg("PANIC: invalid or fatal FRED event; event type %u " "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", - regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax, + regs->fred_ss.type, regs->fred_ss.vector, error_code, fred_event_data(regs), regs->cs, regs->ip); - die("invalid or fatal FRED event", regs, regs->orig_ax); + die("invalid or fatal FRED event", regs, error_code); panic("invalid or fatal FRED event"); } else { unsigned long flags = oops_begin(); @@ -38,10 +38,10 @@ static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code pr_alert("BUG: invalid or fatal FRED event; event type %u " "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", - regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax, + regs->fred_ss.type, regs->fred_ss.vector, error_code, fred_event_data(regs), regs->cs, regs->ip); - if (__die("Invalid or fatal FRED event", regs, regs->orig_ax)) + if (__die("Invalid or fatal FRED event", regs, error_code)) sig = 0; oops_end(flags, regs, sig); @@ -66,7 +66,7 @@ static noinstr void fred_intx(struct pt_regs *regs) /* INT80 */ case IA32_SYSCALL_VECTOR: if (ia32_enabled()) - return int80_emulation(regs); + return fred_int80_emulation(regs); fallthrough; #endif diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8cfc9bc73e7f..c2235bae17ef 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -18,8 +18,25 @@ #include <asm/syscalls_32.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ +#ifdef CONFIG_X86_32 #define __SYSCALL(nr, sym) __ia32_##sym, - -__visible const sys_call_ptr_t ia32_sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_32.h> }; +#undef __SYSCALL +#endif + +#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); + +long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_32.h> + default: return __ia32_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index be120eec1fc9..33b3f09e6f15 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -11,8 +11,23 @@ #include <asm/syscalls_64.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ #define __SYSCALL(nr, sym) __x64_##sym, - -asmlinkage const sys_call_ptr_t sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_64.h> }; +#undef __SYSCALL + +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); + +long x64_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_64.h> + default: return __x64_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index bdd0e03a1265..03de4a932131 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -11,8 +11,12 @@ #include <asm/syscalls_x32.h> #undef __SYSCALL -#define __SYSCALL(nr, sym) __x64_##sym, +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); -asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { -#include <asm/syscalls_x32.h> +long x32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_x32.h> + default: return __x64_sys_ni_syscall(regs); + } }; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 09050641ce5d..5b0dd07b1ef1 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1644,6 +1644,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; + cpuc->assign[i-1] = cpuc->assign[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 78cd5084104e..4367aa77cb8d 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1693,6 +1693,7 @@ void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) lbr->from = x86_pmu.lbr_from; lbr->to = x86_pmu.lbr_to; lbr->info = x86_pmu.lbr_info; + lbr->has_callstack = x86_pmu_has_lbr_callstack(); } EXPORT_SYMBOL_GPL(x86_perf_get_lbr); diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5fc45543e955..0569f579338b 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -105,7 +105,7 @@ static bool cpu_is_self(int cpu) * IPI implementation on Hyper-V. */ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, - bool exclude_self) + bool exclude_self) { struct hv_send_ipi_ex *ipi_arg; unsigned long flags; @@ -132,8 +132,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset_skip(&(ipi_arg->vp_set), mask, - exclude_self ? cpu_is_self : NULL); + nr_bank = cpumask_to_vpset_skip(&ipi_arg->vp_set, mask, + exclude_self ? cpu_is_self : NULL); /* * 'nr_bank <= 0' means some CPUs in cpumask can't be @@ -147,7 +147,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, } status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank, - ipi_arg, NULL); + ipi_arg, NULL); ipi_mask_ex_done: local_irq_restore(flags); @@ -155,7 +155,7 @@ ipi_mask_ex_done: } static bool __send_ipi_mask(const struct cpumask *mask, int vector, - bool exclude_self) + bool exclude_self) { int cur_cpu, vcpu, this_cpu = smp_processor_id(); struct hv_send_ipi ipi_arg; @@ -181,7 +181,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector, return false; } - if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) + if (vector < HV_IPI_LOW_VECTOR || vector > HV_IPI_HIGH_VECTOR) return false; /* @@ -218,7 +218,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector, } status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector, - ipi_arg.cpu_mask); + ipi_arg.cpu_mask); return hv_result_success(status); do_ex_hypercall: @@ -241,7 +241,7 @@ static bool __send_ipi_one(int cpu, int vector) return false; } - if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) + if (vector < HV_IPI_LOW_VECTOR || vector > HV_IPI_HIGH_VECTOR) return false; if (vp >= 64) diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c index 68a0843d4750..3fa1f2ee7b0d 100644 --- a/arch/x86/hyperv/hv_proc.c +++ b/arch/x86/hyperv/hv_proc.c @@ -3,7 +3,6 @@ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/clockchips.h> -#include <linux/acpi.h> #include <linux/hyperv.h> #include <linux/slab.h> #include <linux/cpuhotplug.h> @@ -116,12 +115,11 @@ free_buf: int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id) { - struct hv_add_logical_processor_in *input; - struct hv_add_logical_processor_out *output; + struct hv_input_add_logical_processor *input; + struct hv_output_add_logical_processor *output; u64 status; unsigned long flags; int ret = HV_STATUS_SUCCESS; - int pxm = node_to_pxm(node); /* * When adding a logical processor, the hypervisor may return @@ -137,11 +135,7 @@ int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id) input->lp_index = lp_index; input->apic_id = apic_id; - input->flags = 0; - input->proximity_domain_info.domain_id = pxm; - input->proximity_domain_info.flags.reserved = 0; - input->proximity_domain_info.flags.proximity_info_valid = 1; - input->proximity_domain_info.flags.proximity_preferred = 1; + input->proximity_domain_info = hv_numa_node_to_pxm_info(node); status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR, input, output); local_irq_restore(flags); @@ -166,7 +160,6 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) u64 status; unsigned long irq_flags; int ret = HV_STATUS_SUCCESS; - int pxm = node_to_pxm(node); /* Root VPs don't seem to need pages deposited */ if (partition_id != hv_current_partition_id) { @@ -185,14 +178,7 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) input->vp_index = vp_index; input->flags = flags; input->subnode_type = HvSubnodeAny; - if (node != NUMA_NO_NODE) { - input->proximity_domain_info.domain_id = pxm; - input->proximity_domain_info.flags.reserved = 0; - input->proximity_domain_info.flags.proximity_info_valid = 1; - input->proximity_domain_info.flags.proximity_preferred = 1; - } else { - input->proximity_domain_info.as_uint64 = 0; - } + input->proximity_domain_info = hv_numa_node_to_pxm_info(node); status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL); local_irq_restore(irq_flags); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 94ce0f7c9d3a..e6ab0cf15ed5 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -13,6 +13,7 @@ #include <asm/mpspec.h> #include <asm/msr.h> #include <asm/hardirq.h> +#include <asm/io.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -98,7 +99,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v) static inline u32 native_apic_mem_read(u32 reg) { - return *((volatile u32 *)(APIC_BASE + reg)); + return readl((void __iomem *)(APIC_BASE + reg)); } static inline void native_apic_mem_eoi(void) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index fe1e7e3cc844..63bdc6b85219 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -79,6 +79,9 @@ do { \ #define __smp_mb__before_atomic() do { } while (0) #define __smp_mb__after_atomic() do { } while (0) +/* Writing to CR3 provides a full memory barrier in switch_mm(). */ +#define smp_mb__after_switch_mm() do { } while (0) + #include <asm-generic/barrier.h> #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index a38f8f9ba657..3c7434329661 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -461,11 +461,15 @@ /* * Extended auxiliary flags: Linux defined - for features scattered in various - * CPUID levels like 0x80000022, etc. + * CPUID levels like 0x80000022, etc and Linux defined features. * * Reuse free bits when adding new feature flags! */ #define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ /* * BUG word(s) @@ -515,4 +519,5 @@ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 16e07a2eee19..6efd1497b026 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -855,6 +855,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; struct kvm_hypervisor_cpuid kvm_cpuid; + bool is_amd_compatible; /* * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 05956bd8bacf..e72c2b872957 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -61,10 +61,13 @@ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) /* A mask for bits which the kernel toggles when controlling mitigations */ #define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ - | SPEC_CTRL_RRSBA_DIS_S) + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -163,6 +166,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 170c89ed22fc..ff5f1ecc7d1e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -326,6 +326,19 @@ ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF .endm +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -368,6 +381,10 @@ extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + extern void (*x86_return_thunk)(void); extern void __warn_thunk(void); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 3736b8a46c04..7f1e17250546 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -555,6 +555,7 @@ struct x86_pmu_lbr { unsigned int from; unsigned int to; unsigned int info; + bool has_callstack; }; extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index f44e2f9ab65d..2fc7bc3863ff 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,19 +16,17 @@ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> +/* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; -#if defined(CONFIG_X86_32) -#define ia32_sys_call_table sys_call_table -#else /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ -extern const sys_call_ptr_t ia32_sys_call_table[]; -extern const sys_call_ptr_t x32_sys_call_table[]; -#endif +extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. @@ -127,6 +125,7 @@ static inline int syscall_get_arch(struct task_struct *task) } bool do_syscall_64(struct pt_regs *regs, int nr); +void do_int80_emulation(struct pt_regs *regs); #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a42d8a6f7149..c342c4aa9c68 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1687,11 +1687,11 @@ static int x2apic_state; static bool x2apic_hw_locked(void) { - u64 ia32_cap; + u64 x86_arch_cap_msr; u64 msr; - ia32_cap = x86_read_arch_cap_msr(); - if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + x86_arch_cap_msr = x86_read_arch_cap_msr(); + if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) { rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); return (msr & LEGACY_XAPIC_DISABLED); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9bf17c9c29da..cb9eece55904 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -535,7 +535,6 @@ clear_sev: static void early_init_amd(struct cpuinfo_x86 *c) { - u64 value; u32 dummy; if (c->x86 >= 0xf) @@ -603,20 +602,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) early_detect_mem_encrypt(c); - /* Re-enable TopologyExtensions if switched off by BIOS */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x6f) && - !cpu_has(c, X86_FEATURE_TOPOEXT)) { - - if (msr_set_bit(0xc0011005, 54) > 0) { - rdmsrl(0xc0011005, value); - if (value & BIT_64(54)) { - set_cpu_cap(c, X86_FEATURE_TOPOEXT); - pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); - } - } - } - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) { if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB)) setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e7ba936d798b..ab18185894df 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -61,6 +61,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); +static u64 __ro_after_init x86_arch_cap_msr; + static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; @@ -144,6 +146,8 @@ void __init cpu_select_mitigations(void) x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; } + x86_arch_cap_msr = x86_read_arch_cap_msr(); + /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); @@ -301,8 +305,6 @@ static const char * const taa_strings[] = { static void __init taa_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_TAA)) { taa_mitigation = TAA_MITIGATION_OFF; return; @@ -341,9 +343,8 @@ static void __init taa_select_mitigation(void) * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode * update is required. */ - ia32_cap = x86_read_arch_cap_msr(); - if ( (ia32_cap & ARCH_CAP_MDS_NO) && - !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) && + !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)) taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; /* @@ -401,8 +402,6 @@ static const char * const mmio_strings[] = { static void __init mmio_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || cpu_mitigations_off()) { @@ -413,8 +412,6 @@ static void __init mmio_select_mitigation(void) if (mmio_mitigation == MMIO_MITIGATION_OFF) return; - ia32_cap = x86_read_arch_cap_msr(); - /* * Enable CPU buffer clear mitigation for host and VMM, if also affected * by MDS or TAA. Otherwise, enable mitigation for VMM only. @@ -437,7 +434,7 @@ static void __init mmio_select_mitigation(void) * be propagated to uncore buffers, clearing the Fill buffers on idle * is required irrespective of SMT state. */ - if (!(ia32_cap & ARCH_CAP_FBSDP_NO)) + if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) static_branch_enable(&mds_idle_clear); /* @@ -447,10 +444,10 @@ static void __init mmio_select_mitigation(void) * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS * affected systems. */ - if ((ia32_cap & ARCH_CAP_FB_CLEAR) || + if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) || (boot_cpu_has(X86_FEATURE_MD_CLEAR) && boot_cpu_has(X86_FEATURE_FLUSH_L1D) && - !(ia32_cap & ARCH_CAP_MDS_NO))) + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))) mmio_mitigation = MMIO_MITIGATION_VERW; else mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; @@ -508,7 +505,7 @@ static void __init rfds_select_mitigation(void) if (rfds_mitigation == RFDS_MITIGATION_OFF) return; - if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; @@ -659,8 +656,6 @@ void update_srbds_msr(void) static void __init srbds_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return; @@ -669,8 +664,7 @@ static void __init srbds_select_mitigation(void) * are only exposed to SRBDS when TSX is enabled or when CPU is affected * by Processor MMIO Stale Data vulnerability. */ - ia32_cap = x86_read_arch_cap_msr(); - if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && + if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) @@ -813,7 +807,7 @@ static void __init gds_select_mitigation(void) /* Will verify below that mitigation _can_ be disabled */ /* No microcode */ - if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) { if (gds_mitigation == GDS_MITIGATION_FORCE) { /* * This only needs to be done on the boot CPU so do it @@ -1544,20 +1538,25 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +static bool __ro_after_init rrsba_disabled; + /* Disable in-kernel use of non-RSB RET predictors */ static void __init spec_ctrl_disable_kernel_rrsba(void) { - u64 ia32_cap; + if (rrsba_disabled) + return; - if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) { + rrsba_disabled = true; return; + } - ia32_cap = x86_read_arch_cap_msr(); + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; - if (ia32_cap & ARCH_CAP_RRSBA) { - x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - update_spec_ctrl(x86_spec_ctrl_base); - } + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + rrsba_disabled = true; } static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) @@ -1607,6 +1606,74 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ dump_stack(); } +/* + * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by + * branch history in userspace. Not needed if BHI_NO is set. + */ +static bool __init spec_ctrl_bhi_dis(void) +{ + if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); + + return true; +} + +enum bhi_mitigations { + BHI_MITIGATION_OFF, + BHI_MITIGATION_ON, +}; + +static enum bhi_mitigations bhi_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF; + +static int __init spectre_bhi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + bhi_mitigation = BHI_MITIGATION_OFF; + else if (!strcmp(str, "on")) + bhi_mitigation = BHI_MITIGATION_ON; + else + pr_err("Ignoring unknown spectre_bhi option (%s)", str); + + return 0; +} +early_param("spectre_bhi", spectre_bhi_parse_cmdline); + +static void __init bhi_select_mitigation(void) +{ + if (bhi_mitigation == BHI_MITIGATION_OFF) + return; + + /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + spec_ctrl_disable_kernel_rrsba(); + if (rrsba_disabled) + return; + } + + if (spec_ctrl_bhi_dis()) + return; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Mitigate KVM by default */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + + /* Mitigate syscalls when the mitigation is forced =on */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1718,6 +1785,9 @@ static void __init spectre_v2_select_mitigation(void) mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); + if (boot_cpu_has(X86_BUG_BHI)) + bhi_select_mitigation(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -1832,8 +1902,6 @@ static void update_indir_branch_cond(void) /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { - u64 ia32_cap = x86_read_arch_cap_msr(); - /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. @@ -1848,7 +1916,7 @@ static void update_mds_branch_idle(void) if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || - (ia32_cap & ARCH_CAP_FBSDP_NO)) { + (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); } } @@ -2695,15 +2763,15 @@ static char *stibp_state(void) switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: - return ", STIBP: disabled"; + return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: - return ", STIBP: forced"; + return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: - return ", STIBP: always-on"; + return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) - return ", STIBP: conditional"; + return "; STIBP: conditional"; } return ""; } @@ -2712,10 +2780,10 @@ static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) - return ", IBPB: always-on"; + return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) - return ", IBPB: conditional"; - return ", IBPB: disabled"; + return "; IBPB: conditional"; + return "; IBPB: disabled"; } return ""; } @@ -2725,14 +2793,32 @@ static char *pbrsb_eibrs_state(void) if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) - return ", PBRSB-eIBRS: SW sequence"; + return "; PBRSB-eIBRS: SW sequence"; else - return ", PBRSB-eIBRS: Vulnerable"; + return "; PBRSB-eIBRS: Vulnerable"; } else { - return ", PBRSB-eIBRS: Not affected"; + return "; PBRSB-eIBRS: Not affected"; } } +static const char *spectre_bhi_state(void) +{ + if (!boot_cpu_has_bug(X86_BUG_BHI)) + return "; BHI: Not affected"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + return "; BHI: BHI_DIS_S"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + return "; BHI: SW loop, KVM: SW loop"; + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) && + rrsba_disabled) + return "; BHI: Retpoline"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) + return "; BHI: Vulnerable, KVM: SW loop"; + + return "; BHI: Vulnerable"; +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) @@ -2745,13 +2831,15 @@ static ssize_t spectre_v2_show_state(char *buf) spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sysfs_emit(buf, "%s%s%s%s%s%s%s\n", + return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", pbrsb_eibrs_state(), + spectre_bhi_state(), + /* this should always be at the end */ spectre_v2_module_string()); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 5c1e6d6be267..605c26c009c8 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1120,6 +1120,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SPECTRE_V2 BIT(8) #define NO_MMIO BIT(9) #define NO_EIBRS_PBRSB BIT(10) +#define NO_BHI BIT(11) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1182,18 +1183,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), {} }; @@ -1283,25 +1284,25 @@ static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long whi u64 x86_read_arch_cap_msr(void) { - u64 ia32_cap = 0; + u64 x86_arch_cap_msr = 0; if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr); - return ia32_cap; + return x86_arch_cap_msr; } -static bool arch_cap_mmio_immune(u64 ia32_cap) +static bool arch_cap_mmio_immune(u64 x86_arch_cap_msr) { - return (ia32_cap & ARCH_CAP_FBSDP_NO && - ia32_cap & ARCH_CAP_PSDP_NO && - ia32_cap & ARCH_CAP_SBDR_SSDP_NO); + return (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO && + x86_arch_cap_msr & ARCH_CAP_PSDP_NO && + x86_arch_cap_msr & ARCH_CAP_SBDR_SSDP_NO); } -static bool __init vulnerable_to_rfds(u64 ia32_cap) +static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) { /* The "immunity" bit trumps everything else: */ - if (ia32_cap & ARCH_CAP_RFDS_NO) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_NO) return false; /* @@ -1309,7 +1310,7 @@ static bool __init vulnerable_to_rfds(u64 ia32_cap) * indicate that mitigation is needed because guest is running on a * vulnerable hardware or may migrate to such hardware: */ - if (ia32_cap & ARCH_CAP_RFDS_CLEAR) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) return true; /* Only consult the blacklist when there is no enumeration: */ @@ -1318,11 +1319,11 @@ static bool __init vulnerable_to_rfds(u64 ia32_cap) static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { - u64 ia32_cap = x86_read_arch_cap_msr(); + u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && - !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) @@ -1334,7 +1335,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && - !(ia32_cap & ARCH_CAP_SSB_NO) && + !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -1345,17 +1346,17 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Don't use AutoIBRS when SNP is enabled because it degrades host * userspace indirect branch performance. */ - if ((ia32_cap & ARCH_CAP_IBRS_ALL) || + if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || (cpu_has(c, X86_FEATURE_AUTOIBRS) && !cpu_feature_enabled(X86_FEATURE_SEV_SNP))) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO)) setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && - !(ia32_cap & ARCH_CAP_MDS_NO)) { + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); @@ -1374,9 +1375,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * TSX_CTRL check alone is not sufficient for cases when the microcode * update is not present or running as guest that don't get TSX_CTRL. */ - if (!(ia32_cap & ARCH_CAP_TAA_NO) && + if (!(x86_arch_cap_msr & ARCH_CAP_TAA_NO) && (cpu_has(c, X86_FEATURE_RTM) || - (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + (x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); /* @@ -1402,7 +1403,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (!arch_cap_mmio_immune(ia32_cap)) { + if (!arch_cap_mmio_immune(x86_arch_cap_msr)) { if (cpu_matches(cpu_vuln_blacklist, MMIO)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) @@ -1410,7 +1411,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) } if (!cpu_has(c, X86_FEATURE_BTC_NO)) { - if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (x86_arch_cap_msr & ARCH_CAP_RSBA)) setup_force_cpu_bug(X86_BUG_RETBLEED); } @@ -1428,18 +1429,25 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * disabling AVX2. The only way to do this in HW is to clear XCR0[2], * which means that AVX will be disabled. */ - if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(x86_arch_cap_msr & ARCH_CAP_GDS_NO) && boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); - if (vulnerable_to_rfds(ia32_cap)) + if (vulnerable_to_rfds(x86_arch_cap_msr)) setup_force_cpu_bug(X86_BUG_RFDS); + /* When virtualized, eIBRS could be hidden, assume vulnerable */ + if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && + !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || + boot_cpu_has(X86_FEATURE_HYPERVISOR))) + setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ - if (ia32_cap & ARCH_CAP_RDCL_NO) + if (x86_arch_cap_msr & ARCH_CAP_RDCL_NO) return; setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index b7174209d855..946813d816bf 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_VAES, X86_FEATURE_AVX }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, @@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index a515328d9d7d..af5aa2c754c2 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index aaca8d235dc2..d17c9b71eb4a 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -123,7 +123,6 @@ static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) early_per_cpu(x86_cpu_to_apicid, cpu) = apic_id; early_per_cpu(x86_cpu_to_acpiid, cpu) = acpi_id; #endif - set_cpu_possible(cpu, true); set_cpu_present(cpu, true); } @@ -210,7 +209,11 @@ static __init void topo_register_apic(u32 apic_id, u32 acpi_id, bool present) topo_info.nr_disabled_cpus++; } - /* Register present and possible CPUs in the domain maps */ + /* + * Register present and possible CPUs in the domain + * maps. cpu_possible_map will be updated in + * topology_init_possible_cpus() after enumeration is done. + */ for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++) set_bit(topo_apicid(apic_id, dom), apic_maps[dom].map); } diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c index 1a8b3ad493af..a7aa6eff4ae5 100644 --- a/arch/x86/kernel/cpu/topology_amd.c +++ b/arch/x86/kernel/cpu/topology_amd.c @@ -29,11 +29,21 @@ static bool parse_8000_0008(struct topo_scan *tscan) if (!sft) sft = get_count_order(ecx.cpu_nthreads + 1); - topology_set_dom(tscan, TOPO_SMT_DOMAIN, sft, ecx.cpu_nthreads + 1); + /* + * cpu_nthreads describes the number of threads in the package + * sft is the number of APIC ID bits per package + * + * As the number of actual threads per core is not described in + * this leaf, just set the CORE domain shift and let the later + * parsers set SMT shift. Assume one thread per core by default + * which is correct if there are no other CPUID leafs to parse. + */ + topology_update_dom(tscan, TOPO_SMT_DOMAIN, 0, 1); + topology_set_dom(tscan, TOPO_CORE_DOMAIN, sft, ecx.cpu_nthreads + 1); return true; } -static void store_node(struct topo_scan *tscan, unsigned int nr_nodes, u16 node_id) +static void store_node(struct topo_scan *tscan, u16 nr_nodes, u16 node_id) { /* * Starting with Fam 17h the DIE domain could probably be used to @@ -73,12 +83,14 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb) tscan->c->topo.initial_apicid = leaf.ext_apic_id; /* - * If leaf 0xb is available, then SMT shift is set already. If not - * take it from ecx.threads_per_core and use topo_update_dom() - - * topology_set_dom() would propagate and overwrite the already - * propagated CORE level. + * If leaf 0xb is available, then the domain shifts are set + * already and nothing to do here. */ if (!has_0xb) { + /* + * Leaf 0x80000008 set the CORE domain shift already. + * Update the SMT domain, but do not propagate it. + */ unsigned int nthreads = leaf.core_nthreads + 1; topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads); @@ -109,13 +121,13 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb) static bool parse_fam10h_node_id(struct topo_scan *tscan) { - struct { - union { + union { + struct { u64 node_id : 3, nodes_per_pkg : 3, unused : 58; - u64 msr; }; + u64 msr; } nid; if (!boot_cpu_has(X86_FEATURE_NODEID_MSR)) @@ -135,6 +147,26 @@ static void legacy_set_llc(struct topo_scan *tscan) tscan->c->topo.llc_id = apicid >> tscan->dom_shifts[TOPO_CORE_DOMAIN]; } +static void topoext_fixup(struct topo_scan *tscan) +{ + struct cpuinfo_x86 *c = tscan->c; + u64 msrval; + + /* Try to re-enable TopologyExtensions if switched off by BIOS */ + if (cpu_has(c, X86_FEATURE_TOPOEXT) || c->x86_vendor != X86_VENDOR_AMD || + c->x86 != 0x15 || c->x86_model < 0x10 || c->x86_model > 0x6f) + return; + + if (msr_set_bit(0xc0011005, 54) <= 0) + return; + + rdmsrl(0xc0011005, msrval); + if (msrval & BIT_64(54)) { + set_cpu_cap(c, X86_FEATURE_TOPOEXT); + pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); + } +} + static void parse_topology_amd(struct topo_scan *tscan) { bool has_0xb = false; @@ -164,6 +196,7 @@ static void parse_topology_amd(struct topo_scan *tscan) void cpu_parse_topology_amd(struct topo_scan *tscan) { tscan->amd_nodes_per_pkg = 1; + topoext_fixup(tscan); parse_topology_amd(tscan); if (tscan->amd_nodes_per_pkg > 1) diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index a88bb14266b6..addc44fc7187 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -3,11 +3,6 @@ ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror -ifeq ($(CONFIG_FRAME_POINTER),y) -OBJECT_FILES_NON_STANDARD_vmx/vmenter.o := y -OBJECT_FILES_NON_STANDARD_svm/vmenter.o := y -endif - include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index bfc0bfcb2bc6..77352a4abd87 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -376,6 +376,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_update_pv_runtime(vcpu); + vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 856e3037e74f..23dbb9eb277c 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -120,6 +120,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu) return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx); } +static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.is_amd_compatible; +} + +static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu) +{ + return !guest_cpuid_is_amd_compatible(vcpu); +} + static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cf37586f0466..ebf41023be38 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2776,7 +2776,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); - if (r && lvt_type == APIC_LVTPC) + if (r && lvt_type == APIC_LVTPC && + guest_cpuid_is_intel_compatible(apic->vcpu)) kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); return r; } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 992e651540e8..db007a4dffa2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4935,7 +4935,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, context->cpu_role.base.level, is_efer_nx(context), guest_can_use(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), - guest_cpuid_is_amd_or_hygon(vcpu)); + guest_cpuid_is_amd_compatible(vcpu)); } static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, @@ -5576,9 +5576,9 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ - vcpu->arch.root_mmu.root_role.word = 0; - vcpu->arch.guest_mmu.root_role.word = 0; - vcpu->arch.nested_mmu.root_role.word = 0; + vcpu->arch.root_mmu.root_role.invalid = 1; + vcpu->arch.guest_mmu.root_role.invalid = 1; + vcpu->arch.nested_mmu.root_role.invalid = 1; vcpu->arch.root_mmu.cpu_role.ext.valid = 0; vcpu->arch.guest_mmu.cpu_role.ext.valid = 0; vcpu->arch.nested_mmu.cpu_role.ext.valid = 0; @@ -7399,7 +7399,8 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, * by the memslot, KVM can't use a hugepage due to the * misaligned address regardless of memory attributes. */ - if (gfn >= slot->base_gfn) { + if (gfn >= slot->base_gfn && + gfn + nr_pages <= slot->base_gfn + slot->npages) { if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) hugepage_clear_mixed(slot, gfn, level); else diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d078157e62aa..04c1f0957fea 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1548,17 +1548,21 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, } } -/* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. - */ +static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp) +{ + /* + * All TDP MMU shadow pages share the same role as their root, aside + * from level, so it is valid to key off any shadow page to determine if + * write protection is needed for an entire tree. + */ + return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled(); +} + static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { - u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK; + const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; bool spte_set = false; @@ -1573,7 +1577,7 @@ retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (!(iter.old_spte & dbit)) @@ -1590,11 +1594,9 @@ retry: } /* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. + * Clear the dirty status (D-bit or W-bit) of all the SPTEs mapping GFNs in the + * memslot. Returns true if an SPTE has been changed and the TLBs need to be + * flushed. */ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -1610,18 +1612,11 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, return spte_set; } -/* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. - */ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { - u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK : - shadow_dirty_mask; + const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; lockdep_assert_held_write(&kvm->mmu_lock); @@ -1633,7 +1628,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (iter.level > PG_LEVEL_4K || @@ -1659,11 +1654,9 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. + * Clear the dirty status (D-bit or W-bit) of all the 4k SPTEs mapping GFNs for + * which a bit is set in mask, starting at gfn. The given memslot is expected to + * contain all the GFNs represented by set bits in the mask. */ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index c397b28e3d1b..a593b03c9aed 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -775,8 +775,20 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) pmu->pebs_data_cfg_mask = ~0ull; bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX); - if (vcpu->kvm->arch.enable_pmu) - static_call(kvm_x86_pmu_refresh)(vcpu); + if (!vcpu->kvm->arch.enable_pmu) + return; + + static_call(kvm_x86_pmu_refresh)(vcpu); + + /* + * At RESET, both Intel and AMD CPUs set all enable bits for general + * purpose counters in IA32_PERF_GLOBAL_CTRL (so that software that + * was written for v1 PMUs don't unknowingly leave GP counters disabled + * in the global controls). Emulate that behavior when refreshing the + * PMU so that userspace doesn't need to manually set PERF_GLOBAL_CTRL. + */ + if (kvm_pmu_has_perf_global_ctrl(pmu) && pmu->nr_arch_gp_counters) + pmu->global_ctrl = GENMASK_ULL(pmu->nr_arch_gp_counters - 1, 0); } void kvm_pmu_init(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 58ac8d69c94b..2f4e155080ba 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -52,7 +52,7 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) #define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) #define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) -#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) #define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) /* CPUID level 0x80000007 (EDX). */ @@ -128,6 +128,7 @@ static __always_inline u32 __feature_translate(int x86_feature) KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC); KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); default: return x86_feature; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 61a7531d41b0..759581bb2128 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -434,7 +434,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) - pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT); else pages = kmalloc(size, GFP_KERNEL_ACCOUNT); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d1a9f9951635..9aaf83c8d57d 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1503,6 +1503,11 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } +static struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd) +{ + return page_address(sd->save_area) + 0x400; +} + static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1519,12 +1524,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * or subsequent vmload of host save area. */ vmsave(sd->save_area_pa); - if (sev_es_guest(vcpu->kvm)) { - struct sev_es_save_area *hostsa; - hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); - - sev_es_prepare_switch_to_guest(hostsa); - } + if (sev_es_guest(vcpu->kvm)) + sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd)); if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); @@ -4101,6 +4102,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted) { + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); guest_state_enter_irqoff(); @@ -4108,7 +4110,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in amd_clear_divider(); if (sev_es_guest(vcpu->kvm)) - __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); + __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted, + sev_es_host_save_area(sd)); else __svm_vcpu_run(svm, spec_ctrl_intercepted); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 7f1fbd874c45..33878efdebc8 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -698,7 +698,8 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); /* vmenter.S */ -void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted, + struct sev_es_save_area *hostsa); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); #define DEFINE_KVM_GHCB_ACCESSORS(field) \ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 187018c424bf..a0c8eb37d3e1 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/asm-offsets.h> #include <asm/bitsperlong.h> +#include <asm/frame.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> #include "kvm-asm-offsets.h" @@ -67,7 +68,7 @@ "", X86_FEATURE_V_SPEC_CTRL 901: .endm -.macro RESTORE_HOST_SPEC_CTRL_BODY +.macro RESTORE_HOST_SPEC_CTRL_BODY spec_ctrl_intercepted:req 900: /* Same for after vmexit. */ mov $MSR_IA32_SPEC_CTRL, %ecx @@ -76,7 +77,7 @@ * Load the value that the guest had written into MSR_IA32_SPEC_CTRL, * if it was not intercepted during guest execution. */ - cmpb $0, (%_ASM_SP) + cmpb $0, \spec_ctrl_intercepted jnz 998f rdmsr movl %eax, SVM_spec_ctrl(%_ASM_DI) @@ -99,6 +100,7 @@ */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP + mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 push %r15 push %r14 @@ -268,7 +270,7 @@ SYM_FUNC_START(__svm_vcpu_run) RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY (%_ASM_SP) 10: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b @@ -290,66 +292,68 @@ SYM_FUNC_START(__svm_vcpu_run) SYM_FUNC_END(__svm_vcpu_run) +#ifdef CONFIG_KVM_AMD_SEV + + +#ifdef CONFIG_X86_64 +#define SEV_ES_GPRS_BASE 0x300 +#define SEV_ES_RBX (SEV_ES_GPRS_BASE + __VCPU_REGS_RBX * WORD_SIZE) +#define SEV_ES_RBP (SEV_ES_GPRS_BASE + __VCPU_REGS_RBP * WORD_SIZE) +#define SEV_ES_RSI (SEV_ES_GPRS_BASE + __VCPU_REGS_RSI * WORD_SIZE) +#define SEV_ES_RDI (SEV_ES_GPRS_BASE + __VCPU_REGS_RDI * WORD_SIZE) +#define SEV_ES_R12 (SEV_ES_GPRS_BASE + __VCPU_REGS_R12 * WORD_SIZE) +#define SEV_ES_R13 (SEV_ES_GPRS_BASE + __VCPU_REGS_R13 * WORD_SIZE) +#define SEV_ES_R14 (SEV_ES_GPRS_BASE + __VCPU_REGS_R14 * WORD_SIZE) +#define SEV_ES_R15 (SEV_ES_GPRS_BASE + __VCPU_REGS_R15 * WORD_SIZE) +#endif + /** * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode * @svm: struct vcpu_svm * * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_sev_es_vcpu_run) - push %_ASM_BP -#ifdef CONFIG_X86_64 - push %r15 - push %r14 - push %r13 - push %r12 -#else - push %edi - push %esi -#endif - push %_ASM_BX + FRAME_BEGIN /* - * Save variables needed after vmexit on the stack, in inverse - * order compared to when they are needed. + * Save non-volatile (callee-saved) registers to the host save area. + * Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not + * saved on VMRUN. */ + mov %rbp, SEV_ES_RBP (%rdx) + mov %r15, SEV_ES_R15 (%rdx) + mov %r14, SEV_ES_R14 (%rdx) + mov %r13, SEV_ES_R13 (%rdx) + mov %r12, SEV_ES_R12 (%rdx) + mov %rbx, SEV_ES_RBX (%rdx) - /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ - push %_ASM_ARG2 - - /* Save @svm. */ - push %_ASM_ARG1 - -.ifnc _ASM_ARG1, _ASM_DI /* - * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX - * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + * Save volatile registers that hold arguments that are needed after + * #VMEXIT (RDI=@svm and RSI=@spec_ctrl_intercepted). */ - mov %_ASM_ARG1, %_ASM_DI -.endif + mov %rdi, SEV_ES_RDI (%rdx) + mov %rsi, SEV_ES_RSI (%rdx) - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX (@hostsa). */ RESTORE_GUEST_SPEC_CTRL /* Get svm->current_vmcb->pa into RAX. */ - mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX - mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX + mov SVM_current_vmcb(%rdi), %rax + mov KVM_VMCB_pa(%rax), %rax /* Enter guest mode */ sti -1: vmrun %_ASM_AX +1: vmrun %rax 2: cli - /* Pop @svm to RDI, guest registers have been saved already. */ - pop %_ASM_DI - #ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */ RESTORE_HOST_SPEC_CTRL /* @@ -361,30 +365,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) */ UNTRAIN_RET_VM - /* "Pop" @spec_ctrl_intercepted. */ - pop %_ASM_BX - - pop %_ASM_BX - -#ifdef CONFIG_X86_64 - pop %r12 - pop %r13 - pop %r14 - pop %r15 -#else - pop %esi - pop %edi -#endif - pop %_ASM_BP + FRAME_END RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY %sil -3: cmpb $0, _ASM_RIP(kvm_rebooting) +3: cmpb $0, kvm_rebooting(%rip) jne 2b ud2 _ASM_EXTABLE(1b, 3b) SYM_FUNC_END(__svm_sev_es_vcpu_run) +#endif /* CONFIG_KVM_AMD_SEV */ diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 12ade343a17e..be40474de6e4 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -535,7 +535,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) perf_capabilities = vcpu_get_perf_capabilities(vcpu); if (cpuid_model_is_consistent(vcpu) && (perf_capabilities & PMU_CAP_LBR_FMT)) - x86_perf_get_lbr(&lbr_desc->records); + memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps)); else lbr_desc->records.nr = 0; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 2bfbf758d061..f6986dee6f8c 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -275,6 +275,8 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) call vmx_spec_ctrl_restore_host + CLEAR_BRANCH_HISTORY_VMEXIT + /* Put return value in AX */ mov %_ASM_BX, %_ASM_AX diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c37a89eda90f..22411f4aff53 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -218,6 +218,8 @@ module_param(ple_window_max, uint, 0444); int __read_mostly pt_mode = PT_MODE_SYSTEM; module_param(pt_mode, int, S_IRUGO); +struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; + static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); @@ -7862,10 +7864,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } -static u64 vmx_get_perf_capabilities(void) +static __init u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; - struct x86_pmu_lbr lbr; u64 host_perf_cap = 0; if (!enable_pmu) @@ -7875,15 +7876,43 @@ static u64 vmx_get_perf_capabilities(void) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { - x86_perf_get_lbr(&lbr); - if (lbr.nr) + x86_perf_get_lbr(&vmx_lbr_caps); + + /* + * KVM requires LBR callstack support, as the overhead due to + * context switching LBRs without said support is too high. + * See intel_pmu_create_guest_lbr_event() for more info. + */ + if (!vmx_lbr_caps.has_callstack) + memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps)); + else if (vmx_lbr_caps.nr) perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; } if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; + + /* + * Disallow adaptive PEBS as it is functionally broken, can be + * used by the guest to read *host* LBRs, and can be used to + * bypass userspace event filters. To correctly and safely + * support adaptive PEBS, KVM needs to: + * + * 1. Account for the ADAPTIVE flag when (re)programming fixed + * counters. + * + * 2. Gain support from perf (or take direct control of counter + * programming) to support events without adaptive PEBS + * enabled for the hardware counter. + * + * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with + * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. + * + * 4. Document which PMU events are effectively exposed to the + * guest via adaptive PEBS, and make adaptive PEBS mutually + * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. + */ + perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 65786dbe7d60..90f9e4434646 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -15,6 +15,7 @@ #include "vmx_ops.h" #include "../cpuid.h" #include "run_flags.h" +#include "../mmu.h" #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -109,6 +110,8 @@ struct lbr_desc { bool msr_passthrough; }; +extern struct x86_pmu_lbr vmx_lbr_caps; + /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -719,7 +722,8 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) if (!enable_ept) return true; - return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + return allow_smaller_maxphyaddr && + cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits(); } static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 47d9f03b7778..91478b769af0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1621,7 +1621,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ - ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR) + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { @@ -3470,7 +3470,7 @@ static bool is_mci_status_msr(u32 msr) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd_or_hygon(vcpu)) + if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index e674ccf720b9..391059b2c6fb 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -382,8 +382,15 @@ SYM_FUNC_END(call_depth_return_thunk) SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || \ + defined(CONFIG_MITIGATION_SRSO) || \ + defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) ALTERNATIVE __stringify(ANNOTATE_UNRET_SAFE; ret), \ "jmp warn_thunk_thunk", X86_FEATURE_ALWAYS +#else + ANNOTATE_UNRET_SAFE + ret +#endif int3 SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) diff --git a/block/bdev.c b/block/bdev.c index b8e32d933a63..4dc94145eb53 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -645,6 +645,14 @@ static void blkdev_flush_mapping(struct block_device *bdev) bdev_write_inode(bdev); } +static void blkdev_put_whole(struct block_device *bdev) +{ + if (atomic_dec_and_test(&bdev->bd_openers)) + blkdev_flush_mapping(bdev); + if (bdev->bd_disk->fops->release) + bdev->bd_disk->fops->release(bdev->bd_disk); +} + static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) { struct gendisk *disk = bdev->bd_disk; @@ -663,20 +671,21 @@ static int blkdev_get_whole(struct block_device *bdev, blk_mode_t mode) if (!atomic_read(&bdev->bd_openers)) set_init_blocksize(bdev); - if (test_bit(GD_NEED_PART_SCAN, &disk->state)) - bdev_disk_changed(disk, false); atomic_inc(&bdev->bd_openers); + if (test_bit(GD_NEED_PART_SCAN, &disk->state)) { + /* + * Only return scanning errors if we are called from contexts + * that explicitly want them, e.g. the BLKRRPART ioctl. + */ + ret = bdev_disk_changed(disk, false); + if (ret && (mode & BLK_OPEN_STRICT_SCAN)) { + blkdev_put_whole(bdev); + return ret; + } + } return 0; } -static void blkdev_put_whole(struct block_device *bdev) -{ - if (atomic_dec_and_test(&bdev->bd_openers)) - blkdev_flush_mapping(bdev); - if (bdev->bd_disk->fops->release) - bdev->bd_disk->fops->release(bdev->bd_disk); -} - static int blkdev_get_part(struct block_device *part, blk_mode_t mode) { struct gendisk *disk = part->bd_disk; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index bdbb557feb5a..059467086b13 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1409,6 +1409,12 @@ static int blkcg_css_online(struct cgroup_subsys_state *css) return 0; } +void blkg_init_queue(struct request_queue *q) +{ + INIT_LIST_HEAD(&q->blkg_list); + mutex_init(&q->blkcg_mutex); +} + int blkcg_init_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; @@ -1416,9 +1422,6 @@ int blkcg_init_disk(struct gendisk *disk) bool preloaded; int ret; - INIT_LIST_HEAD(&q->blkg_list); - mutex_init(&q->blkcg_mutex); - new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 78b74106bf10..90b3959d88cf 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -189,6 +189,7 @@ struct blkcg_policy { extern struct blkcg blkcg_root; extern bool blkcg_debug_stats; +void blkg_init_queue(struct request_queue *q); int blkcg_init_disk(struct gendisk *disk); void blkcg_exit_disk(struct gendisk *disk); @@ -482,6 +483,7 @@ struct blkcg { }; static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } +static inline void blkg_init_queue(struct request_queue *q) { } static inline int blkcg_init_disk(struct gendisk *disk) { return 0; } static inline void blkcg_exit_disk(struct gendisk *disk) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } diff --git a/block/blk-core.c b/block/blk-core.c index a16b5abdbbf5..b795ac177281 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -442,6 +442,8 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id) init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); + blkg_init_queue(q); + /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. @@ -1195,6 +1197,7 @@ void __blk_flush_plug(struct blk_plug *plug, bool from_schedule) if (unlikely(!rq_list_empty(plug->cached_rq))) blk_mq_free_plug_rqs(plug); + plug->cur_ktime = 0; current->flags &= ~PF_BLOCK_TS; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 9a85bfbbc45a..690ca99dfaca 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1347,7 +1347,7 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) { struct ioc *ioc = iocg->ioc; struct blkcg_gq *blkg = iocg_to_blkg(iocg); - u64 tdelta, delay, new_delay; + u64 tdelta, delay, new_delay, shift; s64 vover, vover_pct; u32 hwa; @@ -1362,8 +1362,9 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now) /* calculate the current delay in effect - 1/2 every second */ tdelta = now->now - iocg->delay_at; - if (iocg->delay) - delay = iocg->delay >> div64_u64(tdelta, USEC_PER_SEC); + shift = div64_u64(tdelta, USEC_PER_SEC); + if (iocg->delay && shift < BITS_PER_LONG) + delay = iocg->delay >> shift; else delay = 0; @@ -1438,8 +1439,11 @@ static void iocg_pay_debt(struct ioc_gq *iocg, u64 abs_vpay, lockdep_assert_held(&iocg->ioc->lock); lockdep_assert_held(&iocg->waitq.lock); - /* make sure that nobody messed with @iocg */ - WARN_ON_ONCE(list_empty(&iocg->active_list)); + /* + * make sure that nobody messed with @iocg. Check iocg->pd.online + * to avoid warn when removing blkcg or disk. + */ + WARN_ON_ONCE(list_empty(&iocg->active_list) && iocg->pd.online); WARN_ON_ONCE(iocg->inuse > 1); iocg->abs_vdebt -= min(abs_vpay, iocg->abs_vdebt); diff --git a/block/blk-settings.c b/block/blk-settings.c index cdbaef159c4b..d2731843f2fc 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -182,17 +182,13 @@ static int blk_validate_limits(struct queue_limits *lim) return -EINVAL; /* - * Devices that require a virtual boundary do not support scatter/gather - * I/O natively, but instead require a descriptor list entry for each - * page (which might not be identical to the Linux PAGE_SIZE). Because - * of that they are not limited by our notion of "segment size". + * Stacking device may have both virtual boundary and max segment + * size limit, so allow this setting now, and long-term the two + * might need to move out of stacking limits since we have immutable + * bvec and lower layer bio splitting is supposed to handle the two + * correctly. */ - if (lim->virt_boundary_mask) { - if (WARN_ON_ONCE(lim->max_segment_size && - lim->max_segment_size != UINT_MAX)) - return -EINVAL; - lim->max_segment_size = UINT_MAX; - } else { + if (!lim->virt_boundary_mask) { /* * The maximum segment size has an odd historic 64k default that * drivers probably should override. Just like the I/O size we diff --git a/block/ioctl.c b/block/ioctl.c index a9028a2c2db5..f505f9c341eb 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -563,7 +563,8 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode, return -EACCES; if (bdev_is_partition(bdev)) return -EINVAL; - return disk_scan_partitions(bdev->bd_disk, mode); + return disk_scan_partitions(bdev->bd_disk, + mode | BLK_OPEN_STRICT_SCAN); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACETEARDOWN: diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 39f6d1b98fd6..51d3f1a55d02 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include <linux/firmware.h> @@ -131,22 +131,6 @@ static int ivpu_get_capabilities(struct ivpu_device *vdev, struct drm_ivpu_param return 0; } -static int ivpu_get_core_clock_rate(struct ivpu_device *vdev, u64 *clk_rate) -{ - int ret; - - ret = ivpu_rpm_get_if_active(vdev); - if (ret < 0) - return ret; - - *clk_rate = ret ? ivpu_hw_reg_pll_freq_get(vdev) : 0; - - if (ret) - ivpu_rpm_put(vdev); - - return 0; -} - static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { struct ivpu_file_priv *file_priv = file->driver_priv; @@ -170,7 +154,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f args->value = vdev->platform; break; case DRM_IVPU_PARAM_CORE_CLOCK_RATE: - ret = ivpu_get_core_clock_rate(vdev, &args->value); + args->value = ivpu_hw_ratio_to_freq(vdev, vdev->hw->pll.max_ratio); break; case DRM_IVPU_PARAM_NUM_CONTEXTS: args->value = ivpu_get_context_count(vdev); @@ -387,12 +371,15 @@ int ivpu_shutdown(struct ivpu_device *vdev) { int ret; - ivpu_prepare_for_reset(vdev); + /* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */ + pci_save_state(to_pci_dev(vdev->drm.dev)); ret = ivpu_hw_power_down(vdev); if (ret) ivpu_warn(vdev, "Failed to power down HW: %d\n", ret); + pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); + return ret; } @@ -530,7 +517,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev) vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID; vdev->context_xa_limit.max = IVPU_USER_CONTEXT_MAX_SSID; atomic64_set(&vdev->unique_id_counter, 0); - xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC); + xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ); xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1); xa_init_flags(&vdev->db_xa, XA_FLAGS_ALLOC1); lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key); @@ -560,11 +547,11 @@ static int ivpu_dev_init(struct ivpu_device *vdev) /* Power up early so the rest of init code can access VPU registers */ ret = ivpu_hw_power_up(vdev); if (ret) - goto err_power_down; + goto err_shutdown; ret = ivpu_mmu_global_context_init(vdev); if (ret) - goto err_power_down; + goto err_shutdown; ret = ivpu_mmu_init(vdev); if (ret) @@ -601,10 +588,8 @@ err_mmu_rctx_fini: ivpu_mmu_reserved_context_fini(vdev); err_mmu_gctx_fini: ivpu_mmu_global_context_fini(vdev); -err_power_down: - ivpu_hw_power_down(vdev); - if (IVPU_WA(d3hot_after_power_off)) - pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); +err_shutdown: + ivpu_shutdown(vdev); err_xa_destroy: xa_destroy(&vdev->db_xa); xa_destroy(&vdev->submitted_jobs_xa); @@ -628,9 +613,8 @@ static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev) static void ivpu_dev_fini(struct ivpu_device *vdev) { ivpu_pm_disable(vdev); + ivpu_prepare_for_reset(vdev); ivpu_shutdown(vdev); - if (IVPU_WA(d3hot_after_power_off)) - pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); ivpu_jobs_abort_all(vdev); ivpu_job_done_consumer_fini(vdev); diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 7be0500d9bb8..bb4374d0eaec 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #ifndef __IVPU_DRV_H__ @@ -90,7 +90,6 @@ struct ivpu_wa_table { bool punit_disabled; bool clear_runtime_mem; - bool d3hot_after_power_off; bool interrupt_clear_with_0; bool disable_clock_relinquish; bool disable_d0i3_msg; diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h index b2909168a0a6..094c659d2800 100644 --- a/drivers/accel/ivpu/ivpu_hw.h +++ b/drivers/accel/ivpu/ivpu_hw.h @@ -21,6 +21,7 @@ struct ivpu_hw_ops { u32 (*profiling_freq_get)(struct ivpu_device *vdev); void (*profiling_freq_drive)(struct ivpu_device *vdev, bool enable); u32 (*reg_pll_freq_get)(struct ivpu_device *vdev); + u32 (*ratio_to_freq)(struct ivpu_device *vdev, u32 ratio); u32 (*reg_telemetry_offset_get)(struct ivpu_device *vdev); u32 (*reg_telemetry_size_get)(struct ivpu_device *vdev); u32 (*reg_telemetry_enable_get)(struct ivpu_device *vdev); @@ -130,6 +131,11 @@ static inline u32 ivpu_hw_reg_pll_freq_get(struct ivpu_device *vdev) return vdev->hw->ops->reg_pll_freq_get(vdev); }; +static inline u32 ivpu_hw_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) +{ + return vdev->hw->ops->ratio_to_freq(vdev, ratio); +} + static inline u32 ivpu_hw_reg_telemetry_offset_get(struct ivpu_device *vdev) { return vdev->hw->ops->reg_telemetry_offset_get(vdev); diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index 9a0c9498baba..bd25e2d9fb0f 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include "ivpu_drv.h" @@ -75,7 +75,6 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) { vdev->wa.punit_disabled = false; vdev->wa.clear_runtime_mem = false; - vdev->wa.d3hot_after_power_off = true; REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK); if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) { @@ -86,7 +85,6 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) IVPU_PRINT_WA(punit_disabled); IVPU_PRINT_WA(clear_runtime_mem); - IVPU_PRINT_WA(d3hot_after_power_off); IVPU_PRINT_WA(interrupt_clear_with_0); } @@ -805,12 +803,12 @@ static void ivpu_hw_37xx_profiling_freq_drive(struct ivpu_device *vdev, bool ena /* Profiling freq - is a debug feature. Unavailable on VPU 37XX. */ } -static u32 ivpu_hw_37xx_pll_to_freq(u32 ratio, u32 config) +static u32 ivpu_hw_37xx_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) { u32 pll_clock = PLL_REF_CLK_FREQ * ratio; u32 cpu_clock; - if ((config & 0xff) == PLL_RATIO_4_3) + if ((vdev->hw->config & 0xff) == PLL_RATIO_4_3) cpu_clock = pll_clock * 2 / 4; else cpu_clock = pll_clock * 2 / 5; @@ -829,7 +827,7 @@ static u32 ivpu_hw_37xx_reg_pll_freq_get(struct ivpu_device *vdev) if (!ivpu_is_silicon(vdev)) return PLL_SIMULATION_FREQ; - return ivpu_hw_37xx_pll_to_freq(pll_curr_ratio, vdev->hw->config); + return ivpu_hw_37xx_ratio_to_freq(vdev, pll_curr_ratio); } static u32 ivpu_hw_37xx_reg_telemetry_offset_get(struct ivpu_device *vdev) @@ -1052,6 +1050,7 @@ const struct ivpu_hw_ops ivpu_hw_37xx_ops = { .profiling_freq_get = ivpu_hw_37xx_profiling_freq_get, .profiling_freq_drive = ivpu_hw_37xx_profiling_freq_drive, .reg_pll_freq_get = ivpu_hw_37xx_reg_pll_freq_get, + .ratio_to_freq = ivpu_hw_37xx_ratio_to_freq, .reg_telemetry_offset_get = ivpu_hw_37xx_reg_telemetry_offset_get, .reg_telemetry_size_get = ivpu_hw_37xx_reg_telemetry_size_get, .reg_telemetry_enable_get = ivpu_hw_37xx_reg_telemetry_enable_get, diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index e4eddbf5d11c..b0b88d4c8926 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -980,6 +980,11 @@ static u32 ivpu_hw_40xx_reg_pll_freq_get(struct ivpu_device *vdev) return PLL_RATIO_TO_FREQ(pll_curr_ratio); } +static u32 ivpu_hw_40xx_ratio_to_freq(struct ivpu_device *vdev, u32 ratio) +{ + return PLL_RATIO_TO_FREQ(ratio); +} + static u32 ivpu_hw_40xx_reg_telemetry_offset_get(struct ivpu_device *vdev) { return REGB_RD32(VPU_40XX_BUTTRESS_VPU_TELEMETRY_OFFSET); @@ -1230,6 +1235,7 @@ const struct ivpu_hw_ops ivpu_hw_40xx_ops = { .profiling_freq_get = ivpu_hw_40xx_profiling_freq_get, .profiling_freq_drive = ivpu_hw_40xx_profiling_freq_drive, .reg_pll_freq_get = ivpu_hw_40xx_reg_pll_freq_get, + .ratio_to_freq = ivpu_hw_40xx_ratio_to_freq, .reg_telemetry_offset_get = ivpu_hw_40xx_reg_telemetry_offset_get, .reg_telemetry_size_get = ivpu_hw_40xx_reg_telemetry_size_get, .reg_telemetry_enable_get = ivpu_hw_40xx_reg_telemetry_enable_get, diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c index 04ac4b9840fb..56ff067f63e2 100644 --- a/drivers/accel/ivpu/ivpu_ipc.c +++ b/drivers/accel/ivpu/ivpu_ipc.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include <linux/genalloc.h> @@ -501,7 +501,11 @@ int ivpu_ipc_init(struct ivpu_device *vdev) spin_lock_init(&ipc->cons_lock); INIT_LIST_HEAD(&ipc->cons_list); INIT_LIST_HEAD(&ipc->cb_msg_list); - drmm_mutex_init(&vdev->drm, &ipc->lock); + ret = drmm_mutex_init(&vdev->drm, &ipc->lock); + if (ret) { + ivpu_err(vdev, "Failed to initialize ipc->lock, ret %d\n", ret); + goto err_free_rx; + } ivpu_ipc_reset(vdev); return 0; diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c index 91bd640655ab..2e46b322c450 100644 --- a/drivers/accel/ivpu/ivpu_mmu.c +++ b/drivers/accel/ivpu/ivpu_mmu.c @@ -278,7 +278,7 @@ static const char *ivpu_mmu_event_to_str(u32 cmd) case IVPU_MMU_EVT_F_VMS_FETCH: return "Fetch of VMS caused external abort"; default: - return "Unknown CMDQ command"; + return "Unknown event"; } } @@ -286,15 +286,15 @@ static const char *ivpu_mmu_cmdq_err_to_str(u32 err) { switch (err) { case IVPU_MMU_CERROR_NONE: - return "No CMDQ Error"; + return "No error"; case IVPU_MMU_CERROR_ILL: return "Illegal command"; case IVPU_MMU_CERROR_ABT: - return "External abort on CMDQ read"; + return "External abort on command queue read"; case IVPU_MMU_CERROR_ATC_INV_SYNC: return "Sync failed to complete ATS invalidation"; default: - return "Unknown CMDQ Error"; + return "Unknown error"; } } diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 7cce1c928a7f..4f5ea466731f 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include <linux/highmem.h> @@ -58,14 +58,11 @@ static int ivpu_suspend(struct ivpu_device *vdev) { int ret; - /* Save PCI state before powering down as it sometimes gets corrupted if NPU hangs */ - pci_save_state(to_pci_dev(vdev->drm.dev)); + ivpu_prepare_for_reset(vdev); ret = ivpu_shutdown(vdev); if (ret) - ivpu_err(vdev, "Failed to shutdown VPU: %d\n", ret); - - pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); + ivpu_err(vdev, "Failed to shutdown NPU: %d\n", ret); return ret; } @@ -74,10 +71,10 @@ static int ivpu_resume(struct ivpu_device *vdev) { int ret; - pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0); +retry: pci_restore_state(to_pci_dev(vdev->drm.dev)); + pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D0); -retry: ret = ivpu_hw_power_up(vdev); if (ret) { ivpu_err(vdev, "Failed to power up HW: %d\n", ret); @@ -100,6 +97,7 @@ err_mmu_disable: ivpu_mmu_disable(vdev); err_power_down: ivpu_hw_power_down(vdev); + pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot); if (!ivpu_fw_is_cold_boot(vdev)) { ivpu_pm_prepare_cold_boot(vdev); diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index 1fbc9b921c4f..736c2eb8c0f3 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -574,7 +574,7 @@ static u_long get_word(struct vc_data *vc) } attr_ch = get_char(vc, (u_short *)tmp_pos, &spk_attr); buf[cnt++] = attr_ch; - while (tmpx < vc->vc_cols - 1) { + while (tmpx < vc->vc_cols - 1 && cnt < sizeof(buf) - 1) { tmp_pos += 2; tmpx++; ch = get_char(vc, (u_short *)tmp_pos, &temp); diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 4bfbe55553f4..a40b6f3946ef 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/scan.c b/drivers/acpi/scan.c index 7c157bf92695..d1464324de95 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1843,7 +1843,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev) if (dep->honor_dep) adev->flags.honor_deps = 1; - adev->dep_unmet++; + if (!dep->met) + adev->dep_unmet++; } } } diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index cd84af23f7ea..dd0b40b9bbe8 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/android/binder.c b/drivers/android/binder.c index bad28cf42010..dd6923d37931 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1708,8 +1708,10 @@ static size_t binder_get_object(struct binder_proc *proc, size_t object_size = 0; read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset); - if (offset > buffer->data_size || read_size < sizeof(*hdr)) + if (offset > buffer->data_size || read_size < sizeof(*hdr) || + !IS_ALIGNED(offset, sizeof(u32))) return 0; + if (u) { if (copy_from_user(object, u + offset, read_size)) return 0; diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 562302e2e57c..6548f10e61d9 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -666,6 +666,87 @@ static int mobile_lpm_policy = -1; module_param(mobile_lpm_policy, int, 0644); MODULE_PARM_DESC(mobile_lpm_policy, "Default LPM policy for mobile chipsets"); +static char *ahci_mask_port_map; +module_param_named(mask_port_map, ahci_mask_port_map, charp, 0444); +MODULE_PARM_DESC(mask_port_map, + "32-bits port map masks to ignore controllers ports. " + "Valid values are: " + "\"<mask>\" to apply the same mask to all AHCI controller " + "devices, and \"<pci_dev>=<mask>,<pci_dev>=<mask>,...\" to " + "specify different masks for the controllers specified, " + "where <pci_dev> is the PCI ID of an AHCI controller in the " + "form \"domain:bus:dev.func\""); + +static void ahci_apply_port_map_mask(struct device *dev, + struct ahci_host_priv *hpriv, char *mask_s) +{ + unsigned int mask; + + if (kstrtouint(mask_s, 0, &mask)) { + dev_err(dev, "Invalid port map mask\n"); + return; + } + + hpriv->mask_port_map = mask; +} + +static void ahci_get_port_map_mask(struct device *dev, + struct ahci_host_priv *hpriv) +{ + char *param, *end, *str, *mask_s; + char *name; + + if (!strlen(ahci_mask_port_map)) + return; + + str = kstrdup(ahci_mask_port_map, GFP_KERNEL); + if (!str) + return; + + /* Handle single mask case */ + if (!strchr(str, '=')) { + ahci_apply_port_map_mask(dev, hpriv, str); + goto free; + } + + /* + * Mask list case: parse the parameter to apply the mask only if + * the device name matches. + */ + param = str; + end = param + strlen(param); + while (param && param < end && *param) { + name = param; + param = strchr(name, '='); + if (!param) + break; + + *param = '\0'; + param++; + if (param >= end) + break; + + if (strcmp(dev_name(dev), name) != 0) { + param = strchr(param, ','); + if (param) + param++; + continue; + } + + mask_s = param; + param = strchr(mask_s, ','); + if (param) { + *param = '\0'; + param++; + } + + ahci_apply_port_map_mask(dev, hpriv, mask_s); + } + +free: + kfree(str); +} + static void ahci_pci_save_initial_config(struct pci_dev *pdev, struct ahci_host_priv *hpriv) { @@ -688,6 +769,10 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev, "Disabling your PATA port. Use the boot option 'ahci.marvell_enable=0' to avoid this.\n"); } + /* Handle port map masks passed as module parameter. */ + if (ahci_mask_port_map) + ahci_get_port_map_mask(&pdev->dev, hpriv); + ahci_save_initial_config(&pdev->dev, hpriv); } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index be3412cdb22e..c449d60d9bb9 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2539,7 +2539,7 @@ static void ata_dev_config_cdl(struct ata_device *dev) bool cdl_enabled; u64 val; - if (ata_id_major_version(dev->id) < 12) + if (ata_id_major_version(dev->id) < 11) goto not_supported; if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE) || diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 2f4c58837641..e954976891a9 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4745,7 +4745,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) * bail out. */ if (ap->pflags & ATA_PFLAG_SUSPENDED) - goto unlock; + goto unlock_ap; if (!sdev) continue; @@ -4758,7 +4758,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) if (do_resume) { ret = scsi_resume_device(sdev); if (ret == -EWOULDBLOCK) - goto unlock; + goto unlock_scan; dev->flags &= ~ATA_DFLAG_RESUMING; } ret = scsi_rescan_device(sdev); @@ -4766,12 +4766,13 @@ void ata_scsi_dev_rescan(struct work_struct *work) spin_lock_irqsave(ap->lock, flags); if (ret) - goto unlock; + goto unlock_ap; } } -unlock: +unlock_ap: spin_unlock_irqrestore(ap->lock, flags); +unlock_scan: mutex_unlock(&ap->scsi_scan_mutex); /* Reschedule with a delay if scsi_rescan_device() returned an error */ diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index ac8ebccd3507..812fd2a8f853 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 19cfc342fc7b..216826c31ee3 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 06e915b57283..e3946f7b736e 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 ecbc52eaf101..0c9c9ee56592 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 @@ retry: 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 @@ retry: 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/cache/sifive_ccache.c b/drivers/cache/sifive_ccache.c index 89ed6cd6b059..e9cc8b4786fb 100644 --- a/drivers/cache/sifive_ccache.c +++ b/drivers/cache/sifive_ccache.c @@ -15,6 +15,8 @@ #include <linux/of_address.h> #include <linux/device.h> #include <linux/bitfield.h> +#include <linux/platform_device.h> +#include <linux/property.h> #include <asm/cacheflush.h> #include <asm/cacheinfo.h> #include <asm/dma-noncoherent.h> @@ -247,13 +249,49 @@ static irqreturn_t ccache_int_handler(int irq, void *device) return IRQ_HANDLED; } +static int sifive_ccache_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + unsigned long quirks; + int intr_num, rc; + + quirks = (unsigned long)device_get_match_data(dev); + + intr_num = platform_irq_count(pdev); + if (!intr_num) + return dev_err_probe(dev, -ENODEV, "No interrupts property\n"); + + for (int i = 0; i < intr_num; i++) { + if (i == DATA_UNCORR && (quirks & QUIRK_BROKEN_DATA_UNCORR)) + continue; + + g_irq[i] = platform_get_irq(pdev, i); + if (g_irq[i] < 0) + return g_irq[i]; + + rc = devm_request_irq(dev, g_irq[i], ccache_int_handler, 0, "ccache_ecc", NULL); + if (rc) + return dev_err_probe(dev, rc, "Could not request IRQ %d\n", g_irq[i]); + } + + return 0; +} + +static struct platform_driver sifive_ccache_driver = { + .probe = sifive_ccache_probe, + .driver = { + .name = "sifive_ccache", + .of_match_table = sifive_ccache_ids, + }, +}; + static int __init sifive_ccache_init(void) { struct device_node *np; struct resource res; - int i, rc, intr_num; const struct of_device_id *match; unsigned long quirks; + int rc; np = of_find_matching_node_and_match(NULL, sifive_ccache_ids, &match); if (!np) @@ -277,28 +315,6 @@ static int __init sifive_ccache_init(void) goto err_unmap; } - intr_num = of_property_count_u32_elems(np, "interrupts"); - if (!intr_num) { - pr_err("No interrupts property\n"); - rc = -ENODEV; - goto err_unmap; - } - - for (i = 0; i < intr_num; i++) { - g_irq[i] = irq_of_parse_and_map(np, i); - - if (i == DATA_UNCORR && (quirks & QUIRK_BROKEN_DATA_UNCORR)) - continue; - - rc = request_irq(g_irq[i], ccache_int_handler, 0, "ccache_ecc", - NULL); - if (rc) { - pr_err("Could not request IRQ %d\n", g_irq[i]); - goto err_free_irq; - } - } - of_node_put(np); - #ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS if (quirks & QUIRK_NONSTANDARD_CACHE_OPS) { riscv_cbom_block_size = SIFIVE_CCACHE_LINE_SIZE; @@ -315,11 +331,15 @@ static int __init sifive_ccache_init(void) #ifdef CONFIG_DEBUG_FS setup_sifive_debug(); #endif + + rc = platform_driver_register(&sifive_ccache_driver); + if (rc) + goto err_unmap; + + of_node_put(np); + return 0; -err_free_irq: - while (--i >= 0) - free_irq(g_irq[i], NULL); err_unmap: iounmap(ccache_base); err_node_put: diff --git a/drivers/char/random.c b/drivers/char/random.c index 456be28ba67c..2597cb43f438 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -702,7 +702,7 @@ static void extract_entropy(void *buf, size_t len) static void __cold _credit_init_bits(size_t bits) { - static struct execute_work set_ready; + static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; @@ -718,8 +718,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - if (static_key_initialized) - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized && system_unbound_wq) + queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); @@ -890,8 +890,8 @@ void __init random_init(void) /* * If we were initialized by the cpu or bootloader before jump labels - * are initialized, then we should enable the static branch here, where - * it's guaranteed that jump labels have been initialized. + * or workqueues are initialized, then we should enable the static + * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 25371c91a58f..8cca52be993f 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -37,6 +37,10 @@ static HLIST_HEAD(clk_root_list); static HLIST_HEAD(clk_orphan_list); static LIST_HEAD(clk_notifier_list); +/* List of registered clks that use runtime PM */ +static HLIST_HEAD(clk_rpm_list); +static DEFINE_MUTEX(clk_rpm_list_lock); + static const struct hlist_head *all_lists[] = { &clk_root_list, &clk_orphan_list, @@ -59,6 +63,7 @@ struct clk_core { struct clk_hw *hw; struct module *owner; struct device *dev; + struct hlist_node rpm_node; struct device_node *of_node; struct clk_core *parent; struct clk_parent_map *parents; @@ -122,6 +127,89 @@ static void clk_pm_runtime_put(struct clk_core *core) pm_runtime_put_sync(core->dev); } +/** + * clk_pm_runtime_get_all() - Runtime "get" all clk provider devices + * + * Call clk_pm_runtime_get() on all runtime PM enabled clks in the clk tree so + * that disabling unused clks avoids a deadlock where a device is runtime PM + * resuming/suspending and the runtime PM callback is trying to grab the + * prepare_lock for something like clk_prepare_enable() while + * clk_disable_unused_subtree() holds the prepare_lock and is trying to runtime + * PM resume/suspend the device as well. + * + * Context: Acquires the 'clk_rpm_list_lock' and returns with the lock held on + * success. Otherwise the lock is released on failure. + * + * Return: 0 on success, negative errno otherwise. + */ +static int clk_pm_runtime_get_all(void) +{ + int ret; + struct clk_core *core, *failed; + + /* + * Grab the list lock to prevent any new clks from being registered + * or unregistered until clk_pm_runtime_put_all(). + */ + mutex_lock(&clk_rpm_list_lock); + + /* + * Runtime PM "get" all the devices that are needed for the clks + * currently registered. Do this without holding the prepare_lock, to + * avoid the deadlock. + */ + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + ret = clk_pm_runtime_get(core); + if (ret) { + failed = core; + pr_err("clk: Failed to runtime PM get '%s' for clk '%s'\n", + dev_name(failed->dev), failed->name); + goto err; + } + } + + return 0; + +err: + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) { + if (core == failed) + break; + + clk_pm_runtime_put(core); + } + mutex_unlock(&clk_rpm_list_lock); + + return ret; +} + +/** + * clk_pm_runtime_put_all() - Runtime "put" all clk provider devices + * + * Put the runtime PM references taken in clk_pm_runtime_get_all() and release + * the 'clk_rpm_list_lock'. + */ +static void clk_pm_runtime_put_all(void) +{ + struct clk_core *core; + + hlist_for_each_entry(core, &clk_rpm_list, rpm_node) + clk_pm_runtime_put(core); + mutex_unlock(&clk_rpm_list_lock); +} + +static void clk_pm_runtime_init(struct clk_core *core) +{ + struct device *dev = core->dev; + + if (dev && pm_runtime_enabled(dev)) { + core->rpm_enabled = true; + + mutex_lock(&clk_rpm_list_lock); + hlist_add_head(&core->rpm_node, &clk_rpm_list); + mutex_unlock(&clk_rpm_list_lock); + } +} + /*** locking ***/ static void clk_prepare_lock(void) { @@ -1381,9 +1469,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) if (core->flags & CLK_IGNORE_UNUSED) return; - if (clk_pm_runtime_get(core)) - return; - if (clk_core_is_prepared(core)) { trace_clk_unprepare(core); if (core->ops->unprepare_unused) @@ -1392,8 +1477,6 @@ static void __init clk_unprepare_unused_subtree(struct clk_core *core) core->ops->unprepare(core->hw); trace_clk_unprepare_complete(core); } - - clk_pm_runtime_put(core); } static void __init clk_disable_unused_subtree(struct clk_core *core) @@ -1409,9 +1492,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_prepare_enable(core->parent); - if (clk_pm_runtime_get(core)) - goto unprepare_out; - flags = clk_enable_lock(); if (core->enable_count) @@ -1436,8 +1516,6 @@ static void __init clk_disable_unused_subtree(struct clk_core *core) unlock_out: clk_enable_unlock(flags); - clk_pm_runtime_put(core); -unprepare_out: if (core->flags & CLK_OPS_PARENT_ENABLE) clk_core_disable_unprepare(core->parent); } @@ -1453,6 +1531,7 @@ __setup("clk_ignore_unused", clk_ignore_unused_setup); static int __init clk_disable_unused(void) { struct clk_core *core; + int ret; if (clk_ignore_unused) { pr_warn("clk: Not disabling unused clocks\n"); @@ -1461,6 +1540,13 @@ static int __init clk_disable_unused(void) pr_info("clk: Disabling unused clocks\n"); + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; + /* + * Grab the prepare lock to keep the clk topology stable while iterating + * over clks. + */ clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) @@ -1477,6 +1563,8 @@ static int __init clk_disable_unused(void) clk_prepare_unlock(); + clk_pm_runtime_put_all(); + return 0; } late_initcall_sync(clk_disable_unused); @@ -3252,9 +3340,7 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, { struct clk_core *child; - clk_pm_runtime_get(c); clk_summary_show_one(s, c, level); - clk_pm_runtime_put(c); hlist_for_each_entry(child, &c->children, child_node) clk_summary_show_subtree(s, child, level + 1); @@ -3264,11 +3350,15 @@ static int clk_summary_show(struct seq_file *s, void *data) { struct clk_core *c; struct hlist_head **lists = s->private; + int ret; seq_puts(s, " enable prepare protect duty hardware connection\n"); seq_puts(s, " clock count count count rate accuracy phase cycle enable consumer id\n"); seq_puts(s, "---------------------------------------------------------------------------------------------------------------------------------------------\n"); + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; clk_prepare_lock(); @@ -3277,6 +3367,7 @@ static int clk_summary_show(struct seq_file *s, void *data) clk_summary_show_subtree(s, c, 0); clk_prepare_unlock(); + clk_pm_runtime_put_all(); return 0; } @@ -3324,8 +3415,14 @@ static int clk_dump_show(struct seq_file *s, void *data) struct clk_core *c; bool first_node = true; struct hlist_head **lists = s->private; + int ret; + + ret = clk_pm_runtime_get_all(); + if (ret) + return ret; seq_putc(s, '{'); + clk_prepare_lock(); for (; *lists; lists++) { @@ -3338,6 +3435,7 @@ static int clk_dump_show(struct seq_file *s, void *data) } clk_prepare_unlock(); + clk_pm_runtime_put_all(); seq_puts(s, "}\n"); return 0; @@ -3981,8 +4079,6 @@ static int __clk_core_init(struct clk_core *core) } clk_core_reparent_orphans_nolock(); - - kref_init(&core->ref); out: clk_pm_runtime_put(core); unlock: @@ -4211,6 +4307,22 @@ static void clk_core_free_parent_map(struct clk_core *core) kfree(core->parents); } +/* Free memory allocated for a struct clk_core */ +static void __clk_release(struct kref *ref) +{ + struct clk_core *core = container_of(ref, struct clk_core, ref); + + if (core->rpm_enabled) { + mutex_lock(&clk_rpm_list_lock); + hlist_del(&core->rpm_node); + mutex_unlock(&clk_rpm_list_lock); + } + + clk_core_free_parent_map(core); + kfree_const(core->name); + kfree(core); +} + static struct clk * __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) { @@ -4231,6 +4343,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_out; } + kref_init(&core->ref); + core->name = kstrdup_const(init->name, GFP_KERNEL); if (!core->name) { ret = -ENOMEM; @@ -4243,9 +4357,8 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) } core->ops = init->ops; - if (dev && pm_runtime_enabled(dev)) - core->rpm_enabled = true; core->dev = dev; + clk_pm_runtime_init(core); core->of_node = np; if (dev && dev->driver) core->owner = dev->driver->owner; @@ -4285,12 +4398,10 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) hw->clk = NULL; fail_create_clk: - clk_core_free_parent_map(core); fail_parents: fail_ops: - kfree_const(core->name); fail_name: - kfree(core); + kref_put(&core->ref, __clk_release); fail_out: return ERR_PTR(ret); } @@ -4370,18 +4481,6 @@ int of_clk_hw_register(struct device_node *node, struct clk_hw *hw) } EXPORT_SYMBOL_GPL(of_clk_hw_register); -/* Free memory allocated for a clock. */ -static void __clk_release(struct kref *ref) -{ - struct clk_core *core = container_of(ref, struct clk_core, ref); - - lockdep_assert_held(&prepare_lock); - - clk_core_free_parent_map(core); - kfree_const(core->name); - kfree(core); -} - /* * Empty clk_ops for unregistered clocks. These are used temporarily * after clk_unregister() was called on a clock and until last clock @@ -4472,7 +4571,8 @@ void clk_unregister(struct clk *clk) if (ops == &clk_nodrv_ops) { pr_err("%s: unregistered clock: %s\n", __func__, clk->core->name); - goto unlock; + clk_prepare_unlock(); + return; } /* * Assign empty clock ops for consumers that might still hold @@ -4506,11 +4606,10 @@ void clk_unregister(struct clk *clk) if (clk->core->protect_count) pr_warn("%s: unregistering protected clock: %s\n", __func__, clk->core->name); + clk_prepare_unlock(); kref_put(&clk->core->ref, __clk_release); free_clk(clk); -unlock: - clk_prepare_unlock(); } EXPORT_SYMBOL_GPL(clk_unregister); @@ -4669,13 +4768,11 @@ void __clk_put(struct clk *clk) if (clk->min_rate > 0 || clk->max_rate < ULONG_MAX) clk_set_rate_range_nolock(clk, 0, ULONG_MAX); - owner = clk->core->owner; - kref_put(&clk->core->ref, __clk_release); - clk_prepare_unlock(); + owner = clk->core->owner; + kref_put(&clk->core->ref, __clk_release); module_put(owner); - free_clk(clk); } diff --git a/drivers/clk/mediatek/clk-mt7988-infracfg.c b/drivers/clk/mediatek/clk-mt7988-infracfg.c index 449041f8abbc..c8c023afe3e5 100644 --- a/drivers/clk/mediatek/clk-mt7988-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7988-infracfg.c @@ -156,7 +156,7 @@ static const struct mtk_gate infra_clks[] = { GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P1, "infra_pcie_peri_ck_26m_ck_p1", "csw_infra_f26m_sel", 8), GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P2, "infra_pcie_peri_ck_26m_ck_p2", - "csw_infra_f26m_sel", 9), + "infra_pcie_peri_ck_26m_ck_p3", 9), GATE_INFRA0(CLK_INFRA_PCIE_PERI_26M_CK_P3, "infra_pcie_peri_ck_26m_ck_p3", "csw_infra_f26m_sel", 10), /* INFRA1 */ diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index 2e55368dc4d8..bd37ab4d1a9b 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -13,6 +13,7 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/slab.h> #include "clk-mtk.h" @@ -494,6 +495,16 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, return IS_ERR(base) ? PTR_ERR(base) : -ENOMEM; } + + devm_pm_runtime_enable(&pdev->dev); + /* + * Do a pm_runtime_resume_and_get() to workaround a possible + * deadlock between clk_register() and the genpd framework. + */ + r = pm_runtime_resume_and_get(&pdev->dev); + if (r) + return r; + /* Calculate how many clk_hw_onecell_data entries to allocate */ num_clks = mcd->num_clks + mcd->num_composite_clks; num_clks += mcd->num_fixed_clks + mcd->num_factor_clks; @@ -574,6 +585,8 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, goto unregister_clks; } + pm_runtime_put(&pdev->dev); + return r; unregister_clks: @@ -604,6 +617,8 @@ free_data: free_base: if (mcd->shared_io && base) iounmap(base); + + pm_runtime_put(&pdev->dev); return r; } diff --git a/drivers/comedi/drivers/vmk80xx.c b/drivers/comedi/drivers/vmk80xx.c index 4536ed43f65b..84dce5184a77 100644 --- a/drivers/comedi/drivers/vmk80xx.c +++ b/drivers/comedi/drivers/vmk80xx.c @@ -641,33 +641,22 @@ static int vmk80xx_find_usb_endpoints(struct comedi_device *dev) struct vmk80xx_private *devpriv = dev->private; struct usb_interface *intf = comedi_to_usb_interface(dev); struct usb_host_interface *iface_desc = intf->cur_altsetting; - struct usb_endpoint_descriptor *ep_desc; - int i; - - if (iface_desc->desc.bNumEndpoints != 2) - return -ENODEV; - - for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) { - ep_desc = &iface_desc->endpoint[i].desc; - - if (usb_endpoint_is_int_in(ep_desc) || - usb_endpoint_is_bulk_in(ep_desc)) { - if (!devpriv->ep_rx) - devpriv->ep_rx = ep_desc; - continue; - } + struct usb_endpoint_descriptor *ep_rx_desc, *ep_tx_desc; + int ret; - if (usb_endpoint_is_int_out(ep_desc) || - usb_endpoint_is_bulk_out(ep_desc)) { - if (!devpriv->ep_tx) - devpriv->ep_tx = ep_desc; - continue; - } - } + if (devpriv->model == VMK8061_MODEL) + ret = usb_find_common_endpoints(iface_desc, &ep_rx_desc, + &ep_tx_desc, NULL, NULL); + else + ret = usb_find_common_endpoints(iface_desc, NULL, NULL, + &ep_rx_desc, &ep_tx_desc); - if (!devpriv->ep_rx || !devpriv->ep_tx) + if (ret) return -ENODEV; + devpriv->ep_rx = ep_rx_desc; + devpriv->ep_tx = ep_tx_desc; + if (!usb_endpoint_maxp(devpriv->ep_rx) || !usb_endpoint_maxp(devpriv->ep_tx)) return -EINVAL; diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index af5cb818f84d..cb8c155a2c9b 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -525,22 +525,11 @@ static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport) { struct acpi_device *hb = to_cxl_host_bridge(NULL, dev); u32 uid; - int rc; if (kstrtou32(acpi_device_uid(hb), 0, &uid)) return -EINVAL; - rc = acpi_get_genport_coordinates(uid, dport->hb_coord); - if (rc < 0) - return rc; - - /* Adjust back to picoseconds from nanoseconds */ - for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { - dport->hb_coord[i].read_latency *= 1000; - dport->hb_coord[i].write_latency *= 1000; - } - - return 0; + return acpi_get_genport_coordinates(uid, dport->coord); } static int add_host_bridge_dport(struct device *match, void *arg) diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c index eddbbe21450c..bb83867d9fec 100644 --- a/drivers/cxl/core/cdat.c +++ b/drivers/cxl/core/cdat.c @@ -14,12 +14,42 @@ struct dsmas_entry { struct range dpa_range; u8 handle; - struct access_coordinate coord; + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; int entries; int qos_class; }; +static u32 cdat_normalize(u16 entry, u64 base, u8 type) +{ + u32 value; + + /* + * Check for invalid and overflow values + */ + if (entry == 0xffff || !entry) + return 0; + else if (base > (UINT_MAX / (entry))) + return 0; + + /* + * CDAT fields follow the format of HMAT fields. See table 5 Device + * Scoped Latency and Bandwidth Information Structure in Coherent Device + * Attribute Table (CDAT) Specification v1.01. + */ + value = entry * base; + switch (type) { + case ACPI_HMAT_ACCESS_LATENCY: + case ACPI_HMAT_READ_LATENCY: + case ACPI_HMAT_WRITE_LATENCY: + value = DIV_ROUND_UP(value, 1000); + break; + default: + break; + } + return value; +} + static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg, const unsigned long end) { @@ -58,8 +88,8 @@ static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg, return 0; } -static void cxl_access_coordinate_set(struct access_coordinate *coord, - int access, unsigned int val) +static void __cxl_access_coordinate_set(struct access_coordinate *coord, + int access, unsigned int val) { switch (access) { case ACPI_HMAT_ACCESS_LATENCY: @@ -85,6 +115,13 @@ static void cxl_access_coordinate_set(struct access_coordinate *coord, } } +static void cxl_access_coordinate_set(struct access_coordinate *coord, + int access, unsigned int val) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + __cxl_access_coordinate_set(&coord[i], access, val); +} + static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg, const unsigned long end) { @@ -97,7 +134,6 @@ static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg, __le16 le_val; u64 val; u16 len; - int rc; len = le16_to_cpu((__force __le16)hdr->length); if (len != size || (unsigned long)hdr + len > end) { @@ -124,12 +160,10 @@ static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg, le_base = (__force __le64)dslbis->entry_base_unit; le_val = (__force __le16)dslbis->entry[0]; - rc = check_mul_overflow(le64_to_cpu(le_base), - le16_to_cpu(le_val), &val); - if (rc) - pr_warn("DSLBIS value overflowed.\n"); + val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base), + dslbis->data_type); - cxl_access_coordinate_set(&dent->coord, dslbis->data_type, val); + cxl_access_coordinate_set(dent->coord, dslbis->data_type, val); return 0; } @@ -163,25 +197,18 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port, static int cxl_port_perf_data_calculate(struct cxl_port *port, struct xarray *dsmas_xa) { - struct access_coordinate ep_c; - struct access_coordinate coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate ep_c[ACCESS_COORDINATE_MAX]; struct dsmas_entry *dent; int valid_entries = 0; unsigned long index; int rc; - rc = cxl_endpoint_get_perf_coordinates(port, &ep_c); + rc = cxl_endpoint_get_perf_coordinates(port, ep_c); if (rc) { dev_dbg(&port->dev, "Failed to retrieve ep perf coordinates.\n"); return rc; } - rc = cxl_hb_get_perf_coordinates(port, coord); - if (rc) { - dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n"); - return rc; - } - struct cxl_root *cxl_root __free(put_cxl_root) = find_cxl_root(port); if (!cxl_root) @@ -193,18 +220,10 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, xa_for_each(dsmas_xa, index, dent) { int qos_class; - cxl_coordinates_combine(&dent->coord, &dent->coord, &ep_c); - /* - * Keeping the host bridge coordinates separate from the dsmas - * coordinates in order to allow calculation of access class - * 0 and 1 for region later. - */ - cxl_coordinates_combine(&coord[ACCESS_COORDINATE_CPU], - &coord[ACCESS_COORDINATE_CPU], - &dent->coord); + cxl_coordinates_combine(dent->coord, dent->coord, ep_c); dent->entries = 1; rc = cxl_root->ops->qos_class(cxl_root, - &coord[ACCESS_COORDINATE_CPU], + &dent->coord[ACCESS_COORDINATE_CPU], 1, &qos_class); if (rc != 1) continue; @@ -222,14 +241,17 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, static void update_perf_entry(struct device *dev, struct dsmas_entry *dent, struct cxl_dpa_perf *dpa_perf) { + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + dpa_perf->coord[i] = dent->coord[i]; dpa_perf->dpa_range = dent->dpa_range; - dpa_perf->coord = dent->coord; dpa_perf->qos_class = dent->qos_class; dev_dbg(dev, "DSMAS: dpa: %#llx qos: %d read_bw: %d write_bw %d read_lat: %d write_lat: %d\n", dent->dpa_range.start, dpa_perf->qos_class, - dent->coord.read_bandwidth, dent->coord.write_bandwidth, - dent->coord.read_latency, dent->coord.write_latency); + dent->coord[ACCESS_COORDINATE_CPU].read_bandwidth, + dent->coord[ACCESS_COORDINATE_CPU].write_bandwidth, + dent->coord[ACCESS_COORDINATE_CPU].read_latency, + dent->coord[ACCESS_COORDINATE_CPU].write_latency); } static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds, @@ -461,17 +483,16 @@ static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg, le_base = (__force __le64)tbl->sslbis_header.entry_base_unit; le_val = (__force __le16)tbl->entries[i].latency_or_bandwidth; - - if (check_mul_overflow(le64_to_cpu(le_base), - le16_to_cpu(le_val), &val)) - dev_warn(dev, "SSLBIS value overflowed!\n"); + val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base), + sslbis->data_type); xa_for_each(&port->dports, index, dport) { if (dsp_id == ACPI_CDAT_SSLBIS_ANY_PORT || - dsp_id == dport->port_id) - cxl_access_coordinate_set(&dport->sw_coord, + dsp_id == dport->port_id) { + cxl_access_coordinate_set(dport->coord, sslbis->data_type, val); + } } } @@ -493,6 +514,21 @@ void cxl_switch_parse_cdat(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL); +static void __cxl_coordinates_combine(struct access_coordinate *out, + struct access_coordinate *c1, + struct access_coordinate *c2) +{ + if (c1->write_bandwidth && c2->write_bandwidth) + out->write_bandwidth = min(c1->write_bandwidth, + c2->write_bandwidth); + out->write_latency = c1->write_latency + c2->write_latency; + + if (c1->read_bandwidth && c2->read_bandwidth) + out->read_bandwidth = min(c1->read_bandwidth, + c2->read_bandwidth); + out->read_latency = c1->read_latency + c2->read_latency; +} + /** * cxl_coordinates_combine - Combine the two input coordinates * @@ -504,15 +540,8 @@ void cxl_coordinates_combine(struct access_coordinate *out, struct access_coordinate *c1, struct access_coordinate *c2) { - if (c1->write_bandwidth && c2->write_bandwidth) - out->write_bandwidth = min(c1->write_bandwidth, - c2->write_bandwidth); - out->write_latency = c1->write_latency + c2->write_latency; - - if (c1->read_bandwidth && c2->read_bandwidth) - out->read_bandwidth = min(c1->read_bandwidth, - c2->read_bandwidth); - out->read_latency = c1->read_latency + c2->read_latency; + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + __cxl_coordinates_combine(&out[i], &c1[i], &c2[i]); } MODULE_IMPORT_NS(CXL); @@ -521,17 +550,13 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr, struct cxl_endpoint_decoder *cxled) { struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); - struct cxl_port *port = cxlmd->endpoint; struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds); - struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX]; - struct access_coordinate coord; struct range dpa = { .start = cxled->dpa_res->start, .end = cxled->dpa_res->end, }; struct cxl_dpa_perf *perf; - int rc; switch (cxlr->mode) { case CXL_DECODER_RAM: @@ -549,35 +574,16 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr, if (!range_contains(&perf->dpa_range, &dpa)) return; - rc = cxl_hb_get_perf_coordinates(port, hb_coord); - if (rc) { - dev_dbg(&port->dev, "Failed to retrieve hb perf coordinates.\n"); - return; - } - for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { - /* Pickup the host bridge coords */ - cxl_coordinates_combine(&coord, &hb_coord[i], &perf->coord); - /* Get total bandwidth and the worst latency for the cxl region */ cxlr->coord[i].read_latency = max_t(unsigned int, cxlr->coord[i].read_latency, - coord.read_latency); + perf->coord[i].read_latency); cxlr->coord[i].write_latency = max_t(unsigned int, cxlr->coord[i].write_latency, - coord.write_latency); - cxlr->coord[i].read_bandwidth += coord.read_bandwidth; - cxlr->coord[i].write_bandwidth += coord.write_bandwidth; - - /* - * Convert latency to nanosec from picosec to be consistent - * with the resulting latency coordinates computed by the - * HMAT_REPORTING code. - */ - cxlr->coord[i].read_latency = - DIV_ROUND_UP(cxlr->coord[i].read_latency, 1000); - cxlr->coord[i].write_latency = - DIV_ROUND_UP(cxlr->coord[i].write_latency, 1000); + perf->coord[i].write_latency); + cxlr->coord[i].read_bandwidth += perf->coord[i].read_bandwidth; + cxlr->coord[i].write_bandwidth += perf->coord[i].write_bandwidth; } } diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 9adda4795eb7..f0f54aeccc87 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -915,7 +915,7 @@ static int cxl_clear_event_record(struct cxl_memdev_state *mds, payload->handles[i++] = gen->hdr.handle; dev_dbg(mds->cxlds.dev, "Event log '%d': Clearing %u\n", log, - le16_to_cpu(payload->handles[i])); + le16_to_cpu(payload->handles[i - 1])); if (i == max_handles) { payload->nr_recs = i; @@ -958,13 +958,14 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, .payload_in = &log_type, .size_in = sizeof(log_type), .payload_out = payload, - .size_out = mds->payload_size, .min_out = struct_size(payload, records, 0), }; do { int rc, i; + mbox_cmd.size_out = mds->payload_size; + rc = cxl_internal_send_cmd(mds, &mbox_cmd); if (rc) { dev_err_ratelimited(dev, diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 2b0cab556072..762783bb091a 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -2133,36 +2133,44 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd) } EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL); -/** - * cxl_hb_get_perf_coordinates - Retrieve performance numbers between initiator - * and host bridge - * - * @port: endpoint cxl_port - * @coord: output access coordinates - * - * Return: errno on failure, 0 on success. - */ -int cxl_hb_get_perf_coordinates(struct cxl_port *port, - struct access_coordinate *coord) +static void add_latency(struct access_coordinate *c, long latency) { - struct cxl_port *iter = port; - struct cxl_dport *dport; + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + c[i].write_latency += latency; + c[i].read_latency += latency; + } +} - if (!is_cxl_endpoint(port)) - return -EINVAL; +static bool coordinates_valid(struct access_coordinate *c) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + if (c[i].read_bandwidth && c[i].write_bandwidth && + c[i].read_latency && c[i].write_latency) + continue; + return false; + } - dport = iter->parent_dport; - while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) { - iter = to_cxl_port(iter->dev.parent); - dport = iter->parent_dport; + return true; +} + +static void set_min_bandwidth(struct access_coordinate *c, unsigned int bw) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + c[i].write_bandwidth = min(c[i].write_bandwidth, bw); + c[i].read_bandwidth = min(c[i].read_bandwidth, bw); } +} - coord[ACCESS_COORDINATE_LOCAL] = - dport->hb_coord[ACCESS_COORDINATE_LOCAL]; - coord[ACCESS_COORDINATE_CPU] = - dport->hb_coord[ACCESS_COORDINATE_CPU]; +static void set_access_coordinates(struct access_coordinate *out, + struct access_coordinate *in) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + out[i] = in[i]; +} - return 0; +static bool parent_port_is_cxl_root(struct cxl_port *port) +{ + return is_cxl_root(to_cxl_port(port->dev.parent)); } /** @@ -2176,35 +2184,53 @@ int cxl_hb_get_perf_coordinates(struct cxl_port *port, int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, struct access_coordinate *coord) { - struct access_coordinate c = { - .read_bandwidth = UINT_MAX, - .write_bandwidth = UINT_MAX, + struct access_coordinate c[] = { + { + .read_bandwidth = UINT_MAX, + .write_bandwidth = UINT_MAX, + }, + { + .read_bandwidth = UINT_MAX, + .write_bandwidth = UINT_MAX, + }, }; struct cxl_port *iter = port; struct cxl_dport *dport; struct pci_dev *pdev; unsigned int bw; + bool is_cxl_root; if (!is_cxl_endpoint(port)) return -EINVAL; - dport = iter->parent_dport; - /* - * Exit the loop when the parent port of the current port is cxl root. - * The iterative loop starts at the endpoint and gathers the - * latency of the CXL link from the current iter to the next downstream - * port each iteration. If the parent is cxl root then there is - * nothing to gather. + * Exit the loop when the parent port of the current iter port is cxl + * root. The iterative loop starts at the endpoint and gathers the + * latency of the CXL link from the current device/port to the connected + * downstream port each iteration. */ - while (iter && !is_cxl_root(to_cxl_port(iter->dev.parent))) { - cxl_coordinates_combine(&c, &c, &dport->sw_coord); - c.write_latency += dport->link_latency; - c.read_latency += dport->link_latency; - - iter = to_cxl_port(iter->dev.parent); + do { dport = iter->parent_dport; - } + iter = to_cxl_port(iter->dev.parent); + is_cxl_root = parent_port_is_cxl_root(iter); + + /* + * There's no valid access_coordinate for a root port since RPs do not + * have CDAT and therefore needs to be skipped. + */ + if (!is_cxl_root) { + if (!coordinates_valid(dport->coord)) + return -EINVAL; + cxl_coordinates_combine(c, c, dport->coord); + } + add_latency(c, dport->link_latency); + } while (!is_cxl_root); + + dport = iter->parent_dport; + /* Retrieve HB coords */ + if (!coordinates_valid(dport->coord)) + return -EINVAL; + cxl_coordinates_combine(c, c, dport->coord); /* Get the calculated PCI paths bandwidth */ pdev = to_pci_dev(port->uport_dev->parent); @@ -2213,10 +2239,8 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, return -ENXIO; bw /= BITS_PER_BYTE; - c.write_bandwidth = min(c.write_bandwidth, bw); - c.read_bandwidth = min(c.read_bandwidth, bw); - - *coord = c; + set_min_bandwidth(c, bw); + set_access_coordinates(coord, c); return 0; } diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c index 372786f80955..3c42f984eeaf 100644 --- a/drivers/cxl/core/regs.c +++ b/drivers/cxl/core/regs.c @@ -271,6 +271,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_map_device_regs, CXL); static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi, struct cxl_register_map *map) { + u8 reg_type = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK, reg_lo); int bar = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BIR_MASK, reg_lo); u64 offset = ((u64)reg_hi << 32) | (reg_lo & CXL_DVSEC_REG_LOCATOR_BLOCK_OFF_LOW_MASK); @@ -278,11 +279,11 @@ static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi, if (offset > pci_resource_len(pdev, bar)) { dev_warn(&pdev->dev, "BAR%d: %pr: too small (offset: %pa, type: %d)\n", bar, - &pdev->resource[bar], &offset, map->reg_type); + &pdev->resource[bar], &offset, reg_type); return false; } - map->reg_type = FIELD_GET(CXL_DVSEC_REG_LOCATOR_BLOCK_ID_MASK, reg_lo); + map->reg_type = reg_type; map->resource = pci_resource_start(pdev, bar) + offset; map->max_size = pci_resource_len(pdev, bar) - offset; return true; diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 534e25e2f0a4..036d17db68e0 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -663,8 +663,7 @@ struct cxl_rcrb_info { * @rch: Indicate whether this dport was enumerated in RCH or VH mode * @port: reference to cxl_port that contains this downstream port * @regs: Dport parsed register blocks - * @sw_coord: access coordinates (performance) for switch from CDAT - * @hb_coord: access coordinates (performance) from ACPI generic port (host bridge) + * @coord: access coordinates (bandwidth and latency performance attributes) * @link_latency: calculated PCIe downstream latency */ struct cxl_dport { @@ -675,8 +674,7 @@ struct cxl_dport { bool rch; struct cxl_port *port; struct cxl_regs regs; - struct access_coordinate sw_coord; - struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; long link_latency; }; @@ -884,8 +882,6 @@ void cxl_switch_parse_cdat(struct cxl_port *port); int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, struct access_coordinate *coord); -int cxl_hb_get_perf_coordinates(struct cxl_port *port, - struct access_coordinate *coord); void cxl_region_perf_data_calculate(struct cxl_region *cxlr, struct cxl_endpoint_decoder *cxled); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 20fb3b35e89e..36cee9c30ceb 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -401,7 +401,7 @@ enum cxl_devtype { */ struct cxl_dpa_perf { struct range dpa_range; - struct access_coordinate coord; + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; int qos_class; }; diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 64eaca80d736..d0f6693ca142 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/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index f2556a8e9401..9bc2e10381af 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -790,7 +790,7 @@ static void ffa_notification_info_get(void) part_id = packed_id_list[ids_processed++]; - if (!ids_count[list]) { /* Global Notification */ + if (ids_count[list] == 1) { /* Global Notification */ __do_sched_recv_cb(part_id, 0, false); continue; } diff --git a/drivers/firmware/arm_scmi/powercap.c b/drivers/firmware/arm_scmi/powercap.c index ea9201e7044c..1fa79bba492e 100644 --- a/drivers/firmware/arm_scmi/powercap.c +++ b/drivers/firmware/arm_scmi/powercap.c @@ -736,7 +736,7 @@ static void scmi_powercap_domain_init_fc(const struct scmi_protocol_handle *ph, ph->hops->fastchannel_init(ph, POWERCAP_DESCRIBE_FASTCHANNEL, POWERCAP_PAI_GET, 4, domain, &fc[POWERCAP_FC_PAI].get_addr, NULL, - &fc[POWERCAP_PAI_GET].rate_limit); + &fc[POWERCAP_FC_PAI].rate_limit); *p_fc = fc; } diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index 350573518503..130d13e9cd6b 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -921,7 +921,7 @@ static int scmi_dbg_raw_mode_open(struct inode *inode, struct file *filp) rd->raw = raw; filp->private_data = rd; - return 0; + return nonseekable_open(inode, filp); } static int scmi_dbg_raw_mode_release(struct inode *inode, struct file *filp) @@ -950,6 +950,7 @@ static const struct file_operations scmi_dbg_raw_mode_reset_fops = { .open = scmi_dbg_raw_mode_open, .release = scmi_dbg_raw_mode_release, .write = scmi_dbg_raw_mode_reset_write, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -959,6 +960,7 @@ static const struct file_operations scmi_dbg_raw_mode_message_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_write, .poll = scmi_dbg_raw_mode_message_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -975,6 +977,7 @@ static const struct file_operations scmi_dbg_raw_mode_message_async_fops = { .read = scmi_dbg_raw_mode_message_read, .write = scmi_dbg_raw_mode_message_async_write, .poll = scmi_dbg_raw_mode_message_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -998,6 +1001,7 @@ static const struct file_operations scmi_dbg_raw_mode_notification_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_notif_read, .poll = scmi_test_dbg_raw_mode_notif_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; @@ -1021,6 +1025,7 @@ static const struct file_operations scmi_dbg_raw_mode_errors_fops = { .release = scmi_dbg_raw_mode_release, .read = scmi_test_dbg_raw_mode_errors_read, .poll = scmi_test_dbg_raw_mode_errors_poll, + .llseek = no_llseek, .owner = THIS_MODULE, }; diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c index 1ee62cd58582..25db014494a4 100644 --- a/drivers/gpio/gpio-crystalcove.c +++ b/drivers/gpio/gpio-crystalcove.c @@ -92,7 +92,7 @@ static inline int to_reg(int gpio, enum ctrl_register reg_type) case 0x5e: return GPIOPANELCTL; default: - return -EOPNOTSUPP; + return -ENOTSUPP; } } diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c index 5ef8af824980..c097e310c9e8 100644 --- a/drivers/gpio/gpio-lpc32xx.c +++ b/drivers/gpio/gpio-lpc32xx.c @@ -529,6 +529,7 @@ static const struct of_device_id lpc32xx_gpio_of_match[] = { { .compatible = "nxp,lpc3220-gpio", }, { }, }; +MODULE_DEVICE_TABLE(of, lpc32xx_gpio_of_match); static struct platform_driver lpc32xx_gpio_driver = { .driver = { diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c index c18b6b47384f..94ca9d03c094 100644 --- a/drivers/gpio/gpio-wcove.c +++ b/drivers/gpio/gpio-wcove.c @@ -104,7 +104,7 @@ static inline int to_reg(int gpio, enum ctrl_register type) unsigned int reg = type == CTRL_IN ? GPIO_IN_CTRL_BASE : GPIO_OUT_CTRL_BASE; if (gpio >= WCOVE_GPIO_NUM) - return -EOPNOTSUPP; + return -ENOTSUPP; return reg + gpio; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 9c62552bec34..b3b84647207e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -210,6 +210,7 @@ extern int amdgpu_async_gfx_ring; extern int amdgpu_mcbp; extern int amdgpu_discovery; extern int amdgpu_mes; +extern int amdgpu_mes_log_enable; extern int amdgpu_mes_kiq; extern int amdgpu_noretry; extern int amdgpu_force_asic_type; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 0a4b09709cfb..ec888fc6ead8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -819,7 +819,7 @@ retry: p->bytes_moved += ctx.bytes_moved; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - amdgpu_bo_in_cpu_visible_vram(bo)) + amdgpu_res_cpu_visible(adev, bo->tbo.resource)) p->bytes_moved_vis += ctx.bytes_moved; if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index aa16d51dd842..7753a2e64d41 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4135,18 +4135,22 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->ip_blocks[i].status.hw = true; } } + } else if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 10) && + !amdgpu_device_has_display_hardware(adev)) { + r = psp_gpu_reset(adev); } else { - tmp = amdgpu_reset_method; - /* It should do a default reset when loading or reloading the driver, - * regardless of the module parameter reset_method. - */ - amdgpu_reset_method = AMD_RESET_METHOD_NONE; - r = amdgpu_asic_reset(adev); - amdgpu_reset_method = tmp; - if (r) { - dev_err(adev->dev, "asic reset on init failed\n"); - goto failed; - } + tmp = amdgpu_reset_method; + /* It should do a default reset when loading or reloading the driver, + * regardless of the module parameter reset_method. + */ + amdgpu_reset_method = AMD_RESET_METHOD_NONE; + r = amdgpu_asic_reset(adev); + amdgpu_reset_method = tmp; + } + + if (r) { + dev_err(adev->dev, "asic reset on init failed\n"); + goto failed; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index fdd36fb027ab..ac5bf01fe8d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -1896,6 +1896,7 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block); break; case IP_VERSION(14, 0, 0): + case IP_VERSION(14, 0, 1): amdgpu_device_ip_block_add(adev, &smu_v14_0_ip_block); break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 80b9642f2bc4..e4277298cf1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -195,6 +195,7 @@ int amdgpu_async_gfx_ring = 1; int amdgpu_mcbp = -1; int amdgpu_discovery = -1; int amdgpu_mes; +int amdgpu_mes_log_enable = 0; int amdgpu_mes_kiq; int amdgpu_noretry = -1; int amdgpu_force_asic_type = -1; @@ -668,6 +669,15 @@ MODULE_PARM_DESC(mes, module_param_named(mes, amdgpu_mes, int, 0444); /** + * DOC: mes_log_enable (int) + * Enable Micro Engine Scheduler log. This is used to enable/disable MES internal log. + * (0 = disabled (default), 1 = enabled) + */ +MODULE_PARM_DESC(mes_log_enable, + "Enable Micro Engine Scheduler log (0 = disabled (default), 1 = enabled)"); +module_param_named(mes_log_enable, amdgpu_mes_log_enable, int, 0444); + +/** * DOC: mes_kiq (int) * Enable Micro Engine Scheduler KIQ. This is a new engine pipe for kiq. * (0 = disabled (default), 1 = enabled) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 4b3000c21ef2..e4742b65032d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -304,12 +304,15 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) dma_fence_set_error(finished, -ECANCELED); if (finished->error < 0) { - DRM_INFO("Skip scheduling IBs!\n"); + dev_dbg(adev->dev, "Skip scheduling IBs in ring(%s)", + ring->name); } else { r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job, &fence); if (r) - DRM_ERROR("Error scheduling IBs (%d)\n", r); + dev_err(adev->dev, + "Error scheduling IBs (%d) in ring(%s)", r, + ring->name); } job->job_run_counter++; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index a98e03e0a51f..a00cf4756ad0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -102,7 +102,10 @@ static int amdgpu_mes_event_log_init(struct amdgpu_device *adev) { int r; - r = amdgpu_bo_create_kernel(adev, PAGE_SIZE, PAGE_SIZE, + if (!amdgpu_mes_log_enable) + return 0; + + r = amdgpu_bo_create_kernel(adev, AMDGPU_MES_LOG_BUFFER_SIZE, PAGE_SIZE, AMDGPU_GEM_DOMAIN_GTT, &adev->mes.event_log_gpu_obj, &adev->mes.event_log_gpu_addr, @@ -1549,12 +1552,11 @@ static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused) uint32_t *mem = (uint32_t *)(adev->mes.event_log_cpu_addr); seq_hex_dump(m, "", DUMP_PREFIX_OFFSET, 32, 4, - mem, PAGE_SIZE, false); + mem, AMDGPU_MES_LOG_BUFFER_SIZE, false); return 0; } - DEFINE_SHOW_ATTRIBUTE(amdgpu_debugfs_mes_event_log); #endif @@ -1565,7 +1567,7 @@ void amdgpu_debugfs_mes_event_log_init(struct amdgpu_device *adev) #if defined(CONFIG_DEBUG_FS) struct drm_minor *minor = adev_to_drm(adev)->primary; struct dentry *root = minor->debugfs_root; - if (adev->enable_mes) + if (adev->enable_mes && amdgpu_mes_log_enable) debugfs_create_file("amdgpu_mes_event_log", 0444, root, adev, &amdgpu_debugfs_mes_event_log_fops); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index 7d4f93fea937..4c8fc3117ef8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -52,6 +52,7 @@ enum amdgpu_mes_priority_level { #define AMDGPU_MES_PROC_CTX_SIZE 0x1000 /* one page area */ #define AMDGPU_MES_GANG_CTX_SIZE 0x1000 /* one page area */ +#define AMDGPU_MES_LOG_BUFFER_SIZE 0x4000 /* Maximu log buffer size for MES */ struct amdgpu_mes_funcs; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 010b0cb7693c..2099159a693f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -617,8 +617,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev, return r; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - bo->tbo.resource->mem_type == TTM_PL_VRAM && - amdgpu_bo_in_cpu_visible_vram(bo)) + amdgpu_res_cpu_visible(adev, bo->tbo.resource)) amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, ctx.bytes_moved); else @@ -1272,23 +1271,25 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict) void amdgpu_bo_get_memory(struct amdgpu_bo *bo, struct amdgpu_mem_stats *stats) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct ttm_resource *res = bo->tbo.resource; uint64_t size = amdgpu_bo_size(bo); struct drm_gem_object *obj; unsigned int domain; bool shared; /* Abort if the BO doesn't currently have a backing store */ - if (!bo->tbo.resource) + if (!res) return; obj = &bo->tbo.base; shared = drm_gem_object_is_shared_for_memory_stats(obj); - domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); + domain = amdgpu_mem_type_to_domain(res->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: stats->vram += size; - if (amdgpu_bo_in_cpu_visible_vram(bo)) + if (amdgpu_res_cpu_visible(adev, bo->tbo.resource)) stats->visible_vram += size; if (shared) stats->vram_shared += size; @@ -1389,10 +1390,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* Remember that this BO was accessed by the CPU */ abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - if (bo->resource->mem_type != TTM_PL_VRAM) - return 0; - - if (amdgpu_bo_in_cpu_visible_vram(abo)) + if (amdgpu_res_cpu_visible(adev, bo->resource)) return 0; /* Can't move a pinned BO to visible VRAM */ @@ -1415,7 +1413,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) /* this should never happen */ if (bo->resource->mem_type == TTM_PL_VRAM && - !amdgpu_bo_in_cpu_visible_vram(abo)) + !amdgpu_res_cpu_visible(adev, bo->resource)) return VM_FAULT_SIGBUS; ttm_bo_move_to_lru_tail_unlocked(bo); @@ -1579,6 +1577,7 @@ uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev, */ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct dma_buf_attachment *attachment; struct dma_buf *dma_buf; const char *placement; @@ -1587,10 +1586,11 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) if (dma_resv_trylock(bo->tbo.base.resv)) { unsigned int domain; + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: - if (amdgpu_bo_in_cpu_visible_vram(bo)) + if (amdgpu_res_cpu_visible(adev, bo->tbo.resource)) placement = "VRAM VISIBLE"; else placement = "VRAM"; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index be679c42b0b8..fa03d9e4874c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -251,28 +251,6 @@ static inline u64 amdgpu_bo_mmap_offset(struct amdgpu_bo *bo) } /** - * amdgpu_bo_in_cpu_visible_vram - check if BO is (partly) in visible VRAM - */ -static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo) -{ - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - struct amdgpu_res_cursor cursor; - - if (!bo->tbo.resource || bo->tbo.resource->mem_type != TTM_PL_VRAM) - return false; - - amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor); - while (cursor.remaining) { - if (cursor.start < adev->gmc.visible_vram_size) - return true; - - amdgpu_res_next(&cursor, cursor.size); - } - - return false; -} - -/** * amdgpu_bo_explicit_sync - return whether the bo is explicitly synced */ static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index fc418e670fda..1d71729e3f6b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -133,7 +133,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, } else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) && - amdgpu_bo_in_cpu_visible_vram(abo)) { + amdgpu_res_cpu_visible(adev, bo->resource)) { /* Try evicting to the CPU inaccessible part of VRAM * first, but only set GTT as busy placement, so this @@ -403,40 +403,55 @@ error: return r; } -/* - * amdgpu_mem_visible - Check that memory can be accessed by ttm_bo_move_memcpy +/** + * amdgpu_res_cpu_visible - Check that resource can be accessed by CPU + * @adev: amdgpu device + * @res: the resource to check * - * Called by amdgpu_bo_move() + * Returns: true if the full resource is CPU visible, false otherwise. */ -static bool amdgpu_mem_visible(struct amdgpu_device *adev, - struct ttm_resource *mem) +bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, + struct ttm_resource *res) { - u64 mem_size = (u64)mem->size; struct amdgpu_res_cursor cursor; - u64 end; - if (mem->mem_type == TTM_PL_SYSTEM || - mem->mem_type == TTM_PL_TT) + if (!res) + return false; + + if (res->mem_type == TTM_PL_SYSTEM || res->mem_type == TTM_PL_TT || + res->mem_type == AMDGPU_PL_PREEMPT) return true; - if (mem->mem_type != TTM_PL_VRAM) + + if (res->mem_type != TTM_PL_VRAM) return false; - amdgpu_res_first(mem, 0, mem_size, &cursor); - end = cursor.start + cursor.size; + amdgpu_res_first(res, 0, res->size, &cursor); while (cursor.remaining) { + if ((cursor.start + cursor.size) >= adev->gmc.visible_vram_size) + return false; amdgpu_res_next(&cursor, cursor.size); + } - if (!cursor.remaining) - break; + return true; +} - /* ttm_resource_ioremap only supports contiguous memory */ - if (end != cursor.start) - return false; +/* + * amdgpu_res_copyable - Check that memory can be accessed by ttm_bo_move_memcpy + * + * Called by amdgpu_bo_move() + */ +static bool amdgpu_res_copyable(struct amdgpu_device *adev, + struct ttm_resource *mem) +{ + if (!amdgpu_res_cpu_visible(adev, mem)) + return false; - end = cursor.start + cursor.size; - } + /* ttm_resource_ioremap only supports contiguous memory */ + if (mem->mem_type == TTM_PL_VRAM && + !(mem->placement & TTM_PL_FLAG_CONTIGUOUS)) + return false; - return end <= adev->gmc.visible_vram_size; + return true; } /* @@ -529,8 +544,8 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, if (r) { /* Check that all memory is CPU accessible */ - if (!amdgpu_mem_visible(adev, old_mem) || - !amdgpu_mem_visible(adev, new_mem)) { + if (!amdgpu_res_copyable(adev, old_mem) || + !amdgpu_res_copyable(adev, new_mem)) { pr_err("Move buffer fallback to memcpy unavailable\n"); return r; } @@ -557,7 +572,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(bdev); - size_t bus_size = (size_t)mem->size; switch (mem->mem_type) { case TTM_PL_SYSTEM: @@ -568,9 +582,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, break; case TTM_PL_VRAM: mem->bus.offset = mem->start << PAGE_SHIFT; - /* check if it's visible */ - if ((mem->bus.offset + bus_size) > adev->gmc.visible_vram_size) - return -EINVAL; if (adev->mman.aper_base_kaddr && mem->placement & TTM_PL_FLAG_CONTIGUOUS) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 65ec82141a8e..32cf6b6f6efd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -139,6 +139,9 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start); +bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, + struct ttm_resource *res); + int amdgpu_ttm_init(struct amdgpu_device *adev); void amdgpu_ttm_fini(struct amdgpu_device *adev); void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 4299ce386322..94089069c9ad 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1613,6 +1613,37 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev, trace_amdgpu_vm_bo_map(bo_va, mapping); } +/* Validate operation parameters to prevent potential abuse */ +static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev, + struct amdgpu_bo *bo, + uint64_t saddr, + uint64_t offset, + uint64_t size) +{ + uint64_t tmp, lpfn; + + if (saddr & AMDGPU_GPU_PAGE_MASK + || offset & AMDGPU_GPU_PAGE_MASK + || size & AMDGPU_GPU_PAGE_MASK) + return -EINVAL; + + if (check_add_overflow(saddr, size, &tmp) + || check_add_overflow(offset, size, &tmp) + || size == 0 /* which also leads to end < begin */) + return -EINVAL; + + /* make sure object fit at this offset */ + if (bo && offset + size > amdgpu_bo_size(bo)) + return -EINVAL; + + /* Ensure last pfn not exceed max_pfn */ + lpfn = (saddr + size - 1) >> AMDGPU_GPU_PAGE_SHIFT; + if (lpfn >= adev->vm_manager.max_pfn) + return -EINVAL; + + return 0; +} + /** * amdgpu_vm_bo_map - map bo inside a vm * @@ -1639,21 +1670,14 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; uint64_t eaddr; + int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; tmp = amdgpu_vm_it_iter_first(&vm->va, saddr, eaddr); if (tmp) { @@ -1706,17 +1730,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, uint64_t eaddr; int r; - /* validate the parameters */ - if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || size & ~PAGE_MASK) - return -EINVAL; - if (saddr + size <= saddr || offset + size <= offset) - return -EINVAL; - - /* make sure object fit at this offset */ - eaddr = saddr + size - 1; - if ((bo && offset + size > amdgpu_bo_size(bo)) || - (eaddr >= adev->vm_manager.max_pfn << AMDGPU_GPU_PAGE_SHIFT)) - return -EINVAL; + r = amdgpu_vm_verify_parameters(adev, bo, saddr, offset, size); + if (r) + return r; /* Allocate all the needed memory */ mapping = kmalloc(sizeof(*mapping), GFP_KERNEL); @@ -1730,7 +1746,7 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, } saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; mapping->start = saddr; mapping->last = eaddr; @@ -1817,10 +1833,14 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *before, *after, *tmp, *next; LIST_HEAD(removed); uint64_t eaddr; + int r; + + r = amdgpu_vm_verify_parameters(adev, NULL, saddr, 0, size); + if (r) + return r; - eaddr = saddr + size - 1; saddr /= AMDGPU_GPU_PAGE_SIZE; - eaddr /= AMDGPU_GPU_PAGE_SIZE; + eaddr = saddr + (size - 1) / AMDGPU_GPU_PAGE_SIZE; /* Allocate all the needed memory */ before = kzalloc(sizeof(*before), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c index d6f808acfb17..fbb43ae7624f 100644 --- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c +++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c @@ -62,6 +62,11 @@ void aqua_vanjaram_doorbell_index_init(struct amdgpu_device *adev) adev->doorbell_index.max_assignment = AMDGPU_DOORBELL_LAYOUT1_MAX_ASSIGNMENT << 1; } +static bool aqua_vanjaram_xcp_vcn_shared(struct amdgpu_device *adev) +{ + return (adev->xcp_mgr->num_xcps > adev->vcn.num_vcn_inst); +} + static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, uint32_t inst_idx, struct amdgpu_ring *ring) { @@ -87,7 +92,7 @@ static void aqua_vanjaram_set_xcp_id(struct amdgpu_device *adev, case AMDGPU_RING_TYPE_VCN_ENC: case AMDGPU_RING_TYPE_VCN_JPEG: ip_blk = AMDGPU_XCP_VCN; - if (adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE) + if (aqua_vanjaram_xcp_vcn_shared(adev)) inst_mask = 1 << (inst_idx * 2); break; default: @@ -140,10 +145,12 @@ static int aqua_vanjaram_xcp_sched_list_update( aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id); - /* VCN is shared by two partitions under CPX MODE */ + /* VCN may be shared by two partitions under CPX MODE in certain + * configs. + */ if ((ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC || - ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) && - adev->xcp_mgr->mode == AMDGPU_CPX_PARTITION_MODE) + ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG) && + aqua_vanjaram_xcp_vcn_shared(adev)) aqua_vanjaram_xcp_gpu_sched_update(adev, ring, ring->xcp_id + 1); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 1770e496c1b7..f7325b02a191 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1635,7 +1635,7 @@ static void gfx_v11_0_setup_rb(struct amdgpu_device *adev) active_rb_bitmap |= (0x3 << (i * rb_bitmap_width_per_sa)); } - active_rb_bitmap |= global_active_rb_bitmap; + active_rb_bitmap &= global_active_rb_bitmap; adev->gfx.config.backend_enable_mask = active_rb_bitmap; adev->gfx.config.num_rbs = hweight32(active_rb_bitmap); } @@ -5465,6 +5465,7 @@ static void gfx_v11_0_ring_emit_vm_flush(struct amdgpu_ring *ring, /* Make sure that we can't skip the SET_Q_MODE packets when the VM * changed in any way. */ + ring->set_q_mode_offs = 0; ring->set_q_mode_ptr = NULL; } diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 072c478665ad..63f281a9984d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -411,8 +411,11 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes) mes_set_hw_res_pkt.enable_reg_active_poll = 1; mes_set_hw_res_pkt.enable_level_process_quantum_check = 1; mes_set_hw_res_pkt.oversubscription_timer = 50; - mes_set_hw_res_pkt.enable_mes_event_int_logging = 1; - mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr; + if (amdgpu_mes_log_enable) { + mes_set_hw_res_pkt.enable_mes_event_int_logging = 1; + mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = + mes->event_log_gpu_addr; + } return mes_v11_0_submit_pkt_and_poll_completion(mes, &mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt), diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 34237a1b1f2e..82eab49be82b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -1602,19 +1602,9 @@ static int sdma_v4_4_2_set_ecc_irq_state(struct amdgpu_device *adev, u32 sdma_cntl; sdma_cntl = RREG32_SDMA(type, regSDMA_CNTL); - switch (state) { - case AMDGPU_IRQ_STATE_DISABLE: - sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, - DRAM_ECC_INT_ENABLE, 0); - WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl); - break; - /* sdma ecc interrupt is enabled by default - * driver doesn't need to do anything to - * enable the interrupt */ - case AMDGPU_IRQ_STATE_ENABLE: - default: - break; - } + sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, DRAM_ECC_INT_ENABLE, + state == AMDGPU_IRQ_STATE_ENABLE ? 1 : 0); + WREG32_SDMA(type, regSDMA_CNTL, sdma_cntl); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 581a3bd11481..43ca63fe85ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -457,10 +457,8 @@ static bool soc21_need_full_reset(struct amdgpu_device *adev) { switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(11, 0, 0): - return amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC); case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): - return false; default: return true; } @@ -722,7 +720,10 @@ static int soc21_common_early_init(void *handle) AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_JPEG | AMD_PG_SUPPORT_GFX_PG; - adev->external_rev_id = adev->rev_id + 0x1; + if (adev->rev_id == 0) + adev->external_rev_id = 0x1; + else + adev->external_rev_id = adev->rev_id + 0x10; break; case IP_VERSION(11, 5, 1): adev->cg_flags = @@ -869,10 +870,35 @@ static int soc21_common_suspend(void *handle) return soc21_common_hw_fini(adev); } +static bool soc21_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg1, sol_reg2; + + /* Will reset for the following suspend abort cases. + * 1) Only reset dGPU side. + * 2) S3 suspend got aborted and TOS is active. + */ + if (!(adev->flags & AMD_IS_APU) && adev->in_s3 && + !adev->suspend_complete) { + sol_reg1 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81); + msleep(100); + sol_reg2 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81); + + return (sol_reg1 != sol_reg2); + } + + return false; +} + static int soc21_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (soc21_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend aborted, resetting..."); + soc21_asic_reset(adev); + } + return soc21_common_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c index 84368cf1e175..bd57896ab85d 100644 --- a/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/umsch_mm_v4_0.c @@ -225,6 +225,8 @@ static int umsch_mm_v4_0_ring_start(struct amdgpu_umsch_mm *umsch) WREG32_SOC15(VCN, 0, regVCN_UMSCH_RB_SIZE, ring->ring_size); + ring->wptr = 0; + data = RREG32_SOC15(VCN, 0, regVCN_RB_ENABLE); data &= ~(VCN_RB_ENABLE__AUDIO_RB_EN_MASK); WREG32_SOC15(VCN, 0, regVCN_RB_ENABLE, data); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index f9631f4b1a02..55aa74cbc532 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -779,8 +779,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * nodes, but not more than args->num_of_nodes as that is * the amount of memory allocated by user */ - pa = kzalloc((sizeof(struct kfd_process_device_apertures) * - args->num_of_nodes), GFP_KERNEL); + pa = kcalloc(args->num_of_nodes, sizeof(struct kfd_process_device_apertures), + GFP_KERNEL); if (!pa) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 041ec3de55e7..719d6d365e15 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -960,7 +960,6 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) { struct kfd_node *node; int i; - int count; if (!kfd->init_complete) return; @@ -968,12 +967,10 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) /* for runtime suspend, skip locking kfd */ if (!run_pm) { mutex_lock(&kfd_processes_mutex); - count = ++kfd_locked; - mutex_unlock(&kfd_processes_mutex); - /* For first KFD device suspend all the KFD processes */ - if (count == 1) + if (++kfd_locked == 1) kfd_suspend_all_processes(); + mutex_unlock(&kfd_processes_mutex); } for (i = 0; i < kfd->num_nodes; i++) { @@ -984,7 +981,7 @@ void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm) int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) { - int ret, count, i; + int ret, i; if (!kfd->init_complete) return 0; @@ -998,12 +995,10 @@ int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm) /* for runtime resume, skip unlocking kfd */ if (!run_pm) { mutex_lock(&kfd_processes_mutex); - count = --kfd_locked; - mutex_unlock(&kfd_processes_mutex); - - WARN_ONCE(count < 0, "KFD suspend / resume ref. error"); - if (count == 0) + if (--kfd_locked == 0) ret = kfd_resume_all_processes(); + WARN_ONCE(kfd_locked < 0, "KFD suspend / resume ref. error"); + mutex_unlock(&kfd_processes_mutex); } return ret; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index f4d395e38683..0b655555e167 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -2001,6 +2001,7 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, dev_err(dev, "HIQ MQD's queue_doorbell_id0 is not 0, Queue preemption time out\n"); while (halt_if_hws_hang) schedule(); + kfd_hws_hang(dqm); return -ETIME; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 717a60d7a4ea..b79986412cd8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -819,9 +819,9 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) mutex_lock(&kfd_processes_mutex); if (kfd_is_locked()) { - mutex_unlock(&kfd_processes_mutex); pr_debug("KFD is locked! Cannot create process"); - return ERR_PTR(-EINVAL); + process = ERR_PTR(-EINVAL); + goto out; } /* A prior open of /dev/kfd could have already created the process. */ 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 71d2d44681b2..6d2f60c61dec 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -148,6 +148,9 @@ MODULE_FIRMWARE(FIRMWARE_NAVI12_DMCU); #define FIRMWARE_DCN_35_DMUB "amdgpu/dcn_3_5_dmcub.bin" MODULE_FIRMWARE(FIRMWARE_DCN_35_DMUB); +#define FIRMWARE_DCN_351_DMUB "amdgpu/dcn_3_5_1_dmcub.bin" +MODULE_FIRMWARE(FIRMWARE_DCN_351_DMUB); + /* Number of bytes in PSP header for firmware. */ #define PSP_HEADER_BYTES 0x100 @@ -3044,6 +3047,10 @@ static int dm_resume(void *handle) /* Do mst topology probing after resuming cached state*/ drm_connector_list_iter_begin(ddev, &iter); drm_for_each_connector_iter(connector, &iter) { + + if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) + continue; + aconnector = to_amdgpu_dm_connector(connector); if (aconnector->dc_link->type != dc_connection_mst_branch || aconnector->mst_root) @@ -4820,9 +4827,11 @@ static int dm_init_microcode(struct amdgpu_device *adev) fw_name_dmub = FIRMWARE_DCN_V3_2_1_DMCUB; break; case IP_VERSION(3, 5, 0): - case IP_VERSION(3, 5, 1): fw_name_dmub = FIRMWARE_DCN_35_DMUB; break; + case IP_VERSION(3, 5, 1): + fw_name_dmub = FIRMWARE_DCN_351_DMUB; + break; default: /* ASIC doesn't support DMUB. */ return 0; @@ -5921,6 +5930,9 @@ get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector, &aconnector->base.probed_modes : &aconnector->base.modes; + if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_WRITEBACK) + return NULL; + if (aconnector->freesync_vid_base.clock != 0) return &aconnector->freesync_vid_base; @@ -6306,19 +6318,16 @@ create_stream_for_sink(struct drm_connector *connector, if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket); - if (stream->link->psr_settings.psr_feature_enabled || stream->link->replay_settings.replay_feature_enabled) { + if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT || + stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST || + stream->signal == SIGNAL_TYPE_EDP) { // // should decide stream support vsc sdp colorimetry capability // before building vsc info packet // - stream->use_vsc_sdp_for_colorimetry = false; - if (aconnector->dc_sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT_MST) { - stream->use_vsc_sdp_for_colorimetry = - aconnector->dc_sink->is_vsc_sdp_colorimetry_supported; - } else { - if (stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED) - stream->use_vsc_sdp_for_colorimetry = true; - } + stream->use_vsc_sdp_for_colorimetry = stream->link->dpcd_caps.dpcd_rev.raw >= 0x14 && + stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED; + if (stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) tf = TRANSFER_FUNC_GAMMA_22; mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf); @@ -8762,10 +8771,10 @@ static void amdgpu_dm_commit_audio(struct drm_device *dev, if (!drm_atomic_crtc_needs_modeset(new_crtc_state)) continue; +notify: if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) continue; -notify: aconnector = to_amdgpu_dm_connector(connector); mutex_lock(&adev->dm.audio_lock); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c index 16e72d623630..08c494a7a21b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_wb.c @@ -76,10 +76,8 @@ static int amdgpu_dm_wb_encoder_atomic_check(struct drm_encoder *encoder, static int amdgpu_dm_wb_connector_get_modes(struct drm_connector *connector) { - struct drm_device *dev = connector->dev; - - return drm_add_modes_noedid(connector, dev->mode_config.max_width, - dev->mode_config.max_height); + /* Maximum resolution supported by DWB */ + return drm_add_modes_noedid(connector, 3840, 2160); } static int amdgpu_dm_wb_prepare_job(struct drm_writeback_connector *wb_connector, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 12f3e8aa46d8..6ad4f4efec5d 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -99,20 +99,25 @@ static int dcn316_get_active_display_cnt_wa( return display_count; } -static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) +static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, + bool safe_to_lower, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; for (i = 0; i < dc->res_pool->pipe_count; ++i) { - struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + struct pipe_ctx *pipe = safe_to_lower + ? &context->res_ctx.pipe_ctx[i] + : &dc->current_state->res_ctx.pipe_ctx[i]; if (pipe->top_pipe || pipe->prev_odm_pipe) continue; - if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || - dc_is_virtual_signal(pipe->stream->signal))) { + if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal) || + !pipe->stream->link_enc)) { if (disable) { - pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); + if (pipe->stream_res.tg && pipe->stream_res.tg->funcs->immediate_disable_crtc) + pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); + reset_sync_context_for_pipe(dc, context, i); } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); @@ -207,11 +212,11 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn316_disable_otg_wa(clk_mgr_base, context, true); + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn316_disable_otg_wa(clk_mgr_base, context, false); + dcn316_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index 101fe96287cb..d9c5692c86c2 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -73,6 +73,12 @@ #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK 0x00000007L #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV_MASK 0x000F0000L +#define regCLK5_0_CLK5_spll_field_8 0x464b +#define regCLK5_0_CLK5_spll_field_8_BASE_IDX 0 + +#define CLK5_0_CLK5_spll_field_8__spll_ssc_en__SHIFT 0xd +#define CLK5_0_CLK5_spll_field_8__spll_ssc_en_MASK 0x00002000L + #define SMU_VER_THRESHOLD 0x5D4A00 //93.74.0 #define REG(reg_name) \ @@ -411,6 +417,17 @@ static void dcn35_dump_clk_registers(struct clk_state_registers_and_bypass *regs { } +static bool dcn35_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base) +{ + struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + struct dc_context *ctx = clk_mgr->base.ctx; + uint32_t ssc_enable; + + REG_GET(CLK5_0_CLK5_spll_field_8, spll_ssc_en, &ssc_enable); + + return ssc_enable == 1; +} + static void init_clk_states(struct clk_mgr *clk_mgr) { struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr); @@ -428,7 +445,16 @@ static void init_clk_states(struct clk_mgr *clk_mgr) void dcn35_init_clocks(struct clk_mgr *clk_mgr) { + struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr); init_clk_states(clk_mgr); + + // to adjust dp_dto reference clock if ssc is enable otherwise to apply dprefclk + if (dcn35_is_spll_ssc_enabled(clk_mgr)) + clk_mgr->dp_dto_source_clock_in_khz = + dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz); + else + clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz; + } static struct clk_bw_params dcn35_bw_params = { .vram_type = Ddr4MemType, @@ -517,6 +543,28 @@ static DpmClocks_t_dcn35 dummy_clocks; static struct dcn35_watermarks dummy_wms = { 0 }; +static struct dcn35_ss_info_table ss_info_table = { + .ss_divider = 1000, + .ss_percentage = {0, 0, 375, 375, 375} +}; + +static void dcn35_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr) +{ + struct dc_context *ctx = clk_mgr->base.ctx; + uint32_t clock_source; + + REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source); + // If it's DFS mode, clock_source is 0. + if (dcn35_is_spll_ssc_enabled(&clk_mgr->base) && (clock_source < ARRAY_SIZE(ss_info_table.ss_percentage))) { + clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source]; + + if (clk_mgr->dprefclk_ss_percentage != 0) { + clk_mgr->ss_on_dprefclk = true; + clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider; + } + } +} + static void dcn35_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn35_watermarks *table) { int i, num_valid_sets; @@ -1061,6 +1109,8 @@ void dcn35_clk_mgr_construct( dce_clock_read_ss_info(&clk_mgr->base); /*when clk src is from FCH, it could have ss, same clock src as DPREF clk*/ + dcn35_read_ss_info_from_lut(&clk_mgr->base); + clk_mgr->base.base.bw_params = &dcn35_bw_params; if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index 5cc7f8da209c..61986e5cb491 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -436,6 +436,15 @@ bool dc_state_add_plane( goto out; } + if (stream_status->plane_count == 0 && dc->config.enable_windowed_mpo_odm) + /* ODM combine could prevent us from supporting more planes + * we will reset ODM slice count back to 1 when all planes have + * been removed to maximize the amount of planes supported when + * new planes are added. + */ + resource_update_pipes_for_stream_with_slice_count( + state, dc->current_state, dc->res_pool, stream, 1); + otg_master_pipe = resource_get_otg_master_for_stream( &state->res_ctx, stream); if (otg_master_pipe) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index 970644b695cd..b5e0289d2fe8 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -976,7 +976,10 @@ static bool dcn31_program_pix_clk( struct bp_pixel_clock_parameters bp_pc_params = {0}; enum transmitter_color_depth bp_pc_colour_depth = TRANSMITTER_COLOR_DEPTH_24; - if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0) + // Apply ssed(spread spectrum) dpref clock for edp only. + if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0 + && pix_clk_params->signal_type == SIGNAL_TYPE_EDP + && encoding == DP_8b_10b_ENCODING) dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz; // For these signal types Driver to program DP_DTO without calling VBIOS Command table if (dc_is_dp_signal(pix_clk_params->signal_type) || dc_is_virtual_signal(pix_clk_params->signal_type)) { @@ -1093,9 +1096,6 @@ static bool get_pixel_clk_frequency_100hz( unsigned int modulo_hz = 0; unsigned int dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dprefclk_khz; - if (clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz != 0) - dp_dto_ref_khz = clock_source->ctx->dc->clk_mgr->dp_dto_source_clock_in_khz; - if (clock_source->id == CLOCK_SOURCE_ID_DP_DTO) { clock_hz = REG_READ(PHASE[inst]); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c index e224a028d68a..8a0460e86309 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c @@ -248,14 +248,12 @@ void dcn32_link_encoder_construct( enc10->base.hpd_source = init_data->hpd_source; enc10->base.connector = init_data->connector; - enc10->base.preferred_engine = ENGINE_ID_UNKNOWN; - - enc10->base.features = *enc_features; if (enc10->base.connector.id == CONNECTOR_ID_USBC) enc10->base.features.flags.bits.DP_IS_USB_C = 1; - if (enc10->base.connector.id == CONNECTOR_ID_USBC) - enc10->base.features.flags.bits.DP_IS_USB_C = 1; + enc10->base.preferred_engine = ENGINE_ID_UNKNOWN; + + enc10->base.features = *enc_features; enc10->base.transmitter = init_data->transmitter; diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c index 81e349d5835b..da94e5309fba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_link_encoder.c @@ -184,6 +184,8 @@ void dcn35_link_encoder_construct( enc10->base.hpd_source = init_data->hpd_source; enc10->base.connector = init_data->connector; + if (enc10->base.connector.id == CONNECTOR_ID_USBC) + enc10->base.features.flags.bits.DP_IS_USB_C = 1; enc10->base.preferred_engine = ENGINE_ID_UNKNOWN; @@ -238,8 +240,6 @@ void dcn35_link_encoder_construct( } enc10->base.features.flags.bits.HDMI_6GB_EN = 1; - if (enc10->base.connector.id == CONNECTOR_ID_USBC) - enc10->base.features.flags.bits.DP_IS_USB_C = 1; if (bp_funcs->get_connector_speed_cap_info) result = bp_funcs->get_connector_speed_cap_info(enc10->base.ctx->dc_bios, diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c index f07a4c7e48bc..52eab8fccb7f 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c @@ -267,9 +267,6 @@ static void optc32_setup_manual_trigger(struct timing_generator *optc) OTG_V_TOTAL_MAX_SEL, 1, OTG_FORCE_LOCK_ON_EVENT, 0, OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */ - - // Setup manual flow control for EOF via TRIG_A - optc->funcs->setup_manual_trigger(optc); } } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 246b211b1e85..65333141b1c1 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -735,7 +735,7 @@ static int smu_early_init(void *handle) smu->adev = adev; smu->pm_enabled = !!amdgpu_dpm; smu->is_apu = false; - smu->smu_baco.state = SMU_BACO_STATE_EXIT; + smu->smu_baco.state = SMU_BACO_STATE_NONE; smu->smu_baco.platform_support = false; smu->user_dpm_profile.fan_mode = -1; @@ -1966,10 +1966,25 @@ static int smu_smc_hw_cleanup(struct smu_context *smu) return 0; } +static int smu_reset_mp1_state(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int ret = 0; + + if ((!adev->in_runpm) && (!adev->in_suspend) && + (!amdgpu_in_reset(adev)) && amdgpu_ip_version(adev, MP1_HWIP, 0) == + IP_VERSION(13, 0, 10) && + !amdgpu_device_has_display_hardware(adev)) + ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD); + + return ret; +} + static int smu_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct smu_context *smu = adev->powerplay.pp_handle; + int ret; if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) return 0; @@ -1987,7 +2002,15 @@ static int smu_hw_fini(void *handle) adev->pm.dpm_enabled = false; - return smu_smc_hw_cleanup(smu); + ret = smu_smc_hw_cleanup(smu); + if (ret) + return ret; + + ret = smu_reset_mp1_state(smu); + if (ret) + return ret; + + return 0; } static void smu_late_fini(void *handle) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index a870bdd49a4e..1fa81575788c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -424,6 +424,7 @@ enum smu_reset_mode { enum smu_baco_state { SMU_BACO_STATE_ENTER = 0, SMU_BACO_STATE_EXIT, + SMU_BACO_STATE_NONE, }; struct smu_baco_context { diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h index 5bb7a63c0602..97522c085258 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h @@ -144,6 +144,37 @@ typedef struct { uint32_t MaxGfxClk; } DpmClocks_t; +//Freq in MHz +//Voltage in milli volts with 2 fractional bits +typedef struct { + uint32_t DcfClocks[NUM_DCFCLK_DPM_LEVELS]; + uint32_t DispClocks[NUM_DISPCLK_DPM_LEVELS]; + uint32_t DppClocks[NUM_DPPCLK_DPM_LEVELS]; + uint32_t SocClocks[NUM_SOCCLK_DPM_LEVELS]; + uint32_t VClocks0[NUM_VCN_DPM_LEVELS]; + uint32_t VClocks1[NUM_VCN_DPM_LEVELS]; + uint32_t DClocks0[NUM_VCN_DPM_LEVELS]; + uint32_t DClocks1[NUM_VCN_DPM_LEVELS]; + uint32_t VPEClocks[NUM_VPE_DPM_LEVELS]; + uint32_t FclkClocks_Freq[NUM_FCLK_DPM_LEVELS]; + uint32_t FclkClocks_Voltage[NUM_FCLK_DPM_LEVELS]; + uint32_t SocVoltage[NUM_SOC_VOLTAGE_LEVELS]; + MemPstateTable_t MemPstateTable[NUM_MEM_PSTATE_LEVELS]; + + uint8_t NumDcfClkLevelsEnabled; + uint8_t NumDispClkLevelsEnabled; //Applies to both Dispclk and Dppclk + uint8_t NumSocClkLevelsEnabled; + uint8_t Vcn0ClkLevelsEnabled; //Applies to both Vclk0 and Dclk0 + uint8_t Vcn1ClkLevelsEnabled; //Applies to both Vclk1 and Dclk1 + uint8_t VpeClkLevelsEnabled; + uint8_t NumMemPstatesEnabled; + uint8_t NumFclkLevelsEnabled; + uint8_t spare; + + uint32_t MinGfxClk; + uint32_t MaxGfxClk; +} DpmClocks_t_v14_0_1; + typedef struct { uint16_t CoreFrequency[16]; //Target core frequency [MHz] uint16_t CorePower[16]; //CAC calculated core power [mW] @@ -224,7 +255,7 @@ typedef enum { #define TABLE_CUSTOM_DPM 2 // Called by Driver #define TABLE_BIOS_GPIO_CONFIG 3 // Called by BIOS #define TABLE_DPMCLOCKS 4 // Called by Driver and VBIOS -#define TABLE_SPARE0 5 // Unused +#define TABLE_MOMENTARY_PM 5 // Called by Tools #define TABLE_MODERN_STDBY 6 // Called by Tools for Modern Standby Log #define TABLE_SMU_METRICS 7 // Called by Driver and SMF/PMF #define TABLE_COUNT 8 diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h index 356e0f57a426..ddb625860083 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_pmfw.h @@ -42,7 +42,7 @@ #define FEATURE_EDC_BIT 7 #define FEATURE_PLL_POWER_DOWN_BIT 8 #define FEATURE_VDDOFF_BIT 9 -#define FEATURE_VCN_DPM_BIT 10 +#define FEATURE_VCN_DPM_BIT 10 /* this is for both VCN0 and VCN1 */ #define FEATURE_DS_MPM_BIT 11 #define FEATURE_FCLK_DPM_BIT 12 #define FEATURE_SOCCLK_DPM_BIT 13 @@ -56,9 +56,9 @@ #define FEATURE_DS_GFXCLK_BIT 21 #define FEATURE_DS_SOCCLK_BIT 22 #define FEATURE_DS_LCLK_BIT 23 -#define FEATURE_LOW_POWER_DCNCLKS_BIT 24 // for all DISP clks +#define FEATURE_LOW_POWER_DCNCLKS_BIT 24 #define FEATURE_DS_SHUBCLK_BIT 25 -#define FEATURE_SPARE0_BIT 26 //SPARE +#define FEATURE_RESERVED0_BIT 26 #define FEATURE_ZSTATES_BIT 27 #define FEATURE_IOMMUL2_PG_BIT 28 #define FEATURE_DS_FCLK_BIT 29 @@ -66,8 +66,8 @@ #define FEATURE_DS_MP1CLK_BIT 31 #define FEATURE_WHISPER_MODE_BIT 32 #define FEATURE_SMU_LOW_POWER_BIT 33 -#define FEATURE_SMART_L3_RINSER_BIT 34 -#define FEATURE_SPARE1_BIT 35 //SPARE +#define FEATURE_RESERVED1_BIT 34 /* v14_0_0 SMART_L3_RINSER; v14_0_1 RESERVED1 */ +#define FEATURE_GFX_DEM_BIT 35 /* v14_0_0 SPARE; v14_0_1 GFX_DEM */ #define FEATURE_PSI_BIT 36 #define FEATURE_PROCHOT_BIT 37 #define FEATURE_CPUOFF_BIT 38 @@ -77,11 +77,11 @@ #define FEATURE_PERF_LIMIT_BIT 42 #define FEATURE_CORE_DLDO_BIT 43 #define FEATURE_DVO_BIT 44 -#define FEATURE_DS_VCN_BIT 45 +#define FEATURE_DS_VCN_BIT 45 /* v14_0_1 this is for both VCN0 and VCN1 */ #define FEATURE_CPPC_BIT 46 #define FEATURE_CPPC_PREFERRED_CORES 47 #define FEATURE_DF_CSTATES_BIT 48 -#define FEATURE_SPARE2_BIT 49 //SPARE +#define FEATURE_FAST_PSTATE_CLDO_BIT 49 /* v14_0_0 SPARE */ #define FEATURE_ATHUB_PG_BIT 50 #define FEATURE_VDDOFF_ECO_BIT 51 #define FEATURE_ZSTATES_ECO_BIT 52 @@ -93,8 +93,8 @@ #define FEATURE_DS_IPUCLK_BIT 58 #define FEATURE_DS_VPECLK_BIT 59 #define FEATURE_VPE_DPM_BIT 60 -#define FEATURE_SPARE_61 61 -#define FEATURE_FP_DIDT 62 +#define FEATURE_SMART_L3_RINSER_BIT 61 /* v14_0_0 SPARE*/ +#define FEATURE_PCC_BIT 62 /* v14_0_0 FP_DIDT v14_0_1 PCC_BIT */ #define NUM_FEATURES 63 // Firmware Header/Footer @@ -151,6 +151,43 @@ typedef struct { // MP1_EXT_SCRATCH7 = RTOS Current Job } FwStatus_t; +typedef struct { + // MP1_EXT_SCRATCH0 + uint32_t DpmHandlerID : 8; + uint32_t ActivityMonitorID : 8; + uint32_t DpmTimerID : 8; + uint32_t DpmHubID : 4; + uint32_t DpmHubTask : 4; + // MP1_EXT_SCRATCH1 + uint32_t CclkSyncStatus : 8; + uint32_t ZstateStatus : 4; + uint32_t Cpu1VddOff : 4; + uint32_t DstateFun : 4; + uint32_t DstateDev : 4; + uint32_t GfxOffStatus : 2; + uint32_t Cpu0Off : 2; + uint32_t Cpu1Off : 2; + uint32_t Cpu0VddOff : 2; + // MP1_EXT_SCRATCH2 + uint32_t P2JobHandler :32; + // MP1_EXT_SCRATCH3 + uint32_t PostCode :32; + // MP1_EXT_SCRATCH4 + uint32_t MsgPortBusy :15; + uint32_t RsmuPmiP1Pending : 1; + uint32_t RsmuPmiP2PendingCnt : 8; + uint32_t DfCstateExitPending : 1; + uint32_t Pc6EntryPending : 1; + uint32_t Pc6ExitPending : 1; + uint32_t WarmResetPending : 1; + uint32_t Mp0ClkPending : 1; + uint32_t InWhisperMode : 1; + uint32_t spare2 : 2; + // MP1_EXT_SCRATCH5 + uint32_t IdleMask :32; + // MP1_EXT_SCRATCH6 = RTOS threads' status + // MP1_EXT_SCRATCH7 = RTOS Current Job +} FwStatus_t_v14_0_1; #pragma pack(pop) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h index ca7ce4251482..c4dc5881d8df 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h @@ -72,23 +72,19 @@ #define PPSMC_MSG_SetHardMinSocclkByFreq 0x13 ///< Set hard min for SOC CLK #define PPSMC_MSG_SetSoftMinFclk 0x14 ///< Set hard min for FCLK #define PPSMC_MSG_SetSoftMinVcn0 0x15 ///< Set soft min for VCN0 clocks (VCLK0 and DCLK0) - #define PPSMC_MSG_EnableGfxImu 0x16 ///< Enable GFX IMU - -#define PPSMC_MSG_spare_0x17 0x17 -#define PPSMC_MSG_spare_0x18 0x18 +#define PPSMC_MSG_spare_0x17 0x17 ///< Get GFX clock frequency +#define PPSMC_MSG_spare_0x18 0x18 ///< Get FCLK frequency #define PPSMC_MSG_AllowGfxOff 0x19 ///< Inform PMFW of allowing GFXOFF entry #define PPSMC_MSG_DisallowGfxOff 0x1A ///< Inform PMFW of disallowing GFXOFF entry #define PPSMC_MSG_SetSoftMaxGfxClk 0x1B ///< Set soft max for GFX CLK #define PPSMC_MSG_SetHardMinGfxClk 0x1C ///< Set hard min for GFX CLK - #define PPSMC_MSG_SetSoftMaxSocclkByFreq 0x1D ///< Set soft max for SOC CLK #define PPSMC_MSG_SetSoftMaxFclkByFreq 0x1E ///< Set soft max for FCLK #define PPSMC_MSG_SetSoftMaxVcn0 0x1F ///< Set soft max for VCN0 clocks (VCLK0 and DCLK0) -#define PPSMC_MSG_spare_0x20 0x20 +#define PPSMC_MSG_spare_0x20 0x20 ///< Set power limit percentage #define PPSMC_MSG_PowerDownJpeg0 0x21 ///< Power down Jpeg of VCN0 #define PPSMC_MSG_PowerUpJpeg0 0x22 ///< Power up Jpeg of VCN0; VCN0 is power gated by default - #define PPSMC_MSG_SetHardMinFclkByFreq 0x23 ///< Set hard min for FCLK #define PPSMC_MSG_SetSoftMinSocclkByFreq 0x24 ///< Set soft min for SOC CLK #define PPSMC_MSG_AllowZstates 0x25 ///< Inform PMFM of allowing Zstate entry, i.e. no Miracast activity @@ -99,8 +95,8 @@ #define PPSMC_MSG_PowerUpIspByTile 0x2A ///< This message is used to power up ISP tiles and enable the ISP DPM #define PPSMC_MSG_SetHardMinIspiclkByFreq 0x2B ///< Set HardMin by frequency for ISPICLK #define PPSMC_MSG_SetHardMinIspxclkByFreq 0x2C ///< Set HardMin by frequency for ISPXCLK -#define PPSMC_MSG_PowerDownUmsch 0x2D ///< Power down VCN.UMSCH (aka VSCH) scheduler -#define PPSMC_MSG_PowerUpUmsch 0x2E ///< Power up VCN.UMSCH (aka VSCH) scheduler +#define PPSMC_MSG_PowerDownUmsch 0x2D ///< Power down VCN0.UMSCH (aka VSCH) scheduler +#define PPSMC_MSG_PowerUpUmsch 0x2E ///< Power up VCN0.UMSCH (aka VSCH) scheduler #define PPSMC_Message_IspStutterOn_MmhubPgDis 0x2F ///< ISP StutterOn mmHub PgDis #define PPSMC_Message_IspStutterOff_MmhubPgEn 0x30 ///< ISP StufferOff mmHub PgEn #define PPSMC_MSG_PowerUpVpe 0x31 ///< Power up VPE @@ -110,7 +106,9 @@ #define PPSMC_MSG_DisableLSdma 0x35 ///< Disable LSDMA #define PPSMC_MSG_SetSoftMaxVpe 0x36 ///< #define PPSMC_MSG_SetSoftMinVpe 0x37 ///< -#define PPSMC_Message_Count 0x38 ///< Total number of PPSMC messages +#define PPSMC_MSG_AllocMALLCache 0x38 ///< Allocating MALL Cache +#define PPSMC_MSG_ReleaseMALLCache 0x39 ///< Releasing MALL Cache +#define PPSMC_Message_Count 0x3A ///< Total number of PPSMC messages /** @}*/ /** diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h index 3f7463c1c1a9..4af1985ae446 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h @@ -27,6 +27,7 @@ #define SMU14_DRIVER_IF_VERSION_INV 0xFFFFFFFF #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_0 0x7 +#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_1 0x6 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x1 #define FEATURE_MASK(feature) (1ULL << feature) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 9c03296f92cd..67117ced7c6a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2751,7 +2751,13 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu, switch (mp1_state) { case PP_MP1_STATE_UNLOAD: - ret = smu_cmn_set_mp1_state(smu, mp1_state); + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_PrepareMp1ForUnload, + 0x55, NULL); + + if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT) + ret = smu_v13_0_disable_pmfw_state(smu); + break; default: /* Ignore others */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index bb98156b2fa1..949131bd1ecb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -226,8 +226,18 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en) struct amdgpu_device *adev = smu->adev; int ret = 0; - if (!en && !adev->in_s0ix) + if (!en && !adev->in_s0ix) { + /* Adds a GFX reset as workaround just before sending the + * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering + * an invalid state. + */ + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, + SMU_RESET_MODE_2, NULL); + if (ret) + return ret; + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); + } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index 9e39f99154f9..07a65e005785 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -234,7 +234,7 @@ int smu_v14_0_check_fw_version(struct smu_context *smu) smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0; break; case IP_VERSION(14, 0, 1): - smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0; + smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_1; break; default: diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index d6de6d97286c..63399c00cc28 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -161,7 +161,7 @@ static int smu_v14_0_0_init_smc_tables(struct smu_context *smu) SMU_TABLE_INIT(tables, SMU_TABLE_WATERMARKS, sizeof(Watermarks_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, sizeof(DpmClocks_t), + SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, max(sizeof(DpmClocks_t), sizeof(DpmClocks_t_v14_0_1)), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); @@ -171,7 +171,7 @@ static int smu_v14_0_0_init_smc_tables(struct smu_context *smu) goto err0_out; smu_table->metrics_time = 0; - smu_table->clocks_table = kzalloc(sizeof(DpmClocks_t), GFP_KERNEL); + smu_table->clocks_table = kzalloc(max(sizeof(DpmClocks_t), sizeof(DpmClocks_t_v14_0_1)), GFP_KERNEL); if (!smu_table->clocks_table) goto err1_out; @@ -593,6 +593,60 @@ static int smu_v14_0_0_mode2_reset(struct smu_context *smu) return ret; } +static int smu_v14_0_1_get_dpm_freq_by_index(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t dpm_level, + uint32_t *freq) +{ + DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table; + + if (!clk_table || clk_type >= SMU_CLK_COUNT) + return -EINVAL; + + switch (clk_type) { + case SMU_SOCCLK: + if (dpm_level >= clk_table->NumSocClkLevelsEnabled) + return -EINVAL; + *freq = clk_table->SocClocks[dpm_level]; + break; + case SMU_VCLK: + if (dpm_level >= clk_table->Vcn0ClkLevelsEnabled) + return -EINVAL; + *freq = clk_table->VClocks0[dpm_level]; + break; + case SMU_DCLK: + if (dpm_level >= clk_table->Vcn0ClkLevelsEnabled) + return -EINVAL; + *freq = clk_table->DClocks0[dpm_level]; + break; + case SMU_VCLK1: + if (dpm_level >= clk_table->Vcn1ClkLevelsEnabled) + return -EINVAL; + *freq = clk_table->VClocks1[dpm_level]; + break; + case SMU_DCLK1: + if (dpm_level >= clk_table->Vcn1ClkLevelsEnabled) + return -EINVAL; + *freq = clk_table->DClocks1[dpm_level]; + break; + case SMU_UCLK: + case SMU_MCLK: + if (dpm_level >= clk_table->NumMemPstatesEnabled) + return -EINVAL; + *freq = clk_table->MemPstateTable[dpm_level].MemClk; + break; + case SMU_FCLK: + if (dpm_level >= clk_table->NumFclkLevelsEnabled) + return -EINVAL; + *freq = clk_table->FclkClocks_Freq[dpm_level]; + break; + default: + return -EINVAL; + } + + return 0; +} + static int smu_v14_0_0_get_dpm_freq_by_index(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t dpm_level, @@ -637,6 +691,19 @@ static int smu_v14_0_0_get_dpm_freq_by_index(struct smu_context *smu, return 0; } +static int smu_v14_0_common_get_dpm_freq_by_index(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t dpm_level, + uint32_t *freq) +{ + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0)) + smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, dpm_level, freq); + else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) + smu_v14_0_1_get_dpm_freq_by_index(smu, clk_type, dpm_level, freq); + + return 0; +} + static bool smu_v14_0_0_clk_dpm_is_enabled(struct smu_context *smu, enum smu_clk_type clk_type) { @@ -657,6 +724,8 @@ static bool smu_v14_0_0_clk_dpm_is_enabled(struct smu_context *smu, break; case SMU_VCLK: case SMU_DCLK: + case SMU_VCLK1: + case SMU_DCLK1: feature_id = SMU_FEATURE_VCN_DPM_BIT; break; default: @@ -666,6 +735,126 @@ static bool smu_v14_0_0_clk_dpm_is_enabled(struct smu_context *smu, return smu_cmn_feature_is_enabled(smu, feature_id); } +static int smu_v14_0_1_get_dpm_ultimate_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *min, + uint32_t *max) +{ + DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table; + uint32_t clock_limit; + uint32_t max_dpm_level, min_dpm_level; + int ret = 0; + + if (!smu_v14_0_0_clk_dpm_is_enabled(smu, clk_type)) { + switch (clk_type) { + case SMU_MCLK: + case SMU_UCLK: + clock_limit = smu->smu_table.boot_values.uclk; + break; + case SMU_FCLK: + clock_limit = smu->smu_table.boot_values.fclk; + break; + case SMU_GFXCLK: + case SMU_SCLK: + clock_limit = smu->smu_table.boot_values.gfxclk; + break; + case SMU_SOCCLK: + clock_limit = smu->smu_table.boot_values.socclk; + break; + case SMU_VCLK: + case SMU_VCLK1: + clock_limit = smu->smu_table.boot_values.vclk; + break; + case SMU_DCLK: + case SMU_DCLK1: + clock_limit = smu->smu_table.boot_values.dclk; + break; + default: + clock_limit = 0; + break; + } + + /* clock in Mhz unit */ + if (min) + *min = clock_limit / 100; + if (max) + *max = clock_limit / 100; + + return 0; + } + + if (max) { + switch (clk_type) { + case SMU_GFXCLK: + case SMU_SCLK: + *max = clk_table->MaxGfxClk; + break; + case SMU_MCLK: + case SMU_UCLK: + case SMU_FCLK: + max_dpm_level = 0; + break; + case SMU_SOCCLK: + max_dpm_level = clk_table->NumSocClkLevelsEnabled - 1; + break; + case SMU_VCLK: + case SMU_DCLK: + max_dpm_level = clk_table->Vcn0ClkLevelsEnabled - 1; + break; + case SMU_VCLK1: + case SMU_DCLK1: + max_dpm_level = clk_table->Vcn1ClkLevelsEnabled - 1; + break; + default: + ret = -EINVAL; + goto failed; + } + + if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) { + ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max); + if (ret) + goto failed; + } + } + + if (min) { + switch (clk_type) { + case SMU_GFXCLK: + case SMU_SCLK: + *min = clk_table->MinGfxClk; + break; + case SMU_MCLK: + case SMU_UCLK: + min_dpm_level = clk_table->NumMemPstatesEnabled - 1; + break; + case SMU_FCLK: + min_dpm_level = clk_table->NumFclkLevelsEnabled - 1; + break; + case SMU_SOCCLK: + min_dpm_level = 0; + break; + case SMU_VCLK: + case SMU_DCLK: + case SMU_VCLK1: + case SMU_DCLK1: + min_dpm_level = 0; + break; + default: + ret = -EINVAL; + goto failed; + } + + if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) { + ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min); + if (ret) + goto failed; + } + } + +failed: + return ret; +} + static int smu_v14_0_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *min, @@ -736,7 +925,7 @@ static int smu_v14_0_0_get_dpm_ultimate_freq(struct smu_context *smu, } if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) { - ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max); + ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, max_dpm_level, max); if (ret) goto failed; } @@ -768,7 +957,7 @@ static int smu_v14_0_0_get_dpm_ultimate_freq(struct smu_context *smu, } if (clk_type != SMU_GFXCLK && clk_type != SMU_SCLK) { - ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min); + ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, min_dpm_level, min); if (ret) goto failed; } @@ -778,6 +967,19 @@ failed: return ret; } +static int smu_v14_0_common_get_dpm_ultimate_freq(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *min, + uint32_t *max) +{ + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0)) + smu_v14_0_0_get_dpm_ultimate_freq(smu, clk_type, min, max); + else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) + smu_v14_0_1_get_dpm_ultimate_freq(smu, clk_type, min, max); + + return 0; +} + static int smu_v14_0_0_get_current_clk_freq(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *value) @@ -811,6 +1013,37 @@ static int smu_v14_0_0_get_current_clk_freq(struct smu_context *smu, return smu_v14_0_0_get_smu_metrics_data(smu, member_type, value); } +static int smu_v14_0_1_get_dpm_level_count(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *count) +{ + DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table; + + switch (clk_type) { + case SMU_SOCCLK: + *count = clk_table->NumSocClkLevelsEnabled; + break; + case SMU_VCLK: + case SMU_DCLK: + *count = clk_table->Vcn0ClkLevelsEnabled; + break; + case SMU_VCLK1: + case SMU_DCLK1: + *count = clk_table->Vcn1ClkLevelsEnabled; + break; + case SMU_MCLK: + *count = clk_table->NumMemPstatesEnabled; + break; + case SMU_FCLK: + *count = clk_table->NumFclkLevelsEnabled; + break; + default: + break; + } + + return 0; +} + static int smu_v14_0_0_get_dpm_level_count(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *count) @@ -840,6 +1073,18 @@ static int smu_v14_0_0_get_dpm_level_count(struct smu_context *smu, return 0; } +static int smu_v14_0_common_get_dpm_level_count(struct smu_context *smu, + enum smu_clk_type clk_type, + uint32_t *count) +{ + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0)) + smu_v14_0_0_get_dpm_level_count(smu, clk_type, count); + else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) + smu_v14_0_1_get_dpm_level_count(smu, clk_type, count); + + return 0; +} + static int smu_v14_0_0_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { @@ -866,18 +1111,20 @@ static int smu_v14_0_0_print_clk_levels(struct smu_context *smu, case SMU_SOCCLK: case SMU_VCLK: case SMU_DCLK: + case SMU_VCLK1: + case SMU_DCLK1: case SMU_MCLK: case SMU_FCLK: ret = smu_v14_0_0_get_current_clk_freq(smu, clk_type, &cur_value); if (ret) break; - ret = smu_v14_0_0_get_dpm_level_count(smu, clk_type, &count); + ret = smu_v14_0_common_get_dpm_level_count(smu, clk_type, &count); if (ret) break; for (i = 0; i < count; i++) { - ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, i, &value); + ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, i, &value); if (ret) break; @@ -940,8 +1187,13 @@ static int smu_v14_0_0_set_soft_freq_limited_range(struct smu_context *smu, break; case SMU_VCLK: case SMU_DCLK: - msg_set_min = SMU_MSG_SetHardMinVcn; - msg_set_max = SMU_MSG_SetSoftMaxVcn; + msg_set_min = SMU_MSG_SetHardMinVcn0; + msg_set_max = SMU_MSG_SetSoftMaxVcn0; + break; + case SMU_VCLK1: + case SMU_DCLK1: + msg_set_min = SMU_MSG_SetHardMinVcn1; + msg_set_max = SMU_MSG_SetSoftMaxVcn1; break; default: return -EINVAL; @@ -971,11 +1223,11 @@ static int smu_v14_0_0_force_clk_levels(struct smu_context *smu, case SMU_FCLK: case SMU_VCLK: case SMU_DCLK: - ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq); + ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq); if (ret) break; - ret = smu_v14_0_0_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq); + ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq); if (ret) break; @@ -1000,25 +1252,25 @@ static int smu_v14_0_0_set_performance_level(struct smu_context *smu, switch (level) { case AMD_DPM_FORCED_LEVEL_HIGH: - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, NULL, &sclk_max); - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &fclk_max); - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &socclk_max); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, NULL, &sclk_max); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, NULL, &fclk_max); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, NULL, &socclk_max); sclk_min = sclk_max; fclk_min = fclk_max; socclk_min = socclk_max; break; case AMD_DPM_FORCED_LEVEL_LOW: - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, NULL); - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, NULL); - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, NULL); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, NULL); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, NULL); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, NULL); sclk_max = sclk_min; fclk_max = fclk_min; socclk_max = socclk_min; break; case AMD_DPM_FORCED_LEVEL_AUTO: - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, &sclk_max); - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, &fclk_max); - smu_v14_0_0_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, &socclk_max); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SCLK, &sclk_min, &sclk_max); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_FCLK, &fclk_min, &fclk_max); + smu_v14_0_common_get_dpm_ultimate_freq(smu, SMU_SOCCLK, &socclk_min, &socclk_max); break; case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD: case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK: @@ -1067,6 +1319,18 @@ static int smu_v14_0_0_set_performance_level(struct smu_context *smu, return ret; } +static int smu_v14_0_1_set_fine_grain_gfx_freq_parameters(struct smu_context *smu) +{ + DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table; + + smu->gfx_default_hard_min_freq = clk_table->MinGfxClk; + smu->gfx_default_soft_max_freq = clk_table->MaxGfxClk; + smu->gfx_actual_hard_min_freq = 0; + smu->gfx_actual_soft_max_freq = 0; + + return 0; +} + static int smu_v14_0_0_set_fine_grain_gfx_freq_parameters(struct smu_context *smu) { DpmClocks_t *clk_table = smu->smu_table.clocks_table; @@ -1079,6 +1343,16 @@ static int smu_v14_0_0_set_fine_grain_gfx_freq_parameters(struct smu_context *sm return 0; } +static int smu_v14_0_common_set_fine_grain_gfx_freq_parameters(struct smu_context *smu) +{ + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0)) + smu_v14_0_0_set_fine_grain_gfx_freq_parameters(smu); + else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) + smu_v14_0_1_set_fine_grain_gfx_freq_parameters(smu); + + return 0; +} + static int smu_v14_0_0_set_vpe_enable(struct smu_context *smu, bool enable) { @@ -1095,6 +1369,25 @@ static int smu_v14_0_0_set_umsch_mm_enable(struct smu_context *smu, 0, NULL); } +static int smu_14_0_1_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table) +{ + DpmClocks_t_v14_0_1 *clk_table = smu->smu_table.clocks_table; + uint8_t idx; + + /* Only the Clock information of SOC and VPE is copied to provide VPE DPM settings for use. */ + for (idx = 0; idx < NUM_SOCCLK_DPM_LEVELS; idx++) { + clock_table->SocClocks[idx].Freq = (idx < clk_table->NumSocClkLevelsEnabled) ? clk_table->SocClocks[idx]:0; + clock_table->SocClocks[idx].Vol = 0; + } + + for (idx = 0; idx < NUM_VPE_DPM_LEVELS; idx++) { + clock_table->VPEClocks[idx].Freq = (idx < clk_table->VpeClkLevelsEnabled) ? clk_table->VPEClocks[idx]:0; + clock_table->VPEClocks[idx].Vol = 0; + } + + return 0; +} + static int smu_14_0_0_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table) { DpmClocks_t *clk_table = smu->smu_table.clocks_table; @@ -1114,6 +1407,16 @@ static int smu_14_0_0_get_dpm_table(struct smu_context *smu, struct dpm_clocks * return 0; } +static int smu_v14_0_common_get_dpm_table(struct smu_context *smu, struct dpm_clocks *clock_table) +{ + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 0)) + smu_14_0_0_get_dpm_table(smu, clock_table); + else if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) + smu_14_0_1_get_dpm_table(smu, clock_table); + + return 0; +} + static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .check_fw_status = smu_v14_0_check_fw_status, .check_fw_version = smu_v14_0_check_fw_version, @@ -1135,16 +1438,16 @@ static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .set_driver_table_location = smu_v14_0_set_driver_table_location, .gfx_off_control = smu_v14_0_gfx_off_control, .mode2_reset = smu_v14_0_0_mode2_reset, - .get_dpm_ultimate_freq = smu_v14_0_0_get_dpm_ultimate_freq, + .get_dpm_ultimate_freq = smu_v14_0_common_get_dpm_ultimate_freq, .od_edit_dpm_table = smu_v14_0_od_edit_dpm_table, .print_clk_levels = smu_v14_0_0_print_clk_levels, .force_clk_levels = smu_v14_0_0_force_clk_levels, .set_performance_level = smu_v14_0_0_set_performance_level, - .set_fine_grain_gfx_freq_parameters = smu_v14_0_0_set_fine_grain_gfx_freq_parameters, + .set_fine_grain_gfx_freq_parameters = smu_v14_0_common_set_fine_grain_gfx_freq_parameters, .set_gfx_power_up_by_imu = smu_v14_0_set_gfx_power_up_by_imu, .dpm_set_vpe_enable = smu_v14_0_0_set_vpe_enable, .dpm_set_umsch_mm_enable = smu_v14_0_0_set_umsch_mm_enable, - .get_dpm_clock_table = smu_14_0_0_get_dpm_table, + .get_dpm_clock_table = smu_v14_0_common_get_dpm_table, }; static void smu_v14_0_0_set_smu_mailbox_registers(struct smu_context *smu) diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c index ebb6d8ebd44e..1e9259416980 100644 --- a/drivers/gpu/drm/ast/ast_dp.c +++ b/drivers/gpu/drm/ast/ast_dp.c @@ -180,6 +180,7 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on) { struct ast_device *ast = to_ast_device(dev); u8 video_on_off = on; + u32 i = 0; // Video On/Off ast_set_index_reg_mask(ast, AST_IO_VGACRI, 0xE3, (u8) ~AST_DP_VIDEO_ENABLE, on); @@ -192,6 +193,8 @@ void ast_dp_set_on_off(struct drm_device *dev, bool on) ASTDP_MIRROR_VIDEO_ENABLE) != video_on_off) { // wait 1 ms mdelay(1); + if (++i > 200) + break; } } } diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 871e4e2129d6..0683a129b362 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -777,6 +777,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, unsigned int total_modes_count = 0; struct drm_client_offset *offsets; unsigned int connector_count = 0; + /* points to modes protected by mode_config.mutex */ struct drm_display_mode **modes; struct drm_crtc **crtcs; int i, ret = 0; @@ -845,7 +846,6 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, drm_client_pick_crtcs(client, connectors, connector_count, crtcs, modes, 0, width, height); } - mutex_unlock(&dev->mode_config.mutex); drm_client_modeset_release(client); @@ -875,6 +875,7 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, modeset->y = offset->y; } } + mutex_unlock(&dev->mode_config.mutex); mutex_unlock(&client->modeset_mutex); out: diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index ed89b86ea625..f672bfd70d45 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2534,7 +2534,8 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state) intel_atomic_get_old_cdclk_state(state); const struct intel_cdclk_state *new_cdclk_state = intel_atomic_get_new_cdclk_state(state); - enum pipe pipe = new_cdclk_state->pipe; + struct intel_cdclk_config cdclk_config; + enum pipe pipe; if (!intel_cdclk_changed(&old_cdclk_state->actual, &new_cdclk_state->actual)) @@ -2543,12 +2544,25 @@ intel_set_cdclk_pre_plane_update(struct intel_atomic_state *state) if (IS_DG2(i915)) intel_cdclk_pcode_pre_notify(state); - if (pipe == INVALID_PIPE || - old_cdclk_state->actual.cdclk <= new_cdclk_state->actual.cdclk) { - drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + if (new_cdclk_state->disable_pipes) { + cdclk_config = new_cdclk_state->actual; + pipe = INVALID_PIPE; + } else { + if (new_cdclk_state->actual.cdclk >= old_cdclk_state->actual.cdclk) { + cdclk_config = new_cdclk_state->actual; + pipe = new_cdclk_state->pipe; + } else { + cdclk_config = old_cdclk_state->actual; + pipe = INVALID_PIPE; + } - intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); + cdclk_config.voltage_level = max(new_cdclk_state->actual.voltage_level, + old_cdclk_state->actual.voltage_level); } + + drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + + intel_set_cdclk(i915, &cdclk_config, pipe); } /** @@ -2566,7 +2580,7 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state) intel_atomic_get_old_cdclk_state(state); const struct intel_cdclk_state *new_cdclk_state = intel_atomic_get_new_cdclk_state(state); - enum pipe pipe = new_cdclk_state->pipe; + enum pipe pipe; if (!intel_cdclk_changed(&old_cdclk_state->actual, &new_cdclk_state->actual)) @@ -2575,12 +2589,15 @@ intel_set_cdclk_post_plane_update(struct intel_atomic_state *state) if (IS_DG2(i915)) intel_cdclk_pcode_post_notify(state); - if (pipe != INVALID_PIPE && - old_cdclk_state->actual.cdclk > new_cdclk_state->actual.cdclk) { - drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); + if (!new_cdclk_state->disable_pipes && + new_cdclk_state->actual.cdclk < old_cdclk_state->actual.cdclk) + pipe = new_cdclk_state->pipe; + else + pipe = INVALID_PIPE; + + drm_WARN_ON(&i915->drm, !new_cdclk_state->base.changed); - intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); - } + intel_set_cdclk(i915, &new_cdclk_state->actual, pipe); } static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state) @@ -3058,6 +3075,7 @@ static struct intel_global_state *intel_cdclk_duplicate_state(struct intel_globa return NULL; cdclk_state->pipe = INVALID_PIPE; + cdclk_state->disable_pipes = false; return &cdclk_state->base; } @@ -3236,6 +3254,8 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) if (ret) return ret; + new_cdclk_state->disable_pipes = true; + drm_dbg_kms(&dev_priv->drm, "Modeset required for cdclk change\n"); } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index 48fd7d39e0cd..71bc032bfef1 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -51,6 +51,9 @@ struct intel_cdclk_state { /* bitmask of active pipes */ u8 active_pipes; + + /* update cdclk with pipes disabled */ + bool disable_pipes; }; int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index c587a8efeafc..c17462b4c2ac 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -4256,7 +4256,12 @@ static bool m_n_equal(const struct intel_link_m_n *m_n_1, static bool crtcs_port_sync_compatible(const struct intel_crtc_state *crtc_state1, const struct intel_crtc_state *crtc_state2) { + /* + * FIXME the modeset sequence is currently wrong and + * can't deal with bigjoiner + port sync at the same time. + */ return crtc_state1->hw.active && crtc_state2->hw.active && + !crtc_state1->bigjoiner_pipes && !crtc_state2->bigjoiner_pipes && crtc_state1->output_types == crtc_state2->output_types && crtc_state1->output_format == crtc_state2->output_format && crtc_state1->lane_count == crtc_state2->lane_count && diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index abd62bebc46d..e583515f9b25 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -2725,7 +2725,11 @@ intel_dp_drrs_compute_config(struct intel_connector *connector, intel_panel_downclock_mode(connector, &pipe_config->hw.adjusted_mode); int pixel_clock; - if (has_seamless_m_n(connector)) + /* + * FIXME all joined pipes share the same transcoder. + * Need to account for that when updating M/N live. + */ + if (has_seamless_m_n(connector) && !pipe_config->bigjoiner_pipes) pipe_config->update_m_n = true; if (!can_enable_drrs(connector, pipe_config, downclock_mode)) { diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c index b98a87883fef..9db43bd81ce2 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c @@ -691,12 +691,15 @@ int intel_dp_hdcp_get_remote_capability(struct intel_connector *connector, u8 bcaps; int ret; + *hdcp_capable = false; + *hdcp2_capable = false; if (!intel_encoder_is_mst(connector->encoder)) return -EINVAL; ret = _intel_dp_hdcp2_get_capability(aux, hdcp2_capable); if (ret) - return ret; + drm_dbg_kms(&i915->drm, + "HDCP2 DPCD capability read failed err: %d\n", ret); ret = intel_dp_hdcp_read_bcaps(aux, i915, &bcaps); if (ret) diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index b6e539f1342c..aabd018bd737 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1422,6 +1422,17 @@ void intel_psr_compute_config(struct intel_dp *intel_dp, return; } + /* + * FIXME figure out what is wrong with PSR+bigjoiner and + * fix it. Presumably something related to the fact that + * PSR is a transcoder level feature. + */ + if (crtc_state->bigjoiner_pipes) { + drm_dbg_kms(&dev_priv->drm, + "PSR disabled due to bigjoiner\n"); + return; + } + if (CAN_PANEL_REPLAY(intel_dp)) crtc_state->has_panel_replay = true; else diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index eb5bd0743902..f542ee1db1d9 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -117,6 +117,13 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state, const struct drm_display_info *info = &connector->base.display_info; int vmin, vmax; + /* + * FIXME all joined pipes share the same transcoder. + * Need to account for that during VRR toggle/push/etc. + */ + if (crtc_state->bigjoiner_pipes) + return; + if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) return; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index f3dcae4b9d45..0f83c6d4376f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1403,14 +1403,17 @@ static void guc_cancel_busyness_worker(struct intel_guc *guc) * Trying to pass a 'need_sync' or 'in_reset' flag all the way down through * every possible call stack is unfeasible. It would be too intrusive to many * areas that really don't care about the GuC backend. However, there is the - * 'reset_in_progress' flag available, so just use that. + * I915_RESET_BACKOFF flag and the gt->reset.mutex can be tested for is_locked. + * So just use those. Note that testing both is required due to the hideously + * complex nature of the i915 driver's reset code paths. * * And note that in the case of a reset occurring during driver unload - * (wedge_on_fini), skipping the cancel in _prepare (when the reset flag is set - * is fine because there is another cancel in _finish (when the reset flag is - * not). + * (wedged_on_fini), skipping the cancel in reset_prepare/reset_fini (when the + * reset flag/mutex are set) is fine because there is another explicit cancel in + * intel_guc_submission_fini (when the reset flag/mutex are not). */ - if (guc_to_gt(guc)->uc.reset_in_progress) + if (mutex_is_locked(&guc_to_gt(guc)->reset.mutex) || + test_bit(I915_RESET_BACKOFF, &guc_to_gt(guc)->reset.flags)) cancel_delayed_work(&guc->timestamp.work); else cancel_delayed_work_sync(&guc->timestamp.work); @@ -1424,8 +1427,6 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc) unsigned long flags; ktime_t unused; - guc_cancel_busyness_worker(guc); - spin_lock_irqsave(&guc->timestamp.lock, flags); guc_update_pm_timestamp(guc, &unused); @@ -2004,13 +2005,6 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc) void intel_guc_submission_reset_finish(struct intel_guc *guc) { - /* - * Ensure the busyness worker gets cancelled even on a fatal wedge. - * Note that reset_prepare is not allowed to because it confuses lockdep. - */ - if (guc_submission_initialized(guc)) - guc_cancel_busyness_worker(guc); - /* Reset called during driver load or during wedge? */ if (unlikely(!guc_submission_initialized(guc) || !intel_guc_is_fw_running(guc) || @@ -2136,6 +2130,7 @@ void intel_guc_submission_fini(struct intel_guc *guc) if (!guc->submission_initialized) return; + guc_fini_engine_stats(guc); guc_flush_destroyed_contexts(guc); guc_lrc_desc_pool_destroy_v69(guc); i915_sched_engine_put(guc->sched_engine); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index 6dfe5d9456c6..399bc319180b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -637,6 +637,10 @@ void intel_uc_reset_finish(struct intel_uc *uc) { struct intel_guc *guc = &uc->guc; + /* + * NB: The wedge code path results in prepare -> prepare -> finish -> finish. + * So this function is sometimes called with the in-progress flag not set. + */ uc->reset_in_progress = false; /* Firmware expected to be running when this function is called */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 0674aca0f8a3..cf0b1de1c071 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1377,6 +1377,10 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu) if (adreno_is_a618(gpu)) gpu->ubwc_config.highest_bank_bit = 14; + if (adreno_is_a619(gpu)) + /* TODO: Should be 14 but causes corruption at e.g. 1920x1200 on DP */ + gpu->ubwc_config.highest_bank_bit = 13; + if (adreno_is_a619_holi(gpu)) gpu->ubwc_config.highest_bank_bit = 13; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 1f5245fc2cdc..a847a0f7a73c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -852,7 +852,7 @@ static void a6xx_get_shader_block(struct msm_gpu *gpu, (block->type << 8) | i); in += CRASHDUMP_READ(in, REG_A6XX_HLSQ_DBG_AHB_READ_APERTURE, - block->size, dumper->iova + A6XX_CD_DATA_OFFSET); + block->size, out); out += block->size * sizeof(u32); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h index 9a9f7092c526..a3e60ac70689 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h @@ -324,6 +324,7 @@ static const struct dpu_wb_cfg x1e80100_wb[] = { }, }; +/* TODO: INTF 3, 8 and 7 are used for MST, marked as INTF_NONE for now */ static const struct dpu_intf_cfg x1e80100_intf[] = { { .name = "intf_0", .id = INTF_0, @@ -358,8 +359,8 @@ static const struct dpu_intf_cfg x1e80100_intf[] = { .name = "intf_3", .id = INTF_3, .base = 0x37000, .len = 0x280, .features = INTF_SC7280_MASK, - .type = INTF_DP, - .controller_id = MSM_DP_CONTROLLER_1, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_0, /* pair with intf_0 for DP MST */ .prog_fetch_lines_worst_case = 24, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31), @@ -368,7 +369,7 @@ static const struct dpu_intf_cfg x1e80100_intf[] = { .base = 0x38000, .len = 0x280, .features = INTF_SC7280_MASK, .type = INTF_DP, - .controller_id = MSM_DP_CONTROLLER_2, + .controller_id = MSM_DP_CONTROLLER_1, .prog_fetch_lines_worst_case = 24, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 20), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 21), @@ -381,6 +382,33 @@ static const struct dpu_intf_cfg x1e80100_intf[] = { .prog_fetch_lines_worst_case = 24, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 22), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 23), + }, { + .name = "intf_6", .id = INTF_6, + .base = 0x3A000, .len = 0x280, + .features = INTF_SC7280_MASK, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_2, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + }, { + .name = "intf_7", .id = INTF_7, + .base = 0x3b000, .len = 0x280, + .features = INTF_SC7280_MASK, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_2, /* pair with intf_6 for DP MST */ + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 18), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 19), + }, { + .name = "intf_8", .id = INTF_8, + .base = 0x3c000, .len = 0x280, + .features = INTF_SC7280_MASK, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_1, /* pair with intf_4 for DP MST */ + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), }, }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index ef871239adb2..68fae048a9a8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -459,15 +459,15 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) &perf->core_clk_rate); debugfs_create_u32("enable_bw_release", 0600, entry, (u32 *)&perf->enable_bw_release); - debugfs_create_u32("threshold_low", 0600, entry, + debugfs_create_u32("threshold_low", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_low); - debugfs_create_u32("threshold_high", 0600, entry, + debugfs_create_u32("threshold_high", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_high); - debugfs_create_u32("min_core_ib", 0600, entry, + debugfs_create_u32("min_core_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_core_ib); - debugfs_create_u32("min_llcc_ib", 0600, entry, + debugfs_create_u32("min_llcc_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_llcc_ib); - debugfs_create_u32("min_dram_ib", 0600, entry, + debugfs_create_u32("min_dram_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_dram_ib); debugfs_create_file("perf_mode", 0600, entry, (u32 *)perf, &dpu_core_perf_mode_fops); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 946dd0135dff..6a0a74832fb6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -525,14 +525,14 @@ int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int ret; if (!irq_cb) { - DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n", - DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb); + DPU_ERROR("IRQ=[%d, %d] NULL callback\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); return -EINVAL; } if (!dpu_core_irq_is_valid(irq_idx)) { - DPU_ERROR("invalid IRQ=[%d, %d]\n", - DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx)); + DPU_ERROR("invalid IRQ=[%d, %d] irq_cb:%ps\n", + DPU_IRQ_REG(irq_idx), DPU_IRQ_BIT(irq_idx), irq_cb); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index c4cb82af5c2f..ffbfde922589 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -484,7 +484,7 @@ static void dp_display_handle_video_request(struct dp_display_private *dp) } } -static int dp_display_handle_port_ststus_changed(struct dp_display_private *dp) +static int dp_display_handle_port_status_changed(struct dp_display_private *dp) { int rc = 0; @@ -541,7 +541,7 @@ static int dp_display_usbpd_attention_cb(struct device *dev) drm_dbg_dp(dp->drm_dev, "hpd_state=%d sink_request=%d\n", dp->hpd_state, sink_request); if (sink_request & DS_PORT_STATUS_CHANGED) - rc = dp_display_handle_port_ststus_changed(dp); + rc = dp_display_handle_port_status_changed(dp); else rc = dp_display_handle_irq_hpd(dp); } @@ -588,6 +588,7 @@ static int dp_hpd_plug_handle(struct dp_display_private *dp, u32 data) ret = dp_display_usbpd_configure_cb(&pdev->dev); if (ret) { /* link train failed */ dp->hpd_state = ST_DISCONNECTED; + pm_runtime_put_sync(&pdev->dev); } else { dp->hpd_state = ST_MAINLINK_READY; } @@ -645,6 +646,7 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) dp_display_host_phy_exit(dp); dp->hpd_state = ST_DISCONNECTED; dp_display_notify_disconnect(&dp->dp_display.pdev->dev); + pm_runtime_put_sync(&pdev->dev); mutex_unlock(&dp->event_mutex); return 0; } diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c index e3f61c39df69..80166f702a0d 100644 --- a/drivers/gpu/drm/msm/msm_fb.c +++ b/drivers/gpu/drm/msm/msm_fb.c @@ -89,7 +89,7 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb, for (i = 0; i < n; i++) { ret = msm_gem_get_and_pin_iova(fb->obj[i], aspace, &msm_fb->iova[i]); - drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)", + drm_dbg_state(fb->dev, "FB[%u]: iova[%d]: %08llx (%d)\n", fb->base.id, i, msm_fb->iova[i], ret); if (ret) return ret; @@ -176,7 +176,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, const struct msm_format *format; int ret, i, n; - drm_dbg_state(dev, "create framebuffer: mode_cmd=%p (%dx%d@%4.4s)", + drm_dbg_state(dev, "create framebuffer: mode_cmd=%p (%dx%d@%4.4s)\n", mode_cmd, mode_cmd->width, mode_cmd->height, (char *)&mode_cmd->pixel_format); @@ -232,7 +232,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev, refcount_set(&msm_fb->dirtyfb, 1); - drm_dbg_state(dev, "create: FB ID: %d (%p)", fb->base.id, fb); + drm_dbg_state(dev, "create: FB ID: %d (%p)\n", fb->base.id, fb); return fb; diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 84c21ec2ceea..af6a6fcb1173 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -149,7 +149,7 @@ int msm_crtc_enable_vblank(struct drm_crtc *crtc) struct msm_kms *kms = priv->kms; if (!kms) return -ENXIO; - drm_dbg_vbl(dev, "crtc=%u", crtc->base.id); + drm_dbg_vbl(dev, "crtc=%u\n", crtc->base.id); return vblank_ctrl_queue_work(priv, crtc, true); } @@ -160,7 +160,7 @@ void msm_crtc_disable_vblank(struct drm_crtc *crtc) struct msm_kms *kms = priv->kms; if (!kms) return; - drm_dbg_vbl(dev, "crtc=%u", crtc->base.id); + drm_dbg_vbl(dev, "crtc=%u\n", crtc->base.id); vblank_ctrl_queue_work(priv, crtc, false); } diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 479effcf607e..79cfab53f80e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -23,6 +23,7 @@ */ #include "nouveau_drv.h" +#include "nouveau_bios.h" #include "nouveau_reg.h" #include "dispnv04/hw.h" #include "nouveau_encoder.h" @@ -1677,7 +1678,7 @@ apply_dcb_encoder_quirks(struct drm_device *dev, int idx, u32 *conn, u32 *conf) */ if (nv_match_device(dev, 0x0201, 0x1462, 0x8851)) { if (*conn == 0xf2005014 && *conf == 0xffffffff) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, 1); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 1, 1, DCB_OUTPUT_B); return false; } } @@ -1763,26 +1764,26 @@ fabricate_dcb_encoder_table(struct drm_device *dev, struct nvbios *bios) #ifdef __powerpc__ /* Apple iMac G4 NV17 */ if (of_machine_is_compatible("PowerMac4,5")) { - fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, 1); - fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, 2); + fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, 0, all_heads, DCB_OUTPUT_B); + fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, 1, all_heads, DCB_OUTPUT_C); return; } #endif /* Make up some sane defaults */ fabricate_dcb_output(dcb, DCB_OUTPUT_ANALOG, - bios->legacy.i2c_indices.crt, 1, 1); + bios->legacy.i2c_indices.crt, 1, DCB_OUTPUT_B); if (nv04_tv_identify(dev, bios->legacy.i2c_indices.tv) >= 0) fabricate_dcb_output(dcb, DCB_OUTPUT_TV, bios->legacy.i2c_indices.tv, - all_heads, 0); + all_heads, DCB_OUTPUT_A); else if (bios->tmds.output0_script_ptr || bios->tmds.output1_script_ptr) fabricate_dcb_output(dcb, DCB_OUTPUT_TMDS, bios->legacy.i2c_indices.panel, - all_heads, 1); + all_heads, DCB_OUTPUT_B); } static int diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 7de7707ec6a8..a72c45809484 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -225,12 +225,18 @@ nouveau_dp_detect(struct nouveau_connector *nv_connector, u8 *dpcd = nv_encoder->dp.dpcd; int ret = NOUVEAU_DP_NONE, hpd; - /* If we've already read the DPCD on an eDP device, we don't need to - * reread it as it won't change + /* eDP ports don't support hotplugging - so there's no point in probing eDP ports unless we + * haven't probed them once before. */ - if (connector->connector_type == DRM_MODE_CONNECTOR_eDP && - dpcd[DP_DPCD_REV] != 0) - return NOUVEAU_DP_SST; + if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { + if (connector->status == connector_status_connected) + return NOUVEAU_DP_SST; + else if (connector->status == connector_status_disconnected) + return NOUVEAU_DP_NONE; + } + + // Ensure that the aux bus is enabled for probing + drm_dp_dpcd_set_powered(&nv_connector->aux, true); mutex_lock(&nv_encoder->dp.hpd_irq_lock); if (mstm) { @@ -293,6 +299,13 @@ out: if (mstm && !mstm->suspended && ret != NOUVEAU_DP_MST) nv50_mstm_remove(mstm); + /* GSP doesn't like when we try to do aux transactions on a port it considers disconnected, + * and since we don't really have a usecase for that anyway - just disable the aux bus here + * if we've decided the connector is disconnected + */ + if (ret == NOUVEAU_DP_NONE) + drm_dp_dpcd_set_powered(&nv_connector->aux, false); + mutex_unlock(&nv_encoder->dp.hpd_irq_lock); return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c index 4bf486b57101..cb05f7f48a98 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowof.c @@ -66,11 +66,16 @@ of_init(struct nvkm_bios *bios, const char *name) return ERR_PTR(-EINVAL); } +static void of_fini(void *p) +{ + kfree(p); +} + const struct nvbios_source nvbios_of = { .name = "OpenFirmware", .init = of_init, - .fini = (void(*)(void *))kfree, + .fini = of_fini, .read = of_read, .size = of_size, .rw = false, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c index 7bcbc4895ec2..271bfa038f5b 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c @@ -25,6 +25,7 @@ #include <subdev/bios.h> #include <subdev/bios/init.h> +#include <subdev/gsp.h> void gm107_devinit_disable(struct nvkm_devinit *init) @@ -33,10 +34,13 @@ gm107_devinit_disable(struct nvkm_devinit *init) u32 r021c00 = nvkm_rd32(device, 0x021c00); u32 r021c04 = nvkm_rd32(device, 0x021c04); - if (r021c00 & 0x00000001) - nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0); - if (r021c00 & 0x00000004) - nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2); + /* gsp only wants to enable/disable display */ + if (!nvkm_gsp_rm(device->gsp)) { + if (r021c00 & 0x00000001) + nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0); + if (r021c00 & 0x00000004) + nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2); + } if (r021c04 & 0x00000001) nvkm_subdev_disable(device, NVKM_ENGINE_DISP, 0); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c index 11b4c9c274a1..666eb93b1742 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c @@ -41,6 +41,7 @@ r535_devinit_new(const struct nvkm_devinit_func *hw, rm->dtor = r535_devinit_dtor; rm->post = hw->post; + rm->disable = hw->disable; ret = nv50_devinit_new_(rm, device, type, inst, pdevinit); if (ret) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index 9994cbd6f1c4..9858c1438aa7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -1112,7 +1112,7 @@ r535_gsp_rpc_set_registry(struct nvkm_gsp *gsp) rpc->numEntries = NV_GSP_REG_NUM_ENTRIES; str_offset = offsetof(typeof(*rpc), entries[NV_GSP_REG_NUM_ENTRIES]); - strings = (char *)&rpc->entries[NV_GSP_REG_NUM_ENTRIES]; + strings = (char *)rpc + str_offset; for (i = 0; i < NV_GSP_REG_NUM_ENTRIES; i++) { int name_len = strlen(r535_registry_entries[i].name) + 1; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index a7f3fc342d87..dd5b5a17ece0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -222,8 +222,11 @@ nv50_instobj_acquire(struct nvkm_memory *memory) void __iomem *map = NULL; /* Already mapped? */ - if (refcount_inc_not_zero(&iobj->maps)) + if (refcount_inc_not_zero(&iobj->maps)) { + /* read barrier match the wmb on refcount set */ + smp_rmb(); return iobj->map; + } /* Take the lock, and re-check that another thread hasn't * already mapped the object in the meantime. @@ -250,6 +253,8 @@ nv50_instobj_acquire(struct nvkm_memory *memory) iobj->base.memory.ptrs = &nv50_instobj_fast; else iobj->base.memory.ptrs = &nv50_instobj_slow; + /* barrier to ensure the ptrs are written before refcount is set */ + smp_wmb(); refcount_set(&iobj->maps, 1); } diff --git a/drivers/gpu/drm/panel/panel-novatek-nt36672e.c b/drivers/gpu/drm/panel/panel-novatek-nt36672e.c index cb7406d74466..c39fe0fc5d69 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt36672e.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt36672e.c @@ -614,8 +614,6 @@ static void nt36672e_panel_remove(struct mipi_dsi_device *dsi) struct nt36672e_panel *ctx = mipi_dsi_get_drvdata(dsi); mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_panel_remove(&ctx->panel); } diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c index 775144695283..b15ca56a09a7 100644 --- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c +++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c @@ -253,8 +253,6 @@ static void visionox_rm69299_remove(struct mipi_dsi_device *dsi) struct visionox_rm69299 *ctx = mipi_dsi_get_drvdata(dsi); mipi_dsi_detach(ctx->dsi); - mipi_dsi_device_unregister(ctx->dsi); - drm_panel_remove(&ctx->panel); } diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index f38385fe76bb..b91019cd5acb 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -502,11 +502,18 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, mapping_set_unevictable(mapping); for (i = page_offset; i < page_offset + NUM_FAULT_PAGES; i++) { + /* Can happen if the last fault only partially filled this + * section of the pages array before failing. In that case + * we skip already filled pages. + */ + if (pages[i]) + continue; + pages[i] = shmem_read_mapping_page(mapping, i); if (IS_ERR(pages[i])) { ret = PTR_ERR(pages[i]); pages[i] = NULL; - goto err_pages; + goto err_unlock; } } @@ -514,7 +521,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, ret = sg_alloc_table_from_pages(sgt, pages + page_offset, NUM_FAULT_PAGES, 0, SZ_2M, GFP_KERNEL); if (ret) - goto err_pages; + goto err_unlock; ret = dma_map_sgtable(pfdev->dev, sgt, DMA_BIDIRECTIONAL, 0); if (ret) @@ -537,8 +544,6 @@ out: err_map: sg_free_table(sgt); -err_pages: - drm_gem_shmem_put_pages(&bo->base); err_unlock: dma_resv_unlock(obj->resv); err_bo: diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index 368d26da0d6a..9febc8b73f09 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -58,16 +58,56 @@ static long qxl_fence_wait(struct dma_fence *fence, bool intr, signed long timeout) { struct qxl_device *qdev; + struct qxl_release *release; + int count = 0, sc = 0; + bool have_drawable_releases; unsigned long cur, end = jiffies + timeout; qdev = container_of(fence->lock, struct qxl_device, release_lock); + release = container_of(fence, struct qxl_release, base); + have_drawable_releases = release->type == QXL_RELEASE_DRAWABLE; - if (!wait_event_timeout(qdev->release_event, - (dma_fence_is_signaled(fence) || - (qxl_io_notify_oom(qdev), 0)), - timeout)) - return 0; +retry: + sc++; + + if (dma_fence_is_signaled(fence)) + goto signaled; + + qxl_io_notify_oom(qdev); + + for (count = 0; count < 11; count++) { + if (!qxl_queue_garbage_collect(qdev, true)) + break; + + if (dma_fence_is_signaled(fence)) + goto signaled; + } + + if (dma_fence_is_signaled(fence)) + goto signaled; + + if (have_drawable_releases || sc < 4) { + if (sc > 2) + /* back off */ + usleep_range(500, 1000); + + if (time_after(jiffies, end)) + return 0; + + if (have_drawable_releases && sc > 300) { + DMA_FENCE_WARN(fence, + "failed to wait on release %llu after spincount %d\n", + fence->context & ~0xf0000000, sc); + goto signaled; + } + goto retry; + } + /* + * yeah, original sync_obj_wait gave up after 3 spins when + * have_drawable_releases is not set. + */ +signaled: cur = jiffies; if (time_after(cur, end)) return 0; diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h index 94947229888b..b7f22597ee95 100644 --- a/drivers/gpu/drm/radeon/pptable.h +++ b/drivers/gpu/drm/radeon/pptable.h @@ -424,7 +424,7 @@ typedef struct _ATOM_PPLIB_SUMO_CLOCK_INFO{ typedef struct _ATOM_PPLIB_STATE_V2 { //number of valid dpm levels in this state; Driver uses it to calculate the whole - //size of the state: sizeof(ATOM_PPLIB_STATE_V2) + (ucNumDPMLevels - 1) * sizeof(UCHAR) + //size of the state: struct_size(ATOM_PPLIB_STATE_V2, clockInfoIndex, ucNumDPMLevels) UCHAR ucNumDPMLevels; //a index to the array of nonClockInfos @@ -432,14 +432,14 @@ typedef struct _ATOM_PPLIB_STATE_V2 /** * Driver will read the first ucNumDPMLevels in this array */ - UCHAR clockInfoIndex[1]; + UCHAR clockInfoIndex[] __counted_by(ucNumDPMLevels); } ATOM_PPLIB_STATE_V2; typedef struct _StateArray{ //how many states we have UCHAR ucNumEntries; - ATOM_PPLIB_STATE_V2 states[1]; + ATOM_PPLIB_STATE_V2 states[] __counted_by(ucNumEntries); }StateArray; @@ -450,7 +450,7 @@ typedef struct _ClockInfoArray{ //sizeof(ATOM_PPLIB_CLOCK_INFO) UCHAR ucEntrySize; - UCHAR clockInfo[1]; + UCHAR clockInfo[] __counted_by(ucNumEntries); }ClockInfoArray; typedef struct _NonClockInfoArray{ @@ -460,7 +460,7 @@ typedef struct _NonClockInfoArray{ //sizeof(ATOM_PPLIB_NONCLOCK_INFO) UCHAR ucEntrySize; - ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[1]; + ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries); }NonClockInfoArray; typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index bb1f0a3371ab..10793a433bf5 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -923,8 +923,12 @@ bool radeon_get_atom_connector_info_from_supported_devices_table(struct max_device = ATOM_MAX_SUPPORTED_DEVICE_INFO; for (i = 0; i < max_device; i++) { - ATOM_CONNECTOR_INFO_I2C ci = - supported_devices->info.asConnInfo[i]; + ATOM_CONNECTOR_INFO_I2C ci; + + if (frev > 1) + ci = supported_devices->info_2d1.asConnInfo[i]; + else + ci = supported_devices->info.asConnInfo[i]; bios_connectors[i].valid = false; diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index 112438d965ff..6e1fd6985ffc 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -288,17 +288,23 @@ static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool, enum ttm_caching caching, unsigned int order) { - if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) + if (pool->use_dma_alloc) return &pool->caching[caching].orders[order]; #ifdef CONFIG_X86 switch (caching) { case ttm_write_combined: + if (pool->nid != NUMA_NO_NODE) + return &pool->caching[caching].orders[order]; + if (pool->use_dma32) return &global_dma32_write_combined[order]; return &global_write_combined[order]; case ttm_uncached: + if (pool->nid != NUMA_NO_NODE) + return &pool->caching[caching].orders[order]; + if (pool->use_dma32) return &global_dma32_uncached[order]; @@ -566,11 +572,17 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev, pool->use_dma_alloc = use_dma_alloc; pool->use_dma32 = use_dma32; - if (use_dma_alloc || nid != NUMA_NO_NODE) { - for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) - for (j = 0; j < NR_PAGE_ORDERS; ++j) - ttm_pool_type_init(&pool->caching[i].orders[j], - pool, i, j); + for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) { + for (j = 0; j < NR_PAGE_ORDERS; ++j) { + struct ttm_pool_type *pt; + + /* Initialize only pool types which are actually used */ + pt = ttm_pool_select_type(pool, i, j); + if (pt != &pool->caching[i].orders[j]) + continue; + + ttm_pool_type_init(pt, pool, i, j); + } } } EXPORT_SYMBOL(ttm_pool_init); @@ -599,10 +611,16 @@ void ttm_pool_fini(struct ttm_pool *pool) { unsigned int i, j; - if (pool->use_dma_alloc || pool->nid != NUMA_NO_NODE) { - for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) - for (j = 0; j < NR_PAGE_ORDERS; ++j) - ttm_pool_type_fini(&pool->caching[i].orders[j]); + for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) { + for (j = 0; j < NR_PAGE_ORDERS; ++j) { + struct ttm_pool_type *pt; + + pt = ttm_pool_select_type(pool, i, j); + if (pt != &pool->caching[i].orders[j]) + continue; + + ttm_pool_type_fini(pt); + } } /* We removed the pool types from the LRU, but we need to also make sure diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index 2e04f6cb661e..ce6b2fb341d1 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -105,7 +105,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->bin_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_BIN]; - file->enabled_ns[V3D_BIN] += local_clock() - file->start_ns[V3D_BIN]; file->jobs_sent[V3D_BIN]++; v3d->queue[V3D_BIN].jobs_sent++; @@ -126,7 +125,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->render_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_RENDER]; - file->enabled_ns[V3D_RENDER] += local_clock() - file->start_ns[V3D_RENDER]; file->jobs_sent[V3D_RENDER]++; v3d->queue[V3D_RENDER].jobs_sent++; @@ -147,7 +145,6 @@ v3d_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->csd_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_CSD]; - file->enabled_ns[V3D_CSD] += local_clock() - file->start_ns[V3D_CSD]; file->jobs_sent[V3D_CSD]++; v3d->queue[V3D_CSD].jobs_sent++; @@ -195,7 +192,6 @@ v3d_hub_irq(int irq, void *arg) struct v3d_file_priv *file = v3d->tfu_job->base.file->driver_priv; u64 runtime = local_clock() - file->start_ns[V3D_TFU]; - file->enabled_ns[V3D_TFU] += local_clock() - file->start_ns[V3D_TFU]; file->jobs_sent[V3D_TFU]++; v3d->queue[V3D_TFU].jobs_sent++; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c index c52c7bf1485b..717d624e9a05 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c @@ -456,8 +456,10 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, .no_wait_gpu = false }; u32 j, initial_line = dst_offset / dst_stride; - struct vmw_bo_blit_line_data d; + struct vmw_bo_blit_line_data d = {0}; int ret = 0; + struct page **dst_pages = NULL; + struct page **src_pages = NULL; /* Buffer objects need to be either pinned or reserved: */ if (!(dst->pin_count)) @@ -477,12 +479,35 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst, return ret; } + if (!src->ttm->pages && src->ttm->sg) { + src_pages = kvmalloc_array(src->ttm->num_pages, + sizeof(struct page *), GFP_KERNEL); + if (!src_pages) + return -ENOMEM; + ret = drm_prime_sg_to_page_array(src->ttm->sg, src_pages, + src->ttm->num_pages); + if (ret) + goto out; + } + if (!dst->ttm->pages && dst->ttm->sg) { + dst_pages = kvmalloc_array(dst->ttm->num_pages, + sizeof(struct page *), GFP_KERNEL); + if (!dst_pages) { + ret = -ENOMEM; + goto out; + } + ret = drm_prime_sg_to_page_array(dst->ttm->sg, dst_pages, + dst->ttm->num_pages); + if (ret) + goto out; + } + d.mapped_dst = 0; d.mapped_src = 0; d.dst_addr = NULL; d.src_addr = NULL; - d.dst_pages = dst->ttm->pages; - d.src_pages = src->ttm->pages; + d.dst_pages = dst->ttm->pages ? dst->ttm->pages : dst_pages; + d.src_pages = src->ttm->pages ? src->ttm->pages : src_pages; d.dst_num_pages = PFN_UP(dst->resource->size); d.src_num_pages = PFN_UP(src->resource->size); d.dst_prot = ttm_io_prot(dst, dst->resource, PAGE_KERNEL); @@ -504,6 +529,10 @@ out: kunmap_atomic(d.src_addr); if (d.dst_addr) kunmap_atomic(d.dst_addr); + if (src_pages) + kvfree(src_pages); + if (dst_pages) + kvfree(dst_pages); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index bfd41ce3c8f4..e5eb21a471a6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -377,7 +377,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv, { struct ttm_operation_ctx ctx = { .interruptible = params->bo_type != ttm_bo_type_kernel, - .no_wait_gpu = false + .no_wait_gpu = false, + .resv = params->resv, }; struct ttm_device *bdev = &dev_priv->bdev; struct drm_device *vdev = &dev_priv->drm; @@ -394,8 +395,8 @@ static int vmw_bo_init(struct vmw_private *dev_priv, vmw_bo_placement_set(vmw_bo, params->domain, params->busy_domain); ret = ttm_bo_init_reserved(bdev, &vmw_bo->tbo, params->bo_type, - &vmw_bo->placement, 0, &ctx, NULL, - NULL, destroy); + &vmw_bo->placement, 0, &ctx, + params->sg, params->resv, destroy); if (unlikely(ret)) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h index 0d496dc9c6af..f349642e6190 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h @@ -55,6 +55,8 @@ struct vmw_bo_params { enum ttm_bo_type bo_type; size_t size; bool pin; + struct dma_resv *resv; + struct sg_table *sg; }; /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index c7d90f96d16a..58fb40c93100 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -666,11 +666,12 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_map_populate] = "Caching DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; - /* TTM currently doesn't fully support SEV encryption. */ - if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) - return -EINVAL; - - if (vmw_force_coherent) + /* + * When running with SEV we always want dma mappings, because + * otherwise ttm tt pool pages will bounce through swiotlb running + * out of available space. + */ + if (vmw_force_coherent || cc_platform_has(CC_ATTR_MEM_ENCRYPT)) dev_priv->map_mode = vmw_dma_alloc_coherent; else if (vmw_restrict_iommu) dev_priv->map_mode = vmw_dma_map_bind; @@ -1627,6 +1628,7 @@ static const struct drm_driver driver = { .prime_fd_to_handle = vmw_prime_fd_to_handle, .prime_handle_to_fd = vmw_prime_handle_to_fd, + .gem_prime_import_sg_table = vmw_prime_import_sg_table, .fops = &vmwgfx_driver_fops, .name = VMWGFX_DRIVER_NAME, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 12efecc17df6..b019a1a1787a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1130,6 +1130,9 @@ extern int vmw_prime_handle_to_fd(struct drm_device *dev, struct drm_file *file_priv, uint32_t handle, uint32_t flags, int *prime_fd); +struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev, + struct dma_buf_attachment *attach, + struct sg_table *table); /* * MemoryOBject management - vmwgfx_mob.c diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index 12787bb9c111..d6bcaf078b1f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -149,6 +149,38 @@ out_no_bo: return ret; } +struct drm_gem_object *vmw_prime_import_sg_table(struct drm_device *dev, + struct dma_buf_attachment *attach, + struct sg_table *table) +{ + int ret; + struct vmw_private *dev_priv = vmw_priv(dev); + struct drm_gem_object *gem = NULL; + struct vmw_bo *vbo; + struct vmw_bo_params params = { + .domain = (dev_priv->has_mob) ? VMW_BO_DOMAIN_SYS : VMW_BO_DOMAIN_VRAM, + .busy_domain = VMW_BO_DOMAIN_SYS, + .bo_type = ttm_bo_type_sg, + .size = attach->dmabuf->size, + .pin = false, + .resv = attach->dmabuf->resv, + .sg = table, + + }; + + dma_resv_lock(params.resv, NULL); + + ret = vmw_bo_create(dev_priv, ¶ms, &vbo); + if (ret != 0) + goto out_no_bo; + + vbo->tbo.base.funcs = &vmw_gem_object_funcs; + + gem = &vbo->tbo.base; +out_no_bo: + dma_resv_unlock(params.resv); + return gem; +} int vmw_gem_object_create_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index cd4925346ed4..84ae4e10a2eb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -933,6 +933,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane, int vmw_du_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { + struct vmw_private *vmw = vmw_priv(crtc->dev); struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc); struct vmw_display_unit *du = vmw_crtc_to_du(new_state->crtc); @@ -940,9 +941,13 @@ int vmw_du_crtc_atomic_check(struct drm_crtc *crtc, bool has_primary = new_state->plane_mask & drm_plane_mask(crtc->primary); - /* We always want to have an active plane with an active CRTC */ - if (has_primary != new_state->enable) - return -EINVAL; + /* + * This is fine in general, but broken userspace might expect + * some actual rendering so give a clue as why it's blank. + */ + if (new_state->enable && !has_primary) + drm_dbg_driver(&vmw->drm, + "CRTC without a primary plane will be blank.\n"); if (new_state->connector_mask != connector_mask && diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index a94947b588e8..19a843da87b7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -243,10 +243,10 @@ struct vmw_framebuffer_bo { static const uint32_t __maybe_unused vmw_primary_plane_formats[] = { - DRM_FORMAT_XRGB1555, - DRM_FORMAT_RGB565, DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGB565, + DRM_FORMAT_XRGB1555, }; static const uint32_t __maybe_unused vmw_cursor_plane_formats[] = { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c index 2d72a5ee7c0c..c99cad444991 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c @@ -75,8 +75,12 @@ int vmw_prime_fd_to_handle(struct drm_device *dev, int fd, u32 *handle) { struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; + int ret = ttm_prime_fd_to_handle(tfile, fd, handle); - return ttm_prime_fd_to_handle(tfile, fd, handle); + if (ret) + ret = drm_gem_prime_fd_to_handle(dev, file_priv, fd, handle); + + return ret; } int vmw_prime_handle_to_fd(struct drm_device *dev, @@ -85,5 +89,12 @@ int vmw_prime_handle_to_fd(struct drm_device *dev, int *prime_fd) { struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile; - return ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd); + int ret; + + if (handle > VMWGFX_NUM_MOB) + ret = ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd); + else + ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd); + + return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 4d23d0a70bcb..621d98b376bb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -188,13 +188,18 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) switch (dev_priv->map_mode) { case vmw_dma_map_bind: case vmw_dma_map_populate: - vsgt->sgt = &vmw_tt->sgt; - ret = sg_alloc_table_from_pages_segment( - &vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0, - (unsigned long)vsgt->num_pages << PAGE_SHIFT, - dma_get_max_seg_size(dev_priv->drm.dev), GFP_KERNEL); - if (ret) - goto out_sg_alloc_fail; + if (vmw_tt->dma_ttm.page_flags & TTM_TT_FLAG_EXTERNAL) { + vsgt->sgt = vmw_tt->dma_ttm.sg; + } else { + vsgt->sgt = &vmw_tt->sgt; + ret = sg_alloc_table_from_pages_segment(&vmw_tt->sgt, + vsgt->pages, vsgt->num_pages, 0, + (unsigned long)vsgt->num_pages << PAGE_SHIFT, + dma_get_max_seg_size(dev_priv->drm.dev), + GFP_KERNEL); + if (ret) + goto out_sg_alloc_fail; + } ret = vmw_ttm_map_for_dma(vmw_tt); if (unlikely(ret != 0)) @@ -209,8 +214,9 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) return 0; out_map_fail: - sg_free_table(vmw_tt->vsgt.sgt); - vmw_tt->vsgt.sgt = NULL; + drm_warn(&dev_priv->drm, "VSG table map failed!"); + sg_free_table(vsgt->sgt); + vsgt->sgt = NULL; out_sg_alloc_fail: return ret; } @@ -356,15 +362,17 @@ static void vmw_ttm_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) static int vmw_ttm_populate(struct ttm_device *bdev, struct ttm_tt *ttm, struct ttm_operation_ctx *ctx) { - int ret; + bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0; - /* TODO: maybe completely drop this ? */ if (ttm_tt_is_populated(ttm)) return 0; - ret = ttm_pool_alloc(&bdev->pool, ttm, ctx); + if (external && ttm->sg) + return drm_prime_sg_to_dma_addr_array(ttm->sg, + ttm->dma_address, + ttm->num_pages); - return ret; + return ttm_pool_alloc(&bdev->pool, ttm, ctx); } static void vmw_ttm_unpopulate(struct ttm_device *bdev, @@ -372,6 +380,10 @@ static void vmw_ttm_unpopulate(struct ttm_device *bdev, { struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt, dma_ttm); + bool external = (ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0; + + if (external) + return; vmw_ttm_unbind(bdev, ttm); @@ -390,6 +402,7 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, { struct vmw_ttm_tt *vmw_be; int ret; + bool external = bo->type == ttm_bo_type_sg; vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL); if (!vmw_be) @@ -398,7 +411,10 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, vmw_be->dev_priv = vmw_priv_from_ttm(bo->bdev); vmw_be->mob = NULL; - if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent) + if (external) + page_flags |= TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE; + + if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent || external) ret = ttm_sg_tt_init(&vmw_be->dma_ttm, bo, page_flags, ttm_cached); else diff --git a/drivers/gpu/drm/xe/display/intel_fb_bo.c b/drivers/gpu/drm/xe/display/intel_fb_bo.c index b21da7b745a5..a9c1f9885c6b 100644 --- a/drivers/gpu/drm/xe/display/intel_fb_bo.c +++ b/drivers/gpu/drm/xe/display/intel_fb_bo.c @@ -31,7 +31,7 @@ int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb, ret = ttm_bo_reserve(&bo->ttm, true, false, NULL); if (ret) - return ret; + goto err; if (!(bo->flags & XE_BO_SCANOUT_BIT)) { /* @@ -42,12 +42,16 @@ int intel_fb_bo_framebuffer_init(struct intel_framebuffer *intel_fb, */ if (XE_IOCTL_DBG(i915, !list_empty(&bo->ttm.base.gpuva.list))) { ttm_bo_unreserve(&bo->ttm); - return -EINVAL; + ret = -EINVAL; + goto err; } bo->flags |= XE_BO_SCANOUT_BIT; } ttm_bo_unreserve(&bo->ttm); + return 0; +err: + xe_bo_put(bo); return ret; } diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index e4db069f0db3..6ec375c1c4b6 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -108,11 +108,6 @@ int xe_display_create(struct xe_device *xe) xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0); drmm_mutex_init(&xe->drm, &xe->sb_lock); - drmm_mutex_init(&xe->drm, &xe->display.backlight.lock); - drmm_mutex_init(&xe->drm, &xe->display.audio.mutex); - drmm_mutex_init(&xe->drm, &xe->display.wm.wm_mutex); - drmm_mutex_init(&xe->drm, &xe->display.pps.mutex); - drmm_mutex_init(&xe->drm, &xe->display.hdcp.hdcp_mutex); xe->enabled_irq_mask = ~0; err = drmm_add_action_or_reset(&xe->drm, display_destroy, NULL); diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h index 0b1266c88a6a..deddc8be48c0 100644 --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h @@ -125,7 +125,7 @@ #define RING_EXECLIST_STATUS_LO(base) XE_REG((base) + 0x234) #define RING_EXECLIST_STATUS_HI(base) XE_REG((base) + 0x234 + 4) -#define RING_CONTEXT_CONTROL(base) XE_REG((base) + 0x244) +#define RING_CONTEXT_CONTROL(base) XE_REG((base) + 0x244, XE_REG_OPTION_MASKED) #define CTX_CTRL_INHIBIT_SYN_CTX_SWITCH REG_BIT(3) #define CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT REG_BIT(0) diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index b82233a41606..9ac7fbe201b3 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -290,7 +290,7 @@ xe_hwmon_power1_max_interval_show(struct device *dev, struct device_attribute *a * As y can be < 2, we compute tau4 = (4 | x) << y * and then add 2 when doing the final right shift to account for units */ - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; /* val in hwmon interface units (millisec) */ out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); @@ -330,7 +330,7 @@ xe_hwmon_power1_max_interval_store(struct device *dev, struct device_attribute * r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT); x = REG_FIELD_GET(PKG_MAX_WIN_X, r); y = REG_FIELD_GET(PKG_MAX_WIN_Y, r); - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); if (val > max_win) diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 1426febe86eb..57066faf575e 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -525,9 +525,8 @@ static const u8 *reg_offsets(struct xe_device *xe, enum xe_engine_class class) static void set_context_control(u32 *regs, struct xe_hw_engine *hwe) { - regs[CTX_CONTEXT_CONTROL] = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH) | - _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) | - CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT; + regs[CTX_CONTEXT_CONTROL] = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH | + CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT); /* TODO: Timestamp */ } diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index ee1bb938c493..2ba4fb9511f6 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -227,7 +227,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, if (vm->flags & XE_VM_FLAG_64K && level == 1) flags = XE_PDE_64K; - entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (level - 1) * + entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (u64)(level - 1) * XE_PAGE_SIZE, pat_index); xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE * level, u64, entry | flags); @@ -235,7 +235,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, /* Write PDE's that point to our BO. */ for (i = 0; i < num_entries - num_level; i++) { - entry = vm->pt_ops->pde_encode_bo(bo, i * XE_PAGE_SIZE, + entry = vm->pt_ops->pde_encode_bo(bo, (u64)i * XE_PAGE_SIZE, pat_index); xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE + @@ -291,7 +291,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m, #define VM_SA_UPDATE_UNIT_SIZE (XE_PAGE_SIZE / NUM_VMUSA_UNIT_PER_PAGE) #define NUM_VMUSA_WRITES_PER_UNIT (VM_SA_UPDATE_UNIT_SIZE / sizeof(u64)) drm_suballoc_manager_init(&m->vm_update_sa, - (map_ofs / XE_PAGE_SIZE - NUM_KERNEL_PDE) * + (size_t)(map_ofs / XE_PAGE_SIZE - NUM_KERNEL_PDE) * NUM_VMUSA_UNIT_PER_PAGE, 0); m->pt_bo = bo; @@ -490,7 +490,7 @@ static void emit_pte(struct xe_migrate *m, struct xe_vm *vm = m->q->vm; u16 pat_index; u32 ptes; - u64 ofs = at_pt * XE_PAGE_SIZE; + u64 ofs = (u64)at_pt * XE_PAGE_SIZE; u64 cur_ofs; /* Indirect access needs compression enabled uncached PAT index */ diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 62d1ef8867a8..3d4c8f342e21 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1577,6 +1577,16 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe->usm.num_vm_in_fault_mode--; else if (!(vm->flags & XE_VM_FLAG_MIGRATION)) xe->usm.num_vm_in_non_fault_mode--; + + if (vm->usm.asid) { + void *lookup; + + xe_assert(xe, xe->info.has_asid); + xe_assert(xe, !(vm->flags & XE_VM_FLAG_MIGRATION)); + + lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid); + xe_assert(xe, lookup == vm); + } mutex_unlock(&xe->usm.lock); for_each_tile(tile, xe, id) @@ -1592,24 +1602,15 @@ static void vm_destroy_work_func(struct work_struct *w) struct xe_device *xe = vm->xe; struct xe_tile *tile; u8 id; - void *lookup; /* xe_vm_close_and_put was not called? */ xe_assert(xe, !vm->size); mutex_destroy(&vm->snap_mutex); - if (!(vm->flags & XE_VM_FLAG_MIGRATION)) { + if (!(vm->flags & XE_VM_FLAG_MIGRATION)) xe_device_mem_access_put(xe); - if (xe->info.has_asid && vm->usm.asid) { - mutex_lock(&xe->usm.lock); - lookup = xa_erase(&xe->usm.asid_to_vm, vm->usm.asid); - xe_assert(xe, lookup == vm); - mutex_unlock(&xe->usm.lock); - } - } - for_each_tile(tile, xe, id) XE_WARN_ON(vm->pt_root[id]); diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 783975d1384f..7c52757a89db 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -351,11 +351,6 @@ static int host1x_device_uevent(const struct device *dev, return 0; } -static int host1x_dma_configure(struct device *dev) -{ - return of_dma_configure(dev, dev->of_node, true); -} - static const struct dev_pm_ops host1x_device_pm_ops = { .suspend = pm_generic_suspend, .resume = pm_generic_resume, @@ -369,7 +364,6 @@ const struct bus_type host1x_bus_type = { .name = "host1x", .match = host1x_device_match, .uevent = host1x_device_uevent, - .dma_configure = host1x_dma_configure, .pm = &host1x_device_pm_ops, }; @@ -458,8 +452,6 @@ static int host1x_device_add(struct host1x *host1x, device->dev.bus = &host1x_bus_type; device->dev.parent = host1x->dev; - of_dma_configure(&device->dev, host1x->dev->of_node, true); - device->dev.dma_parms = &device->dma_parms; dma_set_max_seg_size(&device->dev, UINT_MAX); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index e6a8b6d8eab7..3c3c497b6b91 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 f9cceaeffd08..da5ea5a23b08 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 ab5953fc2436..80e0f23c1c33 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 2df1ab3c31cc..d965382196c6 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 a49c6affd7c4..dd5fc60874ba 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/hv/channel.c b/drivers/hv/channel.c index adbf674355b2..fb8cd8469328 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -153,7 +153,9 @@ void vmbus_free_ring(struct vmbus_channel *channel) hv_ringbuffer_cleanup(&channel->inbound); if (channel->ringbuffer_page) { - __free_pages(channel->ringbuffer_page, + /* In a CoCo VM leak the memory if it didn't get re-encrypted */ + if (!channel->ringbuffer_gpadlhandle.decrypted) + __free_pages(channel->ringbuffer_page, get_order(channel->ringbuffer_pagecount << PAGE_SHIFT)); channel->ringbuffer_page = NULL; @@ -436,9 +438,18 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel, (atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1); ret = create_gpadl_header(type, kbuffer, size, send_offset, &msginfo); - if (ret) + if (ret) { + gpadl->decrypted = false; return ret; + } + /* + * Set the "decrypted" flag to true for the set_memory_decrypted() + * success case. In the failure case, the encryption state of the + * memory is unknown. Leave "decrypted" as true to ensure the + * memory will be leaked instead of going back on the free list. + */ + gpadl->decrypted = true; ret = set_memory_decrypted((unsigned long)kbuffer, PFN_UP(size)); if (ret) { @@ -527,9 +538,15 @@ cleanup: kfree(msginfo); - if (ret) - set_memory_encrypted((unsigned long)kbuffer, - PFN_UP(size)); + if (ret) { + /* + * If set_memory_encrypted() fails, the decrypted flag is + * left as true so the memory is leaked instead of being + * put back on the free list. + */ + if (!set_memory_encrypted((unsigned long)kbuffer, PFN_UP(size))) + gpadl->decrypted = false; + } return ret; } @@ -850,6 +867,8 @@ post_msg_err: if (ret) pr_warn("Fail to set mem host visibility in GPADL teardown %d.\n", ret); + gpadl->decrypted = ret; + return ret; } EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl); diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 3cabeeabb1ca..f001ae880e1d 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -237,8 +237,17 @@ int vmbus_connect(void) vmbus_connection.monitor_pages[0], 1); ret |= set_memory_decrypted((unsigned long) vmbus_connection.monitor_pages[1], 1); - if (ret) + if (ret) { + /* + * If set_memory_decrypted() fails, the encryption state + * of the memory is unknown. So leak the memory instead + * of risking returning decrypted memory to the free list. + * For simplicity, always handle both pages the same. + */ + vmbus_connection.monitor_pages[0] = NULL; + vmbus_connection.monitor_pages[1] = NULL; goto cleanup; + } /* * Set_memory_decrypted() will change the memory contents if @@ -337,13 +346,19 @@ void vmbus_disconnect(void) vmbus_connection.int_page = NULL; } - set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[0], 1); - set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[1], 1); + if (vmbus_connection.monitor_pages[0]) { + if (!set_memory_encrypted( + (unsigned long)vmbus_connection.monitor_pages[0], 1)) + hv_free_hyperv_page(vmbus_connection.monitor_pages[0]); + vmbus_connection.monitor_pages[0] = NULL; + } - hv_free_hyperv_page(vmbus_connection.monitor_pages[0]); - hv_free_hyperv_page(vmbus_connection.monitor_pages[1]); - vmbus_connection.monitor_pages[0] = NULL; - vmbus_connection.monitor_pages[1] = NULL; + if (vmbus_connection.monitor_pages[1]) { + if (!set_memory_encrypted( + (unsigned long)vmbus_connection.monitor_pages[1], 1)) + hv_free_hyperv_page(vmbus_connection.monitor_pages[1]); + vmbus_connection.monitor_pages[1] = NULL; + } } /* diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 4cb17603a828..12a707ab73f8 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -131,7 +131,7 @@ static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", hv_dev->channel->offermsg.child_relid); + return sysfs_emit(buf, "%d\n", hv_dev->channel->offermsg.child_relid); } static DEVICE_ATTR_RO(id); @@ -142,7 +142,7 @@ static ssize_t state_show(struct device *dev, struct device_attribute *dev_attr, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", hv_dev->channel->state); + return sysfs_emit(buf, "%d\n", hv_dev->channel->state); } static DEVICE_ATTR_RO(state); @@ -153,7 +153,7 @@ static ssize_t monitor_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", hv_dev->channel->offermsg.monitorid); + return sysfs_emit(buf, "%d\n", hv_dev->channel->offermsg.monitorid); } static DEVICE_ATTR_RO(monitor_id); @@ -164,8 +164,8 @@ static ssize_t class_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "{%pUl}\n", - &hv_dev->channel->offermsg.offer.if_type); + return sysfs_emit(buf, "{%pUl}\n", + &hv_dev->channel->offermsg.offer.if_type); } static DEVICE_ATTR_RO(class_id); @@ -176,8 +176,8 @@ static ssize_t device_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "{%pUl}\n", - &hv_dev->channel->offermsg.offer.if_instance); + return sysfs_emit(buf, "{%pUl}\n", + &hv_dev->channel->offermsg.offer.if_instance); } static DEVICE_ATTR_RO(device_id); @@ -186,7 +186,7 @@ static ssize_t modalias_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); - return sprintf(buf, "vmbus:%*phN\n", UUID_SIZE, &hv_dev->dev_type); + return sysfs_emit(buf, "vmbus:%*phN\n", UUID_SIZE, &hv_dev->dev_type); } static DEVICE_ATTR_RO(modalias); @@ -199,7 +199,7 @@ static ssize_t numa_node_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", cpu_to_node(hv_dev->channel->target_cpu)); + return sysfs_emit(buf, "%d\n", cpu_to_node(hv_dev->channel->target_cpu)); } static DEVICE_ATTR_RO(numa_node); #endif @@ -212,9 +212,8 @@ static ssize_t server_monitor_pending_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_pending(hv_dev->channel, - vmbus_connection.monitor_pages[0])); + return sysfs_emit(buf, "%d\n", channel_pending(hv_dev->channel, + vmbus_connection.monitor_pages[0])); } static DEVICE_ATTR_RO(server_monitor_pending); @@ -226,9 +225,8 @@ static ssize_t client_monitor_pending_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_pending(hv_dev->channel, - vmbus_connection.monitor_pages[1])); + return sysfs_emit(buf, "%d\n", channel_pending(hv_dev->channel, + vmbus_connection.monitor_pages[1])); } static DEVICE_ATTR_RO(client_monitor_pending); @@ -240,9 +238,8 @@ static ssize_t server_monitor_latency_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_latency(hv_dev->channel, - vmbus_connection.monitor_pages[0])); + return sysfs_emit(buf, "%d\n", channel_latency(hv_dev->channel, + vmbus_connection.monitor_pages[0])); } static DEVICE_ATTR_RO(server_monitor_latency); @@ -254,9 +251,8 @@ static ssize_t client_monitor_latency_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_latency(hv_dev->channel, - vmbus_connection.monitor_pages[1])); + return sysfs_emit(buf, "%d\n", channel_latency(hv_dev->channel, + vmbus_connection.monitor_pages[1])); } static DEVICE_ATTR_RO(client_monitor_latency); @@ -268,9 +264,8 @@ static ssize_t server_monitor_conn_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_conn_id(hv_dev->channel, - vmbus_connection.monitor_pages[0])); + return sysfs_emit(buf, "%d\n", channel_conn_id(hv_dev->channel, + vmbus_connection.monitor_pages[0])); } static DEVICE_ATTR_RO(server_monitor_conn_id); @@ -282,9 +277,8 @@ static ssize_t client_monitor_conn_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_conn_id(hv_dev->channel, - vmbus_connection.monitor_pages[1])); + return sysfs_emit(buf, "%d\n", channel_conn_id(hv_dev->channel, + vmbus_connection.monitor_pages[1])); } static DEVICE_ATTR_RO(client_monitor_conn_id); @@ -303,7 +297,7 @@ static ssize_t out_intr_mask_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.current_interrupt_mask); + return sysfs_emit(buf, "%d\n", outbound.current_interrupt_mask); } static DEVICE_ATTR_RO(out_intr_mask); @@ -321,7 +315,7 @@ static ssize_t out_read_index_show(struct device *dev, &outbound); if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.current_read_index); + return sysfs_emit(buf, "%d\n", outbound.current_read_index); } static DEVICE_ATTR_RO(out_read_index); @@ -340,7 +334,7 @@ static ssize_t out_write_index_show(struct device *dev, &outbound); if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.current_write_index); + return sysfs_emit(buf, "%d\n", outbound.current_write_index); } static DEVICE_ATTR_RO(out_write_index); @@ -359,7 +353,7 @@ static ssize_t out_read_bytes_avail_show(struct device *dev, &outbound); if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.bytes_avail_toread); + return sysfs_emit(buf, "%d\n", outbound.bytes_avail_toread); } static DEVICE_ATTR_RO(out_read_bytes_avail); @@ -378,7 +372,7 @@ static ssize_t out_write_bytes_avail_show(struct device *dev, &outbound); if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.bytes_avail_towrite); + return sysfs_emit(buf, "%d\n", outbound.bytes_avail_towrite); } static DEVICE_ATTR_RO(out_write_bytes_avail); @@ -396,7 +390,7 @@ static ssize_t in_intr_mask_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.current_interrupt_mask); + return sysfs_emit(buf, "%d\n", inbound.current_interrupt_mask); } static DEVICE_ATTR_RO(in_intr_mask); @@ -414,7 +408,7 @@ static ssize_t in_read_index_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.current_read_index); + return sysfs_emit(buf, "%d\n", inbound.current_read_index); } static DEVICE_ATTR_RO(in_read_index); @@ -432,7 +426,7 @@ static ssize_t in_write_index_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.current_write_index); + return sysfs_emit(buf, "%d\n", inbound.current_write_index); } static DEVICE_ATTR_RO(in_write_index); @@ -451,7 +445,7 @@ static ssize_t in_read_bytes_avail_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.bytes_avail_toread); + return sysfs_emit(buf, "%d\n", inbound.bytes_avail_toread); } static DEVICE_ATTR_RO(in_read_bytes_avail); @@ -470,7 +464,7 @@ static ssize_t in_write_bytes_avail_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.bytes_avail_towrite); + return sysfs_emit(buf, "%d\n", inbound.bytes_avail_towrite); } static DEVICE_ATTR_RO(in_write_bytes_avail); @@ -480,7 +474,7 @@ static ssize_t channel_vp_mapping_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct vmbus_channel *channel = hv_dev->channel, *cur_sc; - int buf_size = PAGE_SIZE, n_written, tot_written; + int n_written; struct list_head *cur; if (!channel) @@ -488,25 +482,21 @@ static ssize_t channel_vp_mapping_show(struct device *dev, mutex_lock(&vmbus_connection.channel_mutex); - tot_written = snprintf(buf, buf_size, "%u:%u\n", - channel->offermsg.child_relid, channel->target_cpu); + n_written = sysfs_emit(buf, "%u:%u\n", + channel->offermsg.child_relid, + channel->target_cpu); list_for_each(cur, &channel->sc_list) { - if (tot_written >= buf_size - 1) - break; cur_sc = list_entry(cur, struct vmbus_channel, sc_list); - n_written = scnprintf(buf + tot_written, - buf_size - tot_written, - "%u:%u\n", - cur_sc->offermsg.child_relid, - cur_sc->target_cpu); - tot_written += n_written; + n_written += sysfs_emit_at(buf, n_written, "%u:%u\n", + cur_sc->offermsg.child_relid, + cur_sc->target_cpu); } mutex_unlock(&vmbus_connection.channel_mutex); - return tot_written; + return n_written; } static DEVICE_ATTR_RO(channel_vp_mapping); @@ -516,7 +506,7 @@ static ssize_t vendor_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); - return sprintf(buf, "0x%x\n", hv_dev->vendor_id); + return sysfs_emit(buf, "0x%x\n", hv_dev->vendor_id); } static DEVICE_ATTR_RO(vendor); @@ -526,7 +516,7 @@ static ssize_t device_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); - return sprintf(buf, "0x%x\n", hv_dev->device_id); + return sysfs_emit(buf, "0x%x\n", hv_dev->device_id); } static DEVICE_ATTR_RO(device); @@ -551,7 +541,7 @@ static ssize_t driver_override_show(struct device *dev, ssize_t len; device_lock(dev); - len = snprintf(buf, PAGE_SIZE, "%s\n", hv_dev->driver_override); + len = sysfs_emit(buf, "%s\n", hv_dev->driver_override); device_unlock(dev); return len; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index bf0df6ee4f78..07fb8d3c037f 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -1026,23 +1026,26 @@ static void cm_reset_to_idle(struct cm_id_private *cm_id_priv) } } -static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id) +static noinline void cm_destroy_id_wait_timeout(struct ib_cm_id *cm_id, + enum ib_cm_state old_state) { struct cm_id_private *cm_id_priv; cm_id_priv = container_of(cm_id, struct cm_id_private, id); - pr_err("%s: cm_id=%p timed out. state=%d refcnt=%d\n", __func__, - cm_id, cm_id->state, refcount_read(&cm_id_priv->refcount)); + pr_err("%s: cm_id=%p timed out. state %d -> %d, refcnt=%d\n", __func__, + cm_id, old_state, cm_id->state, refcount_read(&cm_id_priv->refcount)); } static void cm_destroy_id(struct ib_cm_id *cm_id, int err) { struct cm_id_private *cm_id_priv; + enum ib_cm_state old_state; struct cm_work *work; int ret; cm_id_priv = container_of(cm_id, struct cm_id_private, id); spin_lock_irq(&cm_id_priv->lock); + old_state = cm_id->state; retest: switch (cm_id->state) { case IB_CM_LISTEN: @@ -1151,7 +1154,7 @@ retest: msecs_to_jiffies( CM_DESTROY_ID_WAIT_TIMEOUT)); if (!ret) /* timeout happened */ - cm_destroy_id_wait_timeout(cm_id); + cm_destroy_id_wait_timeout(cm_id, old_state); } while (!ret); while ((work = cm_dequeue_work(cm_id_priv)) != NULL) diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 0c3c4e64812c..3e43687a7f6f 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -188,7 +188,8 @@ static int process_pma_cmd(struct mlx5_ib_dev *dev, u32 port_num, mdev = dev->mdev; mdev_port_num = 1; } - if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1) { + if (MLX5_CAP_GEN(dev->mdev, num_ports) == 1 && + !mlx5_core_mp_enabled(mdev)) { /* set local port to one for Function-Per-Port HCA. */ mdev = dev->mdev; mdev_port_num = 1; diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index ae466e72fc43..255677bc12b2 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -33,6 +33,8 @@ void rxe_dealloc(struct ib_device *ib_dev) if (rxe->tfm) crypto_free_shash(rxe->tfm); + + mutex_destroy(&rxe->usdev_lock); } /* initialize rxe device parameters */ diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 5d1010cafed8..7e9b996b47c8 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -176,6 +176,8 @@ static struct icc_path *path_init(struct device *dev, struct icc_node *dst, path->num_nodes = num_nodes; + mutex_lock(&icc_bw_lock); + for (i = num_nodes - 1; i >= 0; i--) { node->provider->users++; hlist_add_head(&path->reqs[i].req_node, &node->req_list); @@ -186,6 +188,8 @@ static struct icc_path *path_init(struct device *dev, struct icc_node *dst, node = node->reverse; } + mutex_unlock(&icc_bw_lock); + return path; } @@ -792,12 +796,16 @@ void icc_put(struct icc_path *path) pr_err("%s: error (%d)\n", __func__, ret); mutex_lock(&icc_lock); + mutex_lock(&icc_bw_lock); + for (i = 0; i < path->num_nodes; i++) { node = path->reqs[i].node; hlist_del(&path->reqs[i].req_node); if (!WARN_ON(!node->provider->users)) node->provider->users--; } + + mutex_unlock(&icc_bw_lock); mutex_unlock(&icc_lock); kfree_const(path->name); diff --git a/drivers/interconnect/qcom/x1e80100.c b/drivers/interconnect/qcom/x1e80100.c index 99824675ee3f..654abb9ce08e 100644 --- a/drivers/interconnect/qcom/x1e80100.c +++ b/drivers/interconnect/qcom/x1e80100.c @@ -116,15 +116,6 @@ static struct qcom_icc_node xm_sdc2 = { .links = { X1E80100_SLAVE_A2NOC_SNOC }, }; -static struct qcom_icc_node ddr_perf_mode_master = { - .name = "ddr_perf_mode_master", - .id = X1E80100_MASTER_DDR_PERF_MODE, - .channels = 1, - .buswidth = 4, - .num_links = 1, - .links = { X1E80100_SLAVE_DDR_PERF_MODE }, -}; - static struct qcom_icc_node qup0_core_master = { .name = "qup0_core_master", .id = X1E80100_MASTER_QUP_CORE_0, @@ -688,14 +679,6 @@ static struct qcom_icc_node qns_a2noc_snoc = { .links = { X1E80100_MASTER_A2NOC_SNOC }, }; -static struct qcom_icc_node ddr_perf_mode_slave = { - .name = "ddr_perf_mode_slave", - .id = X1E80100_SLAVE_DDR_PERF_MODE, - .channels = 1, - .buswidth = 4, - .num_links = 0, -}; - static struct qcom_icc_node qup0_core_slave = { .name = "qup0_core_slave", .id = X1E80100_SLAVE_QUP_CORE_0, @@ -1377,12 +1360,6 @@ static struct qcom_icc_bcm bcm_acv = { .nodes = { &ebi }, }; -static struct qcom_icc_bcm bcm_acv_perf = { - .name = "ACV_PERF", - .num_nodes = 1, - .nodes = { &ddr_perf_mode_slave }, -}; - static struct qcom_icc_bcm bcm_ce0 = { .name = "CE0", .num_nodes = 1, @@ -1583,18 +1560,15 @@ static const struct qcom_icc_desc x1e80100_aggre2_noc = { }; static struct qcom_icc_bcm * const clk_virt_bcms[] = { - &bcm_acv_perf, &bcm_qup0, &bcm_qup1, &bcm_qup2, }; static struct qcom_icc_node * const clk_virt_nodes[] = { - [MASTER_DDR_PERF_MODE] = &ddr_perf_mode_master, [MASTER_QUP_CORE_0] = &qup0_core_master, [MASTER_QUP_CORE_1] = &qup1_core_master, [MASTER_QUP_CORE_2] = &qup2_core_master, - [SLAVE_DDR_PERF_MODE] = &ddr_perf_mode_slave, [SLAVE_QUP_CORE_0] = &qup0_core_slave, [SLAVE_QUP_CORE_1] = &qup1_core_slave, [SLAVE_QUP_CORE_2] = &qup2_core_slave, diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 33228c1c8980..ac6754a85f35 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3232,28 +3232,29 @@ static void iommu_snp_enable(void) return; /* * The SNP support requires that IOMMU must be enabled, and is - * not configured in the passthrough mode. + * configured with V1 page table (DTE[Mode] = 0 is not supported). */ if (no_iommu || iommu_default_passthrough()) { - pr_err("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n"); - cc_platform_clear(CC_ATTR_HOST_SEV_SNP); - return; + pr_warn("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n"); + goto disable_snp; + } + + if (amd_iommu_pgtable != AMD_IOMMU_V1) { + pr_warn("SNP: IOMMU is configured with V2 page table mode, SNP cannot be supported.\n"); + goto disable_snp; } amd_iommu_snp_en = check_feature(FEATURE_SNP); if (!amd_iommu_snp_en) { - pr_err("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n"); - cc_platform_clear(CC_ATTR_HOST_SEV_SNP); - return; + pr_warn("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n"); + goto disable_snp; } pr_info("IOMMU SNP support enabled.\n"); + return; - /* Enforce IOMMU v1 pagetable when SNP is enabled. */ - if (amd_iommu_pgtable != AMD_IOMMU_V1) { - pr_warn("Forcing use of AMD IOMMU v1 page table due to SNP.\n"); - amd_iommu_pgtable = AMD_IOMMU_V1; - } +disable_snp: + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); #endif } diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index d35c1b8c8e65..e692217fcb28 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1692,26 +1692,29 @@ int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid, static u16 domain_id_alloc(void) { + unsigned long flags; int id; - spin_lock(&pd_bitmap_lock); + spin_lock_irqsave(&pd_bitmap_lock, flags); id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID); BUG_ON(id == 0); if (id > 0 && id < MAX_DOMAIN_ID) __set_bit(id, amd_iommu_pd_alloc_bitmap); else id = 0; - spin_unlock(&pd_bitmap_lock); + spin_unlock_irqrestore(&pd_bitmap_lock, flags); return id; } static void domain_id_free(int id) { - spin_lock(&pd_bitmap_lock); + unsigned long flags; + + spin_lock_irqsave(&pd_bitmap_lock, flags); if (id > 0 && id < MAX_DOMAIN_ID) __clear_bit(id, amd_iommu_pd_alloc_bitmap); - spin_unlock(&pd_bitmap_lock); + spin_unlock_irqrestore(&pd_bitmap_lock, flags); } static void free_gcr3_tbl_level1(u64 *tbl) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 50eb9aed47cc..a7ecd90303dc 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4299,9 +4299,11 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) } dev_iommu_priv_set(dev, info); - ret = device_rbtree_insert(iommu, info); - if (ret) - goto free; + if (pdev && pci_ats_supported(pdev)) { + ret = device_rbtree_insert(iommu, info); + if (ret) + goto free; + } if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) { ret = intel_pasid_alloc_table(dev); @@ -4336,7 +4338,8 @@ static void intel_iommu_release_device(struct device *dev) struct intel_iommu *iommu = info->iommu; mutex_lock(&iommu->iopf_lock); - device_rbtree_remove(info); + if (dev_is_pci(dev) && pci_ats_supported(to_pci_dev(dev))) + device_rbtree_remove(info); mutex_unlock(&iommu->iopf_lock); if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev) && diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c index cf43e798eca4..44083d01852d 100644 --- a/drivers/iommu/intel/perfmon.c +++ b/drivers/iommu/intel/perfmon.c @@ -438,7 +438,7 @@ static int iommu_pmu_assign_event(struct iommu_pmu *iommu_pmu, iommu_pmu_set_filter(domain, event->attr.config1, IOMMU_PMU_FILTER_DOMAIN, idx, event->attr.config1); - iommu_pmu_set_filter(pasid, event->attr.config1, + iommu_pmu_set_filter(pasid, event->attr.config2, IOMMU_PMU_FILTER_PASID, idx, event->attr.config1); iommu_pmu_set_filter(ats, event->attr.config2, diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index c1bed89b1026..ee3b469e2da1 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -66,7 +66,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu) struct page *pages; int irq, ret; - pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, PRQ_ORDER); + pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO, PRQ_ORDER); if (!pages) { pr_warn("IOMMU: %s: Failed to allocate page request queue\n", iommu->name); diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig index 99d4b075df49..76656fe0470d 100644 --- a/drivers/iommu/iommufd/Kconfig +++ b/drivers/iommu/iommufd/Kconfig @@ -37,6 +37,7 @@ config IOMMUFD_TEST depends on DEBUG_KERNEL depends on FAULT_INJECTION depends on RUNTIME_TESTING_MENU + select IOMMUFD_DRIVER default n help This is dangerous, do not enable unless running diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index b8c47f18bc26..6a2707fe7a78 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -1790,6 +1790,7 @@ static const struct of_device_id mtk_iommu_of_ids[] = { { .compatible = "mediatek,mt8365-m4u", .data = &mt8365_data}, {} }; +MODULE_DEVICE_TABLE(of, mtk_iommu_of_ids); static struct platform_driver mtk_iommu_driver = { .probe = mtk_iommu_probe, diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index a9fa2a54dc9b..d6e4002200bd 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -600,6 +600,7 @@ static const struct of_device_id mtk_iommu_v1_of_ids[] = { { .compatible = "mediatek,mt2701-m4u", }, {} }; +MODULE_DEVICE_TABLE(of, mtk_iommu_v1_of_ids); static const struct component_master_ops mtk_iommu_v1_com_ops = { .bind = mtk_iommu_v1_bind, diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index fca888b36680..2a537cbfcb07 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -786,6 +786,7 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, struct its_cmd_block *cmd, struct its_cmd_desc *desc) { + struct its_vpe *vpe = valid_vpe(its, desc->its_vmapp_cmd.vpe); unsigned long vpt_addr, vconf_addr; u64 target; bool alloc; @@ -798,6 +799,11 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, if (is_v4_1(its)) { alloc = !atomic_dec_return(&desc->its_vmapp_cmd.vpe->vmapp_count); its_encode_alloc(cmd, alloc); + /* + * Unmapping a VPE is self-synchronizing on GICv4.1, + * no need to issue a VSYNC. + */ + vpe = NULL; } goto out; @@ -832,7 +838,7 @@ static struct its_vpe *its_build_vmapp_cmd(struct its_node *its, out: its_fixup_cmd(cmd); - return valid_vpe(its, desc->its_vmapp_cmd.vpe); + return vpe; } static struct its_vpe *its_build_vmapti_cmd(struct its_node *its, diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index 2776ca5fc33f..b215b28cad7b 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -401,23 +401,23 @@ data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } static int data_sock_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int len) + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0, opt = 0; if (*debug & DEBUG_SOCKET) printk(KERN_DEBUG "%s(%p, %d, %x, optval, %d)\n", __func__, sock, - level, optname, len); + level, optname, optlen); lock_sock(sk); switch (optname) { case MISDN_TIME_STAMP: - if (copy_from_sockptr(&opt, optval, sizeof(int))) { - err = -EFAULT; + err = copy_safe_from_sockptr(&opt, sizeof(opt), + optval, optlen); + if (err) break; - } if (opt) _pms(sk)->cmask |= MISDN_TIME_STAMP; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index be8ac24f50b6..7b8a71ca66dd 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1558,7 +1558,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, for (j = 0; j < i; j++) if (r1_bio->bios[j]) rdev_dec_pending(conf->mirrors[j].rdev, mddev); - free_r1bio(r1_bio); + mempool_free(r1_bio, &conf->r1bio_pool); allow_barrier(conf, bio->bi_iter.bi_sector); if (bio->bi_opf & REQ_NOWAIT) { diff --git a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c index 4c34344dc7dc..d7027d600208 100644 --- a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c +++ b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c @@ -50,12 +50,12 @@ static void mtk_vcodec_vpu_reset_dec_handler(void *priv) dev_err(&dev->plat_dev->dev, "Watchdog timeout!!"); - mutex_lock(&dev->dev_mutex); + mutex_lock(&dev->dev_ctx_lock); list_for_each_entry(ctx, &dev->ctx_list, list) { ctx->state = MTK_STATE_ABORT; mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id); } - mutex_unlock(&dev->dev_mutex); + mutex_unlock(&dev->dev_ctx_lock); } static void mtk_vcodec_vpu_reset_enc_handler(void *priv) @@ -65,12 +65,12 @@ static void mtk_vcodec_vpu_reset_enc_handler(void *priv) dev_err(&dev->plat_dev->dev, "Watchdog timeout!!"); - mutex_lock(&dev->dev_mutex); + mutex_lock(&dev->dev_ctx_lock); list_for_each_entry(ctx, &dev->ctx_list, list) { ctx->state = MTK_STATE_ABORT; mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id); } - mutex_unlock(&dev->dev_mutex); + mutex_unlock(&dev->dev_ctx_lock); } static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = { diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c index f47c98faf068..2073781ccadb 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c @@ -268,7 +268,9 @@ static int fops_vcodec_open(struct file *file) ctx->dev->vdec_pdata->init_vdec_params(ctx); + mutex_lock(&dev->dev_ctx_lock); list_add(&ctx->list, &dev->ctx_list); + mutex_unlock(&dev->dev_ctx_lock); mtk_vcodec_dbgfs_create(ctx); mutex_unlock(&dev->dev_mutex); @@ -311,7 +313,9 @@ static int fops_vcodec_release(struct file *file) v4l2_ctrl_handler_free(&ctx->ctrl_hdl); mtk_vcodec_dbgfs_remove(dev, ctx->id); + mutex_lock(&dev->dev_ctx_lock); list_del_init(&ctx->list); + mutex_unlock(&dev->dev_ctx_lock); kfree(ctx); mutex_unlock(&dev->dev_mutex); return 0; @@ -404,6 +408,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) for (i = 0; i < MTK_VDEC_HW_MAX; i++) mutex_init(&dev->dec_mutex[i]); mutex_init(&dev->dev_mutex); + mutex_init(&dev->dev_ctx_lock); spin_lock_init(&dev->irqlock); snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s", diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h index 849b89dd205c..85b2c0d3d8bc 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h +++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h @@ -241,6 +241,7 @@ struct mtk_vcodec_dec_ctx { * * @dec_mutex: decoder hardware lock * @dev_mutex: video_device lock + * @dev_ctx_lock: the lock of context list * @decode_workqueue: decode work queue * * @irqlock: protect data access by irq handler and work thread @@ -282,6 +283,7 @@ struct mtk_vcodec_dec_dev { /* decoder hardware mutex lock */ struct mutex dec_mutex[MTK_VDEC_HW_MAX]; struct mutex dev_mutex; + struct mutex dev_ctx_lock; struct workqueue_struct *decode_workqueue; spinlock_t irqlock; diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c index 06ed47df693b..21836dd6ef85 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c @@ -869,7 +869,6 @@ static int vdec_hevc_slice_init(struct mtk_vcodec_dec_ctx *ctx) inst->vpu.codec_type = ctx->current_codec; inst->vpu.capture_type = ctx->capture_fourcc; - ctx->drv_handle = inst; err = vpu_dec_init(&inst->vpu); if (err) { mtk_vdec_err(ctx, "vdec_hevc init err=%d", err); @@ -898,6 +897,7 @@ static int vdec_hevc_slice_init(struct mtk_vcodec_dec_ctx *ctx) mtk_vdec_debug(ctx, "lat hevc instance >> %p, codec_type = 0x%x", inst, inst->vpu.codec_type); + ctx->drv_handle = inst; return 0; error_free_inst: kfree(inst); diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c index 19407f9bc773..987b3d71b662 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c @@ -449,7 +449,7 @@ static int vdec_vp8_decode(void *h_vdec, struct mtk_vcodec_mem *bs, inst->frm_cnt, y_fb_dma, c_fb_dma, fb); inst->cur_fb = fb; - dec->bs_dma = (unsigned long)bs->dma_addr; + dec->bs_dma = (uint64_t)bs->dma_addr; dec->bs_sz = bs->size; dec->cur_y_fb_dma = y_fb_dma; dec->cur_c_fb_dma = c_fb_dma; diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c index 55355fa70090..039082f600c8 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c @@ -16,6 +16,7 @@ #include "../vdec_drv_base.h" #include "../vdec_vpu_if.h" +#define VP9_MAX_SUPER_FRAMES_NUM 8 #define VP9_SUPER_FRAME_BS_SZ 64 #define MAX_VP9_DPB_SIZE 9 @@ -133,11 +134,11 @@ struct vp9_sf_ref_fb { */ struct vdec_vp9_vsi { unsigned char sf_bs_buf[VP9_SUPER_FRAME_BS_SZ]; - struct vp9_sf_ref_fb sf_ref_fb[VP9_MAX_FRM_BUF_NUM-1]; + struct vp9_sf_ref_fb sf_ref_fb[VP9_MAX_SUPER_FRAMES_NUM]; int sf_next_ref_fb_idx; unsigned int sf_frm_cnt; - unsigned int sf_frm_offset[VP9_MAX_FRM_BUF_NUM-1]; - unsigned int sf_frm_sz[VP9_MAX_FRM_BUF_NUM-1]; + unsigned int sf_frm_offset[VP9_MAX_SUPER_FRAMES_NUM]; + unsigned int sf_frm_sz[VP9_MAX_SUPER_FRAMES_NUM]; unsigned int sf_frm_idx; unsigned int sf_init; struct vdec_fb fb; @@ -526,7 +527,7 @@ static void vp9_swap_frm_bufs(struct vdec_vp9_inst *inst) /* if this super frame and it is not last sub-frame, get next fb for * sub-frame decode */ - if (vsi->sf_frm_cnt > 0 && vsi->sf_frm_idx != vsi->sf_frm_cnt - 1) + if (vsi->sf_frm_cnt > 0 && vsi->sf_frm_idx != vsi->sf_frm_cnt) vsi->sf_next_ref_fb_idx = vp9_get_sf_ref_fb(inst); } @@ -735,7 +736,7 @@ static void get_free_fb(struct vdec_vp9_inst *inst, struct vdec_fb **out_fb) static int validate_vsi_array_indexes(struct vdec_vp9_inst *inst, struct vdec_vp9_vsi *vsi) { - if (vsi->sf_frm_idx >= VP9_MAX_FRM_BUF_NUM - 1) { + if (vsi->sf_frm_idx > VP9_MAX_SUPER_FRAMES_NUM) { mtk_vdec_err(inst->ctx, "Invalid vsi->sf_frm_idx=%u.", vsi->sf_frm_idx); return -EIO; } diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c index cf48d09b78d7..eea709d93820 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c @@ -1074,7 +1074,7 @@ static int vdec_vp9_slice_setup_tile_buffer(struct vdec_vp9_slice_instance *inst unsigned int mi_row; unsigned int mi_col; unsigned int offset; - unsigned int pa; + dma_addr_t pa; unsigned int size; struct vdec_vp9_slice_tiles *tiles; unsigned char *pos; @@ -1109,7 +1109,7 @@ static int vdec_vp9_slice_setup_tile_buffer(struct vdec_vp9_slice_instance *inst pos = va + offset; end = va + bs->size; /* truncated */ - pa = (unsigned int)bs->dma_addr + offset; + pa = bs->dma_addr + offset; tb = instance->tile.va; for (i = 0; i < rows; i++) { for (j = 0; j < cols; j++) { diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c index 82e57ae983d5..da6be556727b 100644 --- a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c @@ -77,12 +77,14 @@ static bool vpu_dec_check_ap_inst(struct mtk_vcodec_dec_dev *dec_dev, struct vde struct mtk_vcodec_dec_ctx *ctx; int ret = false; + mutex_lock(&dec_dev->dev_ctx_lock); list_for_each_entry(ctx, &dec_dev->ctx_list, list) { if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) { ret = true; break; } } + mutex_unlock(&dec_dev->dev_ctx_lock); return ret; } diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c index 6319f24bc714..3cb8a1622222 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c @@ -177,7 +177,9 @@ static int fops_vcodec_open(struct file *file) mtk_v4l2_venc_dbg(2, ctx, "Create instance [%d]@%p m2m_ctx=%p ", ctx->id, ctx, ctx->m2m_ctx); + mutex_lock(&dev->dev_ctx_lock); list_add(&ctx->list, &dev->ctx_list); + mutex_unlock(&dev->dev_ctx_lock); mutex_unlock(&dev->dev_mutex); mtk_v4l2_venc_dbg(0, ctx, "%s encoder [%d]", dev_name(&dev->plat_dev->dev), @@ -212,7 +214,9 @@ static int fops_vcodec_release(struct file *file) v4l2_fh_exit(&ctx->fh); v4l2_ctrl_handler_free(&ctx->ctrl_hdl); + mutex_lock(&dev->dev_ctx_lock); list_del_init(&ctx->list); + mutex_unlock(&dev->dev_ctx_lock); kfree(ctx); mutex_unlock(&dev->dev_mutex); return 0; @@ -294,6 +298,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev) mutex_init(&dev->enc_mutex); mutex_init(&dev->dev_mutex); + mutex_init(&dev->dev_ctx_lock); spin_lock_init(&dev->irqlock); snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s", diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h index a042f607ed8d..0bd85d0fb379 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h +++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h @@ -178,6 +178,7 @@ struct mtk_vcodec_enc_ctx { * * @enc_mutex: encoder hardware lock. * @dev_mutex: video_device lock + * @dev_ctx_lock: the lock of context list * @encode_workqueue: encode work queue * * @enc_irq: h264 encoder irq resource @@ -205,6 +206,7 @@ struct mtk_vcodec_enc_dev { /* encoder hardware mutex lock */ struct mutex enc_mutex; struct mutex dev_mutex; + struct mutex dev_ctx_lock; struct workqueue_struct *encode_workqueue; int enc_irq; diff --git a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c index 84ad1cc6ad17..51bb7ee141b9 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c @@ -47,12 +47,14 @@ static bool vpu_enc_check_ap_inst(struct mtk_vcodec_enc_dev *enc_dev, struct ven struct mtk_vcodec_enc_ctx *ctx; int ret = false; + mutex_lock(&enc_dev->dev_ctx_lock); list_for_each_entry(ctx, &enc_dev->ctx_list, list) { if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) { ret = true; break; } } + mutex_unlock(&enc_dev->dev_ctx_lock); return ret; } diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 1a64364700eb..0ad2ff9065aa 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1002,7 +1002,7 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id) } else { pcr->card_removed |= SD_EXIST; pcr->card_inserted &= ~SD_EXIST; - if (PCI_PID(pcr) == PID_5261) { + if ((PCI_PID(pcr) == PID_5261) || (PCI_PID(pcr) == PID_5264)) { rtsx_pci_write_register(pcr, RTS5261_FW_STATUS, RTS5261_EXPRESS_LINK_FAIL_MASK, 0); pcr->extra_caps |= EXTRA_CAPS_SD_EXPRESS; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index b5757993c9b2..c39718042e2e 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -116,7 +116,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ADP_P, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ADP_N, MEI_ME_PCH15_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)}, diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c index 6c9f00bcb94b..b543e6b9f3cf 100644 --- a/drivers/misc/mei/platform-vsc.c +++ b/drivers/misc/mei/platform-vsc.c @@ -400,25 +400,40 @@ static void mei_vsc_remove(struct platform_device *pdev) static int mei_vsc_suspend(struct device *dev) { struct mei_device *mei_dev = dev_get_drvdata(dev); + struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev); mei_stop(mei_dev); + mei_disable_interrupts(mei_dev); + + vsc_tp_free_irq(hw->tp); + return 0; } static int mei_vsc_resume(struct device *dev) { struct mei_device *mei_dev = dev_get_drvdata(dev); + struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev); int ret; - ret = mei_restart(mei_dev); + ret = vsc_tp_request_irq(hw->tp); if (ret) return ret; + ret = mei_restart(mei_dev); + if (ret) + goto err_free; + /* start timer if stopped in suspend */ schedule_delayed_work(&mei_dev->timer_work, HZ); return 0; + +err_free: + vsc_tp_free_irq(hw->tp); + + return ret; } static DEFINE_SIMPLE_DEV_PM_OPS(mei_vsc_pm_ops, mei_vsc_suspend, mei_vsc_resume); diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c index ecfb70cd057c..e6a98dba8a73 100644 --- a/drivers/misc/mei/vsc-tp.c +++ b/drivers/misc/mei/vsc-tp.c @@ -94,6 +94,27 @@ static const struct acpi_gpio_mapping vsc_tp_acpi_gpios[] = { {} }; +static irqreturn_t vsc_tp_isr(int irq, void *data) +{ + struct vsc_tp *tp = data; + + atomic_inc(&tp->assert_cnt); + + wake_up(&tp->xfer_wait); + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t vsc_tp_thread_isr(int irq, void *data) +{ + struct vsc_tp *tp = data; + + if (tp->event_notify) + tp->event_notify(tp->event_notify_context); + + return IRQ_HANDLED; +} + /* wakeup firmware and wait for response */ static int vsc_tp_wakeup_request(struct vsc_tp *tp) { @@ -384,6 +405,37 @@ int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb, EXPORT_SYMBOL_NS_GPL(vsc_tp_register_event_cb, VSC_TP); /** + * vsc_tp_request_irq - request irq for vsc_tp device + * @tp: vsc_tp device handle + */ +int vsc_tp_request_irq(struct vsc_tp *tp) +{ + struct spi_device *spi = tp->spi; + struct device *dev = &spi->dev; + int ret; + + irq_set_status_flags(spi->irq, IRQ_DISABLE_UNLAZY); + ret = request_threaded_irq(spi->irq, vsc_tp_isr, vsc_tp_thread_isr, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + dev_name(dev), tp); + if (ret) + return ret; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(vsc_tp_request_irq, VSC_TP); + +/** + * vsc_tp_free_irq - free irq for vsc_tp device + * @tp: vsc_tp device handle + */ +void vsc_tp_free_irq(struct vsc_tp *tp) +{ + free_irq(tp->spi->irq, tp); +} +EXPORT_SYMBOL_NS_GPL(vsc_tp_free_irq, VSC_TP); + +/** * vsc_tp_intr_synchronize - synchronize vsc_tp interrupt * @tp: vsc_tp device handle */ @@ -413,27 +465,6 @@ void vsc_tp_intr_disable(struct vsc_tp *tp) } EXPORT_SYMBOL_NS_GPL(vsc_tp_intr_disable, VSC_TP); -static irqreturn_t vsc_tp_isr(int irq, void *data) -{ - struct vsc_tp *tp = data; - - atomic_inc(&tp->assert_cnt); - - return IRQ_WAKE_THREAD; -} - -static irqreturn_t vsc_tp_thread_isr(int irq, void *data) -{ - struct vsc_tp *tp = data; - - wake_up(&tp->xfer_wait); - - if (tp->event_notify) - tp->event_notify(tp->event_notify_context); - - return IRQ_HANDLED; -} - static int vsc_tp_match_any(struct acpi_device *adev, void *data) { struct acpi_device **__adev = data; @@ -490,10 +521,9 @@ static int vsc_tp_probe(struct spi_device *spi) tp->spi = spi; irq_set_status_flags(spi->irq, IRQ_DISABLE_UNLAZY); - ret = devm_request_threaded_irq(dev, spi->irq, vsc_tp_isr, - vsc_tp_thread_isr, - IRQF_TRIGGER_FALLING | IRQF_ONESHOT, - dev_name(dev), tp); + ret = request_threaded_irq(spi->irq, vsc_tp_isr, vsc_tp_thread_isr, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + dev_name(dev), tp); if (ret) return ret; @@ -522,6 +552,8 @@ static int vsc_tp_probe(struct spi_device *spi) err_destroy_lock: mutex_destroy(&tp->mutex); + free_irq(spi->irq, tp); + return ret; } @@ -532,6 +564,8 @@ static void vsc_tp_remove(struct spi_device *spi) platform_device_unregister(tp->pdev); mutex_destroy(&tp->mutex); + + free_irq(spi->irq, tp); } static const struct acpi_device_id vsc_tp_acpi_ids[] = { diff --git a/drivers/misc/mei/vsc-tp.h b/drivers/misc/mei/vsc-tp.h index f9513ddc3e40..14ca195cbddc 100644 --- a/drivers/misc/mei/vsc-tp.h +++ b/drivers/misc/mei/vsc-tp.h @@ -37,6 +37,9 @@ int vsc_tp_xfer(struct vsc_tp *tp, u8 cmd, const void *obuf, size_t olen, int vsc_tp_register_event_cb(struct vsc_tp *tp, vsc_tp_event_cb_t event_cb, void *context); +int vsc_tp_request_irq(struct vsc_tp *tp); +void vsc_tp_free_irq(struct vsc_tp *tp); + void vsc_tp_intr_enable(struct vsc_tp *tp); void vsc_tp_intr_disable(struct vsc_tp *tp); void vsc_tp_intr_synchronize(struct vsc_tp *tp); diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c index 088f8ed4fdc4..a8ee0df47148 100644 --- a/drivers/mmc/host/omap.c +++ b/drivers/mmc/host/omap.c @@ -1114,10 +1114,25 @@ static void mmc_omap_set_power(struct mmc_omap_slot *slot, int power_on, host = slot->host; - if (slot->vsd) - gpiod_set_value(slot->vsd, power_on); - if (slot->vio) - gpiod_set_value(slot->vio, power_on); + if (power_on) { + if (slot->vsd) { + gpiod_set_value(slot->vsd, power_on); + msleep(1); + } + if (slot->vio) { + gpiod_set_value(slot->vio, power_on); + msleep(1); + } + } else { + if (slot->vio) { + gpiod_set_value(slot->vio, power_on); + msleep(50); + } + if (slot->vsd) { + gpiod_set_value(slot->vsd, power_on); + msleep(50); + } + } if (slot->pdata->set_power != NULL) slot->pdata->set_power(mmc_dev(slot->mmc), slot->id, power_on, @@ -1254,18 +1269,18 @@ static int mmc_omap_new_slot(struct mmc_omap_host *host, int id) slot->pdata = &host->pdata->slots[id]; /* Check for some optional GPIO controls */ - slot->vsd = gpiod_get_index_optional(host->dev, "vsd", - id, GPIOD_OUT_LOW); + slot->vsd = devm_gpiod_get_index_optional(host->dev, "vsd", + id, GPIOD_OUT_LOW); if (IS_ERR(slot->vsd)) return dev_err_probe(host->dev, PTR_ERR(slot->vsd), "error looking up VSD GPIO\n"); - slot->vio = gpiod_get_index_optional(host->dev, "vio", - id, GPIOD_OUT_LOW); + slot->vio = devm_gpiod_get_index_optional(host->dev, "vio", + id, GPIOD_OUT_LOW); if (IS_ERR(slot->vio)) return dev_err_probe(host->dev, PTR_ERR(slot->vio), "error looking up VIO GPIO\n"); - slot->cover = gpiod_get_index_optional(host->dev, "cover", - id, GPIOD_IN); + slot->cover = devm_gpiod_get_index_optional(host->dev, "cover", + id, GPIOD_IN); if (IS_ERR(slot->cover)) return dev_err_probe(host->dev, PTR_ERR(slot->cover), "error looking up cover switch GPIO\n"); @@ -1379,13 +1394,6 @@ static int mmc_omap_probe(struct platform_device *pdev) if (IS_ERR(host->virt_base)) return PTR_ERR(host->virt_base); - host->slot_switch = gpiod_get_optional(host->dev, "switch", - GPIOD_OUT_LOW); - if (IS_ERR(host->slot_switch)) - return dev_err_probe(host->dev, PTR_ERR(host->slot_switch), - "error looking up slot switch GPIO\n"); - - INIT_WORK(&host->slot_release_work, mmc_omap_slot_release_work); INIT_WORK(&host->send_stop_work, mmc_omap_send_stop_work); @@ -1404,6 +1412,12 @@ static int mmc_omap_probe(struct platform_device *pdev) host->dev = &pdev->dev; platform_set_drvdata(pdev, host); + host->slot_switch = devm_gpiod_get_optional(host->dev, "switch", + GPIOD_OUT_LOW); + if (IS_ERR(host->slot_switch)) + return dev_err_probe(host->dev, PTR_ERR(host->slot_switch), + "error looking up slot switch GPIO\n"); + host->id = pdev->id; host->irq = irq; host->phys_base = res->start; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 1035820c2377..8090390edaf9 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -950,20 +950,173 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface) mutex_unlock(&priv->reg_mutex); } -/* On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std - * 802.1Qâ„¢-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA - * must only be propagated to C-VLAN and MAC Bridge components. That means - * VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports, - * these frames are supposed to be processed by the CPU (software). So we make - * the switch only forward them to the CPU port. And if received from a CPU - * port, forward to a single port. The software is responsible of making the - * switch conform to the latter by setting a single port as destination port on - * the special tag. +/* In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL) + * of the Open Systems Interconnection basic reference model (OSI/RM) are + * described; the medium access control (MAC) and logical link control (LLC) + * sublayers. The MAC sublayer is the one facing the physical layer. * - * This switch intellectual property cannot conform to this part of the standard - * fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC - * DAs, it also includes :22-FF which the scope of propagation is not supposed - * to be restricted for these MAC DAs. + * In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A + * Bridge component comprises a MAC Relay Entity for interconnecting the Ports + * of the Bridge, at least two Ports, and higher layer entities with at least a + * Spanning Tree Protocol Entity included. + * + * Each Bridge Port also functions as an end station and shall provide the MAC + * Service to an LLC Entity. Each instance of the MAC Service is provided to a + * distinct LLC Entity that supports protocol identification, multiplexing, and + * demultiplexing, for protocol data unit (PDU) transmission and reception by + * one or more higher layer entities. + * + * It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC + * Entity associated with each Bridge Port is modeled as being directly + * connected to the attached Local Area Network (LAN). + * + * On the switch with CPU port architecture, CPU port functions as Management + * Port, and the Management Port functionality is provided by software which + * functions as an end station. Software is connected to an IEEE 802 LAN that is + * wholly contained within the system that incorporates the Bridge. Software + * provides access to the LLC Entity associated with each Bridge Port by the + * value of the source port field on the special tag on the frame received by + * software. + * + * We call frames that carry control information to determine the active + * topology and current extent of each Virtual Local Area Network (VLAN), i.e., + * spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration + * Protocol Data Units (MVRPDUs), and frames from other link constrained + * protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and + * Link Layer Discovery Protocol (LLDP), link-local frames. They are not + * forwarded by a Bridge. Permanently configured entries in the filtering + * database (FDB) ensure that such frames are discarded by the Forwarding + * Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail: + * + * Each of the reserved MAC addresses specified in Table 8-1 + * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be + * permanently configured in the FDB in C-VLAN components and ERs. + * + * Each of the reserved MAC addresses specified in Table 8-2 + * (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently + * configured in the FDB in S-VLAN components. + * + * Each of the reserved MAC addresses specified in Table 8-3 + * (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in + * TPMR components. + * + * The FDB entries for reserved MAC addresses shall specify filtering for all + * Bridge Ports and all VIDs. Management shall not provide the capability to + * modify or remove entries for reserved MAC addresses. + * + * The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of + * propagation of PDUs within a Bridged Network, as follows: + * + * The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no + * conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN) + * component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward. + * PDUs transmitted using this destination address, or any other addresses + * that appear in Table 8-1, Table 8-2, and Table 8-3 + * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can + * therefore travel no further than those stations that can be reached via a + * single individual LAN from the originating station. + * + * The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an + * address that no conformant S-VLAN component, C-VLAN component, or MAC + * Bridge can forward; however, this address is relayed by a TPMR component. + * PDUs using this destination address, or any of the other addresses that + * appear in both Table 8-1 and Table 8-2 but not in Table 8-3 + * (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by + * any TPMRs but will propagate no further than the nearest S-VLAN component, + * C-VLAN component, or MAC Bridge. + * + * The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address + * that no conformant C-VLAN component, MAC Bridge can forward; however, it is + * relayed by TPMR components and S-VLAN components. PDUs using this + * destination address, or any of the other addresses that appear in Table 8-1 + * but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]), + * will be relayed by TPMR components and S-VLAN components but will propagate + * no further than the nearest C-VLAN component or MAC Bridge. + * + * Because the LLC Entity associated with each Bridge Port is provided via CPU + * port, we must not filter these frames but forward them to CPU port. + * + * In a Bridge, the transmission Port is majorly decided by ingress and egress + * rules, FDB, and spanning tree Port State functions of the Forwarding Process. + * For link-local frames, only CPU port should be designated as destination port + * in the FDB, and the other functions of the Forwarding Process must not + * interfere with the decision of the transmission Port. We call this process + * trapping frames to CPU port. + * + * Therefore, on the switch with CPU port architecture, link-local frames must + * be trapped to CPU port, and certain link-local frames received by a Port of a + * Bridge comprising a TPMR component or an S-VLAN component must be excluded + * from it. + * + * A Bridge of the switch with CPU port architecture cannot comprise a Two-Port + * MAC Relay (TPMR) component as a TPMR component supports only a subset of the + * functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port + * doesn't count) of this architecture will either function as a standard MAC + * Bridge or a standard VLAN Bridge. + * + * Therefore, a Bridge of this architecture can only comprise S-VLAN components, + * C-VLAN components, or MAC Bridge components. Since there's no TPMR component, + * we don't need to relay PDUs using the destination addresses specified on the + * Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge + * section where they must be relayed by TPMR components. + * + * One option to trap link-local frames to CPU port is to add static FDB entries + * with CPU port designated as destination port. However, because that + * Independent VLAN Learning (IVL) is being used on every VID, each entry only + * applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC + * Bridge component or a C-VLAN component, there would have to be 16 times 4096 + * entries. This switch intellectual property can only hold a maximum of 2048 + * entries. Using this option, there also isn't a mechanism to prevent + * link-local frames from being discarded when the spanning tree Port State of + * the reception Port is discarding. + * + * The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4 + * registers. Whilst this applies to every VID, it doesn't contain all of the + * reserved MAC addresses without affecting the remaining Standard Group MAC + * Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the + * remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination + * addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF + * destination addresses which may be relayed by MAC Bridges or VLAN Bridges. + * The latter option provides better but not complete conformance. + * + * This switch intellectual property also does not provide a mechanism to trap + * link-local frames with specific destination addresses to CPU port by Bridge, + * to conform to the filtering rules for the distinct Bridge components. + * + * Therefore, regardless of the type of the Bridge component, link-local frames + * with these destination addresses will be trapped to CPU port: + * + * 01-80-C2-00-00-[00,01,02,03,0E] + * + * In a Bridge comprising a MAC Bridge component or a C-VLAN component: + * + * Link-local frames with these destination addresses won't be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] + * + * In a Bridge comprising an S-VLAN component: + * + * Link-local frames with these destination addresses will be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-00 + * + * Link-local frames with these destination addresses won't be trapped to CPU + * port which won't conform to IEEE Std 802.1Q-2022: + * + * 01-80-C2-00-00-[04,05,06,07,08,09,0A] + * + * To trap link-local frames to CPU port as conformant as this switch + * intellectual property can allow, link-local frames are made to be regarded as + * Bridge Protocol Data Units (BPDUs). This is because this switch intellectual + * property only lets the frames regarded as BPDUs bypass the spanning tree Port + * State function of the Forwarding Process. + * + * The only remaining interference is the ingress rules. When the reception Port + * has no PVID assigned on software, VLAN-untagged frames won't be allowed in. + * There doesn't seem to be a mechanism on the switch intellectual property to + * have link-local frames bypass this function of the Forwarding Process. */ static void mt753x_trap_frames(struct mt7530_priv *priv) @@ -971,35 +1124,43 @@ mt753x_trap_frames(struct mt7530_priv *priv) /* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them * VLAN-untagged. */ - mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_EG_TAG_MASK | - MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK | - MT753X_BPDU_PORT_FW_MASK, - MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | - MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) | - MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | - MT753X_BPDU_CPU_ONLY); + mt7530_rmw(priv, MT753X_BPC, + MT753X_PAE_BPDU_FR | MT753X_PAE_EG_TAG_MASK | + MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK | + MT753X_BPDU_PORT_FW_MASK, + MT753X_PAE_BPDU_FR | + MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); /* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress * them VLAN-untagged. */ - mt7530_rmw(priv, MT753X_RGAC1, MT753X_R02_EG_TAG_MASK | - MT753X_R02_PORT_FW_MASK | MT753X_R01_EG_TAG_MASK | - MT753X_R01_PORT_FW_MASK, - MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | - MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) | - MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | - MT753X_BPDU_CPU_ONLY); + mt7530_rmw(priv, MT753X_RGAC1, + MT753X_R02_BPDU_FR | MT753X_R02_EG_TAG_MASK | + MT753X_R02_PORT_FW_MASK | MT753X_R01_BPDU_FR | + MT753X_R01_EG_TAG_MASK | MT753X_R01_PORT_FW_MASK, + MT753X_R02_BPDU_FR | + MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_R01_BPDU_FR | + MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); /* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress * them VLAN-untagged. */ - mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_EG_TAG_MASK | - MT753X_R0E_PORT_FW_MASK | MT753X_R03_EG_TAG_MASK | - MT753X_R03_PORT_FW_MASK, - MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | - MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) | - MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | - MT753X_BPDU_CPU_ONLY); + mt7530_rmw(priv, MT753X_RGAC2, + MT753X_R0E_BPDU_FR | MT753X_R0E_EG_TAG_MASK | + MT753X_R0E_PORT_FW_MASK | MT753X_R03_BPDU_FR | + MT753X_R03_EG_TAG_MASK | MT753X_R03_PORT_FW_MASK, + MT753X_R0E_BPDU_FR | + MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) | + MT753X_R03_BPDU_FR | + MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + MT753X_BPDU_CPU_ONLY); } static void @@ -1722,14 +1883,16 @@ mt7530_port_vlan_del(struct dsa_switch *ds, int port, static int mt753x_mirror_port_get(unsigned int id, u32 val) { - return (id == ID_MT7531) ? MT7531_MIRROR_PORT_GET(val) : - MIRROR_PORT(val); + return (id == ID_MT7531 || id == ID_MT7988) ? + MT7531_MIRROR_PORT_GET(val) : + MIRROR_PORT(val); } static int mt753x_mirror_port_set(unsigned int id, u32 val) { - return (id == ID_MT7531) ? MT7531_MIRROR_PORT_SET(val) : - MIRROR_PORT(val); + return (id == ID_MT7531 || id == ID_MT7988) ? + MT7531_MIRROR_PORT_SET(val) : + MIRROR_PORT(val); } static int mt753x_port_mirror_add(struct dsa_switch *ds, int port, @@ -2319,6 +2482,9 @@ mt7530_setup(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Setup VLAN ID 0 for VLAN-unaware bridges */ ret = mt7530_setup_vlan0(priv); if (ret) @@ -2430,6 +2596,9 @@ mt7531_setup_common(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Allow mirroring frames received on the local port (monitor port). */ + mt7530_set(priv, MT753X_AGC, LOCAL_EN); + /* Flush the FDB table */ ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL); if (ret < 0) @@ -2505,18 +2674,25 @@ mt7531_setup(struct dsa_switch *ds) mt7530_rmw(priv, MT7531_GPIO_MODE0, MT7531_GPIO0_MASK, MT7531_GPIO0_INTERRUPT); - /* Enable PHY core PLL, since phy_device has not yet been created - * provided for phy_[read,write]_mmd_indirect is called, we provide - * our own mt7531_ind_mmd_phy_[read,write] to complete this - * function. + /* Enable Energy-Efficient Ethernet (EEE) and PHY core PLL, since + * phy_device has not yet been created provided for + * phy_[read,write]_mmd_indirect is called, we provide our own + * mt7531_ind_mmd_phy_[read,write] to complete this function. */ val = mt7531_ind_c45_phy_read(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2, CORE_PLL_GROUP4); - val |= MT7531_PHY_PLL_BYPASS_MODE; + val |= MT7531_RG_SYSPLL_DMY2 | MT7531_PHY_PLL_BYPASS_MODE; val &= ~MT7531_PHY_PLL_OFF; mt7531_ind_c45_phy_write(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2, CORE_PLL_GROUP4, val); + /* Disable EEE advertisement on the switch PHYs. */ + for (i = MT753X_CTRL_PHY_ADDR; + i < MT753X_CTRL_PHY_ADDR + MT7530_NUM_PHYS; i++) { + mt7531_ind_c45_phy_write(priv, i, MDIO_MMD_AN, MDIO_AN_EEE_ADV, + 0); + } + mt7531_setup_common(ds); /* Setup VLAN ID 0 for VLAN-unaware bridges */ diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index d17b318e6ee4..a08053390b28 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -32,6 +32,10 @@ enum mt753x_id { #define SYSC_REG_RSTCTRL 0x34 #define RESET_MCM BIT(2) +/* Register for ARL global control */ +#define MT753X_AGC 0xc +#define LOCAL_EN BIT(7) + /* Registers to mac forward control for unknown frames */ #define MT7530_MFC 0x10 #define BC_FFP(x) (((x) & 0xff) << 24) @@ -65,6 +69,7 @@ enum mt753x_id { /* Registers for BPDU and PAE frame control*/ #define MT753X_BPC 0x24 +#define MT753X_PAE_BPDU_FR BIT(25) #define MT753X_PAE_EG_TAG_MASK GENMASK(24, 22) #define MT753X_PAE_EG_TAG(x) FIELD_PREP(MT753X_PAE_EG_TAG_MASK, x) #define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16) @@ -75,20 +80,24 @@ enum mt753x_id { /* Register for :01 and :02 MAC DA frame control */ #define MT753X_RGAC1 0x28 +#define MT753X_R02_BPDU_FR BIT(25) #define MT753X_R02_EG_TAG_MASK GENMASK(24, 22) #define MT753X_R02_EG_TAG(x) FIELD_PREP(MT753X_R02_EG_TAG_MASK, x) #define MT753X_R02_PORT_FW_MASK GENMASK(18, 16) #define MT753X_R02_PORT_FW(x) FIELD_PREP(MT753X_R02_PORT_FW_MASK, x) +#define MT753X_R01_BPDU_FR BIT(9) #define MT753X_R01_EG_TAG_MASK GENMASK(8, 6) #define MT753X_R01_EG_TAG(x) FIELD_PREP(MT753X_R01_EG_TAG_MASK, x) #define MT753X_R01_PORT_FW_MASK GENMASK(2, 0) /* Register for :03 and :0E MAC DA frame control */ #define MT753X_RGAC2 0x2c +#define MT753X_R0E_BPDU_FR BIT(25) #define MT753X_R0E_EG_TAG_MASK GENMASK(24, 22) #define MT753X_R0E_EG_TAG(x) FIELD_PREP(MT753X_R0E_EG_TAG_MASK, x) #define MT753X_R0E_PORT_FW_MASK GENMASK(18, 16) #define MT753X_R0E_PORT_FW(x) FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x) +#define MT753X_R03_BPDU_FR BIT(9) #define MT753X_R03_EG_TAG_MASK GENMASK(8, 6) #define MT753X_R03_EG_TAG(x) FIELD_PREP(MT753X_R03_EG_TAG_MASK, x) #define MT753X_R03_PORT_FW_MASK GENMASK(2, 0) @@ -616,6 +625,7 @@ enum mt7531_clk_skew { #define RG_SYSPLL_DDSFBK_EN BIT(12) #define RG_SYSPLL_BIAS_EN BIT(11) #define RG_SYSPLL_BIAS_LPF_EN BIT(10) +#define MT7531_RG_SYSPLL_DMY2 BIT(6) #define MT7531_PHY_PLL_OFF BIT(5) #define MT7531_PHY_PLL_BYPASS_MODE BIT(4) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c95787cb9086..59b5dd0e2f41 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; } diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index 86deeb347cbc..ddadeb9bfdae 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -25,10 +25,25 @@ #define MV88E6250_PORT_STS_PORTMODE_PHY_100_HALF 0x0900 #define MV88E6250_PORT_STS_PORTMODE_PHY_10_FULL 0x0a00 #define MV88E6250_PORT_STS_PORTMODE_PHY_100_FULL 0x0b00 -#define MV88E6250_PORT_STS_PORTMODE_MII_10_HALF 0x0c00 -#define MV88E6250_PORT_STS_PORTMODE_MII_100_HALF 0x0d00 -#define MV88E6250_PORT_STS_PORTMODE_MII_10_FULL 0x0e00 -#define MV88E6250_PORT_STS_PORTMODE_MII_100_FULL 0x0f00 +/* - Modes with PHY suffix use output instead of input clock + * - Modes without RMII or RGMII use MII + * - Modes without speed do not have a fixed speed specified in the manual + * ("DC to x MHz" - variable clock support?) + */ +#define MV88E6250_PORT_STS_PORTMODE_MII_DISABLED 0x0000 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_RGMII 0x0100 +#define MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL_PHY 0x0200 +#define MV88E6250_PORT_STS_PORTMODE_MII_200_RMII_FULL_PHY 0x0400 +#define MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL 0x0600 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL 0x0700 +#define MV88E6250_PORT_STS_PORTMODE_MII_HALF 0x0800 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_HALF_PHY 0x0900 +#define MV88E6250_PORT_STS_PORTMODE_MII_FULL 0x0a00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL_PHY 0x0b00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_HALF_PHY 0x0c00 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_HALF_PHY 0x0d00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_FULL_PHY 0x0e00 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_FULL_PHY 0x0f00 #define MV88E6XXX_PORT_STS_LINK 0x0800 #define MV88E6XXX_PORT_STS_DUPLEX 0x0400 #define MV88E6XXX_PORT_STS_SPEED_MASK 0x0300 diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 9e9e4a03f1a8..2d8a66ea82fa 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -351,7 +351,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, ENA_COM_BOUNCE_BUFFER_CNTRL_CNT; io_sq->bounce_buf_ctrl.next_to_use = 0; - size = io_sq->bounce_buf_ctrl.buffer_size * + size = (size_t)io_sq->bounce_buf_ctrl.buffer_size * io_sq->bounce_buf_ctrl.buffers_num; dev_node = dev_to_node(ena_dev->dmadev); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 09e7da1a69c9..be5acfa41ee0 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -718,8 +718,11 @@ void ena_unmap_tx_buff(struct ena_ring *tx_ring, static void ena_free_tx_bufs(struct ena_ring *tx_ring) { bool print_once = true; + bool is_xdp_ring; u32 i; + is_xdp_ring = ENA_IS_XDP_INDEX(tx_ring->adapter, tx_ring->qid); + for (i = 0; i < tx_ring->ring_size; i++) { struct ena_tx_buffer *tx_info = &tx_ring->tx_buffer_info[i]; @@ -739,10 +742,15 @@ static void ena_free_tx_bufs(struct ena_ring *tx_ring) ena_unmap_tx_buff(tx_ring, tx_info); - dev_kfree_skb_any(tx_info->skb); + if (is_xdp_ring) + xdp_return_frame(tx_info->xdpf); + else + dev_kfree_skb_any(tx_info->skb); } - netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev, - tx_ring->qid)); + + if (!is_xdp_ring) + netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->qid)); } static void ena_free_all_tx_bufs(struct ena_adapter *adapter) @@ -3481,10 +3489,11 @@ static void check_for_missing_completions(struct ena_adapter *adapter) { struct ena_ring *tx_ring; struct ena_ring *rx_ring; - int i, budget, rc; + int qid, budget, rc; int io_queue_count; io_queue_count = adapter->xdp_num_queues + adapter->num_io_queues; + /* Make sure the driver doesn't turn the device in other process */ smp_rmb(); @@ -3497,27 +3506,29 @@ static void check_for_missing_completions(struct ena_adapter *adapter) if (adapter->missing_tx_completion_to == ENA_HW_HINTS_NO_TIMEOUT) return; - budget = ENA_MONITORED_TX_QUEUES; + budget = min_t(u32, io_queue_count, ENA_MONITORED_TX_QUEUES); - for (i = adapter->last_monitored_tx_qid; i < io_queue_count; i++) { - tx_ring = &adapter->tx_ring[i]; - rx_ring = &adapter->rx_ring[i]; + qid = adapter->last_monitored_tx_qid; + + while (budget) { + qid = (qid + 1) % io_queue_count; + + tx_ring = &adapter->tx_ring[qid]; + rx_ring = &adapter->rx_ring[qid]; rc = check_missing_comp_in_tx_queue(adapter, tx_ring); if (unlikely(rc)) return; - rc = !ENA_IS_XDP_INDEX(adapter, i) ? + rc = !ENA_IS_XDP_INDEX(adapter, qid) ? check_for_rx_interrupt_queue(adapter, rx_ring) : 0; if (unlikely(rc)) return; budget--; - if (!budget) - break; } - adapter->last_monitored_tx_qid = i % io_queue_count; + adapter->last_monitored_tx_qid = qid; } /* trigger napi schedule after 2 consecutive detections */ diff --git a/drivers/net/ethernet/amazon/ena/ena_xdp.c b/drivers/net/ethernet/amazon/ena/ena_xdp.c index 337c435d3ce9..5b175e7e92a1 100644 --- a/drivers/net/ethernet/amazon/ena/ena_xdp.c +++ b/drivers/net/ethernet/amazon/ena/ena_xdp.c @@ -89,7 +89,7 @@ int ena_xdp_xmit_frame(struct ena_ring *tx_ring, rc = ena_xdp_tx_map_frame(tx_ring, tx_info, xdpf, &ena_tx_ctx); if (unlikely(rc)) - return rc; + goto err; ena_tx_ctx.req_id = req_id; @@ -112,7 +112,9 @@ int ena_xdp_xmit_frame(struct ena_ring *tx_ring, error_unmap_dma: ena_unmap_tx_buff(tx_ring, tx_info); +err: tx_info->xdpf = NULL; + return rc; } diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 9662ee72814c..536635e57727 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -593,6 +593,16 @@ err_out: pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY); } +void pdsc_pci_reset_thread(struct work_struct *work) +{ + struct pdsc *pdsc = container_of(work, struct pdsc, pci_reset_work); + struct pci_dev *pdev = pdsc->pdev; + + pci_dev_get(pdev); + pci_reset_function(pdev); + pci_dev_put(pdev); +} + static void pdsc_check_pci_health(struct pdsc *pdsc) { u8 fw_status; @@ -607,7 +617,8 @@ static void pdsc_check_pci_health(struct pdsc *pdsc) if (fw_status != PDS_RC_BAD_PCI) return; - pci_reset_function(pdsc->pdev); + /* prevent deadlock between pdsc_reset_prepare and pdsc_health_thread */ + queue_work(pdsc->wq, &pdsc->pci_reset_work); } void pdsc_health_thread(struct work_struct *work) diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index 92d7657dd614..a3e17a0c187a 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -197,6 +197,7 @@ struct pdsc { struct pdsc_qcq notifyqcq; u64 last_eid; struct pdsc_viftype *viftype_status; + struct work_struct pci_reset_work; }; /** enum pds_core_dbell_bits - bitwise composition of dbell values. @@ -313,5 +314,6 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw, void pdsc_fw_down(struct pdsc *pdsc); void pdsc_fw_up(struct pdsc *pdsc); +void pdsc_pci_reset_thread(struct work_struct *work); #endif /* _PDSC_H_ */ diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index e494e1298dc9..495ef4ef8c10 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -229,6 +229,9 @@ int pdsc_devcmd_reset(struct pdsc *pdsc) .reset.opcode = PDS_CORE_CMD_RESET, }; + if (!pdsc_is_fw_running(pdsc)) + return 0; + return pdsc_devcmd(pdsc, &cmd, &comp, pdsc->devcmd_timeout); } diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index ab6133e7db42..660268ff9562 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -239,6 +239,7 @@ static int pdsc_init_pf(struct pdsc *pdsc) snprintf(wq_name, sizeof(wq_name), "%s.%d", PDS_CORE_DRV_NAME, pdsc->uid); pdsc->wq = create_singlethread_workqueue(wq_name); INIT_WORK(&pdsc->health_work, pdsc_health_thread); + INIT_WORK(&pdsc->pci_reset_work, pdsc_pci_reset_thread); timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0); pdsc->wdtimer_period = PDSC_WATCHDOG_SECS * HZ; diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index 72ea97c5d5d4..82768b0e9026 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 3e4fb3c3e834..1be6d14030bc 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 493b724848c8..2c2ee79c4d77 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 @@ next_rx_no_prod_no_len: *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 | @@ -11758,6 +11750,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* VF-reps may need to be re-opened after the PF is re-opened */ if (BNXT_PF(bp)) bnxt_vf_reps_open(bp); + if (bp->ptp_cfg) + atomic_set(&bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS); bnxt_ptp_init_rtc(bp, true); bnxt_ptp_cfg_tstamp_filters(bp); bnxt_cfg_usr_fltrs(bp); @@ -13035,6 +13029,16 @@ 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); @@ -13048,12 +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); @@ -15371,6 +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"); @@ -15379,16 +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); @@ -15472,6 +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/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 93f9bd55020f..195c02dc0683 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -210,6 +210,9 @@ void bnxt_ulp_start(struct bnxt *bp, int err) if (err) return; + if (edev->ulp_tbl->msix_requested) + bnxt_fill_msix_vecs(bp, edev->msix_entries); + if (aux_priv) { struct auxiliary_device *adev; @@ -392,12 +395,13 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp) if (!edev) goto aux_dev_uninit; + aux_priv->edev = edev; + ulp = kzalloc(sizeof(*ulp), GFP_KERNEL); if (!ulp) goto aux_dev_uninit; edev->ulp_tbl = ulp; - aux_priv->edev = edev; bp->edev = edev; bnxt_set_edev_info(edev, bp); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 48b9ddb2b1b3..ffb9f9f15c52 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 ef2440f3abf8..166832a4213a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3503,6 +3503,34 @@ static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) } /** + * iavf_is_tc_config_same - Compare the mqprio TC config with the + * TC config already configured on this adapter. + * @adapter: board private structure + * @mqprio_qopt: TC config received from kernel. + * + * This function compares the TC config received from the kernel + * with the config already configured on the adapter. + * + * Return: True if configuration is same, false otherwise. + **/ +static bool iavf_is_tc_config_same(struct iavf_adapter *adapter, + struct tc_mqprio_qopt *mqprio_qopt) +{ + struct virtchnl_channel_info *ch = &adapter->ch_config.ch_info[0]; + int i; + + if (adapter->num_tc != mqprio_qopt->num_tc) + return false; + + for (i = 0; i < adapter->num_tc; i++) { + if (ch[i].count != mqprio_qopt->count[i] || + ch[i].offset != mqprio_qopt->offset[i]) + return false; + } + return true; +} + +/** * __iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure * @type_data: tc offload data @@ -3559,7 +3587,7 @@ 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_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index b890410a2bc0..688ccb0615ab 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -28,6 +28,8 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, * - ICE_TC_FLWR_FIELD_VLAN_TPID (present if specified) * - Tunnel flag (present if tunnel) */ + if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) + lkups_cnt++; if (flags & ICE_TC_FLWR_FIELD_TENANT_ID) lkups_cnt++; @@ -363,6 +365,11 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, /* Always add direction metadata */ ice_rule_add_direction_metadata(&list[ICE_TC_METADATA_LKUP_IDX]); + if (tc_fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { + ice_rule_add_src_vsi_metadata(&list[i]); + i++; + } + rule_info->tun_type = ice_sw_type_from_tunnel(tc_fltr->tunnel_type); if (tc_fltr->tunnel_type != TNL_LAST) { i = ice_tc_fill_tunnel_outer(flags, tc_fltr, list, i); @@ -772,7 +779,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) int ret; int i; - if (!flags || (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT)) { + if (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)"); return -EOPNOTSUPP; } @@ -820,6 +827,7 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) /* specify the cookie as filter_rule_id */ rule_info.fltr_rule_id = fltr->cookie; + rule_info.src_vsi = vsi->idx; ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); if (ret == -EEXIST) { @@ -1481,7 +1489,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, (BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID) | - BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS))) { + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_OPTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_CONTROL))) { NL_SET_ERR_MSG_MOD(fltr->extack, "Tunnel key used, but device isn't a tunnel"); return -EOPNOTSUPP; } else { diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 21d26e19338a..d10a4be965b5 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 90316dc58630..6bc56c7c181e 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 bf240c5daf86..3929b25b6ae6 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 35ad40a803cb..4d975d620a8e 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_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index d39001cdc707..00af8888e329 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4819,18 +4819,18 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw) */ rvu_write64(rvu, blkaddr, NIX_AF_CFG, rvu_read64(rvu, blkaddr, NIX_AF_CFG) | 0x40ULL); + } - /* Set chan/link to backpressure TL3 instead of TL2 */ - rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01); + /* Set chan/link to backpressure TL3 instead of TL2 */ + rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01); - /* Disable SQ manager's sticky mode operation (set TM6 = 0) - * This sticky mode is known to cause SQ stalls when multiple - * SQs are mapped to same SMQ and transmitting pkts at a time. - */ - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS); - cfg &= ~BIT_ULL(15); - rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg); - } + /* Disable SQ manager's sticky mode operation (set TM6 = 0) + * This sticky mode is known to cause SQ stalls when multiple + * SQs are mapped to same SMQ and transmitting pkts at a time. + */ + cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS); + cfg &= ~BIT_ULL(15); + rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg); ltdefs = rvu->kpu.lt_def; /* Calibrate X2P bus to check if CGX/LBK links are fine */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index be709f83f331..e8b73b9d75e3 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/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 87bdb93cb066..f4655a8c0705 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -689,6 +689,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_match_control match; + u32 val; flow_rule_match_control(rule, &match); if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { @@ -697,12 +698,14 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, } if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { + val = match.key->flags & FLOW_DIS_IS_FRAGMENT; if (ntohs(flow_spec->etype) == ETH_P_IP) { - flow_spec->ip_flag = IPV4_FLAG_MORE; + flow_spec->ip_flag = val ? IPV4_FLAG_MORE : 0; flow_mask->ip_flag = IPV4_FLAG_MORE; req->features |= BIT_ULL(NPC_IPFRAG_IPV4); } else if (ntohs(flow_spec->etype) == ETH_P_IPV6) { - flow_spec->next_header = IPPROTO_FRAGMENT; + flow_spec->next_header = val ? + IPPROTO_FRAGMENT : 0; flow_mask->next_header = 0xff; req->features |= BIT_ULL(NPC_IPFRAG_IPV6); } else { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c index 1e77bbf5d22a..1723e9912ae0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c @@ -382,6 +382,7 @@ static void otx2_qos_read_txschq_cfg_tl(struct otx2_qos_node *parent, otx2_qos_read_txschq_cfg_tl(node, cfg); cnt = cfg->static_node_pos[node->level]; cfg->schq_contig_list[node->level][cnt] = node->schq; + cfg->schq_index_used[node->level][cnt] = true; cfg->schq_contig[node->level]++; cfg->static_node_pos[node->level]++; otx2_qos_read_txschq_cfg_schq(node, cfg); diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index c895e265ae0e..61334a71058c 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1074,13 +1074,13 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) static void mtk_wed_stop(struct mtk_wed_device *dev) { + mtk_wed_dma_disable(dev); mtk_wed_set_ext_int(dev, false); wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER, 0); wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, 0); wdma_w32(dev, MTK_WDMA_INT_MASK, 0); wdma_w32(dev, MTK_WDMA_INT_GRP2, 0); - wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0); if (!mtk_wed_get_rx_capa(dev)) return; @@ -1093,7 +1093,6 @@ static void mtk_wed_deinit(struct mtk_wed_device *dev) { mtk_wed_stop(dev); - mtk_wed_dma_disable(dev); wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WDMA_INT_AGENT_EN | @@ -2605,9 +2604,6 @@ mtk_wed_irq_get(struct mtk_wed_device *dev, u32 mask) static void mtk_wed_irq_set_mask(struct mtk_wed_device *dev, u32 mask) { - if (!dev->running) - return; - mtk_wed_set_ext_int(dev, !!mask); wed_w32(dev, MTK_WED_INT_MASK, mask); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index 86f1854698b4..883c044852f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -95,9 +95,15 @@ static inline void mlx5e_ptp_metadata_fifo_push(struct mlx5e_ptp_metadata_fifo * } static inline u8 +mlx5e_ptp_metadata_fifo_peek(struct mlx5e_ptp_metadata_fifo *fifo) +{ + return fifo->data[fifo->mask & fifo->cc]; +} + +static inline void mlx5e_ptp_metadata_fifo_pop(struct mlx5e_ptp_metadata_fifo *fifo) { - return fifo->data[fifo->mask & fifo->cc++]; + fifo->cc++; } static inline void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index e87e26f2c669..6743806b8480 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -83,24 +83,25 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs, txq_ix = mlx5e_qid_from_qos(chs, node_qid); - WARN_ON(node_qid > priv->htb_max_qos_sqs); - if (node_qid == priv->htb_max_qos_sqs) { - struct mlx5e_sq_stats *stats, **stats_list = NULL; - - if (priv->htb_max_qos_sqs == 0) { - stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev), - sizeof(*stats_list), - GFP_KERNEL); - if (!stats_list) - return -ENOMEM; - } + WARN_ON(node_qid >= mlx5e_htb_cur_leaf_nodes(priv->htb)); + if (!priv->htb_qos_sq_stats) { + struct mlx5e_sq_stats **stats_list; + + stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev), + sizeof(*stats_list), GFP_KERNEL); + if (!stats_list) + return -ENOMEM; + + WRITE_ONCE(priv->htb_qos_sq_stats, stats_list); + } + + if (!priv->htb_qos_sq_stats[node_qid]) { + struct mlx5e_sq_stats *stats; + stats = kzalloc(sizeof(*stats), GFP_KERNEL); - if (!stats) { - kvfree(stats_list); + if (!stats) return -ENOMEM; - } - if (stats_list) - WRITE_ONCE(priv->htb_qos_sq_stats, stats_list); + WRITE_ONCE(priv->htb_qos_sq_stats[node_qid], stats); /* Order htb_max_qos_sqs increment after writing the array pointer. * Pairs with smp_load_acquire in en_stats.c. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 0ab9db319530..22918b2ef7f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -108,7 +108,10 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) mlx5e_reset_txqsq_cc_pc(sq); sq->stats->recover++; clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); + rtnl_lock(); mlx5e_activate_txqsq(sq); + rtnl_unlock(); + if (sq->channel) mlx5e_trigger_napi_icosq(sq->channel); else @@ -179,12 +182,16 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx) carrier_ok = netif_carrier_ok(netdev); netif_carrier_off(netdev); + rtnl_lock(); mlx5e_deactivate_priv_channels(priv); + rtnl_unlock(); mlx5e_ptp_close(chs->ptp); err = mlx5e_ptp_open(priv, &chs->params, chs->c[0]->lag_port, &chs->ptp); + rtnl_lock(); mlx5e_activate_priv_channels(priv); + rtnl_unlock(); /* return carrier back if needed */ if (carrier_ok) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c index bcafb4bf9415..8d9a3b5ec973 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c @@ -179,6 +179,13 @@ u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels) return min_t(u32, rqt_size, max_cap_rqt_size); } +#define MLX5E_MAX_RQT_SIZE_ALLOWED_WITH_XOR8_HASH 256 + +unsigned int mlx5e_rqt_max_num_channels_allowed_for_xor8(void) +{ + return MLX5E_MAX_RQT_SIZE_ALLOWED_WITH_XOR8_HASH / MLX5E_UNIFORM_SPREAD_RQT_FACTOR; +} + void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt) { mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h index e0bc30308c77..2f9e04a8418f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h @@ -38,6 +38,7 @@ static inline u32 mlx5e_rqt_get_rqtn(struct mlx5e_rqt *rqt) } u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels); +unsigned int mlx5e_rqt_max_num_channels_allowed_for_xor8(void); int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id); int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c index f675b1926340..f66bbc846464 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c @@ -57,6 +57,7 @@ int mlx5e_selq_init(struct mlx5e_selq *selq, struct mutex *state_lock) void mlx5e_selq_cleanup(struct mlx5e_selq *selq) { + mutex_lock(selq->state_lock); WARN_ON_ONCE(selq->is_prepared); kvfree(selq->standby); @@ -67,6 +68,7 @@ void mlx5e_selq_cleanup(struct mlx5e_selq *selq) kvfree(selq->standby); selq->standby = NULL; + mutex_unlock(selq->state_lock); } void mlx5e_selq_prepare_params(struct mlx5e_selq *selq, struct mlx5e_params *params) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index b2cabd6ab86c..cc9bcc420032 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/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index c7f542d0b8f0..93cf23278d93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -46,6 +46,10 @@ struct arfs_table { struct hlist_head rules_hash[ARFS_HASH_SIZE]; }; +enum { + MLX5E_ARFS_STATE_ENABLED, +}; + enum arfs_type { ARFS_IPV4_TCP, ARFS_IPV6_TCP, @@ -60,6 +64,7 @@ struct mlx5e_arfs_tables { spinlock_t arfs_lock; int last_filter_id; struct workqueue_struct *wq; + unsigned long state; }; struct arfs_tuple { @@ -170,6 +175,8 @@ int mlx5e_arfs_enable(struct mlx5e_flow_steering *fs) return err; } } + set_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + return 0; } @@ -455,6 +462,8 @@ static void arfs_del_rules(struct mlx5e_flow_steering *fs) int i; int j; + clear_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state); + spin_lock_bh(&arfs->arfs_lock); mlx5e_for_each_arfs_rule(rule, htmp, arfs->arfs_tables, i, j) { hlist_del_init(&rule->hlist); @@ -627,17 +636,8 @@ static void arfs_handle_work(struct work_struct *work) struct mlx5_flow_handle *rule; arfs = mlx5e_fs_get_arfs(priv->fs); - mutex_lock(&priv->state_lock); - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - spin_lock_bh(&arfs->arfs_lock); - hlist_del(&arfs_rule->hlist); - spin_unlock_bh(&arfs->arfs_lock); - - mutex_unlock(&priv->state_lock); - kfree(arfs_rule); - goto out; - } - mutex_unlock(&priv->state_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) + return; if (!arfs_rule->rule) { rule = arfs_add_rule(priv, arfs_rule); @@ -753,6 +753,11 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, return -EPROTONOSUPPORT; spin_lock_bh(&arfs->arfs_lock); + if (!test_bit(MLX5E_ARFS_STATE_ENABLED, &arfs->state)) { + spin_unlock_bh(&arfs->arfs_lock); + return -EPERM; + } + arfs_rule = arfs_find_rule(arfs_t, &fk); if (arfs_rule) { if (arfs_rule->rxq == rxq_index || work_busy(&arfs_rule->arfs_work)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index cc51ce16df14..67a29826bb57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -451,6 +451,34 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, mutex_lock(&priv->state_lock); + if (mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc == ETH_RSS_HASH_XOR) { + unsigned int xor8_max_channels = mlx5e_rqt_max_num_channels_allowed_for_xor8(); + + if (count > xor8_max_channels) { + err = -EINVAL; + netdev_err(priv->netdev, "%s: Requested number of channels (%d) exceeds the maximum allowed by the XOR8 RSS hfunc (%d)\n", + __func__, count, xor8_max_channels); + goto out; + } + } + + /* If RXFH is configured, changing the channels number is allowed only if + * it does not require resizing the RSS table. This is because the previous + * configuration may no longer be compatible with the new RSS table. + */ + if (netif_is_rxfh_configured(priv->netdev)) { + int cur_rqt_size = mlx5e_rqt_size(priv->mdev, cur_params->num_channels); + int new_rqt_size = mlx5e_rqt_size(priv->mdev, count); + + if (new_rqt_size != cur_rqt_size) { + err = -EINVAL; + netdev_err(priv->netdev, + "%s: RXFH is configured, block changing channels number that affects RSS table size (new: %d, current: %d)\n", + __func__, new_rqt_size, cur_rqt_size); + goto out; + } + } + /* Don't allow changing the number of channels if HTB offload is active, * because the numeration of the QoS SQs will change, while per-queue * qdiscs are attached. @@ -561,12 +589,12 @@ static int mlx5e_get_coalesce(struct net_device *netdev, static void mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { - struct mlx5_core_dev *mdev = priv->mdev; int tc; int i; for (i = 0; i < priv->channels.num; ++i) { struct mlx5e_channel *c = priv->channels.c[i]; + struct mlx5_core_dev *mdev = c->mdev; for (tc = 0; tc < c->num_tc; tc++) { mlx5_core_modify_cq_moderation(mdev, @@ -580,11 +608,11 @@ mlx5e_set_priv_channels_tx_coalesce(struct mlx5e_priv *priv, struct ethtool_coal static void mlx5e_set_priv_channels_rx_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { - struct mlx5_core_dev *mdev = priv->mdev; int i; for (i = 0; i < priv->channels.num; ++i) { struct mlx5e_channel *c = priv->channels.c[i]; + struct mlx5_core_dev *mdev = c->mdev; mlx5_core_modify_cq_moderation(mdev, &c->rq.cq.mcq, coal->rx_coalesce_usecs, @@ -1281,17 +1309,30 @@ int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh, struct mlx5e_priv *priv = netdev_priv(dev); u32 *rss_context = &rxfh->rss_context; u8 hfunc = rxfh->hfunc; + unsigned int count; int err; mutex_lock(&priv->state_lock); + + count = priv->channels.params.num_channels; + + if (hfunc == ETH_RSS_HASH_XOR) { + unsigned int xor8_max_channels = mlx5e_rqt_max_num_channels_allowed_for_xor8(); + + if (count > xor8_max_channels) { + err = -EINVAL; + netdev_err(priv->netdev, "%s: Cannot set RSS hash function to XOR, current number of channels (%d) exceeds the maximum allowed for XOR8 RSS hfunc (%d)\n", + __func__, count, xor8_max_channels); + goto unlock; + } + } + if (*rss_context && rxfh->rss_delete) { err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context); goto unlock; } if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) { - unsigned int count = priv->channels.params.num_channels; - err = mlx5e_rx_res_rss_init(priv->rx_res, rss_context, count); if (err) goto unlock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 91848eae4565..319930c04093 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -209,8 +209,8 @@ static int mlx5e_devcom_init_mpv(struct mlx5e_priv *priv, u64 *data) *data, mlx5e_devcom_event_mpv, priv); - if (IS_ERR_OR_NULL(priv->devcom)) - return -EOPNOTSUPP; + if (IS_ERR(priv->devcom)) + return PTR_ERR(priv->devcom); if (mlx5_core_is_mp_master(priv->mdev)) { mlx5_devcom_send_event(priv->devcom, MPV_DEVCOM_MASTER_UP, @@ -5726,9 +5726,7 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) kfree(priv->tx_rates); kfree(priv->txq2sq); destroy_workqueue(priv->wq); - mutex_lock(&priv->state_lock); mlx5e_selq_cleanup(&priv->selq); - mutex_unlock(&priv->state_lock); free_cpumask_var(priv->scratchpad.cpumask); for (i = 0; i < priv->htb_max_qos_sqs; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 2fa076b23fbe..e21a3b4128ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -398,6 +398,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) { u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata); + mlx5e_ptp_metadata_fifo_pop(&sq->ptpsq->metadata_freelist); + mlx5e_skb_cb_hwtstamp_init(skb); mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, metadata_index); @@ -496,9 +498,6 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, err_drop: stats->dropped++; - if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) - mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist, - be32_to_cpu(eseg->flow_table_metadata)); dev_kfree_skb_any(skb); mlx5e_tx_flush(sq); } @@ -657,7 +656,7 @@ static void mlx5e_cqe_ts_id_eseg(struct mlx5e_ptpsq *ptpsq, struct sk_buff *skb, { if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) eseg->flow_table_metadata = - cpu_to_be32(mlx5e_ptp_metadata_fifo_pop(&ptpsq->metadata_freelist)); + cpu_to_be32(mlx5e_ptp_metadata_fifo_peek(&ptpsq->metadata_freelist)); } static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 3047d7015c52..1789800faaeb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1868,6 +1868,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) if (err) goto abort; + dev->priv.eswitch = esw; err = esw_offloads_init(esw); if (err) goto reps_err; @@ -1892,11 +1893,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; else esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; - if (MLX5_ESWITCH_MANAGER(dev) && - mlx5_esw_vport_match_metadata_supported(esw)) - esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA; - - dev->priv.eswitch = esw; BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head); esw_info(dev, @@ -1908,6 +1904,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) reps_err: mlx5_esw_vports_cleanup(esw); + dev->priv.eswitch = NULL; abort: if (esw->work_queue) destroy_workqueue(esw->work_queue); @@ -1926,7 +1923,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw_info(esw->dev, "cleanup\n"); - esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); WARN_ON(refcount_read(&esw->qos.refcnt)); mutex_destroy(&esw->state_lock); @@ -1937,6 +1933,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) mutex_destroy(&esw->offloads.encap_tbl_lock); mutex_destroy(&esw->offloads.decap_tbl_lock); esw_offloads_cleanup(esw); + esw->dev->priv.eswitch = NULL; mlx5_esw_vports_cleanup(esw); debugfs_remove_recursive(esw->debugfs_root); devl_params_unregister(priv_to_devlink(esw->dev), mlx5_eswitch_params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index baaae628b0a0..844d3e3a65dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -43,6 +43,7 @@ #include "rdma.h" #include "en.h" #include "fs_core.h" +#include "lib/mlx5.h" #include "lib/devcom.h" #include "lib/eq.h" #include "lib/fs_chains.h" @@ -2476,6 +2477,10 @@ int esw_offloads_init(struct mlx5_eswitch *esw) if (err) return err; + if (MLX5_ESWITCH_MANAGER(esw->dev) && + mlx5_esw_vport_match_metadata_supported(esw)) + esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA; + err = devl_params_register(priv_to_devlink(esw->dev), esw_devlink_params, ARRAY_SIZE(esw_devlink_params)); @@ -3055,7 +3060,7 @@ void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw, u64 key) key, mlx5_esw_offloads_devcom_event, esw); - if (IS_ERR_OR_NULL(esw->devcom)) + if (IS_ERR(esw->devcom)) return; mlx5_devcom_send_event(esw->devcom, @@ -3707,6 +3712,12 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; + if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && mlx5_get_sd(esw->dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Can't change E-Switch mode to switchdev when multi-PF netdev (Socket Direct) is configured."); + return -EPERM; + } + mlx5_lag_disable_change(esw->dev); err = mlx5_esw_try_lock(esw); if (err < 0) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index e6bfa7e4f146..cf085a478e3e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1664,6 +1664,16 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft, return err; } +static bool mlx5_pkt_reformat_cmp(struct mlx5_pkt_reformat *p1, + struct mlx5_pkt_reformat *p2) +{ + return p1->owner == p2->owner && + (p1->owner == MLX5_FLOW_RESOURCE_OWNER_FW ? + p1->id == p2->id : + mlx5_fs_dr_action_get_pkt_reformat_id(p1) == + mlx5_fs_dr_action_get_pkt_reformat_id(p2)); +} + static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, struct mlx5_flow_destination *d2) { @@ -1675,8 +1685,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ? (d1->vport.vhca_id == d2->vport.vhca_id) : true) && ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ? - (d1->vport.pkt_reformat->id == - d2->vport.pkt_reformat->id) : true)) || + mlx5_pkt_reformat_cmp(d1->vport.pkt_reformat, + d2->vport.pkt_reformat) : true)) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && d1->ft == d2->ft) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR && @@ -1808,8 +1818,9 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, } trace_mlx5_fs_set_fte(fte, false); + /* Link newly added rules into the tree. */ for (i = 0; i < handle->num_rules; i++) { - if (refcount_read(&handle->rule[i]->node.refcount) == 1) { + if (!handle->rule[i]->node.parent) { tree_add_node(&handle->rule[i]->node, &fte->node); trace_mlx5_fs_add_rule(handle->rule[i]); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index d14459e5c04f..69d482f7c5a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -703,8 +703,10 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev) return err; } - if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) + if (test_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, &flags)) { mlx5_lag_port_sel_destroy(ldev); + ldev->buckets = 1; + } if (mlx5_lag_has_drop_rule(ldev)) mlx5_lag_drop_rule_cleanup(ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index e7d59cfa8708..7b0766c89f4c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -220,7 +220,7 @@ mlx5_devcom_register_component(struct mlx5_devcom_dev *devc, struct mlx5_devcom_comp *comp; if (IS_ERR_OR_NULL(devc)) - return NULL; + return ERR_PTR(-EINVAL); mutex_lock(&comp_list_lock); comp = devcom_component_get(devc, id, key, handler); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index 5b28084e8a03..dd5d186dc614 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -213,8 +213,8 @@ static int sd_register(struct mlx5_core_dev *dev) sd = mlx5_get_sd(dev); devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP, sd->group_id, NULL, dev); - if (!devcom) - return -ENOMEM; + if (IS_ERR(devcom)) + return PTR_ERR(devcom); sd->devcom = devcom; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c2593625c09a..331ce47f51a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -956,7 +956,7 @@ static void mlx5_register_hca_devcom_comp(struct mlx5_core_dev *dev) mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_HCA_PORTS, mlx5_query_nic_system_image_guid(dev), NULL, dev); - if (IS_ERR_OR_NULL(dev->priv.hca_devcom_comp)) + if (IS_ERR(dev->priv.hca_devcom_comp)) mlx5_core_err(dev, "Failed to register devcom HCA component\n"); } @@ -1480,6 +1480,14 @@ int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev) if (err) goto err_register; + err = mlx5_crdump_enable(dev); + if (err) + mlx5_core_err(dev, "mlx5_crdump_enable failed with error code %d\n", err); + + err = mlx5_hwmon_dev_register(dev); + if (err) + mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err); + mutex_unlock(&dev->intf_state_mutex); return 0; @@ -1505,7 +1513,10 @@ int mlx5_init_one(struct mlx5_core_dev *dev) int err; devl_lock(devlink); + devl_register(devlink); err = mlx5_init_one_devl_locked(dev); + if (err) + devl_unregister(devlink); devl_unlock(devlink); return err; } @@ -1517,6 +1528,8 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev) devl_lock(devlink); mutex_lock(&dev->intf_state_mutex); + mlx5_hwmon_dev_unregister(dev); + mlx5_crdump_disable(dev); mlx5_unregister_device(dev); if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { @@ -1534,6 +1547,7 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev) mlx5_function_teardown(dev, true); out: mutex_unlock(&dev->intf_state_mutex); + devl_unregister(devlink); devl_unlock(devlink); } @@ -1680,16 +1694,23 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev) } devl_lock(devlink); + devl_register(devlink); + err = mlx5_devlink_params_register(priv_to_devlink(dev)); - devl_unlock(devlink); if (err) { mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err); - goto query_hca_caps_err; + goto params_reg_err; } + devl_unlock(devlink); return 0; +params_reg_err: + devl_unregister(devlink); + devl_unlock(devlink); query_hca_caps_err: + devl_unregister(devlink); + devl_unlock(devlink); mlx5_function_disable(dev, true); out: dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; @@ -1702,6 +1723,7 @@ void mlx5_uninit_one_light(struct mlx5_core_dev *dev) devl_lock(devlink); mlx5_devlink_params_unregister(priv_to_devlink(dev)); + devl_unregister(devlink); devl_unlock(devlink); if (dev->state != MLX5_DEVICE_STATE_UP) return; @@ -1943,16 +1965,7 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_init_one; } - err = mlx5_crdump_enable(dev); - if (err) - dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); - - err = mlx5_hwmon_dev_register(dev); - if (err) - mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err); - pci_save_state(pdev); - devlink_register(devlink); return 0; err_init_one: @@ -1973,16 +1986,9 @@ static void remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(dev); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); - /* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using - * devlink notify APIs. - * Hence, we must drain them before unregistering the devlink. - */ mlx5_drain_fw_reset(dev); mlx5_drain_health_wq(dev); - devlink_unregister(devlink); mlx5_sriov_disable(pdev, false); - mlx5_hwmon_dev_unregister(dev); - mlx5_crdump_disable(dev); mlx5_uninit_one(dev); mlx5_pci_close(dev); mlx5_mdev_uninit(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 4dcf995cb1a2..6bac8ad70ba6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -19,6 +19,7 @@ #define MLX5_IRQ_CTRL_SF_MAX 8 /* min num of vectors for SFs to be enabled */ #define MLX5_IRQ_VEC_COMP_BASE_SF 2 +#define MLX5_IRQ_VEC_COMP_BASE 1 #define MLX5_EQ_SHARE_IRQ_MAX_COMP (8) #define MLX5_EQ_SHARE_IRQ_MAX_CTRL (UINT_MAX) @@ -246,6 +247,7 @@ static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) return; } + vecidx -= MLX5_IRQ_VEC_COMP_BASE; snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx); } @@ -585,7 +587,7 @@ struct mlx5_irq *mlx5_irq_request_vector(struct mlx5_core_dev *dev, u16 cpu, struct mlx5_irq_table *table = mlx5_irq_table_get(dev); struct mlx5_irq_pool *pool = table->pcif_pool; struct irq_affinity_desc af_desc; - int offset = 1; + int offset = MLX5_IRQ_VEC_COMP_BASE; if (!pool->xa_num_irqs.max) offset = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index bc863e1f062e..7ebe71280827 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -75,7 +75,6 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto peer_devlink_set_err; } - devlink_register(devlink); return 0; peer_devlink_set_err: @@ -101,7 +100,6 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev) devlink = priv_to_devlink(mdev); set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state); mlx5_drain_health_wq(mdev); - devlink_unregister(devlink); if (mlx5_dev_is_lightweight(mdev)) mlx5_uninit_one_light(mdev); else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c index 64f4cc284aea..030a5776c937 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c @@ -205,12 +205,11 @@ dr_dump_hex_print(char hex[DR_HEX_SIZE], char *src, u32 size) } static int -dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id, +dr_dump_rule_action_mem(struct seq_file *file, char *buff, const u64 rule_id, struct mlx5dr_rule_action_member *action_mem) { struct mlx5dr_action *action = action_mem->action; const u64 action_id = DR_DBG_PTR_TO_ID(action); - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; u64 hit_tbl_ptr, miss_tbl_ptr; u32 hit_tbl_id, miss_tbl_id; int ret; @@ -488,10 +487,9 @@ dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id, } static int -dr_dump_rule_mem(struct seq_file *file, struct mlx5dr_ste *ste, +dr_dump_rule_mem(struct seq_file *file, char *buff, struct mlx5dr_ste *ste, bool is_rx, const u64 rule_id, u8 format_ver) { - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; char hw_ste_dump[DR_HEX_SIZE]; u32 mem_rec_type; int ret; @@ -522,7 +520,8 @@ dr_dump_rule_mem(struct seq_file *file, struct mlx5dr_ste *ste, } static int -dr_dump_rule_rx_tx(struct seq_file *file, struct mlx5dr_rule_rx_tx *rule_rx_tx, +dr_dump_rule_rx_tx(struct seq_file *file, char *buff, + struct mlx5dr_rule_rx_tx *rule_rx_tx, bool is_rx, const u64 rule_id, u8 format_ver) { struct mlx5dr_ste *ste_arr[DR_RULE_MAX_STES + DR_ACTION_MAX_STES]; @@ -533,7 +532,7 @@ dr_dump_rule_rx_tx(struct seq_file *file, struct mlx5dr_rule_rx_tx *rule_rx_tx, return 0; while (i--) { - ret = dr_dump_rule_mem(file, ste_arr[i], is_rx, rule_id, + ret = dr_dump_rule_mem(file, buff, ste_arr[i], is_rx, rule_id, format_ver); if (ret < 0) return ret; @@ -542,7 +541,8 @@ dr_dump_rule_rx_tx(struct seq_file *file, struct mlx5dr_rule_rx_tx *rule_rx_tx, return 0; } -static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule) +static noinline_for_stack int +dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule) { struct mlx5dr_rule_action_member *action_mem; const u64 rule_id = DR_DBG_PTR_TO_ID(rule); @@ -565,19 +565,19 @@ static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule) return ret; if (rx->nic_matcher) { - ret = dr_dump_rule_rx_tx(file, rx, true, rule_id, format_ver); + ret = dr_dump_rule_rx_tx(file, buff, rx, true, rule_id, format_ver); if (ret < 0) return ret; } if (tx->nic_matcher) { - ret = dr_dump_rule_rx_tx(file, tx, false, rule_id, format_ver); + ret = dr_dump_rule_rx_tx(file, buff, tx, false, rule_id, format_ver); if (ret < 0) return ret; } list_for_each_entry(action_mem, &rule->rule_actions_list, list) { - ret = dr_dump_rule_action_mem(file, rule_id, action_mem); + ret = dr_dump_rule_action_mem(file, buff, rule_id, action_mem); if (ret < 0) return ret; } @@ -586,10 +586,10 @@ static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule) } static int -dr_dump_matcher_mask(struct seq_file *file, struct mlx5dr_match_param *mask, +dr_dump_matcher_mask(struct seq_file *file, char *buff, + struct mlx5dr_match_param *mask, u8 criteria, const u64 matcher_id) { - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; char dump[DR_HEX_SIZE]; int ret; @@ -681,10 +681,10 @@ dr_dump_matcher_mask(struct seq_file *file, struct mlx5dr_match_param *mask, } static int -dr_dump_matcher_builder(struct seq_file *file, struct mlx5dr_ste_build *builder, +dr_dump_matcher_builder(struct seq_file *file, char *buff, + struct mlx5dr_ste_build *builder, u32 index, bool is_rx, const u64 matcher_id) { - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; int ret; ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, @@ -702,11 +702,10 @@ dr_dump_matcher_builder(struct seq_file *file, struct mlx5dr_ste_build *builder, } static int -dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx, +dr_dump_matcher_rx_tx(struct seq_file *file, char *buff, bool is_rx, struct mlx5dr_matcher_rx_tx *matcher_rx_tx, const u64 matcher_id) { - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; enum dr_dump_rec_type rec_type; u64 s_icm_addr, e_icm_addr; int i, ret; @@ -731,7 +730,7 @@ dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx, return ret; for (i = 0; i < matcher_rx_tx->num_of_builders; i++) { - ret = dr_dump_matcher_builder(file, + ret = dr_dump_matcher_builder(file, buff, &matcher_rx_tx->ste_builder[i], i, is_rx, matcher_id); if (ret < 0) @@ -741,7 +740,7 @@ dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx, return 0; } -static int +static noinline_for_stack int dr_dump_matcher(struct seq_file *file, struct mlx5dr_matcher *matcher) { struct mlx5dr_matcher_rx_tx *rx = &matcher->rx; @@ -763,19 +762,19 @@ dr_dump_matcher(struct seq_file *file, struct mlx5dr_matcher *matcher) if (ret) return ret; - ret = dr_dump_matcher_mask(file, &matcher->mask, + ret = dr_dump_matcher_mask(file, buff, &matcher->mask, matcher->match_criteria, matcher_id); if (ret < 0) return ret; if (rx->nic_tbl) { - ret = dr_dump_matcher_rx_tx(file, true, rx, matcher_id); + ret = dr_dump_matcher_rx_tx(file, buff, true, rx, matcher_id); if (ret < 0) return ret; } if (tx->nic_tbl) { - ret = dr_dump_matcher_rx_tx(file, false, tx, matcher_id); + ret = dr_dump_matcher_rx_tx(file, buff, false, tx, matcher_id); if (ret < 0) return ret; } @@ -803,11 +802,10 @@ dr_dump_matcher_all(struct seq_file *file, struct mlx5dr_matcher *matcher) } static int -dr_dump_table_rx_tx(struct seq_file *file, bool is_rx, +dr_dump_table_rx_tx(struct seq_file *file, char *buff, bool is_rx, struct mlx5dr_table_rx_tx *table_rx_tx, const u64 table_id) { - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; enum dr_dump_rec_type rec_type; u64 s_icm_addr; int ret; @@ -829,7 +827,8 @@ dr_dump_table_rx_tx(struct seq_file *file, bool is_rx, return 0; } -static int dr_dump_table(struct seq_file *file, struct mlx5dr_table *table) +static noinline_for_stack int +dr_dump_table(struct seq_file *file, struct mlx5dr_table *table) { struct mlx5dr_table_rx_tx *rx = &table->rx; struct mlx5dr_table_rx_tx *tx = &table->tx; @@ -848,14 +847,14 @@ static int dr_dump_table(struct seq_file *file, struct mlx5dr_table *table) return ret; if (rx->nic_dmn) { - ret = dr_dump_table_rx_tx(file, true, rx, + ret = dr_dump_table_rx_tx(file, buff, true, rx, DR_DBG_PTR_TO_ID(table)); if (ret < 0) return ret; } if (tx->nic_dmn) { - ret = dr_dump_table_rx_tx(file, false, tx, + ret = dr_dump_table_rx_tx(file, buff, false, tx, DR_DBG_PTR_TO_ID(table)); if (ret < 0) return ret; @@ -881,10 +880,10 @@ static int dr_dump_table_all(struct seq_file *file, struct mlx5dr_table *tbl) } static int -dr_dump_send_ring(struct seq_file *file, struct mlx5dr_send_ring *ring, +dr_dump_send_ring(struct seq_file *file, char *buff, + struct mlx5dr_send_ring *ring, const u64 domain_id) { - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; int ret; ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, @@ -902,13 +901,13 @@ dr_dump_send_ring(struct seq_file *file, struct mlx5dr_send_ring *ring, return 0; } -static noinline_for_stack int +static int dr_dump_domain_info_flex_parser(struct seq_file *file, + char *buff, const char *flex_parser_name, const u8 flex_parser_value, const u64 domain_id) { - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; int ret; ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH, @@ -925,11 +924,11 @@ dr_dump_domain_info_flex_parser(struct seq_file *file, return 0; } -static noinline_for_stack int -dr_dump_domain_info_caps(struct seq_file *file, struct mlx5dr_cmd_caps *caps, +static int +dr_dump_domain_info_caps(struct seq_file *file, char *buff, + struct mlx5dr_cmd_caps *caps, const u64 domain_id) { - char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH]; struct mlx5dr_cmd_vport_cap *vport_caps; unsigned long i, vports_num; int ret; @@ -969,34 +968,35 @@ dr_dump_domain_info_caps(struct seq_file *file, struct mlx5dr_cmd_caps *caps, } static int -dr_dump_domain_info(struct seq_file *file, struct mlx5dr_domain_info *info, +dr_dump_domain_info(struct seq_file *file, char *buff, + struct mlx5dr_domain_info *info, const u64 domain_id) { int ret; - ret = dr_dump_domain_info_caps(file, &info->caps, domain_id); + ret = dr_dump_domain_info_caps(file, buff, &info->caps, domain_id); if (ret < 0) return ret; - ret = dr_dump_domain_info_flex_parser(file, "icmp_dw0", + ret = dr_dump_domain_info_flex_parser(file, buff, "icmp_dw0", info->caps.flex_parser_id_icmp_dw0, domain_id); if (ret < 0) return ret; - ret = dr_dump_domain_info_flex_parser(file, "icmp_dw1", + ret = dr_dump_domain_info_flex_parser(file, buff, "icmp_dw1", info->caps.flex_parser_id_icmp_dw1, domain_id); if (ret < 0) return ret; - ret = dr_dump_domain_info_flex_parser(file, "icmpv6_dw0", + ret = dr_dump_domain_info_flex_parser(file, buff, "icmpv6_dw0", info->caps.flex_parser_id_icmpv6_dw0, domain_id); if (ret < 0) return ret; - ret = dr_dump_domain_info_flex_parser(file, "icmpv6_dw1", + ret = dr_dump_domain_info_flex_parser(file, buff, "icmpv6_dw1", info->caps.flex_parser_id_icmpv6_dw1, domain_id); if (ret < 0) @@ -1032,12 +1032,12 @@ dr_dump_domain(struct seq_file *file, struct mlx5dr_domain *dmn) if (ret) return ret; - ret = dr_dump_domain_info(file, &dmn->info, domain_id); + ret = dr_dump_domain_info(file, buff, &dmn->info, domain_id); if (ret < 0) return ret; if (dmn->info.supp_sw_steering) { - ret = dr_dump_send_ring(file, dmn->send_ring, domain_id); + ret = dr_dump_send_ring(file, buff, dmn->send_ring, domain_id); if (ret < 0) return ret; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e4d7739bd7c8..4a79c0d7e7ad 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -849,7 +849,7 @@ free_skb: 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 53b150b7ae4e..6c06b0592760 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 af99bf17eb36..f42a1b1c9368 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 f20052776b3f..92a406f02eae 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -10,6 +10,7 @@ #include <linux/netdevice.h> #include <linux/mutex.h> #include <linux/refcount.h> +#include <linux/idr.h> #include <net/devlink.h> #include <trace/events/mlxsw.h> @@ -58,41 +59,43 @@ 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. @@ -726,6 +731,17 @@ static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) } static void +mlxsw_sp_acl_tcam_rehash_ctx_vchunk_reset(struct mlxsw_sp_acl_tcam_rehash_ctx *ctx) +{ + /* The entry markers are relative to the current chunk and therefore + * needs to be reset together with the chunk marker. + */ + ctx->current_vchunk = NULL; + ctx->start_ventry = NULL; + ctx->stop_ventry = NULL; +} + +static void mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(struct mlxsw_sp_acl_tcam_vchunk *vchunk) { struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion; @@ -747,7 +763,7 @@ 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 462bf448497d..79a1d8606512 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -6,15 +6,16 @@ #include <linux/list.h> #include <linux/parman.h> +#include <linux/idr.h> #include "reg.h" #include "spectrum.h" #include "core_acl_flex_keys.h" struct mlxsw_sp_acl_tcam { - unsigned long *used_regions; /* bit array */ + struct ida used_regions; unsigned int max_regions; - unsigned long *used_groups; /* bit array */ + struct ida used_groups; unsigned int max_groups; unsigned int max_group_size; struct mutex lock; /* guards vregion list */ diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index e5ec0a363aff..31f75b4a67fd 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -368,7 +368,6 @@ union ks8851_tx_hdr { * @rdfifo: FIFO read callback * @wrfifo: FIFO write callback * @start_xmit: start_xmit() implementation callback - * @rx_skb: rx_skb() implementation callback * @flush_tx_work: flush_tx_work() implementation callback * * The @statelock is used to protect information in the structure which may @@ -423,8 +422,6 @@ struct ks8851_net { struct sk_buff *txp, bool irq); netdev_tx_t (*start_xmit)(struct sk_buff *skb, struct net_device *dev); - void (*rx_skb)(struct ks8851_net *ks, - struct sk_buff *skb); void (*flush_tx_work)(struct ks8851_net *ks); }; diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 0bf13b38b8f5..d4cdf3d4f552 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -232,16 +232,6 @@ static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt) } /** - * ks8851_rx_skb - receive skbuff - * @ks: The device state. - * @skb: The skbuff - */ -static void ks8851_rx_skb(struct ks8851_net *ks, struct sk_buff *skb) -{ - ks->rx_skb(ks, skb); -} - -/** * ks8851_rx_pkts - receive packets from the host * @ks: The device information. * @@ -309,7 +299,7 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) ks8851_dbg_dumpkkt(ks, rxpkt); skb->protocol = eth_type_trans(skb, ks->netdev); - ks8851_rx_skb(ks, skb); + __netif_rx(skb); ks->netdev->stats.rx_packets++; ks->netdev->stats.rx_bytes += rxlen; @@ -340,6 +330,8 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) unsigned long flags; unsigned int status; + local_bh_disable(); + ks8851_lock(ks, &flags); status = ks8851_rdreg16(ks, KS_ISR); @@ -416,6 +408,8 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) if (status & IRQ_LCI) mii_check_link(&ks->mii); + local_bh_enable(); + return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c index 2a7f29854267..381b9cd285eb 100644 --- a/drivers/net/ethernet/micrel/ks8851_par.c +++ b/drivers/net/ethernet/micrel/ks8851_par.c @@ -210,16 +210,6 @@ static void ks8851_wrfifo_par(struct ks8851_net *ks, struct sk_buff *txp, iowrite16_rep(ksp->hw_addr, txp->data, len / 2); } -/** - * ks8851_rx_skb_par - receive skbuff - * @ks: The device state. - * @skb: The skbuff - */ -static void ks8851_rx_skb_par(struct ks8851_net *ks, struct sk_buff *skb) -{ - netif_rx(skb); -} - static unsigned int ks8851_rdreg16_par_txqcr(struct ks8851_net *ks) { return ks8851_rdreg16_par(ks, KS_TXQCR); @@ -298,7 +288,6 @@ static int ks8851_probe_par(struct platform_device *pdev) ks->rdfifo = ks8851_rdfifo_par; ks->wrfifo = ks8851_wrfifo_par; ks->start_xmit = ks8851_start_xmit_par; - ks->rx_skb = ks8851_rx_skb_par; #define STD_IRQ (IRQ_LCI | /* Link Change */ \ IRQ_RXI | /* RX done */ \ diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 2f803377c9f9..670c1de966db 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -299,16 +299,6 @@ static unsigned int calc_txlen(unsigned int len) } /** - * ks8851_rx_skb_spi - receive skbuff - * @ks: The device state - * @skb: The skbuff - */ -static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb) -{ - netif_rx(skb); -} - -/** * ks8851_tx_work - process tx packet(s) * @work: The work strucutre what was scheduled. * @@ -435,7 +425,6 @@ static int ks8851_probe_spi(struct spi_device *spi) ks->rdfifo = ks8851_rdfifo_spi; ks->wrfifo = ks8851_wrfifo_spi; ks->start_xmit = ks8851_start_xmit_spi; - ks->rx_skb = ks8851_rx_skb_spi; ks->flush_tx_work = ks8851_flush_tx_work_spi; #define STD_IRQ (IRQ_LCI | /* Link Change */ \ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 3a1b1a1f5a19..60dd2fd603a8 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -731,7 +731,7 @@ static int sparx5_port_pcs_low_set(struct sparx5 *sparx5, bool sgmii = false, inband_aneg = false; int err; - if (port->conf.inband) { + if (conf->inband) { if (conf->portmode == PHY_INTERFACE_MODE_SGMII || conf->portmode == PHY_INTERFACE_MODE_QSGMII) inband_aneg = true; /* Cisco-SGMII in-band-aneg */ @@ -948,7 +948,7 @@ int sparx5_port_pcs_set(struct sparx5 *sparx5, if (err) return -EINVAL; - if (port->conf.inband) { + if (conf->inband) { /* Enable/disable 1G counters in ASM */ spx5_rmw(ASM_PORT_CFG_CSC_STAT_DIS_SET(high_speed_dev), ASM_PORT_CFG_CSC_STAT_DIS, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 523e0c470894..55f255a3c9db 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -36,6 +36,27 @@ struct sparx5_tc_flower_template { u16 l3_proto; /* protocol specified in the template */ }; +/* SparX-5 VCAP fragment types: + * 0 = no fragment, 1 = initial fragment, + * 2 = suspicious fragment, 3 = valid follow-up fragment + */ +enum { /* key / mask */ + FRAG_NOT = 0x03, /* 0 / 3 */ + FRAG_SOME = 0x11, /* 1 / 1 */ + FRAG_FIRST = 0x13, /* 1 / 3 */ + FRAG_LATER = 0x33, /* 3 / 3 */ + FRAG_INVAL = 0xff, /* invalid */ +}; + +/* Flower fragment flag to VCAP fragment type mapping */ +static const u8 sparx5_vcap_frag_map[4][4] = { /* is_frag */ + { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_FIRST }, /* 0/0 */ + { FRAG_NOT, FRAG_NOT, FRAG_INVAL, FRAG_INVAL }, /* 0/1 */ + { FRAG_INVAL, FRAG_INVAL, FRAG_INVAL, FRAG_INVAL }, /* 1/0 */ + { FRAG_SOME, FRAG_LATER, FRAG_INVAL, FRAG_FIRST } /* 1/1 */ + /* 0/0 0/1 1/0 1/1 <-- first_frag */ +}; + static int sparx5_tc_flower_es0_tpid(struct vcap_tc_flower_parse_usage *st) { @@ -145,29 +166,27 @@ sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) flow_rule_match_control(st->frule, &mt); if (mt.mask->flags) { - if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { - if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { - value = 1; /* initial fragment */ - mask = 0x3; - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } - } - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } + u8 is_frag_key = !!(mt.key->flags & FLOW_DIS_IS_FRAGMENT); + u8 is_frag_mask = !!(mt.mask->flags & FLOW_DIS_IS_FRAGMENT); + u8 is_frag_idx = (is_frag_key << 1) | is_frag_mask; + + u8 first_frag_key = !!(mt.key->flags & FLOW_DIS_FIRST_FRAG); + u8 first_frag_mask = !!(mt.mask->flags & FLOW_DIS_FIRST_FRAG); + u8 first_frag_idx = (first_frag_key << 1) | first_frag_mask; + + /* Lookup verdict based on the 2 + 2 input bits */ + u8 vdt = sparx5_vcap_frag_map[is_frag_idx][first_frag_idx]; + + if (vdt == FRAG_INVAL) { + NL_SET_ERR_MSG_MOD(st->fco->common.extack, + "Match on invalid fragment flag combination"); + return -EINVAL; } + /* Extract VCAP fragment key and mask from verdict */ + value = (vdt >> 4) & 0x3; + mask = vdt & 0x3; + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_FRAGMENT_TYPE, value, mask); diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h index 4c043052198d..00882ffc7a02 100644 --- a/drivers/net/ethernet/realtek/r8169.h +++ b/drivers/net/ethernet/realtek/r8169.h @@ -73,6 +73,7 @@ enum mac_version { }; struct rtl8169_private; +struct r8169_led_classdev; void r8169_apply_firmware(struct rtl8169_private *tp); u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp); @@ -84,7 +85,8 @@ void r8169_get_led_name(struct rtl8169_private *tp, int idx, char *buf, int buf_len); int rtl8168_get_led_mode(struct rtl8169_private *tp); int rtl8168_led_mod_ctrl(struct rtl8169_private *tp, u16 mask, u16 val); -void rtl8168_init_leds(struct net_device *ndev); +struct r8169_led_classdev *rtl8168_init_leds(struct net_device *ndev); int rtl8125_get_led_mode(struct rtl8169_private *tp, int index); int rtl8125_set_led_mode(struct rtl8169_private *tp, int index, u16 mode); -void rtl8125_init_leds(struct net_device *ndev); +struct r8169_led_classdev *rtl8125_init_leds(struct net_device *ndev); +void r8169_remove_leds(struct r8169_led_classdev *leds); diff --git a/drivers/net/ethernet/realtek/r8169_leds.c b/drivers/net/ethernet/realtek/r8169_leds.c index 7c5dc9d0df85..e10bee706bc6 100644 --- a/drivers/net/ethernet/realtek/r8169_leds.c +++ b/drivers/net/ethernet/realtek/r8169_leds.c @@ -146,22 +146,22 @@ static void rtl8168_setup_ldev(struct r8169_led_classdev *ldev, led_cdev->hw_control_get_device = r8169_led_hw_control_get_device; /* ignore errors */ - devm_led_classdev_register(&ndev->dev, led_cdev); + led_classdev_register(&ndev->dev, led_cdev); } -void rtl8168_init_leds(struct net_device *ndev) +struct r8169_led_classdev *rtl8168_init_leds(struct net_device *ndev) { - /* bind resource mgmt to netdev */ - struct device *dev = &ndev->dev; struct r8169_led_classdev *leds; int i; - leds = devm_kcalloc(dev, RTL8168_NUM_LEDS, sizeof(*leds), GFP_KERNEL); + leds = kcalloc(RTL8168_NUM_LEDS + 1, sizeof(*leds), GFP_KERNEL); if (!leds) - return; + return NULL; for (i = 0; i < RTL8168_NUM_LEDS; i++) rtl8168_setup_ldev(leds + i, ndev, i); + + return leds; } static int rtl8125_led_hw_control_is_supported(struct led_classdev *led_cdev, @@ -245,20 +245,31 @@ static void rtl8125_setup_led_ldev(struct r8169_led_classdev *ldev, led_cdev->hw_control_get_device = r8169_led_hw_control_get_device; /* ignore errors */ - devm_led_classdev_register(&ndev->dev, led_cdev); + led_classdev_register(&ndev->dev, led_cdev); } -void rtl8125_init_leds(struct net_device *ndev) +struct r8169_led_classdev *rtl8125_init_leds(struct net_device *ndev) { - /* bind resource mgmt to netdev */ - struct device *dev = &ndev->dev; struct r8169_led_classdev *leds; int i; - leds = devm_kcalloc(dev, RTL8125_NUM_LEDS, sizeof(*leds), GFP_KERNEL); + leds = kcalloc(RTL8125_NUM_LEDS + 1, sizeof(*leds), GFP_KERNEL); if (!leds) - return; + return NULL; for (i = 0; i < RTL8125_NUM_LEDS; i++) rtl8125_setup_led_ldev(leds + i, ndev, i); + + return leds; +} + +void r8169_remove_leds(struct r8169_led_classdev *leds) +{ + if (!leds) + return; + + for (struct r8169_led_classdev *l = leds; l->ndev; l++) + led_classdev_unregister(&l->led); + + kfree(leds); } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 6f1e6f386b7b..0fc5fe564ae5 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -647,6 +647,8 @@ struct rtl8169_private { const char *fw_name; struct rtl_fw *rtl_fw; + struct r8169_led_classdev *leds; + u32 ocp_base; }; @@ -5044,6 +5046,9 @@ static void rtl_remove_one(struct pci_dev *pdev) cancel_work_sync(&tp->wk.work); + if (IS_ENABLED(CONFIG_R8169_LEDS)) + r8169_remove_leds(tp->leds); + unregister_netdev(tp->dev); if (tp->dash_type != RTL_DASH_NONE) @@ -5501,9 +5506,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (IS_ENABLED(CONFIG_R8169_LEDS)) { if (rtl_is_8125(tp)) - rtl8125_init_leds(dev); + tp->leds = rtl8125_init_leds(dev); else if (tp->mac_version > RTL_GIGA_MAC_VER_06) - rtl8168_init_leds(dev); + tp->leds = rtl8168_init_leds(dev); } netdev_info(dev, "%s, %pM, XID %03x, IRQ %d\n", diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ba01c8cc3c90..9b1f639f64a1 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -769,25 +769,28 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) dma_addr_t dma_addr; int rx_packets = 0; u8 desc_status; - u16 pkt_len; + u16 desc_len; u8 die_dt; int entry; int limit; int i; - entry = priv->cur_rx[q] % priv->num_rx_ring[q]; limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; stats = &priv->stats[q]; - desc = &priv->rx_ring[q].desc[entry]; - for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) { + for (i = 0; i < limit; i++, priv->cur_rx[q]++) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->rx_ring[q].desc[entry]; + if (rx_packets == *quota || desc->die_dt == DT_FEMPTY) + break; + /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; - pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; + desc_len = le16_to_cpu(desc->ds_cc) & RX_DS; /* We use 0-byte descriptors to mark the DMA mapping errors */ - if (!pkt_len) + if (!desc_len) continue; if (desc_status & MSC_MC) @@ -808,25 +811,25 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) switch (die_dt) { case DT_FSINGLE: skb = ravb_get_skb_gbeth(ndev, entry, desc); - skb_put(skb, pkt_len); + skb_put(skb, desc_len); skb->protocol = eth_type_trans(skb, ndev); if (ndev->features & NETIF_F_RXCSUM) ravb_rx_csum_gbeth(skb); napi_gro_receive(&priv->napi[q], skb); rx_packets++; - stats->rx_bytes += pkt_len; + stats->rx_bytes += desc_len; break; case DT_FSTART: priv->rx_1st_skb = ravb_get_skb_gbeth(ndev, entry, desc); - skb_put(priv->rx_1st_skb, pkt_len); + skb_put(priv->rx_1st_skb, desc_len); break; case DT_FMID: skb = ravb_get_skb_gbeth(ndev, entry, desc); skb_copy_to_linear_data_offset(priv->rx_1st_skb, priv->rx_1st_skb->len, skb->data, - pkt_len); - skb_put(priv->rx_1st_skb, pkt_len); + desc_len); + skb_put(priv->rx_1st_skb, desc_len); dev_kfree_skb(skb); break; case DT_FEND: @@ -834,23 +837,20 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) skb_copy_to_linear_data_offset(priv->rx_1st_skb, priv->rx_1st_skb->len, skb->data, - pkt_len); - skb_put(priv->rx_1st_skb, pkt_len); + desc_len); + skb_put(priv->rx_1st_skb, desc_len); dev_kfree_skb(skb); priv->rx_1st_skb->protocol = eth_type_trans(priv->rx_1st_skb, ndev); if (ndev->features & NETIF_F_RXCSUM) - ravb_rx_csum_gbeth(skb); + ravb_rx_csum_gbeth(priv->rx_1st_skb); + stats->rx_bytes += priv->rx_1st_skb->len; napi_gro_receive(&priv->napi[q], priv->rx_1st_skb); rx_packets++; - stats->rx_bytes += pkt_len; break; } } - - entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q].desc[entry]; } /* Refill the RX ring buffers. */ @@ -891,30 +891,29 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - int entry = priv->cur_rx[q] % priv->num_rx_ring[q]; - int boguscnt = (priv->dirty_rx[q] + priv->num_rx_ring[q]) - - priv->cur_rx[q]; struct net_device_stats *stats = &priv->stats[q]; struct ravb_ex_rx_desc *desc; + unsigned int limit, i; struct sk_buff *skb; dma_addr_t dma_addr; struct timespec64 ts; + int rx_packets = 0; u8 desc_status; u16 pkt_len; - int limit; + int entry; + + limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; + for (i = 0; i < limit; i++, priv->cur_rx[q]++) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->rx_ring[q].ex_desc[entry]; + if (rx_packets == *quota || desc->die_dt == DT_FEMPTY) + break; - boguscnt = min(boguscnt, *quota); - limit = boguscnt; - desc = &priv->rx_ring[q].ex_desc[entry]; - while (desc->die_dt != DT_FEMPTY) { /* Descriptor type must be checked before all other reads */ dma_rmb(); desc_status = desc->msc; pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; - if (--boguscnt < 0) - break; - /* We use 0-byte descriptors to mark the DMA mapping errors */ if (!pkt_len) continue; @@ -960,12 +959,9 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) if (ndev->features & NETIF_F_RXCSUM) ravb_rx_csum(skb); napi_gro_receive(&priv->napi[q], skb); - stats->rx_packets++; + rx_packets++; stats->rx_bytes += pkt_len; } - - entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q].ex_desc[entry]; } /* Refill the RX ring buffers. */ @@ -995,9 +991,9 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) desc->die_dt = DT_FEMPTY; } - *quota -= limit - (++boguscnt); - - return boguscnt <= 0; + stats->rx_packets += rx_packets; + *quota -= rx_packets; + return *quota == 0; } /* Packet receive function for Ethernet AVB */ @@ -2726,19 +2722,18 @@ 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; } @@ -2748,9 +2743,9 @@ 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/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index a6fefe675ef1..3b7d4ac1e7be 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -553,6 +553,7 @@ extern const struct stmmac_hwtimestamp stmmac_ptp; extern const struct stmmac_mode_ops dwmac4_ring_mode_ops; struct mac_link { + u32 caps; u32 speed_mask; u32 speed10; u32 speed100; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index b21d99faa2d0..e1b761dcfa1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1096,6 +1096,8 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv) priv->dev->priv_flags |= IFF_UNICAST_FLT; + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; /* The loopback bit seems to be re-set when link change * Simply mask it each time * Speed 10/100/1000 are set in BIT(2)/BIT(3) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 3927609abc44..8555299443f4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -539,6 +539,8 @@ int dwmac1000_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; mac->link.duplex = GMAC_CONTROL_DM; mac->link.speed10 = GMAC_CONTROL_PS; mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index a6e8d7bd9588..7667d103cd0e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -175,6 +175,8 @@ int dwmac100_setup(struct stmmac_priv *priv) dev_info(priv->device, "\tDWMAC100\n"); mac->pcsr = priv->ioaddr; + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; mac->link.duplex = MAC_CONTROL_F; mac->link.speed10 = 0; mac->link.speed100 = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index cef25efbdff9..a38226d7cc6a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -70,7 +70,10 @@ static void dwmac4_core_init(struct mac_device_info *hw, static void dwmac4_phylink_get_caps(struct stmmac_priv *priv) { - priv->phylink_config.mac_capabilities |= MAC_2500FD; + if (priv->plat->tx_queues_to_use > 1) + priv->hw->link.caps &= ~(MAC_10HD | MAC_100HD | MAC_1000HD); + else + priv->hw->link.caps |= (MAC_10HD | MAC_100HD | MAC_1000HD); } static void dwmac4_rx_queue_enable(struct mac_device_info *hw, @@ -1378,6 +1381,8 @@ int dwmac4_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; mac->link.duplex = GMAC_CONFIG_DM; mac->link.speed10 = GMAC_CONFIG_PS; mac->link.speed100 = GMAC_CONFIG_FES | GMAC_CONFIG_PS; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index e841e312077e..f8e7775bb633 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -47,14 +47,6 @@ static void dwxgmac2_core_init(struct mac_device_info *hw, writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN); } -static void xgmac_phylink_get_caps(struct stmmac_priv *priv) -{ - priv->phylink_config.mac_capabilities |= MAC_2500FD | MAC_5000FD | - MAC_10000FD | MAC_25000FD | - MAC_40000FD | MAC_50000FD | - MAC_100000FD; -} - static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable) { u32 tx = readl(ioaddr + XGMAC_TX_CONFIG); @@ -1540,7 +1532,6 @@ static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg * const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, - .phylink_get_caps = xgmac_phylink_get_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxgmac2_rx_queue_enable, @@ -1601,7 +1592,6 @@ static void dwxlgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode, const struct stmmac_ops dwxlgmac2_ops = { .core_init = dwxgmac2_core_init, - .phylink_get_caps = xgmac_phylink_get_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxlgmac2_rx_queue_enable, @@ -1661,6 +1651,9 @@ int dwxgmac2_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_1000FD | MAC_2500FD | MAC_5000FD | + MAC_10000FD; mac->link.duplex = 0; mac->link.speed10 = XGMAC_CONFIG_SS_10_MII; mac->link.speed100 = XGMAC_CONFIG_SS_100_MII; @@ -1698,6 +1691,11 @@ int dwxlgmac2_setup(struct stmmac_priv *priv) if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_1000FD | MAC_2500FD | MAC_5000FD | + MAC_10000FD | MAC_25000FD | + MAC_40000FD | MAC_50000FD | + MAC_100000FD; mac->link.duplex = 0; mac->link.speed1000 = XLGMAC_CONFIG_SS_1000; mac->link.speed2500 = XLGMAC_CONFIG_SS_2500; diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h index dff02d75d519..5d1ea3e07459 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc.h +++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h @@ -52,6 +52,7 @@ struct stmmac_counters { unsigned int mmc_tx_excessdef; unsigned int mmc_tx_pause_frame; unsigned int mmc_tx_vlan_frame_g; + unsigned int mmc_tx_oversize_g; unsigned int mmc_tx_lpi_usec; unsigned int mmc_tx_lpi_tran; @@ -80,6 +81,7 @@ struct stmmac_counters { unsigned int mmc_rx_fifo_overflow; unsigned int mmc_rx_vlan_frames_gb; unsigned int mmc_rx_watchdog_error; + unsigned int mmc_rx_error; unsigned int mmc_rx_lpi_usec; unsigned int mmc_rx_lpi_tran; unsigned int mmc_rx_discard_frames_gb; diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index 7eb477faa75a..0fab842902a8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -53,6 +53,7 @@ #define MMC_TX_EXCESSDEF 0x6c #define MMC_TX_PAUSE_FRAME 0x70 #define MMC_TX_VLAN_FRAME_G 0x74 +#define MMC_TX_OVERSIZE_G 0x78 /* MMC RX counter registers */ #define MMC_RX_FRAMECOUNT_GB 0x80 @@ -79,6 +80,13 @@ #define MMC_RX_FIFO_OVERFLOW 0xd4 #define MMC_RX_VLAN_FRAMES_GB 0xd8 #define MMC_RX_WATCHDOG_ERROR 0xdc +#define MMC_RX_ERROR 0xe0 + +#define MMC_TX_LPI_USEC 0xec +#define MMC_TX_LPI_TRAN 0xf0 +#define MMC_RX_LPI_USEC 0xf4 +#define MMC_RX_LPI_TRAN 0xf8 + /* IPC*/ #define MMC_RX_IPC_INTR_MASK 0x100 #define MMC_RX_IPC_INTR 0x108 @@ -283,6 +291,9 @@ static void dwmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc) mmc->mmc_tx_excessdef += readl(mmcaddr + MMC_TX_EXCESSDEF); mmc->mmc_tx_pause_frame += readl(mmcaddr + MMC_TX_PAUSE_FRAME); mmc->mmc_tx_vlan_frame_g += readl(mmcaddr + MMC_TX_VLAN_FRAME_G); + mmc->mmc_tx_oversize_g += readl(mmcaddr + MMC_TX_OVERSIZE_G); + mmc->mmc_tx_lpi_usec += readl(mmcaddr + MMC_TX_LPI_USEC); + mmc->mmc_tx_lpi_tran += readl(mmcaddr + MMC_TX_LPI_TRAN); /* MMC RX counter registers */ mmc->mmc_rx_framecount_gb += readl(mmcaddr + MMC_RX_FRAMECOUNT_GB); @@ -316,6 +327,10 @@ static void dwmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc) mmc->mmc_rx_fifo_overflow += readl(mmcaddr + MMC_RX_FIFO_OVERFLOW); mmc->mmc_rx_vlan_frames_gb += readl(mmcaddr + MMC_RX_VLAN_FRAMES_GB); mmc->mmc_rx_watchdog_error += readl(mmcaddr + MMC_RX_WATCHDOG_ERROR); + mmc->mmc_rx_error += readl(mmcaddr + MMC_RX_ERROR); + mmc->mmc_rx_lpi_usec += readl(mmcaddr + MMC_RX_LPI_USEC); + mmc->mmc_rx_lpi_tran += readl(mmcaddr + MMC_RX_LPI_TRAN); + /* IPv4 */ mmc->mmc_rx_ipv4_gd += readl(mmcaddr + MMC_RX_IPV4_GD); mmc->mmc_rx_ipv4_hderr += readl(mmcaddr + MMC_RX_IPV4_HDERR); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index e1537a57815f..542e2633a6f5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -212,6 +212,7 @@ static const struct stmmac_stats stmmac_mmc[] = { STMMAC_MMC_STAT(mmc_tx_excessdef), STMMAC_MMC_STAT(mmc_tx_pause_frame), STMMAC_MMC_STAT(mmc_tx_vlan_frame_g), + STMMAC_MMC_STAT(mmc_tx_oversize_g), STMMAC_MMC_STAT(mmc_tx_lpi_usec), STMMAC_MMC_STAT(mmc_tx_lpi_tran), STMMAC_MMC_STAT(mmc_rx_framecount_gb), @@ -238,6 +239,7 @@ static const struct stmmac_stats stmmac_mmc[] = { STMMAC_MMC_STAT(mmc_rx_fifo_overflow), STMMAC_MMC_STAT(mmc_rx_vlan_frames_gb), STMMAC_MMC_STAT(mmc_rx_watchdog_error), + STMMAC_MMC_STAT(mmc_rx_error), STMMAC_MMC_STAT(mmc_rx_lpi_usec), STMMAC_MMC_STAT(mmc_rx_lpi_tran), STMMAC_MMC_STAT(mmc_rx_discard_frames_gb), diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 24cd80490d19..7c6fb14b5555 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1198,17 +1198,6 @@ static int stmmac_init_phy(struct net_device *dev) return ret; } -static void stmmac_set_half_duplex(struct stmmac_priv *priv) -{ - /* Half-Duplex can only work with single tx queue */ - if (priv->plat->tx_queues_to_use > 1) - priv->phylink_config.mac_capabilities &= - ~(MAC_10HD | MAC_100HD | MAC_1000HD); - else - priv->phylink_config.mac_capabilities |= - (MAC_10HD | MAC_100HD | MAC_1000HD); -} - static int stmmac_phy_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data; @@ -1236,15 +1225,11 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) xpcs_get_interfaces(priv->hw->xpcs, priv->phylink_config.supported_interfaces); - priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | - MAC_10FD | MAC_100FD | - MAC_1000FD; - - stmmac_set_half_duplex(priv); - /* Get the MAC specific capabilities */ stmmac_mac_phylink_get_caps(priv); + priv->phylink_config.mac_capabilities = priv->hw->link.caps; + max_speed = priv->plat->max_speed; if (max_speed) phylink_limit_mac_speed(&priv->phylink_config, max_speed); @@ -7342,6 +7327,7 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) { struct stmmac_priv *priv = netdev_priv(dev); int ret = 0, i; + int max_speed; if (netif_running(dev)) stmmac_release(dev); @@ -7355,7 +7341,14 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) priv->rss.table[i] = ethtool_rxfh_indir_default(i, rx_cnt); - stmmac_set_half_duplex(priv); + stmmac_mac_phylink_get_caps(priv); + + priv->phylink_config.mac_capabilities = priv->hw->link.caps; + + max_speed = priv->plat->max_speed; + if (max_speed) + phylink_limit_mac_speed(&priv->phylink_config, max_speed); + stmmac_napi_add(dev); if (netif_running(dev)) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2939a21ca74f..1d00e21808c1 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2793,6 +2793,8 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { + struct am65_cpsw_rx_chn *rx_chan = &common->rx_chns; + struct am65_cpsw_tx_chn *tx_chan = common->tx_chns; struct device *dev = common->dev; struct am65_cpsw_port *port; int ret = 0, i; @@ -2805,6 +2807,22 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) if (ret) return ret; + /* The DMA Channels are not guaranteed to be in a clean state. + * Reset and disable them to ensure that they are back to the + * clean state and ready to be used. + */ + for (i = 0; i < common->tx_ch_num; i++) { + k3_udma_glue_reset_tx_chn(tx_chan[i].tx_chn, &tx_chan[i], + am65_cpsw_nuss_tx_cleanup); + k3_udma_glue_disable_tx_chn(tx_chan[i].tx_chn); + } + + for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++) + k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i, rx_chan, + am65_cpsw_nuss_rx_cleanup, !!i); + + k3_udma_glue_disable_rx_chn(rx_chan->rx_chn); + ret = am65_cpsw_nuss_register_devlink(common); if (ret) return ret; diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index c66618d91c28..f89716b1cfb6 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 cf7b73f8f450..b69af69a1ccd 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 6dff2c85682d..6fae161cbcb8 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 2fa511227eac..93295916b1d2 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/geneve.c b/drivers/net/geneve.c index 2f6739fe78af..6c2835086b57 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -822,7 +822,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!pskb_inet_may_pull(skb)) + if (!skb_vlan_inet_prepare(skb)) return -EINVAL; if (!gs4) @@ -929,7 +929,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - if (!pskb_inet_may_pull(skb)) + if (!skb_vlan_inet_prepare(skb)) return -EINVAL; if (!gs6) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index ba4704c2c640..e62d6cbdf9bc 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1098,11 +1098,12 @@ out_hashtable: static void gtp_dellink(struct net_device *dev, struct list_head *head) { struct gtp_dev *gtp = netdev_priv(dev); + struct hlist_node *next; struct pdp_ctx *pctx; int i; for (i = 0; i < gtp->hash_size; i++) - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid) pdp_context_delete(pctx); list_del_rcu(>p->list); diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index a6fcbda64ecc..2b6ec979a62f 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -154,8 +154,11 @@ static void free_netvsc_device(struct rcu_head *head) int i; kfree(nvdev->extension); - vfree(nvdev->recv_buf); - vfree(nvdev->send_buf); + + if (!nvdev->recv_buf_gpadl_handle.decrypted) + vfree(nvdev->recv_buf); + if (!nvdev->send_buf_gpadl_handle.decrypted) + vfree(nvdev->send_buf); bitmap_free(nvdev->send_section_map); for (i = 0; i < VRSS_CHANNEL_MAX; i++) { diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 0206b84284ab..ff016c11b4a0 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 fa8c6fdcf301..d7aaefb5226b 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 0f3a1538a8b8..f4f9412d0cd7 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/tun.c b/drivers/net/tun.c index 0b3f21cba552..92da8c03d960 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2125,14 +2125,16 @@ static ssize_t tun_put_user(struct tun_struct *tun, tun_is_little_endian(tun), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); - pr_err("unexpected GSO type: " - "0x%x, gso_size %d, hdr_len %d\n", - sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), - tun16_to_cpu(tun, gso.hdr_len)); - print_hex_dump(KERN_ERR, "tun: ", - DUMP_PREFIX_NONE, - 16, 1, skb->head, - min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + + if (net_ratelimit()) { + netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size), + tun16_to_cpu(tun, gso.hdr_len)); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true); + } WARN_ON_ONCE(1); return -EINVAL; } diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index a9c418890a1c..df9d767cb524 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1317,6 +1317,8 @@ static int ax88179_bind(struct usbnet *dev, struct usb_interface *intf) netif_set_tso_max_size(dev->net, 16384); + ax88179_reset(dev); + return 0; } @@ -1454,21 +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); - - /* Skip IP alignment pseudo header */ - skb_pull(ax_skb, 2); + skb_put(ax_skb, pkt_len); + memcpy(ax_skb->data, skb->data + 2, pkt_len); - skb->truesize = pkt_len_plus_padd + - SKB_DATA_ALIGN(sizeof(struct sk_buff)); ax88179_rx_checksum(ax_skb, pkt_hdr); usbnet_skb_return(dev, ax_skb); @@ -1695,7 +1692,6 @@ static const struct driver_info ax88179_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, @@ -1708,7 +1704,6 @@ static const struct driver_info ax88178a_info = { .unbind = ax88179_unbind, .status = ax88179_status, .link_reset = ax88179_link_reset, - .reset = ax88179_reset, .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index e2e181378f41..a5469cf5cf67 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 */ @@ -1431,6 +1434,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ {QMI_QUIRK_SET_DTR(0x1546, 0x1312, 4)}, /* u-blox LARA-R6 01B */ {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ + {QMI_QUIRK_SET_DTR(0x33f8, 0x0104, 4)}, /* Rolling RW101 RMNET */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c22d1118a133..115c3c5414f2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3807,6 +3807,7 @@ static int virtnet_set_rxfh(struct net_device *dev, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); + bool update = false; int i; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && @@ -3814,13 +3815,28 @@ static int virtnet_set_rxfh(struct net_device *dev, return -EOPNOTSUPP; if (rxfh->indir) { + if (!vi->has_rss) + return -EOPNOTSUPP; + for (i = 0; i < vi->rss_indir_table_size; ++i) vi->ctrl->rss.indirection_table[i] = rxfh->indir[i]; + update = true; } - if (rxfh->key) + + if (rxfh->key) { + /* If either _F_HASH_REPORT or _F_RSS are negotiated, the + * device provides hash calculation capabilities, that is, + * hash_key is configured. + */ + if (!vi->has_rss && !vi->has_rss_hash_report) + return -EOPNOTSUPP; + memcpy(vi->ctrl->rss.key, rxfh->key, vi->rss_key_size); + update = true; + } - virtnet_commit_rss_command(vi); + if (update) + virtnet_commit_rss_command(vi); return 0; } @@ -4729,13 +4745,15 @@ static int virtnet_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT)) vi->has_rss_hash_report = true; - if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) + if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) { vi->has_rss = true; - if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_indir_table_size = virtio_cread16(vdev, offsetof(struct virtio_net_config, rss_max_indirection_table_length)); + } + + if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_key_size = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 3495591a5c29..ba319fc21957 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; diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index a6a37d67a50a..9f4bf41a3d41 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 072b0a5827d1..eca1457caa0c 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 9b79279fd76c..dbbcb2d0968c 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 4863a3c74640..d84d7e955bb0 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 9f69e04594e4..fe5bba8561d0 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 f3e3986b4c72..11559563ae38 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 b55fe320633c..59e1fc0018df 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 7eb17f46a815..9e1a34e23af2 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 @@ err_shutdown: 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/pci/quirks.c b/drivers/pci/quirks.c index bf4833221816..eff7f5df08e2 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3766,14 +3766,6 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATHEROS, 0x003e, quirk_no_bus_reset); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CAVIUM, 0xa100, quirk_no_bus_reset); /* - * Apparently the LSI / Agere FW643 can't recover after a Secondary Bus - * Reset and requires a power-off or suspend/resume and rescan. Prevent - * use of that reset. - */ -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATT, 0x5900, quirk_no_bus_reset); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATT, 0x5901, quirk_no_bus_reset); - -/* * Some TI KeyStone C667X devices do not support bus/hot reset. The PCIESS * automatically disables LTSSM when Secondary Bus Reset is received and * the device stops working. Prevent bus reset for these devices. With diff --git a/drivers/platform/chrome/cros_ec_uart.c b/drivers/platform/chrome/cros_ec_uart.c index 8ea867c2a01a..62bc24f6dcc7 100644 --- a/drivers/platform/chrome/cros_ec_uart.c +++ b/drivers/platform/chrome/cros_ec_uart.c @@ -263,12 +263,6 @@ static int cros_ec_uart_probe(struct serdev_device *serdev) if (!ec_dev) return -ENOMEM; - ret = devm_serdev_device_open(dev, serdev); - if (ret) { - dev_err(dev, "Unable to open UART device"); - return ret; - } - serdev_device_set_drvdata(serdev, ec_dev); init_waitqueue_head(&ec_uart->response.wait_queue); @@ -280,14 +274,6 @@ static int cros_ec_uart_probe(struct serdev_device *serdev) return ret; } - ret = serdev_device_set_baudrate(serdev, ec_uart->baudrate); - if (ret < 0) { - dev_err(dev, "Failed to set up host baud rate (%d)", ret); - return ret; - } - - serdev_device_set_flow_control(serdev, ec_uart->flowcontrol); - /* Initialize ec_dev for cros_ec */ ec_dev->phys_name = dev_name(dev); ec_dev->dev = dev; @@ -301,6 +287,20 @@ static int cros_ec_uart_probe(struct serdev_device *serdev) serdev_device_set_client_ops(serdev, &cros_ec_uart_client_ops); + ret = devm_serdev_device_open(dev, serdev); + if (ret) { + dev_err(dev, "Unable to open UART device"); + return ret; + } + + ret = serdev_device_set_baudrate(serdev, ec_uart->baudrate); + if (ret < 0) { + dev_err(dev, "Failed to set up host baud rate (%d)", ret); + return ret; + } + + serdev_device_set_flow_control(serdev, ec_uart->flowcontrol); + return cros_ec_register(ec_dev); } diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index ee2e164f86b9..38c932df6446 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -598,6 +598,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = { .driver_data = &quirk_acer_predator_v4, }, { + .callback = dmi_matched, + .ident = "Acer Predator PH18-71", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Predator PH18-71"), + }, + .driver_data = &quirk_acer_predator_v4, + }, + { .callback = set_force_caps, .ident = "Acer Aspire Switch 10E SW3-016", .matches = { diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index b456370166b6..b4f49720c87f 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -208,6 +208,15 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BIOS_VERSION, "03.03"), } }, + { + .ident = "Framework Laptop 13 (Phoenix)", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Framework"), + DMI_MATCH(DMI_PRODUCT_NAME, "Laptop 13 (AMD Ryzen 7040Series)"), + DMI_MATCH(DMI_BIOS_VERSION, "03.05"), + } + }, {} }; diff --git a/drivers/platform/x86/amd/pmf/Makefile b/drivers/platform/x86/amd/pmf/Makefile index 6b26e48ce8ad..7d6079b02589 100644 --- a/drivers/platform/x86/amd/pmf/Makefile +++ b/drivers/platform/x86/amd/pmf/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_AMD_PMF) += amd-pmf.o amd-pmf-objs := core.o acpi.o sps.o \ auto-mode.o cnqf.o \ - tee-if.o spc.o + tee-if.o spc.o pmf-quirks.o diff --git a/drivers/platform/x86/amd/pmf/acpi.c b/drivers/platform/x86/amd/pmf/acpi.c index d0cf46e2fc8e..1157ec148880 100644 --- a/drivers/platform/x86/amd/pmf/acpi.c +++ b/drivers/platform/x86/amd/pmf/acpi.c @@ -343,7 +343,10 @@ static int apmf_if_verify_interface(struct amd_pmf_dev *pdev) if (err) return err; - pdev->supported_func = output.supported_functions; + /* only set if not already set by a quirk */ + if (!pdev->supported_func) + pdev->supported_func = output.supported_functions; + dev_dbg(pdev->dev, "supported functions:0x%x notifications:0x%x version:%u\n", output.supported_functions, output.notification_mask, output.version); @@ -437,7 +440,7 @@ int apmf_check_smart_pc(struct amd_pmf_dev *pmf_dev) status = acpi_walk_resources(ahandle, METHOD_NAME__CRS, apmf_walk_resources, pmf_dev); if (ACPI_FAILURE(status)) { - dev_err(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status); + dev_dbg(pmf_dev->dev, "acpi_walk_resources failed :%d\n", status); return -EINVAL; } diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index 5d4f80698a8b..64e6e34a2a9a 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -445,6 +445,7 @@ static int amd_pmf_probe(struct platform_device *pdev) mutex_init(&dev->lock); mutex_init(&dev->update_mutex); + amd_pmf_quirks_init(dev); apmf_acpi_init(dev); platform_set_drvdata(pdev, dev); amd_pmf_dbgfs_register(dev); diff --git a/drivers/platform/x86/amd/pmf/pmf-quirks.c b/drivers/platform/x86/amd/pmf/pmf-quirks.c new file mode 100644 index 000000000000..0b2eb0ae85fe --- /dev/null +++ b/drivers/platform/x86/amd/pmf/pmf-quirks.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Platform Management Framework Driver Quirks + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Mario Limonciello <mario.limonciello@amd.com> + */ + +#include <linux/dmi.h> + +#include "pmf.h" + +struct quirk_entry { + u32 supported_func; +}; + +static struct quirk_entry quirk_no_sps_bug = { + .supported_func = 0x4003, +}; + +static const struct dmi_system_id fwbug_list[] = { + { + .ident = "ROG Zephyrus G14", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "GA403UV"), + }, + .driver_data = &quirk_no_sps_bug, + }, + {} +}; + +void amd_pmf_quirks_init(struct amd_pmf_dev *dev) +{ + const struct dmi_system_id *dmi_id; + struct quirk_entry *quirks; + + dmi_id = dmi_first_match(fwbug_list); + if (!dmi_id) + return; + + quirks = dmi_id->driver_data; + if (quirks->supported_func) { + dev->supported_func = quirks->supported_func; + pr_info("Using supported funcs quirk to avoid %s platform firmware bug\n", + dmi_id->ident); + } +} + diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h index 8c4df5753f40..eeedd0c0395a 100644 --- a/drivers/platform/x86/amd/pmf/pmf.h +++ b/drivers/platform/x86/amd/pmf/pmf.h @@ -720,4 +720,7 @@ int apmf_check_smart_pc(struct amd_pmf_dev *pmf_dev); void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in); void amd_pmf_dump_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in); +/* Quirk infrastructure */ +void amd_pmf_quirks_init(struct amd_pmf_dev *dev); + #endif /* PMF_H */ diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 7457ca2b27a6..c7a827645864 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -49,6 +49,8 @@ static const struct acpi_device_id intel_hid_ids[] = { {"INTC1076", 0}, {"INTC1077", 0}, {"INTC1078", 0}, + {"INTC107B", 0}, + {"INTC10CB", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, intel_hid_ids); @@ -504,6 +506,7 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) struct platform_device *device = context; struct intel_hid_priv *priv = dev_get_drvdata(&device->dev); unsigned long long ev_index; + struct key_entry *ke; int err; /* @@ -545,11 +548,15 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) if (event == 0xc0 || !priv->array) return; - if (!sparse_keymap_entry_from_scancode(priv->array, event)) { + ke = sparse_keymap_entry_from_scancode(priv->array, event); + if (!ke) { dev_info(&device->dev, "unknown event 0x%x\n", event); return; } + if (ke->type == KE_IGNORE) + return; + wakeup: pm_wakeup_hard_event(&device->dev); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 08df9494603c..30951f7131cd 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -719,6 +719,7 @@ 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_X, NULL), {} diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c index bd75d61ff8a6..ef730200a04b 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c @@ -29,7 +29,7 @@ #include "uncore-frequency-common.h" #define UNCORE_MAJOR_VERSION 0 -#define UNCORE_MINOR_VERSION 1 +#define UNCORE_MINOR_VERSION 2 #define UNCORE_HEADER_INDEX 0 #define UNCORE_FABRIC_CLUSTER_OFFSET 8 @@ -329,7 +329,7 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_ goto remove_clusters; } - if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) != UNCORE_MINOR_VERSION) + if (TPMI_MINOR_VERSION(pd_info->ufs_header_ver) > UNCORE_MINOR_VERSION) dev_info(&auxdev->dev, "Uncore: Ignore: Unsupported minor version:%lx\n", TPMI_MINOR_VERSION(pd_info->ufs_header_ver)); diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 084c355c86f5..79bb2c801daa 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -136,8 +136,6 @@ static int intel_vbtn_input_setup(struct platform_device *device) priv->switches_dev->id.bustype = BUS_HOST; if (priv->has_switches) { - detect_tablet_mode(&device->dev); - ret = input_register_device(priv->switches_dev); if (ret) return ret; @@ -258,9 +256,6 @@ static const struct dmi_system_id dmi_switches_allow_list[] = { static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel) { - unsigned long long vgbs; - acpi_status status; - /* See dual_accel_detect.h for more info */ if (dual_accel) return false; @@ -268,8 +263,7 @@ static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel) if (!dmi_check_system(dmi_switches_allow_list)) return false; - status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs); - return ACPI_SUCCESS(status); + return acpi_has_method(handle, "VGBS"); } static int intel_vbtn_probe(struct platform_device *device) @@ -316,6 +310,9 @@ static int intel_vbtn_probe(struct platform_device *device) if (ACPI_FAILURE(status)) dev_err(&device->dev, "Error VBDL failed with ACPI status %d\n", status); } + // Check switches after buttons since VBDL may have side effects. + if (has_switches) + detect_tablet_mode(&device->dev); device_init_wakeup(&device->dev, true); /* diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c index ad3c39e9e9f5..e714ee6298dd 100644 --- a/drivers/platform/x86/lg-laptop.c +++ b/drivers/platform/x86/lg-laptop.c @@ -736,7 +736,7 @@ static int acpi_add(struct acpi_device *device) default: year = 2019; } - pr_info("product: %s year: %d\n", product, year); + pr_info("product: %s year: %d\n", product ?: "unknown", year); if (year >= 2019) battery_limit_use_wmbb = 1; diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index 291f14ef6702..77244c9aa60d 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -264,6 +264,7 @@ static const struct key_entry toshiba_acpi_keymap[] = { { KE_KEY, 0xb32, { KEY_NEXTSONG } }, { KE_KEY, 0xb33, { KEY_PLAYPAUSE } }, { KE_KEY, 0xb5a, { KEY_MEDIA } }, + { KE_IGNORE, 0x0e00, { KEY_RESERVED } }, /* Wake from sleep */ { KE_IGNORE, 0x1430, { KEY_RESERVED } }, /* Wake from sleep */ { KE_IGNORE, 0x1501, { KEY_RESERVED } }, /* Output changed */ { KE_IGNORE, 0x1502, { KEY_RESERVED } }, /* HDMI plugged/unplugged */ @@ -3523,9 +3524,10 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event) (dev->kbd_mode == SCI_KBD_MODE_ON) ? LED_FULL : LED_OFF); break; + case 0x8e: /* Power button pressed */ + break; case 0x85: /* Unknown */ case 0x8d: /* Unknown */ - case 0x8e: /* Unknown */ case 0x94: /* Unknown */ case 0x95: /* Unknown */ default: diff --git a/drivers/pwm/pwm-dwc-core.c b/drivers/pwm/pwm-dwc-core.c index 043736972cb9..c8425493b95d 100644 --- a/drivers/pwm/pwm-dwc-core.c +++ b/drivers/pwm/pwm-dwc-core.c @@ -172,7 +172,6 @@ struct pwm_chip *dwc_pwm_alloc(struct device *dev) dwc->clk_ns = 10; chip->ops = &dwc_pwm_ops; - dev_set_drvdata(dev, chip); return chip; } EXPORT_SYMBOL_GPL(dwc_pwm_alloc); diff --git a/drivers/pwm/pwm-dwc.c b/drivers/pwm/pwm-dwc.c index 676eaf8d7a53..fb3eadf6fbc4 100644 --- a/drivers/pwm/pwm-dwc.c +++ b/drivers/pwm/pwm-dwc.c @@ -31,26 +31,34 @@ static const struct dwc_pwm_info ehl_pwm_info = { .size = 0x1000, }; -static int dwc_pwm_init_one(struct device *dev, void __iomem *base, unsigned int offset) +static int dwc_pwm_init_one(struct device *dev, struct dwc_pwm_drvdata *ddata, unsigned int idx) { struct pwm_chip *chip; struct dwc_pwm *dwc; + int ret; chip = dwc_pwm_alloc(dev); if (IS_ERR(chip)) return PTR_ERR(chip); dwc = to_dwc_pwm(chip); - dwc->base = base + offset; + dwc->base = ddata->io_base + (ddata->info->size * idx); - return devm_pwmchip_add(dev, chip); + ret = devm_pwmchip_add(dev, chip); + if (ret) + return ret; + + ddata->chips[idx] = chip; + return 0; } static int dwc_pwm_probe(struct pci_dev *pci, const struct pci_device_id *id) { const struct dwc_pwm_info *info; struct device *dev = &pci->dev; - int i, ret; + struct dwc_pwm_drvdata *ddata; + unsigned int idx; + int ret; ret = pcim_enable_device(pci); if (ret) @@ -63,17 +71,25 @@ static int dwc_pwm_probe(struct pci_dev *pci, const struct pci_device_id *id) return dev_err_probe(dev, ret, "Failed to iomap PCI BAR\n"); info = (const struct dwc_pwm_info *)id->driver_data; - - for (i = 0; i < info->nr; i++) { - /* - * No need to check for pcim_iomap_table() failure, - * pcim_iomap_regions() already does it for us. - */ - ret = dwc_pwm_init_one(dev, pcim_iomap_table(pci)[0], i * info->size); + ddata = devm_kzalloc(dev, struct_size(ddata, chips, info->nr), GFP_KERNEL); + if (!ddata) + return -ENOMEM; + + /* + * No need to check for pcim_iomap_table() failure, + * pcim_iomap_regions() already does it for us. + */ + ddata->io_base = pcim_iomap_table(pci)[0]; + ddata->info = info; + + for (idx = 0; idx < ddata->info->nr; idx++) { + ret = dwc_pwm_init_one(dev, ddata, idx); if (ret) return ret; } + dev_set_drvdata(dev, ddata); + pm_runtime_put(dev); pm_runtime_allow(dev); @@ -88,19 +104,24 @@ static void dwc_pwm_remove(struct pci_dev *pci) static int dwc_pwm_suspend(struct device *dev) { - struct pwm_chip *chip = dev_get_drvdata(dev); - struct dwc_pwm *dwc = to_dwc_pwm(chip); - int i; - - for (i = 0; i < DWC_TIMERS_TOTAL; i++) { - if (chip->pwms[i].state.enabled) { - dev_err(dev, "PWM %u in use by consumer (%s)\n", - i, chip->pwms[i].label); - return -EBUSY; + struct dwc_pwm_drvdata *ddata = dev_get_drvdata(dev); + unsigned int idx; + + for (idx = 0; idx < ddata->info->nr; idx++) { + struct pwm_chip *chip = ddata->chips[idx]; + struct dwc_pwm *dwc = to_dwc_pwm(chip); + unsigned int i; + + for (i = 0; i < DWC_TIMERS_TOTAL; i++) { + if (chip->pwms[i].state.enabled) { + dev_err(dev, "PWM %u in use by consumer (%s)\n", + i, chip->pwms[i].label); + return -EBUSY; + } + dwc->ctx[i].cnt = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT(i)); + dwc->ctx[i].cnt2 = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT2(i)); + dwc->ctx[i].ctrl = dwc_pwm_readl(dwc, DWC_TIM_CTRL(i)); } - dwc->ctx[i].cnt = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT(i)); - dwc->ctx[i].cnt2 = dwc_pwm_readl(dwc, DWC_TIM_LD_CNT2(i)); - dwc->ctx[i].ctrl = dwc_pwm_readl(dwc, DWC_TIM_CTRL(i)); } return 0; @@ -108,14 +129,19 @@ static int dwc_pwm_suspend(struct device *dev) static int dwc_pwm_resume(struct device *dev) { - struct pwm_chip *chip = dev_get_drvdata(dev); - struct dwc_pwm *dwc = to_dwc_pwm(chip); - int i; - - for (i = 0; i < DWC_TIMERS_TOTAL; i++) { - dwc_pwm_writel(dwc, dwc->ctx[i].cnt, DWC_TIM_LD_CNT(i)); - dwc_pwm_writel(dwc, dwc->ctx[i].cnt2, DWC_TIM_LD_CNT2(i)); - dwc_pwm_writel(dwc, dwc->ctx[i].ctrl, DWC_TIM_CTRL(i)); + struct dwc_pwm_drvdata *ddata = dev_get_drvdata(dev); + unsigned int idx; + + for (idx = 0; idx < ddata->info->nr; idx++) { + struct pwm_chip *chip = ddata->chips[idx]; + struct dwc_pwm *dwc = to_dwc_pwm(chip); + unsigned int i; + + for (i = 0; i < DWC_TIMERS_TOTAL; i++) { + dwc_pwm_writel(dwc, dwc->ctx[i].cnt, DWC_TIM_LD_CNT(i)); + dwc_pwm_writel(dwc, dwc->ctx[i].cnt2, DWC_TIM_LD_CNT2(i)); + dwc_pwm_writel(dwc, dwc->ctx[i].ctrl, DWC_TIM_CTRL(i)); + } } return 0; diff --git a/drivers/pwm/pwm-dwc.h b/drivers/pwm/pwm-dwc.h index a8b074841ae8..c6e2df5a6122 100644 --- a/drivers/pwm/pwm-dwc.h +++ b/drivers/pwm/pwm-dwc.h @@ -38,6 +38,12 @@ struct dwc_pwm_info { unsigned int size; }; +struct dwc_pwm_drvdata { + const struct dwc_pwm_info *info; + void __iomem *io_base; + struct pwm_chip *chips[]; +}; + struct dwc_pwm_ctx { u32 cnt; u32 cnt2; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index f95d12345d98..920f550bc313 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -363,10 +363,8 @@ int ccw_device_set_online(struct ccw_device *cdev) spin_lock_irq(cdev->ccwlock); ret = ccw_device_online(cdev); - spin_unlock_irq(cdev->ccwlock); - if (ret == 0) - wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev)); - else { + if (ret) { + spin_unlock_irq(cdev->ccwlock); CIO_MSG_EVENT(0, "ccw_device_online returned %d, " "device 0.%x.%04x\n", ret, cdev->private->dev_id.ssid, @@ -375,7 +373,12 @@ int ccw_device_set_online(struct ccw_device *cdev) put_device(&cdev->dev); return ret; } - spin_lock_irq(cdev->ccwlock); + /* Wait until a final state is reached */ + while (!dev_fsm_final_state(cdev)) { + spin_unlock_irq(cdev->ccwlock); + wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev)); + spin_lock_irq(cdev->ccwlock); + } /* Check if online processing was successful */ if ((cdev->private->state != DEV_STATE_ONLINE) && (cdev->private->state != DEV_STATE_W4SENSE)) { diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c index 65d8b2cfd626..42791fa0b80e 100644 --- a/drivers/s390/cio/device_fsm.c +++ b/drivers/s390/cio/device_fsm.c @@ -504,6 +504,11 @@ callback: ccw_device_done(cdev, DEV_STATE_ONLINE); /* Deliver fake irb to device driver, if needed. */ if (cdev->private->flags.fake_irb) { + CIO_MSG_EVENT(2, "fakeirb: deliver device 0.%x.%04x intparm %lx type=%d\n", + cdev->private->dev_id.ssid, + cdev->private->dev_id.devno, + cdev->private->intparm, + cdev->private->flags.fake_irb); create_fake_irb(&cdev->private->dma_area->irb, cdev->private->flags.fake_irb); cdev->private->flags.fake_irb = 0; diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c index 40c97f873075..acd6790dba4d 100644 --- a/drivers/s390/cio/device_ops.c +++ b/drivers/s390/cio/device_ops.c @@ -208,6 +208,10 @@ int ccw_device_start_timeout_key(struct ccw_device *cdev, struct ccw1 *cpa, if (!cdev->private->flags.fake_irb) { cdev->private->flags.fake_irb = FAKE_CMD_IRB; cdev->private->intparm = intparm; + CIO_MSG_EVENT(2, "fakeirb: queue device 0.%x.%04x intparm %lx type=%d\n", + cdev->private->dev_id.ssid, + cdev->private->dev_id.devno, intparm, + cdev->private->flags.fake_irb); return 0; } else /* There's already a fake I/O around. */ @@ -551,6 +555,10 @@ int ccw_device_tm_start_timeout_key(struct ccw_device *cdev, struct tcw *tcw, if (!cdev->private->flags.fake_irb) { cdev->private->flags.fake_irb = FAKE_TM_IRB; cdev->private->intparm = intparm; + CIO_MSG_EVENT(2, "fakeirb: queue device 0.%x.%04x intparm %lx type=%d\n", + cdev->private->dev_id.ssid, + cdev->private->dev_id.devno, intparm, + cdev->private->flags.fake_irb); return 0; } else /* There's already a fake I/O around. */ diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 3d9f0834c78b..a1cb39f4b7a2 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -722,8 +722,8 @@ static void qdio_handle_activate_check(struct qdio_irq *irq_ptr, lgr_info_log(); } -static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, - int dstat) +static int qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, + int dstat, int dcc) { DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qest irq"); @@ -731,15 +731,18 @@ static void qdio_establish_handle_irq(struct qdio_irq *irq_ptr, int cstat, goto error; if (dstat & ~(DEV_STAT_DEV_END | DEV_STAT_CHN_END)) goto error; + if (dcc == 1) + return -EAGAIN; if (!(dstat & DEV_STAT_DEV_END)) goto error; qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ESTABLISHED); - return; + return 0; error: DBF_ERROR("%4x EQ:error", irq_ptr->schid.sch_no); DBF_ERROR("ds: %2x cs:%2x", dstat, cstat); qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + return -EIO; } /* qdio interrupt handler */ @@ -748,7 +751,7 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, { struct qdio_irq *irq_ptr = cdev->private->qdio_data; struct subchannel_id schid; - int cstat, dstat; + int cstat, dstat, rc, dcc; if (!intparm || !irq_ptr) { ccw_device_get_schid(cdev, &schid); @@ -768,10 +771,12 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, qdio_irq_check_sense(irq_ptr, irb); cstat = irb->scsw.cmd.cstat; dstat = irb->scsw.cmd.dstat; + dcc = scsw_cmd_is_valid_cc(&irb->scsw) ? irb->scsw.cmd.cc : 0; + rc = 0; switch (irq_ptr->state) { case QDIO_IRQ_STATE_INACTIVE: - qdio_establish_handle_irq(irq_ptr, cstat, dstat); + rc = qdio_establish_handle_irq(irq_ptr, cstat, dstat, dcc); break; case QDIO_IRQ_STATE_CLEANUP: qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE); @@ -785,12 +790,25 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, if (cstat || dstat) qdio_handle_activate_check(irq_ptr, intparm, cstat, dstat); + else if (dcc == 1) + rc = -EAGAIN; break; case QDIO_IRQ_STATE_STOPPED: break; default: WARN_ON_ONCE(1); } + + if (rc == -EAGAIN) { + DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qint retry"); + rc = ccw_device_start(cdev, irq_ptr->ccw, intparm, 0, 0); + if (!rc) + return; + DBF_ERROR("%4x RETRY ERR", irq_ptr->schid.sch_no); + DBF_ERROR("rc:%4x", rc); + qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR); + } + wake_up(&cdev->private->wait_q); } diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 2c8e964425dc..43778b088ffa 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -292,13 +292,16 @@ out: static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { clear_bit(dmb->sba_idx, ism->sba_bitmap); - dma_free_coherent(&ism->pdev->dev, dmb->dmb_len, - dmb->cpu_addr, dmb->dma_addr); + dma_unmap_page(&ism->pdev->dev, dmb->dma_addr, dmb->dmb_len, + DMA_FROM_DEVICE); + folio_put(virt_to_folio(dmb->cpu_addr)); } static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { + struct folio *folio; unsigned long bit; + int rc; if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev)) return -EINVAL; @@ -315,14 +318,30 @@ static int ism_alloc_dmb(struct ism_dev *ism, struct ism_dmb *dmb) test_and_set_bit(dmb->sba_idx, ism->sba_bitmap)) return -EINVAL; - dmb->cpu_addr = dma_alloc_coherent(&ism->pdev->dev, dmb->dmb_len, - &dmb->dma_addr, - GFP_KERNEL | __GFP_NOWARN | - __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!dmb->cpu_addr) - clear_bit(dmb->sba_idx, ism->sba_bitmap); + folio = folio_alloc(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | + __GFP_NORETRY, get_order(dmb->dmb_len)); - return dmb->cpu_addr ? 0 : -ENOMEM; + if (!folio) { + rc = -ENOMEM; + goto out_bit; + } + + dmb->cpu_addr = folio_address(folio); + dmb->dma_addr = dma_map_page(&ism->pdev->dev, + virt_to_page(dmb->cpu_addr), 0, + dmb->dmb_len, DMA_FROM_DEVICE); + if (dma_mapping_error(&ism->pdev->dev, dmb->dma_addr)) { + rc = -ENOMEM; + goto out_free; + } + + return 0; + +out_free: + kfree(dmb->cpu_addr); +out_bit: + clear_bit(dmb->sba_idx, ism->sba_bitmap); + return rc; } int ism_register_dmb(struct ism_dev *ism, struct ism_dmb *dmb, diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 097dfe4b620d..35f8e00850d6 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1797,7 +1797,7 @@ static int hisi_sas_debug_I_T_nexus_reset(struct domain_device *device) if (dev_is_sata(device)) { struct ata_link *link = &device->sata_dev.ap->link; - rc = ata_wait_after_reset(link, HISI_SAS_WAIT_PHYUP_TIMEOUT, + rc = ata_wait_after_reset(link, jiffies + HISI_SAS_WAIT_PHYUP_TIMEOUT, smp_ata_check_ready_type); } else { msleep(2000); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 7d2a33514538..34f96cc35342 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2244,7 +2244,15 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task, case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: if ((dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) && (sipc_rx_err_type & RX_FIS_STATUS_ERR_MSK)) { - ts->stat = SAS_PROTO_RESPONSE; + if (task->ata_task.use_ncq) { + struct domain_device *device = task->dev; + struct hisi_sas_device *sas_dev = device->lldd_dev; + + sas_dev->dev_status = HISI_SAS_DEV_NCQ_ERR; + slot->abort = 1; + } else { + ts->stat = SAS_PROTO_RESPONSE; + } } else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) { ts->residual = trans_tx_fail_type; ts->stat = SAS_DATA_UNDERRUN; diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c index 26e6b3e3af43..dcde55c8ee5d 100644 --- a/drivers/scsi/qla2xxx/qla_edif.c +++ b/drivers/scsi/qla2xxx/qla_edif.c @@ -1100,7 +1100,7 @@ qla_edif_app_getstats(scsi_qla_host_t *vha, struct bsg_job *bsg_job) list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) { if (fcport->edif.enable) { - if (pcnt > app_req.num_ports) + if (pcnt >= app_req.num_ports) break; app_reply->elem[pcnt].rekey_count = diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 2e28e2360c85..5b3230ef51fe 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -635,10 +635,9 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (blk_queue_add_random(q)) add_disk_randomness(req->q->disk); - if (!blk_rq_is_passthrough(req)) { - WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED)); - cmd->flags &= ~SCMD_INITIALIZED; - } + WARN_ON_ONCE(!blk_rq_is_passthrough(req) && + !(cmd->flags & SCMD_INITIALIZED)); + cmd->flags = 0; /* * Calling rcu_barrier() is not necessary here because the diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 386981c6976a..baf870a03ecf 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -285,6 +285,7 @@ sg_open(struct inode *inode, struct file *filp) int dev = iminor(inode); int flags = filp->f_flags; struct request_queue *q; + struct scsi_device *device; Sg_device *sdp; Sg_fd *sfp; int retval; @@ -301,11 +302,12 @@ sg_open(struct inode *inode, struct file *filp) /* This driver's module count bumped by fops_get in <linux/fs.h> */ /* Prevent the device driver from vanishing while we sleep */ - retval = scsi_device_get(sdp->device); + device = sdp->device; + retval = scsi_device_get(device); if (retval) goto sg_put; - retval = scsi_autopm_get_device(sdp->device); + retval = scsi_autopm_get_device(device); if (retval) goto sdp_put; @@ -313,7 +315,7 @@ sg_open(struct inode *inode, struct file *filp) * check if O_NONBLOCK. Permits SCSI commands to be issued * during error recovery. Tread carefully. */ if (!((flags & O_NONBLOCK) || - scsi_block_when_processing_errors(sdp->device))) { + scsi_block_when_processing_errors(device))) { retval = -ENXIO; /* we are in error recovery for this device */ goto error_out; @@ -344,7 +346,7 @@ sg_open(struct inode *inode, struct file *filp) if (sdp->open_cnt < 1) { /* no existing opens */ sdp->sgdebug = 0; - q = sdp->device->request_queue; + q = device->request_queue; sdp->sg_tablesize = queue_max_segments(q); } sfp = sg_add_sfp(sdp); @@ -370,10 +372,11 @@ out_undo: error_mutex_locked: mutex_unlock(&sdp->open_rel_lock); error_out: - scsi_autopm_put_device(sdp->device); + scsi_autopm_put_device(device); sdp_put: - scsi_device_put(sdp->device); - goto sg_put; + kref_put(&sdp->d_ref, sg_device_destroy); + scsi_device_put(device); + return retval; } /* Release resources associated with a successful sg_open() @@ -2233,7 +2236,6 @@ sg_remove_sfp_usercontext(struct work_struct *work) "sg_remove_sfp: sfp=0x%p\n", sfp)); kfree(sfp); - WARN_ON_ONCE(kref_read(&sdp->d_ref) != 1); kref_put(&sdp->d_ref, sg_device_destroy); scsi_device_put(device); module_put(THIS_MODULE); diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index c1fbcdd16182..c40217f44b1b 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -3672,6 +3672,8 @@ static int __init target_core_init_configfs(void) { struct configfs_subsystem *subsys = &target_core_fabrics; struct t10_alua_lu_gp *lu_gp; + struct cred *kern_cred; + const struct cred *old_cred; int ret; pr_debug("TARGET_CORE[0]: Loading Generic Kernel Storage" @@ -3748,11 +3750,21 @@ static int __init target_core_init_configfs(void) if (ret < 0) goto out; + /* We use the kernel credentials to access the target directory */ + kern_cred = prepare_kernel_cred(&init_task); + if (!kern_cred) { + ret = -ENOMEM; + goto out; + } + old_cred = override_creds(kern_cred); target_init_dbroot(); + revert_creds(old_cred); + put_cred(kern_cred); return 0; out: + target_xcopy_release_pt(); configfs_unregister_subsystem(subsys); core_dev_release_virtual_lun0(); rd_module_exit(); diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c index c617e8b9f0dd..d78d54ae2605 100644 --- a/drivers/thermal/thermal_debugfs.c +++ b/drivers/thermal/thermal_debugfs.c @@ -616,6 +616,7 @@ void thermal_debug_tz_trip_up(struct thermal_zone_device *tz, tze->trip_stats[trip_id].timestamp = now; tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, temperature); tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, temperature); + tze->trip_stats[trip_id].count++; tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg + (temperature - tze->trip_stats[trip_id].avg) / tze->trip_stats[trip_id].count; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 6ffc4e81ffed..326433df5880 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -3180,22 +3180,29 @@ void tb_switch_unconfigure_link(struct tb_switch *sw) { struct tb_port *up, *down; - if (sw->is_unplugged) - return; if (!tb_route(sw) || tb_switch_is_icm(sw)) return; + /* + * Unconfigure downstream port so that wake-on-connect can be + * configured after router unplug. No need to unconfigure upstream port + * since its router is unplugged. + */ up = tb_upstream_port(sw); - if (tb_switch_is_usb4(up->sw)) - usb4_port_unconfigure(up); - else - tb_lc_unconfigure_port(up); - down = up->remote; if (tb_switch_is_usb4(down->sw)) usb4_port_unconfigure(down); else tb_lc_unconfigure_port(down); + + if (sw->is_unplugged) + return; + + up = tb_upstream_port(sw); + if (tb_switch_is_usb4(up->sw)) + usb4_port_unconfigure(up); + else + tb_lc_unconfigure_port(up); } static void tb_switch_credits_init(struct tb_switch *sw) @@ -3441,7 +3448,26 @@ static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags) return tb_lc_set_wake(sw, flags); } -int tb_switch_resume(struct tb_switch *sw) +static void tb_switch_check_wakes(struct tb_switch *sw) +{ + if (device_may_wakeup(&sw->dev)) { + if (tb_switch_is_usb4(sw)) + usb4_switch_check_wakes(sw); + } +} + +/** + * tb_switch_resume() - Resume a switch after sleep + * @sw: Switch to resume + * @runtime: Is this resume from runtime suspend or system sleep + * + * Resumes and re-enumerates router (and all its children), if still plugged + * after suspend. Don't enumerate device router whose UID was changed during + * suspend. If this is resume from system sleep, notifies PM core about the + * wakes occurred during suspend. Disables all wakes, except USB4 wake of + * upstream port for USB4 routers that shall be always enabled. + */ +int tb_switch_resume(struct tb_switch *sw, bool runtime) { struct tb_port *port; int err; @@ -3490,6 +3516,9 @@ int tb_switch_resume(struct tb_switch *sw) if (err) return err; + if (!runtime) + tb_switch_check_wakes(sw); + /* Disable wakes */ tb_switch_set_wake(sw, 0); @@ -3519,7 +3548,8 @@ int tb_switch_resume(struct tb_switch *sw) */ if (tb_port_unlock(port)) tb_port_warn(port, "failed to unlock port\n"); - if (port->remote && tb_switch_resume(port->remote->sw)) { + if (port->remote && + tb_switch_resume(port->remote->sw, runtime)) { tb_port_warn(port, "lost during suspend, disconnecting\n"); tb_sw_set_unplugged(port->remote->sw); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index c5ce7a694b27..3e44c78ac409 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -1801,6 +1801,12 @@ static struct tb_port *tb_find_dp_out(struct tb *tb, struct tb_port *in) continue; } + /* Needs to be on different routers */ + if (in->sw == port->sw) { + tb_port_dbg(port, "skipping DP OUT on same router\n"); + continue; + } + tb_port_dbg(port, "DP OUT available\n"); /* @@ -2936,7 +2942,7 @@ static int tb_resume_noirq(struct tb *tb) if (!tb_switch_is_usb4(tb->root_switch)) tb_switch_reset(tb->root_switch); - tb_switch_resume(tb->root_switch); + tb_switch_resume(tb->root_switch, false); tb_free_invalid_tunnels(tb); tb_free_unplugged_children(tb->root_switch); tb_restore_children(tb->root_switch); @@ -3062,7 +3068,7 @@ static int tb_runtime_resume(struct tb *tb) struct tb_tunnel *tunnel, *n; mutex_lock(&tb->lock); - tb_switch_resume(tb->root_switch); + tb_switch_resume(tb->root_switch, true); tb_free_invalid_tunnels(tb); tb_restore_children(tb->root_switch); list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index feed8ecaf712..18aae4ccaed5 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -827,7 +827,7 @@ int tb_switch_configuration_valid(struct tb_switch *sw); int tb_switch_add(struct tb_switch *sw); void tb_switch_remove(struct tb_switch *sw); void tb_switch_suspend(struct tb_switch *sw, bool runtime); -int tb_switch_resume(struct tb_switch *sw); +int tb_switch_resume(struct tb_switch *sw, bool runtime); int tb_switch_reset(struct tb_switch *sw); int tb_switch_wait_for_bit(struct tb_switch *sw, u32 offset, u32 bit, u32 value, int timeout_msec); @@ -1288,6 +1288,7 @@ static inline bool tb_switch_is_usb4(const struct tb_switch *sw) return usb4_switch_version(sw) > 0; } +void usb4_switch_check_wakes(struct tb_switch *sw); int usb4_switch_setup(struct tb_switch *sw); int usb4_switch_configuration_valid(struct tb_switch *sw); int usb4_switch_read_uid(struct tb_switch *sw, u64 *uid); diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 9860b49d7a2b..78b06e922fda 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -155,7 +155,13 @@ static inline int usb4_switch_op_data(struct tb_switch *sw, u16 opcode, tx_dwords, rx_data, rx_dwords); } -static void usb4_switch_check_wakes(struct tb_switch *sw) +/** + * usb4_switch_check_wakes() - Check for wakes and notify PM core about them + * @sw: Router whose wakes to check + * + * Checks wakes occurred during suspend and notify the PM core about them. + */ +void usb4_switch_check_wakes(struct tb_switch *sw) { bool wakeup_usb4 = false; struct usb4_port *usb4; @@ -163,9 +169,6 @@ static void usb4_switch_check_wakes(struct tb_switch *sw) bool wakeup = false; u32 val; - if (!device_may_wakeup(&sw->dev)) - return; - if (tb_route(sw)) { if (tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_6, 1)) return; @@ -244,8 +247,6 @@ int usb4_switch_setup(struct tb_switch *sw) u32 val = 0; int ret; - usb4_switch_check_wakes(sw); - if (!tb_route(sw)) return 0; diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index a3acbf0f5da1..1300c92b8702 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -356,9 +356,9 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios, long rate; int ret; + clk_disable_unprepare(d->clk); rate = clk_round_rate(d->clk, newrate); - if (rate > 0 && p->uartclk != rate) { - clk_disable_unprepare(d->clk); + if (rate > 0) { /* * Note that any clock-notifer worker will block in * serial8250_update_uartclk() until we are done. @@ -366,8 +366,8 @@ static void dw8250_set_termios(struct uart_port *p, struct ktermios *termios, ret = clk_set_rate(d->clk, newrate); if (!ret) p->uartclk = rate; - clk_prepare_enable(d->clk); } + clk_prepare_enable(d->clk); dw8250_do_set_termios(p, termios, old); } diff --git a/drivers/tty/serial/8250/8250_lpc18xx.c b/drivers/tty/serial/8250/8250_lpc18xx.c index 7984ee05af1d..47e1a056a60c 100644 --- a/drivers/tty/serial/8250/8250_lpc18xx.c +++ b/drivers/tty/serial/8250/8250_lpc18xx.c @@ -151,7 +151,7 @@ static int lpc18xx_serial_probe(struct platform_device *pdev) ret = uart_read_port_properties(&uart.port); if (ret) - return ret; + goto dis_uart_clk; uart.port.iotype = UPIO_MEM32; uart.port.regshift = 2; diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 0d35c77fad9e..e2e4f99f9d34 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -5010,12 +5010,6 @@ static const struct pci_device_id serial_pci_tbl[] = { { PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_QUATRO_B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_2_115200 }, - { PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_QUATTRO_A, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_b0_bt_2_115200 }, - { PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_QUATTRO_B, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, - pbn_b0_bt_2_115200 }, { PCI_VENDOR_ID_LAVA, PCI_DEVICE_ID_LAVA_OCTO_A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_4_460800 }, diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index 4749331fe618..1e8853eae504 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -1086,11 +1086,13 @@ static void mxs_auart_set_ldisc(struct uart_port *port, static irqreturn_t mxs_auart_irq_handle(int irq, void *context) { - u32 istat; + u32 istat, stat; struct mxs_auart_port *s = context; u32 mctrl_temp = s->mctrl_prev; - u32 stat = mxs_read(s, REG_STAT); + uart_port_lock(&s->port); + + stat = mxs_read(s, REG_STAT); istat = mxs_read(s, REG_INTR); /* ack irq */ @@ -1126,6 +1128,8 @@ static irqreturn_t mxs_auart_irq_handle(int irq, void *context) istat &= ~AUART_INTR_TXIS; } + uart_port_unlock(&s->port); + return IRQ_HANDLED; } diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c index 05d97e89511e..92195f984de1 100644 --- a/drivers/tty/serial/pmac_zilog.c +++ b/drivers/tty/serial/pmac_zilog.c @@ -210,7 +210,6 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) { struct tty_port *port; unsigned char ch, r1, drop, flag; - int loops = 0; /* Sanity check, make sure the old bug is no longer happening */ if (uap->port.state == NULL) { @@ -291,25 +290,12 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) if (r1 & Rx_OVR) tty_insert_flip_char(port, 0, TTY_OVERRUN); next_char: - /* We can get stuck in an infinite loop getting char 0 when the - * line is in a wrong HW state, we break that here. - * When that happens, I disable the receive side of the driver. - * Note that what I've been experiencing is a real irq loop where - * I'm getting flooded regardless of the actual port speed. - * Something strange is going on with the HW - */ - if ((++loops) > 1000) - goto flood; ch = read_zsreg(uap, R0); if (!(ch & Rx_CH_AV)) break; } return true; - flood: - pmz_interrupt_control(uap, 0); - pmz_error("pmz: rx irq flood !\n"); - return true; } static void pmz_status_handle(struct uart_pmac_port *uap) diff --git a/drivers/tty/serial/serial_base.h b/drivers/tty/serial/serial_base.h index c74c548f0db6..b6c38d2edfd4 100644 --- a/drivers/tty/serial/serial_base.h +++ b/drivers/tty/serial/serial_base.h @@ -22,6 +22,7 @@ struct serial_ctrl_device { struct serial_port_device { struct device dev; struct uart_port *port; + unsigned int tx_enabled:1; }; int serial_base_ctrl_init(void); @@ -30,6 +31,9 @@ void serial_base_ctrl_exit(void); int serial_base_port_init(void); void serial_base_port_exit(void); +void serial_base_port_startup(struct uart_port *port); +void serial_base_port_shutdown(struct uart_port *port); + int serial_base_driver_register(struct device_driver *driver); void serial_base_driver_unregister(struct device_driver *driver); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index ff85ebd3a007..c476d884356d 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -156,7 +156,7 @@ static void __uart_start(struct uart_state *state) * enabled, serial_port_runtime_resume() calls start_tx() again * after enabling the device. */ - if (pm_runtime_active(&port_dev->dev)) + if (!pm_runtime_enabled(port->dev) || pm_runtime_active(&port_dev->dev)) port->ops->start_tx(port); pm_runtime_mark_last_busy(&port_dev->dev); pm_runtime_put_autosuspend(&port_dev->dev); @@ -323,16 +323,26 @@ static int uart_startup(struct tty_struct *tty, struct uart_state *state, bool init_hw) { struct tty_port *port = &state->port; + struct uart_port *uport; int retval; if (tty_port_initialized(port)) - return 0; + goto out_base_port_startup; retval = uart_port_startup(tty, state, init_hw); - if (retval) + if (retval) { set_bit(TTY_IO_ERROR, &tty->flags); + return retval; + } - return retval; +out_base_port_startup: + uport = uart_port_check(state); + if (!uport) + return -EIO; + + serial_base_port_startup(uport); + + return 0; } /* @@ -355,6 +365,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) if (tty) set_bit(TTY_IO_ERROR, &tty->flags); + if (uport) + serial_base_port_shutdown(uport); + if (tty_port_initialized(port)) { tty_port_set_initialized(port, false); @@ -1775,6 +1788,7 @@ static void uart_tty_port_shutdown(struct tty_port *port) uport->ops->stop_rx(uport); uart_port_unlock_irq(uport); + serial_base_port_shutdown(uport); uart_port_shutdown(port); /* @@ -1788,6 +1802,7 @@ static void uart_tty_port_shutdown(struct tty_port *port) * Free the transmit buffer. */ uart_port_lock_irq(uport); + uart_circ_clear(&state->xmit); buf = state->xmit.buf; state->xmit.buf = NULL; uart_port_unlock_irq(uport); diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c index 22b9eeb23e68..7e3a1c7b097c 100644 --- a/drivers/tty/serial/serial_port.c +++ b/drivers/tty/serial/serial_port.c @@ -39,8 +39,12 @@ static int serial_port_runtime_resume(struct device *dev) /* Flush any pending TX for the port */ uart_port_lock_irqsave(port, &flags); + if (!port_dev->tx_enabled) + goto unlock; if (__serial_port_busy(port)) port->ops->start_tx(port); + +unlock: uart_port_unlock_irqrestore(port, flags); out: @@ -60,6 +64,11 @@ static int serial_port_runtime_suspend(struct device *dev) return 0; uart_port_lock_irqsave(port, &flags); + if (!port_dev->tx_enabled) { + uart_port_unlock_irqrestore(port, flags); + return 0; + } + busy = __serial_port_busy(port); if (busy) port->ops->start_tx(port); @@ -71,6 +80,31 @@ static int serial_port_runtime_suspend(struct device *dev) return busy ? -EBUSY : 0; } +static void serial_base_port_set_tx(struct uart_port *port, + struct serial_port_device *port_dev, + bool enabled) +{ + unsigned long flags; + + uart_port_lock_irqsave(port, &flags); + port_dev->tx_enabled = enabled; + uart_port_unlock_irqrestore(port, flags); +} + +void serial_base_port_startup(struct uart_port *port) +{ + struct serial_port_device *port_dev = port->port_dev; + + serial_base_port_set_tx(port, port_dev, true); +} + +void serial_base_port_shutdown(struct uart_port *port) +{ + struct serial_port_device *port_dev = port->port_dev; + + serial_base_port_set_tx(port, port_dev, false); +} + static DEFINE_RUNTIME_DEV_PM_OPS(serial_port_pm, serial_port_runtime_suspend, serial_port_runtime_resume, NULL); diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 58d169e5c1db..4fa5a03ebac0 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -861,6 +861,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; u32 sr; unsigned int size; + irqreturn_t ret = IRQ_NONE; sr = readl_relaxed(port->membase + ofs->isr); @@ -869,11 +870,14 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) (sr & USART_SR_TC)) { stm32_usart_tc_interrupt_disable(port); stm32_usart_rs485_rts_disable(port); + ret = IRQ_HANDLED; } - if ((sr & USART_SR_RTOF) && ofs->icr != UNDEF_REG) + if ((sr & USART_SR_RTOF) && ofs->icr != UNDEF_REG) { writel_relaxed(USART_ICR_RTOCF, port->membase + ofs->icr); + ret = IRQ_HANDLED; + } if ((sr & USART_SR_WUF) && ofs->icr != UNDEF_REG) { /* Clear wake up flag and disable wake up interrupt */ @@ -882,6 +886,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) stm32_usart_clr_bits(port, ofs->cr3, USART_CR3_WUFIE); if (irqd_is_wakeup_set(irq_get_irq_data(port->irq))) pm_wakeup_event(tport->tty->dev, 0); + ret = IRQ_HANDLED; } /* @@ -896,6 +901,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); + ret = IRQ_HANDLED; } } @@ -903,6 +909,7 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) uart_port_lock(port); stm32_usart_transmit_chars(port); uart_port_unlock(port); + ret = IRQ_HANDLED; } /* Receiver timeout irq for DMA RX */ @@ -912,9 +919,10 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); + ret = IRQ_HANDLED; } - return IRQ_HANDLED; + return ret; } static void stm32_usart_set_mctrl(struct uart_port *port, unsigned int mctrl) @@ -1084,6 +1092,7 @@ static int stm32_usart_startup(struct uart_port *port) val |= USART_CR2_SWAP; writel_relaxed(val, port->membase + ofs->cr2); } + stm32_port->throttled = false; /* RX FIFO Flush */ if (ofs->rqr != UNDEF_REG) diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 06859e17b67b..7a00004bfd03 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -47,7 +47,7 @@ enum { TSTBUS_MAX, }; -#define QCOM_UFS_MAX_GEAR 4 +#define QCOM_UFS_MAX_GEAR 5 #define QCOM_UFS_MAX_LANE 2 enum { @@ -67,26 +67,32 @@ static const struct __ufs_qcom_bw_table { [MODE_PWM][UFS_PWM_G2][UFS_LANE_1] = { 1844, 1000 }, [MODE_PWM][UFS_PWM_G3][UFS_LANE_1] = { 3688, 1000 }, [MODE_PWM][UFS_PWM_G4][UFS_LANE_1] = { 7376, 1000 }, + [MODE_PWM][UFS_PWM_G5][UFS_LANE_1] = { 14752, 1000 }, [MODE_PWM][UFS_PWM_G1][UFS_LANE_2] = { 1844, 1000 }, [MODE_PWM][UFS_PWM_G2][UFS_LANE_2] = { 3688, 1000 }, [MODE_PWM][UFS_PWM_G3][UFS_LANE_2] = { 7376, 1000 }, [MODE_PWM][UFS_PWM_G4][UFS_LANE_2] = { 14752, 1000 }, + [MODE_PWM][UFS_PWM_G5][UFS_LANE_2] = { 29504, 1000 }, [MODE_HS_RA][UFS_HS_G1][UFS_LANE_1] = { 127796, 1000 }, [MODE_HS_RA][UFS_HS_G2][UFS_LANE_1] = { 255591, 1000 }, [MODE_HS_RA][UFS_HS_G3][UFS_LANE_1] = { 1492582, 102400 }, [MODE_HS_RA][UFS_HS_G4][UFS_LANE_1] = { 2915200, 204800 }, + [MODE_HS_RA][UFS_HS_G5][UFS_LANE_1] = { 5836800, 409600 }, [MODE_HS_RA][UFS_HS_G1][UFS_LANE_2] = { 255591, 1000 }, [MODE_HS_RA][UFS_HS_G2][UFS_LANE_2] = { 511181, 1000 }, [MODE_HS_RA][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 }, [MODE_HS_RA][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 }, + [MODE_HS_RA][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 }, [MODE_HS_RB][UFS_HS_G1][UFS_LANE_1] = { 149422, 1000 }, [MODE_HS_RB][UFS_HS_G2][UFS_LANE_1] = { 298189, 1000 }, [MODE_HS_RB][UFS_HS_G3][UFS_LANE_1] = { 1492582, 102400 }, [MODE_HS_RB][UFS_HS_G4][UFS_LANE_1] = { 2915200, 204800 }, + [MODE_HS_RB][UFS_HS_G5][UFS_LANE_1] = { 5836800, 409600 }, [MODE_HS_RB][UFS_HS_G1][UFS_LANE_2] = { 298189, 1000 }, [MODE_HS_RB][UFS_HS_G2][UFS_LANE_2] = { 596378, 1000 }, [MODE_HS_RB][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 }, [MODE_HS_RB][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 }, + [MODE_HS_RB][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 }, [MODE_MAX][0][0] = { 7643136, 307200 }, }; diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 20d9762331bd..6be3462b109f 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -181,12 +181,14 @@ hv_uio_cleanup(struct hv_device *dev, struct hv_uio_private_data *pdata) { if (pdata->send_gpadl.gpadl_handle) { vmbus_teardown_gpadl(dev->channel, &pdata->send_gpadl); - vfree(pdata->send_buf); + if (!pdata->send_gpadl.decrypted) + vfree(pdata->send_buf); } if (pdata->recv_gpadl.gpadl_handle) { vmbus_teardown_gpadl(dev->channel, &pdata->recv_gpadl); - vfree(pdata->recv_buf); + if (!pdata->recv_gpadl.decrypted) + vfree(pdata->recv_buf); } } @@ -295,7 +297,8 @@ hv_uio_probe(struct hv_device *dev, ret = vmbus_establish_gpadl(channel, pdata->recv_buf, RECV_BUFFER_SIZE, &pdata->recv_gpadl); if (ret) { - vfree(pdata->recv_buf); + if (!pdata->recv_gpadl.decrypted) + vfree(pdata->recv_buf); goto fail_close; } @@ -317,7 +320,8 @@ hv_uio_probe(struct hv_device *dev, ret = vmbus_establish_gpadl(channel, pdata->send_buf, SEND_BUFFER_SIZE, &pdata->send_gpadl); if (ret) { - vfree(pdata->send_buf); + if (!pdata->send_gpadl.decrypted) + vfree(pdata->send_buf); goto fail_close; } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index c8262e2f2917..c553decb5461 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -485,7 +485,6 @@ out_free_mem: static int service_outstanding_interrupt(struct wdm_device *desc) { int rv = 0; - int used; /* submit read urb only if the device is waiting for it */ if (!desc->resp_count || !--desc->resp_count) @@ -500,10 +499,7 @@ static int service_outstanding_interrupt(struct wdm_device *desc) goto out; } - used = test_and_set_bit(WDM_RESPONDING, &desc->flags); - if (used) - goto out; - + set_bit(WDM_RESPONDING, &desc->flags); spin_unlock_irq(&desc->iuspin); rv = usb_submit_urb(desc->response, GFP_KERNEL); spin_lock_irq(&desc->iuspin); diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 686c01af03e6..0e1262a077ae 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -449,8 +449,10 @@ static void usb_port_shutdown(struct device *dev) { struct usb_port *port_dev = to_usb_port(dev); - if (port_dev->child) + if (port_dev->child) { usb_disable_usb2_hardware_lpm(port_dev->child); + usb_unlocked_disable_lpm(port_dev->child); + } } static const struct dev_pm_ops usb_port_pm_ops = { diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index 79582b102c7e..994a78ad084b 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -867,13 +867,15 @@ static int dwc2_cmpl_host_isoc_dma_desc(struct dwc2_hsotg *hsotg, struct dwc2_dma_desc *dma_desc; struct dwc2_hcd_iso_packet_desc *frame_desc; u16 frame_desc_idx; - struct urb *usb_urb = qtd->urb->priv; + struct urb *usb_urb; u16 remain = 0; int rc = 0; if (!qtd->urb) return -EINVAL; + usb_urb = qtd->urb->priv; + dma_sync_single_for_cpu(hsotg->dev, qh->desc_list_dma + (idx * sizeof(struct dwc2_dma_desc)), sizeof(struct dwc2_dma_desc), diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 72bb722da2f2..d96ffbe52039 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -226,7 +226,8 @@ void dwc3_ep0_stall_and_restart(struct dwc3 *dwc) /* reinitialize physical ep1 */ dep = dwc->eps[1]; - dep->flags = DWC3_EP_ENABLED; + dep->flags &= DWC3_EP_RESOURCE_ALLOCATED; + dep->flags |= DWC3_EP_ENABLED; /* stall is always issued on EP0 */ dep = dwc->eps[0]; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index bffbc1dc651f..f855f1fc8e5e 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -46,6 +46,8 @@ #define FUNCTIONFS_MAGIC 0xa647361 /* Chosen by a honest dice roll ;) */ +#define DMABUF_ENQUEUE_TIMEOUT_MS 5000 + MODULE_IMPORT_NS(DMA_BUF); /* Reference counter handling */ @@ -1578,10 +1580,13 @@ static int ffs_dmabuf_transfer(struct file *file, struct ffs_dmabuf_priv *priv; struct ffs_dma_fence *fence; struct usb_request *usb_req; + enum dma_resv_usage resv_dir; struct dma_buf *dmabuf; + unsigned long timeout; struct ffs_ep *ep; bool cookie; u32 seqno; + long retl; int ret; if (req->flags & ~USB_FFS_DMABUF_TRANSFER_MASK) @@ -1615,17 +1620,14 @@ static int ffs_dmabuf_transfer(struct file *file, goto err_attachment_put; /* Make sure we don't have writers */ - if (!dma_resv_test_signaled(dmabuf->resv, DMA_RESV_USAGE_WRITE)) { - pr_vdebug("FFS WRITE fence is not signaled\n"); - ret = -EBUSY; - goto err_resv_unlock; - } - - /* If we're writing to the DMABUF, make sure we don't have readers */ - if (epfile->in && - !dma_resv_test_signaled(dmabuf->resv, DMA_RESV_USAGE_READ)) { - pr_vdebug("FFS READ fence is not signaled\n"); - ret = -EBUSY; + timeout = nonblock ? 0 : msecs_to_jiffies(DMABUF_ENQUEUE_TIMEOUT_MS); + retl = dma_resv_wait_timeout(dmabuf->resv, + dma_resv_usage_rw(epfile->in), + true, timeout); + if (retl == 0) + retl = -EBUSY; + if (retl < 0) { + ret = (int)retl; goto err_resv_unlock; } @@ -1665,8 +1667,9 @@ static int ffs_dmabuf_transfer(struct file *file, dma_fence_init(&fence->base, &ffs_dmabuf_fence_ops, &priv->lock, priv->context, seqno); - dma_resv_add_fence(dmabuf->resv, &fence->base, - dma_resv_usage_rw(epfile->in)); + resv_dir = epfile->in ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ; + + dma_resv_add_fence(dmabuf->resv, &fence->base, resv_dir); dma_resv_unlock(dmabuf->resv); /* Now that the dma_fence is in place, queue the transfer. */ diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index 28f4e6552e84..0acc32ed9960 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -878,7 +878,7 @@ static int ncm_set_alt(struct usb_function *f, unsigned intf, unsigned alt) if (alt > 1) goto fail; - if (ncm->port.in_ep->enabled) { + if (ncm->netdev) { DBG(cdev, "reset ncm\n"); ncm->netdev = NULL; gether_disconnect(&ncm->port); @@ -1367,7 +1367,7 @@ static void ncm_disable(struct usb_function *f) DBG(cdev, "ncm deactivated\n"); - if (ncm->port.in_ep->enabled) { + if (ncm->netdev) { ncm->netdev = NULL; gether_disconnect(&ncm->port); } diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index e82d03224f94..3432ebfae978 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -868,7 +868,7 @@ fsl_ep_queue(struct usb_ep *_ep, struct usb_request *_req, gfp_t gfp_flags) { struct fsl_ep *ep = container_of(_ep, struct fsl_ep, ep); struct fsl_req *req = container_of(_req, struct fsl_req, req); - struct fsl_udc *udc; + struct fsl_udc *udc = ep->udc; unsigned long flags; int ret; @@ -878,7 +878,7 @@ fsl_ep_queue(struct usb_ep *_ep, struct usb_request *_req, gfp_t gfp_flags) dev_vdbg(&udc->gadget.dev, "%s, bad params\n", __func__); return -EINVAL; } - if (unlikely(!_ep || !ep->ep.desc)) { + if (unlikely(!ep->ep.desc)) { dev_vdbg(&udc->gadget.dev, "%s, bad ep\n", __func__); return -EINVAL; } @@ -887,7 +887,6 @@ fsl_ep_queue(struct usb_ep *_ep, struct usb_request *_req, gfp_t gfp_flags) return -EMSGSIZE; } - udc = ep->udc; if (!udc->driver || udc->gadget.speed == USB_SPEED_UNKNOWN) return -ESHUTDOWN; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 52278afea94b..575f0fd9c9f1 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3133,7 +3133,7 @@ static int xhci_handle_events(struct xhci_hcd *xhci, struct xhci_interrupter *ir irqreturn_t xhci_irq(struct usb_hcd *hcd) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); - irqreturn_t ret = IRQ_NONE; + irqreturn_t ret = IRQ_HANDLED; u32 status; spin_lock(&xhci->lock); @@ -3141,12 +3141,13 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) status = readl(&xhci->op_regs->status); if (status == ~(u32)0) { xhci_hc_died(xhci); - ret = IRQ_HANDLED; goto out; } - if (!(status & STS_EINT)) + if (!(status & STS_EINT)) { + ret = IRQ_NONE; goto out; + } if (status & STS_HCE) { xhci_warn(xhci, "WARNING: Host Controller Error\n"); @@ -3156,7 +3157,6 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) if (status & STS_FATAL) { xhci_warn(xhci, "WARNING: Host System Error\n"); xhci_halt(xhci); - ret = IRQ_HANDLED; goto out; } @@ -3167,7 +3167,6 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) */ status |= STS_EINT; writel(status, &xhci->op_regs->status); - ret = IRQ_HANDLED; /* This is the handler of the primary interrupter */ xhci_handle_events(xhci, xhci->interrupters[0]); diff --git a/drivers/usb/host/xhci-trace.h b/drivers/usb/host/xhci-trace.h index 1740000d54c2..5762564b9d73 100644 --- a/drivers/usb/host/xhci-trace.h +++ b/drivers/usb/host/xhci-trace.h @@ -172,8 +172,7 @@ DECLARE_EVENT_CLASS(xhci_log_free_virt_dev, __field(void *, vdev) __field(unsigned long long, out_ctx) __field(unsigned long long, in_ctx) - __field(int, hcd_portnum) - __field(int, hw_portnum) + __field(int, slot_id) __field(u16, current_mel) ), @@ -181,13 +180,12 @@ DECLARE_EVENT_CLASS(xhci_log_free_virt_dev, __entry->vdev = vdev; __entry->in_ctx = (unsigned long long) vdev->in_ctx->dma; __entry->out_ctx = (unsigned long long) vdev->out_ctx->dma; - __entry->hcd_portnum = (int) vdev->rhub_port->hcd_portnum; - __entry->hw_portnum = (int) vdev->rhub_port->hw_portnum; + __entry->slot_id = (int) vdev->slot_id; __entry->current_mel = (u16) vdev->current_mel; ), - TP_printk("vdev %p ctx %llx | %llx hcd_portnum %d hw_portnum %d current_mel %d", - __entry->vdev, __entry->in_ctx, __entry->out_ctx, - __entry->hcd_portnum, __entry->hw_portnum, __entry->current_mel + TP_printk("vdev %p slot %d ctx %llx | %llx current_mel %d", + __entry->vdev, __entry->slot_id, __entry->in_ctx, + __entry->out_ctx, __entry->current_mel ) ); diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c index c6101ed2d9d4..d8049275a023 100644 --- a/drivers/usb/misc/onboard_usb_hub.c +++ b/drivers/usb/misc/onboard_usb_hub.c @@ -78,7 +78,7 @@ static int onboard_hub_power_on(struct onboard_hub *hub) err = regulator_bulk_enable(hub->pdata->num_supplies, hub->supplies); if (err) { dev_err(hub->dev, "failed to enable supplies: %pe\n", ERR_PTR(err)); - return err; + goto disable_clk; } fsleep(hub->pdata->reset_us); @@ -87,6 +87,10 @@ static int onboard_hub_power_on(struct onboard_hub *hub) hub->is_powered_on = true; return 0; + +disable_clk: + clk_disable_unprepare(hub->clk); + return err; } static int onboard_hub_power_off(struct onboard_hub *hub) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 55a65d941ccb..8a5846d4adf6 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -255,6 +255,10 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM061K_LMS 0x0124 #define QUECTEL_PRODUCT_EC25 0x0125 #define QUECTEL_PRODUCT_EM060K_128 0x0128 +#define QUECTEL_PRODUCT_EM060K_129 0x0129 +#define QUECTEL_PRODUCT_EM060K_12a 0x012a +#define QUECTEL_PRODUCT_EM060K_12b 0x012b +#define QUECTEL_PRODUCT_EM060K_12c 0x012c #define QUECTEL_PRODUCT_EG91 0x0191 #define QUECTEL_PRODUCT_EG95 0x0195 #define QUECTEL_PRODUCT_BG96 0x0296 @@ -1218,6 +1222,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_128, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_129, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12a, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12b, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K_12c, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM061K_LCN, 0xff, 0xff, 0x40) }, @@ -1360,6 +1376,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff), /* Telit FE990 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a0, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a4, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a9, 0xff), /* Telit FN20C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2052,6 +2074,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, 0x9803, 0xff), .driver_info = RSVD(4) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b05), /* Longsung U8300 */ + .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, 0x9b3c), /* Longsung U9300 */ + .driver_info = RSVD(0) | RSVD(4) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) }, { USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) }, @@ -2272,15 +2298,29 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) }, /* Fibocom FG150 Diag */ { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) }, /* Fibocom FG150 AT */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0111, 0xff) }, /* Fibocom FM160 (MBIM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0115, 0xff), /* Fibocom FM135 (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) }, /* Fibocom NL668-AM/NL652-EU (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a3, 0xff) }, /* Fibocom FM101-GL (laptop MBIM) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff), /* Fibocom FM101-GL (laptop MBIM) */ .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a04, 0xff) }, /* Fibocom FM650-CN (ECM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a05, 0xff) }, /* Fibocom FM650-CN (NCM mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a06, 0xff) }, /* Fibocom FM650-CN (RNDIS mode) */ + { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a07, 0xff) }, /* Fibocom FM650-CN (MBIM mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ + { USB_DEVICE(0x33f8, 0x0104), /* Rolling RW101-GL (laptop RMNET) */ + .driver_info = RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a2, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a3, 0xff) }, /* Rolling RW101-GL (laptop MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x01a4, 0xff), /* Rolling RW101-GL (laptop MBIM) */ + .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0115, 0xff), /* Rolling RW135-GL (laptop MBIM) */ + .driver_info = RSVD(5) }, { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, diff --git a/drivers/usb/typec/mux/it5205.c b/drivers/usb/typec/mux/it5205.c index 5535932e42cd..4357cc67a867 100644 --- a/drivers/usb/typec/mux/it5205.c +++ b/drivers/usb/typec/mux/it5205.c @@ -22,7 +22,7 @@ #include <linux/usb/typec_mux.h> #define IT5205_REG_CHIP_ID(x) (0x4 + (x)) -#define IT5205FN_CHIP_ID 0x35323035 /* "5205" */ +#define IT5205FN_CHIP_ID 0x35303235 /* "5025" -> "5205" */ /* MUX power down register */ #define IT5205_REG_MUXPDR 0x10 diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index c26fb70c3ec6..ab6ed6111ed0 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -6855,14 +6855,14 @@ static int tcpm_pd_set(struct typec_port *p, struct usb_power_delivery *pd) if (data->sink_desc.pdo[0]) { for (i = 0; i < PDO_MAX_OBJECTS && data->sink_desc.pdo[i]; i++) port->snk_pdo[i] = data->sink_desc.pdo[i]; - port->nr_snk_pdo = i + 1; + port->nr_snk_pdo = i; port->operating_snk_mw = data->operating_snk_mw; } if (data->source_desc.pdo[0]) { for (i = 0; i < PDO_MAX_OBJECTS && data->source_desc.pdo[i]; i++) port->src_pdo[i] = data->source_desc.pdo[i]; - port->nr_src_pdo = i + 1; + port->nr_src_pdo = i; } switch (port->state) { diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 31d8a46ae5e7..bd6ae92aa39e 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1736,11 +1736,13 @@ static int ucsi_init(struct ucsi *ucsi) ucsi->connector = connector; ucsi->ntfy = ntfy; + mutex_lock(&ucsi->ppm_lock); ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci)); + mutex_unlock(&ucsi->ppm_lock); if (ret) return ret; - if (UCSI_CCI_CONNECTOR(READ_ONCE(cci))) - ucsi_connector_change(ucsi, cci); + if (UCSI_CCI_CONNECTOR(cci)) + ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci)); return 0; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index b246067e074b..6cb96a1e8b7d 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/vhost/vhost.c b/drivers/vhost/vhost.c index 045f666b4f12..8995730ce0bf 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2515,7 +2515,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, vq->avail_idx = vhost16_to_cpu(vq, avail_idx); if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) { - vq_err(vq, "Guest moved used index from %u to %u", + vq_err(vq, "Guest moved avail index from %u to %u", last_avail_idx, vq->avail_idx); return -EFAULT; } @@ -2799,9 +2799,19 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq) r = vhost_get_avail_idx(vq, &avail_idx); if (unlikely(r)) return false; + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); + if (vq->avail_idx != vq->last_avail_idx) { + /* Since we have updated avail_idx, the following + * call to vhost_get_vq_desc() will read available + * ring entries. Make sure that read happens after + * the avail_idx read. + */ + smp_rmb(); + return false; + } - return vq->avail_idx == vq->last_avail_idx; + return true; } EXPORT_SYMBOL_GPL(vhost_vq_avail_empty); @@ -2838,9 +2848,19 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) &vq->avail->idx, r); return false; } + vq->avail_idx = vhost16_to_cpu(vq, avail_idx); + if (vq->avail_idx != vq->last_avail_idx) { + /* Since we have updated avail_idx, the following + * call to vhost_get_vq_desc() will read available + * ring entries. Make sure that read happens after + * the avail_idx read. + */ + smp_rmb(); + return true; + } - return vq->avail_idx != vq->last_avail_idx; + return false; } EXPORT_SYMBOL_GPL(vhost_enable_notify); diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c index b67a28da4702..a1c467a0e9f7 100644 --- a/drivers/virt/vmgenid.c +++ b/drivers/virt/vmgenid.c @@ -68,7 +68,6 @@ out: static void vmgenid_notify(struct acpi_device *device, u32 event) { struct vmgenid_state *state = acpi_driver_data(device); - char *envp[] = { "NEW_VMGENID=1", NULL }; u8 old_id[VMGENID_SIZE]; memcpy(old_id, state->this_id, sizeof(old_id)); @@ -76,7 +75,6 @@ static void vmgenid_notify(struct acpi_device *device, u32 event) if (!memcmp(old_id, state->this_id, sizeof(old_id))) return; add_vmfork_randomness(state->this_id, sizeof(state->this_id)); - kobject_uevent_env(&device->dev.kobj, KOBJ_CHANGE, envp); } static const struct acpi_device_id vmgenid_ids[] = { diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index f173587893cb..9510c551dce8 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -362,14 +362,16 @@ static const struct bus_type virtio_bus = { .remove = virtio_dev_remove, }; -int register_virtio_driver(struct virtio_driver *driver) +int __register_virtio_driver(struct virtio_driver *driver, struct module *owner) { /* Catch this early. */ BUG_ON(driver->feature_table_size && !driver->feature_table); driver->driver.bus = &virtio_bus; + driver->driver.owner = owner; + return driver_register(&driver->driver); } -EXPORT_SYMBOL_GPL(register_virtio_driver); +EXPORT_SYMBOL_GPL(__register_virtio_driver); void unregister_virtio_driver(struct virtio_driver *driver) { diff --git a/fs/9p/fid.h b/fs/9p/fid.h index 29281b7c3887..0d6138bee2a3 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -49,9 +49,6 @@ static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry) static inline void v9fs_fid_add_modes(struct p9_fid *fid, unsigned int s_flags, unsigned int s_cache, unsigned int f_flags) { - if (fid->qid.type != P9_QTFILE) - return; - if ((!s_cache) || ((fid->qid.version == 0) && !(s_flags & V9FS_IGNORE_QV)) || (s_flags & V9FS_DIRECT_IO) || (f_flags & O_DIRECT)) { diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 9defa12208f9..1775fcc7f0e8 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_file.c b/fs/9p/vfs_file.c index abdbbaee5184..348cc90bf9c5 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -520,6 +520,7 @@ const struct file_operations v9fs_file_operations = { .splice_read = v9fs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, + .setlease = simple_nosetlease, }; const struct file_operations v9fs_file_operations_dotl = { @@ -534,4 +535,5 @@ const struct file_operations v9fs_file_operations_dotl = { .splice_read = v9fs_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, + .setlease = simple_nosetlease, }; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index b01b1bbf2493..7a3308d77606 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -83,7 +83,7 @@ static int p9mode2perm(struct v9fs_session_info *v9ses, int res; int mode = stat->mode; - res = mode & S_IALLUGO; + res = mode & 0777; /* S_IRWXUGO */ if (v9fs_proto_dotu(v9ses)) { if ((mode & P9_DMSETUID) == P9_DMSETUID) res |= S_ISUID; @@ -178,6 +178,9 @@ int v9fs_uflags2omode(int uflags, int extended) break; } + if (uflags & O_TRUNC) + ret |= P9_OTRUNC; + if (extended) { if (uflags & O_EXCL) ret |= P9_OEXCL; @@ -361,7 +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; @@ -373,8 +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 @@ -398,11 +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); - } /** @@ -434,8 +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); + } + } } /** @@ -486,6 +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); @@ -551,7 +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, @@ -680,7 +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 @@ -1061,8 +1085,6 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, struct v9fs_session_info *v9ses = sb->s_fs_info; struct v9fs_inode *v9inode = V9FS_I(inode); - set_nlink(inode, 1); - inode_set_atime(inode, stat->atime, 0); inode_set_mtime(inode, stat->mtime, 0); inode_set_ctime(inode, stat->mtime, 0); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 55dde186041a..c61b97bd13b9 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 4236058c7bbd..f52fdf42945c 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; @@ -244,6 +244,21 @@ done: return res; } +static int v9fs_drop_inode(struct inode *inode) +{ + struct v9fs_session_info *v9ses; + + v9ses = v9fs_inode2v9ses(inode); + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) + return generic_drop_inode(inode); + /* + * in case of non cached mode always drop the + * inode because we want the inode attribute + * to always match that on the server. + */ + return 1; +} + static int v9fs_write_inode(struct inode *inode, struct writeback_control *wbc) { @@ -268,6 +283,7 @@ static const struct super_operations v9fs_super_ops = { .alloc_inode = v9fs_alloc_inode, .free_inode = v9fs_free_inode, .statfs = simple_statfs, + .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, @@ -278,6 +294,7 @@ static const struct super_operations v9fs_super_ops_dotl = { .alloc_inode = v9fs_alloc_inode, .free_inode = v9fs_free_inode, .statfs = v9fs_statfs, + .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, diff --git a/fs/bcachefs/acl.c b/fs/bcachefs/acl.c index 3640f417cce1..5c180fdc3efb 100644 --- a/fs/bcachefs/acl.c +++ b/fs/bcachefs/acl.c @@ -281,7 +281,6 @@ struct posix_acl *bch2_get_acl(struct mnt_idmap *idmap, struct xattr_search_key search = X_SEARCH(acl_to_xattr_type(type), "", 0); struct btree_trans *trans = bch2_trans_get(c); struct btree_iter iter = { NULL }; - struct bkey_s_c_xattr xattr; struct posix_acl *acl = NULL; struct bkey_s_c k; int ret; @@ -290,28 +289,27 @@ retry: ret = bch2_hash_lookup(trans, &iter, bch2_xattr_hash_desc, &hash, inode_inum(inode), &search, 0); - if (ret) { - if (!bch2_err_matches(ret, ENOENT)) - acl = ERR_PTR(ret); - goto out; - } + if (ret) + goto err; k = bch2_btree_iter_peek_slot(&iter); ret = bkey_err(k); - if (ret) { - acl = ERR_PTR(ret); - goto out; - } + if (ret) + goto err; - xattr = bkey_s_c_to_xattr(k); + struct bkey_s_c_xattr xattr = bkey_s_c_to_xattr(k); acl = bch2_acl_from_disk(trans, xattr_val(xattr.v), - le16_to_cpu(xattr.v->x_val_len)); + le16_to_cpu(xattr.v->x_val_len)); + ret = PTR_ERR_OR_ZERO(acl); +err: + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) + goto retry; - if (!IS_ERR(acl)) + if (ret) + acl = !bch2_err_matches(ret, ENOENT) ? ERR_PTR(ret) : NULL; + + if (!IS_ERR_OR_NULL(acl)) set_cached_acl(&inode->v, type, acl); -out: - if (bch2_err_matches(PTR_ERR_OR_ZERO(acl), BCH_ERR_transaction_restart)) - goto retry; bch2_trans_iter_exit(trans, &iter); bch2_trans_put(trans); diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index 114328acde72..a20044201002 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -49,13 +49,15 @@ int bch2_backpointer_invalid(struct bch_fs *c, struct bkey_s_c k, if (!bch2_dev_exists2(c, bp.k->p.inode)) return 0; + struct bch_dev *ca = bch_dev_bkey_exists(c, bp.k->p.inode); struct bpos bucket = bp_pos_to_bucket(c, bp.k->p); int ret = 0; - bkey_fsck_err_on(!bpos_eq(bp.k->p, bucket_pos_to_bp(c, bucket, bp.v->bucket_offset)), + bkey_fsck_err_on((bp.v->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT) >= ca->mi.bucket_size || + !bpos_eq(bp.k->p, bucket_pos_to_bp(c, bucket, bp.v->bucket_offset)), c, err, - backpointer_pos_wrong, - "backpointer at wrong pos"); + backpointer_bucket_offset_wrong, + "backpointer bucket_offset wrong"); fsck_err: return ret; } @@ -468,7 +470,7 @@ found: goto err; } - bio = bio_alloc(ca->disk_sb.bdev, 1, REQ_OP_READ, GFP_KERNEL); + bio = bio_alloc(ca->disk_sb.bdev, buf_pages(data_buf, bytes), REQ_OP_READ, GFP_KERNEL); bio->bi_iter.bi_sector = p.ptr.offset; bch2_bio_map(bio, data_buf, bytes); ret = submit_bio_wait(bio); diff --git a/fs/bcachefs/backpointers.h b/fs/bcachefs/backpointers.h index da012ca7daee..85949b9fd880 100644 --- a/fs/bcachefs/backpointers.h +++ b/fs/bcachefs/backpointers.h @@ -53,14 +53,11 @@ static inline struct bpos bucket_pos_to_bp(const struct bch_fs *c, u64 bucket_offset) { struct bch_dev *ca = bch_dev_bkey_exists(c, bucket.inode); - struct bpos ret; - - ret = POS(bucket.inode, - (bucket_to_sector(ca, bucket.offset) << - MAX_EXTENT_COMPRESS_RATIO_SHIFT) + bucket_offset); + struct bpos ret = POS(bucket.inode, + (bucket_to_sector(ca, bucket.offset) << + MAX_EXTENT_COMPRESS_RATIO_SHIFT) + bucket_offset); EBUG_ON(!bkey_eq(bucket, bp_pos_to_bucket(c, ret))); - return ret; } diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index a31a5f706929..91c3c1fef233 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -709,6 +709,8 @@ struct btree_trans_buf { x(stripe_delete) \ x(reflink) \ x(fallocate) \ + x(fsync) \ + x(dio_write) \ x(discard) \ x(discard_fast) \ x(invalidate) \ diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 63102992d955..f7fbfccd2b1e 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -578,7 +578,8 @@ struct bch_member { __le64 nbuckets; /* device size */ __le16 first_bucket; /* index of first bucket used */ __le16 bucket_size; /* sectors */ - __le32 pad; + __u8 btree_bitmap_shift; + __u8 pad[3]; __le64 last_mount; /* time_t */ __le64 flags; @@ -587,6 +588,7 @@ struct bch_member { __le64 errors_at_reset[BCH_MEMBER_ERROR_NR]; __le64 errors_reset_time; __le64 seq; + __le64 btree_allocated_bitmap; }; #define BCH_MEMBER_V1_BYTES 56 @@ -876,7 +878,8 @@ struct bch_sb_field_downgrade { x(rebalance_work, BCH_VERSION(1, 3)) \ x(member_seq, BCH_VERSION(1, 4)) \ x(subvolume_fs_parent, BCH_VERSION(1, 5)) \ - x(btree_subvolume_children, BCH_VERSION(1, 6)) + x(btree_subvolume_children, BCH_VERSION(1, 6)) \ + x(mi_btree_bitmap, BCH_VERSION(1, 7)) enum bcachefs_metadata_version { bcachefs_metadata_version_min = 9, @@ -1314,7 +1317,7 @@ static inline __u64 __bset_magic(struct bch_sb *sb) x(write_buffer_keys, 11) \ x(datetime, 12) -enum { +enum bch_jset_entry_type { #define x(f, nr) BCH_JSET_ENTRY_##f = nr, BCH_JSET_ENTRY_TYPES() #undef x @@ -1360,7 +1363,7 @@ struct jset_entry_blacklist_v2 { x(inodes, 1) \ x(key_version, 2) -enum { +enum bch_fs_usage_type { #define x(f, nr) BCH_FS_USAGE_##f = nr, BCH_FS_USAGE_TYPES() #undef x @@ -1501,7 +1504,8 @@ 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, \ @@ -1535,6 +1539,20 @@ enum btree_id { BTREE_ID_NR }; +static inline bool btree_id_is_alloc(enum btree_id id) +{ + switch (id) { + case BTREE_ID_alloc: + case BTREE_ID_backpointers: + case BTREE_ID_need_discard: + case BTREE_ID_freespace: + case BTREE_ID_bucket_gens: + return true; + default: + return false; + } +} + #define BTREE_MAX_DEPTH 4U /* Btree nodes */ diff --git a/fs/bcachefs/bkey.h b/fs/bcachefs/bkey.h index cf23ff47bed8..3a45d128f608 100644 --- a/fs/bcachefs/bkey.h +++ b/fs/bcachefs/bkey.h @@ -314,6 +314,12 @@ static inline unsigned bkeyp_key_u64s(const struct bkey_format *format, return bkey_packed(k) ? format->key_u64s : BKEY_U64s; } +static inline bool bkeyp_u64s_valid(const struct bkey_format *f, + const struct bkey_packed *k) +{ + return ((unsigned) k->u64s - bkeyp_key_u64s(f, k) <= U8_MAX - BKEY_U64s); +} + static inline unsigned bkeyp_key_bytes(const struct bkey_format *format, const struct bkey_packed *k) { diff --git a/fs/bcachefs/bkey_methods.c b/fs/bcachefs/bkey_methods.c index 5e52684764eb..db336a43fc08 100644 --- a/fs/bcachefs/bkey_methods.c +++ b/fs/bcachefs/bkey_methods.c @@ -171,11 +171,15 @@ int __bch2_bkey_invalid(struct bch_fs *c, struct bkey_s_c k, if (type >= BKEY_TYPE_NR) return 0; - bkey_fsck_err_on((flags & BKEY_INVALID_COMMIT) && + bkey_fsck_err_on((type == BKEY_TYPE_btree || + (flags & BKEY_INVALID_COMMIT)) && !(bch2_key_types_allowed[type] & BIT_ULL(k.k->type)), c, err, bkey_invalid_type_for_btree, "invalid key type for btree %s (%s)", - bch2_btree_node_type_str(type), bch2_bkey_types[k.k->type]); + bch2_btree_node_type_str(type), + k.k->type < KEY_TYPE_MAX + ? bch2_bkey_types[k.k->type] + : "(unknown)"); if (btree_node_type_is_extents(type) && !bkey_whiteout(k.k)) { bkey_fsck_err_on(k.k->size == 0, c, err, diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 84474324dba9..02c70e813fac 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -709,9 +709,31 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans, struct bch_fs *c = trans->c; struct btree_cache *bc = &c->btree_cache; struct btree *b; - u32 seq; - BUG_ON(level + 1 >= BTREE_MAX_DEPTH); + if (unlikely(level >= BTREE_MAX_DEPTH)) { + int ret = bch2_fs_topology_error(c, "attempting to get btree node at level %u, >= max depth %u", + level, BTREE_MAX_DEPTH); + return ERR_PTR(ret); + } + + if (unlikely(!bkey_is_btree_ptr(&k->k))) { + struct printbuf buf = PRINTBUF; + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k)); + + int ret = bch2_fs_topology_error(c, "attempting to get btree node with non-btree key %s", buf.buf); + printbuf_exit(&buf); + return ERR_PTR(ret); + } + + if (unlikely(k->k.u64s > BKEY_BTREE_PTR_U64s_MAX)) { + struct printbuf buf = PRINTBUF; + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k)); + + int ret = bch2_fs_topology_error(c, "attempting to get btree node with too big key %s", buf.buf); + printbuf_exit(&buf); + return ERR_PTR(ret); + } + /* * Parent node must be locked, else we could read in a btree node that's * been freed: @@ -752,34 +774,26 @@ static noinline struct btree *bch2_btree_node_fill(struct btree_trans *trans, } set_btree_node_read_in_flight(b); - six_unlock_write(&b->c.lock); - seq = six_lock_seq(&b->c.lock); - six_unlock_intent(&b->c.lock); - /* Unlock before doing IO: */ - if (path && sync) - bch2_trans_unlock_noassert(trans); - - bch2_btree_node_read(trans, b, sync); + if (path) { + u32 seq = six_lock_seq(&b->c.lock); - if (!sync) - return NULL; + /* Unlock before doing IO: */ + six_unlock_intent(&b->c.lock); + bch2_trans_unlock_noassert(trans); - if (path) { - int ret = bch2_trans_relock(trans) ?: - bch2_btree_path_relock_intent(trans, path); - if (ret) { - BUG_ON(!trans->restarted); - return ERR_PTR(ret); - } - } + bch2_btree_node_read(trans, b, sync); - if (!six_relock_type(&b->c.lock, lock_type, seq)) { - BUG_ON(!path); + if (!sync) + return NULL; - trace_and_count(c, trans_restart_relock_after_fill, trans, _THIS_IP_, path); - return ERR_PTR(btree_trans_restart(trans, BCH_ERR_transaction_restart_relock_after_fill)); + if (!six_relock_type(&b->c.lock, lock_type, seq)) + b = NULL; + } else { + bch2_btree_node_read(trans, b, sync); + if (lock_type == SIX_LOCK_read) + six_lock_downgrade(&b->c.lock); } return b; @@ -1112,18 +1126,19 @@ int bch2_btree_node_prefetch(struct btree_trans *trans, { struct bch_fs *c = trans->c; struct btree_cache *bc = &c->btree_cache; - struct btree *b; BUG_ON(path && !btree_node_locked(path, level + 1)); BUG_ON(level >= BTREE_MAX_DEPTH); - b = btree_cache_find(bc, k); + struct btree *b = btree_cache_find(bc, k); if (b) return 0; b = bch2_btree_node_fill(trans, path, k, btree_id, level, SIX_LOCK_read, false); - return PTR_ERR_OR_ZERO(b); + if (!IS_ERR_OR_NULL(b)) + six_unlock_read(&b->c.lock); + return bch2_trans_relock(trans) ?: PTR_ERR_OR_ZERO(b); } void bch2_btree_node_evict(struct btree_trans *trans, const struct bkey_i *k) @@ -1148,6 +1163,8 @@ wait_on_io: btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_intent); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_write); + if (unlikely(b->hash_val != btree_ptr_hash_val(k))) + goto out; if (btree_node_dirty(b)) { __bch2_btree_node_write(c, b, BTREE_WRITE_cache_reclaim); @@ -1162,7 +1179,7 @@ wait_on_io: btree_node_data_free(c, b); bch2_btree_node_hash_remove(bc, b); mutex_unlock(&bc->lock); - +out: six_unlock_write(&b->c.lock); six_unlock_intent(&b->c.lock); } diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index 6280da1244b5..791470b0c654 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -368,11 +368,16 @@ again: buf.buf)) { bch2_btree_node_evict(trans, cur_k.k); cur = NULL; - ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes) ?: - bch2_journal_key_delete(c, b->c.btree_id, - b->c.level, cur_k.k->k.p); + ret = bch2_journal_key_delete(c, b->c.btree_id, + b->c.level, cur_k.k->k.p); if (ret) break; + + if (!btree_id_is_alloc(b->c.btree_id)) { + ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); + if (ret) + break; + } continue; } @@ -544,12 +549,12 @@ reconstruct_root: bch2_btree_root_alloc_fake(c, i, 0); } else { bch2_btree_root_alloc_fake(c, i, 1); + bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX); if (ret) break; } - bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); reconstructed_root = true; } @@ -823,6 +828,7 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, struct bch_fs *c = trans->c; struct bkey deleted = KEY(0, 0, 0); struct bkey_s_c old = (struct bkey_s_c) { &deleted, NULL }; + struct printbuf buf = PRINTBUF; int ret = 0; deleted.p = k->k->p; @@ -843,11 +849,23 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, if (ret) goto err; + if (mustfix_fsck_err_on(level && !bch2_dev_btree_bitmap_marked(c, *k), + c, btree_bitmap_not_marked, + "btree ptr not marked in member info btree allocated bitmap\n %s", + (bch2_bkey_val_to_text(&buf, c, *k), + buf.buf))) { + mutex_lock(&c->sb_lock); + bch2_dev_btree_bitmap_mark(c, *k); + bch2_write_super(c); + mutex_unlock(&c->sb_lock); + } + ret = commit_do(trans, NULL, NULL, 0, bch2_key_trigger(trans, btree_id, level, old, unsafe_bkey_s_c_to_s(*k), BTREE_TRIGGER_GC)); fsck_err: err: + printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } @@ -1569,7 +1587,7 @@ 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; @@ -1577,6 +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 d7de82ac3893..debb0edc3455 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -831,7 +831,7 @@ static int bset_key_invalid(struct bch_fs *c, struct btree *b, (rw == WRITE ? bch2_bkey_val_invalid(c, k, READ, err) : 0); } -static bool __bkey_valid(struct bch_fs *c, struct btree *b, +static bool bkey_packed_valid(struct bch_fs *c, struct btree *b, struct bset *i, struct bkey_packed *k) { if (bkey_p_next(k) > vstruct_last(i)) @@ -840,7 +840,7 @@ static bool __bkey_valid(struct bch_fs *c, struct btree *b, if (k->format > KEY_FORMAT_CURRENT) return false; - if (k->u64s < bkeyp_key_u64s(&b->format, k)) + if (!bkeyp_u64s_valid(&b->format, k)) return false; struct printbuf buf = PRINTBUF; @@ -884,11 +884,13 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, "invalid bkey format %u", k->format)) goto drop_this_key; - if (btree_err_on(k->u64s < bkeyp_key_u64s(&b->format, k), + if (btree_err_on(!bkeyp_u64s_valid(&b->format, k), -BCH_ERR_btree_node_read_err_fixable, c, NULL, b, i, btree_node_bkey_bad_u64s, - "k->u64s too small (%u < %u)", k->u64s, bkeyp_key_u64s(&b->format, k))) + "bad k->u64s %u (min %u max %zu)", k->u64s, + bkeyp_key_u64s(&b->format, k), + U8_MAX - BKEY_U64s + bkeyp_key_u64s(&b->format, k))) goto drop_this_key; if (!write) @@ -947,13 +949,12 @@ drop_this_key: * do */ - if (!__bkey_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) { + if (!bkey_packed_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) { for (next_good_key = 1; next_good_key < (u64 *) vstruct_last(i) - (u64 *) k; next_good_key++) - if (__bkey_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) + if (bkey_packed_valid(c, b, i, (void *) ((u64 *) k + next_good_key))) goto got_good_key; - } /* @@ -1339,7 +1340,9 @@ start: rb->start_time); bio_put(&rb->bio); - if (saw_error && !btree_node_read_error(b)) { + if (saw_error && + !btree_node_read_error(b) && + c->curr_recovery_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes) { printbuf_reset(&buf); bch2_bpos_to_text(&buf, b->key.k.p); bch_err_ratelimited(c, "%s: rewriting btree node at btree=%s level=%u %s due to error", diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index 24772538e4cc..1c70836dd7cc 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -498,8 +498,13 @@ static inline void set_btree_iter_dontneed(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; - if (!trans->restarted) - btree_iter_path(trans, iter)->preserve = false; + if (!iter->path || trans->restarted) + return; + + struct btree_path *path = btree_iter_path(trans, iter); + path->preserve = false; + if (path->ref == 1) + path->should_be_locked = false; } void *__bch2_trans_kmalloc(struct btree_trans *, size_t); @@ -642,7 +647,7 @@ int __bch2_btree_trans_too_many_iters(struct btree_trans *); static inline int btree_trans_too_many_iters(struct btree_trans *trans) { - if (bitmap_weight(trans->paths_allocated, trans->nr_paths) > BTREE_ITER_INITIAL - 8) + if (bitmap_weight(trans->paths_allocated, trans->nr_paths) > BTREE_ITER_NORMAL_LIMIT - 8) return __bch2_btree_trans_too_many_iters(trans); return 0; diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c index 5cbcbfe85235..1e8cf49a6935 100644 --- a/fs/bcachefs/btree_journal_iter.c +++ b/fs/bcachefs/btree_journal_iter.c @@ -130,12 +130,30 @@ struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *c, enum btree_id btree return bch2_journal_keys_peek_upto(c, btree_id, level, pos, pos, &idx); } +static void journal_iter_verify(struct journal_iter *iter) +{ + struct journal_keys *keys = iter->keys; + size_t gap_size = keys->size - keys->nr; + + BUG_ON(iter->idx >= keys->gap && + iter->idx < keys->gap + gap_size); + + if (iter->idx < keys->size) { + struct journal_key *k = keys->data + iter->idx; + + int cmp = cmp_int(k->btree_id, iter->btree_id) ?: + cmp_int(k->level, iter->level); + BUG_ON(cmp < 0); + } +} + static void journal_iters_fix(struct bch_fs *c) { struct journal_keys *keys = &c->journal_keys; /* The key we just inserted is immediately before the gap: */ size_t gap_end = keys->gap + (keys->size - keys->nr); - struct btree_and_journal_iter *iter; + struct journal_key *new_key = &keys->data[keys->gap - 1]; + struct journal_iter *iter; /* * If an iterator points one after the key we just inserted, decrement @@ -143,9 +161,14 @@ static void journal_iters_fix(struct bch_fs *c) * decrement was unnecessary, bch2_btree_and_journal_iter_peek() will * handle that: */ - list_for_each_entry(iter, &c->journal_iters, journal.list) - if (iter->journal.idx == gap_end) - iter->journal.idx = keys->gap - 1; + list_for_each_entry(iter, &c->journal_iters, list) { + journal_iter_verify(iter); + if (iter->idx == gap_end && + new_key->btree_id == iter->btree_id && + new_key->level == iter->level) + iter->idx = keys->gap - 1; + journal_iter_verify(iter); + } } static void journal_iters_move_gap(struct bch_fs *c, size_t old_gap, size_t new_gap) @@ -192,7 +215,12 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id, if (idx > keys->gap) idx -= keys->size - keys->nr; + size_t old_gap = keys->gap; + if (keys->nr == keys->size) { + journal_iters_move_gap(c, old_gap, keys->size); + old_gap = keys->size; + struct journal_keys new_keys = { .nr = keys->nr, .size = max_t(size_t, keys->size, 8) * 2, @@ -216,7 +244,7 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id, keys->gap = keys->nr; } - journal_iters_move_gap(c, keys->gap, idx); + journal_iters_move_gap(c, old_gap, idx); move_gap(keys, idx); @@ -301,16 +329,21 @@ static void bch2_journal_iter_advance(struct journal_iter *iter) static struct bkey_s_c bch2_journal_iter_peek(struct journal_iter *iter) { - struct journal_key *k = iter->keys->data + iter->idx; + journal_iter_verify(iter); + + while (iter->idx < iter->keys->size) { + struct journal_key *k = iter->keys->data + iter->idx; + + int cmp = cmp_int(k->btree_id, iter->btree_id) ?: + cmp_int(k->level, iter->level); + if (cmp > 0) + break; + BUG_ON(cmp); - while (k < iter->keys->data + iter->keys->size && - k->btree_id == iter->btree_id && - k->level == iter->level) { if (!k->overwritten) return bkey_i_to_s_c(k->k); bch2_journal_iter_advance(iter); - k = iter->keys->data + iter->idx; } return bkey_s_c_null; @@ -330,6 +363,8 @@ static void bch2_journal_iter_init(struct bch_fs *c, iter->level = level; iter->keys = &c->journal_keys; iter->idx = bch2_journal_key_search(&c->journal_keys, id, level, pos); + + journal_iter_verify(iter); } static struct bkey_s_c bch2_journal_iter_peek_btree(struct btree_and_journal_iter *iter) @@ -434,10 +469,15 @@ void __bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans, iter->trans = trans; iter->b = b; iter->node_iter = node_iter; - bch2_journal_iter_init(trans->c, &iter->journal, b->c.btree_id, b->c.level, pos); - INIT_LIST_HEAD(&iter->journal.list); iter->pos = b->data->min_key; iter->at_end = false; + INIT_LIST_HEAD(&iter->journal.list); + + if (trans->journal_replay_not_finished) { + bch2_journal_iter_init(trans->c, &iter->journal, b->c.btree_id, b->c.level, pos); + if (!test_bit(BCH_FS_may_go_rw, &trans->c->flags)) + list_add(&iter->journal.list, &trans->c->journal_iters); + } } /* @@ -452,9 +492,6 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans, bch2_btree_node_iter_init_from_start(&node_iter, b); __bch2_btree_and_journal_iter_init_node_iter(trans, iter, b, node_iter, b->data->min_key); - if (trans->journal_replay_not_finished && - !test_bit(BCH_FS_may_go_rw, &trans->c->flags)) - list_add(&iter->journal.list, &trans->c->journal_iters); } /* sort and dedup all keys in the journal: */ diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 581edcb0911b..e8c1c530cd95 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -169,6 +169,7 @@ static void bkey_cached_move_to_freelist(struct btree_key_cache *bc, } else { mutex_lock(&bc->lock); list_move_tail(&ck->list, &bc->freed_pcpu); + bc->nr_freed_pcpu++; mutex_unlock(&bc->lock); } } @@ -245,6 +246,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, if (!list_empty(&bc->freed_pcpu)) { ck = list_last_entry(&bc->freed_pcpu, struct bkey_cached, list); list_del_init(&ck->list); + bc->nr_freed_pcpu--; } mutex_unlock(&bc->lock); } @@ -659,7 +661,7 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans, commit_flags |= BCH_WATERMARK_reclaim; if (ck->journal.seq != journal_last_seq(j) || - j->watermark == BCH_WATERMARK_stripe) + !test_bit(JOURNAL_SPACE_LOW, &c->journal.flags)) commit_flags |= BCH_TRANS_COMMIT_no_journal_res; ret = bch2_btree_iter_traverse(&b_iter) ?: @@ -840,8 +842,6 @@ 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)) @@ -855,11 +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)) @@ -873,9 +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) @@ -891,12 +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); } @@ -914,7 +906,6 @@ next: } while (scanned < nr && bc->shrink_iter != start); rcu_read_unlock(); -out: memalloc_nofs_restore(flags); srcu_read_unlock(&c->btree_trans_barrier, srcu_idx); mutex_unlock(&bc->lock); diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c index b9b151e693ed..f2caf491957e 100644 --- a/fs/bcachefs/btree_locking.c +++ b/fs/bcachefs/btree_locking.c @@ -440,33 +440,7 @@ void bch2_btree_node_lock_write_nofail(struct btree_trans *trans, struct btree_path *path, struct btree_bkey_cached_common *b) { - struct btree_path *linked; - unsigned i, iter; - int ret; - - /* - * XXX BIG FAT NOTICE - * - * Drop all read locks before taking a write lock: - * - * This is a hack, because bch2_btree_node_lock_write_nofail() is a - * hack - but by dropping read locks first, this should never fail, and - * we only use this in code paths where whatever read locks we've - * already taken are no longer needed: - */ - - trans_for_each_path(trans, linked, iter) { - if (!linked->nodes_locked) - continue; - - for (i = 0; i < BTREE_MAX_DEPTH; i++) - if (btree_node_read_locked(linked, i)) { - btree_node_unlock(trans, linked, i); - btree_path_set_dirty(linked, BTREE_ITER_NEED_RELOCK); - } - } - - ret = __btree_node_lock_write(trans, path, b, true); + int ret = __btree_node_lock_write(trans, path, b, true); BUG_ON(ret); } diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index 3f33be7e5e5c..c60794264da2 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -133,6 +133,19 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, if (le64_to_cpu(bn->magic) != bset_magic(c)) return; + if (bch2_csum_type_is_encryption(BSET_CSUM_TYPE(&bn->keys))) { + struct nonce nonce = btree_nonce(&bn->keys, 0); + unsigned bytes = (void *) &bn->keys - (void *) &bn->flags; + + bch2_encrypt(c, BSET_CSUM_TYPE(&bn->keys), nonce, &bn->flags, bytes); + } + + if (btree_id_is_alloc(BTREE_NODE_ID(bn))) + return; + + if (BTREE_NODE_LEVEL(bn) >= BTREE_MAX_DEPTH) + return; + rcu_read_lock(); struct found_btree_node n = { .btree_id = BTREE_NODE_ID(bn), @@ -192,8 +205,13 @@ static int read_btree_nodes_worker(void *p) last_print = jiffies; } - try_read_btree_node(w->f, ca, bio, buf, - bucket * ca->mi.bucket_size + bucket_offset); + u64 sector = bucket * ca->mi.bucket_size + bucket_offset; + + if (c->sb.version_upgrade_complete >= bcachefs_metadata_version_mi_btree_bitmap && + !bch2_dev_btree_bitmap_marked_sectors(ca, sector, btree_sectors(c))) + continue; + + try_read_btree_node(w->f, ca, bio, buf, sector); } err: bio_put(bio); @@ -213,6 +231,9 @@ static int read_btree_nodes(struct find_btree_nodes *f) closure_init_stack(&cl); for_each_online_member(c, ca) { + if (!(ca->mi.data_allowed & BIT(BCH_DATA_btree))) + continue; + struct find_btree_nodes_worker *w = kmalloc(sizeof(*w), GFP_KERNEL); struct task_struct *t; @@ -281,6 +302,8 @@ again: start->max_key = bpos_predecessor(n->min_key); start->range_updated = true; + } else if (n->level) { + n->overwritten = true; } else { struct printbuf buf = PRINTBUF; @@ -290,7 +313,7 @@ again: found_btree_node_to_text(&buf, c, n); bch_err(c, "%s", buf.buf); printbuf_exit(&buf); - return -1; + return -BCH_ERR_fsck_repair_unimplemented; } } @@ -436,6 +459,9 @@ bool bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree) int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree, unsigned level, struct bpos node_min, struct bpos node_max) { + if (btree_id_is_alloc(btree)) + return 0; + struct find_btree_nodes *f = &c->found_btree_nodes; int ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes); diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index aa9da4970740..bbec91e8e650 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -397,12 +397,13 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags struct bkey_cached *ck = (void *) path->l[0].b; unsigned new_u64s; struct bkey_i *new_k; + unsigned watermark = flags & BCH_WATERMARK_MASK; EBUG_ON(path->level); - if (!test_bit(BKEY_CACHED_DIRTY, &ck->flags) && - bch2_btree_key_cache_must_wait(c) && - !(flags & BCH_TRANS_COMMIT_journal_reclaim)) + if (watermark < BCH_WATERMARK_reclaim && + !test_bit(BKEY_CACHED_DIRTY, &ck->flags) && + bch2_btree_key_cache_must_wait(c)) return -BCH_ERR_btree_insert_need_journal_reclaim; /* @@ -499,9 +500,8 @@ static int run_one_trans_trigger(struct btree_trans *trans, struct btree_insert_ } static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, - struct btree_insert_entry *btree_id_start) + unsigned btree_id_start) { - struct btree_insert_entry *i; bool trans_trigger_run; int ret, overwrite; @@ -514,13 +514,13 @@ static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, do { trans_trigger_run = false; - for (i = btree_id_start; - i < trans->updates + trans->nr_updates && i->btree_id <= btree_id; + for (unsigned i = btree_id_start; + i < trans->nr_updates && trans->updates[i].btree_id <= btree_id; i++) { - if (i->btree_id != btree_id) + if (trans->updates[i].btree_id != btree_id) continue; - ret = run_one_trans_trigger(trans, i, overwrite); + ret = run_one_trans_trigger(trans, trans->updates + i, overwrite); if (ret < 0) return ret; if (ret) @@ -534,8 +534,7 @@ static int run_btree_triggers(struct btree_trans *trans, enum btree_id btree_id, static int bch2_trans_commit_run_triggers(struct btree_trans *trans) { - struct btree_insert_entry *btree_id_start = trans->updates; - unsigned btree_id = 0; + unsigned btree_id = 0, btree_id_start = 0; int ret = 0; /* @@ -549,8 +548,8 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans) if (btree_id == BTREE_ID_alloc) continue; - while (btree_id_start < trans->updates + trans->nr_updates && - btree_id_start->btree_id < btree_id) + while (btree_id_start < trans->nr_updates && + trans->updates[btree_id_start].btree_id < btree_id) btree_id_start++; ret = run_btree_triggers(trans, btree_id, btree_id_start); @@ -558,11 +557,13 @@ static int bch2_trans_commit_run_triggers(struct btree_trans *trans) return ret; } - trans_for_each_update(trans, i) { + for (unsigned idx = 0; idx < trans->nr_updates; idx++) { + struct btree_insert_entry *i = trans->updates + idx; + if (i->btree_id > BTREE_ID_alloc) break; if (i->btree_id == BTREE_ID_alloc) { - ret = run_btree_triggers(trans, BTREE_ID_alloc, i); + ret = run_btree_triggers(trans, BTREE_ID_alloc, idx); if (ret) return ret; break; @@ -826,7 +827,8 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags struct bch_fs *c = trans->c; int ret = 0, u64s_delta = 0; - trans_for_each_update(trans, i) { + for (unsigned idx = 0; idx < trans->nr_updates; idx++) { + struct btree_insert_entry *i = trans->updates + idx; if (i->cached) continue; diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index 9404d96c38f3..c69b233c41bb 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; @@ -364,7 +364,21 @@ struct btree_insert_entry { unsigned long ip_allocated; }; +/* Number of btree paths we preallocate, usually enough */ #define BTREE_ITER_INITIAL 64 +/* + * Lmiit for btree_trans_too_many_iters(); this is enough that almost all code + * paths should run inside this limit, and if they don't it usually indicates a + * bug (leaking/duplicated btree paths). + * + * exception: some fsck paths + * + * bugs with excessive path usage seem to have possibly been eliminated now, so + * we might consider eliminating this (and btree_trans_too_many_iter()) at some + * point. + */ +#define BTREE_ITER_NORMAL_LIMIT 256 +/* never exceed limit */ #define BTREE_ITER_MAX (1U << 10) struct btree_trans_commit_hook; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index 32397b99752f..b4efd8cc4d1a 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -21,14 +21,15 @@ #include "keylist.h" #include "recovery_passes.h" #include "replicas.h" +#include "sb-members.h" #include "super-io.h" #include "trace.h" #include <linux/random.h> -const char * const bch2_btree_update_modes[] = { +static const char * const bch2_btree_update_modes[] = { #define x(t) #t, - BCH_WATERMARKS() + BTREE_UPDATE_MODES() #undef x NULL }; @@ -605,6 +606,26 @@ static void btree_update_add_key(struct btree_update *as, bch2_keylist_push(keys); } +static bool btree_update_new_nodes_marked_sb(struct btree_update *as) +{ + for_each_keylist_key(&as->new_keys, k) + if (!bch2_dev_btree_bitmap_marked(as->c, bkey_i_to_s_c(k))) + return false; + return true; +} + +static void btree_update_new_nodes_mark_sb(struct btree_update *as) +{ + struct bch_fs *c = as->c; + + mutex_lock(&c->sb_lock); + for_each_keylist_key(&as->new_keys, k) + bch2_dev_btree_bitmap_mark(c, bkey_i_to_s_c(k)); + + bch2_write_super(c); + mutex_unlock(&c->sb_lock); +} + /* * The transactional part of an interior btree node update, where we journal the * update we did to the interior node and update alloc info: @@ -662,6 +683,9 @@ static void btree_update_nodes_written(struct btree_update *as) if (ret) goto err; + if (!btree_update_new_nodes_marked_sb(as)) + btree_update_new_nodes_mark_sb(as); + /* * Wait for any in flight writes to finish before we free the old nodes * on disk: @@ -704,9 +728,13 @@ static void btree_update_nodes_written(struct btree_update *as) bch2_fs_fatal_err_on(ret && !bch2_journal_error(&c->journal), c, "%s", bch2_err_str(ret)); err: - if (as->b) { - - b = as->b; + /* + * We have to be careful because another thread might be getting ready + * to free as->b and calling btree_update_reparent() on us - we'll + * recheck under btree_update_lock below: + */ + b = READ_ONCE(as->b); + if (b) { btree_path_idx_t path_idx = get_unlocked_mut_path(trans, as->btree_id, b->c.level, b->key.k.p); struct btree_path *path = trans->paths + path_idx; @@ -850,15 +878,17 @@ static void btree_update_updated_node(struct btree_update *as, struct btree *b) { struct bch_fs *c = as->c; - mutex_lock(&c->btree_interior_update_lock); - list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten); - BUG_ON(as->mode != BTREE_UPDATE_none); + BUG_ON(as->update_level_end < b->c.level); BUG_ON(!btree_node_dirty(b)); BUG_ON(!b->c.level); + mutex_lock(&c->btree_interior_update_lock); + list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten); + as->mode = BTREE_UPDATE_node; as->b = b; + as->update_level_end = b->c.level; set_btree_node_write_blocked(b); list_add(&as->write_blocked_list, &b->write_blocked); @@ -1100,7 +1130,7 @@ static void bch2_btree_update_done(struct btree_update *as, struct btree_trans * static struct btree_update * bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, - unsigned level, bool split, unsigned flags) + unsigned level_start, bool split, unsigned flags) { struct bch_fs *c = trans->c; struct btree_update *as; @@ -1108,7 +1138,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, int disk_res_flags = (flags & BCH_TRANS_COMMIT_no_enospc) ? BCH_DISK_RESERVATION_NOFAIL : 0; unsigned nr_nodes[2] = { 0, 0 }; - unsigned update_level = level; + unsigned level_end = level_start; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; int ret = 0; u32 restart_count = trans->restart_count; @@ -1123,34 +1153,30 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, flags &= ~BCH_WATERMARK_MASK; flags |= watermark; - if (watermark < c->journal.watermark) { - struct journal_res res = { 0 }; - unsigned journal_flags = watermark|JOURNAL_RES_GET_CHECK; + if (watermark < BCH_WATERMARK_reclaim && + test_bit(JOURNAL_SPACE_LOW, &c->journal.flags)) { + if (flags & BCH_TRANS_COMMIT_journal_reclaim) + return ERR_PTR(-BCH_ERR_journal_reclaim_would_deadlock); - if ((flags & BCH_TRANS_COMMIT_journal_reclaim) && - watermark < BCH_WATERMARK_reclaim) - journal_flags |= JOURNAL_RES_GET_NONBLOCK; - - ret = drop_locks_do(trans, - bch2_journal_res_get(&c->journal, &res, 1, journal_flags)); - if (bch2_err_matches(ret, BCH_ERR_operation_blocked)) - ret = -BCH_ERR_journal_reclaim_would_deadlock; + bch2_trans_unlock(trans); + wait_event(c->journal.wait, !test_bit(JOURNAL_SPACE_LOW, &c->journal.flags)); + ret = bch2_trans_relock(trans); if (ret) return ERR_PTR(ret); } while (1) { - nr_nodes[!!update_level] += 1 + split; - update_level++; + nr_nodes[!!level_end] += 1 + split; + level_end++; - ret = bch2_btree_path_upgrade(trans, path, update_level + 1); + ret = bch2_btree_path_upgrade(trans, path, level_end + 1); if (ret) return ERR_PTR(ret); - if (!btree_path_node(path, update_level)) { + if (!btree_path_node(path, level_end)) { /* Allocating new root? */ nr_nodes[1] += split; - update_level = BTREE_MAX_DEPTH; + level_end = BTREE_MAX_DEPTH; break; } @@ -1158,11 +1184,11 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, * Always check for space for two keys, even if we won't have to * split at prior level - it might have been a merge instead: */ - if (bch2_btree_node_insert_fits(path->l[update_level].b, + if (bch2_btree_node_insert_fits(path->l[level_end].b, BKEY_BTREE_PTR_U64s_MAX * 2)) break; - split = path->l[update_level].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c); + split = path->l[level_end].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c); } if (!down_read_trylock(&c->gc_lock)) { @@ -1176,14 +1202,15 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, as = mempool_alloc(&c->btree_interior_update_pool, GFP_NOFS); memset(as, 0, sizeof(*as)); closure_init(&as->cl, NULL); - as->c = c; - as->start_time = start_time; - as->ip_started = _RET_IP_; - as->mode = BTREE_UPDATE_none; - as->watermark = watermark; - as->took_gc_lock = true; - as->btree_id = path->btree_id; - as->update_level = update_level; + as->c = c; + as->start_time = start_time; + as->ip_started = _RET_IP_; + as->mode = BTREE_UPDATE_none; + as->watermark = watermark; + as->took_gc_lock = true; + as->btree_id = path->btree_id; + as->update_level_start = level_start; + as->update_level_end = level_end; INIT_LIST_HEAD(&as->list); INIT_LIST_HEAD(&as->unwritten_list); INIT_LIST_HEAD(&as->write_blocked_list); @@ -1277,23 +1304,29 @@ static void bch2_btree_set_root_inmem(struct bch_fs *c, struct btree *b) bch2_recalc_btree_reserve(c); } -static void bch2_btree_set_root(struct btree_update *as, - struct btree_trans *trans, - struct btree_path *path, - struct btree *b) +static int bch2_btree_set_root(struct btree_update *as, + struct btree_trans *trans, + struct btree_path *path, + struct btree *b, + bool nofail) { struct bch_fs *c = as->c; - struct btree *old; trace_and_count(c, btree_node_set_root, trans, b); - old = btree_node_root(c, b); + struct btree *old = btree_node_root(c, b); /* * Ensure no one is using the old root while we switch to the * new root: */ - bch2_btree_node_lock_write_nofail(trans, path, &old->c); + if (nofail) { + bch2_btree_node_lock_write_nofail(trans, path, &old->c); + } else { + int ret = bch2_btree_node_lock_write(trans, path, &old->c); + if (ret) + return ret; + } bch2_btree_set_root_inmem(c, b); @@ -1307,6 +1340,7 @@ static void bch2_btree_set_root(struct btree_update *as, * depend on the new root would have to update the new root. */ bch2_btree_node_unlock_write(trans, path, old); + return 0; } /* Interior node updates: */ @@ -1373,12 +1407,12 @@ static void bch2_insert_fixup_btree_ptr(struct btree_update *as, } static void -__bch2_btree_insert_keys_interior(struct btree_update *as, - struct btree_trans *trans, - struct btree_path *path, - struct btree *b, - struct btree_node_iter node_iter, - struct keylist *keys) +bch2_btree_insert_keys_interior(struct btree_update *as, + struct btree_trans *trans, + struct btree_path *path, + struct btree *b, + struct btree_node_iter node_iter, + struct keylist *keys) { struct bkey_i *insert = bch2_keylist_front(keys); struct bkey_packed *k; @@ -1534,7 +1568,7 @@ static void btree_split_insert_keys(struct btree_update *as, bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p); - __bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys); + bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys); BUG_ON(bch2_btree_node_check_topology(trans, b)); } @@ -1649,15 +1683,16 @@ static int btree_split(struct btree_update *as, struct btree_trans *trans, if (parent) { /* Split a non root node */ ret = bch2_btree_insert_node(as, trans, path, parent, &as->parent_keys); - if (ret) - goto err; } else if (n3) { - bch2_btree_set_root(as, trans, trans->paths + path, n3); + ret = bch2_btree_set_root(as, trans, trans->paths + path, n3, false); } else { /* Root filled up but didn't need to be split */ - bch2_btree_set_root(as, trans, trans->paths + path, n1); + ret = bch2_btree_set_root(as, trans, trans->paths + path, n1, false); } + if (ret) + goto err; + if (n3) { bch2_btree_update_get_open_buckets(as, n3); bch2_btree_node_write(c, n3, SIX_LOCK_intent, 0); @@ -1714,27 +1749,6 @@ err: goto out; } -static void -bch2_btree_insert_keys_interior(struct btree_update *as, - struct btree_trans *trans, - struct btree_path *path, - struct btree *b, - struct keylist *keys) -{ - struct btree_path *linked; - unsigned i; - - __bch2_btree_insert_keys_interior(as, trans, path, b, - path->l[b->c.level].iter, keys); - - btree_update_updated_node(as, b); - - trans_for_each_path_with_node(trans, b, linked, i) - bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b); - - bch2_trans_verify_paths(trans); -} - /** * bch2_btree_insert_node - insert bkeys into a given btree node * @@ -1755,7 +1769,8 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t struct keylist *keys) { struct bch_fs *c = as->c; - struct btree_path *path = trans->paths + path_idx; + struct btree_path *path = trans->paths + path_idx, *linked; + unsigned i; int old_u64s = le16_to_cpu(btree_bset_last(b)->u64s); int old_live_u64s = b->nr.live_u64s; int live_u64s_added, u64s_added; @@ -1784,7 +1799,13 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t return ret; } - bch2_btree_insert_keys_interior(as, trans, path, b, keys); + bch2_btree_insert_keys_interior(as, trans, path, b, + path->l[b->c.level].iter, keys); + + trans_for_each_path_with_node(trans, b, linked, i) + bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b); + + bch2_trans_verify_paths(trans); live_u64s_added = (int) b->nr.live_u64s - old_live_u64s; u64s_added = (int) le16_to_cpu(btree_bset_last(b)->u64s) - old_u64s; @@ -1798,6 +1819,7 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t bch2_maybe_compact_whiteouts(c, b)) bch2_trans_node_reinit_iter(trans, b); + btree_update_updated_node(as, b); bch2_btree_node_unlock_write(trans, path, b); BUG_ON(bch2_btree_node_check_topology(trans, b)); @@ -1807,7 +1829,7 @@ split: * We could attempt to avoid the transaction restart, by calling * bch2_btree_path_upgrade() and allocating more nodes: */ - if (b->c.level >= as->update_level) { + if (b->c.level >= as->update_level_end) { trace_and_count(c, trans_restart_split_race, trans, _THIS_IP_, b); return btree_trans_restart(trans, BCH_ERR_transaction_restart_split_race); } @@ -1873,7 +1895,9 @@ static void __btree_increase_depth(struct btree_update *as, struct btree_trans * bch2_keylist_add(&as->parent_keys, &b->key); btree_split_insert_keys(as, trans, path_idx, n, &as->parent_keys); - bch2_btree_set_root(as, trans, path, n); + int ret = bch2_btree_set_root(as, trans, path, n, true); + BUG_ON(ret); + bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); bch2_trans_node_add(trans, path, n); @@ -1926,6 +1950,22 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, BUG_ON(!trans->paths[path].should_be_locked); BUG_ON(!btree_node_locked(&trans->paths[path], level)); + /* + * Work around a deadlock caused by the btree write buffer not doing + * merges and leaving tons of merges for us to do - we really don't need + * to be doing merges at all from the interior update path, and if the + * interior update path is generating too many new interior updates we + * deadlock: + */ + if ((flags & BCH_WATERMARK_MASK) == BCH_WATERMARK_interior_updates) + return 0; + + if ((flags & BCH_WATERMARK_MASK) <= BCH_WATERMARK_reclaim) { + flags &= ~BCH_WATERMARK_MASK; + flags |= BCH_WATERMARK_btree; + flags |= BCH_TRANS_COMMIT_journal_reclaim; + } + b = trans->paths[path].l[level].b; if ((sib == btree_prev_sib && bpos_eq(b->data->min_key, POS_MIN)) || @@ -2071,6 +2111,10 @@ err: bch2_path_put(trans, new_path, true); bch2_path_put(trans, sib_path, true); bch2_trans_verify_locks(trans); + if (ret == -BCH_ERR_journal_reclaim_would_deadlock) + ret = 0; + if (!ret) + ret = bch2_trans_relock(trans); return ret; err_free_update: bch2_btree_node_free_never_used(as, trans, n); @@ -2116,12 +2160,13 @@ int bch2_btree_node_rewrite(struct btree_trans *trans, if (parent) { bch2_keylist_add(&as->parent_keys, &n->key); ret = bch2_btree_insert_node(as, trans, iter->path, parent, &as->parent_keys); - if (ret) - goto err; } else { - bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n); + ret = bch2_btree_set_root(as, trans, btree_iter_path(trans, iter), n, false); } + if (ret) + goto err; + bch2_btree_update_get_open_buckets(as, n); bch2_btree_node_write(c, n, SIX_LOCK_intent, 0); @@ -2519,9 +2564,11 @@ void bch2_btree_root_alloc_fake(struct bch_fs *c, enum btree_id id, unsigned lev static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as) { - prt_printf(out, "%ps: btree=%s watermark=%s mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", + prt_printf(out, "%ps: btree=%s l=%u-%u watermark=%s mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n", (void *) as->ip_started, bch2_btree_id_str(as->btree_id), + as->update_level_start, + as->update_level_end, bch2_watermarks[as->watermark], bch2_btree_update_modes[as->mode], as->nodes_written, diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index 88dcf5a22a3b..c1a479ebaad1 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -57,7 +57,8 @@ struct btree_update { unsigned took_gc_lock:1; enum btree_id btree_id; - unsigned update_level; + unsigned update_level_start; + unsigned update_level_end; struct disk_reservation disk_res; diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c index baf63e2fddb6..36a6f42aba5e 100644 --- a/fs/bcachefs/btree_write_buffer.c +++ b/fs/bcachefs/btree_write_buffer.c @@ -316,6 +316,16 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) bpos_gt(k->k.k.p, path->l[0].b->key.k.p)) { bch2_btree_node_unlock_write(trans, path, path->l[0].b); write_locked = false; + + ret = lockrestart_do(trans, + bch2_btree_iter_traverse(&iter) ?: + bch2_foreground_maybe_merge(trans, iter.path, 0, + BCH_WATERMARK_reclaim| + BCH_TRANS_COMMIT_journal_reclaim| + BCH_TRANS_COMMIT_no_check_rw| + BCH_TRANS_COMMIT_no_enospc)); + if (ret) + goto err; } } @@ -382,10 +392,10 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans) ret = commit_do(trans, NULL, NULL, BCH_WATERMARK_reclaim| + BCH_TRANS_COMMIT_journal_reclaim| BCH_TRANS_COMMIT_no_check_rw| BCH_TRANS_COMMIT_no_enospc| - BCH_TRANS_COMMIT_no_journal_res| - BCH_TRANS_COMMIT_journal_reclaim, + BCH_TRANS_COMMIT_no_journal_res , btree_write_buffered_insert(trans, i)); if (ret) goto err; diff --git a/fs/bcachefs/buckets.h b/fs/bcachefs/buckets.h index 00aaf4bb5139..f9af5adabe83 100644 --- a/fs/bcachefs/buckets.h +++ b/fs/bcachefs/buckets.h @@ -395,14 +395,6 @@ static inline const char *bch2_data_type_str(enum bch_data_type type) : "(invalid data type)"; } -static inline void bch2_prt_data_type(struct printbuf *out, enum bch_data_type type) -{ - if (type < BCH_DATA_NR) - prt_str(out, __bch2_data_types[type]); - else - prt_printf(out, "(invalid data type %u)", type); -} - /* disk reservations: */ static inline void bch2_disk_reservation_put(struct bch_fs *c, diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index cbfa6459bdbc..4d14f19f5185 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -134,42 +134,38 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg struct fsck_thread { struct thread_with_stdio thr; struct bch_fs *c; - char **devs; - size_t nr_devs; struct bch_opts opts; }; static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr) { struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr); - if (thr->devs) - for (size_t i = 0; i < thr->nr_devs; i++) - kfree(thr->devs[i]); - kfree(thr->devs); kfree(thr); } static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio) { struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); - struct bch_fs *c = bch2_fs_open(thr->devs, thr->nr_devs, thr->opts); - - if (IS_ERR(c)) - return PTR_ERR(c); + struct bch_fs *c = thr->c; - int ret = 0; - if (test_bit(BCH_FS_errors_fixed, &c->flags)) - ret |= 1; - if (test_bit(BCH_FS_error, &c->flags)) - ret |= 4; + int ret = PTR_ERR_OR_ZERO(c); + if (ret) + return ret; - bch2_fs_stop(c); + ret = bch2_fs_start(thr->c); + if (ret) + goto err; - if (ret & 1) + if (test_bit(BCH_FS_errors_fixed, &c->flags)) { bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name); - if (ret & 4) + ret |= 1; + } + if (test_bit(BCH_FS_error, &c->flags)) { bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name); - + ret |= 4; + } +err: + bch2_fs_stop(c); return ret; } @@ -182,7 +178,7 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a { struct bch_ioctl_fsck_offline arg; struct fsck_thread *thr = NULL; - u64 *devs = NULL; + darray_str(devs) = {}; long ret = 0; if (copy_from_user(&arg, user_arg, sizeof(arg))) @@ -194,29 +190,32 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!(devs = kcalloc(arg.nr_devs, sizeof(*devs), GFP_KERNEL)) || - !(thr = kzalloc(sizeof(*thr), GFP_KERNEL)) || - !(thr->devs = kcalloc(arg.nr_devs, sizeof(*thr->devs), GFP_KERNEL))) { - ret = -ENOMEM; - goto err; - } + for (size_t i = 0; i < arg.nr_devs; i++) { + u64 dev_u64; + ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64)); + if (ret) + goto err; - thr->opts = bch2_opts_empty(); - thr->nr_devs = arg.nr_devs; + char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX); + ret = PTR_ERR_OR_ZERO(dev_str); + if (ret) + goto err; - if (copy_from_user(devs, &user_arg->devs[0], - array_size(sizeof(user_arg->devs[0]), arg.nr_devs))) { - ret = -EINVAL; - goto err; + ret = darray_push(&devs, dev_str); + if (ret) { + kfree(dev_str); + goto err; + } } - for (size_t i = 0; i < arg.nr_devs; i++) { - thr->devs[i] = strndup_user((char __user *)(unsigned long) devs[i], PATH_MAX); - ret = PTR_ERR_OR_ZERO(thr->devs[i]); - if (ret) - goto err; + thr = kzalloc(sizeof(*thr), GFP_KERNEL); + if (!thr) { + ret = -ENOMEM; + goto err; } + thr->opts = bch2_opts_empty(); + if (arg.opts) { char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); @@ -230,15 +229,28 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio); - ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_offline_fsck_ops); -err: - if (ret < 0) { - if (thr) - bch2_fsck_thread_exit(&thr->thr); - pr_err("ret %s", bch2_err_str(ret)); - } - kfree(devs); + /* We need request_key() to be called before we punt to kthread: */ + opt_set(thr->opts, nostart, true); + + bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops); + + thr->c = bch2_fs_open(devs.data, arg.nr_devs, thr->opts); + + if (!IS_ERR(thr->c) && + thr->c->opts.errors == BCH_ON_ERROR_panic) + thr->c->opts.errors = BCH_ON_ERROR_ro; + + ret = __bch2_run_thread_with_stdio(&thr->thr); +out: + darray_for_each(devs, i) + kfree(*i); + darray_exit(&devs); return ret; +err: + if (thr) + bch2_fsck_thread_exit(&thr->thr); + pr_err("ret %s", bch2_err_str(ret)); + goto out; } static long bch2_global_ioctl(unsigned cmd, void __user *arg) diff --git a/fs/bcachefs/checksum.c b/fs/bcachefs/checksum.c index 4701457f6381..7ed779b411f6 100644 --- a/fs/bcachefs/checksum.c +++ b/fs/bcachefs/checksum.c @@ -429,15 +429,20 @@ int bch2_rechecksum_bio(struct bch_fs *c, struct bio *bio, extent_nonce(version, crc_old), bio); if (bch2_crc_cmp(merged, crc_old.csum) && !c->opts.no_data_io) { - bch_err(c, "checksum error in %s() (memory corruption or bug?)\n" - "expected %0llx:%0llx got %0llx:%0llx (old type %s new type %s)", - __func__, - crc_old.csum.hi, - crc_old.csum.lo, - merged.hi, - merged.lo, - bch2_csum_types[crc_old.csum_type], - bch2_csum_types[new_csum_type]); + struct printbuf buf = PRINTBUF; + prt_printf(&buf, "checksum error in %s() (memory corruption or bug?)\n" + "expected %0llx:%0llx got %0llx:%0llx (old type ", + __func__, + crc_old.csum.hi, + crc_old.csum.lo, + merged.hi, + merged.lo); + bch2_prt_csum_type(&buf, crc_old.csum_type); + prt_str(&buf, " new type "); + bch2_prt_csum_type(&buf, new_csum_type); + prt_str(&buf, ")"); + bch_err(c, "%s", buf.buf); + printbuf_exit(&buf); return -EIO; } diff --git a/fs/bcachefs/checksum.h b/fs/bcachefs/checksum.h index 1b8c2c1016dc..e40499fde9a4 100644 --- a/fs/bcachefs/checksum.h +++ b/fs/bcachefs/checksum.h @@ -61,11 +61,12 @@ static inline void bch2_csum_err_msg(struct printbuf *out, struct bch_csum expected, struct bch_csum got) { - prt_printf(out, "checksum error: got "); + prt_str(out, "checksum error, type "); + bch2_prt_csum_type(out, type); + prt_str(out, ": got "); bch2_csum_to_text(out, type, got); prt_str(out, " should be "); bch2_csum_to_text(out, type, expected); - prt_printf(out, " type %s", bch2_csum_types[type]); } int bch2_chacha_encrypt_key(struct bch_key *, struct nonce, void *, size_t); diff --git a/fs/bcachefs/compress.h b/fs/bcachefs/compress.h index 58c2eb45570f..607fd5e232c9 100644 --- a/fs/bcachefs/compress.h +++ b/fs/bcachefs/compress.h @@ -47,14 +47,6 @@ static inline enum bch_compression_type bch2_compression_opt_to_type(unsigned v) return __bch2_compression_opt_to_type[bch2_compression_decode(v).type]; } -static inline void bch2_prt_compression_type(struct printbuf *out, enum bch_compression_type type) -{ - if (type < BCH_COMPRESSION_TYPE_NR) - prt_str(out, __bch2_compression_types[type]); - else - prt_printf(out, "(invalid compression type %u)", type); -} - int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *, struct bch_extent_crc_unpacked *); int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *, diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 34731ee0217f..0022b51ce3c0 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -598,6 +598,8 @@ int bch2_data_update_init(struct btree_trans *trans, i++; } + unsigned durability_required = max(0, (int) (io_opts.data_replicas - durability_have)); + /* * If current extent durability is less than io_opts.data_replicas, * we're not trying to rereplicate the extent up to data_replicas here - @@ -607,7 +609,7 @@ int bch2_data_update_init(struct btree_trans *trans, * rereplicate, currently, so that users don't get an unexpected -ENOSPC */ if (!(m->data_opts.write_flags & BCH_WRITE_CACHED) && - durability_have >= io_opts.data_replicas) { + !durability_required) { m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs; m->data_opts.rewrite_ptrs = 0; /* if iter == NULL, it's just a promote */ @@ -616,11 +618,18 @@ int bch2_data_update_init(struct btree_trans *trans, goto done; } - m->op.nr_replicas = min(durability_removing, io_opts.data_replicas - durability_have) + + m->op.nr_replicas = min(durability_removing, durability_required) + m->data_opts.extra_replicas; - m->op.nr_replicas_required = m->op.nr_replicas; - BUG_ON(!m->op.nr_replicas); + /* + * If device(s) were set to durability=0 after data was written to them + * we can end up with a duribilty=0 extent, and the normal algorithm + * that tries not to increase durability doesn't work: + */ + if (!(durability_have + durability_removing)) + m->op.nr_replicas = max((unsigned) m->op.nr_replicas, 1); + + m->op.nr_replicas_required = m->op.nr_replicas; if (reserve_sectors) { ret = bch2_disk_reservation_add(c, &m->op.res, reserve_sectors, diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c index 208ce6f0fc43..cd99b7399414 100644 --- a/fs/bcachefs/debug.c +++ b/fs/bcachefs/debug.c @@ -13,6 +13,7 @@ #include "btree_iter.h" #include "btree_locking.h" #include "btree_update.h" +#include "btree_update_interior.h" #include "buckets.h" #include "debug.h" #include "error.h" @@ -668,7 +669,7 @@ static ssize_t bch2_journal_pins_read(struct file *file, char __user *buf, i->size = size; i->ret = 0; - do { + while (1) { err = flush_buf(i); if (err) return err; @@ -676,9 +677,12 @@ static ssize_t bch2_journal_pins_read(struct file *file, char __user *buf, if (!i->size) break; + if (done) + break; + done = bch2_journal_seq_pins_to_text(&i->buf, &c->journal, &i->iter); i->iter++; - } while (!done); + } if (i->buf.allocation_failure) return -ENOMEM; @@ -693,13 +697,45 @@ static const struct file_operations journal_pins_ops = { .read = bch2_journal_pins_read, }; +static ssize_t bch2_btree_updates_read(struct file *file, char __user *buf, + size_t size, loff_t *ppos) +{ + struct dump_iter *i = file->private_data; + struct bch_fs *c = i->c; + int err; + + i->ubuf = buf; + i->size = size; + i->ret = 0; + + if (!i->iter) { + bch2_btree_updates_to_text(&i->buf, c); + i->iter++; + } + + err = flush_buf(i); + if (err) + return err; + + if (i->buf.allocation_failure) + return -ENOMEM; + + return i->ret; +} + +static const struct file_operations btree_updates_ops = { + .owner = THIS_MODULE, + .open = bch2_dump_open, + .release = bch2_dump_release, + .read = bch2_btree_updates_read, +}; + static int btree_transaction_stats_open(struct inode *inode, struct file *file) { struct bch_fs *c = inode->i_private; struct dump_iter *i; i = kzalloc(sizeof(struct dump_iter), GFP_KERNEL); - if (!i) return -ENOMEM; @@ -866,6 +902,20 @@ void bch2_fs_debug_exit(struct bch_fs *c) debugfs_remove_recursive(c->fs_debug_dir); } +static void bch2_fs_debug_btree_init(struct bch_fs *c, struct btree_debug *bd) +{ + struct dentry *d; + + d = debugfs_create_dir(bch2_btree_id_str(bd->id), c->btree_debug_dir); + + debugfs_create_file("keys", 0400, d, bd, &btree_debug_ops); + + debugfs_create_file("formats", 0400, d, bd, &btree_format_debug_ops); + + debugfs_create_file("bfloat-failed", 0400, d, bd, + &bfloat_failed_debug_ops); +} + void bch2_fs_debug_init(struct bch_fs *c) { struct btree_debug *bd; @@ -888,6 +938,9 @@ void bch2_fs_debug_init(struct bch_fs *c) debugfs_create_file("journal_pins", 0400, c->fs_debug_dir, c->btree_debug, &journal_pins_ops); + debugfs_create_file("btree_updates", 0400, c->fs_debug_dir, + c->btree_debug, &btree_updates_ops); + debugfs_create_file("btree_transaction_stats", 0400, c->fs_debug_dir, c, &btree_transaction_stats_op); @@ -902,21 +955,7 @@ void bch2_fs_debug_init(struct bch_fs *c) bd < c->btree_debug + ARRAY_SIZE(c->btree_debug); bd++) { bd->id = bd - c->btree_debug; - debugfs_create_file(bch2_btree_id_str(bd->id), - 0400, c->btree_debug_dir, bd, - &btree_debug_ops); - - snprintf(name, sizeof(name), "%s-formats", - bch2_btree_id_str(bd->id)); - - debugfs_create_file(name, 0400, c->btree_debug_dir, bd, - &btree_format_debug_ops); - - snprintf(name, sizeof(name), "%s-bfloat-failed", - bch2_btree_id_str(bd->id)); - - debugfs_create_file(name, 0400, c->btree_debug_dir, bd, - &bfloat_failed_debug_ops); + bch2_fs_debug_btree_init(c, bd); } } diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index 082075244e16..556a217108d3 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -131,29 +131,33 @@ fsck_err: void bch2_stripe_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c k) { - const struct bch_stripe *s = bkey_s_c_to_stripe(k).v; - unsigned i, nr_data = s->nr_blocks - s->nr_redundant; + const struct bch_stripe *sp = bkey_s_c_to_stripe(k).v; + struct bch_stripe s = {}; + + memcpy(&s, sp, min(sizeof(s), bkey_val_bytes(k.k))); + + unsigned nr_data = s.nr_blocks - s.nr_redundant; + + prt_printf(out, "algo %u sectors %u blocks %u:%u csum ", + s.algorithm, + le16_to_cpu(s.sectors), + nr_data, + s.nr_redundant); + bch2_prt_csum_type(out, s.csum_type); + prt_printf(out, " gran %u", 1U << s.csum_granularity_bits); + + for (unsigned i = 0; i < s.nr_blocks; i++) { + const struct bch_extent_ptr *ptr = sp->ptrs + i; + + if ((void *) ptr >= bkey_val_end(k)) + break; + + bch2_extent_ptr_to_text(out, c, ptr); - prt_printf(out, "algo %u sectors %u blocks %u:%u csum %u gran %u", - s->algorithm, - le16_to_cpu(s->sectors), - nr_data, - s->nr_redundant, - s->csum_type, - 1U << s->csum_granularity_bits); - - for (i = 0; i < s->nr_blocks; i++) { - const struct bch_extent_ptr *ptr = s->ptrs + i; - struct bch_dev *ca = bch_dev_bkey_exists(c, ptr->dev); - u32 offset; - u64 b = sector_to_bucket_and_offset(ca, ptr->offset, &offset); - - prt_printf(out, " %u:%llu:%u", ptr->dev, b, offset); - if (i < nr_data) - prt_printf(out, "#%u", stripe_blockcount_get(s, i)); - prt_printf(out, " gen %u", ptr->gen); - if (ptr_stale(ca, ptr)) - prt_printf(out, " stale"); + if (s.csum_type < BCH_CSUM_NR && + i < nr_data && + stripe_blockcount_offset(&s, i) < bkey_val_bytes(k.k)) + prt_printf(out, "#%u", stripe_blockcount_get(sp, i)); } } @@ -607,10 +611,8 @@ static void ec_validate_checksums(struct bch_fs *c, struct ec_stripe_buf *buf) struct printbuf err = PRINTBUF; struct bch_dev *ca = bch_dev_bkey_exists(c, v->ptrs[i].dev); - prt_printf(&err, "stripe checksum error: expected %0llx:%0llx got %0llx:%0llx (type %s)\n", - want.hi, want.lo, - got.hi, got.lo, - bch2_csum_types[v->csum_type]); + prt_str(&err, "stripe "); + bch2_csum_err_msg(&err, v->csum_type, want, got); prt_printf(&err, " for %ps at %u of\n ", (void *) _RET_IP_, i); bch2_bkey_val_to_text(&err, c, bkey_i_to_s_c(&buf->key)); bch_err_ratelimited(ca, "%s", err.buf); diff --git a/fs/bcachefs/ec.h b/fs/bcachefs/ec.h index f4369b02e805..f042616888b0 100644 --- a/fs/bcachefs/ec.h +++ b/fs/bcachefs/ec.h @@ -32,6 +32,8 @@ static inline unsigned stripe_csums_per_device(const struct bch_stripe *s) static inline unsigned stripe_csum_offset(const struct bch_stripe *s, unsigned dev, unsigned csum_idx) { + EBUG_ON(s->csum_type >= BCH_CSUM_NR); + unsigned csum_bytes = bch_crc_bytes[s->csum_type]; return sizeof(struct bch_stripe) + diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 0e3ca99fbd2d..1a331e539204 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -998,7 +998,9 @@ void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *c, const struc prt_str(out, " cached"); if (ptr->unwritten) prt_str(out, " unwritten"); - if (ca && ptr_stale(ca, ptr)) + if (b >= ca->mi.first_bucket && + b < ca->mi.nbuckets && + ptr_stale(ca, ptr)) prt_printf(out, " stale"); } } @@ -1028,11 +1030,12 @@ void bch2_bkey_ptrs_to_text(struct printbuf *out, struct bch_fs *c, struct bch_extent_crc_unpacked crc = bch2_extent_crc_unpack(k.k, entry_to_crc(entry)); - prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum %s compress ", + prt_printf(out, "crc: c_size %u size %u offset %u nonce %u csum ", crc.compressed_size, crc.uncompressed_size, - crc.offset, crc.nonce, - bch2_csum_types[crc.csum_type]); + crc.offset, crc.nonce); + bch2_prt_csum_type(out, crc.csum_type); + prt_str(out, " compress "); bch2_prt_compression_type(out, crc.compression_type); break; } diff --git a/fs/bcachefs/eytzinger.c b/fs/bcachefs/eytzinger.c index 4ce5e957a6e9..0f955c3c76a7 100644 --- a/fs/bcachefs/eytzinger.c +++ b/fs/bcachefs/eytzinger.c @@ -115,7 +115,7 @@ static void swap_bytes(void *a, void *b, size_t n) struct wrapper { cmp_func_t cmp; - swap_func_t swap; + swap_func_t swap_func; }; /* @@ -125,7 +125,7 @@ struct wrapper { static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv) { if (swap_func == SWAP_WRAPPER) { - ((const struct wrapper *)priv)->swap(a, b, (int)size); + ((const struct wrapper *)priv)->swap_func(a, b, (int)size); return; } @@ -174,7 +174,7 @@ void eytzinger0_sort_r(void *base, size_t n, size_t size, int i, c, r; /* called from 'sort' without swap function, let's pick the default */ - if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap) + if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap_func) swap_func = NULL; if (!swap_func) { @@ -227,7 +227,7 @@ void eytzinger0_sort(void *base, size_t n, size_t size, { struct wrapper w = { .cmp = cmp_func, - .swap = swap_func, + .swap_func = swap_func, }; return eytzinger0_sort_r(base, n, size, _CMP_WRAPPER, SWAP_WRAPPER, &w); diff --git a/fs/bcachefs/eytzinger.h b/fs/bcachefs/eytzinger.h index ee0e2df33322..24840aee335c 100644 --- a/fs/bcachefs/eytzinger.h +++ b/fs/bcachefs/eytzinger.h @@ -242,8 +242,8 @@ static inline unsigned inorder_to_eytzinger0(unsigned i, unsigned size) (_i) = eytzinger0_next((_i), (_size))) /* return greatest node <= @search, or -1 if not found */ -static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size, - cmp_func_t cmp, const void *search) +static inline int eytzinger0_find_le(void *base, size_t nr, size_t size, + cmp_func_t cmp, const void *search) { unsigned i, n = 0; @@ -256,18 +256,32 @@ static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size, } while (n < nr); if (n & 1) { - /* @i was greater than @search, return previous node: */ + /* + * @i was greater than @search, return previous node: + * + * if @i was leftmost/smallest element, + * eytzinger0_prev(eytzinger0_first())) returns -1, as expected + */ return eytzinger0_prev(i, nr); } else { return i; } } -static inline ssize_t eytzinger0_find_gt(void *base, size_t nr, size_t size, - cmp_func_t cmp, const void *search) +static inline int eytzinger0_find_gt(void *base, size_t nr, size_t size, + cmp_func_t cmp, const void *search) { ssize_t idx = eytzinger0_find_le(base, nr, size, cmp, search); - return eytzinger0_next(idx, size); + + /* + * if eytitzinger0_find_le() returned -1 - no element was <= search - we + * want to return the first element; next/prev identities mean this work + * as expected + * + * similarly if find_le() returns last element, we should return -1; + * identities mean this all works out: + */ + return eytzinger0_next(idx, nr); } #define eytzinger0_find(base, nr, size, _cmp, search) \ diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c index f49e6c0f0f68..b889370a5088 100644 --- a/fs/bcachefs/fs-io-direct.c +++ b/fs/bcachefs/fs-io-direct.c @@ -387,6 +387,8 @@ static __always_inline long bch2_dio_write_done(struct dio_write *dio) ret = dio->op.error ?: ((long) dio->written << 9); bio_put(&dio->op.wbio.bio); + bch2_write_ref_put(dio->op.c, BCH_WRITE_REF_dio_write); + /* inode->i_dio_count is our ref on inode and thus bch_fs */ inode_dio_end(&inode->v); @@ -590,22 +592,25 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter) prefetch(&inode->ei_inode); prefetch((void *) &inode->ei_inode + 64); + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_dio_write)) + return -EROFS; + inode_lock(&inode->v); ret = generic_write_checks(req, iter); if (unlikely(ret <= 0)) - goto err; + goto err_put_write_ref; ret = file_remove_privs(file); if (unlikely(ret)) - goto err; + goto err_put_write_ref; ret = file_update_time(file); if (unlikely(ret)) - goto err; + goto err_put_write_ref; if (unlikely((req->ki_pos|iter->count) & (block_bytes(c) - 1))) - goto err; + goto err_put_write_ref; inode_dio_begin(&inode->v); bch2_pagecache_block_get(inode); @@ -645,7 +650,7 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter) } ret = bch2_dio_write_loop(dio); -err: +out: if (locked) inode_unlock(&inode->v); return ret; @@ -653,7 +658,9 @@ err_put_bio: bch2_pagecache_block_put(inode); bio_put(bio); inode_dio_end(&inode->v); - goto err; +err_put_write_ref: + bch2_write_ref_put(c, BCH_WRITE_REF_dio_write); + goto out; } void bch2_fs_fs_io_direct_exit(struct bch_fs *c) diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c index 8c70123b6a0c..20b40477425f 100644 --- a/fs/bcachefs/fs-io.c +++ b/fs/bcachefs/fs-io.c @@ -174,18 +174,18 @@ void __bch2_i_sectors_acct(struct bch_fs *c, struct bch_inode_info *inode, static int bch2_flush_inode(struct bch_fs *c, struct bch_inode_info *inode) { - struct bch_inode_unpacked u; - int ret; - if (c->opts.journal_flush_disabled) return 0; - ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u); - if (ret) - return ret; + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_fsync)) + return -EROFS; - return bch2_journal_flush_seq(&c->journal, u.bi_journal_seq) ?: - bch2_inode_flush_nocow_writes(c, inode); + struct bch_inode_unpacked u; + int ret = bch2_inode_find_by_inum(c, inode_inum(inode), &u) ?: + bch2_journal_flush_seq(&c->journal, u.bi_journal_seq) ?: + bch2_inode_flush_nocow_writes(c, inode); + bch2_write_ref_put(c, BCH_WRITE_REF_fsync); + return ret; } int bch2_fsync(struct file *file, loff_t start, loff_t end, int datasync) diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index b5ea9fa1259d..fce690007edf 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/journal_io.c b/fs/bcachefs/journal_io.c index 725fcf46f631..eb1f9d6f5a19 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -247,7 +247,7 @@ static void journal_entry_err_msg(struct printbuf *out, if (entry) { prt_str(out, " type="); - prt_str(out, bch2_jset_entry_types[entry->type]); + bch2_prt_jset_entry_type(out, entry->type); } if (!jset) { @@ -403,7 +403,8 @@ static void journal_entry_btree_keys_to_text(struct printbuf *out, struct bch_fs jset_entry_for_each_key(entry, k) { if (!first) { prt_newline(out); - prt_printf(out, "%s: ", bch2_jset_entry_types[entry->type]); + bch2_prt_jset_entry_type(out, entry->type); + prt_str(out, ": "); } prt_printf(out, "btree=%s l=%u ", bch2_btree_id_str(entry->btree_id), entry->level); bch2_bkey_val_to_text(out, c, bkey_i_to_s_c(k)); @@ -563,9 +564,9 @@ static void journal_entry_usage_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry_usage *u = container_of(entry, struct jset_entry_usage, entry); - prt_printf(out, "type=%s v=%llu", - bch2_fs_usage_types[u->entry.btree_id], - le64_to_cpu(u->v)); + prt_str(out, "type="); + bch2_prt_fs_usage_type(out, u->entry.btree_id); + prt_printf(out, " v=%llu", le64_to_cpu(u->v)); } static int journal_entry_data_usage_validate(struct bch_fs *c, @@ -827,11 +828,11 @@ int bch2_journal_entry_validate(struct bch_fs *c, void bch2_journal_entry_to_text(struct printbuf *out, struct bch_fs *c, struct jset_entry *entry) { + bch2_prt_jset_entry_type(out, entry->type); + if (entry->type < BCH_JSET_ENTRY_NR) { - prt_printf(out, "%s: ", bch2_jset_entry_types[entry->type]); + prt_str(out, ": "); bch2_jset_entry_ops[entry->type].to_text(out, c, entry); - } else { - prt_printf(out, "(unknown type %u)", entry->type); } } @@ -1722,7 +1723,7 @@ 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]); @@ -1767,6 +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); @@ -2032,23 +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/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index ab811c0dad26..04a577848b01 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -67,6 +67,8 @@ void bch2_journal_set_watermark(struct journal *j) track_event_change(&c->times[BCH_TIME_blocked_write_buffer_full], low_on_wb)) trace_and_count(c, journal_full, c); + mod_bit(JOURNAL_SPACE_LOW, &j->flags, low_on_space || low_on_pin); + swap(watermark, j->watermark); if (watermark > j->watermark) journal_wake(j); diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h index 8c053cb64ca5..b5161b5d76a0 100644 --- a/fs/bcachefs/journal_types.h +++ b/fs/bcachefs/journal_types.h @@ -134,6 +134,7 @@ enum journal_flags { JOURNAL_STARTED, JOURNAL_MAY_SKIP_FLUSH, JOURNAL_NEED_FLUSH_WRITE, + JOURNAL_SPACE_LOW, }; /* Reasons we may fail to get a journal reservation: */ diff --git a/fs/bcachefs/opts.c b/fs/bcachefs/opts.c index e1800c4119b5..bb068fd72465 100644 --- a/fs/bcachefs/opts.c +++ b/fs/bcachefs/opts.c @@ -43,7 +43,7 @@ const char * const __bch2_btree_ids[] = { NULL }; -const char * const bch2_csum_types[] = { +static const char * const __bch2_csum_types[] = { BCH_CSUM_TYPES() NULL }; @@ -53,7 +53,7 @@ const char * const bch2_csum_opts[] = { NULL }; -const char * const __bch2_compression_types[] = { +static const char * const __bch2_compression_types[] = { BCH_COMPRESSION_TYPES() NULL }; @@ -83,18 +83,39 @@ const char * const bch2_member_states[] = { NULL }; -const char * const bch2_jset_entry_types[] = { +static const char * const __bch2_jset_entry_types[] = { BCH_JSET_ENTRY_TYPES() NULL }; -const char * const bch2_fs_usage_types[] = { +static const char * const __bch2_fs_usage_types[] = { BCH_FS_USAGE_TYPES() NULL }; #undef x +static void prt_str_opt_boundscheck(struct printbuf *out, const char * const opts[], + unsigned nr, const char *type, unsigned idx) +{ + if (idx < nr) + prt_str(out, opts[idx]); + else + prt_printf(out, "(unknown %s %u)", type, idx); +} + +#define PRT_STR_OPT_BOUNDSCHECKED(name, type) \ +void bch2_prt_##name(struct printbuf *out, type t) \ +{ \ + prt_str_opt_boundscheck(out, __bch2_##name##s, ARRAY_SIZE(__bch2_##name##s) - 1, #name, t);\ +} + +PRT_STR_OPT_BOUNDSCHECKED(jset_entry_type, enum bch_jset_entry_type); +PRT_STR_OPT_BOUNDSCHECKED(fs_usage_type, enum bch_fs_usage_type); +PRT_STR_OPT_BOUNDSCHECKED(data_type, enum bch_data_type); +PRT_STR_OPT_BOUNDSCHECKED(csum_type, enum bch_csum_type); +PRT_STR_OPT_BOUNDSCHECKED(compression_type, enum bch_compression_type); + static int bch2_opt_fix_errors_parse(struct bch_fs *c, const char *val, u64 *res, struct printbuf *err) { diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index 1ac4135cca1c..84e452835a17 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -16,18 +16,20 @@ extern const char * const bch2_version_upgrade_opts[]; extern const char * const bch2_sb_features[]; extern const char * const bch2_sb_compat[]; extern const char * const __bch2_btree_ids[]; -extern const char * const bch2_csum_types[]; extern const char * const bch2_csum_opts[]; -extern const char * const __bch2_compression_types[]; extern const char * const bch2_compression_opts[]; extern const char * const bch2_str_hash_types[]; extern const char * const bch2_str_hash_opts[]; extern const char * const __bch2_data_types[]; extern const char * const bch2_member_states[]; -extern const char * const bch2_jset_entry_types[]; -extern const char * const bch2_fs_usage_types[]; extern const char * const bch2_d_types[]; +void bch2_prt_jset_entry_type(struct printbuf *, enum bch_jset_entry_type); +void bch2_prt_fs_usage_type(struct printbuf *, enum bch_fs_usage_type); +void bch2_prt_data_type(struct printbuf *, enum bch_data_type); +void bch2_prt_csum_type(struct printbuf *, enum bch_csum_type); +void bch2_prt_compression_type(struct printbuf *, enum bch_compression_type); + static inline const char *bch2_d_type_str(unsigned d_type) { return (d_type < BCH_DT_MAX ? bch2_d_types[d_type] : NULL) ?: "(bad d_type)"; diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index b76c16152579..be5b47619327 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -47,20 +47,6 @@ void bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree) } } -static bool btree_id_is_alloc(enum btree_id id) -{ - switch (id) { - case BTREE_ID_alloc: - case BTREE_ID_backpointers: - case BTREE_ID_need_discard: - case BTREE_ID_freespace: - case BTREE_ID_bucket_gens: - return true; - default: - return false; - } -} - /* for -o reconstruct_alloc: */ static void bch2_reconstruct_alloc(struct bch_fs *c) { @@ -263,7 +249,10 @@ 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/recovery_passes.c b/fs/bcachefs/recovery_passes.c index cb501460d615..0cec0f7d9703 100644 --- a/fs/bcachefs/recovery_passes.c +++ b/fs/bcachefs/recovery_passes.c @@ -44,7 +44,7 @@ static int bch2_set_may_go_rw(struct bch_fs *c) set_bit(BCH_FS_may_go_rw, &c->flags); - if (keys->nr || c->opts.fsck || !c->sb.clean) + if (keys->nr || c->opts.fsck || !c->sb.clean || c->recovery_passes_explicit) return bch2_fs_read_write_early(c); return 0; } diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c index 5980ba2563fe..35ca3f138de6 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-downgrade.c b/fs/bcachefs/sb-downgrade.c index d6f81179c3a2..a98ef940b7a3 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -51,7 +51,10 @@ BCH_FSCK_ERR_subvol_fs_path_parent_wrong) \ x(btree_subvolume_children, \ BIT_ULL(BCH_RECOVERY_PASS_check_subvols), \ - BCH_FSCK_ERR_subvol_children_not_set) + BCH_FSCK_ERR_subvol_children_not_set) \ + x(mi_btree_bitmap, \ + BIT_ULL(BCH_RECOVERY_PASS_check_allocations), \ + BCH_FSCK_ERR_btree_bitmap_not_marked) #define DOWNGRADE_TABLE() diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h index d7d609131030..06c7a644f4a4 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -130,7 +130,7 @@ x(bucket_gens_nonzero_for_invalid_buckets, 122) \ x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ x(need_discard_freespace_key_bad, 124) \ - x(backpointer_pos_wrong, 125) \ + x(backpointer_bucket_offset_wrong, 125) \ x(backpointer_to_missing_device, 126) \ x(backpointer_to_missing_alloc, 127) \ x(backpointer_to_missing_ptr, 128) \ @@ -270,7 +270,9 @@ x(btree_ptr_v2_min_key_bad, 262) \ x(btree_root_unreadable_and_scan_found_nothing, 263) \ x(snapshot_node_missing, 264) \ - x(dup_backpointer_to_bad_csum_extent, 265) + x(dup_backpointer_to_bad_csum_extent, 265) \ + x(btree_bitmap_not_marked, 266) \ + x(sb_clean_entry_overrun, 267) enum bch_sb_error_id { #define x(t, n) BCH_FSCK_ERR_##t = n, diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c index eff5ce18c69c..5b8e621ac5eb 100644 --- a/fs/bcachefs/sb-members.c +++ b/fs/bcachefs/sb-members.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" +#include "btree_cache.h" #include "disk_groups.h" #include "opts.h" #include "replicas.h" @@ -426,3 +427,55 @@ void bch2_dev_errors_reset(struct bch_dev *ca) bch2_write_super(c); mutex_unlock(&c->sb_lock); } + +/* + * Per member "range has btree nodes" bitmap: + * + * This is so that if we ever have to run the btree node scan to repair we don't + * have to scan full devices: + */ + +bool bch2_dev_btree_bitmap_marked(struct bch_fs *c, struct bkey_s_c k) +{ + bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) + if (!bch2_dev_btree_bitmap_marked_sectors(bch_dev_bkey_exists(c, ptr->dev), + ptr->offset, btree_sectors(c))) + return false; + return true; +} + +static void __bch2_dev_btree_bitmap_mark(struct bch_sb_field_members_v2 *mi, unsigned dev, + u64 start, unsigned sectors) +{ + struct bch_member *m = __bch2_members_v2_get_mut(mi, dev); + u64 bitmap = le64_to_cpu(m->btree_allocated_bitmap); + + u64 end = start + sectors; + + int resize = ilog2(roundup_pow_of_two(end)) - (m->btree_bitmap_shift + 6); + if (resize > 0) { + u64 new_bitmap = 0; + + for (unsigned i = 0; i < 64; i++) + if (bitmap & BIT_ULL(i)) + new_bitmap |= BIT_ULL(i >> resize); + bitmap = new_bitmap; + m->btree_bitmap_shift += resize; + } + + for (unsigned bit = start >> m->btree_bitmap_shift; + (u64) bit << m->btree_bitmap_shift < end; + bit++) + bitmap |= BIT_ULL(bit); + + m->btree_allocated_bitmap = cpu_to_le64(bitmap); +} + +void bch2_dev_btree_bitmap_mark(struct bch_fs *c, struct bkey_s_c k) +{ + lockdep_assert_held(&c->sb_lock); + + struct bch_sb_field_members_v2 *mi = bch2_sb_field_get(c->disk_sb.sb, members_v2); + bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) + __bch2_dev_btree_bitmap_mark(mi, ptr->dev, ptr->offset, btree_sectors(c)); +} diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h index be0a94183271..5efa64eca5f8 100644 --- a/fs/bcachefs/sb-members.h +++ b/fs/bcachefs/sb-members.h @@ -3,6 +3,7 @@ #define _BCACHEFS_SB_MEMBERS_H #include "darray.h" +#include "bkey_types.h" extern char * const bch2_member_error_strs[]; @@ -220,6 +221,8 @@ static inline struct bch_member_cpu bch2_mi_to_cpu(struct bch_member *mi) : 1, .freespace_initialized = BCH_MEMBER_FREESPACE_INITIALIZED(mi), .valid = bch2_member_exists(mi), + .btree_bitmap_shift = mi->btree_bitmap_shift, + .btree_allocated_bitmap = le64_to_cpu(mi->btree_allocated_bitmap), }; } @@ -228,4 +231,22 @@ void bch2_sb_members_from_cpu(struct bch_fs *); void bch2_dev_io_errors_to_text(struct printbuf *, struct bch_dev *); void bch2_dev_errors_reset(struct bch_dev *); +static inline bool bch2_dev_btree_bitmap_marked_sectors(struct bch_dev *ca, u64 start, unsigned sectors) +{ + u64 end = start + sectors; + + if (end > 64ULL << ca->mi.btree_bitmap_shift) + return false; + + for (unsigned bit = start >> ca->mi.btree_bitmap_shift; + (u64) bit << ca->mi.btree_bitmap_shift < end; + bit++) + if (!(ca->mi.btree_allocated_bitmap & BIT_ULL(bit))) + return false; + return true; +} + +bool bch2_dev_btree_bitmap_marked(struct bch_fs *, struct bkey_s_c); +void bch2_dev_btree_bitmap_mark(struct bch_fs *, struct bkey_s_c); + #endif /* _BCACHEFS_SB_MEMBERS_H */ diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 0e806f04f3d7..544322d5c251 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -125,6 +125,15 @@ static inline u32 get_ancestor_below(struct snapshot_table *t, u32 id, u32 ances return s->parent; } +static bool test_ancestor_bitmap(struct snapshot_table *t, u32 id, u32 ancestor) +{ + const struct snapshot_t *s = __snapshot_t(t, id); + if (!s) + return false; + + return test_bit(ancestor - id - 1, s->is_ancestor); +} + bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor) { bool ret; @@ -140,13 +149,11 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor) while (id && id < ancestor - IS_ANCESTOR_BITMAP) id = get_ancestor_below(t, id, ancestor); - if (id && id < ancestor) { - ret = test_bit(ancestor - id - 1, __snapshot_t(t, id)->is_ancestor); + ret = id && id < ancestor + ? test_ancestor_bitmap(t, id, ancestor) + : id == ancestor; - EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor)); - } else { - ret = id == ancestor; - } + EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor)); out: rcu_read_unlock(); diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index 5eee055ee272..08ea3dbbbe97 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -700,8 +700,11 @@ retry: return -ENOMEM; sb->sb_name = kstrdup(path, GFP_KERNEL); - if (!sb->sb_name) - return -ENOMEM; + if (!sb->sb_name) { + ret = -ENOMEM; + prt_printf(&err, "error allocating memory for sb_name"); + goto err; + } #ifndef __KERNEL__ if (opt_get(*opts, direct_io) == false) diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index ed63018f21be..88e214c609bb 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -288,8 +288,13 @@ static void __bch2_fs_read_only(struct bch_fs *c) if (test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags) && !test_bit(BCH_FS_emergency_ro, &c->flags)) set_bit(BCH_FS_clean_shutdown, &c->flags); + bch2_fs_journal_stop(&c->journal); + bch_info(c, "%sshutdown complete, journal seq %llu", + test_bit(BCH_FS_clean_shutdown, &c->flags) ? "" : "un", + c->journal.seq_ondisk); + /* * After stopping journal: */ @@ -539,6 +544,7 @@ 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/super_types.h b/fs/bcachefs/super_types.h index ec784d975f66..11bcef170c2c 100644 --- a/fs/bcachefs/super_types.h +++ b/fs/bcachefs/super_types.h @@ -37,6 +37,8 @@ struct bch_member_cpu { u8 durability; u8 freespace_initialized; u8 valid; + u8 btree_bitmap_shift; + u64 btree_allocated_bitmap; }; #endif /* _BCACHEFS_SUPER_TYPES_H */ diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c index c86a93a8d8fc..5be92fe3f4ea 100644 --- a/fs/bcachefs/sysfs.c +++ b/fs/bcachefs/sysfs.c @@ -17,7 +17,6 @@ #include "btree_iter.h" #include "btree_key_cache.h" #include "btree_update.h" -#include "btree_update_interior.h" #include "btree_gc.h" #include "buckets.h" #include "clock.h" @@ -26,6 +25,7 @@ #include "ec.h" #include "inode.h" #include "journal.h" +#include "journal_reclaim.h" #include "keylist.h" #include "move.h" #include "movinggc.h" @@ -139,6 +139,7 @@ do { \ write_attribute(trigger_gc); write_attribute(trigger_discards); write_attribute(trigger_invalidates); +write_attribute(trigger_journal_flush); write_attribute(prune_cache); write_attribute(btree_wakeup); rw_attribute(btree_gc_periodic); @@ -166,7 +167,6 @@ read_attribute(btree_write_stats); read_attribute(btree_cache_size); read_attribute(compression_stats); read_attribute(journal_debug); -read_attribute(btree_updates); read_attribute(btree_cache); read_attribute(btree_key_cache); read_attribute(stripes_heap); @@ -415,9 +415,6 @@ SHOW(bch2_fs) if (attr == &sysfs_journal_debug) bch2_journal_debug_to_text(out, &c->journal); - if (attr == &sysfs_btree_updates) - bch2_btree_updates_to_text(out, c); - if (attr == &sysfs_btree_cache) bch2_btree_cache_to_text(out, c); @@ -505,7 +502,7 @@ STORE(bch2_fs) /* Debugging: */ - if (!test_bit(BCH_FS_rw, &c->flags)) + if (!bch2_write_ref_tryget(c, BCH_WRITE_REF_sysfs)) return -EROFS; if (attr == &sysfs_prune_cache) { @@ -538,6 +535,11 @@ STORE(bch2_fs) if (attr == &sysfs_trigger_invalidates) bch2_do_invalidates(c); + if (attr == &sysfs_trigger_journal_flush) { + bch2_journal_flush_all_pins(&c->journal); + bch2_journal_meta(&c->journal); + } + #ifdef CONFIG_BCACHEFS_TESTS if (attr == &sysfs_perf_test) { char *tmp = kstrdup(buf, GFP_KERNEL), *p = tmp; @@ -558,6 +560,7 @@ STORE(bch2_fs) size = ret; } #endif + bch2_write_ref_put(c, BCH_WRITE_REF_sysfs); return size; } SYSFS_OPS(bch2_fs); @@ -639,7 +642,6 @@ SYSFS_OPS(bch2_fs_internal); struct attribute *bch2_fs_internal_files[] = { &sysfs_flags, &sysfs_journal_debug, - &sysfs_btree_updates, &sysfs_btree_cache, &sysfs_btree_key_cache, &sysfs_new_stripes, @@ -657,6 +659,7 @@ struct attribute *bch2_fs_internal_files[] = { &sysfs_trigger_gc, &sysfs_trigger_discards, &sysfs_trigger_invalidates, + &sysfs_trigger_journal_flush, &sysfs_prune_cache, &sysfs_btree_wakeup, diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c index b3fe9fc57747..bfec656f94c0 100644 --- a/fs/bcachefs/tests.c +++ b/fs/bcachefs/tests.c @@ -672,7 +672,7 @@ static int __do_delete(struct btree_trans *trans, struct bpos pos) bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, pos, BTREE_ITER_INTENT); - k = bch2_btree_iter_peek(&iter); + k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX)); ret = bkey_err(k); if (ret) goto err; diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c index 940db15d6a93..b1af7ac430f6 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 af54ea8f5b0f..1d63d14d7dca 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/bcachefs/util.h b/fs/bcachefs/util.h index b7e7c29278fc..5cf885b09986 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -788,6 +788,14 @@ static inline int copy_from_user_errcode(void *to, const void __user *from, unsi #endif +static inline void mod_bit(long nr, volatile unsigned long *addr, bool v) +{ + if (v) + set_bit(nr, addr); + else + clear_bit(nr, addr); +} + static inline void __set_bit_le64(size_t bit, __le64 *addr) { addr[bit / 64] |= cpu_to_le64(BIT_ULL(bit % 64)); @@ -795,7 +803,7 @@ static inline void __set_bit_le64(size_t bit, __le64 *addr) static inline void __clear_bit_le64(size_t bit, __le64 *addr) { - addr[bit / 64] &= !cpu_to_le64(BIT_ULL(bit % 64)); + addr[bit / 64] &= ~cpu_to_le64(BIT_ULL(bit % 64)); } static inline bool test_bit_le64(size_t bit, __le64 *addr) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index c1e6a5bbeeaf..58110c968667 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/delayed-inode.c b/fs/btrfs/delayed-inode.c index dd6f566a383f..121ab890bd05 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1133,6 +1133,9 @@ __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, if (ret) return ret; + ret = btrfs_record_root_in_trans(trans, node->root); + if (ret) + return ret; ret = btrfs_update_delayed_inode(trans, node->root, path, node); return ret; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index beedd6ed64d3..257d044bca91 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3464,6 +3464,14 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (root_id != BTRFS_TREE_LOG_OBJECTID) { struct btrfs_ref generic_ref = { 0 }; + /* + * Assert that the extent buffer is not cleared due to + * EXTENT_BUFFER_ZONED_ZEROOUT. Please refer + * btrfs_clear_buffer_dirty() and btree_csum_one_bio() for + * detail. + */ + ASSERT(btrfs_header_bytenr(buf) != 0); + btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, buf->start, buf->len, parent, btrfs_header_owner(buf)); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 61594eaf1f89..2776112dbdf8 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -681,31 +681,21 @@ static void end_bbio_data_read(struct btrfs_bio *bbio) int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, gfp_t extra_gfp) { + const gfp_t gfp = GFP_NOFS | extra_gfp; unsigned int allocated; for (allocated = 0; allocated < nr_pages;) { unsigned int last = allocated; - allocated = alloc_pages_bulk_array(GFP_NOFS | extra_gfp, - nr_pages, page_array); - - if (allocated == nr_pages) - return 0; - - /* - * During this iteration, no page could be allocated, even - * though alloc_pages_bulk_array() falls back to alloc_page() - * if it could not bulk-allocate. So we must be out of memory. - */ - if (allocated == last) { + allocated = alloc_pages_bulk_array(gfp, nr_pages, page_array); + if (unlikely(allocated == last)) { + /* No progress, fail and do cleanup. */ for (int i = 0; i < allocated; i++) { __free_page(page_array[i]); page_array[i] = NULL; } return -ENOMEM; } - - memalloc_retry_wait(GFP_NOFS); } return 0; } @@ -4154,7 +4144,7 @@ void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans, * The actual zeroout of the buffer will happen later in * btree_csum_one_bio. */ - if (btrfs_is_zoned(fs_info)) { + if (btrfs_is_zoned(fs_info) && test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { set_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags); return; } @@ -4193,6 +4183,7 @@ void set_extent_buffer_dirty(struct extent_buffer *eb) num_folios = num_extent_folios(eb); WARN_ON(atomic_read(&eb->refs) == 0); WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)); + WARN_ON(test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags)); if (!was_dirty) { bool subpage = eb->fs_info->nodesize < PAGE_SIZE; diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 445f7716f1e2..24a048210b15 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 37701531eeb1..7fed887e700c 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 @@ done: out_free_reserve: btrfs_dec_block_group_reservations(fs_info, ins.objectid); btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1); -out_free: mapping_set_error(inode->vfs_inode.i_mapping, -EIO); extent_clear_unlock_delalloc(inode, start, end, NULL, EXTENT_LOCKED | EXTENT_DELALLOC | @@ -2533,7 +2532,7 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode, */ if (bits & EXTENT_CLEAR_META_RESV && root != fs_info->tree_root) - btrfs_delalloc_release_metadata(inode, len, false); + btrfs_delalloc_release_metadata(inode, len, true); /* For sanity tests. */ if (btrfs_is_testing(fs_info)) @@ -4503,6 +4502,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) struct btrfs_trans_handle *trans; struct btrfs_block_rsv block_rsv; u64 root_flags; + u64 qgroup_reserved = 0; int ret; down_write(&fs_info->subvol_sem); @@ -4547,12 +4547,20 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); if (ret) goto out_undead; + qgroup_reserved = block_rsv.qgroup_rsv_reserved; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_release; } + ret = btrfs_record_root_in_trans(trans, root); + if (ret) { + btrfs_abort_transaction(trans, ret); + goto out_end_trans; + } + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + qgroup_reserved = 0; trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; @@ -4611,7 +4619,9 @@ out_end_trans: ret = btrfs_end_transaction(trans); inode->i_flags |= S_DEAD; out_release: - btrfs_subvolume_release_metadata(root, &block_rsv); + btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL); + if (qgroup_reserved) + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); out_undead: if (ret) { spin_lock(&dest->root_item_lock); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 294e31edec9d..55f3ba6a831c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -613,6 +613,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap, int ret; dev_t anon_dev; u64 objectid; + u64 qgroup_reserved = 0; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) @@ -650,13 +651,18 @@ static noinline int create_subvol(struct mnt_idmap *idmap, trans_num_items, false); if (ret) goto out_new_inode_args; + qgroup_reserved = block_rsv.qgroup_rsv_reserved; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - btrfs_subvolume_release_metadata(root, &block_rsv); - goto out_new_inode_args; + goto out_release_rsv; } + ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root); + if (ret) + goto out; + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + qgroup_reserved = 0; trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; /* Tree log can't currently deal with an inode which is a new root. */ @@ -767,9 +773,11 @@ static noinline int create_subvol(struct mnt_idmap *idmap, out: trans->block_rsv = NULL; trans->bytes_reserved = 0; - btrfs_subvolume_release_metadata(root, &block_rsv); - btrfs_end_transaction(trans); +out_release_rsv: + btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL); + if (qgroup_reserved) + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); out_new_inode_args: btrfs_new_inode_args_destroy(&new_inode_args); out_inode: @@ -791,6 +799,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct btrfs_pending_snapshot *pending_snapshot; unsigned int trans_num_items; struct btrfs_trans_handle *trans; + struct btrfs_block_rsv *block_rsv; + u64 qgroup_reserved = 0; int ret; /* We do not support snapshotting right now. */ @@ -827,19 +837,19 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto free_pending; } - btrfs_init_block_rsv(&pending_snapshot->block_rsv, - BTRFS_BLOCK_RSV_TEMP); + block_rsv = &pending_snapshot->block_rsv; + btrfs_init_block_rsv(block_rsv, BTRFS_BLOCK_RSV_TEMP); /* * 1 to add dir item * 1 to add dir index * 1 to update parent inode item */ trans_num_items = create_subvol_num_items(inherit) + 3; - ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, - &pending_snapshot->block_rsv, + ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, block_rsv, trans_num_items, false); if (ret) goto free_pending; + qgroup_reserved = block_rsv->qgroup_rsv_reserved; pending_snapshot->dentry = dentry; pending_snapshot->root = root; @@ -852,6 +862,13 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, ret = PTR_ERR(trans); goto fail; } + ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root); + if (ret) { + btrfs_end_transaction(trans); + goto fail; + } + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); + qgroup_reserved = 0; trans->pending_snapshot = pending_snapshot; @@ -881,7 +898,9 @@ fail: if (ret && pending_snapshot->snap) pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); - btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv); + btrfs_block_rsv_release(fs_info, block_rsv, (u64)-1, NULL); + if (qgroup_reserved) + btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved); free_pending: if (pending_snapshot->anon_dev) free_anon_bdev(pending_snapshot->anon_dev); diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c index c96dd66fd0f7..210d9c82e2ae 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/qgroup.c b/fs/btrfs/qgroup.c index 5f90f0605b12..cf8820ce7aa2 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -4495,6 +4495,8 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes) BTRFS_QGROUP_RSV_META_PREALLOC); trace_qgroup_meta_convert(root, num_bytes); qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes); + if (!sb_rdonly(fs_info->sb)) + add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS); } /* diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 4bb538a372ce..7007f9e0c972 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -548,13 +548,3 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, } return ret; } - -void btrfs_subvolume_release_metadata(struct btrfs_root *root, - struct btrfs_block_rsv *rsv) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - u64 qgroup_to_release; - - btrfs_block_rsv_release(fs_info, rsv, (u64)-1, &qgroup_to_release); - btrfs_qgroup_convert_reserved_meta(root, qgroup_to_release); -} diff --git a/fs/btrfs/root-tree.h b/fs/btrfs/root-tree.h index 6f929cf3bd49..8f5739e732b9 100644 --- a/fs/btrfs/root-tree.h +++ b/fs/btrfs/root-tree.h @@ -18,8 +18,6 @@ struct btrfs_trans_handle; int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, int nitems, bool use_global_rsv); -void btrfs_subvolume_release_metadata(struct btrfs_root *root, - struct btrfs_block_rsv *rsv); int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, u64 ref_id, u64 dirid, u64 sequence, const struct fscrypt_str *name); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index fa25004ab04e..4b22cfe9a98c 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 @@ out: * 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 253cce7ffecf..47b5d301038e 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/transaction.c b/fs/btrfs/transaction.c index 46e8426adf4f..85f359e0e0a7 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -745,14 +745,6 @@ again: h->reloc_reserved = reloc_reserved; } - /* - * Now that we have found a transaction to be a part of, convert the - * qgroup reservation from prealloc to pertrans. A different transaction - * can't race in and free our pertrans out from under us. - */ - if (qgroup_reserved) - btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); - got_it: if (!current->journal_info) current->journal_info = h; @@ -786,8 +778,15 @@ got_it: * not just freed. */ btrfs_end_transaction(h); - return ERR_PTR(ret); + goto reserve_fail; } + /* + * Now that we have found a transaction to be a part of, convert the + * qgroup reservation from prealloc to pertrans. A different transaction + * can't race in and free our pertrans out from under us. + */ + if (qgroup_reserved) + btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved); return h; @@ -1495,6 +1494,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) radix_tree_tag_clear(&fs_info->fs_roots_radix, (unsigned long)root->root_key.objectid, BTRFS_ROOT_TRANS_TAG); + btrfs_qgroup_free_meta_all_pertrans(root); spin_unlock(&fs_info->fs_roots_radix_lock); btrfs_free_log(trans, root); @@ -1519,7 +1519,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) if (ret2) return ret2; spin_lock(&fs_info->fs_roots_radix_lock); - btrfs_qgroup_free_meta_all_pertrans(root); } } spin_unlock(&fs_info->fs_roots_radix_lock); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 1340d77124ae..ee9caf7916fb 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -795,8 +795,10 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) ihold(inode); if (wbc->sync_mode == WB_SYNC_NONE && - ceph_inode_to_fs_client(inode)->write_congested) + ceph_inode_to_fs_client(inode)->write_congested) { + redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; + } wait_on_page_fscache(page); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 55051ad09c19..c4941ba245ac 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4783,13 +4783,13 @@ int ceph_drop_caps_for_unlink(struct inode *inode) doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode, ceph_vinop(inode)); - spin_lock(&mdsc->cap_unlink_delay_lock); + spin_lock(&mdsc->cap_delay_lock); ci->i_ceph_flags |= CEPH_I_FLUSH; if (!list_empty(&ci->i_cap_delay_list)) list_del_init(&ci->i_cap_delay_list); list_add_tail(&ci->i_cap_delay_list, &mdsc->cap_unlink_delay_list); - spin_unlock(&mdsc->cap_unlink_delay_lock); + spin_unlock(&mdsc->cap_delay_lock); /* * Fire the work immediately, because the MDS maybe diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 3ab9c268a8bb..360b686c3c67 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2504,7 +2504,7 @@ static void ceph_cap_unlink_work(struct work_struct *work) struct ceph_client *cl = mdsc->fsc->client; doutc(cl, "begin\n"); - spin_lock(&mdsc->cap_unlink_delay_lock); + spin_lock(&mdsc->cap_delay_lock); while (!list_empty(&mdsc->cap_unlink_delay_list)) { struct ceph_inode_info *ci; struct inode *inode; @@ -2516,15 +2516,15 @@ static void ceph_cap_unlink_work(struct work_struct *work) inode = igrab(&ci->netfs.inode); if (inode) { - spin_unlock(&mdsc->cap_unlink_delay_lock); + spin_unlock(&mdsc->cap_delay_lock); doutc(cl, "on %p %llx.%llx\n", inode, ceph_vinop(inode)); ceph_check_caps(ci, CHECK_CAPS_FLUSH); iput(inode); - spin_lock(&mdsc->cap_unlink_delay_lock); + spin_lock(&mdsc->cap_delay_lock); } } - spin_unlock(&mdsc->cap_unlink_delay_lock); + spin_unlock(&mdsc->cap_delay_lock); doutc(cl, "done\n"); } @@ -5404,7 +5404,6 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) INIT_LIST_HEAD(&mdsc->cap_wait_list); spin_lock_init(&mdsc->cap_delay_lock); INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list); - spin_lock_init(&mdsc->cap_unlink_delay_lock); INIT_LIST_HEAD(&mdsc->snap_flush_list); spin_lock_init(&mdsc->snap_flush_lock); mdsc->last_cap_flush_tid = 1; diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 03f8ff00874f..b88e80415224 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -461,9 +461,8 @@ struct ceph_mds_client { struct delayed_work delayed_work; /* delayed work */ unsigned long last_renew_caps; /* last time we renewed our caps */ struct list_head cap_delay_list; /* caps with delayed release */ - spinlock_t cap_delay_lock; /* protects cap_delay_list */ struct list_head cap_unlink_delay_list; /* caps with delayed release for unlink */ - spinlock_t cap_unlink_delay_lock; /* protects cap_unlink_delay_list */ + spinlock_t cap_delay_lock; /* protects cap_delay_list and cap_unlink_delay_list */ struct list_head snap_flush_list; /* cap_snaps ready to flush */ spinlock_t snap_flush_lock; diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index b6cad106c37e..0b2da7b7e2ad 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -310,6 +310,10 @@ struct cuse_init_args { /** * cuse_process_init_reply - finish initializing CUSE channel * + * @fm: The fuse mount information containing the CUSE connection. + * @args: The arguments passed to the init reply. + * @error: The error code signifying if any error occurred during the process. + * * This function creates the character device and sets up all the * required data structures for it. Please read the comment at the * top of this file for high level overview. diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 4a6df591add6..2b0d4781f394 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1321,6 +1321,7 @@ retry: err = fuse_do_statx(inode, file, stat); if (err == -ENOSYS) { fc->no_statx = 1; + err = 0; goto retry; } } else { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a56e7bffd000..b57ce4157640 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1362,7 +1362,7 @@ static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from, bool *exclusive) { struct inode *inode = file_inode(iocb->ki_filp); - struct fuse_file *ff = iocb->ki_filp->private_data; + struct fuse_inode *fi = get_fuse_inode(inode); *exclusive = fuse_dio_wr_exclusive_lock(iocb, from); if (*exclusive) { @@ -1377,7 +1377,7 @@ static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from, * have raced, so check it again. */ if (fuse_io_past_eof(iocb, from) || - fuse_file_uncached_io_start(inode, ff, NULL) != 0) { + fuse_inode_uncached_io_start(fi, NULL) != 0) { inode_unlock_shared(inode); inode_lock(inode); *exclusive = true; @@ -1388,13 +1388,13 @@ static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from, static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive) { struct inode *inode = file_inode(iocb->ki_filp); - struct fuse_file *ff = iocb->ki_filp->private_data; + struct fuse_inode *fi = get_fuse_inode(inode); if (exclusive) { inode_unlock(inode); } else { /* Allow opens in caching mode after last parallel dio end */ - fuse_file_uncached_io_end(inode, ff); + fuse_inode_uncached_io_end(fi); inode_unlock_shared(inode); } } @@ -2574,8 +2574,10 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) * First mmap of direct_io file enters caching inode io mode. * Also waits for parallel dio writers to go into serial mode * (exclusive instead of shared lock). + * After first mmap, the inode stays in caching io mode until + * the direct_io file release. */ - rc = fuse_file_cached_io_start(inode, ff); + rc = fuse_file_cached_io_open(inode, ff); if (rc) return rc; } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index b24084b60864..f23919610313 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1394,9 +1394,10 @@ int fuse_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); /* iomode.c */ -int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff); -int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb); -void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff); +int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff); +int fuse_inode_uncached_io_start(struct fuse_inode *fi, + struct fuse_backing *fb); +void fuse_inode_uncached_io_end(struct fuse_inode *fi); int fuse_file_io_open(struct file *file, struct inode *inode); void fuse_file_io_release(struct fuse_file *ff, struct inode *inode); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 3a5d88878335..99e44ea7d875 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -175,6 +175,7 @@ static void fuse_evict_inode(struct inode *inode) } } if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { + WARN_ON(fi->iocachectr != 0); WARN_ON(!list_empty(&fi->write_files)); WARN_ON(!list_empty(&fi->queued_writes)); } diff --git a/fs/fuse/iomode.c b/fs/fuse/iomode.c index c653ddcf0578..c99e285f3183 100644 --- a/fs/fuse/iomode.c +++ b/fs/fuse/iomode.c @@ -21,12 +21,13 @@ static inline bool fuse_is_io_cache_wait(struct fuse_inode *fi) } /* - * Start cached io mode. + * Called on cached file open() and on first mmap() of direct_io file. + * Takes cached_io inode mode reference to be dropped on file release. * * Blocks new parallel dio writes and waits for the in-progress parallel dio * writes to complete. */ -int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff) +int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -67,10 +68,9 @@ int fuse_file_cached_io_start(struct inode *inode, struct fuse_file *ff) return 0; } -static void fuse_file_cached_io_end(struct inode *inode, struct fuse_file *ff) +static void fuse_file_cached_io_release(struct fuse_file *ff, + struct fuse_inode *fi) { - struct fuse_inode *fi = get_fuse_inode(inode); - spin_lock(&fi->lock); WARN_ON(fi->iocachectr <= 0); WARN_ON(ff->iomode != IOM_CACHED); @@ -82,16 +82,15 @@ static void fuse_file_cached_io_end(struct inode *inode, struct fuse_file *ff) } /* Start strictly uncached io mode where cache access is not allowed */ -int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struct fuse_backing *fb) +int fuse_inode_uncached_io_start(struct fuse_inode *fi, struct fuse_backing *fb) { - struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_backing *oldfb; int err = 0; spin_lock(&fi->lock); /* deny conflicting backing files on same fuse inode */ oldfb = fuse_inode_backing(fi); - if (oldfb && oldfb != fb) { + if (fb && oldfb && oldfb != fb) { err = -EBUSY; goto unlock; } @@ -99,12 +98,10 @@ int fuse_file_uncached_io_start(struct inode *inode, struct fuse_file *ff, struc err = -ETXTBSY; goto unlock; } - WARN_ON(ff->iomode != IOM_NONE); fi->iocachectr--; - ff->iomode = IOM_UNCACHED; /* fuse inode holds a single refcount of backing file */ - if (!oldfb) { + if (fb && !oldfb) { oldfb = fuse_inode_backing_set(fi, fb); WARN_ON_ONCE(oldfb != NULL); } else { @@ -115,15 +112,29 @@ unlock: return err; } -void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff) +/* Takes uncached_io inode mode reference to be dropped on file release */ +static int fuse_file_uncached_io_open(struct inode *inode, + struct fuse_file *ff, + struct fuse_backing *fb) { struct fuse_inode *fi = get_fuse_inode(inode); + int err; + + err = fuse_inode_uncached_io_start(fi, fb); + if (err) + return err; + + WARN_ON(ff->iomode != IOM_NONE); + ff->iomode = IOM_UNCACHED; + return 0; +} + +void fuse_inode_uncached_io_end(struct fuse_inode *fi) +{ struct fuse_backing *oldfb = NULL; spin_lock(&fi->lock); WARN_ON(fi->iocachectr >= 0); - WARN_ON(ff->iomode != IOM_UNCACHED); - ff->iomode = IOM_NONE; fi->iocachectr++; if (!fi->iocachectr) { wake_up(&fi->direct_io_waitq); @@ -134,6 +145,15 @@ void fuse_file_uncached_io_end(struct inode *inode, struct fuse_file *ff) fuse_backing_put(oldfb); } +/* Drop uncached_io reference from passthrough open */ +static void fuse_file_uncached_io_release(struct fuse_file *ff, + struct fuse_inode *fi) +{ + WARN_ON(ff->iomode != IOM_UNCACHED); + ff->iomode = IOM_NONE; + fuse_inode_uncached_io_end(fi); +} + /* * Open flags that are allowed in combination with FOPEN_PASSTHROUGH. * A combination of FOPEN_PASSTHROUGH and FOPEN_DIRECT_IO means that read/write @@ -163,7 +183,7 @@ static int fuse_file_passthrough_open(struct inode *inode, struct file *file) return PTR_ERR(fb); /* First passthrough file open denies caching inode io mode */ - err = fuse_file_uncached_io_start(inode, ff, fb); + err = fuse_file_uncached_io_open(inode, ff, fb); if (!err) return 0; @@ -216,7 +236,7 @@ int fuse_file_io_open(struct file *file, struct inode *inode) if (ff->open_flags & FOPEN_PASSTHROUGH) err = fuse_file_passthrough_open(inode, file); else - err = fuse_file_cached_io_start(inode, ff); + err = fuse_file_cached_io_open(inode, ff); if (err) goto fail; @@ -236,8 +256,10 @@ fail: /* No more pending io and no new io possible to inode via open/mmapped file */ void fuse_file_io_release(struct fuse_file *ff, struct inode *inode) { + struct fuse_inode *fi = get_fuse_inode(inode); + /* - * Last parallel dio close allows caching inode io mode. + * Last passthrough file close allows caching inode io mode. * Last caching file close exits caching inode io mode. */ switch (ff->iomode) { @@ -245,10 +267,10 @@ void fuse_file_io_release(struct fuse_file *ff, struct inode *inode) /* Nothing to do */ break; case IOM_UNCACHED: - fuse_file_uncached_io_end(inode, ff); + fuse_file_uncached_io_release(ff, fi); break; case IOM_CACHED: - fuse_file_cached_io_end(inode, ff); + fuse_file_cached_io_release(ff, fi); break; } } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e9df2f87072c..8502ef68459b 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -636,11 +636,18 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * - * Both paths of the branch look the same. They're supposed to + * For similar reasons, writable and readonly files are given different + * lockdep key, because the writable file /sys/power/resume may call vfs + * lookup helpers for arbitrary paths and readonly files can be read by + * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs. + * + * All three cases look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); + else if (file->f_mode & FMODE_WRITE) + mutex_init(&of->mutex); else mutex_init(&of->mutex); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 87c9547989f6..e88aca0c6e8e 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 fac938f563ad..1955481832e0 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3490,11 +3490,13 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct dentry *dentry, const u32 *bmval, int ignore_crossmnt) { + DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); struct nfsd4_fattr_args args; struct svc_fh *tempfh = NULL; int starting_len = xdr->buf->len; __be32 *attrlen_p, status; int attrlen_offset; + u32 attrmask[3]; int err; struct nfsd4_compoundres *resp = rqstp->rq_resp; u32 minorversion = resp->cstate.minorversion; @@ -3502,10 +3504,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, .mnt = exp->ex_path.mnt, .dentry = dentry, }; - union { - u32 attrmask[3]; - unsigned long mask[2]; - } u; unsigned long bit; bool file_modified = false; u64 size = 0; @@ -3521,20 +3519,19 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, /* * Make a local copy of the attribute bitmap that can be modified. */ - memset(&u, 0, sizeof(u)); - u.attrmask[0] = bmval[0]; - u.attrmask[1] = bmval[1]; - u.attrmask[2] = bmval[2]; + attrmask[0] = bmval[0]; + attrmask[1] = bmval[1]; + attrmask[2] = bmval[2]; args.rdattr_err = 0; if (exp->ex_fslocs.migrated) { - status = fattr_handle_absent_fs(&u.attrmask[0], &u.attrmask[1], - &u.attrmask[2], &args.rdattr_err); + status = fattr_handle_absent_fs(&attrmask[0], &attrmask[1], + &attrmask[2], &args.rdattr_err); if (status) goto out; } args.size = 0; - if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { + if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry), &file_modified, &size); if (status) @@ -3553,16 +3550,16 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (!(args.stat.result_mask & STATX_BTIME)) /* underlying FS does not offer btime so we can't share it */ - u.attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; - if ((u.attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | + attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; + if ((attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || - (u.attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | + (attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL))) { err = vfs_statfs(&path, &args.statfs); if (err) goto out_nfserr; } - if ((u.attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && + if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) { tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL); status = nfserr_jukebox; @@ -3577,10 +3574,10 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.fhp = fhp; args.acl = NULL; - if (u.attrmask[0] & FATTR4_WORD0_ACL) { + if (attrmask[0] & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) - u.attrmask[0] &= ~FATTR4_WORD0_ACL; + attrmask[0] &= ~FATTR4_WORD0_ACL; else if (err == -EINVAL) { status = nfserr_attrnotsupp; goto out; @@ -3592,17 +3589,17 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, #ifdef CONFIG_NFSD_V4_SECURITY_LABEL args.context = NULL; - if ((u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || - u.attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { + if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || + attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { if (exp->ex_flags & NFSEXP_SECURITY_LABEL) err = security_inode_getsecctx(d_inode(dentry), &args.context, &args.contextlen); else err = -EOPNOTSUPP; args.contextsupport = (err == 0); - if (u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { + if (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { if (err == -EOPNOTSUPP) - u.attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; else if (err) goto out_nfserr; } @@ -3610,8 +3607,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ /* attrmask */ - status = nfsd4_encode_bitmap4(xdr, u.attrmask[0], - u.attrmask[1], u.attrmask[2]); + status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1], + attrmask[2]); if (status) goto out; @@ -3620,7 +3617,9 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); if (!attrlen_p) goto out_resource; - for_each_set_bit(bit, (const unsigned long *)&u.mask, + bitmap_from_arr32(attr_bitmap, attrmask, + ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); + for_each_set_bit(bit, attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) { status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args); if (status != nfs_ok) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 01c6f3445646..2ed0fcf879fd 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/nilfs2/dir.c b/fs/nilfs2/dir.c index bc846b904b68..aee40db7a036 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -240,7 +240,7 @@ nilfs_filetype_table[NILFS_FT_MAX] = { #define S_SHIFT 12 static unsigned char -nilfs_type_by_mode[S_IFMT >> S_SHIFT] = { +nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = NILFS_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = NILFS_FT_DIR, [S_IFCHR >> S_SHIFT] = NILFS_FT_CHRDEV, diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c index 902b326e1e56..87dcaae32ff8 100644 --- a/fs/proc/bootconfig.c +++ b/fs/proc/bootconfig.c @@ -62,12 +62,12 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size) break; dst += ret; } - if (ret >= 0 && boot_command_line[0]) { - ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n", - boot_command_line); - if (ret > 0) - dst += ret; - } + } + if (cmdline_has_extra_options() && ret >= 0 && boot_command_line[0]) { + ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n", + boot_command_line); + if (ret > 0) + dst += ret; } out: kfree(key); diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 13a9d7acf8f8..0ff2491c311d 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -433,8 +433,8 @@ smb2_close_cached_fid(struct kref *ref) if (cfid->is_open) { rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, cfid->fid.volatile_fid); - if (rc != -EBUSY && rc != -EAGAIN) - atomic_dec(&cfid->tcon->num_remote_opens); + if (rc) /* should we retry on -EBUSY or -EAGAIN? */ + cifs_dbg(VFS, "close cached dir rc %d\n", rc); } free_cached_dir(cfid); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index d41eedbff674..39277c37185c 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 f6a302205f89..6ff35570db81 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1077,6 +1077,7 @@ struct cifs_ses { and after mount option parsing we fill it */ char *domainName; char *password; + char *password2; /* When key rotation used, new password may be set before it expires */ char workstation_name[CIFS_MAX_WORKSTATION_LEN]; struct session_key auth_key; struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */ @@ -1189,6 +1190,7 @@ struct cifs_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 */ @@ -1275,7 +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/cifsproto.h b/fs/smb/client/cifsproto.h index 8e0a348f1f66..fbc358c09da3 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 85679ae106fd..7a16e12f5da8 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); @@ -2183,6 +2183,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) } ++delim; + /* BB consider adding support for password2 (Key Rotation) for multiuser in future */ ctx->password = kstrndup(delim, len, GFP_KERNEL); if (!ctx->password) { cifs_dbg(FYI, "Unable to allocate %zd bytes for password\n", @@ -2206,6 +2207,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) kfree(ctx->username); ctx->username = NULL; kfree_sensitive(ctx->password); + /* no need to free ctx->password2 since not allocated in this path */ ctx->password = NULL; goto out_key_put; } @@ -2317,6 +2319,12 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) if (!ses->password) goto get_ses_fail; } + /* ctx->password freed at unmount */ + if (ctx->password2) { + ses->password2 = kstrdup(ctx->password2, GFP_KERNEL); + if (!ses->password2) + goto get_ses_fail; + } if (ctx->domainname) { ses->domainName = kstrdup(ctx->domainname, GFP_KERNEL); if (!ses->domainName) @@ -2424,6 +2432,8 @@ 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; @@ -2433,7 +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; @@ -2449,6 +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); @@ -2485,7 +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); } @@ -2539,7 +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; @@ -2729,7 +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); } @@ -2746,7 +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); } @@ -3311,7 +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 b7bfe705b2c4..3bbac925d076 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -162,6 +162,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_string("username", Opt_user), fsparam_string("pass", Opt_pass), fsparam_string("password", Opt_pass), + fsparam_string("password2", Opt_pass2), fsparam_string("ip", Opt_ip), fsparam_string("addr", Opt_ip), fsparam_string("domain", Opt_domain), @@ -345,6 +346,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->nodename = NULL; new_ctx->username = NULL; new_ctx->password = NULL; + new_ctx->password2 = NULL; new_ctx->server_hostname = NULL; new_ctx->domainname = NULL; new_ctx->UNC = NULL; @@ -357,6 +359,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(prepath); DUP_CTX_STR(username); DUP_CTX_STR(password); + DUP_CTX_STR(password2); DUP_CTX_STR(server_hostname); DUP_CTX_STR(UNC); DUP_CTX_STR(source); @@ -745,6 +748,16 @@ 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"); @@ -905,6 +918,8 @@ static int smb3_reconfigure(struct fs_context *fc) else { kfree_sensitive(ses->password); ses->password = kstrdup(ctx->password, GFP_KERNEL); + kfree_sensitive(ses->password2); + ses->password2 = kstrdup(ctx->password2, GFP_KERNEL); } STEAL_STRING(cifs_sb, ctx, domainname); STEAL_STRING(cifs_sb, ctx, nodename); @@ -1014,12 +1029,14 @@ 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) @@ -1305,6 +1322,18 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, goto cifs_parse_mount_err; } break; + case Opt_pass2: + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; + if (strlen(param->string) == 0) + break; + + ctx->password2 = kstrdup(param->string, GFP_KERNEL); + if (ctx->password2 == NULL) { + cifs_errorf(fc, "OOM when copying password2 string\n"); + goto cifs_parse_mount_err; + } + break; case Opt_ip: if (strlen(param->string) == 0) { ctx->got_ip = false; @@ -1608,6 +1637,8 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_parse_mount_err: kfree_sensitive(ctx->password); ctx->password = NULL; + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; return -EINVAL; } @@ -1713,6 +1744,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->username = NULL; kfree_sensitive(ctx->password); ctx->password = NULL; + kfree_sensitive(ctx->password2); + ctx->password2 = NULL; kfree(ctx->server_hostname); ctx->server_hostname = NULL; kfree(ctx->UNC); diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 8a35645e0b65..cf577ec0dd0a 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -145,6 +145,7 @@ enum cifs_param { Opt_source, Opt_user, Opt_pass, + Opt_pass2, Opt_ip, Opt_domain, Opt_srcaddr, @@ -164,6 +165,8 @@ enum cifs_param { }; struct smb3_fs_context { + bool forceuid_specified; + bool forcegid_specified; bool uid_specified; bool cruid_specified; bool gid_specified; @@ -177,6 +180,7 @@ struct smb3_fs_context { char *username; char *password; + char *password2; char *domainname; char *source; char *server_hostname; diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index 340efce8f052..1a895e6243ee 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 @@ out_2: 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/inode.c b/fs/smb/client/inode.c index 91b07ef9e25c..60afab5c83d4 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1105,7 +1105,8 @@ static int cifs_get_fattr(struct cifs_open_info_data *data, } else { cifs_open_info_to_fattr(fattr, data, sb); } - if (!rc && fattr->cf_flags & CIFS_FATTR_DELETE_PENDING) + if (!rc && *inode && + (fattr->cf_flags & CIFS_FATTR_DELETE_PENDING)) cifs_mark_open_handles_for_deleted_file(*inode, full_path); break; case -EREMOTE: diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 33ac4f8f5050..07c468ddb88a 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -98,6 +98,7 @@ sesInfoFree(struct cifs_ses *buf_to_free) kfree(buf_to_free->serverDomain); kfree(buf_to_free->serverNOS); kfree_sensitive(buf_to_free->password); + kfree_sensitive(buf_to_free->password2); kfree(buf_to_free->user_name); kfree(buf_to_free->domainName); kfree_sensitive(buf_to_free->auth_key.response); @@ -110,9 +111,10 @@ 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) @@ -129,7 +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); @@ -138,17 +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 cc72be5a93a9..677ef6f99a5b 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 b156eefa75d7..28f0b7d19d53 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); @@ -4964,68 +4969,84 @@ static int smb2_next_header(struct TCP_Server_Info *server, char *buf, return 0; } -int cifs_sfu_make_node(unsigned int xid, struct inode *inode, - struct dentry *dentry, struct cifs_tcon *tcon, - const char *full_path, umode_t mode, dev_t dev) +static int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev) { - struct cifs_open_info_data buf = {}; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; struct cifs_io_parms io_parms = {}; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_fid fid; unsigned int bytes_written; - struct win_dev *pdev; + struct win_dev pdev = {}; struct kvec iov[2]; __u32 oplock = server->oplocks ? REQ_OPLOCK : 0; int rc; - if (!S_ISCHR(mode) && !S_ISBLK(mode) && !S_ISFIFO(mode)) + switch (mode & S_IFMT) { + case S_IFCHR: + strscpy(pdev.type, "IntxCHR"); + pdev.major = cpu_to_le64(MAJOR(dev)); + pdev.minor = cpu_to_le64(MINOR(dev)); + break; + case S_IFBLK: + strscpy(pdev.type, "IntxBLK"); + pdev.major = cpu_to_le64(MAJOR(dev)); + pdev.minor = cpu_to_le64(MINOR(dev)); + break; + case S_IFIFO: + strscpy(pdev.type, "LnxFIFO"); + break; + default: return -EPERM; + } - oparms = (struct cifs_open_parms) { - .tcon = tcon, - .cifs_sb = cifs_sb, - .desired_access = GENERIC_WRITE, - .create_options = cifs_create_options(cifs_sb, CREATE_NOT_DIR | - CREATE_OPTION_SPECIAL), - .disposition = FILE_CREATE, - .path = full_path, - .fid = &fid, - }; + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, GENERIC_WRITE, + FILE_CREATE, CREATE_NOT_DIR | + CREATE_OPTION_SPECIAL, ACL_NO_MODE); + oparms.fid = &fid; - rc = server->ops->open(xid, &oparms, &oplock, &buf); + rc = server->ops->open(xid, &oparms, &oplock, NULL); if (rc) return rc; - /* - * BB Do not bother to decode buf since no local inode yet to put - * timestamps in, but we can reuse it safely. - */ - pdev = (struct win_dev *)&buf.fi; io_parms.pid = current->tgid; io_parms.tcon = tcon; - io_parms.length = sizeof(*pdev); - iov[1].iov_base = pdev; - iov[1].iov_len = sizeof(*pdev); - if (S_ISCHR(mode)) { - memcpy(pdev->type, "IntxCHR", 8); - pdev->major = cpu_to_le64(MAJOR(dev)); - pdev->minor = cpu_to_le64(MINOR(dev)); - } else if (S_ISBLK(mode)) { - memcpy(pdev->type, "IntxBLK", 8); - pdev->major = cpu_to_le64(MAJOR(dev)); - pdev->minor = cpu_to_le64(MINOR(dev)); - } else if (S_ISFIFO(mode)) { - memcpy(pdev->type, "LnxFIFO", 8); - } + io_parms.length = sizeof(pdev); + iov[1].iov_base = &pdev; + iov[1].iov_len = sizeof(pdev); rc = server->ops->sync_write(xid, &fid, &io_parms, &bytes_written, iov, 1); server->ops->close(xid, tcon, &fid); - d_drop(dentry); - /* FIXME: add code here to set EAs */ - cifs_free_open_info(&buf); + return rc; +} + +int cifs_sfu_make_node(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev) +{ + struct inode *new = NULL; + int rc; + + rc = __cifs_sfu_make_node(xid, inode, dentry, tcon, + full_path, mode, dev); + if (rc) + return rc; + + if (tcon->posix_extensions) { + rc = smb311_posix_get_inode_info(&new, full_path, NULL, + inode->i_sb, xid); + } else if (tcon->unix_ext) { + rc = cifs_get_inode_info_unix(&new, full_path, + inode->i_sb, xid); + } else { + rc = cifs_get_inode_info(&new, full_path, NULL, + inode->i_sb, xid, NULL); + } + if (!rc) + d_instantiate(dentry, new); return rc; } diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index c0c4933af5fc..a5efce03cb58 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -367,6 +367,17 @@ again: } rc = cifs_setup_session(0, ses, server, nls_codepage); + if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) { + /* + * Try alternate password for next reconnect (key rotation + * could be enabled on the server e.g.) if an alternate + * password is available and the current password is expired, + * but do not swap on non pwd related errors like host down + */ + if (ses->password2) + swap(ses->password2, ses->password); + } + if ((rc == -EACCES) && !tcon->retry) { mutex_unlock(&ses->session_mutex); rc = -EHOSTDOWN; @@ -4127,6 +4138,8 @@ 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; } @@ -4165,14 +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) { @@ -4195,7 +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/smb2transport.c b/fs/smb/client/smb2transport.c index 1d6e54f7879e..02135a605305 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 5e83cb9da902..604e52876cd2 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -3,6 +3,9 @@ * Copyright (C) 2018, Microsoft Corporation. * * Author(s): Steve French <stfrench@microsoft.com> + * + * Please use this 3-part article as a reference for writing new tracepoints: + * https://lwn.net/Articles/379903/ */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cifs @@ -15,9 +18,70 @@ #include <linux/inet.h> /* - * Please use this 3-part article as a reference for writing new tracepoints: - * https://lwn.net/Articles/379903/ + * Specify enums for tracing information. + */ +#define smb3_tcon_ref_traces \ + EM(netfs_trace_tcon_ref_dec_dfs_refer, "DEC DfsRef") \ + EM(netfs_trace_tcon_ref_free, "FRE ") \ + EM(netfs_trace_tcon_ref_free_fail, "FRE Fail ") \ + EM(netfs_trace_tcon_ref_free_ipc, "FRE Ipc ") \ + EM(netfs_trace_tcon_ref_free_ipc_fail, "FRE Ipc-F ") \ + EM(netfs_trace_tcon_ref_free_reconnect_server, "FRE Reconn") \ + EM(netfs_trace_tcon_ref_get_cancelled_close, "GET Cn-Cls") \ + EM(netfs_trace_tcon_ref_get_dfs_refer, "GET DfsRef") \ + EM(netfs_trace_tcon_ref_get_find, "GET Find ") \ + EM(netfs_trace_tcon_ref_get_find_sess_tcon, "GET FndSes") \ + EM(netfs_trace_tcon_ref_get_reconnect_server, "GET Reconn") \ + EM(netfs_trace_tcon_ref_new, "NEW ") \ + EM(netfs_trace_tcon_ref_new_ipc, "NEW Ipc ") \ + EM(netfs_trace_tcon_ref_new_reconnect_server, "NEW Reconn") \ + EM(netfs_trace_tcon_ref_put_cancelled_close, "PUT Cn-Cls") \ + EM(netfs_trace_tcon_ref_put_cancelled_close_fid, "PUT Cn-Fid") \ + EM(netfs_trace_tcon_ref_put_cancelled_mid, "PUT Cn-Mid") \ + EM(netfs_trace_tcon_ref_put_mnt_ctx, "PUT MntCtx") \ + EM(netfs_trace_tcon_ref_put_reconnect_server, "PUT Reconn") \ + EM(netfs_trace_tcon_ref_put_tlink, "PUT Tlink ") \ + EM(netfs_trace_tcon_ref_see_cancelled_close, "SEE Cn-Cls") \ + EM(netfs_trace_tcon_ref_see_fscache_collision, "SEE FV-CO!") \ + EM(netfs_trace_tcon_ref_see_fscache_okay, "SEE FV-Ok ") \ + EM(netfs_trace_tcon_ref_see_fscache_relinq, "SEE FV-Rlq") \ + E_(netfs_trace_tcon_ref_see_umount, "SEE Umount") + +#undef EM +#undef E_ + +/* + * Define those tracing enums. + */ +#ifndef __SMB3_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __SMB3_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#define EM(a, b) a, +#define E_(a, b) a + +enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte); + +#undef EM +#undef E_ +#endif + +/* + * Export enum symbols via userspace. + */ +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define E_(a, b) TRACE_DEFINE_ENUM(a); + +smb3_tcon_ref_traces; + +#undef EM +#undef E_ + +/* + * Now redefine the EM() and E_() macros to map the enums to the strings that + * will be printed in the output. */ +#define EM(a, b) { a, b }, +#define E_(a, b) { a, b } /* For logging errors in read or write */ DECLARE_EVENT_CLASS(smb3_rw_err_class, @@ -1125,6 +1189,30 @@ DEFINE_SMB3_CREDIT_EVENT(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/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 1b594307c9d5..202ff9128156 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 686b321c5a8b..f4e55199938d 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 c0788188aa82..c67fbc8d6683 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 5723bbf372d7..355824151c2d 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 22f0f3db3ac9..51b1b0bed616 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -754,10 +754,15 @@ retry: goto out4; } + /* + * explicitly handle file overwrite case, for compatibility with + * filesystems that may not support rename flags (e.g: fuse) + */ if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) { err = -EEXIST; goto out4; } + flags &= ~(RENAME_NOREPLACE); if (old_child == trap) { err = -EINVAL; diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index aa3411354e66..16bd693d0b3a 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -48,6 +48,10 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, gid_t i_gid; int err; + inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); + if (inode->i_ino == 0) + return -EINVAL; + err = squashfs_get_id(sb, le16_to_cpu(sqsh_ino->uid), &i_uid); if (err) return err; @@ -58,7 +62,6 @@ static int squashfs_new_inode(struct super_block *sb, struct inode *inode, i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); - inode->i_ino = le32_to_cpu(sqsh_ino->inode_number); inode_set_mtime(inode, le32_to_cpu(sqsh_ino->mtime), 0); inode_set_atime(inode, inode_get_mtime_sec(inode), 0); inode_set_ctime(inode, inode_get_mtime_sec(inode), 0); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 6b7652fb8050..7cd64021d453 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -463,6 +463,8 @@ struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, kn = kernfs_find_and_get(kobj->sd, attr->name); if (kn) kernfs_break_active_protection(kn); + else + kobject_put(kobj); return kn; } EXPORT_SYMBOL_GPL(sysfs_break_active_protection); diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index dc067eeb6387..894c6ca1e500 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -336,6 +336,7 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode, /** * lookup_file - look up a file in the tracefs filesystem + * @parent_ei: Pointer to the eventfs_inode that represents parent of the file * @dentry: the dentry to look up * @mode: the permission that the file should have. * @attr: saved attributes changed by user @@ -389,6 +390,7 @@ static struct dentry *lookup_file(struct eventfs_inode *parent_ei, /** * lookup_dir_entry - look up a dir in the tracefs filesystem * @dentry: the directory to look up + * @pei: Pointer to the parent eventfs_inode if available * @ei: the eventfs_inode that represents the directory to create * * This function will look up a dentry for a directory represented by @@ -478,16 +480,20 @@ void eventfs_d_release(struct dentry *dentry) /** * lookup_file_dentry - create a dentry for a file of an eventfs_inode + * @dentry: The parent dentry under which the new file's dentry will be created * @ei: the eventfs_inode that the file will be created under * @idx: the index into the entry_attrs[] of the @ei - * @parent: The parent dentry of the created file. - * @name: The name of the file to create * @mode: The mode of the file. * @data: The data to use to set the inode of the file with on open() * @fops: The fops of the file to be created. * - * Create a dentry for a file of an eventfs_inode @ei and place it into the - * address located at @e_dentry. + * This function creates a dentry for a file associated with an + * eventfs_inode @ei. It uses the entry attributes specified by @idx, + * if available. The file will have the specified @mode and its inode will be + * set up with @data upon open. The file operations will be set to @fops. + * + * Return: Returns a pointer to the newly created file's dentry or an error + * pointer. */ static struct dentry * lookup_file_dentry(struct dentry *dentry, diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index c6a124e8d565..964fa7f24003 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1048,7 +1048,7 @@ static int zonefs_init_zgroup(struct super_block *sb, zonefs_info(sb, "Zone group \"%s\" has %u file%s\n", zonefs_zgroup_name(ztype), zgroup->g_nr_zones, - zgroup->g_nr_zones > 1 ? "s" : ""); + str_plural(zgroup->g_nr_zones)); return 0; } diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 5de954e2b18a..e7796f373d0d 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -911,17 +911,19 @@ static inline bool acpi_int_uid_match(struct acpi_device *adev, u64 uid2) * acpi_dev_hid_uid_match - Match device by supplied HID and UID * @adev: ACPI device to match. * @hid2: Hardware ID of the device. - * @uid2: Unique ID of the device, pass 0 or NULL to not check _UID. + * @uid2: Unique ID of the device, pass NULL to not check _UID. * * Matches HID and UID in @adev with given @hid2 and @uid2. Absence of @uid2 * will be treated as a match. If user wants to validate @uid2, it should be * done before calling this function. * - * Returns: %true if matches or @uid2 is 0 or NULL, %false otherwise. + * Returns: %true if matches or @uid2 is NULL, %false otherwise. */ #define acpi_dev_hid_uid_match(adev, hid2, uid2) \ (acpi_dev_hid_match(adev, hid2) && \ - (!(uid2) || acpi_dev_uid_match(adev, uid2))) + /* Distinguish integer 0 from NULL @uid2 */ \ + (_Generic(uid2, ACPI_STR_TYPES(!(uid2)), default: 0) || \ + acpi_dev_uid_match(adev, uid2))) void acpi_dev_clear_dependencies(struct acpi_device *supplier); bool acpi_dev_ready_for_enumeration(const struct acpi_device *device); diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 0c0695763bea..d4f581c1e21d 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -294,5 +294,13 @@ do { \ #define io_stop_wc() do { } while (0) #endif +/* + * Architectures that guarantee an implicit smp_mb() in switch_mm() + * can override smp_mb__after_switch_mm. + */ +#ifndef smp_mb__after_switch_mm +# define smp_mb__after_switch_mm() smp_mb() +#endif + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_GENERIC_BARRIER_H */ diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 6e794420bd39..b7de3a4eade1 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -156,7 +156,10 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); #else /* !CONFIG_BUG */ #ifndef HAVE_ARCH_BUG -#define BUG() do {} while (1) +#define BUG() do { \ + do {} while (1); \ + unreachable(); \ +} while (0) #endif #ifndef HAVE_ARCH_BUG_ON diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index 87e3d49a4e29..814207e7c37f 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -512,13 +512,9 @@ struct hv_proximity_domain_flags { u32 proximity_info_valid : 1; } __packed; -/* Not a union in windows but useful for zeroing */ -union hv_proximity_domain_info { - struct { - u32 domain_id; - struct hv_proximity_domain_flags flags; - }; - u64 as_uint64; +struct hv_proximity_domain_info { + u32 domain_id; + struct hv_proximity_domain_flags flags; } __packed; struct hv_lp_startup_status { @@ -532,14 +528,13 @@ struct hv_lp_startup_status { } __packed; /* HvAddLogicalProcessor hypercall */ -struct hv_add_logical_processor_in { +struct hv_input_add_logical_processor { u32 lp_index; u32 apic_id; - union hv_proximity_domain_info proximity_domain_info; - u64 flags; + struct hv_proximity_domain_info proximity_domain_info; } __packed; -struct hv_add_logical_processor_out { +struct hv_output_add_logical_processor { struct hv_lp_startup_status startup_status; } __packed; @@ -560,7 +555,7 @@ struct hv_create_vp { u8 padding[3]; u8 subnode_type; u64 subnode_id; - union hv_proximity_domain_info proximity_domain_info; + struct hv_proximity_domain_info proximity_domain_info; u64 flags; } __packed; diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 99935779682d..8fe7aaab2599 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -21,6 +21,7 @@ #include <linux/types.h> #include <linux/atomic.h> #include <linux/bitops.h> +#include <acpi/acpi_numa.h> #include <linux/cpumask.h> #include <linux/nmi.h> #include <asm/ptrace.h> @@ -67,6 +68,19 @@ extern u64 hv_do_fast_hypercall8(u16 control, u64 input8); bool hv_isolation_type_snp(void); bool hv_isolation_type_tdx(void); +static inline struct hv_proximity_domain_info hv_numa_node_to_pxm_info(int node) +{ + struct hv_proximity_domain_info pxm_info = {}; + + if (node != NUMA_NO_NODE) { + pxm_info.domain_id = node_to_pxm(node); + pxm_info.flags.proximity_info_valid = 1; + pxm_info.flags.proximity_preferred = 1; + } + + return pxm_info; +} + /* Helper functions that provide a consistent pattern for checking Hyper-V hypercall status. */ static inline int hv_result(u64 status) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 172c91879999..69e7da33ca49 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -128,6 +128,8 @@ typedef unsigned int __bitwise blk_mode_t; #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) /* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ #define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) +/* return partition scanning errors */ +#define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6)) struct gendisk { /* diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index ca73940e26df..3f4b4ac527ca 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -10,6 +10,7 @@ #ifdef __KERNEL__ #include <linux/kernel.h> #include <linux/types.h> +bool __init cmdline_has_extra_options(void); #else /* !__KERNEL__ */ /* * NOTE: This is only for tools/bootconfig, because tools/bootconfig will @@ -287,7 +288,12 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ -void __init xbc_exit(void); +void __init _xbc_exit(bool early); + +static inline void xbc_exit(void) +{ + _xbc_exit(false); +} /* XBC embedded bootconfig data in kernel */ #ifdef CONFIG_BOOT_CONFIG_EMBED diff --git a/include/linux/clk.h b/include/linux/clk.h index 00623f4de5e1..0fa56d672532 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -286,6 +286,11 @@ static inline int clk_rate_exclusive_get(struct clk *clk) return 0; } +static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk) +{ + return 0; +} + static inline void clk_rate_exclusive_put(struct clk *clk) {} #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index c00cc6c0878a..8c252e073bd8 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -268,7 +268,7 @@ static inline void *offset_to_ptr(const int *off) * - When one operand is a null pointer constant (i.e. when x is an integer * constant expression) and the other is an object pointer (i.e. our * third operand), the conditional operator returns the type of the - * object pointer operand (i.e. "int *). Here, within the sizeof(), we + * object pointer operand (i.e. "int *"). Here, within the sizeof(), we * would then get: * sizeof(*((int *)(...)) == sizeof(int) == 4 * - When one operand is a void pointer (i.e. when x is not an integer diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index e06bad467f55..c3f9bb6602ba 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -682,4 +682,11 @@ static inline bool dma_fence_is_container(struct dma_fence *fence) return dma_fence_is_array(fence) || dma_fence_is_chain(fence); } +#define DMA_FENCE_WARN(f, fmt, args...) \ + do { \ + struct dma_fence *__ff = (f); \ + pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\ + ##args); \ + } while (0) + #endif /* __LINUX_DMA_FENCE_H */ diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 224645f17c33..297231854ada 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -608,6 +608,31 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_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/gfp_types.h b/include/linux/gfp_types.h index 868c8fb1bbc1..13becafe41df 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -2,6 +2,8 @@ #ifndef __LINUX_GFP_TYPES_H #define __LINUX_GFP_TYPES_H +#include <linux/bits.h> + /* The typedef is in types.h but we want the documentation here */ #if 0 /** diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h index 6c75c8bd44a0..1a14e239221f 100644 --- a/include/linux/gpio/property.h +++ b/include/linux/gpio/property.h @@ -2,7 +2,6 @@ #ifndef __LINUX_GPIO_PROPERTY_H #define __LINUX_GPIO_PROPERTY_H -#include <dt-bindings/gpio/gpio.h> /* for GPIO_* flags */ #include <linux/property.h> #define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6ef0557b4bff..96ceb4095425 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -832,6 +832,7 @@ struct vmbus_gpadl { u32 gpadl_handle; u32 size; void *buffer; + bool decrypted; }; struct vmbus_channel { diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 05df0e399d7c..ac333ea81d31 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -13,7 +13,7 @@ enum { * A hint to not wake right away but delay until there are enough of * tw's queued to match the number of CQEs the task is waiting for. * - * Must not be used wirh requests generating more than one CQE. + * Must not be used with requests generating more than one CQE. * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set. */ IOU_F_TWQ_LAZY_WAKE = 1, diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 147feebd508c..3f003d5fde53 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -114,7 +114,7 @@ do { \ # define lockdep_softirq_enter() do { } while (0) # define lockdep_softirq_exit() do { } while (0) # define lockdep_hrtimer_enter(__hrtimer) false -# define lockdep_hrtimer_exit(__context) do { } while (0) +# define lockdep_hrtimer_exit(__context) do { (void)(__context); } while (0) # define lockdep_posixtimer_enter() do { } while (0) # define lockdep_posixtimer_exit() do { } while (0) # define lockdep_irq_work_enter(__work) do { } while (0) diff --git a/include/linux/mm.h b/include/linux/mm.h index 0436b919f1c7..7b0ee64225de 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2207,11 +2207,6 @@ static inline int arch_make_folio_accessible(struct folio *folio) */ #include <linux/vmstat.h> -static __always_inline void *lowmem_page_address(const struct page *page) -{ - return page_to_virt(page); -} - #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif @@ -2234,6 +2229,11 @@ void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif +static __always_inline void *lowmem_page_address(const struct page *page) +{ + return page_to_virt(page); +} + #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) diff --git a/include/linux/peci.h b/include/linux/peci.h index 9b3d36aff431..90e241458ef6 100644 --- a/include/linux/peci.h +++ b/include/linux/peci.h @@ -58,7 +58,6 @@ static inline struct peci_controller *to_peci_controller(void *d) /** * struct peci_device - PECI device * @dev: device object to register PECI device to the device model - * @controller: manages the bus segment hosting this PECI device * @info: PECI device characteristics * @info.family: device family * @info.model: device model diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 5d868505a94e..6d92b68efbf6 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -80,7 +80,7 @@ DECLARE_PER_CPU(u32, kstack_offset); if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - offset ^= (rand); \ + offset = ror32(offset, 5) ^ (rand); \ raw_cpu_write(kstack_offset, offset); \ } \ } while (0) diff --git a/include/linux/rwbase_rt.h b/include/linux/rwbase_rt.h index 29c4e4f243e4..f2394a409c9d 100644 --- a/include/linux/rwbase_rt.h +++ b/include/linux/rwbase_rt.h @@ -31,9 +31,9 @@ static __always_inline bool rw_base_is_locked(const struct rwbase_rt *rwb) return atomic_read(&rwb->readers) != READER_BIAS; } -static inline void rw_base_assert_held_write(const struct rwbase_rt *rwb) +static __always_inline bool rw_base_is_write_locked(const struct rwbase_rt *rwb) { - WARN_ON(atomic_read(&rwb->readers) != WRITER_BIAS); + return atomic_read(&rwb->readers) == WRITER_BIAS; } static __always_inline bool rw_base_is_contended(const struct rwbase_rt *rwb) diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 4f1c18992f76..c8b543d428b0 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -167,14 +167,14 @@ static __always_inline int rwsem_is_locked(const struct rw_semaphore *sem) return rw_base_is_locked(&sem->rwbase); } -static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) +static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!rwsem_is_locked(sem)); } -static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) +static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) { - rw_base_assert_held_write(sem); + WARN_ON(!rw_base_is_write_locked(&sem->rwbase)); } static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a4c15db2f5e5..3fb18f7eb73e 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -110,8 +110,17 @@ extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +#else +static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, + struct mm_struct *mm, unsigned long vm_flags) +{ + return false; +} +#endif + #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); #else diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 307961b41541..317200cd3a60 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -50,11 +50,36 @@ static inline int copy_from_sockptr_offset(void *dst, sockptr_t src, return 0; } +/* Deprecated. + * This is unsafe, unless caller checked user provided optlen. + * Prefer copy_safe_from_sockptr() instead. + */ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) { return copy_from_sockptr_offset(dst, src, 0, size); } +/** + * copy_safe_from_sockptr: copy a struct from sockptr + * @dst: Destination address, in kernel space. This buffer must be @ksize + * bytes long. + * @ksize: Size of @dst struct. + * @optval: Source address. (in user or kernel space) + * @optlen: Size of @optval data. + * + * Returns: + * * -EINVAL: @optlen < @ksize + * * -EFAULT: access to userspace failed. + * * 0 : @ksize bytes were copied + */ +static inline int copy_safe_from_sockptr(void *dst, size_t ksize, + sockptr_t optval, unsigned int optlen) +{ + if (optlen < ksize) + return -EINVAL; + return copy_from_sockptr(dst, optval, ksize); +} + static inline int copy_struct_from_sockptr(void *dst, size_t ksize, sockptr_t src, size_t usize) { diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24cd199dd6f3..d33bab33099a 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/swapops.h b/include/linux/swapops.h index 48b700ba1d18..a5c560a2f8c2 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -390,6 +390,35 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) } #endif /* CONFIG_MIGRATION */ +#ifdef CONFIG_MEMORY_FAILURE + +/* + * Support for hardware poisoned pages + */ +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + BUG_ON(!PageLocked(page)); + return swp_entry(SWP_HWPOISON, page_to_pfn(page)); +} + +static inline int is_hwpoison_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_HWPOISON; +} + +#else + +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + return swp_entry(0, 0); +} + +static inline int is_hwpoison_entry(swp_entry_t swp) +{ + return 0; +} +#endif + typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) @@ -483,8 +512,9 @@ static inline struct folio *pfn_swap_entry_folio(swp_entry_t entry) /* * A pfn swap entry is a special type of swap entry that always has a pfn stored - * in the swap offset. They are used to represent unaddressable device memory - * and to restrict access to a page undergoing migration. + * in the swap offset. They can either be used to represent unaddressable device + * memory, to restrict access to a page undergoing migration or to represent a + * pfn which has been hwpoisoned and unmapped. */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { @@ -492,7 +522,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); return is_migration_entry(entry) || is_device_private_entry(entry) || - is_device_exclusive_entry(entry); + is_device_exclusive_entry(entry) || is_hwpoison_entry(entry); } struct page_vma_mapped_walk; @@ -561,35 +591,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd) } #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ -#ifdef CONFIG_MEMORY_FAILURE - -/* - * Support for hardware poisoned pages - */ -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - BUG_ON(!PageLocked(page)); - return swp_entry(SWP_HWPOISON, page_to_pfn(page)); -} - -static inline int is_hwpoison_entry(swp_entry_t entry) -{ - return swp_type(entry) == SWP_HWPOISON; -} - -#else - -static inline swp_entry_t make_hwpoison_entry(struct page *page) -{ - return swp_entry(0, 0); -} - -static inline int is_hwpoison_entry(swp_entry_t swp) -{ - return 0; -} -#endif - static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index ffe48e69b3f3..457879938fc1 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -135,10 +135,11 @@ static inline void u64_stats_inc(u64_stats_t *p) p->v++; } -static inline void u64_stats_init(struct u64_stats_sync *syncp) -{ - seqcount_init(&syncp->seq); -} +#define u64_stats_init(syncp) \ + do { \ + struct u64_stats_sync *__s = (syncp); \ + seqcount_init(&__s->seq); \ + } while (0) static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { diff --git a/include/linux/udp.h b/include/linux/udp.h index 17539d089666..e398e1dbd2d3 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -108,7 +108,7 @@ struct udp_sock { #define udp_assign_bit(nr, sk, val) \ assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) diff --git a/include/linux/virtio.h b/include/linux/virtio.h index b0201747a263..26c4325aa373 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -170,7 +170,7 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev); /** * struct virtio_driver - operations for a virtio I/O driver - * @driver: underlying device driver (populate name and owner). + * @driver: underlying device driver (populate name). * @id_table: the ids serviced by this driver. * @feature_table: an array of feature numbers supported by this driver. * @feature_table_size: number of entries in the feature table array. @@ -208,7 +208,10 @@ static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv) return container_of(drv, struct virtio_driver, driver); } -int register_virtio_driver(struct virtio_driver *drv); +/* use a macro to avoid include chaining to get THIS_MODULE */ +#define register_virtio_driver(drv) \ + __register_virtio_driver(drv, THIS_MODULE) +int __register_virtio_driver(struct virtio_driver *drv, struct module *owner); void unregister_virtio_driver(struct virtio_driver *drv); /* module_virtio_driver() - Helper macro for drivers that don't do diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 9d06eb945509..62a407db1bf5 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -438,6 +438,10 @@ static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) refcount_inc(&ifp->refcnt); } +static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp) +{ + return refcount_inc_not_zero(&ifp->refcnt); +} /* * compute link-local solicited-node multicast address diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 627ea8e2d915..3dee0b2721aa 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/bluetooth.h b/include/net/bluetooth/bluetooth.h index 9fe95a22abeb..eaec5d6caa29 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -585,6 +585,15 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } +static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, + sockptr_t src, size_t src_size) +{ + if (dst_size > src_size) + return -EINVAL; + + return copy_from_sockptr(dst, src, dst_size); +} + int bt_to_errno(u16 code); __u8 bt_status(int err); diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 56fb42df44a3..e8f581f3f3ce 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/ip_tunnels.h b/include/net/ip_tunnels.h index 5cd64bb2104d..c286cc2e766e 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -361,6 +361,39 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb) return pskb_network_may_pull(skb, nhlen); } +/* Variant of pskb_inet_may_pull(). + */ +static inline bool skb_vlan_inet_prepare(struct sk_buff *skb) +{ + int nhlen = 0, maclen = ETH_HLEN; + __be16 type = skb->protocol; + + /* Essentially this is skb_protocol(skb, true) + * And we get MAC len. + */ + if (eth_type_vlan(type)) + type = __vlan_get_protocol(skb, type, &maclen); + + switch (type) { +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + nhlen = sizeof(struct ipv6hdr); + break; +#endif + case htons(ETH_P_IP): + nhlen = sizeof(struct iphdr); + break; + } + /* For ETH_P_IPV6/ETH_P_IP we make sure to pull + * a base network header in skb->head. + */ + if (!pskb_may_pull(skb, maclen + nhlen)) + return false; + + skb_set_network_header(skb, maclen); + return true; +} + static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 353488ab94a2..2d7f87bc5324 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 dbd22180cc5c..de216cbc6b05 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/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index a763dd327c6e..9abb7ee40d72 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -336,7 +336,7 @@ int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, int nf_flow_table_offload_init(void); void nf_flow_table_offload_exit(void); -static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) +static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) { __be16 proto; @@ -352,6 +352,16 @@ static inline __be16 nf_flow_pppoe_proto(const struct sk_buff *skb) return 0; } +static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) +{ + if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) + return false; + + *inner_proto = __nf_flow_pppoe_proto(skb); + + return true; +} + #define NF_FLOW_TABLE_STAT_INC(net, count) __this_cpu_inc((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_DEC(net, count) __this_cpu_dec((net)->ft.stat->count) #define NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count) \ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index e27c28b612e4..3f1ed467f951 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -307,9 +307,23 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) return (void *)priv; } + +/** + * enum nft_iter_type - nftables set iterator type + * + * @NFT_ITER_READ: read-only iteration over set elements + * @NFT_ITER_UPDATE: iteration under mutex to update set element state + */ +enum nft_iter_type { + NFT_ITER_UNSPEC, + NFT_ITER_READ, + NFT_ITER_UPDATE, +}; + struct nft_set; struct nft_set_iter { u8 genmask; + enum nft_iter_type type:8; unsigned int count; unsigned int skip; int err; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index cefe0c4bdae3..41ca14e81d55 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -117,6 +117,7 @@ struct Qdisc { struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; + int owner; unsigned long state; unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; diff --git a/include/net/sock.h b/include/net/sock.h index f57bfd8a2ad2..b4b553df7870 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 340ad43971e4..33f657d3c051 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/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index ba2d96a1bc2f..f50fcafc69de 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -609,7 +609,7 @@ TRACE_EVENT(rpcgss_context, __field(unsigned int, timeout) __field(u32, window_size) __field(int, len) - __string(acceptor, data) + __string_len(acceptor, data, len) ), TP_fast_assign( @@ -618,7 +618,7 @@ TRACE_EVENT(rpcgss_context, __entry->timeout = timeout; __entry->window_size = window_size; __entry->len = len; - strncpy(__get_str(acceptor), data, len); + __assign_str(acceptor, data); ), TP_printk("win_size=%u expiry=%lu now=%lu timeout=%u acceptor=%.*s", diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 43c51698195c..842bf1201ac4 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/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index bea697390613..b95dd84eef2d 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -179,12 +179,6 @@ /* Get the config size */ #define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) -/* Get the count of all virtqueues */ -#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) - -/* Get the number of virtqueue groups. */ -#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) - /* Get the number of address spaces. */ #define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) @@ -228,10 +222,17 @@ #define VHOST_VDPA_GET_VRING_DESC_GROUP _IOWR(VHOST_VIRTIO, 0x7F, \ struct vhost_vring_state) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) + /* Get the queue size of a specific virtqueue. * userspace set the vring index in vhost_vring_state.index * kernel set the queue size in vhost_vring_state.num */ -#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x80, \ +#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x82, \ struct vhost_vring_state) #endif diff --git a/init/main.c b/init/main.c index 2ca52474d0c3..5dcf5274c09c 100644 --- a/init/main.c +++ b/init/main.c @@ -487,6 +487,11 @@ static int __init warn_bootconfig(char *str) early_param("bootconfig", warn_bootconfig); +bool __init cmdline_has_extra_options(void) +{ + return extra_command_line || extra_init_args; +} + /* Change NUL term back to "=", to make "param" the whole string. */ static void __init repair_env_string(char *param, char *val) { @@ -631,6 +636,8 @@ static void __init setup_command_line(char *command_line) if (!saved_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len + ilen); + len = xlen + strlen(command_line) + 1; + static_command_line = memblock_alloc(len, SMP_CACHE_BYTES); if (!static_command_line) panic("%s: Failed to allocate %zu bytes\n", __func__, len); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 4521c2b66b98..c170a2b8d2cf 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2602,19 +2602,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, if (__io_cqring_events_user(ctx) >= min_events) return 0; - if (sig) { -#ifdef CONFIG_COMPAT - if (in_compat_syscall()) - ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, - sigsz); - else -#endif - ret = set_user_sigmask(sig, sigsz); - - if (ret) - return ret; - } - init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; INIT_LIST_HEAD(&iowq.wq.entry); @@ -2633,6 +2620,19 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, io_napi_adjust_timeout(ctx, &iowq, &ts); } + if (sig) { +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, + sigsz); + else +#endif + ret = set_user_sigmask(sig, sigsz); + + if (ret) + return ret; + } + io_napi_busy_loop(ctx, &iowq); trace_io_uring_cqring_wait(ctx, min_events); diff --git a/io_uring/net.c b/io_uring/net.c index 1e7665ff6ef7..4afb475d4197 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1276,6 +1276,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags) if (req_has_async_data(req)) { kmsg = req->async_data; + kmsg->msg.msg_control_user = sr->msg_control; } else { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config index 7a5bbfc024b7..4b4cfcba3190 100644 --- a/kernel/configs/hardening.config +++ b/kernel/configs/hardening.config @@ -39,11 +39,12 @@ CONFIG_UBSAN=y CONFIG_UBSAN_TRAP=y CONFIG_UBSAN_BOUNDS=y # CONFIG_UBSAN_SHIFT is not set -# CONFIG_UBSAN_DIV_ZERO -# CONFIG_UBSAN_UNREACHABLE -# CONFIG_UBSAN_BOOL -# CONFIG_UBSAN_ENUM -# CONFIG_UBSAN_ALIGNMENT +# CONFIG_UBSAN_DIV_ZERO is not set +# CONFIG_UBSAN_UNREACHABLE is not set +# CONFIG_UBSAN_SIGNED_WRAP is not set +# CONFIG_UBSAN_BOOL is not set +# CONFIG_UBSAN_ENUM is not set +# CONFIG_UBSAN_ALIGNMENT is not set # Sampling-based heap out-of-bounds and use-after-free detection. CONFIG_KFENCE=y diff --git a/kernel/cpu.c b/kernel/cpu.c index 8f6affd051f7..07ad53b7f119 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -3207,7 +3207,8 @@ enum cpu_mitigations { }; static enum cpu_mitigations cpu_mitigations __ro_after_init = - CPU_MITIGATIONS_AUTO; + IS_ENABLED(CONFIG_SPECULATION_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : + CPU_MITIGATIONS_OFF; static int __init mitigations_parse_cmdline(char *arg) { diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 86fe172b5958..a5e0dfc44d24 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -69,11 +69,14 @@ * @alloc_size: Size of the allocated buffer. * @list: The free list describing the number of free entries available * from each index. + * @pad_slots: Number of preceding padding slots. Valid only in the first + * allocated non-padding slot. */ struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; - unsigned int list; + unsigned short list; + unsigned short pad_slots; }; static bool swiotlb_force_bounce; @@ -287,6 +290,7 @@ static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start, mem->nslabs - i); mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; + mem->slots[i].pad_slots = 0; } memset(vaddr, 0, bytes); @@ -821,12 +825,30 @@ void swiotlb_dev_init(struct device *dev) #endif } -/* - * Return the offset into a iotlb slot required to keep the device happy. +/** + * swiotlb_align_offset() - Get required offset into an IO TLB allocation. + * @dev: Owning device. + * @align_mask: Allocation alignment mask. + * @addr: DMA address. + * + * Return the minimum offset from the start of an IO TLB allocation which is + * required for a given buffer address and allocation alignment to keep the + * device happy. + * + * First, the address bits covered by min_align_mask must be identical in the + * original address and the bounce buffer address. High bits are preserved by + * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra + * padding bytes before the bounce buffer. + * + * Second, @align_mask specifies which bits of the first allocated slot must + * be zero. This may require allocating additional padding slots, and then the + * offset (in bytes) from the first such padding slot is returned. */ -static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) +static unsigned int swiotlb_align_offset(struct device *dev, + unsigned int align_mask, u64 addr) { - return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); + return addr & dma_get_min_align_mask(dev) & + (align_mask | (IO_TLB_SIZE - 1)); } /* @@ -841,27 +863,23 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start; - unsigned int tlb_offset, orig_addr_offset; + int tlb_offset; if (orig_addr == INVALID_PHYS_ADDR) return; - tlb_offset = tlb_addr & (IO_TLB_SIZE - 1); - orig_addr_offset = swiotlb_align_offset(dev, orig_addr); - if (tlb_offset < orig_addr_offset) { - dev_WARN_ONCE(dev, 1, - "Access before mapping start detected. orig offset %u, requested offset %u.\n", - orig_addr_offset, tlb_offset); - return; - } - - tlb_offset -= orig_addr_offset; - if (tlb_offset > alloc_size) { - dev_WARN_ONCE(dev, 1, - "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n", - alloc_size, size, tlb_offset); - return; - } + /* + * It's valid for tlb_offset to be negative. This can happen when the + * "offset" returned by swiotlb_align_offset() is non-zero, and the + * tlb_addr is pointing within the first "offset" bytes of the second + * or subsequent slots of the allocated swiotlb area. While it's not + * valid for tlb_addr to be pointing within the first "offset" bytes + * of the first slot, there's no way to check for such an error since + * this function can't distinguish the first slot from the second and + * subsequent slots. + */ + tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) - + swiotlb_align_offset(dev, 0, orig_addr); orig_addr += tlb_offset; alloc_size -= tlb_offset; @@ -1005,7 +1023,7 @@ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool unsigned long max_slots = get_max_slots(boundary_mask); unsigned int iotlb_align_mask = dma_get_min_align_mask(dev); unsigned int nslots = nr_slots(alloc_size), stride; - unsigned int offset = swiotlb_align_offset(dev, orig_addr); + unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr); unsigned int index, slots_checked, count = 0, i; unsigned long flags; unsigned int slot_base; @@ -1328,11 +1346,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, unsigned long attrs) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; - unsigned int offset = swiotlb_align_offset(dev, orig_addr); + unsigned int offset; struct io_tlb_pool *pool; unsigned int i; int index; phys_addr_t tlb_addr; + unsigned short pad_slots; if (!mem || !mem->nslabs) { dev_warn_ratelimited(dev, @@ -1349,6 +1368,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, return (phys_addr_t)DMA_MAPPING_ERROR; } + offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr); index = swiotlb_find_slots(dev, orig_addr, alloc_size + offset, alloc_align_mask, &pool); if (index == -1) { @@ -1364,6 +1384,10 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, * This is needed when we sync the memory. Then we sync the buffer if * needed. */ + pad_slots = offset >> IO_TLB_SHIFT; + offset &= (IO_TLB_SIZE - 1); + index += pad_slots; + pool->slots[index].pad_slots = pad_slots; for (i = 0; i < nr_slots(alloc_size + offset); i++) pool->slots[index + i].orig_addr = slot_addr(orig_addr, i); tlb_addr = slot_addr(pool->start, index) + offset; @@ -1384,13 +1408,17 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) { struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr); unsigned long flags; - unsigned int offset = swiotlb_align_offset(dev, tlb_addr); - int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; - int nslots = nr_slots(mem->slots[index].alloc_size + offset); - int aindex = index / mem->area_nslabs; - struct io_tlb_area *area = &mem->areas[aindex]; + unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr); + int index, nslots, aindex; + struct io_tlb_area *area; int count, i; + index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; + index -= mem->slots[index].pad_slots; + nslots = nr_slots(mem->slots[index].alloc_size + offset); + aindex = index / mem->area_nslabs; + area = &mem->areas[aindex]; + /* * Return the buffer to the free list by setting the corresponding * entries to indicate the number of contiguous entries available. @@ -1413,6 +1441,7 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) mem->slots[i].list = ++count; mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; + mem->slots[i].pad_slots = 0; } /* @@ -1647,9 +1676,6 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get, static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, const char *dirname) { - atomic_long_set(&mem->total_used, 0); - atomic_long_set(&mem->used_hiwater, 0); - mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs); if (!mem->nslabs) return; @@ -1660,7 +1686,6 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem, &fops_io_tlb_hiwater); #ifdef CONFIG_SWIOTLB_DYNAMIC - atomic_long_set(&mem->transient_nslabs, 0); debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs, mem, &fops_io_tlb_transient_used); #endif diff --git a/kernel/fork.c b/kernel/fork.c index 39a5046c2f0b..aebb3e6c96dc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -714,6 +714,23 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); + /* + * Copy/update hugetlb private vma information. + */ + if (is_vm_hugetlb_page(tmp)) + hugetlb_dup_vma_private(tmp); + + /* + * Link the vma into the MT. After using __mt_dup(), memory + * allocation is not necessary here, so it cannot fail. + */ + vma_iter_bulk_store(&vmi, tmp); + + mm->map_count++; + + if (tmp->vm_ops && tmp->vm_ops->open) + tmp->vm_ops->open(tmp); + file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; @@ -730,25 +747,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, i_mmap_unlock_write(mapping); } - /* - * Copy/update hugetlb private vma information. - */ - if (is_vm_hugetlb_page(tmp)) - hugetlb_dup_vma_private(tmp); - - /* - * Link the vma into the MT. After using __mt_dup(), memory - * allocation is not necessary here, so it cannot fail. - */ - vma_iter_bulk_store(&vmi, tmp); - - mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); - if (tmp->vm_ops && tmp->vm_ops->open) - tmp->vm_ops->open(tmp); - if (retval) { mpnt = vma_next(&vmi); goto loop_out; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9d9095e81792..65adc815fc6e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1567,10 +1567,17 @@ static int check_kprobe_address_safe(struct kprobe *p, jump_label_lock(); preempt_disable(); - /* Ensure it is not in reserved area nor out of text */ - if (!(core_kernel_text((unsigned long) p->addr) || - is_module_text_address((unsigned long) p->addr)) || - in_gate_area_no_mm((unsigned long) p->addr) || + /* Ensure the address is in a text area, and find a module if exists. */ + *probed_mod = NULL; + if (!core_kernel_text((unsigned long) p->addr)) { + *probed_mod = __module_text_address((unsigned long) p->addr); + if (!(*probed_mod)) { + ret = -EINVAL; + goto out; + } + } + /* Ensure it is not in reserved area. */ + if (in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || @@ -1580,8 +1587,7 @@ static int check_kprobe_address_safe(struct kprobe *p, goto out; } - /* Check if 'p' is probing a module. */ - *probed_mod = __module_text_address((unsigned long) p->addr); + /* Get module refcount and reject __init functions for loaded modules. */ if (*probed_mod) { /* * We must hold a refcount of the probed module while updating diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index e3ae93bbcb9b..09f8397bae15 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -106,6 +106,12 @@ static void s2idle_enter(void) swait_event_exclusive(s2idle_wait_head, s2idle_state == S2IDLE_STATE_WAKE); + /* + * Kick all CPUs to ensure that they resume their timers and restore + * consistent system state. + */ + wake_up_all_idle_cpus(); + cpus_read_unlock(); raw_spin_lock_irq(&s2idle_lock); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d2242679239e..ae50f212775e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -79,6 +79,8 @@ # include <asm/paravirt_api_clock.h> #endif +#include <asm/barrier.h> + #include "cpupri.h" #include "cpudeadline.h" @@ -3445,13 +3447,19 @@ static inline void switch_mm_cid(struct rq *rq, * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu]. * Provide it here. */ - if (!prev->mm) // from kernel + if (!prev->mm) { // from kernel smp_mb(); - /* - * user -> user transition guarantees a memory barrier through - * switch_mm() when current->mm changes. If current->mm is - * unchanged, no barrier is needed. - */ + } else { // from user + /* + * user->user transition relies on an implicit + * memory barrier in switch_mm() when + * current->mm changes. If the architecture + * switch_mm() does not have an implicit memory + * barrier, it is emitted here. If current->mm + * is unchanged, no barrier is needed. + */ + smp_mb__after_switch_mm(); + } } if (prev->mm_cid_active) { mm_cid_snapshot_time(rq, prev->mm); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index fb0fdec8719a..d88b13076b79 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -7,6 +7,7 @@ * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> @@ -84,7 +85,7 @@ int tick_is_oneshot_available(void) */ static void tick_periodic(int cpu) { - if (tick_do_timer_cpu == cpu) { + if (READ_ONCE(tick_do_timer_cpu) == cpu) { raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); @@ -215,8 +216,8 @@ static void tick_setup_device(struct tick_device *td, * If no cpu took the do_timer update, assign it to * this cpu: */ - if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { - tick_do_timer_cpu = cpu; + if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) { + WRITE_ONCE(tick_do_timer_cpu, cpu); tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* @@ -232,7 +233,7 @@ static void tick_setup_device(struct tick_device *td, !tick_nohz_full_cpu(cpu)) { tick_take_do_timer_from_boot(); tick_do_timer_boot_cpu = -1; - WARN_ON(tick_do_timer_cpu != cpu); + WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu); #endif } @@ -406,10 +407,10 @@ void tick_assert_timekeeping_handover(void) int tick_cpu_dying(unsigned int dying_cpu) { /* - * If the current CPU is the timekeeper, it's the only one that - * can safely hand over its duty. Also all online CPUs are in - * stop machine, guaranteed not to be idle, therefore it's safe - * to pick any online successor. + * If the current CPU is the timekeeper, it's the only one that can + * safely hand over its duty. Also all online CPUs are in stop + * machine, guaranteed not to be idle, therefore there is no + * concurrency and it's safe to pick any online successor. */ if (tick_do_timer_cpu == dying_cpu) tick_do_timer_cpu = cpumask_first(cpu_online_mask); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 1331216a9cae..71a792cd8936 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -8,6 +8,7 @@ * * Started by: Thomas Gleixner and Ingo Molnar */ +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> @@ -204,7 +205,7 @@ static inline void tick_sched_flag_clear(struct tick_sched *ts, static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { - int cpu = smp_processor_id(); + int tick_cpu, cpu = smp_processor_id(); /* * Check if the do_timer duty was dropped. We don't care about @@ -216,16 +217,18 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) * If nohz_full is enabled, this should not happen because the * 'tick_do_timer_cpu' CPU never relinquishes. */ - if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && - unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { + tick_cpu = READ_ONCE(tick_do_timer_cpu); + + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && unlikely(tick_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif - tick_do_timer_cpu = cpu; + WRITE_ONCE(tick_do_timer_cpu, cpu); + tick_cpu = cpu; } /* Check if jiffies need an update */ - if (tick_do_timer_cpu == cpu) + if (tick_cpu == cpu) tick_do_update_jiffies64(now); /* @@ -610,7 +613,7 @@ bool tick_nohz_cpu_hotpluggable(unsigned int cpu) * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ - if (tick_nohz_full_running && tick_do_timer_cpu == cpu) + if (tick_nohz_full_running && READ_ONCE(tick_do_timer_cpu) == cpu) return false; return true; } @@ -891,6 +894,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, delta, expires; unsigned long basejiff; + int tick_cpu; basemono = get_jiffies_update(&basejiff); ts->last_jiffies = basejiff; @@ -947,9 +951,9 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); - if (cpu != tick_do_timer_cpu && - (tick_do_timer_cpu != TICK_DO_TIMER_NONE || - !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) + tick_cpu = READ_ONCE(tick_do_timer_cpu); + if (tick_cpu != cpu && + (tick_cpu != TICK_DO_TIMER_NONE || !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) delta = KTIME_MAX; /* Calculate the next expiry time */ @@ -970,6 +974,7 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) unsigned long basejiff = ts->last_jiffies; u64 basemono = ts->timer_expires_base; bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED); + int tick_cpu; u64 expires; /* Make sure we won't be trying to stop it twice in a row. */ @@ -1007,10 +1012,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) * do_timer() never gets invoked. Keep track of the fact that it * was the one which had the do_timer() duty last. */ - if (cpu == tick_do_timer_cpu) { - tick_do_timer_cpu = TICK_DO_TIMER_NONE; + tick_cpu = READ_ONCE(tick_do_timer_cpu); + if (tick_cpu == cpu) { + WRITE_ONCE(tick_do_timer_cpu, TICK_DO_TIMER_NONE); tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST); - } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { + } else if (tick_cpu != TICK_DO_TIMER_NONE) { tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST); } @@ -1173,15 +1179,17 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; if (tick_nohz_full_enabled()) { + int tick_cpu = READ_ONCE(tick_do_timer_cpu); + /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around */ - if (tick_do_timer_cpu == cpu) + if (tick_cpu == cpu) return false; /* Should not happen for nohz-full */ - if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) + if (WARN_ON_ONCE(tick_cpu == TICK_DO_TIMER_NONE)) return false; } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 61c541c36596..47345bf1d4a9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -965,7 +965,7 @@ config FTRACE_RECORD_RECURSION config FTRACE_RECORD_RECURSION_SIZE int "Max number of recursed functions to record" - default 128 + default 128 depends on FTRACE_RECORD_RECURSION help This defines the limit of number of functions that can be diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 25476ead681b..6511dc3a00da 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1393,7 +1393,6 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write); old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries); - local_inc(&cpu_buffer->pages_touched); /* * Just make sure we have seen our old_write and synchronize * with any interrupts that come in. @@ -1430,8 +1429,9 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, */ local_set(&next_page->page->commit, 0); - /* Again, either we update tail_page or an interrupt does */ - (void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page); + /* Either we update tail_page or an interrupt does */ + if (try_cmpxchg(&cpu_buffer->tail_page, &tail_page, next_page)) + local_inc(&cpu_buffer->pages_touched); } } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7c364b87352e..52f75c36bbca 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1670,6 +1670,7 @@ static int trace_format_open(struct inode *inode, struct file *file) return 0; } +#ifdef CONFIG_PERF_EVENTS static ssize_t event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { @@ -1684,6 +1685,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } +#endif static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, @@ -2152,10 +2154,12 @@ static const struct file_operations ftrace_event_format_fops = { .release = seq_release, }; +#ifdef CONFIG_PERF_EVENTS static const struct file_operations ftrace_event_id_fops = { .read = event_id_read, .llseek = default_llseek, }; +#endif static const struct file_operations ftrace_event_filter_fops = { .open = tracing_open_file_tr, diff --git a/lib/bootconfig.c b/lib/bootconfig.c index c59d26068a64..97f8911ea339 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -61,9 +61,12 @@ static inline void * __init xbc_alloc_mem(size_t size) return memblock_alloc(size, SMP_CACHE_BYTES); } -static inline void __init xbc_free_mem(void *addr, size_t size) +static inline void __init xbc_free_mem(void *addr, size_t size, bool early) { - memblock_free(addr, size); + if (early) + memblock_free(addr, size); + else if (addr) + memblock_free_late(__pa(addr), size); } #else /* !__KERNEL__ */ @@ -73,7 +76,7 @@ static inline void *xbc_alloc_mem(size_t size) return malloc(size); } -static inline void xbc_free_mem(void *addr, size_t size) +static inline void xbc_free_mem(void *addr, size_t size, bool early) { free(addr); } @@ -898,19 +901,20 @@ static int __init xbc_parse_tree(void) } /** - * xbc_exit() - Clean up all parsed bootconfig + * _xbc_exit() - Clean up all parsed bootconfig + * @early: Set true if this is called before budy system is initialized. * * This clears all data structures of parsed bootconfig on memory. * If you need to reuse xbc_init() with new boot config, you can * use this. */ -void __init xbc_exit(void) +void __init _xbc_exit(bool early) { - xbc_free_mem(xbc_data, xbc_data_size); + xbc_free_mem(xbc_data, xbc_data_size, early); xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); + xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX, early); xbc_nodes = NULL; brace_index = 0; } @@ -963,7 +967,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) if (!xbc_nodes) { if (emsg) *emsg = "Failed to allocate bootconfig nodes"; - xbc_exit(); + _xbc_exit(true); return -ENOMEM; } memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX); @@ -977,7 +981,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) *epos = xbc_err_pos; if (emsg) *emsg = xbc_err_msg; - xbc_exit(); + _xbc_exit(true); } else ret = xbc_node_num; diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c index bf70850035c7..404dba36bae3 100644 --- a/lib/checksum_kunit.c +++ b/lib/checksum_kunit.c @@ -594,13 +594,15 @@ static void test_ip_fast_csum(struct kunit *test) static void test_csum_ipv6_magic(struct kunit *test) { -#if defined(CONFIG_NET) const struct in6_addr *saddr; const struct in6_addr *daddr; unsigned int len; unsigned char proto; __wsum csum; + if (!IS_ENABLED(CONFIG_NET)) + return; + const int daddr_offset = sizeof(struct in6_addr); const int len_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr); const int proto_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr) + @@ -618,7 +620,6 @@ static void test_csum_ipv6_magic(struct kunit *test) CHECK_EQ(to_sum16(expected_csum_ipv6_magic[i]), csum_ipv6_magic(saddr, daddr, len, proto, csum)); } -#endif /* !CONFIG_NET */ } static struct kunit_case __refdata checksum_test_cases[] = { diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c index 276c12140ee2..c288df9372ed 100644 --- a/lib/test_ubsan.c +++ b/lib/test_ubsan.c @@ -134,7 +134,7 @@ static const test_ubsan_fp test_ubsan_array[] = { }; /* Excluded because they Oops the module. */ -static const test_ubsan_fp skip_ubsan_array[] = { +static __used const test_ubsan_fp skip_ubsan_array[] = { test_ubsan_divrem_overflow, }; diff --git a/lib/ubsan.c b/lib/ubsan.c index 5fc107f61934..a1c983d148f1 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -44,9 +44,10 @@ const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type) case ubsan_shift_out_of_bounds: return "UBSAN: shift out of bounds"; #endif -#ifdef CONFIG_UBSAN_DIV_ZERO +#if defined(CONFIG_UBSAN_DIV_ZERO) || defined(CONFIG_UBSAN_SIGNED_WRAP) /* - * SanitizerKind::IntegerDivideByZero emits + * SanitizerKind::IntegerDivideByZero and + * SanitizerKind::SignedIntegerOverflow emit * SanitizerHandler::DivremOverflow. */ case ubsan_divrem_overflow: @@ -78,6 +79,19 @@ const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type) case ubsan_type_mismatch: return "UBSAN: type mismatch"; #endif +#ifdef CONFIG_UBSAN_SIGNED_WRAP + /* + * SanitizerKind::SignedIntegerOverflow emits + * SanitizerHandler::AddOverflow, SanitizerHandler::SubOverflow, + * or SanitizerHandler::MulOverflow. + */ + case ubsan_add_overflow: + return "UBSAN: integer addition overflow"; + case ubsan_sub_overflow: + return "UBSAN: integer subtraction overflow"; + case ubsan_mul_overflow: + return "UBSAN: integer multiplication overflow"; +#endif default: return "UBSAN: unrecognized failure code"; } @@ -1206,6 +1206,22 @@ static long __get_user_pages(struct mm_struct *mm, /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { + /* + * MADV_POPULATE_(READ|WRITE) wants to handle VMA + * lookups+error reporting differently. + */ + if (gup_flags & FOLL_MADV_POPULATE) { + vma = vma_lookup(mm, start); + if (!vma) { + ret = -ENOMEM; + goto out; + } + if (check_vma_flags(vma, gup_flags)) { + ret = -EINVAL; + goto out; + } + goto retry; + } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, @@ -1685,35 +1701,35 @@ long populate_vma_page_range(struct vm_area_struct *vma, } /* - * faultin_vma_page_range() - populate (prefault) page tables inside the - * given VMA range readable/writable + * faultin_page_range() - populate (prefault) page tables inside the + * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * - * @vma: target vma + * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * - * Returns either number of processed pages in the vma, or a negative error - * code on error (see __get_user_pages()). + * Returns either number of processed pages in the MM, or a negative error + * code on error (see __get_user_pages()). Note that this function reports + * errors related to VMAs, such as incompatible mappings, as expected by + * MADV_POPULATE_(READ|WRITE). * - * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and - * covered by the VMA. If it's released, *@locked will be set to 0. + * The range must be page-aligned. + * + * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ -long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, bool write, int *locked) +long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked) { - struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); - VM_BUG_ON_VMA(start < vma->vm_start, vma); - VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* @@ -1725,19 +1741,13 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ - gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE; + gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | + FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; - /* - * We want to report -EINVAL instead of -EFAULT for any permission - * problems or incompatible mappings. - */ - if (check_vma_flags(vma, gup_flags)) - return -EINVAL; - - ret = __get_user_pages(mm, start, nr_pages, gup_flags, - NULL, locked); + ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, + gup_flags); lru_add_drain(); return ret; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9859aa4f7553..89f58c7603b2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2259,9 +2259,6 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } - folio_move_anon_rmap(src_folio, dst_vma); - WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); - src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { @@ -2270,6 +2267,9 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } + folio_move_anon_rmap(src_folio, dst_vma); + WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 23ef240ba48a..31d00eee028f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7044,9 +7044,13 @@ long hugetlb_change_protection(struct vm_area_struct *vma, if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { - /* No other markers apply for now. */ - WARN_ON_ONCE(!pte_marker_uffd_wp(pte)); - if (uffd_wp_resolve) + /* + * Do nothing on a poison marker; page is + * corrupted, permissons do not apply. Here + * pte_marker_uffd_wp()==true implies !poison + * because they're mutual exclusive. + */ + if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { diff --git a/mm/internal.h b/mm/internal.h index 7e486f2c502c..07ad2675a88b 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -686,9 +686,8 @@ struct anon_vma *folio_anon_vma(struct folio *folio); void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); -extern long faultin_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, - bool write, int *locked); +extern long faultin_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); @@ -1127,10 +1126,13 @@ enum { FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, + /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ + FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ - FOLL_FAST_ONLY | FOLL_UNLOCKABLE) + FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ + FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, diff --git a/mm/madvise.c b/mm/madvise.c index 44a498c94158..1a073fcc4c0c 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -908,27 +908,14 @@ static long madvise_populate(struct vm_area_struct *vma, { const bool write = behavior == MADV_POPULATE_WRITE; struct mm_struct *mm = vma->vm_mm; - unsigned long tmp_end; int locked = 1; long pages; *prev = vma; while (start < end) { - /* - * We might have temporarily dropped the lock. For example, - * our VMA might have been split. - */ - if (!vma || start >= vma->vm_end) { - vma = vma_lookup(mm, start); - if (!vma) - return -ENOMEM; - } - - tmp_end = min_t(unsigned long, end, vma->vm_end); /* Populate (prefault) page tables readable/writable. */ - pages = faultin_vma_page_range(vma, start, tmp_end, write, - &locked); + pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; @@ -949,7 +936,7 @@ static long madvise_populate(struct vm_area_struct *vma, pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; - case -ENOMEM: + case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9349948f1abf..9e62a00b46dd 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -154,11 +154,23 @@ static int __page_handle_poison(struct page *page) { int ret; - zone_pcp_disable(page_zone(page)); + /* + * zone_pcp_disable() can't be used here. It will + * hold pcp_batch_high_lock and dissolve_free_huge_page() might hold + * cpu_hotplug_lock via static_key_slow_dec() when hugetlb vmemmap + * optimization is enabled. This will break current lock dependency + * chain and leads to deadlock. + * Disabling pcp before dissolving the page was a deterministic + * approach because we made sure that those pages cannot end up in any + * PCP list. Draining PCP lists expels those pages to the buddy system, + * but nothing guarantees that those pages do not get back to a PCP + * queue if we need to refill those. + */ ret = dissolve_free_huge_page(page); - if (!ret) + if (!ret) { + drain_all_pages(page_zone(page)); ret = take_page_off_buddy(page); - zone_pcp_enable(page_zone(page)); + } return ret; } diff --git a/mm/page_owner.c b/mm/page_owner.c index d17d1351ec84..742f432e5bf0 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -118,7 +118,6 @@ static __init void init_page_owner(void) register_dummy_stack(); register_failure_stack(); register_early_stack(); - static_branch_enable(&page_owner_inited); init_early_allocated_pages(); /* Initialize dummy and failure stacks and link them to stack_list */ dummy_stack.stack_record = __stack_depot_get_stack_record(dummy_handle); @@ -129,6 +128,7 @@ static __init void init_page_owner(void) refcount_set(&failure_stack.stack_record->count, 1); dummy_stack.next = &failure_stack; stack_list = &dummy_stack; + static_branch_enable(&page_owner_inited); } struct page_ext_operations page_owner_ops = { @@ -196,7 +196,8 @@ static void add_stack_record_to_list(struct stack_record *stack_record, spin_unlock_irqrestore(&stack_list_lock, flags); } -static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask) +static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask, + int nr_base_pages) { struct stack_record *stack_record = __stack_depot_get_stack_record(handle); @@ -217,20 +218,74 @@ static void inc_stack_record_count(depot_stack_handle_t handle, gfp_t gfp_mask) /* Add the new stack_record to our list */ add_stack_record_to_list(stack_record, gfp_mask); } - refcount_inc(&stack_record->count); + refcount_add(nr_base_pages, &stack_record->count); } -static void dec_stack_record_count(depot_stack_handle_t handle) +static void dec_stack_record_count(depot_stack_handle_t handle, + int nr_base_pages) { struct stack_record *stack_record = __stack_depot_get_stack_record(handle); - if (stack_record) - refcount_dec(&stack_record->count); + if (!stack_record) + return; + + if (refcount_sub_and_test(nr_base_pages, &stack_record->count)) + pr_warn("%s: refcount went to 0 for %u handle\n", __func__, + handle); } -void __reset_page_owner(struct page *page, unsigned short order) +static inline void __update_page_owner_handle(struct page_ext *page_ext, + depot_stack_handle_t handle, + unsigned short order, + gfp_t gfp_mask, + short last_migrate_reason, u64 ts_nsec, + pid_t pid, pid_t tgid, char *comm) { int i; + struct page_owner *page_owner; + + for (i = 0; i < (1 << order); i++) { + page_owner = get_page_owner(page_ext); + page_owner->handle = handle; + page_owner->order = order; + page_owner->gfp_mask = gfp_mask; + page_owner->last_migrate_reason = last_migrate_reason; + page_owner->pid = pid; + page_owner->tgid = tgid; + page_owner->ts_nsec = ts_nsec; + strscpy(page_owner->comm, comm, + sizeof(page_owner->comm)); + __set_bit(PAGE_EXT_OWNER, &page_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_ext = page_ext_next(page_ext); + } +} + +static inline void __update_page_owner_free_handle(struct page_ext *page_ext, + depot_stack_handle_t handle, + unsigned short order, + pid_t pid, pid_t tgid, + u64 free_ts_nsec) +{ + int i; + struct page_owner *page_owner; + + for (i = 0; i < (1 << order); i++) { + page_owner = get_page_owner(page_ext); + /* Only __reset_page_owner() wants to clear the bit */ + if (handle) { + __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_owner->free_handle = handle; + } + page_owner->free_ts_nsec = free_ts_nsec; + page_owner->free_pid = current->pid; + page_owner->free_tgid = current->tgid; + page_ext = page_ext_next(page_ext); + } +} + +void __reset_page_owner(struct page *page, unsigned short order) +{ struct page_ext *page_ext; depot_stack_handle_t handle; depot_stack_handle_t alloc_handle; @@ -245,16 +300,10 @@ void __reset_page_owner(struct page *page, unsigned short order) alloc_handle = page_owner->handle; handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); - for (i = 0; i < (1 << order); i++) { - __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - page_owner->free_handle = handle; - page_owner->free_ts_nsec = free_ts_nsec; - page_owner->free_pid = current->pid; - page_owner->free_tgid = current->tgid; - page_ext = page_ext_next(page_ext); - page_owner = get_page_owner(page_ext); - } + __update_page_owner_free_handle(page_ext, handle, order, current->pid, + current->tgid, free_ts_nsec); page_ext_put(page_ext); + if (alloc_handle != early_handle) /* * early_handle is being set as a handle for all those @@ -263,39 +312,14 @@ void __reset_page_owner(struct page *page, unsigned short order) * the machinery is not ready yet, we cannot decrement * their refcount either. */ - dec_stack_record_count(alloc_handle); -} - -static inline void __set_page_owner_handle(struct page_ext *page_ext, - depot_stack_handle_t handle, - unsigned short order, gfp_t gfp_mask) -{ - struct page_owner *page_owner; - int i; - u64 ts_nsec = local_clock(); - - for (i = 0; i < (1 << order); i++) { - page_owner = get_page_owner(page_ext); - page_owner->handle = handle; - page_owner->order = order; - page_owner->gfp_mask = gfp_mask; - page_owner->last_migrate_reason = -1; - page_owner->pid = current->pid; - page_owner->tgid = current->tgid; - page_owner->ts_nsec = ts_nsec; - strscpy(page_owner->comm, current->comm, - sizeof(page_owner->comm)); - __set_bit(PAGE_EXT_OWNER, &page_ext->flags); - __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - - page_ext = page_ext_next(page_ext); - } + dec_stack_record_count(alloc_handle, 1 << order); } noinline void __set_page_owner(struct page *page, unsigned short order, gfp_t gfp_mask) { struct page_ext *page_ext; + u64 ts_nsec = local_clock(); depot_stack_handle_t handle; handle = save_stack(gfp_mask); @@ -303,9 +327,11 @@ noinline void __set_page_owner(struct page *page, unsigned short order, page_ext = page_ext_get(page); if (unlikely(!page_ext)) return; - __set_page_owner_handle(page_ext, handle, order, gfp_mask); + __update_page_owner_handle(page_ext, handle, order, gfp_mask, -1, + current->pid, current->tgid, ts_nsec, + current->comm); page_ext_put(page_ext); - inc_stack_record_count(handle, gfp_mask); + inc_stack_record_count(handle, gfp_mask, 1 << order); } void __set_page_owner_migrate_reason(struct page *page, int reason) @@ -340,9 +366,12 @@ void __split_page_owner(struct page *page, int old_order, int new_order) void __folio_copy_owner(struct folio *newfolio, struct folio *old) { + int i; struct page_ext *old_ext; struct page_ext *new_ext; - struct page_owner *old_page_owner, *new_page_owner; + struct page_owner *old_page_owner; + struct page_owner *new_page_owner; + depot_stack_handle_t migrate_handle; old_ext = page_ext_get(&old->page); if (unlikely(!old_ext)) @@ -356,30 +385,32 @@ void __folio_copy_owner(struct folio *newfolio, struct folio *old) old_page_owner = get_page_owner(old_ext); new_page_owner = get_page_owner(new_ext); - new_page_owner->order = old_page_owner->order; - new_page_owner->gfp_mask = old_page_owner->gfp_mask; - new_page_owner->last_migrate_reason = - old_page_owner->last_migrate_reason; - new_page_owner->handle = old_page_owner->handle; - new_page_owner->pid = old_page_owner->pid; - new_page_owner->tgid = old_page_owner->tgid; - new_page_owner->free_pid = old_page_owner->free_pid; - new_page_owner->free_tgid = old_page_owner->free_tgid; - new_page_owner->ts_nsec = old_page_owner->ts_nsec; - new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; - strcpy(new_page_owner->comm, old_page_owner->comm); - + migrate_handle = new_page_owner->handle; + __update_page_owner_handle(new_ext, old_page_owner->handle, + old_page_owner->order, old_page_owner->gfp_mask, + old_page_owner->last_migrate_reason, + old_page_owner->ts_nsec, old_page_owner->pid, + old_page_owner->tgid, old_page_owner->comm); + /* + * Do not proactively clear PAGE_EXT_OWNER{_ALLOCATED} bits as the folio + * will be freed after migration. Keep them until then as they may be + * useful. + */ + __update_page_owner_free_handle(new_ext, 0, old_page_owner->order, + old_page_owner->free_pid, + old_page_owner->free_tgid, + old_page_owner->free_ts_nsec); /* - * We don't clear the bit on the old folio as it's going to be freed - * after migration. Until then, the info can be useful in case of - * a bug, and the overall stats will be off a bit only temporarily. - * Also, migrate_misplaced_transhuge_page() can still fail the - * migration and then we want the old folio to retain the info. But - * in that case we also don't need to explicitly clear the info from - * the new page, which will be freed. + * We linked the original stack to the new folio, we need to do the same + * for the new one and the old folio otherwise there will be an imbalance + * when subtracting those pages from the stack. */ - __set_bit(PAGE_EXT_OWNER, &new_ext->flags); - __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); + for (i = 0; i < (1 << new_page_owner->order); i++) { + old_page_owner->handle = migrate_handle; + old_ext = page_ext_next(old_ext); + old_page_owner = get_page_owner(old_ext); + } + page_ext_put(new_ext); page_ext_put(old_ext); } @@ -787,8 +818,9 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) goto ext_put_continue; /* Found early allocated page */ - __set_page_owner_handle(page_ext, early_handle, - 0, 0); + __update_page_owner_handle(page_ext, early_handle, 0, 0, + -1, local_clock(), current->pid, + current->tgid, current->comm); count++; ext_put_continue: page_ext_put(page_ext); @@ -840,13 +872,11 @@ static void *stack_start(struct seq_file *m, loff_t *ppos) * value of stack_list. */ stack = smp_load_acquire(&stack_list); + m->private = stack; } else { stack = m->private; - stack = stack->next; } - m->private = stack; - return stack; } @@ -861,11 +891,11 @@ static void *stack_next(struct seq_file *m, void *v, loff_t *ppos) return stack; } -static unsigned long page_owner_stack_threshold; +static unsigned long page_owner_pages_threshold; static int stack_print(struct seq_file *m, void *v) { - int i, stack_count; + int i, nr_base_pages; struct stack *stack = v; unsigned long *entries; unsigned long nr_entries; @@ -876,14 +906,14 @@ static int stack_print(struct seq_file *m, void *v) nr_entries = stack_record->size; entries = stack_record->entries; - stack_count = refcount_read(&stack_record->count) - 1; + nr_base_pages = refcount_read(&stack_record->count) - 1; - if (stack_count < 1 || stack_count < page_owner_stack_threshold) + if (nr_base_pages < 1 || nr_base_pages < page_owner_pages_threshold) return 0; for (i = 0; i < nr_entries; i++) seq_printf(m, " %pS\n", (void *)entries[i]); - seq_printf(m, "stack_count: %d\n\n", stack_count); + seq_printf(m, "nr_base_pages: %d\n\n", nr_base_pages); return 0; } @@ -913,13 +943,13 @@ static const struct file_operations page_owner_stack_operations = { static int page_owner_threshold_get(void *data, u64 *val) { - *val = READ_ONCE(page_owner_stack_threshold); + *val = READ_ONCE(page_owner_pages_threshold); return 0; } static int page_owner_threshold_set(void *data, u64 val) { - WRITE_ONCE(page_owner_stack_threshold, val); + WRITE_ONCE(page_owner_pages_threshold, val); return 0; } diff --git a/mm/shmem.c b/mm/shmem.c index 0aad0d9a621b..94ab99b6b574 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -748,12 +748,6 @@ static long shmem_unused_huge_count(struct super_block *sb, #define shmem_huge SHMEM_HUGE_DENY -bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, - struct mm_struct *mm, unsigned long vm_flags) -{ - return false; -} - static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 558e158c98d0..9169efb2f43a 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -103,7 +103,7 @@ again: s->ax25_dev = NULL; if (sk->sk_socket) { netdev_put(ax25_dev->dev, - &ax25_dev->dev_tracker); + &s->dev_tracker); ax25_dev_put(ax25_dev); } ax25_cb_del(s); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b95c36765d04..2243cec18ecc 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -3948,7 +3948,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface) spin_lock_bh(&bat_priv->tt.commit_lock); - while (true) { + while (timeout) { table_size = batadv_tt_local_table_transmit_size(bat_priv); if (packet_size_max >= table_size) break; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3ad74f76983b..05346250f719 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 a8b8cfebe018..4a27e4a17a67 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_request.c b/net/bluetooth/hci_request.c index 00e02138003e..efea25eb56ce 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -105,8 +105,10 @@ void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (hdev->req_status == HCI_REQ_PEND) { hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; - if (skb) + if (skb) { + kfree_skb(hdev->req_skb); hdev->req_skb = skb_get(skb); + } wake_up_interruptible(&hdev->req_wait_q); } } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 4ee1b976678b..703b84bd48d5 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1946,10 +1946,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, switch (optname) { case HCI_DATA_DIR: - if (copy_from_sockptr(&opt, optval, sizeof(opt))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + if (err) break; - } if (opt) hci_pi(sk)->cmsg_mask |= HCI_CMSG_DIR; @@ -1958,10 +1957,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, break; case HCI_TIME_STAMP: - if (copy_from_sockptr(&opt, optval, sizeof(opt))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + if (err) break; - } if (opt) hci_pi(sk)->cmsg_mask |= HCI_CMSG_TSTAMP; @@ -1979,11 +1977,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, uf.event_mask[1] = *((u32 *) f->event_mask + 1); } - len = min_t(unsigned int, len, sizeof(uf)); - if (copy_from_sockptr(&uf, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&uf, sizeof(uf), optval, len); + if (err) break; - } if (!capable(CAP_NET_RAW)) { uf.type_mask &= hci_sec_filter.type_mask; @@ -2042,10 +2038,9 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname, goto done; } - if (copy_from_sockptr(&opt, optval, sizeof(opt))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + if (err) break; - } hci_pi(sk)->mtu = opt; break; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 8fe02921adf1..4c707eb64e6f 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2814,8 +2814,8 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, if (qos->bcast.in.phy & BT_ISO_PHY_CODED) { cp->scanning_phys |= LE_SCAN_PHY_CODED; hci_le_scan_phy_params(phy, type, - interval, - window); + interval * 3, + window * 3); num_phy++; phy++; } @@ -2835,7 +2835,7 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, if (scan_coded(hdev)) { cp->scanning_phys |= LE_SCAN_PHY_CODED; - hci_le_scan_phy_params(phy, type, interval, window); + hci_le_scan_phy_params(phy, type, interval * 3, window * 3); num_phy++; phy++; } @@ -6346,7 +6346,8 @@ 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/iso.c b/net/bluetooth/iso.c index c8793e57f4b5..ef0cc80b4c0c 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1451,8 +1451,8 @@ static bool check_ucast_qos(struct bt_iso_qos *qos) static bool check_bcast_qos(struct bt_iso_qos *qos) { - if (qos->bcast.sync_factor == 0x00) - return false; + if (!qos->bcast.sync_factor) + qos->bcast.sync_factor = 0x01; if (qos->bcast.packing > 0x01) return false; @@ -1475,6 +1475,9 @@ static bool check_bcast_qos(struct bt_iso_qos *qos) if (qos->bcast.skip > 0x01f3) return false; + if (!qos->bcast.sync_timeout) + qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; + if (qos->bcast.sync_timeout < 0x000a || qos->bcast.sync_timeout > 0x4000) return false; @@ -1484,6 +1487,9 @@ static bool check_bcast_qos(struct bt_iso_qos *qos) if (qos->bcast.mse > 0x1f) return false; + if (!qos->bcast.timeout) + qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; + if (qos->bcast.timeout < 0x000a || qos->bcast.timeout > 0x4000) return false; @@ -1494,7 +1500,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - int len, err = 0; + int err = 0; struct bt_iso_qos qos = default_qos; u32 opt; @@ -1509,10 +1515,9 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -1521,10 +1526,9 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); @@ -1539,17 +1543,9 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - len = min_t(unsigned int, sizeof(qos), optlen); - - if (copy_from_sockptr(&qos, optval, len)) { - err = -EFAULT; - break; - } - - if (len == sizeof(qos.ucast) && !check_ucast_qos(&qos)) { - err = -EINVAL; + err = bt_copy_from_sockptr(&qos, sizeof(qos), optval, optlen); + if (err) break; - } iso_pi(sk)->qos = qos; iso_pi(sk)->qos_user_set = true; @@ -1564,18 +1560,16 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, } if (optlen > sizeof(iso_pi(sk)->base)) { - err = -EOVERFLOW; + err = -EINVAL; break; } - len = min_t(unsigned int, sizeof(iso_pi(sk)->base), optlen); - - if (copy_from_sockptr(iso_pi(sk)->base, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(iso_pi(sk)->base, optlen, optval, + optlen); + if (err) break; - } - iso_pi(sk)->base_len = len; + iso_pi(sk)->base_len = optlen; break; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 467b242d8be0..84fc70862d78 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4054,8 +4054,7 @@ static int l2cap_connect_req(struct l2cap_conn *conn, return -EPROTO; hci_dev_lock(hdev); - if (hci_dev_test_flag(hdev, HCI_MGMT) && - !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags)) + if (hci_dev_test_flag(hdev, HCI_MGMT)) mgmt_device_connected(hdev, hcon, NULL, 0); hci_dev_unlock(hdev); @@ -7019,7 +7018,7 @@ 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 4287aa6cc988..5cc83f906c12 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; @@ -727,7 +728,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; - int len, err = 0; + int err = 0; u32 opt; BT_DBG("sk %p", sk); @@ -754,11 +755,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, opts.max_tx = chan->max_tx; opts.txwin_size = chan->tx_win; - len = min_t(unsigned int, sizeof(opts), optlen); - if (copy_from_sockptr(&opts, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen); + if (err) break; - } if (opts.txwin_size > L2CAP_DEFAULT_EXT_WINDOW) { err = -EINVAL; @@ -801,10 +800,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; case L2CAP_LM: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt & L2CAP_LM_FIPS) { err = -EINVAL; @@ -885,7 +883,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, struct bt_security sec; struct bt_power pwr; struct l2cap_conn *conn; - int len, err = 0; + int err = 0; u32 opt; u16 mtu; u8 mode; @@ -911,11 +909,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - len = min_t(unsigned int, sizeof(sec), optlen); - if (copy_from_sockptr(&sec, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + if (err) break; - } if (sec.level < BT_SECURITY_LOW || sec.level > BT_SECURITY_FIPS) { @@ -960,10 +956,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) { set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -975,10 +970,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_FLUSHABLE: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt > BT_FLUSHABLE_ON) { err = -EINVAL; @@ -1010,11 +1004,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, pwr.force_active = BT_POWER_FORCE_ACTIVE_ON; - len = min_t(unsigned int, sizeof(pwr), optlen); - if (copy_from_sockptr(&pwr, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen); + if (err) break; - } if (pwr.force_active) set_bit(FLAG_FORCE_ACTIVE, &chan->flags); @@ -1023,10 +1015,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_CHANNEL_POLICY: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } err = -EOPNOTSUPP; break; @@ -1055,10 +1046,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&mtu, optval, sizeof(u16))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen); + if (err) break; - } if (chan->mode == L2CAP_MODE_EXT_FLOWCTL && sk->sk_state == BT_CONNECTED) @@ -1086,10 +1076,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&mode, optval, sizeof(u8))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen); + if (err) break; - } BT_DBG("mode %u", mode); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 32ed6e9245a3..965f621ef865 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 @@ update_class: 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/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index b54e8a530f55..29aa07e9db9d 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -629,7 +629,7 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, switch (optname) { case RFCOMM_LM: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { + if (bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen)) { err = -EFAULT; break; } @@ -664,7 +664,6 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct bt_security sec; int err = 0; - size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -686,11 +685,9 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - len = min_t(unsigned int, sizeof(sec), optlen); - if (copy_from_sockptr(&sec, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + if (err) break; - } if (sec.level > BT_SECURITY_HIGH) { err = -EINVAL; @@ -706,10 +703,9 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 43daf965a01e..5d03c5440b06 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -824,7 +824,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - int len, err = 0; + int err = 0; struct bt_voice voice; u32 opt; struct bt_codecs *codecs; @@ -843,10 +843,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -863,11 +862,10 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, voice.setting = sco_pi(sk)->setting; - len = min_t(unsigned int, sizeof(voice), optlen); - if (copy_from_sockptr(&voice, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, + optlen); + if (err) break; - } /* Explicitly check for these values */ if (voice.setting != BT_VOICE_TRANSPARENT && @@ -890,10 +888,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); @@ -934,9 +931,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(buffer, optval, optlen)) { + err = bt_copy_from_sockptr(buffer, optlen, optval, optlen); + if (err) { hci_dev_put(hdev); - err = -EFAULT; break; } @@ -967,7 +964,8 @@ 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); @@ -989,7 +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; @@ -1007,7 +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_input.c b/net/bridge/br_input.c index f21097e73482..ceaa5a89b947 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -30,7 +30,7 @@ br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) return netif_receive_skb(skb); } -static int br_pass_frame_up(struct sk_buff *skb) +static int br_pass_frame_up(struct sk_buff *skb, bool promisc) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); @@ -65,6 +65,8 @@ static int br_pass_frame_up(struct sk_buff *skb) br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb), BR_MCAST_DIR_TX); + BR_INPUT_SKB_CB(skb)->promisc = promisc; + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(indev), NULL, skb, indev, NULL, br_netif_receive_skb); @@ -82,6 +84,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_mcast *brmctx; struct net_bridge_vlan *vlan; struct net_bridge *br; + bool promisc; u16 vid = 0; u8 state; @@ -137,7 +140,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (p->flags & BR_LEARNING) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, 0); - local_rcv = !!(br->dev->flags & IFF_PROMISC); + promisc = !!(br->dev->flags & IFF_PROMISC); + local_rcv = promisc; + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) { @@ -200,7 +205,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb unsigned long now = jiffies; if (test_bit(BR_FDB_LOCAL, &dst->flags)) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, false); if (now != dst->used) dst->used = now; @@ -213,7 +218,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb } if (local_rcv) - return br_pass_frame_up(skb); + return br_pass_frame_up(skb, promisc); out: return 0; @@ -386,6 +391,8 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto forward; } + BR_INPUT_SKB_CB(skb)->promisc = false; + /* The else clause should be hit when nf_hook(): * - returns < 0 (drop/error) * - returns = 0 (stolen/nf_queue) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 35e10c5a766d..22e35623c148 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -600,11 +600,17 @@ static unsigned int br_nf_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; struct nf_conntrack *nfct = skb_nfct(skb); const struct nf_ct_hook *ct_hook; struct nf_conn *ct; int ret; + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 2cf4fc756263..f17dbac7d828 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/bridge/br_private.h b/net/bridge/br_private.h index 86ea5e6689b5..d4bedc87b1d8 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -589,6 +589,7 @@ struct br_input_skb_cb { #endif u8 proxyarp_replied:1; u8 src_port_isolated:1; + u8 promisc:1; #ifdef CONFIG_BRIDGE_VLAN_FILTERING u8 vlan_filtered:1; #endif diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 6f877e31709b..c3c51b9a6826 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -294,18 +294,24 @@ static unsigned int nf_ct_bridge_pre(void *priv, struct sk_buff *skb, static unsigned int nf_ct_bridge_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - enum ip_conntrack_info ctinfo; + bool promisc = BR_INPUT_SKB_CB(skb)->promisc; + struct nf_conntrack *nfct = skb_nfct(skb); struct nf_conn *ct; - if (skb->pkt_type == PACKET_HOST) + if (promisc) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + + if (!nfct || skb->pkt_type == PACKET_HOST) return NF_ACCEPT; /* nf_conntrack_confirm() cannot handle concurrent clones, * this happens for broad/multicast frames with e.g. macvlan on top * of the bridge device. */ - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) + ct = container_of(nfct, struct nf_conn, ct_general); + if (nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) return NF_ACCEPT; /* let inet prerouting call conntrack again */ diff --git a/net/core/dev.c b/net/core/dev.c index 984ff8b9d0e1..331848eca7d3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3775,6 +3775,10 @@ no_lock_out: return rc; } + if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { + kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); + return NET_XMIT_DROP; + } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. @@ -3814,7 +3818,9 @@ no_lock_out: qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { + WRITE_ONCE(q->owner, smp_processor_id()); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); + WRITE_ONCE(q->owner, -1); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 2edc8b796a4e..049c3adeb850 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/fib_frontend.c b/net/ipv4/fib_frontend.c index 48741352a88a..c484b1c0fc00 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1050,6 +1050,11 @@ next: e++; } } + + /* Don't let NLM_DONE coalesce into a message, even if it could. + * Some user space expects NLM_DONE in a separate recv(). + */ + err = skb->len; out: cb->args[1] = e; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index e63a3bf99617..437e782b9663 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -92,6 +92,7 @@ #include <net/inet_common.h> #include <net/ip_fib.h> #include <net/l3mdev.h> +#include <net/addrconf.h> /* * Build xmit assembly blocks @@ -1032,6 +1033,8 @@ 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/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index b150c9929b12..14365b20f1c5 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -966,6 +966,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1266,6 +1268,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 487670759578..fe89a056eb06 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1118,6 +1118,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1504,6 +1506,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c8f76f56dc16..b814fdab19f7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -926,13 +926,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; -#ifdef CONFIG_IP_ROUTE_VERBOSE - if (log_martians && + if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); -#endif } out_put_peer: inet_putpeer(peer); @@ -2168,6 +2166,9 @@ int 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 3afeeb68e8a7..781b67a52571 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 c02bf011d4a6..420905be5f30 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1123,16 +1123,17 @@ 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/ipv6/addrconf.c b/net/ipv6/addrconf.c index 92db9b474f2b..779aa6ecdd49 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2091,9 +2091,10 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { - result = ifp; - in6_ifa_hold(ifp); - break; + if (in6_ifa_hold_safe(ifp)) { + result = ifp; + break; + } } } } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7209419cfb0e..c1f62352a481 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1385,7 +1385,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; - struct fib6_node *fn, *pn = NULL; + struct fib6_node *fn; +#ifdef CONFIG_IPV6_SUBTREES + struct fib6_node *pn = NULL; +#endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; @@ -1409,9 +1412,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, goto out; } +#ifdef CONFIG_IPV6_SUBTREES pn = fn; -#ifdef CONFIG_IPV6_SUBTREES if (rt->fib6_src.plen) { struct fib6_node *sn; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 636b360311c5..131f7bb2110d 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1135,6 +1135,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1513,6 +1515,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8b1dd7f51249..1a4cccdd40c9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1474,9 +1474,11 @@ do_udp_sendmsg: 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 +1490,6 @@ do_udp_sendmsg: } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; - connected = false; } if (!opt) { opt = txopt_get(np); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 80e4b9784131..ccacaed32817 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 @@ out: 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 32475da98d73..cbc9b5e40cb3 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 d913ce7ba72e..3f9664e4e00c 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -135,9 +135,38 @@ struct mesh_path { #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 91b55d6a68b9..a6b62169f084 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 96b70006b7fc..3bbb216a0fc8 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 @@ again: 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 @@ again: break; } - conn->mode = ap_mode; chanreq->oper = ap_chandef; /* wider-bandwidth OFDMA is only done in EHT */ @@ -753,8 +758,10 @@ again: } /* 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 23404b275457..4dc1def69548 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 c1f850138405..6e24864f9a40 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 0429e59ba387..73850312580f 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 6bf223e6cd1a..cfd0a62d0152 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/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index a0921adc31a9..1e689c714127 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/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 9505f9d188ff..6eef15648b7b 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -21,7 +21,8 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, proto = veth->h_vlan_encapsulated_proto; break; case htons(ETH_P_PPP_SES): - proto = nf_flow_pppoe_proto(skb); + if (!nf_flow_pppoe_proto(skb, &proto)) + return NF_ACCEPT; break; default: proto = skb->protocol; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index e45fade76409..5383bed3d3e0 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -157,7 +157,7 @@ static void nf_flow_tuple_encap(struct sk_buff *skb, tuple->encap[i].proto = skb->protocol; break; case htons(ETH_P_PPP_SES): - phdr = (struct pppoe_hdr *)skb_mac_header(skb); + phdr = (struct pppoe_hdr *)skb_network_header(skb); tuple->encap[i].id = ntohs(phdr->sid); tuple->encap[i].proto = skb->protocol; break; @@ -273,10 +273,11 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } -static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, +static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, u32 *offset) { struct vlan_ethhdr *veth; + __be16 inner_proto; switch (skb->protocol) { case htons(ETH_P_8021Q): @@ -287,7 +288,8 @@ static bool nf_flow_skb_encap_protocol(const struct sk_buff *skb, __be16 proto, } break; case htons(ETH_P_PPP_SES): - if (nf_flow_pppoe_proto(skb) == proto) { + if (nf_flow_pppoe_proto(skb, &inner_proto) && + inner_proto == proto) { *offset += PPPOE_SES_HLEN; return true; } @@ -316,7 +318,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb, skb_reset_network_header(skb); break; case htons(ETH_P_PPP_SES): - skb->protocol = nf_flow_pppoe_proto(skb); + skb->protocol = __nf_flow_pppoe_proto(skb); skb_pull(skb, PPPOE_SES_HLEN); skb_reset_network_header(skb); break; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d89d77946719..167074283ea9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -594,6 +594,12 @@ static int nft_mapelem_deactivate(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + + nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, elem_priv); return 0; @@ -617,6 +623,7 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; + nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); break; } @@ -626,6 +633,7 @@ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, .fn = nft_mapelem_deactivate, }; @@ -3060,7 +3068,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, { const struct nft_expr_type *type, *candidate = NULL; - list_for_each_entry(type, &nf_tables_expressions, list) { + list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; @@ -3092,9 +3100,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); + rcu_read_lock(); type = __nft_expr_type_get(family, nla); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -3875,6 +3887,9 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_data *data; int err; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; @@ -3898,17 +3913,20 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { - u8 genmask = nft_genmask_next(ctx->net); + struct nft_set_iter dummy_iter = { + .genmask = nft_genmask_next(ctx->net), + }; struct nft_set_elem_catchall *catchall; + struct nft_set_ext *ext; int ret = 0; list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) + if (!nft_set_elem_active(ext, dummy_iter.genmask)) continue; - ret = nft_setelem_validate(ctx, set, NULL, catchall->elem); + ret = nft_setelem_validate(ctx, set, &dummy_iter, catchall->elem); if (ret < 0) return ret; } @@ -5397,6 +5415,11 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + return nft_setelem_data_validate(ctx, set, elem_priv); } @@ -5441,6 +5464,7 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, } iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; @@ -5488,6 +5512,13 @@ static int nft_mapelem_activate(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + + /* called from abort path, reverse check to undo changes. */ + if (nft_set_elem_active(ext, iter->genmask)) + return 0; + + nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, elem_priv); return 0; @@ -5505,6 +5536,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; + nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); break; } @@ -5514,6 +5546,7 @@ static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, .fn = nft_mapelem_activate, }; @@ -5778,6 +5811,9 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext)) return 0; @@ -5888,6 +5924,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) args.skb = skb; args.reset = dump_ctx->reset; args.iter.genmask = nft_genmask_cur(net); + args.iter.type = NFT_ITER_READ; args.iter.skip = cb->args[0]; args.iter.count = 0; args.iter.err = 0; @@ -6627,7 +6664,7 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_setelem_is_catchall(set, elem_priv)) { - nft_set_elem_change_active(net, set, ext); + nft_clear(net, ext); } else { set->ops->activate(net, set, elem_priv); } @@ -7186,6 +7223,16 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) } } +static int nft_setelem_active_next(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + u8 genmask = nft_genmask_next(net); + + return nft_set_elem_active(ext, genmask); +} + static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) @@ -7309,8 +7356,12 @@ static int nft_setelem_flush(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_elem_priv *elem_priv) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_trans *trans; + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, sizeof(struct nft_trans_elem), GFP_ATOMIC); if (!trans) @@ -7372,6 +7423,7 @@ static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { struct nft_set_iter iter = { .genmask = genmask, + .type = NFT_ITER_UPDATE, .fn = nft_setelem_flush, }; @@ -7607,7 +7659,7 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family) { const struct nft_object_type *type; - list_for_each_entry(type, &nf_tables_objects, list) { + list_for_each_entry_rcu(type, &nf_tables_objects, list) { if (type->family != NFPROTO_UNSPEC && type->family != family) continue; @@ -7623,9 +7675,13 @@ nft_obj_type_get(struct net *net, u32 objtype, u8 family) { const struct nft_object_type *type; + rcu_read_lock(); type = __nft_obj_type_get(objtype, family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -10598,8 +10654,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_setelem_data_activate(net, te->set, te->elem_priv); - nft_setelem_activate(net, te->set, te->elem_priv); + if (!nft_setelem_active_next(net, te->set, te->elem_priv)) { + nft_setelem_data_activate(net, te->set, te->elem_priv); + nft_setelem_activate(net, te->set, te->elem_priv); + } if (!nft_setelem_is_catchall(te->set, te->elem_priv)) te->set->ndeact--; @@ -10787,6 +10845,9 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); + if (!nft_set_elem_active(ext, iter->genmask)) + return 0; + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) return 0; @@ -10871,6 +10932,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, continue; iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 274b6f7e6bb5..d170758a1eb5 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/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index a0055f510e31..b314ca728a29 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -216,6 +216,7 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, return 0; iter.genmask = nft_genmask_next(ctx->net); + iter.type = NFT_ITER_UPDATE; iter.skip = 0; iter.count = 0; iter.err = 0; diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 32df7a16835d..1caa04619dc6 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -172,7 +172,7 @@ static void nft_bitmap_activate(const struct net *net, nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 11 state. */ priv->bitmap[idx] |= (genmask << off); - nft_set_elem_change_active(net, set, &be->ext); + nft_clear(net, &be->ext); } static void nft_bitmap_flush(const struct net *net, @@ -222,8 +222,6 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, list_for_each_entry_rcu(be, &priv->list, head) { if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&be->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &be->priv); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6968a3b34236..daa56dda737a 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -199,7 +199,7 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, { struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &he->ext); + nft_clear(net, &he->ext); } static void nft_rhash_flush(const struct net *net, @@ -286,8 +286,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) @@ -599,7 +597,7 @@ static void nft_hash_activate(const struct net *net, const struct nft_set *set, { struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &he->ext); + nft_clear(net, &he->ext); } static void nft_hash_flush(const struct net *net, @@ -652,8 +650,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, hlist_for_each_entry_rcu(he, &priv->table[i], node) { if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&he->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index df8de5090246..187138afac45 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1847,7 +1847,7 @@ static void nft_pipapo_activate(const struct net *net, { struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &e->ext); + nft_clear(net, &e->ext); } /** @@ -2077,6 +2077,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -2089,16 +2091,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** @@ -2115,13 +2119,15 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_pipapo *priv = nft_set_priv(set); - struct net *net = read_pnet(&set->net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; unsigned int i, r; + WARN_ON_ONCE(iter->type != NFT_ITER_READ && + iter->type != NFT_ITER_UPDATE); + rcu_read_lock(); - if (iter->genmask == nft_genmask_cur(net)) + if (iter->type == NFT_ITER_READ) m = rcu_dereference(priv->match); else m = priv->clone; @@ -2143,9 +2149,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; - if (!nft_set_elem_active(&e->ext, iter->genmask)) - goto cont; - iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) goto out; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 9944fe479e53..b7ea21327549 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -532,7 +532,7 @@ static void nft_rbtree_activate(const struct net *net, { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); - nft_set_elem_change_active(net, set, &rbe->ext); + nft_clear(net, &rbe->ext); } static void nft_rbtree_flush(const struct net *net, @@ -600,8 +600,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (!nft_set_elem_active(&rbe->ext, iter->genmask)) - goto cont; iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 819157bbb5a2..d5344563e525 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -252,10 +252,10 @@ static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = copy_safe_from_sockptr(&opt, sizeof(opt), + optval, optlen); + if (err) break; - } if (opt > LLCP_MAX_RW) { err = -EINVAL; @@ -274,10 +274,10 @@ static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = copy_safe_from_sockptr(&opt, sizeof(opt), + optval, optlen); + if (err) break; - } if (opt > LLCP_MAX_MIUX) { err = -EINVAL; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 3019a4406ca4..2928c142a2dd 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1380,8 +1380,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) - pr_info_ratelimited("Failed to associated timeout " - "policy `%s'\n", ct_info.timeout); + OVS_NLERR(log, + "Failed to associated timeout policy '%s'", + ct_info.timeout); else ct_info.nf_ct_timeout = rcu_dereference( nf_ct_timeout_find(ct_info.ct)->timeout); @@ -1592,9 +1593,9 @@ 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/sched/sch_generic.c b/net/sched/sch_generic.c index ff5336493777..4a2c763e2d11 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -974,6 +974,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; + sch->owner = -1; netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index f2a100c4c81f..40797114d50a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -231,28 +231,6 @@ static void svc_rdma_write_info_free(struct svc_rdma_write_info *info) } /** - * svc_rdma_write_chunk_release - Release Write chunk I/O resources - * @rdma: controlling transport - * @ctxt: Send context that is being released - */ -void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt) -{ - struct svc_rdma_write_info *info; - struct svc_rdma_chunk_ctxt *cc; - - while (!list_empty(&ctxt->sc_write_info_list)) { - info = list_first_entry(&ctxt->sc_write_info_list, - struct svc_rdma_write_info, wi_list); - list_del(&info->wi_list); - - cc = &info->wi_cc; - svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); - svc_rdma_write_info_free(info); - } -} - -/** * svc_rdma_reply_chunk_release - Release Reply chunk I/O resources * @rdma: controlling transport * @ctxt: Send context that is being released @@ -308,11 +286,13 @@ 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 @@ out_err: } /** - * 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 dfca39abd16c..bb5436b719e0 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/tls/tls.h b/net/tls/tls.h index 762f424ff2d5..e5e47452308a 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 ca1e0e198ceb..5df08d848b5c 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/af_unix.c b/net/unix/af_unix.c index 5b41e2321209..9a6ad5974dff 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2663,9 +2663,13 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, WRITE_ONCE(u->oob_skb, NULL); consume_skb(skb); } - } else if (!(flags & MSG_PEEK)) { + } else if (flags & MSG_PEEK) { + skb = NULL; + } else { skb_unlink(skb, &sk->sk_receive_queue); - consume_skb(skb); + WRITE_ONCE(u->oob_skb, NULL); + if (!WARN_ON_ONCE(skb_unref(skb))) + kfree_skb(skb); skb = skb_peek(&sk->sk_receive_queue); } } @@ -2739,18 +2743,16 @@ redo: last = skb = skb_peek(&sk->sk_receive_queue); last_len = last ? last->len : 0; +again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) if (skb) { skb = manage_oob(skb, sk, flags, copied); - if (!skb) { + if (!skb && copied) { unix_state_unlock(sk); - if (copied) - break; - goto redo; + break; } } #endif -again: if (skb == NULL) { if (copied >= target) goto unlock; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index fa39b6265238..0104be9d4704 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -274,11 +274,22 @@ static void __unix_gc(struct work_struct *work) * receive queues. Other, non candidate sockets _can_ be * added to queue, so we must make sure only to touch * candidates. + * + * Embryos, though never candidates themselves, affect which + * candidates are reachable by the garbage collector. Before + * being added to a listener's queue, an embryo may already + * receive data carrying SCM_RIGHTS, potentially making the + * passed socket a candidate that is not yet reachable by the + * collector. It becomes reachable once the embryo is + * enqueued. Therefore, we must ensure that no SCM-laden + * embryo appears in a (candidate) listener's queue between + * consecutive scan_children() calls. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { + struct sock *sk = &u->sk; long total_refs; - total_refs = file_count(u->sk.sk_socket->file); + total_refs = file_count(sk->sk_socket->file); WARN_ON_ONCE(!u->inflight); WARN_ON_ONCE(total_refs < u->inflight); @@ -286,6 +297,11 @@ static void __unix_gc(struct work_struct *work) list_move_tail(&u->link, &gc_candidates); __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); + + if (sk->sk_state == TCP_LISTEN) { + unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); + unix_state_unlock(sk); + } } } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b4edba6b0b7b..30ff9a470813 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 cbbf347c6b2e..df013c98b80d 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/net/xdp/xsk.c b/net/xdp/xsk.c index 3404d076a8a3..727aa20be4bd 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1417,6 +1417,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, struct xsk_queue **q; int entries; + if (optlen < sizeof(entries)) + return -EINVAL; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c index c5c2ce113c92..d20c47d21ad8 100644 --- a/scripts/gcc-plugins/stackleak_plugin.c +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -467,6 +467,8 @@ static bool stackleak_gate(void) return false; if (STRING_EQUAL(section, ".entry.text")) return false; + if (STRING_EQUAL(section, ".head.text")) + return false; } return track_frame_size >= 0; diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index b141024830ec..ee6ac649df83 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -428,7 +428,7 @@ static int cvt_ump_midi2_to_midi1(struct snd_seq_client *dest, midi1->note.group = midi2->note.group; midi1->note.status = midi2->note.status; midi1->note.channel = midi2->note.channel; - switch (midi2->note.status << 4) { + switch (midi2->note.status) { case UMP_MSG_STATUS_NOTE_ON: case UMP_MSG_STATUS_NOTE_OFF: midi1->note.note = midi2->note.note; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index cdcb28aa9d7b..70d80b6af3fe 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7467,6 +7467,10 @@ enum { ALC285_FIXUP_CS35L56_I2C_2, ALC285_FIXUP_CS35L56_I2C_4, ALC285_FIXUP_ASUS_GA403U, + ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC, + ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC, + ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1 }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -9690,6 +9694,38 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_asus_ga403u, }, + [ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1 + }, + [ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC, + }, + [ALC285_FIXUP_ASUS_GU605_SPI_2_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_CS35L56_SPI_2 + }, + [ALC285_FIXUP_ASUS_GA403U_I2C_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_GA403U, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -10084,6 +10120,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), @@ -10143,7 +10181,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), - SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U), + SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2), @@ -10151,7 +10189,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), - SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_CS35L56_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), @@ -10228,6 +10266,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x152d, 0x1082, "Quanta NL3", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x152d, 0x1262, "Huawei NBLB-WAX9N", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1558, 0x0353, "Clevo V35[05]SN[CDE]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1323, "Clevo N130ZU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x1325, "Clevo N15[01][CW]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -10333,6 +10372,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x222e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2231, "Thinkpad T560", ALC292_FIXUP_TPT460), SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC292_FIXUP_TPT460), + SND_PCI_QUIRK(0x17aa, 0x2234, "Thinkpad ICE-1", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x2245, "Thinkpad T470", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2246, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), SND_PCI_QUIRK(0x17aa, 0x2247, "Thinkpad", ALC298_FIXUP_TPT470_DOCK), @@ -10394,8 +10434,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a8, "Y780P AMD VECO dual", ALC287_FIXUP_TAS2781_I2C), - SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2), - SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x38a9, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x38ab, "Thinkbook 16P", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38b4, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38b5, "Legion Slim 7 16IRH8", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x38b6, "Legion Slim 7 16APH8", ALC287_FIXUP_CS35L41_I2C_2), @@ -10457,6 +10497,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 48dae3339305..75f7674c66ee 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -514,10 +514,10 @@ static int tas2563_save_calibration(struct tasdevice_priv *tas_priv) static void tas2781_apply_calib(struct tasdevice_priv *tas_priv) { static const unsigned char page_array[CALIB_MAX] = { - 0x17, 0x18, 0x18, 0x0d, 0x18 + 0x17, 0x18, 0x18, 0x13, 0x18, }; static const unsigned char rgno_array[CALIB_MAX] = { - 0x74, 0x0c, 0x14, 0x3c, 0x7c + 0x74, 0x0c, 0x14, 0x70, 0x7c, }; unsigned char *data; int i, j, rc; diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 7c7493cb571f..52f076afeb96 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -61,6 +61,7 @@ #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 #define ARM_CPU_IMP_AMPERE 0xC0 +#define ARM_CPU_IMP_MICROSOFT 0x6D #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -135,6 +136,8 @@ #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -193,6 +196,7 @@ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 89d2fc872d9f..964df31da975 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -37,9 +37,7 @@ #include <asm/ptrace.h> #include <asm/sve_context.h> -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_READONLY_MEM #define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -76,11 +74,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ - KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK __GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ - KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK __GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 @@ -162,6 +160,11 @@ struct kvm_sync_regs { __u64 device_irq_level; }; +/* Bits for run->s.regs.device_irq_level */ +#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) +#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) +#define KVM_ARM_DEV_PMU (1 << 2) + /* * PMU filter structure. Describe a range of events with a particular * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER. diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 9f18fa090f1f..1691297a766a 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -28,7 +28,6 @@ #define __KVM_HAVE_PPC_SMT #define __KVM_HAVE_IRQCHIP #define __KVM_HAVE_IRQ_LINE -#define __KVM_HAVE_GUEST_DEBUG /* Not always available, but if it is, this is the correct offset. */ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -733,4 +732,48 @@ struct kvm_ppc_xive_eq { #define KVM_XIVE_TIMA_PAGE_OFFSET 0 #define KVM_XIVE_ESB_PAGE_OFFSET 4 +/* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + +struct kvm_ppc_pvinfo { + /* out */ + __u32 flags; + __u32 hcall[4]; + __u8 pad[108]; +}; + +/* for KVM_PPC_GET_SMMU_INFO */ +#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 + +struct kvm_ppc_one_page_size { + __u32 page_shift; /* Page shift (or 0) */ + __u32 pte_enc; /* Encoding in the HPTE (>>12) */ +}; + +struct kvm_ppc_one_seg_page_size { + __u32 page_shift; /* Base page shift of segment (or 0) */ + __u32 slb_enc; /* SLB encoding for BookS */ + struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 +#define KVM_PPC_1T_SEGMENTS 0x00000002 +#define KVM_PPC_NO_HASH 0x00000004 + +struct kvm_ppc_smmu_info { + __u64 flags; + __u32 slb_size; + __u16 data_keys; /* # storage keys supported for data */ + __u16 instr_keys; /* # storage keys supported for instructions */ + struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; +}; + +/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ +struct kvm_ppc_resize_hpt { + __u64 flags; + __u32 shift; + __u32 pad; +}; + #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index abe926d43cbe..05eaf6db3ad4 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -12,7 +12,320 @@ #include <linux/types.h> #define __KVM_S390 -#define __KVM_HAVE_GUEST_DEBUG + +struct kvm_s390_skeys { + __u64 start_gfn; + __u64 count; + __u64 skeydata_addr; + __u32 flags; + __u32 reserved[9]; +}; + +#define KVM_S390_CMMA_PEEK (1 << 0) + +/** + * kvm_s390_cmma_log - Used for CMMA migration. + * + * Used both for input and output. + * + * @start_gfn: Guest page number to start from. + * @count: Size of the result buffer. + * @flags: Control operation mode via KVM_S390_CMMA_* flags + * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty + * pages are still remaining. + * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set + * in the PGSTE. + * @values: Pointer to the values buffer. + * + * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. + */ +struct kvm_s390_cmma_log { + __u64 start_gfn; + __u32 count; + __u32 flags; + union { + __u64 remaining; + __u64 mask; + }; + __u64 values; +}; + +#define KVM_S390_RESET_POR 1 +#define KVM_S390_RESET_CLEAR 2 +#define KVM_S390_RESET_SUBSYSTEM 4 +#define KVM_S390_RESET_CPU_INIT 8 +#define KVM_S390_RESET_IPL 16 + +/* for KVM_S390_MEM_OP */ +struct kvm_s390_mem_op { + /* in */ + __u64 gaddr; /* the guest address */ + __u64 flags; /* flags */ + __u32 size; /* amount of bytes */ + __u32 op; /* type of operation */ + __u64 buf; /* buffer in userspace */ + union { + struct { + __u8 ar; /* the access register number */ + __u8 key; /* access key, ignored if flag unset */ + __u8 pad1[6]; /* ignored */ + __u64 old_addr; /* ignored if cmpxchg flag unset */ + }; + __u32 sida_offset; /* offset into the sida */ + __u8 reserved[32]; /* ignored */ + }; +}; +/* types for kvm_s390_mem_op->op */ +#define KVM_S390_MEMOP_LOGICAL_READ 0 +#define KVM_S390_MEMOP_LOGICAL_WRITE 1 +#define KVM_S390_MEMOP_SIDA_READ 2 +#define KVM_S390_MEMOP_SIDA_WRITE 3 +#define KVM_S390_MEMOP_ABSOLUTE_READ 4 +#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 +#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 + +/* flags for kvm_s390_mem_op->flags */ +#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) +#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) +#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) + +/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ +#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) +#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) + +struct kvm_s390_psw { + __u64 mask; + __u64 addr; +}; + +/* valid values for type in kvm_s390_interrupt */ +#define KVM_S390_SIGP_STOP 0xfffe0000u +#define KVM_S390_PROGRAM_INT 0xfffe0001u +#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u +#define KVM_S390_RESTART 0xfffe0003u +#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u +#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u +#define KVM_S390_MCHK 0xfffe1000u +#define KVM_S390_INT_CLOCK_COMP 0xffff1004u +#define KVM_S390_INT_CPU_TIMER 0xffff1005u +#define KVM_S390_INT_VIRTIO 0xffff2603u +#define KVM_S390_INT_SERVICE 0xffff2401u +#define KVM_S390_INT_EMERGENCY 0xffff1201u +#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u +/* Anything below 0xfffe0000u is taken by INT_IO */ +#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ + (((schid)) | \ + ((ssid) << 16) | \ + ((cssid) << 18) | \ + ((ai) << 26)) +#define KVM_S390_INT_IO_MIN 0x00000000u +#define KVM_S390_INT_IO_MAX 0xfffdffffu +#define KVM_S390_INT_IO_AI_MASK 0x04000000u + + +struct kvm_s390_interrupt { + __u32 type; + __u32 parm; + __u64 parm64; +}; + +struct kvm_s390_io_info { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; +}; + +struct kvm_s390_ext_info { + __u32 ext_params; + __u32 pad; + __u64 ext_params2; +}; + +struct kvm_s390_pgm_info { + __u64 trans_exc_code; + __u64 mon_code; + __u64 per_address; + __u32 data_exc_code; + __u16 code; + __u16 mon_class_nr; + __u8 per_code; + __u8 per_atmid; + __u8 exc_access_id; + __u8 per_access_id; + __u8 op_access_id; +#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 +#define KVM_S390_PGM_FLAGS_ILC_0 0x02 +#define KVM_S390_PGM_FLAGS_ILC_1 0x04 +#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 +#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 + __u8 flags; + __u8 pad[2]; +}; + +struct kvm_s390_prefix_info { + __u32 address; +}; + +struct kvm_s390_extcall_info { + __u16 code; +}; + +struct kvm_s390_emerg_info { + __u16 code; +}; + +#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 +struct kvm_s390_stop_info { + __u32 flags; +}; + +struct kvm_s390_mchk_info { + __u64 cr14; + __u64 mcic; + __u64 failing_storage_address; + __u32 ext_damage_code; + __u32 pad; + __u8 fixed_logout[16]; +}; + +struct kvm_s390_irq { + __u64 type; + union { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_stop_info stop; + struct kvm_s390_mchk_info mchk; + char reserved[64]; + } u; +}; + +struct kvm_s390_irq_state { + __u64 buf; + __u32 flags; /* will stay unused for compatibility reasons */ + __u32 len; + __u32 reserved[4]; /* will stay unused for compatibility reasons */ +}; + +struct kvm_s390_ucas_mapping { + __u64 user_addr; + __u64 vcpu_addr; + __u64 length; +}; + +struct kvm_s390_pv_sec_parm { + __u64 origin; + __u64 length; +}; + +struct kvm_s390_pv_unp { + __u64 addr; + __u64 size; + __u64 tweak; +}; + +enum pv_cmd_dmp_id { + KVM_PV_DUMP_INIT, + KVM_PV_DUMP_CONFIG_STOR_STATE, + KVM_PV_DUMP_COMPLETE, + KVM_PV_DUMP_CPU, +}; + +struct kvm_s390_pv_dmp { + __u64 subcmd; + __u64 buff_addr; + __u64 buff_len; + __u64 gaddr; /* For dump storage state */ + __u64 reserved[4]; +}; + +enum pv_cmd_info_id { + KVM_PV_INFO_VM, + KVM_PV_INFO_DUMP, +}; + +struct kvm_s390_pv_info_dump { + __u64 dump_cpu_buffer_len; + __u64 dump_config_mem_buffer_per_1m; + __u64 dump_config_finalize_len; +}; + +struct kvm_s390_pv_info_vm { + __u64 inst_calls_list[4]; + __u64 max_cpus; + __u64 max_guests; + __u64 max_guest_addr; + __u64 feature_indication; +}; + +struct kvm_s390_pv_info_header { + __u32 id; + __u32 len_max; + __u32 len_written; + __u32 reserved; +}; + +struct kvm_s390_pv_info { + struct kvm_s390_pv_info_header header; + union { + struct kvm_s390_pv_info_dump dump; + struct kvm_s390_pv_info_vm vm; + }; +}; + +enum pv_cmd_id { + KVM_PV_ENABLE, + KVM_PV_DISABLE, + KVM_PV_SET_SEC_PARMS, + KVM_PV_UNPACK, + KVM_PV_VERIFY, + KVM_PV_PREP_RESET, + KVM_PV_UNSHARE_ALL, + KVM_PV_INFO, + KVM_PV_DUMP, + KVM_PV_ASYNC_CLEANUP_PREPARE, + KVM_PV_ASYNC_CLEANUP_PERFORM, +}; + +struct kvm_pv_cmd { + __u32 cmd; /* Command to be executed */ + __u16 rc; /* Ultravisor return code */ + __u16 rrc; /* Ultravisor return reason code */ + __u64 data; /* Data or address */ + __u32 flags; /* flags for future extensions. Must be 0 for now */ + __u32 reserved[3]; +}; + +struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) /* Device control API: s390-specific devices */ #define KVM_DEV_FLIC_GET_ALL_IRQS 1 diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 25160d26764b..a38f8f9ba657 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -81,10 +81,8 @@ #define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ #define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ - -/* CPU types for specific tunings: */ #define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */ #define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ #define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ @@ -97,7 +95,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -462,6 +460,14 @@ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ + +/* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) @@ -508,4 +514,5 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 1f23960d2b06..c492bdc97b05 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -123,6 +123,12 @@ # define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31)) #endif +#ifdef CONFIG_KVM_AMD_SEV +#define DISABLE_SEV_SNP 0 +#else +#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -147,8 +153,9 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 (DISABLE_IBT) -#define DISABLED_MASK19 0 +#define DISABLED_MASK19 (DISABLE_SEV_SNP) #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h index 3f73ac3ed3a0..d18bfb238f66 100644 --- a/tools/arch/x86/include/asm/irq_vectors.h +++ b/tools/arch/x86/include/asm/irq_vectors.h @@ -84,11 +84,9 @@ #define HYPERVISOR_CALLBACK_VECTOR 0xf3 /* Vector for KVM to deliver posted interrupt IPI */ -#if IS_ENABLED(CONFIG_KVM) #define POSTED_INTR_VECTOR 0xf2 #define POSTED_INTR_WAKEUP_VECTOR 0xf1 #define POSTED_INTR_NESTED_VECTOR 0xf0 -#endif #define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 1f9dc9bd13eb..05956bd8bacf 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -176,6 +176,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -605,34 +613,47 @@ #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 -#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 -#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) - -/* SNP feature bits enabled by the hypervisor */ -#define MSR_AMD64_SNP_VTOM BIT_ULL(3) -#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) -#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) -#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) -#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) -#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) -#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) -#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) -#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) -#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) -#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) -#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) -#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) - -/* SNP feature bits reserved for future use. */ -#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) -#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) -#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) +#define MSR_AMD64_SNP_VTOM_BIT 3 +#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT) +#define MSR_AMD64_SNP_REFLECT_VC_BIT 4 +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT) +#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5 +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT) +#define MSR_AMD64_SNP_ALT_INJ_BIT 6 +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT) +#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7 +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8 +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT) +#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9 +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT) +#define MSR_AMD64_SNP_VMPL_SSS_BIT 10 +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT) +#define MSR_AMD64_SNP_SECURE_TSC_BIT 11 +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT) +#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12 +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_IBS_VIRT_BIT 14 +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16 +#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT) +#define MSR_AMD64_SNP_SMT_PROT_BIT 17 +#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) +#define MSR_AMD64_SNP_RESV_BIT 18 +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +#define MSR_AMD64_RMP_BASE 0xc0010132 +#define MSR_AMD64_RMP_END 0xc0010133 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -719,8 +740,15 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_AMD64_SYSCFG 0xc0010010 -#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 #define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24 +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT) +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25 +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT) +#define MSR_AMD64_SYSCFG_MFDM_BIT 19 +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT) + #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 7ba1726b71c7..e9187ddd3d1f 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -99,6 +99,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index a448d0964fc0..ef11aa4cab42 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -7,6 +7,8 @@ * */ +#include <linux/const.h> +#include <linux/bits.h> #include <linux/types.h> #include <linux/ioctl.h> #include <linux/stddef.h> @@ -40,7 +42,6 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 @@ -49,7 +50,6 @@ #define __KVM_HAVE_DEBUGREGS #define __KVM_HAVE_XSAVE #define __KVM_HAVE_XCRS -#define __KVM_HAVE_READONLY_MEM /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -526,9 +526,301 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 -#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0) #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) +/* for KVM_CAP_MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; + +/* for KVM_CAP_XEN_HVM */ +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) +#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) +#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8) + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + __u8 runstate_update_flag; + union { + __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) + __u64 hva; + } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; + __u64 pad[8]; + } u; +}; + + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6 + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) + __u64 hva; + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9 + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u32 pad0; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u32 pad0; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u32 pad1; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u32 pad2; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u32 pad3; + __u64 session_uaddr; + __u32 session_len; + __u32 pad4; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +struct kvm_hyperv_eventfd { + __u32 conn_id; + __s32 fd; + __u32 flags; + __u32 padding[3]; +}; + +#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff +#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + /* * Masked event layout. * Bits Description @@ -549,10 +841,10 @@ struct kvm_pmu_event_filter { ((__u64)(!!(exclude)) << 55)) #define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ - (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) -#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) + (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55)) #define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ @@ -560,7 +852,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ /* x86-specific KVM_EXIT_HYPERCALL flags. */ -#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0) #define KVM_X86_DEFAULT_VM 0 #define KVM_X86_SW_PROTECTED_VM 1 diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 318e2dad27e0..ae57bf69ad4a 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -76,6 +76,12 @@ enum { DNS }; +enum { + IPV4 = 1, + IPV6, + IP_TYPE_MAX +}; + static int in_hand_shake; static char *os_name = ""; @@ -102,6 +108,11 @@ static struct utsname uts_buf; #define MAX_FILE_NAME 100 #define ENTRIES_PER_BLOCK 50 +/* + * Change this entry if the number of addresses increases in future + */ +#define MAX_IP_ENTRIES 64 +#define OUTSTR_BUF_SIZE ((INET6_ADDRSTRLEN + 1) * MAX_IP_ENTRIES) struct kvp_record { char key[HV_KVP_EXCHANGE_MAX_KEY_SIZE]; @@ -1171,6 +1182,18 @@ static int process_ip_string(FILE *f, char *ip_string, int type) return 0; } +int ip_version_check(const char *input_addr) +{ + struct in6_addr addr; + + if (inet_pton(AF_INET, input_addr, &addr)) + return IPV4; + else if (inet_pton(AF_INET6, input_addr, &addr)) + return IPV6; + + return -EINVAL; +} + /* * Only IPv4 subnet strings needs to be converted to plen * For IPv6 the subnet is already privided in plen format @@ -1197,14 +1220,75 @@ static int kvp_subnet_to_plen(char *subnet_addr_str) return plen; } +static int process_dns_gateway_nm(FILE *f, char *ip_string, int type, + int ip_sec) +{ + char addr[INET6_ADDRSTRLEN], *output_str; + int ip_offset = 0, error = 0, ip_ver; + char *param_name; + + if (type == DNS) + param_name = "dns"; + else if (type == GATEWAY) + param_name = "gateway"; + else + return -EINVAL; + + output_str = (char *)calloc(OUTSTR_BUF_SIZE, sizeof(char)); + if (!output_str) + return -ENOMEM; + + while (1) { + memset(addr, 0, sizeof(addr)); + + if (!parse_ip_val_buffer(ip_string, &ip_offset, addr, + (MAX_IP_ADDR_SIZE * 2))) + break; + + ip_ver = ip_version_check(addr); + if (ip_ver < 0) + continue; + + if ((ip_ver == IPV4 && ip_sec == IPV4) || + (ip_ver == IPV6 && ip_sec == IPV6)) { + /* + * do a bound check to avoid out-of bound writes + */ + if ((OUTSTR_BUF_SIZE - strlen(output_str)) > + (strlen(addr) + 1)) { + strncat(output_str, addr, + OUTSTR_BUF_SIZE - + strlen(output_str) - 1); + strncat(output_str, ",", + OUTSTR_BUF_SIZE - + strlen(output_str) - 1); + } + } else { + continue; + } + } + + if (strlen(output_str)) { + /* + * This is to get rid of that extra comma character + * in the end of the string + */ + output_str[strlen(output_str) - 1] = '\0'; + error = fprintf(f, "%s=%s\n", param_name, output_str); + } + + free(output_str); + return error; +} + static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet, - int is_ipv6) + int ip_sec) { char addr[INET6_ADDRSTRLEN]; char subnet_addr[INET6_ADDRSTRLEN]; - int error, i = 0; + int error = 0, i = 0; int ip_offset = 0, subnet_offset = 0; - int plen; + int plen, ip_ver; memset(addr, 0, sizeof(addr)); memset(subnet_addr, 0, sizeof(subnet_addr)); @@ -1216,10 +1300,16 @@ static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet, subnet_addr, (MAX_IP_ADDR_SIZE * 2))) { - if (!is_ipv6) + ip_ver = ip_version_check(addr); + if (ip_ver < 0) + continue; + + if (ip_ver == IPV4 && ip_sec == IPV4) plen = kvp_subnet_to_plen((char *)subnet_addr); - else + else if (ip_ver == IPV6 && ip_sec == IPV6) plen = atoi(subnet_addr); + else + continue; if (plen < 0) return plen; @@ -1233,17 +1323,16 @@ static int process_ip_string_nm(FILE *f, char *ip_string, char *subnet, memset(subnet_addr, 0, sizeof(subnet_addr)); } - return 0; + return error; } static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) { - int error = 0; + int error = 0, ip_ver; char if_filename[PATH_MAX]; char nm_filename[PATH_MAX]; FILE *ifcfg_file, *nmfile; char cmd[PATH_MAX]; - int is_ipv6 = 0; char *mac_addr; int str_len; @@ -1421,52 +1510,94 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (error) goto setval_error; - if (new_val->addr_family & ADDR_FAMILY_IPV6) { - error = fprintf(nmfile, "\n[ipv6]\n"); - if (error < 0) - goto setval_error; - is_ipv6 = 1; - } else { - error = fprintf(nmfile, "\n[ipv4]\n"); - if (error < 0) - goto setval_error; - } - /* * Now we populate the keyfile format + * + * The keyfile format expects the IPv6 and IPv4 configuration in + * different sections. Therefore we iterate through the list twice, + * once to populate the IPv4 section and the next time for IPv6 */ + ip_ver = IPV4; + do { + if (ip_ver == IPV4) { + error = fprintf(nmfile, "\n[ipv4]\n"); + if (error < 0) + goto setval_error; + } else { + error = fprintf(nmfile, "\n[ipv6]\n"); + if (error < 0) + goto setval_error; + } - if (new_val->dhcp_enabled) { - error = kvp_write_file(nmfile, "method", "", "auto"); - if (error < 0) - goto setval_error; - } else { - error = kvp_write_file(nmfile, "method", "", "manual"); + /* + * Write the configuration for ipaddress, netmask, gateway and + * name services + */ + error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr, + (char *)new_val->sub_net, + ip_ver); if (error < 0) goto setval_error; - } - /* - * Write the configuration for ipaddress, netmask, gateway and - * name services - */ - error = process_ip_string_nm(nmfile, (char *)new_val->ip_addr, - (char *)new_val->sub_net, is_ipv6); - if (error < 0) - goto setval_error; + /* + * As dhcp_enabled is only valid for ipv4, we do not set dhcp + * methods for ipv6 based on dhcp_enabled flag. + * + * For ipv4, set method to manual only when dhcp_enabled is + * false and specific ipv4 addresses are configured. If neither + * dhcp_enabled is true and no ipv4 addresses are configured, + * set method to 'disabled'. + * + * For ipv6, set method to manual when we configure ipv6 + * addresses. Otherwise set method to 'auto' so that SLAAC from + * RA may be used. + */ + if (ip_ver == IPV4) { + if (new_val->dhcp_enabled) { + error = kvp_write_file(nmfile, "method", "", + "auto"); + if (error < 0) + goto setval_error; + } else if (error) { + error = kvp_write_file(nmfile, "method", "", + "manual"); + if (error < 0) + goto setval_error; + } else { + error = kvp_write_file(nmfile, "method", "", + "disabled"); + if (error < 0) + goto setval_error; + } + } else if (ip_ver == IPV6) { + if (error) { + error = kvp_write_file(nmfile, "method", "", + "manual"); + if (error < 0) + goto setval_error; + } else { + error = kvp_write_file(nmfile, "method", "", + "auto"); + if (error < 0) + goto setval_error; + } + } - /* we do not want ipv4 addresses in ipv6 section and vice versa */ - if (is_ipv6 != is_ipv4((char *)new_val->gate_way)) { - error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way); + error = process_dns_gateway_nm(nmfile, + (char *)new_val->gate_way, + GATEWAY, ip_ver); if (error < 0) goto setval_error; - } - if (is_ipv6 != is_ipv4((char *)new_val->dns_addr)) { - error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr); + error = process_dns_gateway_nm(nmfile, + (char *)new_val->dns_addr, DNS, + ip_ver); if (error < 0) goto setval_error; - } + + ip_ver++; + } while (ip_ver < IP_TYPE_MAX); + fclose(nmfile); fclose(ifcfg_file); diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h index 03f721a8a2b1..54ccccf96e21 100644 --- a/tools/include/asm-generic/bitops/__fls.h +++ b/tools/include/asm-generic/bitops/__fls.h @@ -5,12 +5,12 @@ #include <asm/types.h> /** - * __fls - find last (most-significant) set bit in a long word + * generic___fls - find last (most-significant) set bit in a long word * @word: the word to search * * Undefined if no set bit exists, so code should check against 0 first. */ -static __always_inline unsigned long __fls(unsigned long word) +static __always_inline unsigned long generic___fls(unsigned long word) { int num = BITS_PER_LONG - 1; @@ -41,4 +41,8 @@ static __always_inline unsigned long __fls(unsigned long word) return num; } +#ifndef __HAVE_ARCH___FLS +#define __fls(word) generic___fls(word) +#endif + #endif /* _ASM_GENERIC_BITOPS___FLS_H_ */ diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h index b168bb10e1be..26f3ce1dd6e4 100644 --- a/tools/include/asm-generic/bitops/fls.h +++ b/tools/include/asm-generic/bitops/fls.h @@ -3,14 +3,14 @@ #define _ASM_GENERIC_BITOPS_FLS_H_ /** - * fls - find last (most-significant) bit set + * generic_fls - find last (most-significant) bit set * @x: the word to search * * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static __always_inline int fls(unsigned int x) +static __always_inline int generic_fls(unsigned int x) { int r = 32; @@ -39,4 +39,8 @@ static __always_inline int fls(unsigned int x) return r; } +#ifndef __HAVE_ARCH_FLS +#define fls(x) generic_fls(x) +#endif + #endif /* _ASM_GENERIC_BITOPS_FLS_H_ */ diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 4b0673bf52c2..07cfad817d53 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -8,6 +8,7 @@ #include <linux/build_bug.h> #include <linux/compiler.h> #include <linux/math.h> +#include <linux/panic.h> #include <endian.h> #include <byteswap.h> diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h index f3c82ab5b14c..7d73da098047 100644 --- a/tools/include/linux/mm.h +++ b/tools/include/linux/mm.h @@ -37,4 +37,9 @@ static inline void totalram_pages_add(long count) { } +static inline int early_pfn_to_nid(unsigned long pfn) +{ + return 0; +} + #endif diff --git a/tools/include/linux/panic.h b/tools/include/linux/panic.h new file mode 100644 index 000000000000..9c8f17a41ce8 --- /dev/null +++ b/tools/include/linux/panic.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_LINUX_PANIC_H +#define _TOOLS_LINUX_PANIC_H + +#include <stdarg.h> +#include <stdio.h> +#include <stdlib.h> + +static inline void panic(const char *fmt, ...) +{ + va_list argp; + + va_start(argp, fmt); + vfprintf(stderr, fmt, argp); + va_end(argp); + exit(-1); +} + +#endif diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index fd4f9574d177..2ee338860b7e 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -3013,6 +3013,7 @@ struct drm_i915_query_item { * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions) * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`) * - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info) + * - %DRM_I915_QUERY_GUC_SUBMISSION_VERSION (see struct drm_i915_query_guc_submission_version) */ __u64 query_id; #define DRM_I915_QUERY_TOPOLOGY_INFO 1 @@ -3021,6 +3022,7 @@ struct drm_i915_query_item { #define DRM_I915_QUERY_MEMORY_REGIONS 4 #define DRM_I915_QUERY_HWCONFIG_BLOB 5 #define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6 +#define DRM_I915_QUERY_GUC_SUBMISSION_VERSION 7 /* Must be kept compact -- no holes and well documented */ /** @@ -3567,6 +3569,20 @@ struct drm_i915_query_memory_regions { }; /** + * struct drm_i915_query_guc_submission_version - query GuC submission interface version + */ +struct drm_i915_query_guc_submission_version { + /** @branch: Firmware branch version. */ + __u32 branch; + /** @major: Firmware major version. */ + __u32 major; + /** @minor: Firmware minor version. */ + __u32 minor; + /** @patch: Firmware patch version. */ + __u32 patch; +}; + +/** * DOC: GuC HWCONFIG blob uAPI * * The GuC produces a blob with information about the current device. diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h index 48ad69f7722e..45e4e64fd664 100644 --- a/tools/include/uapi/linux/fs.h +++ b/tools/include/uapi/linux/fs.h @@ -64,6 +64,24 @@ struct fstrim_range { __u64 minlen; }; +/* + * We include a length field because some filesystems (vfat) have an identifier + * that we do want to expose as a UUID, but doesn't have the standard length. + * + * We use a fixed size buffer beacuse this interface will, by fiat, never + * support "UUIDs" longer than 16 bytes; we don't want to force all downstream + * users to have to deal with that. + */ +struct fsuuid2 { + __u8 len; + __u8 uuid[16]; +}; + +struct fs_sysfs_path { + __u8 len; + __u8 name[128]; +}; + /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ #define FILE_DEDUPE_RANGE_SAME 0 #define FILE_DEDUPE_RANGE_DIFFERS 1 @@ -215,6 +233,13 @@ struct fsxattr { #define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) #define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX]) #define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX]) +/* Returns the external filesystem UUID, the same one blkid returns */ +#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2) +/* + * Returns the path component under /sys/fs/ that refers to this filesystem; + * also /sys/kernel/debug/ for filesystems with debugfs exports + */ +#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) @@ -301,9 +326,12 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO O_APPEND */ #define RWF_APPEND ((__force __kernel_rwf_t)0x00000010) +/* per-IO negation of O_APPEND */ +#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND) + RWF_APPEND | RWF_NOAPPEND) /* Pagemap ioctl */ #define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index c3308536482b..2190adbe3002 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -16,6 +16,11 @@ #define KVM_API_VERSION 12 +/* + * Backwards-compatible definitions. + */ +#define __KVM_HAVE_GUEST_DEBUG + /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -85,43 +90,6 @@ struct kvm_pit_config { #define KVM_PIT_SPEAKER_DUMMY 1 -struct kvm_s390_skeys { - __u64 start_gfn; - __u64 count; - __u64 skeydata_addr; - __u32 flags; - __u32 reserved[9]; -}; - -#define KVM_S390_CMMA_PEEK (1 << 0) - -/** - * kvm_s390_cmma_log - Used for CMMA migration. - * - * Used both for input and output. - * - * @start_gfn: Guest page number to start from. - * @count: Size of the result buffer. - * @flags: Control operation mode via KVM_S390_CMMA_* flags - * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty - * pages are still remaining. - * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set - * in the PGSTE. - * @values: Pointer to the values buffer. - * - * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls. - */ -struct kvm_s390_cmma_log { - __u64 start_gfn; - __u32 count; - __u32 flags; - union { - __u64 remaining; - __u64 mask; - }; - __u64 values; -}; - struct kvm_hyperv_exit { #define KVM_EXIT_HYPERV_SYNIC 1 #define KVM_EXIT_HYPERV_HCALL 2 @@ -315,11 +283,6 @@ struct kvm_run { __u32 ipb; } s390_sieic; /* KVM_EXIT_S390_RESET */ -#define KVM_S390_RESET_POR 1 -#define KVM_S390_RESET_CLEAR 2 -#define KVM_S390_RESET_SUBSYSTEM 4 -#define KVM_S390_RESET_CPU_INIT 8 -#define KVM_S390_RESET_IPL 16 __u64 s390_reset_flags; /* KVM_EXIT_S390_UCONTROL */ struct { @@ -536,43 +499,6 @@ struct kvm_translation { __u8 pad[5]; }; -/* for KVM_S390_MEM_OP */ -struct kvm_s390_mem_op { - /* in */ - __u64 gaddr; /* the guest address */ - __u64 flags; /* flags */ - __u32 size; /* amount of bytes */ - __u32 op; /* type of operation */ - __u64 buf; /* buffer in userspace */ - union { - struct { - __u8 ar; /* the access register number */ - __u8 key; /* access key, ignored if flag unset */ - __u8 pad1[6]; /* ignored */ - __u64 old_addr; /* ignored if cmpxchg flag unset */ - }; - __u32 sida_offset; /* offset into the sida */ - __u8 reserved[32]; /* ignored */ - }; -}; -/* types for kvm_s390_mem_op->op */ -#define KVM_S390_MEMOP_LOGICAL_READ 0 -#define KVM_S390_MEMOP_LOGICAL_WRITE 1 -#define KVM_S390_MEMOP_SIDA_READ 2 -#define KVM_S390_MEMOP_SIDA_WRITE 3 -#define KVM_S390_MEMOP_ABSOLUTE_READ 4 -#define KVM_S390_MEMOP_ABSOLUTE_WRITE 5 -#define KVM_S390_MEMOP_ABSOLUTE_CMPXCHG 6 - -/* flags for kvm_s390_mem_op->flags */ -#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0) -#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1) -#define KVM_S390_MEMOP_F_SKEY_PROTECTION (1ULL << 2) - -/* flags specifying extension support via KVM_CAP_S390_MEM_OP_EXTENSION */ -#define KVM_S390_MEMOP_EXTENSION_CAP_BASE (1 << 0) -#define KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG (1 << 1) - /* for KVM_INTERRUPT */ struct kvm_interrupt { /* in */ @@ -637,124 +563,6 @@ struct kvm_mp_state { __u32 mp_state; }; -struct kvm_s390_psw { - __u64 mask; - __u64 addr; -}; - -/* valid values for type in kvm_s390_interrupt */ -#define KVM_S390_SIGP_STOP 0xfffe0000u -#define KVM_S390_PROGRAM_INT 0xfffe0001u -#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u -#define KVM_S390_RESTART 0xfffe0003u -#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u -#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u -#define KVM_S390_MCHK 0xfffe1000u -#define KVM_S390_INT_CLOCK_COMP 0xffff1004u -#define KVM_S390_INT_CPU_TIMER 0xffff1005u -#define KVM_S390_INT_VIRTIO 0xffff2603u -#define KVM_S390_INT_SERVICE 0xffff2401u -#define KVM_S390_INT_EMERGENCY 0xffff1201u -#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u -/* Anything below 0xfffe0000u is taken by INT_IO */ -#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \ - (((schid)) | \ - ((ssid) << 16) | \ - ((cssid) << 18) | \ - ((ai) << 26)) -#define KVM_S390_INT_IO_MIN 0x00000000u -#define KVM_S390_INT_IO_MAX 0xfffdffffu -#define KVM_S390_INT_IO_AI_MASK 0x04000000u - - -struct kvm_s390_interrupt { - __u32 type; - __u32 parm; - __u64 parm64; -}; - -struct kvm_s390_io_info { - __u16 subchannel_id; - __u16 subchannel_nr; - __u32 io_int_parm; - __u32 io_int_word; -}; - -struct kvm_s390_ext_info { - __u32 ext_params; - __u32 pad; - __u64 ext_params2; -}; - -struct kvm_s390_pgm_info { - __u64 trans_exc_code; - __u64 mon_code; - __u64 per_address; - __u32 data_exc_code; - __u16 code; - __u16 mon_class_nr; - __u8 per_code; - __u8 per_atmid; - __u8 exc_access_id; - __u8 per_access_id; - __u8 op_access_id; -#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01 -#define KVM_S390_PGM_FLAGS_ILC_0 0x02 -#define KVM_S390_PGM_FLAGS_ILC_1 0x04 -#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06 -#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08 - __u8 flags; - __u8 pad[2]; -}; - -struct kvm_s390_prefix_info { - __u32 address; -}; - -struct kvm_s390_extcall_info { - __u16 code; -}; - -struct kvm_s390_emerg_info { - __u16 code; -}; - -#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01 -struct kvm_s390_stop_info { - __u32 flags; -}; - -struct kvm_s390_mchk_info { - __u64 cr14; - __u64 mcic; - __u64 failing_storage_address; - __u32 ext_damage_code; - __u32 pad; - __u8 fixed_logout[16]; -}; - -struct kvm_s390_irq { - __u64 type; - union { - struct kvm_s390_io_info io; - struct kvm_s390_ext_info ext; - struct kvm_s390_pgm_info pgm; - struct kvm_s390_emerg_info emerg; - struct kvm_s390_extcall_info extcall; - struct kvm_s390_prefix_info prefix; - struct kvm_s390_stop_info stop; - struct kvm_s390_mchk_info mchk; - char reserved[64]; - } u; -}; - -struct kvm_s390_irq_state { - __u64 buf; - __u32 flags; /* will stay unused for compatibility reasons */ - __u32 len; - __u32 reserved[4]; /* will stay unused for compatibility reasons */ -}; - /* for KVM_SET_GUEST_DEBUG */ #define KVM_GUESTDBG_ENABLE 0x00000001 @@ -810,50 +618,6 @@ struct kvm_enable_cap { __u8 pad[64]; }; -/* for KVM_PPC_GET_PVINFO */ - -#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) - -struct kvm_ppc_pvinfo { - /* out */ - __u32 flags; - __u32 hcall[4]; - __u8 pad[108]; -}; - -/* for KVM_PPC_GET_SMMU_INFO */ -#define KVM_PPC_PAGE_SIZES_MAX_SZ 8 - -struct kvm_ppc_one_page_size { - __u32 page_shift; /* Page shift (or 0) */ - __u32 pte_enc; /* Encoding in the HPTE (>>12) */ -}; - -struct kvm_ppc_one_seg_page_size { - __u32 page_shift; /* Base page shift of segment (or 0) */ - __u32 slb_enc; /* SLB encoding for BookS */ - struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -#define KVM_PPC_PAGE_SIZES_REAL 0x00000001 -#define KVM_PPC_1T_SEGMENTS 0x00000002 -#define KVM_PPC_NO_HASH 0x00000004 - -struct kvm_ppc_smmu_info { - __u64 flags; - __u32 slb_size; - __u16 data_keys; /* # storage keys supported for data */ - __u16 instr_keys; /* # storage keys supported for instructions */ - struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; -}; - -/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ -struct kvm_ppc_resize_hpt { - __u64 flags; - __u32 shift; - __u32 pad; -}; - #define KVMIO 0xAE /* machine type bits, to be used as argument to KVM_CREATE_VM */ @@ -923,9 +687,7 @@ struct kvm_ppc_resize_hpt { /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */ #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21 #define KVM_CAP_USER_NMI 22 -#ifdef __KVM_HAVE_GUEST_DEBUG #define KVM_CAP_SET_GUEST_DEBUG 23 -#endif #ifdef __KVM_HAVE_PIT #define KVM_CAP_REINJECT_CONTROL 24 #endif @@ -1156,8 +918,6 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 -#ifdef KVM_CAP_IRQ_ROUTING - struct kvm_irq_routing_irqchip { __u32 irqchip; __u32 pin; @@ -1222,42 +982,6 @@ struct kvm_irq_routing { struct kvm_irq_routing_entry entries[]; }; -#endif - -#ifdef KVM_CAP_MCE -/* x86 MCE */ -struct kvm_x86_mce { - __u64 status; - __u64 addr; - __u64 misc; - __u64 mcg_status; - __u8 bank; - __u8 pad1[7]; - __u64 pad2[3]; -}; -#endif - -#ifdef KVM_CAP_XEN_HVM -#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) -#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) -#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) -#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) -#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) -#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) -#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) -#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) - -struct kvm_xen_hvm_config { - __u32 flags; - __u32 msr; - __u64 blob_addr_32; - __u64 blob_addr_64; - __u8 blob_size_32; - __u8 blob_size_64; - __u8 pad2[30]; -}; -#endif - #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) /* * Available with KVM_CAP_IRQFD_RESAMPLE @@ -1442,11 +1166,6 @@ struct kvm_vfio_spapr_tce { struct kvm_userspace_memory_region2) /* enable ucontrol for s390 */ -struct kvm_s390_ucas_mapping { - __u64 user_addr; - __u64 vcpu_addr; - __u64 length; -}; #define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) #define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) #define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) @@ -1641,89 +1360,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -struct kvm_s390_pv_sec_parm { - __u64 origin; - __u64 length; -}; - -struct kvm_s390_pv_unp { - __u64 addr; - __u64 size; - __u64 tweak; -}; - -enum pv_cmd_dmp_id { - KVM_PV_DUMP_INIT, - KVM_PV_DUMP_CONFIG_STOR_STATE, - KVM_PV_DUMP_COMPLETE, - KVM_PV_DUMP_CPU, -}; - -struct kvm_s390_pv_dmp { - __u64 subcmd; - __u64 buff_addr; - __u64 buff_len; - __u64 gaddr; /* For dump storage state */ - __u64 reserved[4]; -}; - -enum pv_cmd_info_id { - KVM_PV_INFO_VM, - KVM_PV_INFO_DUMP, -}; - -struct kvm_s390_pv_info_dump { - __u64 dump_cpu_buffer_len; - __u64 dump_config_mem_buffer_per_1m; - __u64 dump_config_finalize_len; -}; - -struct kvm_s390_pv_info_vm { - __u64 inst_calls_list[4]; - __u64 max_cpus; - __u64 max_guests; - __u64 max_guest_addr; - __u64 feature_indication; -}; - -struct kvm_s390_pv_info_header { - __u32 id; - __u32 len_max; - __u32 len_written; - __u32 reserved; -}; - -struct kvm_s390_pv_info { - struct kvm_s390_pv_info_header header; - union { - struct kvm_s390_pv_info_dump dump; - struct kvm_s390_pv_info_vm vm; - }; -}; - -enum pv_cmd_id { - KVM_PV_ENABLE, - KVM_PV_DISABLE, - KVM_PV_SET_SEC_PARMS, - KVM_PV_UNPACK, - KVM_PV_VERIFY, - KVM_PV_PREP_RESET, - KVM_PV_UNSHARE_ALL, - KVM_PV_INFO, - KVM_PV_DUMP, - KVM_PV_ASYNC_CLEANUP_PREPARE, - KVM_PV_ASYNC_CLEANUP_PERFORM, -}; - -struct kvm_pv_cmd { - __u32 cmd; /* Command to be executed */ - __u16 rc; /* Ultravisor return code */ - __u16 rrc; /* Ultravisor return reason code */ - __u64 data; /* Data or address */ - __u32 flags; /* flags for future extensions. Must be 0 for now */ - __u32 reserved[3]; -}; - /* Available with KVM_CAP_S390_PROTECTED */ #define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) @@ -1737,58 +1373,6 @@ struct kvm_pv_cmd { #define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) #define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) -struct kvm_xen_hvm_attr { - __u16 type; - __u16 pad[3]; - union { - __u8 long_mode; - __u8 vector; - __u8 runstate_update_flag; - struct { - __u64 gfn; -#define KVM_XEN_INVALID_GFN ((__u64)-1) - } shared_info; - struct { - __u32 send_port; - __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ - __u32 flags; -#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) -#define KVM_XEN_EVTCHN_UPDATE (1 << 1) -#define KVM_XEN_EVTCHN_RESET (1 << 2) - /* - * Events sent by the guest are either looped back to - * the guest itself (potentially on a different port#) - * or signalled via an eventfd. - */ - union { - struct { - __u32 port; - __u32 vcpu; - __u32 priority; - } port; - struct { - __u32 port; /* Zero for eventfd */ - __s32 fd; - } eventfd; - __u32 padding[4]; - } deliver; - } evtchn; - __u32 xen_version; - __u64 pad[8]; - } u; -}; - - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 -#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 -#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 -#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ -#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 - /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) @@ -1799,242 +1383,6 @@ struct kvm_xen_hvm_attr { #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) -struct kvm_xen_vcpu_attr { - __u16 type; - __u16 pad[3]; - union { - __u64 gpa; -#define KVM_XEN_INVALID_GPA ((__u64)-1) - __u64 pad[8]; - struct { - __u64 state; - __u64 state_entry_time; - __u64 time_running; - __u64 time_runnable; - __u64 time_blocked; - __u64 time_offline; - } runstate; - __u32 vcpu_id; - struct { - __u32 port; - __u32 priority; - __u64 expires_ns; - } timer; - __u8 vector; - } u; -}; - -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 -#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 -/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ -#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 -#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 -#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 - -/* Secure Encrypted Virtualization command */ -enum sev_cmd_id { - /* Guest initialization commands */ - KVM_SEV_INIT = 0, - KVM_SEV_ES_INIT, - /* Guest launch commands */ - KVM_SEV_LAUNCH_START, - KVM_SEV_LAUNCH_UPDATE_DATA, - KVM_SEV_LAUNCH_UPDATE_VMSA, - KVM_SEV_LAUNCH_SECRET, - KVM_SEV_LAUNCH_MEASURE, - KVM_SEV_LAUNCH_FINISH, - /* Guest migration commands (outgoing) */ - KVM_SEV_SEND_START, - KVM_SEV_SEND_UPDATE_DATA, - KVM_SEV_SEND_UPDATE_VMSA, - KVM_SEV_SEND_FINISH, - /* Guest migration commands (incoming) */ - KVM_SEV_RECEIVE_START, - KVM_SEV_RECEIVE_UPDATE_DATA, - KVM_SEV_RECEIVE_UPDATE_VMSA, - KVM_SEV_RECEIVE_FINISH, - /* Guest status and debug commands */ - KVM_SEV_GUEST_STATUS, - KVM_SEV_DBG_DECRYPT, - KVM_SEV_DBG_ENCRYPT, - /* Guest certificates commands */ - KVM_SEV_CERT_EXPORT, - /* Attestation report */ - KVM_SEV_GET_ATTESTATION_REPORT, - /* Guest Migration Extension */ - KVM_SEV_SEND_CANCEL, - - KVM_SEV_NR_MAX, -}; - -struct kvm_sev_cmd { - __u32 id; - __u64 data; - __u32 error; - __u32 sev_fd; -}; - -struct kvm_sev_launch_start { - __u32 handle; - __u32 policy; - __u64 dh_uaddr; - __u32 dh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_launch_update_data { - __u64 uaddr; - __u32 len; -}; - - -struct kvm_sev_launch_secret { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_launch_measure { - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_guest_status { - __u32 handle; - __u32 policy; - __u32 state; -}; - -struct kvm_sev_dbg { - __u64 src_uaddr; - __u64 dst_uaddr; - __u32 len; -}; - -struct kvm_sev_attestation_report { - __u8 mnonce[16]; - __u64 uaddr; - __u32 len; -}; - -struct kvm_sev_send_start { - __u32 policy; - __u64 pdh_cert_uaddr; - __u32 pdh_cert_len; - __u64 plat_certs_uaddr; - __u32 plat_certs_len; - __u64 amd_certs_uaddr; - __u32 amd_certs_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_send_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -struct kvm_sev_receive_start { - __u32 handle; - __u32 policy; - __u64 pdh_uaddr; - __u32 pdh_len; - __u64 session_uaddr; - __u32 session_len; -}; - -struct kvm_sev_receive_update_data { - __u64 hdr_uaddr; - __u32 hdr_len; - __u64 guest_uaddr; - __u32 guest_len; - __u64 trans_uaddr; - __u32 trans_len; -}; - -#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) -#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) -#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) - -struct kvm_assigned_pci_dev { - __u32 assigned_dev_id; - __u32 busnr; - __u32 devfn; - __u32 flags; - __u32 segnr; - union { - __u32 reserved[11]; - }; -}; - -#define KVM_DEV_IRQ_HOST_INTX (1 << 0) -#define KVM_DEV_IRQ_HOST_MSI (1 << 1) -#define KVM_DEV_IRQ_HOST_MSIX (1 << 2) - -#define KVM_DEV_IRQ_GUEST_INTX (1 << 8) -#define KVM_DEV_IRQ_GUEST_MSI (1 << 9) -#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10) - -#define KVM_DEV_IRQ_HOST_MASK 0x00ff -#define KVM_DEV_IRQ_GUEST_MASK 0xff00 - -struct kvm_assigned_irq { - __u32 assigned_dev_id; - __u32 host_irq; /* ignored (legacy field) */ - __u32 guest_irq; - __u32 flags; - union { - __u32 reserved[12]; - }; -}; - -struct kvm_assigned_msix_nr { - __u32 assigned_dev_id; - __u16 entry_nr; - __u16 padding; -}; - -#define KVM_MAX_MSIX_PER_DEV 256 -struct kvm_assigned_msix_entry { - __u32 assigned_dev_id; - __u32 gsi; - __u16 entry; /* The index of entry in the MSI-X table */ - __u16 padding[3]; -}; - -#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) -#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) - -/* Available with KVM_CAP_ARM_USER_IRQ */ - -/* Bits for run->s.regs.device_irq_level */ -#define KVM_ARM_DEV_EL1_VTIMER (1 << 0) -#define KVM_ARM_DEV_EL1_PTIMER (1 << 1) -#define KVM_ARM_DEV_PMU (1 << 2) - -struct kvm_hyperv_eventfd { - __u32 conn_id; - __s32 fd; - __u32 flags; - __u32 padding[3]; -}; - -#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff -#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) - #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) #define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) @@ -2180,33 +1528,6 @@ struct kvm_stats_desc { /* Available with KVM_CAP_S390_ZPCI_OP */ #define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) -struct kvm_s390_zpci_op { - /* in */ - __u32 fh; /* target device */ - __u8 op; /* operation to perform */ - __u8 pad[3]; - union { - /* for KVM_S390_ZPCIOP_REG_AEN */ - struct { - __u64 ibv; /* Guest addr of interrupt bit vector */ - __u64 sb; /* Guest addr of summary bit */ - __u32 flags; - __u32 noi; /* Number of interrupts */ - __u8 isc; /* Guest interrupt subclass */ - __u8 sbo; /* Offset of guest summary bit vector */ - __u16 pad; - } reg_aen; - __u64 reserved[8]; - } u; -}; - -/* types for kvm_s390_zpci_op->op */ -#define KVM_S390_ZPCIOP_REG_AEN 0 -#define KVM_S390_ZPCIOP_DEREG_AEN 1 - -/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ -#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) - /* Available with KVM_CAP_MEMORY_ATTRIBUTES */ #define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes) diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index d5b9cfbd9cea..628d46a0da92 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -416,7 +416,7 @@ struct snd_pcm_hw_params { unsigned int rmask; /* W: requested masks */ unsigned int cmask; /* R: changed masks */ unsigned int info; /* R: Info flags for returned setup */ - unsigned int msbits; /* R: used most significant bits */ + unsigned int msbits; /* R: used most significant bits (in sample bit-width) */ unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 5fa7957f6e0f..25810e18b0a7 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -182,6 +182,7 @@ class NlMsg: 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/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index ec5e21932876..4790c735599b 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -970,7 +970,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, if (dso->annotate_warned) return -1; - if (not_annotated) { + if (not_annotated || !sym->annotate2) { err = symbol__annotate2(ms, evsel, &browser.arch); if (err) { char msg[BUFSIZ]; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index ac002d907d81..50ca92255ff6 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2461,6 +2461,9 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel, if (parch) *parch = arch; + if (!list_empty(¬es->src->source)) + return 0; + args.arch = arch; args.ms = *ms; if (annotate_opts.full_addr) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index fb54bd38e7d0..d931a898c434 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -284,6 +284,7 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) struct task_struct *curr; struct mm_struct___old *mm_old; struct mm_struct___new *mm_new; + struct sighand_struct *sighand; switch (flags) { case LCB_F_READ: /* rwsem */ @@ -305,7 +306,9 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) break; case LCB_F_SPIN: /* spinlock */ curr = bpf_get_current_task_btf(); - if (&curr->sighand->siglock == (void *)lock) + sighand = curr->sighand; + + if (sighand && &sighand->siglock == (void *)lock) return LCD_F_SIGHAND_LOCK; break; default: diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index 8f08c3fd498d..0d3672e5d9ed 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -67,6 +67,10 @@ The column name "all" can be used to enable all disabled-by-default built-in cou .PP \fB--quiet\fP Do not decode and print the system configuration header information. .PP ++\fB--no-msr\fP Disable all the uses of the MSR driver. ++.PP ++\fB--no-perf\fP Disable all the uses of the perf API. ++.PP \fB--interval seconds\fP overrides the default 5.0 second measurement interval. .PP \fB--num_iterations num\fP number of the measurement iterations. @@ -125,9 +129,17 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. .PP -\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms. +\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms or /sys/class/drm/card0/gt/gt0/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used. .PP -\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz. +\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used. +.PP +\fBGFXAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used. +.PP +\fBSAM%mc6\fP The percentage of time the SA Media is in the "module C6" state, mc6, during the measurement interval. From /sys/class/drm/card0/gt/gt1/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used. +.PP +\fBSAMMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used. +.PP +\fBSAMAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used. .PP \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. .PP @@ -370,7 +382,7 @@ below the processor's base frequency. Busy% = MPERF_delta/TSC_delta -Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval +Bzy_MHz = TSC_delta*APERF_delta/MPERF_delta/measurement_interval Note that these calculations depend on TSC_delta, so they are not reliable during intervals when TSC_MHz is not running at the base frequency. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 7a334377f92b..98256468e248 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3,7 +3,7 @@ * turbostat -- show CPU frequency and C-state residency * on modern Intel and AMD processors. * - * Copyright (c) 2023 Intel Corporation. + * Copyright (c) 2024 Intel Corporation. * Len Brown <len.brown@intel.com> */ @@ -36,6 +36,8 @@ #include <linux/perf_event.h> #include <asm/unistd.h> #include <stdbool.h> +#include <assert.h> +#include <linux/kernel.h> #define UNUSED(x) (void)(x) @@ -53,9 +55,13 @@ #define NAME_BYTES 20 #define PATH_BYTES 128 +#define MAX_NOFILE 0x8000 + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT }; +enum amperf_source { AMPERF_SOURCE_PERF, AMPERF_SOURCE_MSR }; +enum rapl_source { RAPL_SOURCE_NONE, RAPL_SOURCE_PERF, RAPL_SOURCE_MSR }; struct msr_counter { unsigned int msr_num; @@ -127,6 +133,9 @@ struct msr_counter bic[] = { { 0x0, "IPC", "", 0, 0, 0, NULL, 0 }, { 0x0, "CoreThr", "", 0, 0, 0, NULL, 0 }, { 0x0, "UncMHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "SAM%mc6", "", 0, 0, 0, NULL, 0 }, + { 0x0, "SAMMHz", "", 0, 0, 0, NULL, 0 }, + { 0x0, "SAMAMHz", "", 0, 0, 0, NULL, 0 }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -185,11 +194,14 @@ struct msr_counter bic[] = { #define BIC_IPC (1ULL << 52) #define BIC_CORE_THROT_CNT (1ULL << 53) #define BIC_UNCORE_MHZ (1ULL << 54) +#define BIC_SAM_mc6 (1ULL << 55) +#define BIC_SAMMHz (1ULL << 56) +#define BIC_SAMACTMHz (1ULL << 57) #define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) #define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) -#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_UNCORE_MHZ) -#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX) +#define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ) +#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6) #define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -204,10 +216,13 @@ unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) #define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT) +struct amperf_group_fd; + char *proc_stat = "/proc/stat"; FILE *outf; int *fd_percpu; int *fd_instr_count_percpu; +struct amperf_group_fd *fd_amperf_percpu; /* File descriptors for perf group with APERF and MPERF counters. */ struct timeval interval_tv = { 5, 0 }; struct timespec interval_ts = { 5, 0 }; @@ -242,11 +257,8 @@ char *output_buffer, *outp; unsigned int do_dts; unsigned int do_ptm; unsigned int do_ipc; -unsigned long long gfx_cur_rc6_ms; unsigned long long cpuidle_cur_cpu_lpi_us; unsigned long long cpuidle_cur_sys_lpi_us; -unsigned int gfx_cur_mhz; -unsigned int gfx_act_mhz; unsigned int tj_max; unsigned int tj_max_override; double rapl_power_units, rapl_time_units; @@ -263,6 +275,28 @@ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int first_counter_read = 1; int ignore_stdin; +bool no_msr; +bool no_perf; +enum amperf_source amperf_source; + +enum gfx_sysfs_idx { + GFX_rc6, + GFX_MHz, + GFX_ACTMHz, + SAM_mc6, + SAM_MHz, + SAM_ACTMHz, + GFX_MAX +}; + +struct gfx_sysfs_info { + const char *path; + FILE *fp; + unsigned int val; + unsigned long long val_ull; +}; + +static struct gfx_sysfs_info gfx_info[GFX_MAX]; int get_msr(int cpu, off_t offset, unsigned long long *msr); @@ -652,6 +686,7 @@ static const struct platform_features icx_features = { .bclk_freq = BCLK_100MHZ, .supported_cstates = CC1 | CC6 | PC2 | PC6, .cst_limit = CST_LIMIT_ICX, + .has_msr_core_c1_res = 1, .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, @@ -948,6 +983,175 @@ size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affi #define MAX_ADDED_THREAD_COUNTERS 24 #define BITMASK_SIZE 32 +/* Indexes used to map data read from perf and MSRs into global variables */ +enum rapl_rci_index { + RAPL_RCI_INDEX_ENERGY_PKG = 0, + RAPL_RCI_INDEX_ENERGY_CORES = 1, + RAPL_RCI_INDEX_DRAM = 2, + RAPL_RCI_INDEX_GFX = 3, + RAPL_RCI_INDEX_PKG_PERF_STATUS = 4, + RAPL_RCI_INDEX_DRAM_PERF_STATUS = 5, + RAPL_RCI_INDEX_CORE_ENERGY = 6, + NUM_RAPL_COUNTERS, +}; + +enum rapl_unit { + RAPL_UNIT_INVALID, + RAPL_UNIT_JOULES, + RAPL_UNIT_WATTS, +}; + +struct rapl_counter_info_t { + unsigned long long data[NUM_RAPL_COUNTERS]; + enum rapl_source source[NUM_RAPL_COUNTERS]; + unsigned long long flags[NUM_RAPL_COUNTERS]; + double scale[NUM_RAPL_COUNTERS]; + enum rapl_unit unit[NUM_RAPL_COUNTERS]; + + union { + /* Active when source == RAPL_SOURCE_MSR */ + struct { + unsigned long long msr[NUM_RAPL_COUNTERS]; + unsigned long long msr_mask[NUM_RAPL_COUNTERS]; + int msr_shift[NUM_RAPL_COUNTERS]; + }; + }; + + int fd_perf; +}; + +/* struct rapl_counter_info_t for each RAPL domain */ +struct rapl_counter_info_t *rapl_counter_info_perdomain; + +#define RAPL_COUNTER_FLAG_USE_MSR_SUM (1u << 1) + +struct rapl_counter_arch_info { + int feature_mask; /* Mask for testing if the counter is supported on host */ + const char *perf_subsys; + const char *perf_name; + unsigned long long msr; + unsigned long long msr_mask; + int msr_shift; /* Positive mean shift right, negative mean shift left */ + double *platform_rapl_msr_scale; /* Scale applied to values read by MSR (platform dependent, filled at runtime) */ + unsigned int rci_index; /* Maps data from perf counters to global variables */ + unsigned long long bic; + double compat_scale; /* Some counters require constant scaling to be in the same range as other, similar ones */ + unsigned long long flags; +}; + +static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { + { + .feature_mask = RAPL_PKG, + .perf_subsys = "power", + .perf_name = "energy-pkg", + .msr = MSR_PKG_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PKG, + .bic = BIC_PkgWatt | BIC_Pkg_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_AMD_F17H, + .perf_subsys = "power", + .perf_name = "energy-pkg", + .msr = MSR_PKG_ENERGY_STAT, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PKG, + .bic = BIC_PkgWatt | BIC_Pkg_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_CORE_ENERGY_STATUS, + .perf_subsys = "power", + .perf_name = "energy-cores", + .msr = MSR_PP0_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_CORES, + .bic = BIC_CorWatt | BIC_Cor_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_DRAM, + .perf_subsys = "power", + .perf_name = "energy-ram", + .msr = MSR_DRAM_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_dram_energy_units, + .rci_index = RAPL_RCI_INDEX_DRAM, + .bic = BIC_RAMWatt | BIC_RAM_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_GFX, + .perf_subsys = "power", + .perf_name = "energy-gpu", + .msr = MSR_PP1_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_GFX, + .bic = BIC_GFXWatt | BIC_GFX_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_PKG_PERF_STATUS, + .perf_subsys = NULL, + .perf_name = NULL, + .msr = MSR_PKG_PERF_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_time_units, + .rci_index = RAPL_RCI_INDEX_PKG_PERF_STATUS, + .bic = BIC_PKG__, + .compat_scale = 100.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_DRAM_PERF_STATUS, + .perf_subsys = NULL, + .perf_name = NULL, + .msr = MSR_DRAM_PERF_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_time_units, + .rci_index = RAPL_RCI_INDEX_DRAM_PERF_STATUS, + .bic = BIC_RAM__, + .compat_scale = 100.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_AMD_F17H, + .perf_subsys = NULL, + .perf_name = NULL, + .msr = MSR_CORE_ENERGY_STAT, + .msr_mask = 0xFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_CORE_ENERGY, + .bic = BIC_CorWatt | BIC_Cor_J, + .compat_scale = 1.0, + .flags = 0, + }, +}; + +struct rapl_counter { + unsigned long long raw_value; + enum rapl_unit unit; + double scale; +}; + struct thread_data { struct timeval tv_begin; struct timeval tv_end; @@ -974,7 +1178,7 @@ struct core_data { unsigned long long c7; unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */ unsigned int core_temp_c; - unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */ + struct rapl_counter core_energy; /* MSR_CORE_ENERGY_STAT */ unsigned int core_id; unsigned long long core_throt_cnt; unsigned long long counter[MAX_ADDED_COUNTERS]; @@ -989,8 +1193,8 @@ struct pkg_data { unsigned long long pc8; unsigned long long pc9; unsigned long long pc10; - unsigned long long cpu_lpi; - unsigned long long sys_lpi; + long long cpu_lpi; + long long sys_lpi; unsigned long long pkg_wtd_core_c0; unsigned long long pkg_any_core_c0; unsigned long long pkg_any_gfxe_c0; @@ -998,13 +1202,16 @@ struct pkg_data { long long gfx_rc6_ms; unsigned int gfx_mhz; unsigned int gfx_act_mhz; + long long sam_mc6_ms; + unsigned int sam_mhz; + unsigned int sam_act_mhz; unsigned int package_id; - unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */ - unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */ - unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */ - unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */ - unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ - unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ + struct rapl_counter energy_pkg; /* MSR_PKG_ENERGY_STATUS */ + struct rapl_counter energy_dram; /* MSR_DRAM_ENERGY_STATUS */ + struct rapl_counter energy_cores; /* MSR_PP0_ENERGY_STATUS */ + struct rapl_counter energy_gfx; /* MSR_PP1_ENERGY_STATUS */ + struct rapl_counter rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ + struct rapl_counter rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; unsigned int uncore_mhz; unsigned long long counter[MAX_ADDED_COUNTERS]; @@ -1150,6 +1357,38 @@ struct sys_counters { struct msr_counter *pp; } sys; +void free_sys_counters(void) +{ + struct msr_counter *p = sys.tp, *pnext = NULL; + + while (p) { + pnext = p->next; + free(p); + p = pnext; + } + + p = sys.cp, pnext = NULL; + while (p) { + pnext = p->next; + free(p); + p = pnext; + } + + p = sys.pp, pnext = NULL; + while (p) { + pnext = p->next; + free(p); + p = pnext; + } + + sys.added_thread_counters = 0; + sys.added_core_counters = 0; + sys.added_package_counters = 0; + sys.tp = NULL; + sys.cp = NULL; + sys.pp = NULL; +} + struct system_summary { struct thread_data threads; struct core_data cores; @@ -1280,34 +1519,60 @@ int get_msr_fd(int cpu) sprintf(pathname, "/dev/cpu/%d/msr", cpu); fd = open(pathname, O_RDONLY); if (fd < 0) - err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); + err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, " + "or run with --no-msr, or run as root", pathname); fd_percpu[cpu] = fd; return fd; } +static void bic_disable_msr_access(void) +{ + const unsigned long bic_msrs = + BIC_SMI | + BIC_CPU_c1 | + BIC_CPU_c3 | + BIC_CPU_c6 | + BIC_CPU_c7 | + BIC_Mod_c6 | + BIC_CoreTmp | + BIC_Totl_c0 | + BIC_Any_c0 | + BIC_GFX_c0 | + BIC_CPUGFX | + BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_PkgTmp; + + bic_enabled &= ~bic_msrs; + + free_sys_counters(); +} + static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags) { + assert(!no_perf); + return syscall(__NR_perf_event_open, hw_event, pid, cpu, group_fd, flags); } -static int perf_instr_count_open(int cpu_num) +static long open_perf_counter(int cpu, unsigned int type, unsigned int config, int group_fd, __u64 read_format) { - struct perf_event_attr pea; - int fd; + struct perf_event_attr attr; + const pid_t pid = -1; + const unsigned long flags = 0; - memset(&pea, 0, sizeof(struct perf_event_attr)); - pea.type = PERF_TYPE_HARDWARE; - pea.size = sizeof(struct perf_event_attr); - pea.config = PERF_COUNT_HW_INSTRUCTIONS; + assert(!no_perf); - /* counter for cpu_num, including user + kernel and all processes */ - fd = perf_event_open(&pea, -1, cpu_num, -1, 0); - if (fd == -1) { - warnx("capget(CAP_PERFMON) failed, try \"# setcap cap_sys_admin=ep %s\"", progname); - BIC_NOT_PRESENT(BIC_IPC); - } + memset(&attr, 0, sizeof(struct perf_event_attr)); + + attr.type = type; + attr.size = sizeof(struct perf_event_attr); + attr.config = config; + attr.disabled = 0; + attr.sample_type = PERF_SAMPLE_IDENTIFIER; + attr.read_format = read_format; + + const int fd = perf_event_open(&attr, pid, cpu, group_fd, flags); return fd; } @@ -1317,7 +1582,7 @@ int get_instr_count_fd(int cpu) if (fd_instr_count_percpu[cpu]) return fd_instr_count_percpu[cpu]; - fd_instr_count_percpu[cpu] = perf_instr_count_open(cpu); + fd_instr_count_percpu[cpu] = open_perf_counter(cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0); return fd_instr_count_percpu[cpu]; } @@ -1326,6 +1591,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) { ssize_t retval; + assert(!no_msr); + retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset); if (retval != sizeof *msr) @@ -1334,6 +1601,21 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) return 0; } +int probe_msr(int cpu, off_t offset) +{ + ssize_t retval; + unsigned long long dummy; + + assert(!no_msr); + + retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset); + + if (retval != sizeof(dummy)) + return 1; + + return 0; +} + #define MAX_DEFERRED 16 char *deferred_add_names[MAX_DEFERRED]; char *deferred_skip_names[MAX_DEFERRED]; @@ -1369,6 +1651,8 @@ void help(void) " Override default 5-second measurement interval\n" " -J, --Joules displays energy in Joules instead of Watts\n" " -l, --list list column headers only\n" + " -M, --no-msr Disable all uses of the MSR driver\n" + " -P, --no-perf Disable all uses of the perf API\n" " -n, --num_iterations num\n" " number of the measurement iterations\n" " -N, --header_iterations num\n" @@ -1573,6 +1857,15 @@ void print_header(char *delim) if (DO_BIC(BIC_GFXACTMHz)) outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_SAM_mc6)) + outp += sprintf(outp, "%sSAM%%mc6", (printed++ ? delim : "")); + + if (DO_BIC(BIC_SAMMHz)) + outp += sprintf(outp, "%sSAMMHz", (printed++ ? delim : "")); + + if (DO_BIC(BIC_SAMACTMHz)) + outp += sprintf(outp, "%sSAMAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); if (DO_BIC(BIC_Any_c0)) @@ -1671,26 +1964,35 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p outp += sprintf(outp, "SMI: %d\n", t->smi_count); for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { - outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, t->counter[i]); + outp += + sprintf(outp, "tADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num, + t->counter[i], mp->path); } } - if (c) { + if (c && is_cpu_first_thread_in_core(t, c, p)) { outp += sprintf(outp, "core: %d\n", c->core_id); outp += sprintf(outp, "c3: %016llX\n", c->c3); outp += sprintf(outp, "c6: %016llX\n", c->c6); outp += sprintf(outp, "c7: %016llX\n", c->c7); outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c); outp += sprintf(outp, "cpu_throt_count: %016llX\n", c->core_throt_cnt); - outp += sprintf(outp, "Joules: %0X\n", c->core_energy); + + const unsigned long long energy_value = c->core_energy.raw_value * c->core_energy.scale; + const double energy_scale = c->core_energy.scale; + + if (c->core_energy.unit == RAPL_UNIT_JOULES) + outp += sprintf(outp, "Joules: %0llX (scale: %lf)\n", energy_value, energy_scale); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { - outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, c->counter[i]); + outp += + sprintf(outp, "cADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num, + c->counter[i], mp->path); } outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us); } - if (p) { + if (p && is_cpu_first_core_in_package(t, c, p)) { outp += sprintf(outp, "package: %d\n", p->package_id); outp += sprintf(outp, "Weighted cores: %016llX\n", p->pkg_wtd_core_c0); @@ -1710,16 +2012,18 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); - outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg); - outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores); - outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx); - outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram); - outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status); - outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status); + outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg.raw_value); + outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores.raw_value); + outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx.raw_value); + outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram.raw_value); + outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status.raw_value); + outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status.raw_value); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - outp += sprintf(outp, "pADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, p->counter[i]); + outp += + sprintf(outp, "pADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num, + p->counter[i], mp->path); } } @@ -1728,6 +2032,23 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p return 0; } +double rapl_counter_get_value(const struct rapl_counter *c, enum rapl_unit desired_unit, double interval) +{ + assert(desired_unit != RAPL_UNIT_INVALID); + + /* + * For now we don't expect anything other than joules, + * so just simplify the logic. + */ + assert(c->unit == RAPL_UNIT_JOULES); + + const double scaled = c->raw_value * c->scale; + + if (desired_unit == RAPL_UNIT_WATTS) + return scaled / interval; + return scaled; +} + /* * column formatting convention & formats */ @@ -1921,9 +2242,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl) outp += - sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); + sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&c->core_energy, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&c->core_energy, RAPL_UNIT_JOULES, interval_float)); /* print per-package data only for 1st core in package */ if (!is_cpu_first_core_in_package(t, c, p)) @@ -1951,6 +2274,24 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_GFXACTMHz)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz); + /* SAMmc6 */ + if (DO_BIC(BIC_SAM_mc6)) { + if (p->sam_mc6_ms == -1) { /* detect GFX counter reset */ + outp += sprintf(outp, "%s**.**", (printed++ ? delim : "")); + } else { + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + p->sam_mc6_ms / 10.0 / interval_float); + } + } + + /* SAMMHz */ + if (DO_BIC(BIC_SAMMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_mhz); + + /* SAMACTMHz */ + if (DO_BIC(BIC_SAMACTMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_act_mhz); + /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0 / tsc); @@ -1976,43 +2317,59 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data if (DO_BIC(BIC_Pkgpc10)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10 / tsc); - if (DO_BIC(BIC_CPU_LPI)) - outp += - sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float); - if (DO_BIC(BIC_SYS_LPI)) - outp += - sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float); + if (DO_BIC(BIC_CPU_LPI)) { + if (p->cpu_lpi >= 0) + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + 100.0 * p->cpu_lpi / 1000000.0 / interval_float); + else + outp += sprintf(outp, "%s(neg)", (printed++ ? delim : "")); + } + if (DO_BIC(BIC_SYS_LPI)) { + if (p->sys_lpi >= 0) + outp += + sprintf(outp, "%s%.2f", (printed++ ? delim : ""), + 100.0 * p->sys_lpi / 1000000.0 / interval_float); + else + outp += sprintf(outp, "%s(neg)", (printed++ ? delim : "")); + } if (DO_BIC(BIC_PkgWatt)) outp += - sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float); - + sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl) outp += - sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float); + sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_GFXWatt)) outp += - sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float); + sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_RAMWatt)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), - p->energy_dram * rapl_dram_energy_units / interval_float); + rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_Pkg_J)) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_JOULES, interval_float)); if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_JOULES, interval_float)); if (DO_BIC(BIC_GFX_J)) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_JOULES, interval_float)); if (DO_BIC(BIC_RAM_J)) - outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units); + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), + rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_JOULES, interval_float)); if (DO_BIC(BIC_PKG__)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), - 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float); + rapl_counter_get_value(&p->rapl_pkg_perf_status, RAPL_UNIT_WATTS, interval_float)); if (DO_BIC(BIC_RAM__)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), - 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float); + rapl_counter_get_value(&p->rapl_dram_perf_status, RAPL_UNIT_WATTS, interval_float)); /* UncMHz */ if (DO_BIC(BIC_UNCORE_MHZ)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->uncore_mhz); @@ -2121,12 +2478,22 @@ int delta_package(struct pkg_data *new, struct pkg_data *old) old->gfx_mhz = new->gfx_mhz; old->gfx_act_mhz = new->gfx_act_mhz; - old->energy_pkg = new->energy_pkg - old->energy_pkg; - old->energy_cores = new->energy_cores - old->energy_cores; - old->energy_gfx = new->energy_gfx - old->energy_gfx; - old->energy_dram = new->energy_dram - old->energy_dram; - old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status; - old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status; + /* flag an error when mc6 counter resets/wraps */ + if (old->sam_mc6_ms > new->sam_mc6_ms) + old->sam_mc6_ms = -1; + else + old->sam_mc6_ms = new->sam_mc6_ms - old->sam_mc6_ms; + + old->sam_mhz = new->sam_mhz; + old->sam_act_mhz = new->sam_act_mhz; + + old->energy_pkg.raw_value = new->energy_pkg.raw_value - old->energy_pkg.raw_value; + old->energy_cores.raw_value = new->energy_cores.raw_value - old->energy_cores.raw_value; + old->energy_gfx.raw_value = new->energy_gfx.raw_value - old->energy_gfx.raw_value; + old->energy_dram.raw_value = new->energy_dram.raw_value - old->energy_dram.raw_value; + old->rapl_pkg_perf_status.raw_value = new->rapl_pkg_perf_status.raw_value - old->rapl_pkg_perf_status.raw_value; + old->rapl_dram_perf_status.raw_value = + new->rapl_dram_perf_status.raw_value - old->rapl_dram_perf_status.raw_value; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -2150,7 +2517,7 @@ void delta_core(struct core_data *new, struct core_data *old) old->core_throt_cnt = new->core_throt_cnt; old->mc6_us = new->mc6_us - old->mc6_us; - DELTA_WRAP32(new->core_energy, old->core_energy); + DELTA_WRAP32(new->core_energy.raw_value, old->core_energy.raw_value); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -2277,6 +2644,13 @@ int delta_cpu(struct thread_data *t, struct core_data *c, return retval; } +void rapl_counter_clear(struct rapl_counter *c) +{ + c->raw_value = 0; + c->scale = 0.0; + c->unit = RAPL_UNIT_INVALID; +} + void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { int i; @@ -2304,7 +2678,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data c->c7 = 0; c->mc6_us = 0; c->core_temp_c = 0; - c->core_energy = 0; + rapl_counter_clear(&c->core_energy); c->core_throt_cnt = 0; p->pkg_wtd_core_c0 = 0; @@ -2325,18 +2699,21 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->cpu_lpi = 0; p->sys_lpi = 0; - p->energy_pkg = 0; - p->energy_dram = 0; - p->energy_cores = 0; - p->energy_gfx = 0; - p->rapl_pkg_perf_status = 0; - p->rapl_dram_perf_status = 0; + rapl_counter_clear(&p->energy_pkg); + rapl_counter_clear(&p->energy_dram); + rapl_counter_clear(&p->energy_cores); + rapl_counter_clear(&p->energy_gfx); + rapl_counter_clear(&p->rapl_pkg_perf_status); + rapl_counter_clear(&p->rapl_dram_perf_status); p->pkg_temp_c = 0; p->gfx_rc6_ms = 0; p->uncore_mhz = 0; p->gfx_mhz = 0; p->gfx_act_mhz = 0; + p->sam_mc6_ms = 0; + p->sam_mhz = 0; + p->sam_act_mhz = 0; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -2347,6 +2724,20 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->counter[i] = 0; } +void rapl_counter_accumulate(struct rapl_counter *dst, const struct rapl_counter *src) +{ + /* Copy unit and scale from src if dst is not initialized */ + if (dst->unit == RAPL_UNIT_INVALID) { + dst->unit = src->unit; + dst->scale = src->scale; + } + + assert(dst->unit == src->unit); + assert(dst->scale == src->scale); + + dst->raw_value += src->raw_value; +} + int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { int i; @@ -2393,7 +2784,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c); average.cores.core_throt_cnt = MAX(average.cores.core_throt_cnt, c->core_throt_cnt); - average.cores.core_energy += c->core_energy; + rapl_counter_accumulate(&average.cores.core_energy, &c->core_energy); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -2428,25 +2819,29 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.packages.cpu_lpi = p->cpu_lpi; average.packages.sys_lpi = p->sys_lpi; - average.packages.energy_pkg += p->energy_pkg; - average.packages.energy_dram += p->energy_dram; - average.packages.energy_cores += p->energy_cores; - average.packages.energy_gfx += p->energy_gfx; + rapl_counter_accumulate(&average.packages.energy_pkg, &p->energy_pkg); + rapl_counter_accumulate(&average.packages.energy_dram, &p->energy_dram); + rapl_counter_accumulate(&average.packages.energy_cores, &p->energy_cores); + rapl_counter_accumulate(&average.packages.energy_gfx, &p->energy_gfx); average.packages.gfx_rc6_ms = p->gfx_rc6_ms; average.packages.uncore_mhz = p->uncore_mhz; average.packages.gfx_mhz = p->gfx_mhz; average.packages.gfx_act_mhz = p->gfx_act_mhz; + average.packages.sam_mc6_ms = p->sam_mc6_ms; + average.packages.sam_mhz = p->sam_mhz; + average.packages.sam_act_mhz = p->sam_act_mhz; average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c); - average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status; - average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status; + rapl_counter_accumulate(&average.packages.rapl_pkg_perf_status, &p->rapl_pkg_perf_status); + rapl_counter_accumulate(&average.packages.rapl_dram_perf_status, &p->rapl_dram_perf_status); for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) - continue; - average.packages.counter[i] += p->counter[i]; + if ((mp->format == FORMAT_RAW) && (topo.num_packages == 0)) + average.packages.counter[i] = p->counter[i]; + else + average.packages.counter[i] += p->counter[i]; } return 0; } @@ -2578,6 +2973,7 @@ unsigned long long snapshot_sysfs_counter(char *path) int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp) { if (mp->msr_num != 0) { + assert(!no_msr); if (get_msr(cpu, mp->msr_num, counterp)) return -1; } else { @@ -2599,7 +2995,7 @@ unsigned long long get_uncore_mhz(int package, int die) { char path[128]; - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/current_freq_khz", package, + sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d/current_freq_khz", package, die); return (snapshot_sysfs_counter(path) / 1000); @@ -2627,6 +3023,9 @@ int get_epb(int cpu) return epb; msr_fallback: + if (no_msr) + return -1; + get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr); return msr & 0xf; @@ -2700,6 +3099,351 @@ int get_core_throt_cnt(int cpu, unsigned long long *cnt) return 0; } +struct amperf_group_fd { + int aperf; /* Also the group descriptor */ + int mperf; +}; + +static int read_perf_counter_info(const char *const path, const char *const parse_format, void *value_ptr) +{ + int fdmt; + int bytes_read; + char buf[64]; + int ret = -1; + + fdmt = open(path, O_RDONLY, 0); + if (fdmt == -1) { + if (debug) + fprintf(stderr, "Failed to parse perf counter info %s\n", path); + ret = -1; + goto cleanup_and_exit; + } + + bytes_read = read(fdmt, buf, sizeof(buf) - 1); + if (bytes_read <= 0 || bytes_read >= (int)sizeof(buf)) { + if (debug) + fprintf(stderr, "Failed to parse perf counter info %s\n", path); + ret = -1; + goto cleanup_and_exit; + } + + buf[bytes_read] = '\0'; + + if (sscanf(buf, parse_format, value_ptr) != 1) { + if (debug) + fprintf(stderr, "Failed to parse perf counter info %s\n", path); + ret = -1; + goto cleanup_and_exit; + } + + ret = 0; + +cleanup_and_exit: + close(fdmt); + return ret; +} + +static unsigned int read_perf_counter_info_n(const char *const path, const char *const parse_format) +{ + unsigned int v; + int status; + + status = read_perf_counter_info(path, parse_format, &v); + if (status) + v = -1; + + return v; +} + +static unsigned int read_msr_type(void) +{ + const char *const path = "/sys/bus/event_source/devices/msr/type"; + const char *const format = "%u"; + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_aperf_config(void) +{ + const char *const path = "/sys/bus/event_source/devices/msr/events/aperf"; + const char *const format = "event=%x"; + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_mperf_config(void) +{ + const char *const path = "/sys/bus/event_source/devices/msr/events/mperf"; + const char *const format = "event=%x"; + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_perf_type(const char *subsys) +{ + const char *const path_format = "/sys/bus/event_source/devices/%s/type"; + const char *const format = "%u"; + char path[128]; + + snprintf(path, sizeof(path), path_format, subsys); + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_rapl_config(const char *subsys, const char *event_name) +{ + const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s"; + const char *const format = "event=%x"; + char path[128]; + + snprintf(path, sizeof(path), path_format, subsys, event_name); + + return read_perf_counter_info_n(path, format); +} + +static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_name) +{ + const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.unit"; + const char *const format = "%s"; + char path[128]; + char unit_buffer[16]; + + snprintf(path, sizeof(path), path_format, subsys, event_name); + + read_perf_counter_info(path, format, &unit_buffer); + if (strcmp("Joules", unit_buffer) == 0) + return RAPL_UNIT_JOULES; + + return RAPL_UNIT_INVALID; +} + +static double read_perf_rapl_scale(const char *subsys, const char *event_name) +{ + const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.scale"; + const char *const format = "%lf"; + char path[128]; + double scale; + + snprintf(path, sizeof(path), path_format, subsys, event_name); + + if (read_perf_counter_info(path, format, &scale)) + return 0.0; + + return scale; +} + +static struct amperf_group_fd open_amperf_fd(int cpu) +{ + const unsigned int msr_type = read_msr_type(); + const unsigned int aperf_config = read_aperf_config(); + const unsigned int mperf_config = read_mperf_config(); + struct amperf_group_fd fds = {.aperf = -1, .mperf = -1 }; + + fds.aperf = open_perf_counter(cpu, msr_type, aperf_config, -1, PERF_FORMAT_GROUP); + fds.mperf = open_perf_counter(cpu, msr_type, mperf_config, fds.aperf, PERF_FORMAT_GROUP); + + return fds; +} + +static int get_amperf_fd(int cpu) +{ + assert(fd_amperf_percpu); + + if (fd_amperf_percpu[cpu].aperf) + return fd_amperf_percpu[cpu].aperf; + + fd_amperf_percpu[cpu] = open_amperf_fd(cpu); + + return fd_amperf_percpu[cpu].aperf; +} + +/* Read APERF, MPERF and TSC using the perf API. */ +static int read_aperf_mperf_tsc_perf(struct thread_data *t, int cpu) +{ + union { + struct { + unsigned long nr_entries; + unsigned long aperf; + unsigned long mperf; + }; + + unsigned long as_array[3]; + } cnt; + + const int fd_amperf = get_amperf_fd(cpu); + + /* + * Read the TSC with rdtsc, because we want the absolute value and not + * the offset from the start of the counter. + */ + t->tsc = rdtsc(); + + const int n = read(fd_amperf, &cnt.as_array[0], sizeof(cnt.as_array)); + + if (n != sizeof(cnt.as_array)) + return -2; + + t->aperf = cnt.aperf * aperf_mperf_multiplier; + t->mperf = cnt.mperf * aperf_mperf_multiplier; + + return 0; +} + +/* Read APERF, MPERF and TSC using the MSR driver and rdtsc instruction. */ +static int read_aperf_mperf_tsc_msr(struct thread_data *t, int cpu) +{ + unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; + int aperf_mperf_retry_count = 0; + + /* + * The TSC, APERF and MPERF must be read together for + * APERF/MPERF and MPERF/TSC to give accurate results. + * + * Unfortunately, APERF and MPERF are read by + * individual system call, so delays may occur + * between them. If the time to read them + * varies by a large amount, we re-read them. + */ + + /* + * This initial dummy APERF read has been seen to + * reduce jitter in the subsequent reads. + */ + + if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) + return -3; + +retry: + t->tsc = rdtsc(); /* re-read close to APERF */ + + tsc_before = t->tsc; + + if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) + return -3; + + tsc_between = rdtsc(); + + if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf)) + return -4; + + tsc_after = rdtsc(); + + aperf_time = tsc_between - tsc_before; + mperf_time = tsc_after - tsc_between; + + /* + * If the system call latency to read APERF and MPERF + * differ by more than 2x, then try again. + */ + if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) { + aperf_mperf_retry_count++; + if (aperf_mperf_retry_count < 5) + goto retry; + else + warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time); + } + aperf_mperf_retry_count = 0; + + t->aperf = t->aperf * aperf_mperf_multiplier; + t->mperf = t->mperf * aperf_mperf_multiplier; + + return 0; +} + +size_t rapl_counter_info_count_perf(const struct rapl_counter_info_t *rci) +{ + size_t ret = 0; + + for (int i = 0; i < NUM_RAPL_COUNTERS; ++i) + if (rci->source[i] == RAPL_SOURCE_PERF) + ++ret; + + return ret; +} + +void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci, unsigned int idx) +{ + rc->raw_value = rci->data[idx]; + rc->unit = rci->unit[idx]; + rc->scale = rci->scale[idx]; +} + +int get_rapl_counters(int cpu, int domain, struct core_data *c, struct pkg_data *p) +{ + unsigned long long perf_data[NUM_RAPL_COUNTERS + 1]; + struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain]; + + if (debug) + fprintf(stderr, "%s: cpu%d domain%d\n", __func__, cpu, domain); + + assert(rapl_counter_info_perdomain); + + /* + * If we have any perf counters to read, read them all now, in bulk + */ + if (rci->fd_perf != -1) { + size_t num_perf_counters = rapl_counter_info_count_perf(rci); + const ssize_t expected_read_size = (num_perf_counters + 1) * sizeof(unsigned long long); + const ssize_t actual_read_size = read(rci->fd_perf, &perf_data[0], sizeof(perf_data)); + + if (actual_read_size != expected_read_size) + err(-1, "%s: failed to read perf_data (%zu %zu)", __func__, expected_read_size, + actual_read_size); + } + + for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) { + switch (rci->source[i]) { + case RAPL_SOURCE_NONE: + break; + + case RAPL_SOURCE_PERF: + assert(pi < ARRAY_SIZE(perf_data)); + assert(rci->fd_perf != -1); + + if (debug) + fprintf(stderr, "Reading rapl counter via perf at %u (%llu %e %lf)\n", + i, perf_data[pi], rci->scale[i], perf_data[pi] * rci->scale[i]); + + rci->data[i] = perf_data[pi]; + + ++pi; + break; + + case RAPL_SOURCE_MSR: + if (debug) + fprintf(stderr, "Reading rapl counter via msr at %u\n", i); + + assert(!no_msr); + if (rci->flags[i] & RAPL_COUNTER_FLAG_USE_MSR_SUM) { + if (get_msr_sum(cpu, rci->msr[i], &rci->data[i])) + return -13 - i; + } else { + if (get_msr(cpu, rci->msr[i], &rci->data[i])) + return -13 - i; + } + + rci->data[i] &= rci->msr_mask[i]; + if (rci->msr_shift[i] >= 0) + rci->data[i] >>= abs(rci->msr_shift[i]); + else + rci->data[i] <<= abs(rci->msr_shift[i]); + + break; + } + } + + _Static_assert(NUM_RAPL_COUNTERS == 7); + write_rapl_counter(&p->energy_pkg, rci, RAPL_RCI_INDEX_ENERGY_PKG); + write_rapl_counter(&p->energy_cores, rci, RAPL_RCI_INDEX_ENERGY_CORES); + write_rapl_counter(&p->energy_dram, rci, RAPL_RCI_INDEX_DRAM); + write_rapl_counter(&p->energy_gfx, rci, RAPL_RCI_INDEX_GFX); + write_rapl_counter(&p->rapl_pkg_perf_status, rci, RAPL_RCI_INDEX_PKG_PERF_STATUS); + write_rapl_counter(&p->rapl_dram_perf_status, rci, RAPL_RCI_INDEX_DRAM_PERF_STATUS); + write_rapl_counter(&c->core_energy, rci, RAPL_RCI_INDEX_CORE_ENERGY); + + return 0; +} + /* * get_counters(...) * migrate to cpu @@ -2709,12 +3453,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) { int cpu = t->cpu_id; unsigned long long msr; - int aperf_mperf_retry_count = 0; struct msr_counter *mp; int i; + int status; if (cpu_migrate(cpu)) { - fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu); + fprintf(outf, "%s: Could not migrate to CPU %d\n", __func__, cpu); return -1; } @@ -2722,63 +3466,26 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (first_counter_read) get_apic_id(t); -retry: + t->tsc = rdtsc(); /* we are running on local CPU of interest */ if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC) || soft_c1_residency_display(BIC_Avg_MHz)) { - unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; - - /* - * The TSC, APERF and MPERF must be read together for - * APERF/MPERF and MPERF/TSC to give accurate results. - * - * Unfortunately, APERF and MPERF are read by - * individual system call, so delays may occur - * between them. If the time to read them - * varies by a large amount, we re-read them. - */ - - /* - * This initial dummy APERF read has been seen to - * reduce jitter in the subsequent reads. - */ - - if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) - return -3; - - t->tsc = rdtsc(); /* re-read close to APERF */ - - tsc_before = t->tsc; + int status = -1; - if (get_msr(cpu, MSR_IA32_APERF, &t->aperf)) - return -3; + assert(!no_perf || !no_msr); - tsc_between = rdtsc(); - - if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf)) - return -4; - - tsc_after = rdtsc(); - - aperf_time = tsc_between - tsc_before; - mperf_time = tsc_after - tsc_between; - - /* - * If the system call latency to read APERF and MPERF - * differ by more than 2x, then try again. - */ - if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) { - aperf_mperf_retry_count++; - if (aperf_mperf_retry_count < 5) - goto retry; - else - warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time); + switch (amperf_source) { + case AMPERF_SOURCE_PERF: + status = read_aperf_mperf_tsc_perf(t, cpu); + break; + case AMPERF_SOURCE_MSR: + status = read_aperf_mperf_tsc_msr(t, cpu); + break; } - aperf_mperf_retry_count = 0; - t->aperf = t->aperf * aperf_mperf_multiplier; - t->mperf = t->mperf * aperf_mperf_multiplier; + if (status != 0) + return status; } if (DO_BIC(BIC_IPC)) @@ -2806,6 +3513,12 @@ retry: if (!is_cpu_first_thread_in_core(t, c, p)) goto done; + if (platform->has_per_core_rapl) { + status = get_rapl_counters(cpu, c->core_id, c, p); + if (status != 0) + return status; + } + if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; @@ -2846,12 +3559,6 @@ retry: if (DO_BIC(BIC_CORE_THROT_CNT)) get_core_throt_cnt(cpu, &c->core_throt_cnt); - if (platform->rapl_msrs & RAPL_AMD_F17H) { - if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr)) - return -14; - c->core_energy = msr & 0xFFFFFFFF; - } - for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &c->counter[i])) return -10; @@ -2911,59 +3618,39 @@ retry: if (DO_BIC(BIC_SYS_LPI)) p->sys_lpi = cpuidle_cur_sys_lpi_us; - if (platform->rapl_msrs & RAPL_PKG) { - if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr)) - return -13; - p->energy_pkg = msr; - } - if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) { - if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr)) - return -14; - p->energy_cores = msr; - } - if (platform->rapl_msrs & RAPL_DRAM) { - if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) - return -15; - p->energy_dram = msr; - } - if (platform->rapl_msrs & RAPL_GFX) { - if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr)) - return -16; - p->energy_gfx = msr; - } - if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) { - if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr)) - return -16; - p->rapl_pkg_perf_status = msr; - } - if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) { - if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr)) - return -16; - p->rapl_dram_perf_status = msr; - } - if (platform->rapl_msrs & RAPL_AMD_F17H) { - if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr)) - return -13; - p->energy_pkg = msr; + if (!platform->has_per_core_rapl) { + status = get_rapl_counters(cpu, p->package_id, c, p); + if (status != 0) + return status; } + if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) return -17; p->pkg_temp_c = tj_max - ((msr >> 16) & 0x7F); } - if (DO_BIC(BIC_GFX_rc6)) - p->gfx_rc6_ms = gfx_cur_rc6_ms; - /* n.b. assume die0 uncore frequency applies to whole package */ if (DO_BIC(BIC_UNCORE_MHZ)) p->uncore_mhz = get_uncore_mhz(p->package_id, 0); + if (DO_BIC(BIC_GFX_rc6)) + p->gfx_rc6_ms = gfx_info[GFX_rc6].val_ull; + if (DO_BIC(BIC_GFXMHz)) - p->gfx_mhz = gfx_cur_mhz; + p->gfx_mhz = gfx_info[GFX_MHz].val; if (DO_BIC(BIC_GFXACTMHz)) - p->gfx_act_mhz = gfx_act_mhz; + p->gfx_act_mhz = gfx_info[GFX_ACTMHz].val; + + if (DO_BIC(BIC_SAM_mc6)) + p->sam_mc6_ms = gfx_info[SAM_mc6].val_ull; + + if (DO_BIC(BIC_SAMMHz)) + p->sam_mhz = gfx_info[SAM_MHz].val; + + if (DO_BIC(BIC_SAMACTMHz)) + p->sam_act_mhz = gfx_info[SAM_ACTMHz].val; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &p->counter[i])) @@ -3053,7 +3740,7 @@ void probe_cst_limit(void) unsigned long long msr; int *pkg_cstate_limits; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; switch (platform->cst_limit) { @@ -3097,7 +3784,7 @@ static void dump_platform_info(void) unsigned long long msr; unsigned int ratio; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; get_msr(base_cpu, MSR_PLATFORM_INFO, &msr); @@ -3115,7 +3802,7 @@ static void dump_power_ctl(void) { unsigned long long msr; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr); @@ -3321,7 +4008,7 @@ static void dump_cst_cfg(void) { unsigned long long msr; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); @@ -3393,7 +4080,7 @@ void print_irtl(void) { unsigned long long msr; - if (!platform->has_irtl_msrs) + if (!platform->has_irtl_msrs || no_msr) return; if (platform->supported_cstates & PC3) { @@ -3443,12 +4130,64 @@ void free_fd_percpu(void) { int i; + if (!fd_percpu) + return; + for (i = 0; i < topo.max_cpu_num + 1; ++i) { if (fd_percpu[i] != 0) close(fd_percpu[i]); } free(fd_percpu); + fd_percpu = NULL; +} + +void free_fd_amperf_percpu(void) +{ + int i; + + if (!fd_amperf_percpu) + return; + + for (i = 0; i < topo.max_cpu_num + 1; ++i) { + if (fd_amperf_percpu[i].mperf != 0) + close(fd_amperf_percpu[i].mperf); + + if (fd_amperf_percpu[i].aperf != 0) + close(fd_amperf_percpu[i].aperf); + } + + free(fd_amperf_percpu); + fd_amperf_percpu = NULL; +} + +void free_fd_instr_count_percpu(void) +{ + if (!fd_instr_count_percpu) + return; + + for (int i = 0; i < topo.max_cpu_num + 1; ++i) { + if (fd_instr_count_percpu[i] != 0) + close(fd_instr_count_percpu[i]); + } + + free(fd_instr_count_percpu); + fd_instr_count_percpu = NULL; +} + +void free_fd_rapl_percpu(void) +{ + if (!rapl_counter_info_perdomain) + return; + + const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages; + + for (int domain_id = 0; domain_id < num_domains; ++domain_id) { + if (rapl_counter_info_perdomain[domain_id].fd_perf != -1) + close(rapl_counter_info_perdomain[domain_id].fd_perf); + } + + free(rapl_counter_info_perdomain); } void free_all_buffers(void) @@ -3492,6 +4231,9 @@ void free_all_buffers(void) outp = NULL; free_fd_percpu(); + free_fd_instr_count_percpu(); + free_fd_amperf_percpu(); + free_fd_rapl_percpu(); free(irq_column_2_cpu); free(irqs_per_cpu); @@ -3825,11 +4567,17 @@ static void update_effective_set(bool startup) err(1, "%s: cpu str malformat %s\n", PATH_EFFECTIVE_CPUS, cpu_effective_str); } +void linux_perf_init(void); +void rapl_perf_init(void); + void re_initialize(void) { free_all_buffers(); setup_all_buffers(false); - fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus); + linux_perf_init(); + rapl_perf_init(); + fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, + topo.allowed_cpus); } void set_max_cpu_num(void) @@ -3940,85 +4688,43 @@ int snapshot_proc_interrupts(void) } /* - * snapshot_gfx_rc6_ms() + * snapshot_graphics() * - * record snapshot of - * /sys/class/drm/card0/power/rc6_residency_ms + * record snapshot of specified graphics sysfs knob * * return 1 if config change requires a restart, else return 0 */ -int snapshot_gfx_rc6_ms(void) +int snapshot_graphics(int idx) { FILE *fp; int retval; - fp = fopen_or_die("/sys/class/drm/card0/power/rc6_residency_ms", "r"); - - retval = fscanf(fp, "%lld", &gfx_cur_rc6_ms); - if (retval != 1) - err(1, "GFX rc6"); - - fclose(fp); - - return 0; -} - -/* - * snapshot_gfx_mhz() - * - * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz - * when /sys/class/drm/card0/gt_cur_freq_mhz is not available. - * - * return 1 if config change requires a restart, else return 0 - */ -int snapshot_gfx_mhz(void) -{ - static FILE *fp; - int retval; - - if (fp == NULL) { - fp = fopen("/sys/class/drm/card0/gt_cur_freq_mhz", "r"); - if (!fp) - fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r"); - } else { - rewind(fp); - fflush(fp); - } - - retval = fscanf(fp, "%d", &gfx_cur_mhz); - if (retval != 1) - err(1, "GFX MHz"); - - return 0; -} - -/* - * snapshot_gfx_cur_mhz() - * - * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz - * when /sys/class/drm/card0/gt_act_freq_mhz is not available. - * - * return 1 if config change requires a restart, else return 0 - */ -int snapshot_gfx_act_mhz(void) -{ - static FILE *fp; - int retval; - - if (fp == NULL) { - fp = fopen("/sys/class/drm/card0/gt_act_freq_mhz", "r"); - if (!fp) - fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); - } else { - rewind(fp); - fflush(fp); + switch (idx) { + case GFX_rc6: + case SAM_mc6: + fp = fopen_or_die(gfx_info[idx].path, "r"); + retval = fscanf(fp, "%lld", &gfx_info[idx].val_ull); + if (retval != 1) + err(1, "rc6"); + fclose(fp); + return 0; + case GFX_MHz: + case GFX_ACTMHz: + case SAM_MHz: + case SAM_ACTMHz: + if (gfx_info[idx].fp == NULL) { + gfx_info[idx].fp = fopen_or_die(gfx_info[idx].path, "r"); + } else { + rewind(gfx_info[idx].fp); + fflush(gfx_info[idx].fp); + } + retval = fscanf(gfx_info[idx].fp, "%d", &gfx_info[idx].val); + if (retval != 1) + err(1, "MHz"); + return 0; + default: + return -EINVAL; } - - retval = fscanf(fp, "%d", &gfx_act_mhz); - if (retval != 1) - err(1, "GFX ACT MHz"); - - return 0; } /* @@ -4083,13 +4789,22 @@ int snapshot_proc_sysfs_files(void) return 1; if (DO_BIC(BIC_GFX_rc6)) - snapshot_gfx_rc6_ms(); + snapshot_graphics(GFX_rc6); if (DO_BIC(BIC_GFXMHz)) - snapshot_gfx_mhz(); + snapshot_graphics(GFX_MHz); if (DO_BIC(BIC_GFXACTMHz)) - snapshot_gfx_act_mhz(); + snapshot_graphics(GFX_ACTMHz); + + if (DO_BIC(BIC_SAM_mc6)) + snapshot_graphics(SAM_mc6); + + if (DO_BIC(BIC_SAMMHz)) + snapshot_graphics(SAM_MHz); + + if (DO_BIC(BIC_SAMACTMHz)) + snapshot_graphics(SAM_ACTMHz); if (DO_BIC(BIC_CPU_LPI)) snapshot_cpu_lpi_us(); @@ -4173,6 +4888,8 @@ int get_msr_sum(int cpu, off_t offset, unsigned long long *msr) int ret, idx; unsigned long long msr_cur, msr_last; + assert(!no_msr); + if (!per_cpu_msr_sum) return 1; @@ -4201,6 +4918,8 @@ static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg UNUSED(c); UNUSED(p); + assert(!no_msr); + for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) { unsigned long long msr_cur, msr_last; off_t offset; @@ -4280,7 +4999,8 @@ release_msr: /* * set_my_sched_priority(pri) - * return previous + * return previous priority on success + * return value < -20 on failure */ int set_my_sched_priority(int priority) { @@ -4290,16 +5010,16 @@ int set_my_sched_priority(int priority) errno = 0; original_priority = getpriority(PRIO_PROCESS, 0); if (errno && (original_priority == -1)) - err(errno, "getpriority"); + return -21; retval = setpriority(PRIO_PROCESS, 0, priority); if (retval) - errx(retval, "capget(CAP_SYS_NICE) failed,try \"# setcap cap_sys_nice=ep %s\"", progname); + return -21; errno = 0; retval = getpriority(PRIO_PROCESS, 0); if (retval != priority) - err(retval, "getpriority(%d) != setpriority(%d)", retval, priority); + return -21; return original_priority; } @@ -4314,6 +5034,9 @@ void turbostat_loop() /* * elevate own priority for interval mode + * + * ignore on error - we probably don't have permission to set it, but + * it's not a big deal */ set_my_sched_priority(-20); @@ -4399,10 +5122,13 @@ void check_dev_msr() struct stat sb; char pathname[32]; + if (no_msr) + return; + sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); if (stat(pathname, &sb)) if (system("/sbin/modprobe msr > /dev/null 2>&1")) - err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); + no_msr = 1; } /* @@ -4414,47 +5140,51 @@ int check_for_cap_sys_rawio(void) { cap_t caps; cap_flag_value_t cap_flag_value; + int ret = 0; caps = cap_get_proc(); if (caps == NULL) - err(-6, "cap_get_proc\n"); + return 1; - if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) - err(-6, "cap_get\n"); + if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) { + ret = 1; + goto free_and_exit; + } if (cap_flag_value != CAP_SET) { - warnx("capget(CAP_SYS_RAWIO) failed," " try \"# setcap cap_sys_rawio=ep %s\"", progname); - return 1; + ret = 1; + goto free_and_exit; } +free_and_exit: if (cap_free(caps) == -1) err(-6, "cap_free\n"); - return 0; + return ret; } -void check_permissions(void) +void check_msr_permission(void) { - int do_exit = 0; + int failed = 0; char pathname[32]; + if (no_msr) + return; + /* check for CAP_SYS_RAWIO */ - do_exit += check_for_cap_sys_rawio(); + failed += check_for_cap_sys_rawio(); /* test file permissions */ sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); if (euidaccess(pathname, R_OK)) { - do_exit++; - warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr"); + failed++; } - /* if all else fails, thell them to be root */ - if (do_exit) - if (getuid() != 0) - warnx("... or simply run as root"); - - if (do_exit) - exit(-6); + if (failed) { + warnx("Failed to access %s. Some of the counters may not be available\n" + "\tRun as root to enable them or use %s to disable the access explicitly", pathname, "--no-msr"); + no_msr = 1; + } } void probe_bclk(void) @@ -4462,7 +5192,7 @@ void probe_bclk(void) unsigned long long msr; unsigned int base_ratio; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; if (platform->bclk_freq == BCLK_100MHZ) @@ -4502,7 +5232,7 @@ static void dump_turbo_ratio_info(void) if (!has_turbo) return; - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) return; if (platform->trl_msrs & TRL_LIMIT2) @@ -4567,20 +5297,15 @@ static void dump_sysfs_file(char *path) static void probe_intel_uncore_frequency(void) { int i, j; - char path[128]; + char path[256]; if (!genuine_intel) return; - if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK)) - return; - - /* Cluster level sysfs not supported yet. */ - if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK)) - return; + if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK)) + goto probe_cluster; - if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK)) - BIC_PRESENT(BIC_UNCORE_MHZ); + BIC_PRESENT(BIC_UNCORE_MHZ); if (quiet) return; @@ -4588,40 +5313,178 @@ static void probe_intel_uncore_frequency(void) for (i = 0; i < topo.num_packages; ++i) { for (j = 0; j < topo.num_die; ++j) { int k, l; + char path_base[128]; + + sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d", i, + j); - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/min_freq_khz", - i, j); + sprintf(path, "%s/min_freq_khz", path_base); k = read_sysfs_int(path); - sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/max_freq_khz", - i, j); + sprintf(path, "%s/max_freq_khz", path_base); l = read_sysfs_int(path); - fprintf(outf, "Uncore Frequency pkg%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000); + fprintf(outf, "Uncore Frequency package%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000); - sprintf(path, - "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_min_freq_khz", - i, j); + sprintf(path, "%s/initial_min_freq_khz", path_base); k = read_sysfs_int(path); - sprintf(path, - "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_max_freq_khz", - i, j); + sprintf(path, "%s/initial_max_freq_khz", path_base); l = read_sysfs_int(path); - fprintf(outf, "(%d - %d MHz)\n", k / 1000, l / 1000); + fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000); + + sprintf(path, "%s/current_freq_khz", path_base); + k = read_sysfs_int(path); + fprintf(outf, " %d MHz\n", k / 1000); } } + return; + +probe_cluster: + if (access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00/current_freq_khz", R_OK)) + return; + + if (quiet) + return; + + for (i = 0;; ++i) { + int k, l; + char path_base[128]; + int package_id, domain_id, cluster_id; + + sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/uncore%02d", i); + + if (access(path_base, R_OK)) + break; + + sprintf(path, "%s/package_id", path_base); + package_id = read_sysfs_int(path); + + sprintf(path, "%s/domain_id", path_base); + domain_id = read_sysfs_int(path); + + sprintf(path, "%s/fabric_cluster_id", path_base); + cluster_id = read_sysfs_int(path); + + sprintf(path, "%s/min_freq_khz", path_base); + k = read_sysfs_int(path); + sprintf(path, "%s/max_freq_khz", path_base); + l = read_sysfs_int(path); + fprintf(outf, "Uncore Frequency package%d domain%d cluster%d: %d - %d MHz ", package_id, domain_id, + cluster_id, k / 1000, l / 1000); + + sprintf(path, "%s/initial_min_freq_khz", path_base); + k = read_sysfs_int(path); + sprintf(path, "%s/initial_max_freq_khz", path_base); + l = read_sysfs_int(path); + fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000); + + sprintf(path, "%s/current_freq_khz", path_base); + k = read_sysfs_int(path); + fprintf(outf, " %d MHz\n", k / 1000); + } } static void probe_graphics(void) { + /* Xe graphics sysfs knobs */ + if (!access("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", R_OK)) { + FILE *fp; + char buf[8]; + bool gt0_is_gt; + int idx; + + fp = fopen("/sys/class/drm/card0/device/tile0/gt0/gtidle/name", "r"); + if (!fp) + goto next; + + if (!fread(buf, sizeof(char), 7, fp)) { + fclose(fp); + goto next; + } + fclose(fp); + + if (!strncmp(buf, "gt0-rc", strlen("gt0-rc"))) + gt0_is_gt = true; + else if (!strncmp(buf, "gt0-mc", strlen("gt0-mc"))) + gt0_is_gt = false; + else + goto next; + + idx = gt0_is_gt ? GFX_rc6 : SAM_mc6; + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms"; + + idx = gt0_is_gt ? GFX_MHz : SAM_MHz; + if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq"; + + idx = gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz; + if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq"; + + idx = gt0_is_gt ? SAM_mc6 : GFX_rc6; + if (!access("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms"; + + idx = gt0_is_gt ? SAM_MHz : GFX_MHz; + if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq"; + + idx = gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz; + if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", R_OK)) + gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq"; + + goto end; + } + +next: + /* New i915 graphics sysfs knobs */ + if (!access("/sys/class/drm/card0/gt/gt0/rc6_residency_ms", R_OK)) { + gfx_info[GFX_rc6].path = "/sys/class/drm/card0/gt/gt0/rc6_residency_ms"; + + if (!access("/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz", R_OK)) + gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz"; + + if (!access("/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz", R_OK)) + gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz"; + + if (!access("/sys/class/drm/card0/gt/gt1/rc6_residency_ms", R_OK)) + gfx_info[SAM_mc6].path = "/sys/class/drm/card0/gt/gt1/rc6_residency_ms"; + + if (!access("/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz", R_OK)) + gfx_info[SAM_MHz].path = "/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz"; + + if (!access("/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz", R_OK)) + gfx_info[SAM_ACTMHz].path = "/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz"; + + goto end; + } + + /* Fall back to traditional i915 graphics sysfs knobs */ if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK)) - BIC_PRESENT(BIC_GFX_rc6); + gfx_info[GFX_rc6].path = "/sys/class/drm/card0/power/rc6_residency_ms"; + + if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK)) + gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt_cur_freq_mhz"; + else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) + gfx_info[GFX_MHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz"; - if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK) || - !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) - BIC_PRESENT(BIC_GFXMHz); - if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK) || - !access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK)) + gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt_act_freq_mhz"; + else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + gfx_info[GFX_ACTMHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz"; + +end: + if (gfx_info[GFX_rc6].path) + BIC_PRESENT(BIC_GFX_rc6); + if (gfx_info[GFX_MHz].path) + BIC_PRESENT(BIC_GFXMHz); + if (gfx_info[GFX_ACTMHz].path) BIC_PRESENT(BIC_GFXACTMHz); + if (gfx_info[SAM_mc6].path) + BIC_PRESENT(BIC_SAM_mc6); + if (gfx_info[SAM_MHz].path) + BIC_PRESENT(BIC_SAMMHz); + if (gfx_info[SAM_ACTMHz].path) + BIC_PRESENT(BIC_SAMACTMHz); } static void dump_sysfs_cstate_config(void) @@ -4783,6 +5646,9 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) UNUSED(c); UNUSED(p); + if (no_msr) + return 0; + if (!has_hwp) return 0; @@ -4869,6 +5735,9 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data UNUSED(c); UNUSED(p); + if (no_msr) + return 0; + cpu = t->cpu_id; /* per-package */ @@ -4983,31 +5852,18 @@ void rapl_probe_intel(void) unsigned long long msr; unsigned int time_unit; double tdp; + const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt; + const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J; - if (rapl_joules) { - if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS) - BIC_PRESENT(BIC_Pkg_J); - if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) - BIC_PRESENT(BIC_Cor_J); - if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS) - BIC_PRESENT(BIC_RAM_J); - if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS) - BIC_PRESENT(BIC_GFX_J); - } else { - if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS) - BIC_PRESENT(BIC_PkgWatt); - if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) - BIC_PRESENT(BIC_CorWatt); - if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS) - BIC_PRESENT(BIC_RAMWatt); - if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS) - BIC_PRESENT(BIC_GFXWatt); - } + if (rapl_joules) + bic_enabled &= ~bic_watt_bits; + else + bic_enabled &= ~bic_joules_bits; - if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) - BIC_PRESENT(BIC_PKG__); - if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) - BIC_PRESENT(BIC_RAM__); + if (!(platform->rapl_msrs & RAPL_PKG_PERF_STATUS)) + bic_enabled &= ~BIC_PKG__; + if (!(platform->rapl_msrs & RAPL_DRAM_PERF_STATUS)) + bic_enabled &= ~BIC_RAM__; /* units on package 0, verify later other packages match */ if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr)) @@ -5041,14 +5897,13 @@ void rapl_probe_amd(void) { unsigned long long msr; double tdp; + const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt; + const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - } + if (rapl_joules) + bic_enabled &= ~bic_watt_bits; + else + bic_enabled &= ~bic_joules_bits; if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) return; @@ -5202,7 +6057,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) */ void probe_rapl(void) { - if (!platform->rapl_msrs) + if (!platform->rapl_msrs || no_msr) return; if (genuine_intel) @@ -5258,7 +6113,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk } /* Temperature Target MSR is Nehalem and newer only */ - if (!platform->has_nhm_msrs) + if (!platform->has_nhm_msrs || no_msr) goto guess; if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) @@ -5305,6 +6160,9 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p UNUSED(c); UNUSED(p); + if (no_msr) + return 0; + if (!(do_dts || do_ptm)) return 0; @@ -5402,6 +6260,9 @@ void decode_feature_control_msr(void) { unsigned long long msr; + if (no_msr) + return; + if (!get_msr(base_cpu, MSR_IA32_FEAT_CTL, &msr)) fprintf(outf, "cpu%d: MSR_IA32_FEATURE_CONTROL: 0x%08llx (%sLocked %s)\n", base_cpu, msr, msr & FEAT_CTL_LOCKED ? "" : "UN-", msr & (1 << 18) ? "SGX" : ""); @@ -5411,6 +6272,9 @@ void decode_misc_enable_msr(void) { unsigned long long msr; + if (no_msr) + return; + if (!genuine_intel) return; @@ -5428,6 +6292,9 @@ void decode_misc_feature_control(void) { unsigned long long msr; + if (no_msr) + return; + if (!platform->has_msr_misc_feature_control) return; @@ -5449,6 +6316,9 @@ void decode_misc_pwr_mgmt_msr(void) { unsigned long long msr; + if (no_msr) + return; + if (!platform->has_msr_misc_pwr_mgmt) return; @@ -5468,6 +6338,9 @@ void decode_c6_demotion_policy_msr(void) { unsigned long long msr; + if (no_msr) + return; + if (!platform->has_msr_c6_demotion_policy_config) return; @@ -5489,7 +6362,8 @@ void print_dev_latency(void) fd = open(path, O_RDONLY); if (fd < 0) { - warnx("capget(CAP_SYS_ADMIN) failed, try \"# setcap cap_sys_admin=ep %s\"", progname); + if (debug) + warnx("Read %s failed", path); return; } @@ -5504,23 +6378,260 @@ void print_dev_latency(void) close(fd); } +static int has_instr_count_access(void) +{ + int fd; + int has_access; + + if (no_perf) + return 0; + + fd = open_perf_counter(base_cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0); + has_access = fd != -1; + + if (fd != -1) + close(fd); + + if (!has_access) + warnx("Failed to access %s. Some of the counters may not be available\n" + "\tRun as root to enable them or use %s to disable the access explicitly", + "instructions retired perf counter", "--no-perf"); + + return has_access; +} + +bool is_aperf_access_required(void) +{ + return BIC_IS_ENABLED(BIC_Avg_MHz) + || BIC_IS_ENABLED(BIC_Busy) + || BIC_IS_ENABLED(BIC_Bzy_MHz) + || BIC_IS_ENABLED(BIC_IPC); +} + +int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai, + double *scale_, enum rapl_unit *unit_) +{ + if (no_perf) + return -1; + + const double scale = read_perf_rapl_scale(cai->perf_subsys, cai->perf_name); + + if (scale == 0.0) + return -1; + + const enum rapl_unit unit = read_perf_rapl_unit(cai->perf_subsys, cai->perf_name); + + if (unit == RAPL_UNIT_INVALID) + return -1; + + const unsigned int rapl_type = read_perf_type(cai->perf_subsys); + const unsigned int rapl_energy_pkg_config = read_rapl_config(cai->perf_subsys, cai->perf_name); + + const int fd_counter = + open_perf_counter(cpu, rapl_type, rapl_energy_pkg_config, rci->fd_perf, PERF_FORMAT_GROUP); + if (fd_counter == -1) + return -1; + + /* If it's the first counter opened, make it a group descriptor */ + if (rci->fd_perf == -1) + rci->fd_perf = fd_counter; + + *scale_ = scale; + *unit_ = unit; + return fd_counter; +} + +int add_rapl_perf_counter(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai, + double *scale, enum rapl_unit *unit) +{ + int ret = add_rapl_perf_counter_(cpu, rci, cai, scale, unit); + + if (debug) + fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu); + + return ret; +} + /* * Linux-perf manages the HW instructions-retired counter * by enabling when requested, and hiding rollover */ void linux_perf_init(void) { - if (!BIC_IS_ENABLED(BIC_IPC)) - return; - if (access("/proc/sys/kernel/perf_event_paranoid", F_OK)) return; - fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int)); - if (fd_instr_count_percpu == NULL) - err(-1, "calloc fd_instr_count_percpu"); + if (BIC_IS_ENABLED(BIC_IPC) && has_aperf) { + fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int)); + if (fd_instr_count_percpu == NULL) + err(-1, "calloc fd_instr_count_percpu"); + } + + const bool aperf_required = is_aperf_access_required(); + + if (aperf_required && has_aperf && amperf_source == AMPERF_SOURCE_PERF) { + fd_amperf_percpu = calloc(topo.max_cpu_num + 1, sizeof(*fd_amperf_percpu)); + if (fd_amperf_percpu == NULL) + err(-1, "calloc fd_amperf_percpu"); + } +} + +void rapl_perf_init(void) +{ + const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages; + bool *domain_visited = calloc(num_domains, sizeof(bool)); + + rapl_counter_info_perdomain = calloc(num_domains, sizeof(*rapl_counter_info_perdomain)); + if (rapl_counter_info_perdomain == NULL) + err(-1, "calloc rapl_counter_info_percpu"); + + /* + * Initialize rapl_counter_info_percpu + */ + for (int domain_id = 0; domain_id < num_domains; ++domain_id) { + struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain_id]; + + rci->fd_perf = -1; + for (size_t i = 0; i < NUM_RAPL_COUNTERS; ++i) { + rci->data[i] = 0; + rci->source[i] = RAPL_SOURCE_NONE; + } + } - BIC_PRESENT(BIC_IPC); + /* + * Open/probe the counters + * If can't get it via perf, fallback to MSR + */ + for (size_t i = 0; i < ARRAY_SIZE(rapl_counter_arch_infos); ++i) { + + const struct rapl_counter_arch_info *const cai = &rapl_counter_arch_infos[i]; + bool has_counter = 0; + double scale; + enum rapl_unit unit; + int next_domain; + + memset(domain_visited, 0, num_domains * sizeof(*domain_visited)); + + for (int cpu = 0; cpu < topo.max_cpu_num + 1; ++cpu) { + + if (cpu_is_not_allowed(cpu)) + continue; + + /* Skip already seen and handled RAPL domains */ + next_domain = + platform->has_per_core_rapl ? cpus[cpu].physical_core_id : cpus[cpu].physical_package_id; + + if (domain_visited[next_domain]) + continue; + + domain_visited[next_domain] = 1; + + struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[next_domain]; + + /* Check if the counter is enabled and accessible */ + if (BIC_IS_ENABLED(cai->bic) && (platform->rapl_msrs & cai->feature_mask)) { + + /* Use perf API for this counter */ + if (!no_perf && cai->perf_name + && add_rapl_perf_counter(cpu, rci, cai, &scale, &unit) != -1) { + rci->source[cai->rci_index] = RAPL_SOURCE_PERF; + rci->scale[cai->rci_index] = scale * cai->compat_scale; + rci->unit[cai->rci_index] = unit; + rci->flags[cai->rci_index] = cai->flags; + + /* Use MSR for this counter */ + } else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) { + rci->source[cai->rci_index] = RAPL_SOURCE_MSR; + rci->msr[cai->rci_index] = cai->msr; + rci->msr_mask[cai->rci_index] = cai->msr_mask; + rci->msr_shift[cai->rci_index] = cai->msr_shift; + rci->unit[cai->rci_index] = RAPL_UNIT_JOULES; + rci->scale[cai->rci_index] = *cai->platform_rapl_msr_scale * cai->compat_scale; + rci->flags[cai->rci_index] = cai->flags; + } + } + + if (rci->source[cai->rci_index] != RAPL_SOURCE_NONE) + has_counter = 1; + } + + /* If any CPU has access to the counter, make it present */ + if (has_counter) + BIC_PRESENT(cai->bic); + } + + free(domain_visited); +} + +static int has_amperf_access_via_msr(void) +{ + if (no_msr) + return 0; + + if (probe_msr(base_cpu, MSR_IA32_APERF)) + return 0; + + if (probe_msr(base_cpu, MSR_IA32_MPERF)) + return 0; + + return 1; +} + +static int has_amperf_access_via_perf(void) +{ + struct amperf_group_fd fds; + + /* + * Cache the last result, so we don't warn the user multiple times + * + * Negative means cached, no access + * Zero means not cached + * Positive means cached, has access + */ + static int has_access_cached; + + if (no_perf) + return 0; + + if (has_access_cached != 0) + return has_access_cached > 0; + + fds = open_amperf_fd(base_cpu); + has_access_cached = (fds.aperf != -1) && (fds.mperf != -1); + + if (fds.aperf == -1) + warnx("Failed to access %s. Some of the counters may not be available\n" + "\tRun as root to enable them or use %s to disable the access explicitly", + "APERF perf counter", "--no-perf"); + else + close(fds.aperf); + + if (fds.mperf == -1) + warnx("Failed to access %s. Some of the counters may not be available\n" + "\tRun as root to enable them or use %s to disable the access explicitly", + "MPERF perf counter", "--no-perf"); + else + close(fds.mperf); + + if (has_access_cached == 0) + has_access_cached = -1; + + return has_access_cached > 0; +} + +/* Check if we can access APERF and MPERF */ +static int has_amperf_access(void) +{ + if (!is_aperf_access_required()) + return 0; + + if (!no_msr && has_amperf_access_via_msr()) + return 1; + + if (!no_perf && has_amperf_access_via_perf()) + return 1; + + return 0; } void probe_cstates(void) @@ -5563,7 +6674,7 @@ void probe_cstates(void) if (platform->has_msr_module_c6_res_ms) BIC_PRESENT(BIC_Mod_c6); - if (platform->has_ext_cst_msrs) { + if (platform->has_ext_cst_msrs && !no_msr) { BIC_PRESENT(BIC_Totl_c0); BIC_PRESENT(BIC_Any_c0); BIC_PRESENT(BIC_GFX_c0); @@ -5623,6 +6734,7 @@ void process_cpuid() unsigned int eax, ebx, ecx, edx; unsigned int fms, family, model, stepping, ecx_flags, edx_flags; unsigned long long ucode_patch = 0; + bool ucode_patch_valid = false; eax = ebx = ecx = edx = 0; @@ -5650,8 +6762,12 @@ void process_cpuid() ecx_flags = ecx; edx_flags = edx; - if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) - warnx("get_msr(UCODE)"); + if (!no_msr) { + if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch)) + warnx("get_msr(UCODE)"); + else + ucode_patch_valid = true; + } /* * check max extended function levels of CPUID. @@ -5662,9 +6778,12 @@ void process_cpuid() __cpuid(0x80000000, max_extended_level, ebx, ecx, edx); if (!quiet) { - fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d) microcode 0x%x\n", - family, model, stepping, family, model, stepping, - (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF)); + fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)", + family, model, stepping, family, model, stepping); + if (ucode_patch_valid) + fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF)); + fputc('\n', outf); + fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level); fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n", ecx_flags & (1 << 0) ? "SSE3" : "-", @@ -5700,10 +6819,11 @@ void process_cpuid() __cpuid(0x6, eax, ebx, ecx, edx); has_aperf = ecx & (1 << 0); - if (has_aperf) { + if (has_aperf && has_amperf_access()) { BIC_PRESENT(BIC_Avg_MHz); BIC_PRESENT(BIC_Busy); BIC_PRESENT(BIC_Bzy_MHz); + BIC_PRESENT(BIC_IPC); } do_dts = eax & (1 << 0); if (do_dts) @@ -5786,6 +6906,15 @@ void process_cpuid() base_mhz = max_mhz = bus_mhz = edx = 0; __cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx); + + bclk = bus_mhz; + + base_hz = base_mhz * 1000000; + has_base_hz = 1; + + if (platform->enable_tsc_tweak) + tsc_tweak = base_hz / tsc_hz; + if (!quiet) fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n", base_mhz, max_mhz, bus_mhz); @@ -5814,7 +6943,7 @@ void probe_pm_features(void) probe_thermal(); - if (platform->has_nhm_msrs) + if (platform->has_nhm_msrs && !no_msr) BIC_PRESENT(BIC_SMI); if (!quiet) @@ -6142,6 +7271,7 @@ void topology_update(void) topo.allowed_packages = 0; for_all_cpus(update_topo, ODD_COUNTERS); } + void setup_all_buffers(bool startup) { topology_probe(startup); @@ -6169,21 +7299,129 @@ void set_base_cpu(void) err(-ENODEV, "No valid cpus found"); } +static void set_amperf_source(void) +{ + amperf_source = AMPERF_SOURCE_PERF; + + const bool aperf_required = is_aperf_access_required(); + + if (no_perf || !aperf_required || !has_amperf_access_via_perf()) + amperf_source = AMPERF_SOURCE_MSR; + + if (quiet || !debug) + return; + + fprintf(outf, "aperf/mperf source preference: %s\n", amperf_source == AMPERF_SOURCE_MSR ? "msr" : "perf"); +} + +bool has_added_counters(void) +{ + /* + * It only makes sense to call this after the command line is parsed, + * otherwise sys structure is not populated. + */ + + return sys.added_core_counters | sys.added_thread_counters | sys.added_package_counters; +} + +bool is_msr_access_required(void) +{ + if (no_msr) + return false; + + if (has_added_counters()) + return true; + + return BIC_IS_ENABLED(BIC_SMI) + || BIC_IS_ENABLED(BIC_CPU_c1) + || BIC_IS_ENABLED(BIC_CPU_c3) + || BIC_IS_ENABLED(BIC_CPU_c6) + || BIC_IS_ENABLED(BIC_CPU_c7) + || BIC_IS_ENABLED(BIC_Mod_c6) + || BIC_IS_ENABLED(BIC_CoreTmp) + || BIC_IS_ENABLED(BIC_Totl_c0) + || BIC_IS_ENABLED(BIC_Any_c0) + || BIC_IS_ENABLED(BIC_GFX_c0) + || BIC_IS_ENABLED(BIC_CPUGFX) + || BIC_IS_ENABLED(BIC_Pkgpc3) + || BIC_IS_ENABLED(BIC_Pkgpc6) + || BIC_IS_ENABLED(BIC_Pkgpc2) + || BIC_IS_ENABLED(BIC_Pkgpc7) + || BIC_IS_ENABLED(BIC_Pkgpc8) + || BIC_IS_ENABLED(BIC_Pkgpc9) + || BIC_IS_ENABLED(BIC_Pkgpc10) + /* TODO: Multiplex access with perf */ + || BIC_IS_ENABLED(BIC_CorWatt) + || BIC_IS_ENABLED(BIC_Cor_J) + || BIC_IS_ENABLED(BIC_PkgWatt) + || BIC_IS_ENABLED(BIC_CorWatt) + || BIC_IS_ENABLED(BIC_GFXWatt) + || BIC_IS_ENABLED(BIC_RAMWatt) + || BIC_IS_ENABLED(BIC_Pkg_J) + || BIC_IS_ENABLED(BIC_Cor_J) + || BIC_IS_ENABLED(BIC_GFX_J) + || BIC_IS_ENABLED(BIC_RAM_J) + || BIC_IS_ENABLED(BIC_PKG__) + || BIC_IS_ENABLED(BIC_RAM__) + || BIC_IS_ENABLED(BIC_PkgTmp) + || (is_aperf_access_required() && !has_amperf_access_via_perf()); +} + +void check_msr_access(void) +{ + if (!is_msr_access_required()) + no_msr = 1; + + check_dev_msr(); + check_msr_permission(); + + if (no_msr) + bic_disable_msr_access(); +} + +void check_perf_access(void) +{ + const bool intrcount_required = BIC_IS_ENABLED(BIC_IPC); + + if (no_perf || !intrcount_required || !has_instr_count_access()) + bic_enabled &= ~BIC_IPC; + + const bool aperf_required = is_aperf_access_required(); + + if (!aperf_required || !has_amperf_access()) { + bic_enabled &= ~BIC_Avg_MHz; + bic_enabled &= ~BIC_Busy; + bic_enabled &= ~BIC_Bzy_MHz; + bic_enabled &= ~BIC_IPC; + } +} + void turbostat_init() { setup_all_buffers(true); set_base_cpu(); - check_dev_msr(); - check_permissions(); + check_msr_access(); + check_perf_access(); process_cpuid(); probe_pm_features(); + set_amperf_source(); linux_perf_init(); + rapl_perf_init(); for_all_cpus(get_cpu_type, ODD_COUNTERS); for_all_cpus(get_cpu_type, EVEN_COUNTERS); if (DO_BIC(BIC_IPC)) (void)get_instr_count_fd(base_cpu); + + /* + * If TSC tweak is needed, but couldn't get it, + * disable more BICs, since it can't be reported accurately. + */ + if (platform->enable_tsc_tweak && !has_base_hz) { + bic_enabled &= ~BIC_Busy; + bic_enabled &= ~BIC_Bzy_MHz; + } } int fork_it(char **argv) @@ -6259,7 +7497,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2023.11.07 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2024.04.08 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -6291,6 +7529,9 @@ int add_counter(unsigned int msr_num, char *path, char *name, { struct msr_counter *msrp; + if (no_msr && msr_num) + errx(1, "Requested MSR counter 0x%x, but in --no-msr mode", msr_num); + msrp = calloc(1, sizeof(struct msr_counter)); if (msrp == NULL) { perror("calloc"); @@ -6595,6 +7836,8 @@ void cmdline(int argc, char **argv) { "list", no_argument, 0, 'l' }, { "out", required_argument, 0, 'o' }, { "quiet", no_argument, 0, 'q' }, + { "no-msr", no_argument, 0, 'M' }, + { "no-perf", no_argument, 0, 'P' }, { "show", required_argument, 0, 's' }, { "Summary", no_argument, 0, 'S' }, { "TCC", required_argument, 0, 'T' }, @@ -6604,7 +7847,25 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v", long_options, &option_index)) != -1) { + /* + * Parse some options early, because they may make other options invalid, + * like adding the MSR counter with --add and at the same time using --no-msr. + */ + while ((opt = getopt_long_only(argc, argv, "MP", long_options, &option_index)) != -1) { + switch (opt) { + case 'M': + no_msr = 1; + break; + case 'P': + no_perf = 1; + break; + default: + break; + } + } + optind = 0; + + while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qMST:v", long_options, &option_index)) != -1) { switch (opt) { case 'a': parse_add_command(optarg); @@ -6662,6 +7923,10 @@ void cmdline(int argc, char **argv) case 'q': quiet = 1; break; + case 'M': + case 'P': + /* Parsed earlier */ + break; case 'n': num_iterations = strtod(optarg, NULL); @@ -6704,6 +7969,22 @@ void cmdline(int argc, char **argv) } } +void set_rlimit(void) +{ + struct rlimit limit; + + if (getrlimit(RLIMIT_NOFILE, &limit) < 0) + err(1, "Failed to get rlimit"); + + if (limit.rlim_max < MAX_NOFILE) + limit.rlim_max = MAX_NOFILE; + if (limit.rlim_cur < MAX_NOFILE) + limit.rlim_cur = MAX_NOFILE; + + if (setrlimit(RLIMIT_NOFILE, &limit) < 0) + err(1, "Failed to set rlimit"); +} + int main(int argc, char **argv) { int fd, ret; @@ -6729,9 +8010,13 @@ skip_cgroup_setting: probe_sysfs(); + if (!getuid()) + set_rlimit(); + turbostat_init(); - msr_sum_record(); + if (!no_msr) + msr_sum_record(); /* dump counters and exit */ if (dump_only) diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 908e0d083936..61c69297e797 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -986,10 +986,12 @@ static void dpa_perf_setup(struct cxl_port *endpoint, struct range *range, { dpa_perf->qos_class = FAKE_QTG_ID; dpa_perf->dpa_range = *range; - dpa_perf->coord.read_latency = 500; - dpa_perf->coord.write_latency = 500; - dpa_perf->coord.read_bandwidth = 1000; - dpa_perf->coord.write_bandwidth = 1000; + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + dpa_perf->coord[i].read_latency = 500; + dpa_perf->coord[i].write_latency = 500; + dpa_perf->coord[i].read_bandwidth = 1000; + dpa_perf->coord[i].write_bandwidth = 1000; + } } static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port) diff --git a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc index b1ede6249866..b7c8f29c09a9 100644 --- a/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc +++ b/tools/testing/selftests/ftrace/test.d/event/subsystem-enable.tc @@ -18,7 +18,7 @@ echo 'sched:*' > set_event yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -29,7 +29,7 @@ echo 1 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -lt 3 ]; then fail "at least fork, exec and exit events should be recorded" fi @@ -40,7 +40,7 @@ echo 0 > events/sched/enable yield -count=`cat trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` +count=`head -n 100 trace | grep -v ^# | awk '{ print $5 }' | sort -u | wc -l` if [ $count -ne 0 ]; then fail "any of scheduler events should not be recorded" fi diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config index 110d73917615..02a2a1b267c1 100644 --- a/tools/testing/selftests/iommu/config +++ b/tools/testing/selftests/iommu/config @@ -1,3 +1,5 @@ CONFIG_IOMMUFD=y +CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION=y CONFIG_IOMMUFD_TEST=y +CONFIG_FAILSLAB=y diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 541bf192e30e..14bbab0cce13 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -51,6 +51,7 @@ #include <stdarg.h> #include <string.h> #include <stdio.h> +#include <sys/utsname.h> #endif #ifndef ARRAY_SIZE @@ -79,6 +80,9 @@ #define KSFT_XPASS 3 #define KSFT_SKIP 4 +#ifndef __noreturn +#define __noreturn __attribute__((__noreturn__)) +#endif #define __printf(a, b) __attribute__((format(printf, a, b))) /* counters */ @@ -288,24 +292,26 @@ void ksft_test_result_code(int exit_code, const char *test_name, } /* Docs seem to call for double space if directive is absent */ - if (!directive[0] && msg[0]) + if (!directive[0] && msg) directive = " # "; - va_start(args, msg); printf("%s %u %s%s", tap_code, ksft_test_num(), test_name, directive); errno = saved_errno; - vprintf(msg, args); + if (msg) { + va_start(args, msg); + vprintf(msg, args); + va_end(args); + } printf("\n"); - va_end(args); } -static inline int ksft_exit_pass(void) +static inline __noreturn int ksft_exit_pass(void) { ksft_print_cnts(); exit(KSFT_PASS); } -static inline int ksft_exit_fail(void) +static inline __noreturn int ksft_exit_fail(void) { ksft_print_cnts(); exit(KSFT_FAIL); @@ -332,7 +338,7 @@ static inline int ksft_exit_fail(void) ksft_cnt.ksft_xfail + \ ksft_cnt.ksft_xskip) -static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) +static inline __noreturn __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) { int saved_errno = errno; va_list args; @@ -347,19 +353,19 @@ static inline __printf(1, 2) int ksft_exit_fail_msg(const char *msg, ...) exit(KSFT_FAIL); } -static inline int ksft_exit_xfail(void) +static inline __noreturn int ksft_exit_xfail(void) { ksft_print_cnts(); exit(KSFT_XFAIL); } -static inline int ksft_exit_xpass(void) +static inline __noreturn int ksft_exit_xpass(void) { ksft_print_cnts(); exit(KSFT_XPASS); } -static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...) +static inline __noreturn __printf(1, 2) int ksft_exit_skip(const char *msg, ...) { int saved_errno = errno; va_list args; @@ -388,4 +394,21 @@ static inline __printf(1, 2) int ksft_exit_skip(const char *msg, ...) exit(KSFT_SKIP); } +static inline int ksft_min_kernel_version(unsigned int min_major, + unsigned int min_minor) +{ +#ifdef NOLIBC + ksft_print_msg("NOLIBC: Can't check kernel version: Function not implemented\n"); + return 0; +#else + unsigned int major, minor; + struct utsname info; + + if (uname(&info) || sscanf(info.release, "%u.%u.", &major, &minor) != 2) + ksft_exit_fail_msg("Can't parse kernel version\n"); + + return major > min_major || (major == min_major && minor >= min_minor); +#endif +} + #endif /* __KSELFTEST_H */ diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 4fd735e48ee7..ba3ddeda24bf 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -383,6 +383,7 @@ FIXTURE_DATA(fixture_name) self; \ pid_t child = 1; \ int status = 0; \ + bool jmp = false; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ if (setjmp(_metadata->env) == 0) { \ /* Use the same _metadata. */ \ @@ -399,8 +400,10 @@ _metadata->exit_code = KSFT_FAIL; \ } \ } \ + else \ + jmp = true; \ if (child == 0) { \ - if (_metadata->setup_completed && !_metadata->teardown_parent) \ + if (_metadata->setup_completed && !_metadata->teardown_parent && !jmp) \ fixture_name##_teardown(_metadata, &self, variant->data); \ _exit(0); \ } \ @@ -1202,7 +1205,7 @@ void __run_test(struct __fixture_metadata *f, diagnostic = "unknown"; ksft_test_result_code(t->exit_code, test_name, - diagnostic ? "%s" : "", diagnostic); + diagnostic ? "%s" : NULL, diagnostic); } static int test_harness_run(int argc, char **argv) diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c index 6628dc4dda89..1a6da7389bf1 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -22,10 +22,11 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) { uint64_t gpa; - for (gpa = start_gpa; gpa < end_gpa; gpa += stride) - *((volatile uint64_t *)gpa) = gpa; - - GUEST_DONE(); + for (;;) { + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + *((volatile uint64_t *)gpa) = gpa; + GUEST_SYNC(0); + } } struct vcpu_info { @@ -55,7 +56,7 @@ static void rendezvous_with_boss(void) static void run_vcpu(struct kvm_vcpu *vcpu) { vcpu_run(vcpu); - TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); } static void *vcpu_worker(void *data) @@ -64,17 +65,13 @@ static void *vcpu_worker(void *data) struct kvm_vcpu *vcpu = info->vcpu; struct kvm_vm *vm = vcpu->vm; struct kvm_sregs sregs; - struct kvm_regs regs; vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size); - /* Snapshot regs before the first run. */ - vcpu_regs_get(vcpu, ®s); rendezvous_with_boss(); run_vcpu(vcpu); rendezvous_with_boss(); - vcpu_regs_set(vcpu, ®s); vcpu_sregs_get(vcpu, &sregs); #ifdef __x86_64__ /* Toggle CR0.WP to trigger a MMU context reset. */ diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 06b43ed23580..bd57d991e27d 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -333,7 +333,7 @@ static void test_invalid_memory_region_flags(void) struct kvm_vm *vm; int r, i; -#if defined __aarch64__ || defined __x86_64__ +#if defined __aarch64__ || defined __riscv || defined __x86_64__ supported_flags |= KVM_MEM_READONLY; #endif diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c index 29609b52f8fa..26c85815f7e9 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c @@ -416,12 +416,30 @@ static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters static void guest_test_gp_counters(void) { + uint8_t pmu_version = guest_get_pmu_version(); uint8_t nr_gp_counters = 0; uint32_t base_msr; - if (guest_get_pmu_version()) + if (pmu_version) nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS); + /* + * For v2+ PMUs, PERF_GLOBAL_CTRL's architectural post-RESET value is + * "Sets bits n-1:0 and clears the upper bits", where 'n' is the number + * of GP counters. If there are no GP counters, require KVM to leave + * PERF_GLOBAL_CTRL '0'. This edge case isn't covered by the SDM, but + * follow the spirit of the architecture and only globally enable GP + * counters, of which there are none. + */ + if (pmu_version > 1) { + uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL); + + if (nr_gp_counters) + GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0)); + else + GUEST_ASSERT_EQ(global_ctrl, 0); + } + if (this_cpu_has(X86_FEATURE_PDCM) && rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES) base_msr = MSR_IA32_PMC0; diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 7f6f5f23fb9b..977948fd52e6 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -28,16 +28,16 @@ #define NESTED_TEST_MEM1 0xc0001000 #define NESTED_TEST_MEM2 0xc0002000 -static void l2_guest_code(void) +static void l2_guest_code(u64 *a, u64 *b) { - *(volatile uint64_t *)NESTED_TEST_MEM1; - *(volatile uint64_t *)NESTED_TEST_MEM1 = 1; + READ_ONCE(*a); + WRITE_ONCE(*a, 1); GUEST_SYNC(true); GUEST_SYNC(false); - *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + WRITE_ONCE(*b, 1); GUEST_SYNC(true); - *(volatile uint64_t *)NESTED_TEST_MEM2 = 1; + WRITE_ONCE(*b, 1); GUEST_SYNC(true); GUEST_SYNC(false); @@ -45,17 +45,33 @@ static void l2_guest_code(void) vmcall(); } +static void l2_guest_code_ept_enabled(void) +{ + l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2); +} + +static void l2_guest_code_ept_disabled(void) +{ + /* Access the same L1 GPAs as l2_guest_code_ept_enabled() */ + l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM); +} + void l1_guest_code(struct vmx_pages *vmx) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + void *l2_rip; GUEST_ASSERT(vmx->vmcs_gpa); GUEST_ASSERT(prepare_for_vmx_operation(vmx)); GUEST_ASSERT(load_vmcs(vmx)); - prepare_vmcs(vmx, l2_guest_code, - &l2_guest_stack[L2_GUEST_STACK_SIZE]); + if (vmx->eptp_gpa) + l2_rip = l2_guest_code_ept_enabled; + else + l2_rip = l2_guest_code_ept_disabled; + + prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]); GUEST_SYNC(false); GUEST_ASSERT(!vmlaunch()); @@ -64,7 +80,7 @@ void l1_guest_code(struct vmx_pages *vmx) GUEST_DONE(); } -int main(int argc, char *argv[]) +static void test_vmx_dirty_log(bool enable_ept) { vm_vaddr_t vmx_pages_gva = 0; struct vmx_pages *vmx; @@ -76,8 +92,7 @@ int main(int argc, char *argv[]) struct ucall uc; bool done = false; - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); - TEST_REQUIRE(kvm_cpu_has_ept()); + pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled"); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); @@ -103,11 +118,16 @@ int main(int argc, char *argv[]) * * Note that prepare_eptp should be called only L1's GPA map is done, * meaning after the last call to virt_map. + * + * When EPT is disabled, the L2 guest code will still access the same L1 + * GPAs as the EPT enabled case. */ - prepare_eptp(vmx, vm, 0); - nested_map_memslot(vmx, vm, 0); - nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096); - nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096); + if (enable_ept) { + prepare_eptp(vmx, vm, 0); + nested_map_memslot(vmx, vm, 0); + nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096); + nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096); + } bmap = bitmap_zalloc(TEST_MEM_PAGES); host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM); @@ -148,3 +168,15 @@ int main(int argc, char *argv[]) } } } + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); + + test_vmx_dirty_log(/*enable_ept=*/false); + + if (kvm_cpu_has_ept()) + test_vmx_dirty_log(/*enable_ept=*/true); + + return 0; +} diff --git a/tools/testing/selftests/net/tcp_ao/lib/proc.c b/tools/testing/selftests/net/tcp_ao/lib/proc.c index 2fb6dd8adba6..8b984fa04286 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/proc.c +++ b/tools/testing/selftests/net/tcp_ao/lib/proc.c @@ -86,7 +86,7 @@ static void netstat_read_type(FILE *fnetstat, struct netstat **dest, char *line) pos = strchr(line, ' ') + 1; - if (fscanf(fnetstat, type->header_name) == EOF) + if (fscanf(fnetstat, "%[^ :]", type->header_name) == EOF) test_error("fscanf(%s)", type->header_name); if (fread(&tmp, 1, 1, fnetstat) != 1 || tmp != ':') test_error("Unexpected netstat format (%c)", tmp); diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c index 92276f916f2f..e408b9243b2c 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/setup.c +++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c @@ -17,37 +17,37 @@ static pthread_mutex_t ksft_print_lock = PTHREAD_MUTEX_INITIALIZER; void __test_msg(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_print_msg(buf); + ksft_print_msg("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_ok(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_pass(buf); + ksft_test_result_pass("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_fail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_fail(buf); + ksft_test_result_fail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_xfail(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_xfail(buf); + ksft_test_result_xfail("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_error(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_error(buf); + ksft_test_result_error("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } void __test_skip(const char *buf) { pthread_mutex_lock(&ksft_print_lock); - ksft_test_result_skip(buf); + ksft_test_result_skip("%s", buf); pthread_mutex_unlock(&ksft_print_lock); } diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index 7df8b8700e39..a2fe88d35ac0 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -256,8 +256,6 @@ static int test_wait_fds(int sk[], size_t nr, bool is_writable[], static void test_client_active_rst(unsigned int port) { - /* one in queue, another accept()ed */ - unsigned int wait_for = backlog + 2; int i, sk[3], err; bool is_writable[ARRAY_SIZE(sk)] = {false}; unsigned int last = ARRAY_SIZE(sk) - 1; @@ -275,16 +273,20 @@ static void test_client_active_rst(unsigned int port) for (i = 0; i < last; i++) { err = _test_connect_socket(sk[i], this_ip_dest, port, (i == 0) ? TEST_TIMEOUT_SEC : -1); - if (err < 0) test_error("failed to connect()"); } - synchronize_threads(); /* 2: connection accept()ed, another queued */ - err = test_wait_fds(sk, last, is_writable, wait_for, TEST_TIMEOUT_SEC); + synchronize_threads(); /* 2: two connections: one accept()ed, another queued */ + err = test_wait_fds(sk, last, is_writable, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("test_wait_fds(): %d", err); + /* async connect() with third sk to get into request_sock_queue */ + err = _test_connect_socket(sk[last], this_ip_dest, port, -1); + if (err < 0) + test_error("failed to connect()"); + synchronize_threads(); /* 3: close listen socket */ if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC)) test_fail("Failed to send data on connected socket"); @@ -292,13 +294,14 @@ static void test_client_active_rst(unsigned int port) test_ok("Verified established tcp connection"); synchronize_threads(); /* 4: finishing up */ - err = _test_connect_socket(sk[last], this_ip_dest, port, -1); - if (err < 0) - test_error("failed to connect()"); synchronize_threads(); /* 5: closed active sk */ - err = test_wait_fds(sk, ARRAY_SIZE(sk), NULL, - wait_for, TEST_TIMEOUT_SEC); + /* + * Wait for 2 connections: one accepted, another in the accept queue, + * the one in request_sock_queue won't get fully established, so + * doesn't receive an active RST, see inet_csk_listen_stop(). + */ + err = test_wait_fds(sk, last, NULL, last, TEST_TIMEOUT_SEC); if (err < 0) test_error("select(): %d", err); diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c index 452de131fa3a..517930f9721b 100644 --- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c +++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c @@ -21,7 +21,7 @@ static void make_listen(int sk) static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info, const char *tst) { - struct tcp_ao_info_opt tmp; + struct tcp_ao_info_opt tmp = {}; socklen_t len = sizeof(tmp); if (getsockopt(sk, IPPROTO_TCP, TCP_AO_INFO, &tmp, &len)) diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 1d975bf52af3..85b3baa3f7f3 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -34,7 +34,7 @@ #endif #ifndef UDP_MAX_SEGMENTS -#define UDP_MAX_SEGMENTS (1 << 6UL) +#define UDP_MAX_SEGMENTS (1 << 7UL) #endif #define CONST_MTU_TEST 1500 diff --git a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c index 505294da1b9f..d6f99eb9be65 100644 --- a/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c +++ b/tools/testing/selftests/powerpc/papr_vpd/papr_vpd.c @@ -154,7 +154,7 @@ static int dev_papr_vpd_null_handle(void) static int papr_vpd_close_handle_without_reading(void) { const int devfd = open(DEVPATH, O_RDONLY); - struct papr_location_code lc; + struct papr_location_code lc = { .str = "", }; int fd; SKIP_IF_MSG(devfd < 0 && errno == ENOENT, diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index d49dd3ffd0d9..c001dd79179d 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -66,7 +66,7 @@ static int check_diff(struct timeval start, struct timeval end) diff = end.tv_usec - start.tv_usec; diff += (end.tv_sec - start.tv_sec) * USECS_PER_SEC; - if (abs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { + if (llabs(diff - DELAY * USECS_PER_SEC) > USECS_PER_SEC / 2) { printf("Diff too high: %lld..", diff); return -1; } @@ -184,80 +184,71 @@ static int check_timer_create(int which) return 0; } -int remain; -__thread int got_signal; +static pthread_t ctd_thread; +static volatile int ctd_count, ctd_failed; -static void *distribution_thread(void *arg) +static void ctd_sighandler(int sig) { - while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); - return NULL; + if (pthread_self() != ctd_thread) + ctd_failed = 1; + ctd_count--; } -static void distribution_handler(int nr) +static void *ctd_thread_func(void *arg) { - if (!__atomic_exchange_n(&got_signal, 1, __ATOMIC_RELAXED)) - __atomic_fetch_sub(&remain, 1, __ATOMIC_RELAXED); -} - -/* - * Test that all running threads _eventually_ receive CLOCK_PROCESS_CPUTIME_ID - * timer signals. This primarily tests that the kernel does not favour any one. - */ -static int check_timer_distribution(void) -{ - int err, i; - timer_t id; - const int nthreads = 10; - pthread_t threads[nthreads]; struct itimerspec val = { .it_value.tv_sec = 0, .it_value.tv_nsec = 1000 * 1000, .it_interval.tv_sec = 0, .it_interval.tv_nsec = 1000 * 1000, }; + timer_t id; - remain = nthreads + 1; /* worker threads + this thread */ - signal(SIGALRM, distribution_handler); - err = timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id); - if (err < 0) { - ksft_perror("Can't create timer"); - return -1; - } - err = timer_settime(id, 0, &val, NULL); - if (err < 0) { - ksft_perror("Can't set timer"); - return -1; - } + /* 1/10 seconds to ensure the leader sleeps */ + usleep(10000); - for (i = 0; i < nthreads; i++) { - err = pthread_create(&threads[i], NULL, distribution_thread, - NULL); - if (err) { - ksft_print_msg("Can't create thread: %s (%d)\n", - strerror(errno), errno); - return -1; - } - } + ctd_count = 100; + if (timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id)) + return "Can't create timer\n"; + if (timer_settime(id, 0, &val, NULL)) + return "Can't set timer\n"; - /* Wait for all threads to receive the signal. */ - while (__atomic_load_n(&remain, __ATOMIC_RELAXED)); + while (ctd_count > 0 && !ctd_failed) + ; - for (i = 0; i < nthreads; i++) { - err = pthread_join(threads[i], NULL); - if (err) { - ksft_print_msg("Can't join thread: %s (%d)\n", - strerror(errno), errno); - return -1; - } - } + if (timer_delete(id)) + return "Can't delete timer\n"; - if (timer_delete(id)) { - ksft_perror("Can't delete timer"); - return -1; - } + return NULL; +} + +/* + * Test that only the running thread receives the timer signal. + */ +static int check_timer_distribution(void) +{ + const char *errmsg; - ksft_test_result_pass("check_timer_distribution\n"); + signal(SIGALRM, ctd_sighandler); + + errmsg = "Can't create thread\n"; + if (pthread_create(&ctd_thread, NULL, ctd_thread_func, NULL)) + goto err; + + errmsg = "Can't join thread\n"; + if (pthread_join(ctd_thread, (void **)&errmsg) || errmsg) + goto err; + + if (!ctd_failed) + ksft_test_result_pass("check signal distribution\n"); + else if (ksft_min_kernel_version(6, 3)) + ksft_test_result_fail("check signal distribution\n"); + else + ksft_test_result_skip("check signal distribution (old kernel)\n"); return 0; +err: + ksft_print_msg("%s", errmsg); + return -1; } int main(int argc, char **argv) diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 48b9a803235a..d13ebde20322 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -21,9 +21,6 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ - - - #include <stdio.h> #include <stdlib.h> #include <time.h> @@ -62,45 +59,47 @@ int clear_time_state(void) #define NUM_FREQ_OUTOFRANGE 4 #define NUM_FREQ_INVALID 2 +#define SHIFTED_PPM (1 << 16) + long valid_freq[NUM_FREQ_VALID] = { - -499<<16, - -450<<16, - -400<<16, - -350<<16, - -300<<16, - -250<<16, - -200<<16, - -150<<16, - -100<<16, - -75<<16, - -50<<16, - -25<<16, - -10<<16, - -5<<16, - -1<<16, + -499 * SHIFTED_PPM, + -450 * SHIFTED_PPM, + -400 * SHIFTED_PPM, + -350 * SHIFTED_PPM, + -300 * SHIFTED_PPM, + -250 * SHIFTED_PPM, + -200 * SHIFTED_PPM, + -150 * SHIFTED_PPM, + -100 * SHIFTED_PPM, + -75 * SHIFTED_PPM, + -50 * SHIFTED_PPM, + -25 * SHIFTED_PPM, + -10 * SHIFTED_PPM, + -5 * SHIFTED_PPM, + -1 * SHIFTED_PPM, -1000, - 1<<16, - 5<<16, - 10<<16, - 25<<16, - 50<<16, - 75<<16, - 100<<16, - 150<<16, - 200<<16, - 250<<16, - 300<<16, - 350<<16, - 400<<16, - 450<<16, - 499<<16, + 1 * SHIFTED_PPM, + 5 * SHIFTED_PPM, + 10 * SHIFTED_PPM, + 25 * SHIFTED_PPM, + 50 * SHIFTED_PPM, + 75 * SHIFTED_PPM, + 100 * SHIFTED_PPM, + 150 * SHIFTED_PPM, + 200 * SHIFTED_PPM, + 250 * SHIFTED_PPM, + 300 * SHIFTED_PPM, + 350 * SHIFTED_PPM, + 400 * SHIFTED_PPM, + 450 * SHIFTED_PPM, + 499 * SHIFTED_PPM, }; long outofrange_freq[NUM_FREQ_OUTOFRANGE] = { - -1000<<16, - -550<<16, - 550<<16, - 1000<<16, + -1000 * SHIFTED_PPM, + -550 * SHIFTED_PPM, + 550 * SHIFTED_PPM, + 1000 * SHIFTED_PPM, }; #define LONG_MAX (~0UL>>1) diff --git a/tools/testing/selftests/turbostat/defcolumns.py b/tools/testing/selftests/turbostat/defcolumns.py new file mode 100755 index 000000000000..d9b042097da7 --- /dev/null +++ b/tools/testing/selftests/turbostat/defcolumns.py @@ -0,0 +1,60 @@ +#!/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import subprocess +from shutil import which + +turbostat = which('turbostat') +if turbostat is None: + print('Could not find turbostat binary') + exit(1) + +timeout = which('timeout') +if timeout is None: + print('Could not find timeout binary') + exit(1) + +proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) + +# +# By default --list reports also "usec" and "Time_Of_Day_Seconds" columns +# which are only visible when running with --debug. +# +expected_columns_debug = proc_turbostat.stdout.replace(b',', b'\t').strip() +expected_columns = expected_columns_debug.replace(b'usec\t', b'').replace(b'Time_Of_Day_Seconds\t', b'').replace(b'X2APIC\t', b'').replace(b'APIC\t', b'') + +# +# Run turbostat with no options for 10 seconds and send SIGINT +# +timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '1s'] +turbostat_argv = [turbostat, '-i', '0.250'] + +print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True) +proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) +actual_columns = proc_turbostat.stdout.split(b'\n')[0] +if expected_columns != actual_columns: + print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}') + exit(1) +print('OK') + +# +# Same, but with --debug +# +turbostat_argv.append('--debug') + +print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True) +proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True) +if proc_turbostat.returncode != 0: + print(f'turbostat failed with {proc_turbostat.returncode}') + exit(1) +actual_columns = proc_turbostat.stdout.split(b'\n')[0] +if expected_columns_debug != actual_columns: + print(f'turbostat column check failed\n{expected_columns_debug=}\n{actual_columns=}') + exit(1) +print('OK') diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index fb49c2a60200..ff0a20565f90 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -832,8 +832,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * mn_active_invalidate_count (see above) instead of * mmu_invalidate_in_progress. */ - gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end, - hva_range.may_block); + gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end); /* * If one or more memslots were found and thus zapped, notify arch code diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h index ecefc7ec51af..715f19669d01 100644 --- a/virt/kvm/kvm_mm.h +++ b/virt/kvm/kvm_mm.h @@ -26,13 +26,11 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible, #ifdef CONFIG_HAVE_KVM_PFNCACHE void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, - unsigned long end, - bool may_block); + unsigned long end); #else static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, - unsigned long end, - bool may_block) + unsigned long end) { } #endif /* HAVE_KVM_PFNCACHE */ diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c index 4e07112a24c2..e3453e869e92 100644 --- a/virt/kvm/pfncache.c +++ b/virt/kvm/pfncache.c @@ -23,7 +23,7 @@ * MMU notifier 'invalidate_range_start' hook. */ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, - unsigned long end, bool may_block) + unsigned long end) { struct gfn_to_pfn_cache *gpc; @@ -57,6 +57,19 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, spin_unlock(&kvm->gpc_lock); } +static bool kvm_gpc_is_valid_len(gpa_t gpa, unsigned long uhva, + unsigned long len) +{ + unsigned long offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) : + offset_in_page(gpa); + + /* + * The cached access must fit within a single page. The 'len' argument + * to activate() and refresh() exists only to enforce that. + */ + return offset + len <= PAGE_SIZE; +} + bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(gpc->kvm); @@ -74,7 +87,7 @@ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len) if (kvm_is_error_hva(gpc->uhva)) return false; - if (offset_in_page(gpc->uhva) + len > PAGE_SIZE) + if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len)) return false; if (!gpc->valid) @@ -232,8 +245,7 @@ out_error: return -EFAULT; } -static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva, - unsigned long len) +static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva) { unsigned long page_offset; bool unmap_old = false; @@ -247,15 +259,6 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l if (WARN_ON_ONCE(kvm_is_error_gpa(gpa) == kvm_is_error_hva(uhva))) return -EINVAL; - /* - * The cached acces must fit within a single page. The 'len' argument - * exists only to enforce that. - */ - page_offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) : - offset_in_page(gpa); - if (page_offset + len > PAGE_SIZE) - return -EINVAL; - lockdep_assert_held(&gpc->refresh_lock); write_lock_irq(&gpc->lock); @@ -270,6 +273,8 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l old_uhva = PAGE_ALIGN_DOWN(gpc->uhva); if (kvm_is_error_gpa(gpa)) { + page_offset = offset_in_page(uhva); + gpc->gpa = INVALID_GPA; gpc->memslot = NULL; gpc->uhva = PAGE_ALIGN_DOWN(uhva); @@ -279,6 +284,8 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned l } else { struct kvm_memslots *slots = kvm_memslots(gpc->kvm); + page_offset = offset_in_page(gpa); + if (gpc->gpa != gpa || gpc->generation != slots->generation || kvm_is_error_hva(gpc->uhva)) { gfn_t gfn = gpa_to_gfn(gpa); @@ -354,6 +361,9 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len) guard(mutex)(&gpc->refresh_lock); + if (!kvm_gpc_is_valid_len(gpc->gpa, gpc->uhva, len)) + return -EINVAL; + /* * If the GPA is valid then ignore the HVA, as a cache can be GPA-based * or HVA-based, not both. For GPA-based caches, the HVA will be @@ -361,7 +371,7 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len) */ uhva = kvm_is_error_gpa(gpc->gpa) ? gpc->uhva : KVM_HVA_ERR_BAD; - return __kvm_gpc_refresh(gpc, gpc->gpa, uhva, len); + return __kvm_gpc_refresh(gpc, gpc->gpa, uhva); } void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm) @@ -381,6 +391,9 @@ static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned { struct kvm *kvm = gpc->kvm; + if (!kvm_gpc_is_valid_len(gpa, uhva, len)) + return -EINVAL; + guard(mutex)(&gpc->refresh_lock); if (!gpc->active) { @@ -400,11 +413,18 @@ static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned gpc->active = true; write_unlock_irq(&gpc->lock); } - return __kvm_gpc_refresh(gpc, gpa, uhva, len); + return __kvm_gpc_refresh(gpc, gpa, uhva); } int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len) { + /* + * Explicitly disallow INVALID_GPA so that the magic value can be used + * by KVM to differentiate between GPA-based and HVA-based caches. + */ + if (WARN_ON_ONCE(kvm_is_error_gpa(gpa))) + return -EINVAL; + return __kvm_gpc_activate(gpc, gpa, KVM_HVA_ERR_BAD, len); } |