diff options
960 files changed, 16904 insertions, 8682 deletions
diff --git a/.mailmap b/.mailmap index f877262b0be99a..9f41b3906b6637 100644 --- a/.mailmap +++ b/.mailmap @@ -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> @@ -500,6 +512,7 @@ Praveen BP <praveenbp@ti.com> Pradeep Kumar Chitrapu <quic_pradeepc@quicinc.com> <pradeepc@codeaurora.org> Prasad Sodagudi <quic_psodagud@quicinc.com> <psodagud@codeaurora.org> Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com> +Puranjay Mohan <puranjay@kernel.org> <puranjay12@gmail.com> Qais Yousef <qyousef@layalina.io> <qais.yousef@imgtec.com> Qais Yousef <qyousef@layalina.io> <qais.yousef@arm.com> Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com> diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon index dad4d5ffd78656..cef6e1d20b1855 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-damon +++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -314,9 +314,9 @@ Date: Dec 2022 Contact: SeongJae Park <sj@kernel.org> Description: Writing to and reading from this file sets and gets the type of the memory of the interest. 'anon' for anonymous pages, - 'memcg' for specific memory cgroup, 'addr' for address range - (an open-ended interval), or 'target' for DAMON monitoring - target can be written and read. + 'memcg' for specific memory cgroup, 'young' for young pages, + 'addr' for address range (an open-ended interval), or 'target' + for DAMON monitoring target can be written and read. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/schemes/<S>/filters/<F>/memcg_path Date: Dec 2022 diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-transparent-hugepage b/Documentation/ABI/testing/sysfs-kernel-mm-transparent-hugepage new file mode 100644 index 00000000000000..7bfbb9cc2c1130 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-transparent-hugepage @@ -0,0 +1,18 @@ +What: /sys/kernel/mm/transparent_hugepage/ +Date: April 2024 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: + /sys/kernel/mm/transparent_hugepage/ contains a number of files and + subdirectories, + + - defrag + - enabled + - hpage_pmd_size + - khugepaged + - shmem_enabled + - use_zero_page + - subdirectories of the form hugepages-<size>kB, where <size> + is the page size of the hugepages supported by the kernel/CPU + combination. + + See Documentation/admin-guide/mm/transhuge.rst for details. diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst index ee2b0030d4168a..091e8bb388875d 100644 --- a/Documentation/admin-guide/blockdev/zram.rst +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -466,6 +466,11 @@ of equal or greater size::: #recompress idle pages larger than 2000 bytes echo "type=idle threshold=2000" > /sys/block/zramX/recompress +It is also possible to limit the number of pages zram re-compression will +attempt to recompress::: + + echo "type=huge_idle max_pages=42" > /sys/block/zramX/recompress + Recompression of idle pages requires memory tracking. During re-compression for every page, that matches re-compression criteria, diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index ca7d9402f6be16..9cde26d3384355 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -300,14 +300,14 @@ When oom event notifier is registered, event will be delivered. Lock order is as follows:: - Page lock (PG_locked bit of page->flags) + folio_lock mm->page_table_lock or split pte_lock folio_memcg_lock (memcg->move_lock) mapping->i_pages lock lruvec->lru_lock. Per-node-per-memcgroup LRU (cgroup's private LRU) is guarded by -lruvec->lru_lock; PG_lru bit of page->flags is cleared before +lruvec->lru_lock; the folio LRU flag is cleared before isolating a page from its LRU under lruvec->lru_lock. .. _cgroup-v1-memory-kernel-extension: @@ -802,8 +802,8 @@ a page or a swap can be moved only when it is charged to the task's current | | anonymous pages, file pages (and swaps) in the range mmapped by the task | | | will be moved even if the task hasn't done page fault, i.e. they might | | | not be the task's "RSS", but other task's "RSS" that maps the same file. | -| | And mapcount of the page is ignored (the page can be moved even if | -| | page_mapcount(page) > 1). You must enable Swap Extension (see 2.4) to | +| | The mapcount of the page is ignored (the page can be moved independent | +| | of the mapcount). You must enable Swap Extension (see 2.4) to | | | enable move of swap charges. | +---+--------------------------------------------------------------------------+ diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 17e6e956515640..0270517ade47cf 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1296,17 +1296,10 @@ PAGE_SIZE multiple when read back. This is a simple interface to trigger memory reclaim in the target cgroup. - This file accepts a single key, the number of bytes to reclaim. - No nested keys are currently supported. - Example:: echo "1G" > memory.reclaim - The interface can be later extended with nested keys to - configure the reclaim behavior. For example, specify the - type of memory to reclaim from (anon, file, ..). - Please note that the kernel can over or under reclaim from the target cgroup. If less bytes are reclaimed than the specified amount, -EAGAIN is returned. @@ -1318,6 +1311,17 @@ PAGE_SIZE multiple when read back. This means that the networking layer will not adapt based on reclaim induced by memory.reclaim. +The following nested keys are defined. + + ========== ================================ + swappiness Swappiness value to reclaim with + ========== ================================ + + Specifying a swappiness value instructs the kernel to perform + the reclaim with that swappiness value. Note that this has the + same semantics as vm.swappiness applied to memcg reclaim with + all the existing limitations and potential future extensions. + memory.peak A read-only single value file which exists on non-root cgroups. diff --git a/Documentation/admin-guide/kdump/kdump.rst b/Documentation/admin-guide/kdump/kdump.rst index 0302a93b1d40b7..5376890adbeb07 100644 --- a/Documentation/admin-guide/kdump/kdump.rst +++ b/Documentation/admin-guide/kdump/kdump.rst @@ -136,10 +136,6 @@ System kernel config options CONFIG_KEXEC_CORE=y - Subsequently, CRASH_CORE is selected by KEXEC_CORE:: - - CONFIG_CRASH_CORE=y - 2) Enable "sysfs file system support" in "Filesystem" -> "Pseudo filesystems." This is usually enabled by default:: @@ -168,6 +164,10 @@ Dump-capture kernel config options (Arch Independent) CONFIG_CRASH_DUMP=y + And this will select VMCORE_INFO and CRASH_RESERVE:: + CONFIG_VMCORE_INFO=y + CONFIG_CRASH_RESERVE=y + 2) Enable "/proc/vmcore support" under "Filesystems" -> "Pseudo filesystems":: CONFIG_PROC_VMCORE=y diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 902ecd92a29fbe..827b51450cc28d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2148,6 +2148,12 @@ Format: 0 | 1 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. + init_mlocked_on_free= [MM] Fill freed userspace memory with zeroes if + it was mlock'ed and not explicitly munlock'ed + afterwards. + Format: 0 | 1 + Default set by CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON + init_pkru= [X86] Specify the default memory protection keys rights register contents for all processes. 0x55555554 by default (disallow access to all but pkey 0). Can @@ -3423,6 +3429,9 @@ arch-independent options, each of which is an aggregation of existing arch-specific options. + Note, "mitigations" is supported if and only if the + kernel was built with CPU_MITIGATIONS=y. + off Disable all optional CPU mitigations. This improves system performance, but it may also diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index 6fce035fdbf5c7..69bc8fabf3781c 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -410,19 +410,19 @@ in the numeric order. Each filter directory contains six files, namely ``type``, ``matcing``, ``memcg_path``, ``addr_start``, ``addr_end``, and ``target_idx``. To ``type`` -file, you can write one of four special keywords: ``anon`` for anonymous pages, -``memcg`` for specific memory cgroup, ``addr`` for specific address range (an -open-ended interval), or ``target`` for specific DAMON monitoring target -filtering. In case of the memory cgroup filtering, you can specify the memory -cgroup of the interest by writing the path of the memory cgroup from the -cgroups mount point to ``memcg_path`` file. In case of the address range -filtering, you can specify the start and end address of the range to -``addr_start`` and ``addr_end`` files, respectively. For the DAMON monitoring -target filtering, you can specify the index of the target between the list of -the DAMON context's monitoring targets list to ``target_idx`` file. You can -write ``Y`` or ``N`` to ``matching`` file to filter out pages that does or does -not match to the type, respectively. Then, the scheme's action will not be -applied to the pages that specified to be filtered out. +file, you can write one of five special keywords: ``anon`` for anonymous pages, +``memcg`` for specific memory cgroup, ``young`` for young pages, ``addr`` for +specific address range (an open-ended interval), or ``target`` for specific +DAMON monitoring target filtering. In case of the memory cgroup filtering, you +can specify the memory cgroup of the interest by writing the path of the memory +cgroup from the cgroups mount point to ``memcg_path`` file. In case of the +address range filtering, you can specify the start and end address of the range +to ``addr_start`` and ``addr_end`` files, respectively. For the DAMON +monitoring target filtering, you can specify the index of the target between +the list of the DAMON context's monitoring targets list to ``target_idx`` file. +You can write ``Y`` or ``N`` to ``matching`` file to filter out pages that does +or does not match to the type, respectively. Then, the scheme's action will +not be applied to the pages that specified to be filtered out. For example, below restricts a DAMOS action to be applied to only non-anonymous pages of all memory cgroups except ``/having_care_already``.:: diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index e4d4b4a8dc9736..f34a0d798d5b53 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -376,6 +376,13 @@ Note that the number of overcommit and reserve pages remain global quantities, as we don't know until fault time, when the faulting task's mempolicy is applied, from which node the huge page allocation will be attempted. +The hugetlb may be migrated between the per-node hugepages pool in the following +scenarios: memory offline, memory failure, longterm pinning, syscalls(mbind, +migrate_pages and move_pages), alloc_contig_range() and alloc_contig_pages(). +Now only memory offline, memory failure and syscalls allow fallbacking to allocate +a new hugetlb on a different node if the current node is unable to allocate during +hugetlb migration, that means these 3 cases can break the per-node hugepages pool. + .. _using_huge_pages: Using Huge Pages diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 04eb45a2f94069..076443cc10a6c7 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -278,7 +278,8 @@ collapsed, resulting fewer pages being collapsed into THPs, and lower memory access performance. ``max_ptes_shared`` specifies how many pages can be shared across multiple -processes. Exceeding the number would block the collapse:: +processes. khugepaged might treat pages of THPs as shared if any page of +that THP is shared. Exceeding the number would block the collapse:: /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_shared @@ -369,7 +370,7 @@ monitor how successfully the system is providing huge pages for use. thp_fault_alloc is incremented every time a huge page is successfully - allocated to handle a page fault. + allocated and charged to handle a page fault. thp_collapse_alloc is incremented by khugepaged when it has found @@ -377,7 +378,7 @@ thp_collapse_alloc successfully allocated a new huge page to store the data. thp_fault_fallback - is incremented if a page fault fails to allocate + is incremented if a page fault fails to allocate or charge a huge page and instead falls back to using small pages. thp_fault_fallback_charge @@ -447,6 +448,34 @@ thp_swpout_fallback Usually because failed to allocate some continuous swap space for the huge page. +In /sys/kernel/mm/transparent_hugepage/hugepages-<size>kB/stats, There are +also individual counters for each huge page size, which can be utilized to +monitor the system's effectiveness in providing huge pages for usage. Each +counter has its own corresponding file. + +anon_fault_alloc + is incremented every time a huge page is successfully + allocated and charged to handle a page fault. + +anon_fault_fallback + is incremented if a page fault fails to allocate or charge + a huge page and instead falls back to using huge pages with + lower orders or small pages. + +anon_fault_fallback_charge + is incremented if a page fault fails to charge a huge page and + instead falls back to using huge pages with lower orders or + small pages even though the allocation was successful. + +anon_swpout + is incremented every time a huge page is swapped out in one + piece without splitting. + +anon_swpout_fallback + is incremented if a huge page has to be split before swapout. + Usually because failed to allocate some continuous swap space + for the huge page. + As the system ages, allocating huge pages may be expensive as the system uses memory compaction to copy data around memory to free a huge page for use. There are some counters in ``/proc/vmstat`` to help diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst index 13632671adaeaa..3598dcd7dbe7e1 100644 --- a/Documentation/admin-guide/mm/zswap.rst +++ b/Documentation/admin-guide/mm/zswap.rst @@ -111,35 +111,6 @@ checked if it is a same-value filled page before compressing it. If true, the compressed length of the page is set to zero and the pattern or same-filled value is stored. -Same-value filled pages identification feature is enabled by default and can be -disabled at boot time by setting the ``same_filled_pages_enabled`` attribute -to 0, e.g. ``zswap.same_filled_pages_enabled=0``. It can also be enabled and -disabled at runtime using the sysfs ``same_filled_pages_enabled`` -attribute, e.g.:: - - echo 1 > /sys/module/zswap/parameters/same_filled_pages_enabled - -When zswap same-filled page identification is disabled at runtime, it will stop -checking for the same-value filled pages during store operation. -In other words, every page will be then considered non-same-value filled. -However, the existing pages which are marked as same-value filled pages remain -stored unchanged in zswap until they are either loaded or invalidated. - -In some circumstances it might be advantageous to make use of just the zswap -ability to efficiently store same-filled pages without enabling the whole -compressed page storage. -In this case the handling of non-same-value pages by zswap (enabled by default) -can be disabled by setting the ``non_same_filled_pages_enabled`` attribute -to 0, e.g. ``zswap.non_same_filled_pages_enabled=0``. -It can also be enabled and disabled at runtime using the sysfs -``non_same_filled_pages_enabled`` attribute, e.g.:: - - echo 1 > /sys/module/zswap/parameters/non_same_filled_pages_enabled - -Disabling both ``zswap.same_filled_pages_enabled`` and -``zswap.non_same_filled_pages_enabled`` effectively disables accepting any new -pages by zswap. - To prevent zswap from shrinking pool when zswap is full and there's a high pressure on swap (this will result in flipping pages in and out zswap pool without any real benefit but with a performance drop for the system), a diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index c59889de122b9f..e86c968a7a0ece 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -43,6 +43,7 @@ Currently, these files are in /proc/sys/vm: - legacy_va_layout - lowmem_reserve_ratio - max_map_count +- mem_profiling (only if CONFIG_MEM_ALLOC_PROFILING=y) - memory_failure_early_kill - memory_failure_recovery - min_free_kbytes @@ -425,6 +426,21 @@ e.g., up to one or two maps per allocation. The default value is 65530. +mem_profiling +============== + +Enable memory profiling (when CONFIG_MEM_ALLOC_PROFILING=y) + +1: Enable memory profiling. + +0: Disable memory profiling. + +Enabling memory profiling introduces a small performance overhead for all +memory allocations. + +The default value depends on CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT. + + memory_failure_early_kill: ========================== diff --git a/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst b/Documentation/admin-guide/verify-bugs-and-bisect-regressions.rst index d3504826f40154..c389d4fd7599df 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/core-api/floating-point.rst b/Documentation/core-api/floating-point.rst new file mode 100644 index 00000000000000..a8d0d4b050529f --- /dev/null +++ b/Documentation/core-api/floating-point.rst @@ -0,0 +1,78 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +Floating-point API +================== + +Kernel code is normally prohibited from using floating-point (FP) registers or +instructions, including the C float and double data types. This rule reduces +system call overhead, because the kernel does not need to save and restore the +userspace floating-point register state. + +However, occasionally drivers or library functions may need to include FP code. +This is supported by isolating the functions containing FP code to a separate +translation unit (a separate source file), and saving/restoring the FP register +state around calls to those functions. This creates "critical sections" of +floating-point usage. + +The reason for this isolation is to prevent the compiler from generating code +touching the FP registers outside these critical sections. Compilers sometimes +use FP registers to optimize inlined ``memcpy`` or variable assignment, as +floating-point registers may be wider than general-purpose registers. + +Usability of floating-point code within the kernel is architecture-specific. +Additionally, because a single kernel may be configured to support platforms +both with and without a floating-point unit, FPU availability must be checked +both at build time and at run time. + +Several architectures implement the generic kernel floating-point API from +``linux/fpu.h``, as described below. Some other architectures implement their +own unique APIs, which are documented separately. + +Build-time API +-------------- + +Floating-point code may be built if the option ``ARCH_HAS_KERNEL_FPU_SUPPORT`` +is enabled. For C code, such code must be placed in a separate file, and that +file must have its compilation flags adjusted using the following pattern:: + + CFLAGS_foo.o += $(CC_FLAGS_FPU) + CFLAGS_REMOVE_foo.o += $(CC_FLAGS_NO_FPU) + +Architectures are expected to define one or both of these variables in their +top-level Makefile as needed. For example:: + + CC_FLAGS_FPU := -mhard-float + +or:: + + CC_FLAGS_NO_FPU := -msoft-float + +Normal kernel code is assumed to use the equivalent of ``CC_FLAGS_NO_FPU``. + +Runtime API +----------- + +The runtime API is provided in ``linux/fpu.h``. This header cannot be included +from files implementing FP code (those with their compilation flags adjusted as +above). Instead, it must be included when defining the FP critical sections. + +.. c:function:: bool kernel_fpu_available( void ) + + This function reports if floating-point code can be used on this CPU or + platform. The value returned by this function is not expected to change + at runtime, so it only needs to be called once, not before every + critical section. + +.. c:function:: void kernel_fpu_begin( void ) + void kernel_fpu_end( void ) + + These functions create a floating-point critical section. It is only + valid to call ``kernel_fpu_begin()`` after a previous call to + ``kernel_fpu_available()`` returned ``true``. These functions are only + guaranteed to be callable from (preemptible or non-preemptible) process + context. + + Preemption may be disabled inside critical sections, so their size + should be minimized. They are *not* required to be reentrant. If the + caller expects to nest critical sections, it must implement its own + reference counting. diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index 7a3a08d81f111c..974beccd671f64 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -48,6 +48,7 @@ Library functionality that is used throughout the kernel. errseq wrappers/atomic_t wrappers/atomic_bitops + floating-point Low level entry and exit ======================== diff --git a/Documentation/devicetree/bindings/eeprom/at24.yaml b/Documentation/devicetree/bindings/eeprom/at24.yaml index 1812ef31d5f1e9..3c36cd0510de83 100644 --- a/Documentation/devicetree/bindings/eeprom/at24.yaml +++ b/Documentation/devicetree/bindings/eeprom/at24.yaml @@ -69,14 +69,10 @@ properties: - items: pattern: c32$ - items: - pattern: c32d-wl$ - - items: pattern: cs32$ - items: pattern: c64$ - items: - pattern: c64d-wl$ - - items: pattern: cs64$ - items: pattern: c128$ @@ -136,6 +132,7 @@ properties: - renesas,r1ex24128 - samsung,s524ad0xd1 - const: atmel,24c128 + - pattern: '^atmel,24c(32|64)d-wl$' # Actual vendor is st label: description: Descriptive name of the EEPROM. diff --git a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml index c13c10c8d65da2..eed0df9d3a2322 100644 --- a/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml +++ b/Documentation/devicetree/bindings/iio/health/maxim,max30102.yaml @@ -42,7 +42,7 @@ allOf: properties: compatible: contains: - const: maxim,max30100 + const: maxim,max30102 then: properties: maxim,green-led-current-microamp: false diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml index 0b87c266760c6e..79798c7474768a 100644 --- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml +++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml @@ -171,6 +171,7 @@ allOf: unevaluatedProperties: false pcie-phy: + type: object description: Documentation/devicetree/bindings/phy/rockchip-pcie-phy.txt diff --git a/Documentation/devicetree/bindings/sound/rt5645.txt b/Documentation/devicetree/bindings/sound/rt5645.txt index 41a62fd2ae1ffb..c1fa379f5f3ea1 100644 --- a/Documentation/devicetree/bindings/sound/rt5645.txt +++ b/Documentation/devicetree/bindings/sound/rt5645.txt @@ -20,6 +20,11 @@ Optional properties: a GPIO spec for the external headphone detect pin. If jd-mode = 0, we will get the JD status by getting the value of hp-detect-gpios. +- cbj-sleeve-gpios: + a GPIO spec to control the external combo jack circuit to tie the sleeve/ring2 + contacts to the ground or floating. It could avoid some electric noise from the + active speaker jacks. + - realtek,in2-differential Boolean. Indicate MIC2 input are differential, rather than single-ended. @@ -68,6 +73,7 @@ codec: rt5650@1a { compatible = "realtek,rt5650"; reg = <0x1a>; hp-detect-gpios = <&gpio 19 0>; + cbj-sleeve-gpios = <&gpio 20 0>; interrupt-parent = <&gpio>; interrupts = <7 IRQ_TYPE_EDGE_FALLING>; realtek,dmic-en = "true"; diff --git a/Documentation/driver-api/crypto/iaa/iaa-crypto.rst b/Documentation/driver-api/crypto/iaa/iaa-crypto.rst index de587cf9cbed45..4cb1d52ea6dc4d 100644 --- a/Documentation/driver-api/crypto/iaa/iaa-crypto.rst +++ b/Documentation/driver-api/crypto/iaa/iaa-crypto.rst @@ -457,7 +457,6 @@ Use the following commands to enable zswap:: # echo deflate-iaa > /sys/module/zswap/parameters/compressor # echo zsmalloc > /sys/module/zswap/parameters/zpool # echo 1 > /sys/module/zswap/parameters/enabled - # echo 0 > /sys/module/zswap/parameters/same_filled_pages_enabled # echo 100 > /proc/sys/vm/swappiness # echo never > /sys/kernel/mm/transparent_hugepage/enabled # echo 1 > /proc/sys/vm/overcommit_memory @@ -599,7 +598,6 @@ the 'fixed' compression mode:: echo deflate-iaa > /sys/module/zswap/parameters/compressor echo zsmalloc > /sys/module/zswap/parameters/zpool echo 1 > /sys/module/zswap/parameters/enabled - echo 0 > /sys/module/zswap/parameters/same_filled_pages_enabled echo 100 > /proc/sys/vm/swappiness echo never > /sys/kernel/mm/transparent_hugepage/enabled diff --git a/Documentation/filesystems/api-summary.rst b/Documentation/filesystems/api-summary.rst index 98db2ea5fa12c6..cc5cc7f3fbd8e9 100644 --- a/Documentation/filesystems/api-summary.rst +++ b/Documentation/filesystems/api-summary.rst @@ -56,9 +56,6 @@ Other Functions .. kernel-doc:: fs/namei.c :export: -.. kernel-doc:: fs/buffer.c - :export: - .. kernel-doc:: block/bio.c :export: diff --git a/Documentation/filesystems/buffer.rst b/Documentation/filesystems/buffer.rst new file mode 100644 index 00000000000000..ae24faf68efaba --- /dev/null +++ b/Documentation/filesystems/buffer.rst @@ -0,0 +1,12 @@ +Buffer Heads +============ + +Linux uses buffer heads to maintain state about individual filesystem blocks. +Buffer heads are deprecated and new filesystems should use iomap instead. + +Functions +--------- + +.. kernel-doc:: include/linux/buffer_head.h +.. kernel-doc:: fs/buffer.c + :export: diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index 1f9b4c905a6a7c..8f5c1ee02e2f94 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -50,6 +50,7 @@ filesystem implementations. .. toctree:: :maxdepth: 2 + buffer journalling fscrypt fsverity diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index c6a6b9df210497..245269dd6e0289 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -688,6 +688,7 @@ files are there, and which are missing. ============ =============================================================== File Content ============ =============================================================== + allocinfo Memory allocations profiling information apm Advanced power management info bootconfig Kernel command line obtained from boot config, and, if there were kernel parameters from the @@ -953,6 +954,34 @@ also be allocatable although a lot of filesystem metadata may have to be reclaimed to achieve this. +allocinfo +~~~~~~~~~ + +Provides information about memory allocations at all locations in the code +base. Each allocation in the code is identified by its source file, line +number, module (if originates from a loadable module) and the function calling +the allocation. The number of bytes allocated and number of calls at each +location are reported. + +Example output. + +:: + + > sort -rn /proc/allocinfo + 127664128 31168 mm/page_ext.c:270 func:alloc_page_ext + 56373248 4737 mm/slub.c:2259 func:alloc_slab_page + 14880768 3633 mm/readahead.c:247 func:page_cache_ra_unbounded + 14417920 3520 mm/mm_init.c:2530 func:alloc_large_system_hash + 13377536 234 block/blk-mq.c:3421 func:blk_mq_alloc_rqs + 11718656 2861 mm/filemap.c:1919 func:__filemap_get_folio + 9192960 2800 kernel/fork.c:307 func:alloc_thread_stack_node + 4206592 4 net/netfilter/nf_conntrack_core.c:2567 func:nf_ct_alloc_hashtable + 4136960 1010 drivers/staging/ctagmod/ctagmod.c:20 [ctagmod] func:ctagmod_start + 3940352 962 mm/memory.c:4214 func:alloc_anon_folio + 2894464 22613 fs/kernfs/dir.c:615 func:__kernfs_new_node + ... + + meminfo ~~~~~~~ diff --git a/Documentation/mm/allocation-profiling.rst b/Documentation/mm/allocation-profiling.rst new file mode 100644 index 00000000000000..d3b733b41ae658 --- /dev/null +++ b/Documentation/mm/allocation-profiling.rst @@ -0,0 +1,100 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================== +MEMORY ALLOCATION PROFILING +=========================== + +Low overhead (suitable for production) accounting of all memory allocations, +tracked by file and line number. + +Usage: +kconfig options: +- CONFIG_MEM_ALLOC_PROFILING + +- CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT + +- CONFIG_MEM_ALLOC_PROFILING_DEBUG + adds warnings for allocations that weren't accounted because of a + missing annotation + +Boot parameter: + sysctl.vm.mem_profiling=0|1|never + + When set to "never", memory allocation profiling overhead is minimized and it + cannot be enabled at runtime (sysctl becomes read-only). + When CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=y, default value is "1". + When CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=n, default value is "never". + +sysctl: + /proc/sys/vm/mem_profiling + +Runtime info: + /proc/allocinfo + +Example output:: + + root@moria-kvm:~# sort -g /proc/allocinfo|tail|numfmt --to=iec + 2.8M 22648 fs/kernfs/dir.c:615 func:__kernfs_new_node + 3.8M 953 mm/memory.c:4214 func:alloc_anon_folio + 4.0M 1010 drivers/staging/ctagmod/ctagmod.c:20 [ctagmod] func:ctagmod_start + 4.1M 4 net/netfilter/nf_conntrack_core.c:2567 func:nf_ct_alloc_hashtable + 6.0M 1532 mm/filemap.c:1919 func:__filemap_get_folio + 8.8M 2785 kernel/fork.c:307 func:alloc_thread_stack_node + 13M 234 block/blk-mq.c:3421 func:blk_mq_alloc_rqs + 14M 3520 mm/mm_init.c:2530 func:alloc_large_system_hash + 15M 3656 mm/readahead.c:247 func:page_cache_ra_unbounded + 55M 4887 mm/slub.c:2259 func:alloc_slab_page + 122M 31168 mm/page_ext.c:270 func:alloc_page_ext + +=================== +Theory of operation +=================== + +Memory allocation profiling builds off of code tagging, which is a library for +declaring static structs (that typically describe a file and line number in +some way, hence code tagging) and then finding and operating on them at runtime, +- i.e. iterating over them to print them in debugfs/procfs. + +To add accounting for an allocation call, we replace it with a macro +invocation, alloc_hooks(), that +- declares a code tag +- stashes a pointer to it in task_struct +- calls the real allocation function +- and finally, restores the task_struct alloc tag pointer to its previous value. + +This allows for alloc_hooks() calls to be nested, with the most recent one +taking effect. This is important for allocations internal to the mm/ code that +do not properly belong to the outer allocation context and should be counted +separately: for example, slab object extension vectors, or when the slab +allocates pages from the page allocator. + +Thus, proper usage requires determining which function in an allocation call +stack should be tagged. There are many helper functions that essentially wrap +e.g. kmalloc() and do a little more work, then are called in multiple places; +we'll generally want the accounting to happen in the callers of these helpers, +not in the helpers themselves. + +To fix up a given helper, for example foo(), do the following: +- switch its allocation call to the _noprof() version, e.g. kmalloc_noprof() + +- rename it to foo_noprof() + +- define a macro version of foo() like so: + + #define foo(...) alloc_hooks(foo_noprof(__VA_ARGS__)) + +It's also possible to stash a pointer to an alloc tag in your own data structures. + +Do this when you're implementing a generic data structure that does allocations +"on behalf of" some other code - for example, the rhashtable code. This way, +instead of seeing a large line in /proc/allocinfo for rhashtable.c, we can +break it out by rhashtable type. + +To do so: +- Hook your data structure's init function, like any other allocation function. + +- Within your init function, use the convenience macro alloc_tag_record() to + record alloc tag in your data structure. + +- Then, use the following form for your allocations: + alloc_hooks_tag(ht->your_saved_tag, kmalloc_noprof(...)) diff --git a/Documentation/mm/damon/design.rst b/Documentation/mm/damon/design.rst index 5620aab9b38507..f2baf617184d0a 100644 --- a/Documentation/mm/damon/design.rst +++ b/Documentation/mm/damon/design.rst @@ -461,15 +461,17 @@ number of filters for each scheme. Each filter specifies the type of target memory, and whether it should exclude the memory of the type (filter-out), or all except the memory of the type (filter-in). -Currently, anonymous page, memory cgroup, address range, and DAMON monitoring -target type filters are supported by the feature. Some filter target types -require additional arguments. The memory cgroup filter type asks users to -specify the file path of the memory cgroup for the filter. The address range -type asks the start and end addresses of the range. The DAMON monitoring -target type asks the index of the target from the context's monitoring targets -list. Hence, users can apply specific schemes to only anonymous pages, -non-anonymous pages, pages of specific cgroups, all pages excluding those of -specific cgroups, pages in specific address range, pages in specific DAMON +Currently, anonymous page, memory cgroup, young page, address range, and DAMON +monitoring target type filters are supported by the feature. Some filter +target types require additional arguments. The memory cgroup filter type asks +users to specify the file path of the memory cgroup for the filter. The +address range type asks the start and end addresses of the range. The DAMON +monitoring target type asks the index of the target from the context's +monitoring targets list. Hence, users can apply specific schemes to only +anonymous pages, non-anonymous pages, pages of specific cgroups, all pages +excluding those of specific cgroups, pages that not accessed after the last +access check from the scheme, pages that accessed after the last access check +from the scheme, pages in specific address range, pages in specific DAMON monitoring targets, and any combination of those. To handle filters efficiently, the address range and DAMON monitoring target diff --git a/Documentation/mm/index.rst b/Documentation/mm/index.rst index 31d2ac3064387b..48b9b559ca7b45 100644 --- a/Documentation/mm/index.rst +++ b/Documentation/mm/index.rst @@ -26,6 +26,7 @@ see the :doc:`admin guide <../admin-guide/mm/index>`. page_cache shmfs oom + allocation-profiling Legacy Documentation ==================== diff --git a/Documentation/mm/page_table_check.rst b/Documentation/mm/page_table_check.rst index c12838ce6b8de2..c59f22eb6a0f9a 100644 --- a/Documentation/mm/page_table_check.rst +++ b/Documentation/mm/page_table_check.rst @@ -14,7 +14,7 @@ Page table check performs extra verifications at the time when new pages become accessible from the userspace by getting their page table entries (PTEs PMDs etc.) added into the table. -In case of detected corruption, the kernel is crashed. There is a small +In case of most detected corruption, the kernel is crashed. There is a small performance and memory overhead associated with the page table check. Therefore, it is disabled by default, but can be optionally enabled on systems where the extra hardening outweighs the performance costs. Also, because page table check @@ -22,6 +22,13 @@ is synchronous, it can help with debugging double map memory corruption issues, by crashing kernel at the time wrong mapping occurs instead of later which is often the case with memory corruptions bugs. +It can also be used to do page table entry checks over various flags, dump +warnings when illegal combinations of entry flags are detected. Currently, +userfaultfd is the only user of such to sanity check wr-protect bit against +any writable flags. Illegal flag combinations will not directly cause data +corruption in this case immediately, but that will cause read-only data to +be writable, leading to corrupt when the page content is later modified. + Double mapping detection logic ============================== diff --git a/Documentation/mm/transhuge.rst b/Documentation/mm/transhuge.rst index 93c9239b9ebe23..1ba0ad63246c53 100644 --- a/Documentation/mm/transhuge.rst +++ b/Documentation/mm/transhuge.rst @@ -116,14 +116,14 @@ pages: succeeds on tail pages. - map/unmap of a PMD entry for the whole THP increment/decrement - folio->_entire_mapcount and also increment/decrement - folio->_nr_pages_mapped by ENTIRELY_MAPPED when _entire_mapcount - goes from -1 to 0 or 0 to -1. + folio->_entire_mapcount, increment/decrement folio->_large_mapcount + and also increment/decrement folio->_nr_pages_mapped by ENTIRELY_MAPPED + when _entire_mapcount goes from -1 to 0 or 0 to -1. - map/unmap of individual pages with PTE entry increment/decrement - page->_mapcount and also increment/decrement folio->_nr_pages_mapped - when page->_mapcount goes from -1 to 0 or 0 to -1 as this counts - the number of pages mapped by PTE. + page->_mapcount, increment/decrement folio->_large_mapcount and also + increment/decrement folio->_nr_pages_mapped when page->_mapcount goes + from -1 to 0 or 0 to -1 as this counts the number of pages mapped by PTE. split_huge_page internally has to distribute the refcounts in the head page to the tail pages before clearing all PG_head/tail bits from the page diff --git a/Documentation/mm/vmemmap_dedup.rst b/Documentation/mm/vmemmap_dedup.rst index 593ede6d314ba6..b4a55b6569fa54 100644 --- a/Documentation/mm/vmemmap_dedup.rst +++ b/Documentation/mm/vmemmap_dedup.rst @@ -180,27 +180,7 @@ this correctly. There is only **one** head ``struct page``, the tail ``struct page`` with ``PG_head`` are fake head ``struct page``. We need an approach to distinguish between those two different types of ``struct page`` so that ``compound_head()`` can return the real head ``struct page`` when the -parameter is the tail ``struct page`` but with ``PG_head``. The following code -snippet describes how to distinguish between real and fake head ``struct page``. - -.. code-block:: c - - if (test_bit(PG_head, &page->flags)) { - unsigned long head = READ_ONCE(page[1].compound_head); - - if (head & 1) { - if (head == (unsigned long)page + 1) - /* head struct page */ - else - /* tail struct page */ - } else { - /* head struct page */ - } - } - -We can safely access the field of the **page[1]** with ``PG_head`` because the -page is a compound page composed with at least two contiguous pages. -The implementation refers to ``page_fixed_fake_head()``. +parameter is the tail ``struct page`` but with ``PG_head``. Device DAX ========== diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst index 5c4fa9f5d1cdb7..c9137710633a37 100644 --- a/Documentation/rust/arch-support.rst +++ b/Documentation/rust/arch-support.rst @@ -16,7 +16,7 @@ support corresponds to ``S`` values in the ``MAINTAINERS`` file. Architecture Level of support Constraints ============= ================ ============================================== ``arm64`` Maintained Little Endian only. -``loongarch`` Maintained - +``loongarch`` Maintained \- ``um`` Maintained ``x86_64`` only. ``x86`` Maintained ``x86_64`` only. ============= ================ ============================================== diff --git a/Documentation/timers/no_hz.rst b/Documentation/timers/no_hz.rst index f8786be15183c1..7fe8ef9718d8e3 100644 --- a/Documentation/timers/no_hz.rst +++ b/Documentation/timers/no_hz.rst @@ -129,11 +129,8 @@ adaptive-tick CPUs: At least one non-adaptive-tick CPU must remain online to handle timekeeping tasks in order to ensure that system calls like gettimeofday() returns accurate values on adaptive-tick CPUs. (This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no running -user processes to observe slight drifts in clock rate.) Therefore, the -boot CPU is prohibited from entering adaptive-ticks mode. Specifying a -"nohz_full=" mask that includes the boot CPU will result in a boot-time -error message, and the boot CPU will be removed from the mask. Note that -this means that your system must have at least two CPUs in order for +user processes to observe slight drifts in clock rate.) Note that this +means that your system must have at least two CPUs in order for CONFIG_NO_HZ_FULL=y to do anything for you. Finally, adaptive-ticks CPUs must have their RCU callbacks offloaded. diff --git a/Documentation/translations/zh_CN/core-api/cachetlb.rst b/Documentation/translations/zh_CN/core-api/cachetlb.rst index b4a76ec75daa57..64295c61d1c136 100644 --- a/Documentation/translations/zh_CN/core-api/cachetlb.rst +++ b/Documentation/translations/zh_CN/core-api/cachetlb.rst @@ -260,7 +260,7 @@ HyperSparc cpu就是这样一个具有这种属性的cpu。 如果D-cache别名不是一个问题，这个程序可以简单地定义为该架构上 的nop。 - 在page->flags (PG_arch_1)中有一个位是“架构私有”。内核保证， + 在folio->flags (PG_arch_1)中有一个位是“架构私有”。内核保证， 对于分页缓存的页面，当这样的页面第一次进入分页缓存时，它将清除 这个位。 diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index afecfe3cc4a86b..5926115ec0ed86 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -20,6 +20,7 @@ System calls futex2 ebpf/index ioctl/index + mseal Security-related interfaces =========================== diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst new file mode 100644 index 00000000000000..4132eec995a399 --- /dev/null +++ b/Documentation/userspace-api/mseal.rst @@ -0,0 +1,199 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================== +Introduction of mseal +===================== + +:Author: Jeff Xu <jeffxu@chromium.org> + +Modern CPUs support memory permissions such as RW and NX bits. The memory +permission feature improves security stance on memory corruption bugs, i.e. +the attacker can’t just write to arbitrary memory and point the code to it, +the memory has to be marked with X bit, or else an exception will happen. + +Memory sealing additionally protects the mapping itself against +modifications. This is useful to mitigate memory corruption issues where a +corrupted pointer is passed to a memory management system. For example, +such an attacker primitive can break control-flow integrity guarantees +since read-only memory that is supposed to be trusted can become writable +or .text pages can get remapped. Memory sealing can automatically be +applied by the runtime loader to seal .text and .rodata pages and +applications can additionally seal security critical data at runtime. + +A similar feature already exists in the XNU kernel with the +VM_FLAGS_PERMANENT flag [1] and on OpenBSD with the mimmutable syscall [2]. + +User API +======== +mseal() +----------- +The mseal() syscall has the following signature: + +``int mseal(void addr, size_t len, unsigned long flags)`` + +**addr/len**: virtual memory address range. + +The address range set by ``addr``/``len`` must meet: + - The start address must be in an allocated VMA. + - The start address must be page aligned. + - The end address (``addr`` + ``len``) must be in an allocated VMA. + - no gap (unallocated memory) between start and end address. + +The ``len`` will be paged aligned implicitly by the kernel. + +**flags**: reserved for future use. + +**return values**: + +- ``0``: Success. + +- ``-EINVAL``: + - Invalid input ``flags``. + - The start address (``addr``) is not page aligned. + - Address range (``addr`` + ``len``) overflow. + +- ``-ENOMEM``: + - The start address (``addr``) is not allocated. + - The end address (``addr`` + ``len``) is not allocated. + - A gap (unallocated memory) between start and end address. + +- ``-EPERM``: + - sealing is supported only on 64-bit CPUs, 32-bit is not supported. + +- For above error cases, users can expect the given memory range is + unmodified, i.e. no partial update. + +- There might be other internal errors/cases not listed here, e.g. + error during merging/splitting VMAs, or the process reaching the max + number of supported VMAs. In those cases, partial updates to the given + memory range could happen. However, those cases should be rare. + +**Blocked operations after sealing**: + Unmapping, moving to another location, and shrinking the size, + via munmap() and mremap(), can leave an empty space, therefore + can be replaced with a VMA with a new set of attributes. + + Moving or expanding a different VMA into the current location, + via mremap(). + + Modifying a VMA via mmap(MAP_FIXED). + + Size expansion, via mremap(), does not appear to pose any + specific risks to sealed VMAs. It is included anyway because + the use case is unclear. In any case, users can rely on + merging to expand a sealed VMA. + + mprotect() and pkey_mprotect(). + + Some destructive madvice() behaviors (e.g. MADV_DONTNEED) + for anonymous memory, when users don't have write permission to the + memory. Those behaviors can alter region contents by discarding pages, + effectively a memset(0) for anonymous memory. + + Kernel will return -EPERM for blocked operations. + + For blocked operations, one can expect the given address is unmodified, + i.e. no partial update. Note, this is different from existing mm + system call behaviors, where partial updates are made till an error is + found and returned to userspace. To give an example: + + Assume following code sequence: + + - ptr = mmap(null, 8192, PROT_NONE); + - munmap(ptr + 4096, 4096); + - ret1 = mprotect(ptr, 8192, PROT_READ); + - mseal(ptr, 4096); + - ret2 = mprotect(ptr, 8192, PROT_NONE); + + ret1 will be -ENOMEM, the page from ptr is updated to PROT_READ. + + ret2 will be -EPERM, the page remains to be PROT_READ. + +**Note**: + +- mseal() only works on 64-bit CPUs, not 32-bit CPU. + +- users can call mseal() multiple times, mseal() on an already sealed memory + is a no-action (not error). + +- munseal() is not supported. + +Use cases: +========== +- glibc: + The dynamic linker, during loading ELF executables, can apply sealing to + non-writable memory segments. + +- Chrome browser: protect some security sensitive data-structures. + +Notes on which memory to seal: +============================== + +It might be important to note that sealing changes the lifetime of a mapping, +i.e. the sealed mapping won’t be unmapped till the process terminates or the +exec system call is invoked. Applications can apply sealing to any virtual +memory region from userspace, but it is crucial to thoroughly analyze the +mapping's lifetime prior to apply the sealing. + +For example: + +- aio/shm + + aio/shm can call mmap()/munmap() on behalf of userspace, e.g. ksys_shmdt() in + shm.c. The lifetime of those mapping are not tied to the lifetime of the + process. If those memories are sealed from userspace, then munmap() will fail, + causing leaks in VMA address space during the lifetime of the process. + +- Brk (heap) + + Currently, userspace applications can seal parts of the heap by calling + malloc() and mseal(). + let's assume following calls from user space: + + - ptr = malloc(size); + - mprotect(ptr, size, RO); + - mseal(ptr, size); + - free(ptr); + + Technically, before mseal() is added, the user can change the protection of + the heap by calling mprotect(RO). As long as the user changes the protection + back to RW before free(), the memory range can be reused. + + Adding mseal() into the picture, however, the heap is then sealed partially, + the user can still free it, but the memory remains to be RO. If the address + is re-used by the heap manager for another malloc, the process might crash + soon after. Therefore, it is important not to apply sealing to any memory + that might get recycled. + + Furthermore, even if the application never calls the free() for the ptr, + the heap manager may invoke the brk system call to shrink the size of the + heap. In the kernel, the brk-shrink will call munmap(). Consequently, + depending on the location of the ptr, the outcome of brk-shrink is + nondeterministic. + + +Additional notes: +================= +As Jann Horn pointed out in [3], there are still a few ways to write +to RO memory, which is, in a way, by design. Those cases are not covered +by mseal(). If applications want to block such cases, sandbox tools (such as +seccomp, LSM, etc) might be considered. + +Those cases are: + +- Write to read-only memory through /proc/self/mem interface. +- Write to read-only memory through ptrace (such as PTRACE_POKETEXT). +- userfaultfd. + +The idea that inspired this patch comes from Stephen Röttger’s work in V8 +CFI [4]. Chrome browser in ChromeOS will be the first user of this API. + +Reference: +========== +[1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274 + +[2] https://man.openbsd.org/mimmutable.2 + +[3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com + +[4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc diff --git a/MAINTAINERS b/MAINTAINERS index ebf03f5f0619a6..12bfd1e26a38a0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -553,7 +553,7 @@ F: Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml F: drivers/input/misc/adxl34x.c ADXL355 THREE-AXIS DIGITAL ACCELEROMETER DRIVER -M: Puranjay Mohan <puranjay12@gmail.com> +M: Puranjay Mohan <puranjay@kernel.org> L: linux-iio@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/iio/accel/adi,adxl355.yaml @@ -3714,7 +3714,7 @@ F: drivers/iio/imu/bmi323/ BPF JIT for ARM M: Russell King <linux@armlinux.org.uk> -M: Puranjay Mohan <puranjay12@gmail.com> +M: Puranjay Mohan <puranjay@kernel.org> L: bpf@vger.kernel.org S: Maintained F: arch/arm/net/ @@ -3764,6 +3764,8 @@ X: arch/riscv/net/bpf_jit_comp64.c BPF JIT for RISC-V (64-bit) M: Björn Töpel <bjorn@kernel.org> +R: Pu Lehui <pulehui@huawei.com> +R: Puranjay Mohan <puranjay@kernel.org> L: bpf@vger.kernel.org S: Maintained F: arch/riscv/net/ @@ -5252,6 +5254,14 @@ S: Supported F: Documentation/process/code-of-conduct-interpretation.rst F: Documentation/process/code-of-conduct.rst +CODE TAGGING +M: Suren Baghdasaryan <surenb@google.com> +M: Kent Overstreet <kent.overstreet@linux.dev> +S: Maintained +F: include/asm-generic/codetag.lds.h +F: include/linux/codetag.h +F: lib/codetag.c + COMEDI DRIVERS M: Ian Abbott <abbotti@mev.co.uk> M: H Hartley Sweeten <hsweeten@visionengravers.com> @@ -7829,9 +7839,8 @@ 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 @@ -9576,7 +9585,7 @@ 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 @@ -12041,6 +12050,7 @@ M: Mimi Zohar <zohar@linux.ibm.com> L: linux-integrity@vger.kernel.org L: keyrings@vger.kernel.org S: Supported +W: https://kernsec.org/wiki/index.php/Linux_Kernel_Integrity F: security/integrity/platform_certs KFENCE @@ -14150,6 +14160,16 @@ F: mm/memblock.c F: mm/mm_init.c F: tools/testing/memblock/ +MEMORY ALLOCATION PROFILING +M: Suren Baghdasaryan <surenb@google.com> +M: Kent Overstreet <kent.overstreet@linux.dev> +L: linux-mm@kvack.org +S: Maintained +F: Documentation/mm/allocation-profiling.rst +F: include/linux/alloc_tag.h +F: include/linux/pgalloc_tag.h +F: lib/alloc_tag.c + MEMORY CONTROLLER DRIVERS M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-kernel@vger.kernel.org @@ -16799,12 +16819,6 @@ S: Maintained F: drivers/leds/leds-pca9532.c F: include/linux/leds-pca9532.h -PCA9541 I2C BUS MASTER SELECTOR DRIVER -M: Guenter Roeck <linux@roeck-us.net> -L: linux-i2c@vger.kernel.org -S: Maintained -F: drivers/i2c/muxes/i2c-mux-pca9541.c - PCI DRIVER FOR AARDVARK (Marvell Armada 3700) M: Thomas Petazzoni <thomas.petazzoni@bootlin.com> M: Pali Rohár <pali@kernel.org> @@ -17873,7 +17887,7 @@ F: Documentation/devicetree/bindings/leds/irled/pwm-ir-tx.yaml F: drivers/media/rc/pwm-ir-tx.c PWM SUBSYSTEM -M: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> +M: Uwe Kleine-König <ukleinek@kernel.org> L: linux-pwm@vger.kernel.org S: Maintained Q: https://patchwork.ozlabs.org/project/linux-pwm/list/ @@ -20177,7 +20191,6 @@ F: include/linux/platform_data/simplefb.h SIOX M: Thorsten Scherer <t.scherer@eckelmann.de> -M: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> R: Pengutronix Kernel Team <kernel@pengutronix.de> S: Supported F: drivers/gpio/gpio-siox.c @@ -21926,7 +21939,7 @@ F: include/linux/soc/ti/ti_sci_inta_msi.h F: include/linux/soc/ti/ti_sci_protocol.h TEXAS INSTRUMENTS' TMP117 TEMPERATURE SENSOR DRIVER -M: Puranjay Mohan <puranjay12@gmail.com> +M: Puranjay Mohan <puranjay@kernel.org> L: linux-iio@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml @@ -22419,7 +22432,7 @@ M: Jarkko Sakkinen <jarkko@kernel.org> R: Jason Gunthorpe <jgg@ziepe.ca> L: linux-integrity@vger.kernel.org S: Maintained -W: https://kernsec.org/wiki/index.php/Linux_Kernel_Integrity +W: https://gitlab.com/jarkkojs/linux-tpmdd-test Q: https://patchwork.kernel.org/project/linux-integrity/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd.git F: Documentation/devicetree/bindings/tpm/ @@ -22839,7 +22852,7 @@ 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 diff --git a/Makefile b/Makefile index 949b73bf6d0d1c..f4fe5b0ea931b4 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* @@ -964,6 +964,11 @@ KBUILD_CFLAGS += $(CC_FLAGS_CFI) export CC_FLAGS_CFI endif +# Architectures can define flags to add/remove for floating-point support +CC_FLAGS_FPU += -D_LINUX_FPU_COMPILATION_UNIT +export CC_FLAGS_FPU +export CC_FLAGS_NO_FPU + ifneq ($(CONFIG_FUNCTION_ALIGNMENT),0) # Set the minimal function alignment. Use the newer GCC option # -fmin-function-alignment if it is available, or fall back to -falign-funtions. diff --git a/arch/Kconfig b/arch/Kconfig index 65afb1de48b36e..c5962cd8356109 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -9,6 +9,14 @@ # source "arch/$(SRCARCH)/Kconfig" +config ARCH_CONFIGURES_CPU_MITIGATIONS + bool + +if !ARCH_CONFIGURES_CPU_MITIGATIONS +config CPU_MITIGATIONS + def_bool y +endif + menu "General architecture-dependent options" config ARCH_HAS_SUBPAGE_FAULTS @@ -1569,6 +1577,12 @@ config ARCH_HAS_NONLEAF_PMD_YOUNG address translations. Page table walkers that clear the accessed bit may use this capability to reduce their search space. +config ARCH_HAS_KERNEL_FPU_SUPPORT + bool + help + Architectures that select this option can run floating-point code in + the kernel, as described in Documentation/core-api/floating-point.rst. + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 5db88b6274396d..e5f881bc82881c 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1218,14 +1218,11 @@ static unsigned long arch_get_unmapped_area_1(unsigned long addr, unsigned long len, unsigned long limit) { - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; - info.flags = 0; info.length = len; info.low_limit = addr; info.high_limit = limit; - info.align_mask = 0; - info.align_offset = 0; return vm_unmapped_area(&info); } diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index c81183935e9707..7fcf3e9b710305 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -929,7 +929,7 @@ const struct dma_map_ops alpha_pci_ops = { .dma_supported = alpha_pci_supported, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; EXPORT_SYMBOL(alpha_pci_ops); diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 8ff110826ce21d..d8f96362e9f83e 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -501,3 +501,4 @@ 569 common lsm_get_self_attr sys_lsm_get_self_attr 570 common lsm_set_self_attr sys_lsm_set_self_attr 571 common lsm_list_modules sys_lsm_list_modules +572 common mseal sys_mseal diff --git a/arch/alpha/lib/checksum.c b/arch/alpha/lib/checksum.c index 3f35c3ed694886..c29b98ef9c8267 100644 --- a/arch/alpha/lib/checksum.c +++ b/arch/alpha/lib/checksum.c @@ -14,6 +14,7 @@ #include <linux/string.h> #include <asm/byteorder.h> +#include <asm/checksum.h> static inline unsigned short from64to16(unsigned long x) { diff --git a/arch/alpha/lib/fpreg.c b/arch/alpha/lib/fpreg.c index 7c08b225261c4a..3d32165043f8b1 100644 --- a/arch/alpha/lib/fpreg.c +++ b/arch/alpha/lib/fpreg.c @@ -8,6 +8,7 @@ #include <linux/compiler.h> #include <linux/export.h> #include <linux/preempt.h> +#include <asm/fpu.h> #include <asm/thread_info.h> #if defined(CONFIG_ALPHA_EV6) || defined(CONFIG_ALPHA_EV67) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 99d2845f3feb95..4092bec198beca 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -6,7 +6,6 @@ config ARC def_bool y select ARC_TIMERS - select ARCH_HAS_CPU_CACHE_ALIASING select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DMA_PREP_COHERENT diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile index 5648748c285f52..5a8550124b73ec 100644 --- a/arch/arc/boot/Makefile +++ b/arch/arc/boot/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -# uImage build relies on mkimage being availble on your host for ARC target +# uImage build relies on mkimage being available on your host for ARC target # You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage -# and make sure it's reacable from your PATH +# and make sure it's reachable from your PATH OBJCOPYFLAGS= -O binary -R .note -R .note.gnu.build-id -R .comment -S diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index 3434c8131ecd54..c0a812674ce9ed 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -119,9 +119,9 @@ /* * The DW APB ICTL intc on MB is connected to CPU intc via a * DT "invisible" DW APB GPIO block, configured to simply pass thru - * interrupts - setup accordinly in platform init (plat-axs10x/ax10x.c) + * interrupts - setup accordingly in platform init (plat-axs10x/ax10x.c) * - * So here we mimic a direct connection betwen them, ignoring the + * So here we mimic a direct connection between them, ignoring the * ABPG GPIO. Thus set "interrupts = <24>" (DW APB GPIO to core) * instead of "interrupts = <12>" (DW APB ICTL to DW APB GPIO) * diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 6691f425507788..41b980df862b14 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -205,7 +205,6 @@ }; gmac: ethernet@8000 { - #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; interrupts = <10>; diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi index 90a412026e6433..0e0e2d337bf871 100644 --- a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi +++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi @@ -113,7 +113,7 @@ /* * Embedded Vision subsystem UIO mappings; only relevant for EV VDK * - * This node is intentionally put outside of MB above becase + * This node is intentionally put outside of MB above because * it maps areas outside of MB's 0xez-0xfz. */ uio_ev: uio@d0000000 { diff --git a/arch/arc/include/asm/cachetype.h b/arch/arc/include/asm/cachetype.h deleted file mode 100644 index 05fc7ed5971258..00000000000000 --- a/arch/arc/include/asm/cachetype.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_ARC_CACHETYPE_H -#define __ASM_ARC_CACHETYPE_H - -#include <linux/types.h> - -#define cpu_dcache_is_aliasing() true - -#endif diff --git a/arch/arc/include/asm/dsp.h b/arch/arc/include/asm/dsp.h index 202c78e567045b..f496dbc4640b24 100644 --- a/arch/arc/include/asm/dsp.h +++ b/arch/arc/include/asm/dsp.h @@ -12,7 +12,7 @@ /* * DSP-related saved registers - need to be saved only when you are * scheduled out. - * structure fields name must correspond to aux register defenitions for + * structure fields name must correspond to aux register definitions for * automatic offset calculation in DSP_AUX_SAVE_RESTORE macros */ struct dsp_callee_regs { diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h index 92c3e9f1325219..00946fe04c9b26 100644 --- a/arch/arc/include/asm/entry-compact.h +++ b/arch/arc/include/asm/entry-compact.h @@ -7,7 +7,7 @@ * Stack switching code can no longer reliably rely on the fact that * if we are NOT in user mode, stack is switched to kernel mode. * e.g. L2 IRQ interrupted a L1 ISR which had not yet completed - * it's prologue including stack switching from user mode + * its prologue including stack switching from user mode * * Vineetg: Aug 28th 2008: Bug #94984 * -Zero Overhead Loop Context shd be cleared when entering IRQ/EXcp/Trap @@ -143,7 +143,7 @@ * 2. L1 IRQ taken, ISR starts (CPU auto-switched to KERNEL mode) * 3. But before it could switch SP from USER to KERNEL stack * a L2 IRQ "Interrupts" L1 - * Thay way although L2 IRQ happened in Kernel mode, stack is still + * That way although L2 IRQ happened in Kernel mode, stack is still * not switched. * To handle this, we may need to switch stack even if in kernel mode * provided SP has values in range of USER mode stack ( < 0x7000_0000 ) @@ -173,7 +173,7 @@ GET_CURR_TASK_ON_CPU r9 - /* With current tsk in r9, get it's kernel mode stack base */ + /* With current tsk in r9, get its kernel mode stack base */ GET_TSK_STACK_BASE r9, r9 /* save U mode SP @ pt_regs->sp */ @@ -282,7 +282,7 @@ * NOTE: * * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg - * for memory load operations. If used in that way interrupts are deffered + * for memory load operations. If used in that way interrupts are deferred * by hardware and that is not good. *-------------------------------------------------------------*/ .macro EXCEPTION_EPILOGUE @@ -350,7 +350,7 @@ * NOTE: * * It is recommended that lp_count/ilink1/ilink2 not be used as a dest reg - * for memory load operations. If used in that way interrupts are deffered + * for memory load operations. If used in that way interrupts are deferred * by hardware and that is not good. *-------------------------------------------------------------*/ .macro INTERRUPT_EPILOGUE LVL diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index cf1ba376e992c6..38c35722cebf03 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -7,7 +7,7 @@ #ifndef __ASM_ARC_ENTRY_H #define __ASM_ARC_ENTRY_H -#include <asm/unistd.h> /* For NR_syscalls defination */ +#include <asm/unistd.h> /* For NR_syscalls definition */ #include <asm/arcregs.h> #include <asm/ptrace.h> #include <asm/processor.h> /* For VMALLOC_START */ @@ -56,7 +56,7 @@ .endm /*------------------------------------------------------------- - * given a tsk struct, get to the base of it's kernel mode stack + * given a tsk struct, get to the base of its kernel mode stack * tsk->thread_info is really a PAGE, whose bottom hoists stack * which grows upwards towards thread_info *------------------------------------------------------------*/ diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index c574712ad86589..9cd79263acba82 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -10,7 +10,7 @@ * ARCv2 can support 240 interrupts in the core interrupts controllers and * 128 interrupts in IDU. Thus 512 virtual IRQs must be enough for most * configurations of boards. - * This doesnt affect ARCompact, but we change it to same value + * This doesn't affect ARCompact, but we change it to same value */ #define NR_IRQS 512 diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index 0d63e568d64cb5..936a2f21f315ed 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -46,7 +46,7 @@ * IRQ Control Macros * * All of them have "memory" clobber (compiler barrier) which is needed to - * ensure that LD/ST requiring irq safetly (R-M-W when LLSC is not available) + * ensure that LD/ST requiring irq safety (R-M-W when LLSC is not available) * are redone after IRQs are re-enabled (and gcc doesn't reuse stale register) * * Noted at the time of Abilis Timer List corruption diff --git a/arch/arc/include/asm/mmu-arcv2.h b/arch/arc/include/asm/mmu-arcv2.h index ed9036d4ede310..d85dc07219071f 100644 --- a/arch/arc/include/asm/mmu-arcv2.h +++ b/arch/arc/include/asm/mmu-arcv2.h @@ -9,6 +9,8 @@ #ifndef _ASM_ARC_MMU_ARCV2_H #define _ASM_ARC_MMU_ARCV2_H +#include <soc/arc/aux.h> + /* * TLB Management regs */ diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h index dda471f5f05bbf..9963bb1a5733fb 100644 --- a/arch/arc/include/asm/mmu_context.h +++ b/arch/arc/include/asm/mmu_context.h @@ -165,7 +165,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * for retiring-mm. However destroy_context( ) still needs to do that because * between mm_release( ) = >deactive_mm( ) and * mmput => .. => __mmdrop( ) => destroy_context( ) - * there is a good chance that task gets sched-out/in, making it's ASID valid + * there is a good chance that task gets sched-out/in, making its ASID valid * again (this teased me for a whole day). */ diff --git a/arch/arc/include/asm/pgtable-bits-arcv2.h b/arch/arc/include/asm/pgtable-bits-arcv2.h index f3eea3f30b2e29..8ebec1b21d246e 100644 --- a/arch/arc/include/asm/pgtable-bits-arcv2.h +++ b/arch/arc/include/asm/pgtable-bits-arcv2.h @@ -66,7 +66,7 @@ * Other rules which cause the divergence from 1:1 mapping * * 1. Although ARC700 can do exclusive execute/write protection (meaning R - * can be tracked independet of X/W unlike some other CPUs), still to + * can be tracked independently of X/W unlike some other CPUs), still to * keep things consistent with other archs: * -Write implies Read: W => R * -Execute implies Read: X => R diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h index 00b9318e551e7e..cf79df0b257053 100644 --- a/arch/arc/include/asm/ptrace.h +++ b/arch/arc/include/asm/ptrace.h @@ -169,7 +169,7 @@ static inline unsigned long regs_get_register(struct pt_regs *regs, return *(unsigned long *)((unsigned long)regs + offset); } -extern int syscall_trace_entry(struct pt_regs *); +extern int syscall_trace_enter(struct pt_regs *); extern void syscall_trace_exit(struct pt_regs *); #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/include/asm/shmparam.h b/arch/arc/include/asm/shmparam.h index 8b0251464ffd42..719112af0f41ae 100644 --- a/arch/arc/include/asm/shmparam.h +++ b/arch/arc/include/asm/shmparam.h @@ -6,7 +6,7 @@ #ifndef __ARC_ASM_SHMPARAM_H #define __ARC_ASM_SHMPARAM_H -/* Handle upto 2 cache bins */ +/* Handle up to 2 cache bins */ #define SHMLBA (2 * PAGE_SIZE) /* Enforce SHMLBA in shmat */ diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index e0913f52c2cdda..990f834909f088 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -77,7 +77,7 @@ static inline const char *arc_platform_smp_cpuinfo(void) /* * ARC700 doesn't support atomic Read-Modify-Write ops. - * Originally Interrupts had to be disabled around code to gaurantee atomicity. + * Originally Interrupts had to be disabled around code to guarantee atomicity. * The LLOCK/SCOND insns allow writing interrupt-hassle-free based atomic ops * based on retry-if-irq-in-atomic (with hardware assist). * However despite these, we provide the IRQ disabling variant @@ -86,7 +86,7 @@ static inline const char *arc_platform_smp_cpuinfo(void) * support needed. * * (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be - * gaurantted by the platform (not something which core handles). + * guaranteed by the platform (not something which core handles). * Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ * disabling for atomicity. * diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index 4c530cf131f339..12daaf3a61eaf6 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -38,7 +38,7 @@ struct thread_info { unsigned long flags; /* low level flags */ unsigned long ksp; /* kernel mode stack top in __switch_to */ - int preempt_count; /* 0 => preemptable, <0 => BUG */ + int preempt_count; /* 0 => preemptible, <0 => BUG */ int cpu; /* current CPU */ unsigned long thr_ptr; /* TLS ptr */ struct task_struct *task; /* main task structure */ diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h index 02109cd48ee129..8d1f1ef44ba750 100644 --- a/arch/arc/include/uapi/asm/swab.h +++ b/arch/arc/include/uapi/asm/swab.h @@ -62,7 +62,7 @@ * 8051fdc4: st r2,[r1,20] ; Mem op : save result back to mem * * Joern suggested a better "C" algorithm which is great since - * (1) It is portable to any architecure + * (1) It is portable to any architecture * (2) At the same time it takes advantage of ARC ISA (rotate intrns) */ diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index 2e49c81c8086b1..e238b5fd3c8cff 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -5,7 +5,7 @@ * Copyright (C) 2013 Synopsys, Inc. (www.synopsys.com) */ -#include <linux/linkage.h> /* ARC_{EXTRY,EXIT} */ +#include <linux/linkage.h> /* ARC_{ENTRY,EXIT} */ #include <asm/entry.h> /* SAVE_ALL_{INT1,INT2,TRAP...} */ #include <asm/errno.h> #include <asm/arcregs.h> @@ -31,7 +31,7 @@ VECTOR res_service ; Reset Vector VECTOR mem_service ; Mem exception VECTOR instr_service ; Instrn Error VECTOR EV_MachineCheck ; Fatal Machine check -VECTOR EV_TLBMissI ; Intruction TLB miss +VECTOR EV_TLBMissI ; Instruction TLB miss VECTOR EV_TLBMissD ; Data TLB miss VECTOR EV_TLBProtV ; Protection Violation VECTOR EV_PrivilegeV ; Privilege Violation @@ -76,11 +76,11 @@ ENTRY(handle_interrupt) # query in hard ISR path would return false (since .IE is set) which would # trips genirq interrupt handling asserts. # - # So do a "soft" disable of interrutps here. + # So do a "soft" disable of interrupts here. # # Note this disable is only for consistent book-keeping as further interrupts # will be disabled anyways even w/o this. Hardware tracks active interrupts - # seperately in AUX_IRQ_ACT.active and will not take new interrupts + # separately in AUX_IRQ_ACT.active and will not take new interrupts # unless this one returns (or higher prio becomes pending in 2-prio scheme) IRQ_DISABLE diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 089f6680518f82..3c7e74aba6794e 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -95,7 +95,7 @@ ENTRY(EV_MachineCheck) lr r0, [efa] mov r1, sp - ; MC excpetions disable MMU + ; MC exceptions disable MMU ARC_MMU_REENABLE r3 lsr r3, r10, 8 @@ -209,7 +209,7 @@ trap_with_param: ; --------------------------------------------- ; syscall TRAP -; ABI: (r0-r7) upto 8 args, (r8) syscall number +; ABI: (r0-r7) up to 8 args, (r8) syscall number ; --------------------------------------------- ENTRY(EV_Trap) diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 9152782444b557..8d541f53fae3ec 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -165,7 +165,7 @@ ENTRY(first_lines_of_secondary) ; setup stack (fp, sp) mov fp, 0 - ; set it's stack base to tsk->thread_info bottom + ; set its stack base to tsk->thread_info bottom GET_TSK_STACK_BASE r0, sp j start_kernel_secondary diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c index 678898757e4739..f324f0e3341a39 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -56,7 +56,7 @@ void arc_init_IRQ(void) WRITE_AUX(AUX_IRQ_CTRL, ictrl); /* - * ARCv2 core intc provides multiple interrupt priorities (upto 16). + * ARCv2 core intc provides multiple interrupt priorities (up to 16). * Typical builds though have only two levels (0-high, 1-low) * Linux by default uses lower prio 1 for most irqs, reserving 0 for * NMI style interrupts in future (say perf) diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index e71d64119d71ac..f8e2960832d943 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -190,7 +190,8 @@ static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs) } } -int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) +static int +__kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) { struct kprobe *p; struct kprobe_ctlblk *kcb; @@ -241,8 +242,8 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs) return 0; } -static int __kprobes arc_post_kprobe_handler(unsigned long addr, - struct pt_regs *regs) +static int +__kprobes arc_post_kprobe_handler(unsigned long addr, struct pt_regs *regs) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index adff957962da88..6e5a651cd75cf5 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -38,7 +38,7 @@ * (based on a specific RTL build) * Below is the static map between perf generic/arc specific event_id and * h/w condition names. - * At the time of probe, we loop thru each index and find it's name to + * At the time of probe, we loop thru each index and find its name to * complete the mapping of perf event_id to h/w index as latter is needed * to program the counter really */ diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index d08a5092c2b4d4..7b6a9beba9db6d 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -390,7 +390,7 @@ static void arc_chk_core_config(struct cpuinfo_arc *info) #ifdef CONFIG_ARC_HAS_DCCM /* * DCCM can be arbit placed in hardware. - * Make sure it's placement/sz matches what Linux is built with + * Make sure its placement/sz matches what Linux is built with */ if ((unsigned int)__arc_dccm_base != info->dccm.base) panic("Linux built with incorrect DCCM Base address\n"); diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 8f6f4a5429646f..fefa705a863850 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -8,15 +8,16 @@ * * vineetg: Nov 2009 (Everything needed for TIF_RESTORE_SIGMASK) * -do_signal() supports TIF_RESTORE_SIGMASK - * -do_signal() no loner needs oldset, required by OLD sys_sigsuspend - * -sys_rt_sigsuspend() now comes from generic code, so discard arch implemen + * -do_signal() no longer needs oldset, required by OLD sys_sigsuspend + * -sys_rt_sigsuspend() now comes from generic code, so discard arch + * implementation * -sys_sigsuspend() no longer needs to fudge ptregs, hence that arg removed * -sys_sigsuspend() no longer loops for do_signal(), sets TIF_xxx and leaves * the job to do_signal() * * vineetg: July 2009 * -Modified Code to support the uClibc provided userland sigreturn stub - * to avoid kernel synthesing it on user stack at runtime, costing TLB + * to avoid kernel synthesizing it on user stack at runtime, costing TLB * probes and Cache line flushes. * * vineetg: July 2009 diff --git a/arch/arc/kernel/traps.c b/arch/arc/kernel/traps.c index 9b9570b79362ee..a19751e824fb4c 100644 --- a/arch/arc/kernel/traps.c +++ b/arch/arc/kernel/traps.c @@ -89,7 +89,7 @@ int do_misaligned_access(unsigned long address, struct pt_regs *regs, /* * Entry point for miscll errors such as Nested Exceptions - * -Duplicate TLB entry is handled seperately though + * -Duplicate TLB entry is handled separately though */ void do_machine_check_fault(unsigned long address, struct pt_regs *regs) { diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S index 549c3f40791869..61a1b2b96e1d81 100644 --- a/arch/arc/kernel/vmlinux.lds.S +++ b/arch/arc/kernel/vmlinux.lds.S @@ -41,8 +41,8 @@ SECTIONS #endif /* - * The reason for having a seperate subsection .init.ramfs is to - * prevent objump from including it in kernel dumps + * The reason for having a separate subsection .init.ramfs is to + * prevent objdump from including it in kernel dumps * * Reason for having .init.ramfs above .init is to make sure that the * binary blob is tucked away to one side, reducing the displacement diff --git a/arch/arc/mm/mmap.c b/arch/arc/mm/mmap.c index 3c1c7ae732925c..69a91529715599 100644 --- a/arch/arc/mm/mmap.c +++ b/arch/arc/mm/mmap.c @@ -27,7 +27,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* * We enforce the MAP_FIXED case. @@ -51,11 +51,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; - info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index ad702b49aeb3b8..cae4a7aae0ed4e 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -212,7 +212,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long flags; /* If range @start to @end is more than 32 TLB entries deep, - * its better to move to a new ASID rather than searching for + * it's better to move to a new ASID rather than searching for * individual entries and then shooting them down * * The calc above is rough, doesn't account for unaligned parts, @@ -408,7 +408,7 @@ static void create_tlb(struct vm_area_struct *vma, unsigned long vaddr, pte_t *p * -More importantly it makes this handler inconsistent with fast-path * TLB Refill handler which always deals with "current" * - * Lets see the use cases when current->mm != vma->mm and we land here + * Let's see the use cases when current->mm != vma->mm and we land here * 1. execve->copy_strings()->__get_user_pages->handle_mm_fault * Here VM wants to pre-install a TLB entry for user stack while * current->mm still points to pre-execve mm (hence the condition). diff --git a/arch/arc/mm/tlbex.S b/arch/arc/mm/tlbex.S index e054780a8fe0c9..dc65e87a531fdb 100644 --- a/arch/arc/mm/tlbex.S +++ b/arch/arc/mm/tlbex.S @@ -5,19 +5,19 @@ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) * * Vineetg: April 2011 : - * -MMU v1: moved out legacy code into a seperate file + * -MMU v1: moved out legacy code into a separate file * -MMU v3: PD{0,1} bits layout changed: They don't overlap anymore, * helps avoid a shift when preparing PD0 from PTE * * Vineetg: July 2009 - * -For MMU V2, we need not do heuristics at the time of commiting a D-TLB - * entry, so that it doesn't knock out it's I-TLB entry + * -For MMU V2, we need not do heuristics at the time of committing a D-TLB + * entry, so that it doesn't knock out its I-TLB entry * -Some more fine tuning: * bmsk instead of add, asl.cc instead of branch, delay slot utilise etc * * Vineetg: July 2009 * -Practically rewrote the I/D TLB Miss handlers - * Now 40 and 135 instructions a peice as compared to 131 and 449 resp. + * Now 40 and 135 instructions apiece as compared to 131 and 449 resp. * Hence Leaner by 1.5 K * Used Conditional arithmetic to replace excessive branching * Also used short instructions wherever possible diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index b14aed3a17abb6..35fc382635354a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -15,6 +15,7 @@ config ARM select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_KEEPINITRD select ARCH_HAS_KCOV + select ARCH_HAS_KERNEL_FPU_SUPPORT if KERNEL_MODE_NEON select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL if ARM_LPAE @@ -99,7 +100,7 @@ config ARM select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_EXIT_THREAD - select HAVE_FAST_GUP if ARM_LPAE + select HAVE_GUP_FAST if ARM_LPAE select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER diff --git a/arch/arm/Makefile b/arch/arm/Makefile index d82908b1b1bb44..71afdd98ddf27f 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -130,6 +130,13 @@ endif # Accept old syntax despite ".syntax unified" AFLAGS_NOWARN :=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W) +# The GCC option -ffreestanding is required in order to compile code containing +# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) +CC_FLAGS_FPU := -ffreestanding +# Enable <arm_neon.h> +CC_FLAGS_FPU += -isystem $(shell $(CC) -print-file-name=include) +CC_FLAGS_FPU += -march=armv7-a -mfloat-abi=softfp -mfpu=neon + ifeq ($(CONFIG_THUMB2_KERNEL),y) CFLAGS_ISA :=-Wa,-mimplicit-it=always $(AFLAGS_NOWARN) AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb diff --git a/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts index 4f609e9e510ef6..009d2c83242102 100644 --- a/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts +++ b/arch/arm/boot/dts/microchip/at91-sama7g54_curiosity.dts @@ -242,7 +242,7 @@ regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1150000>; + regulator-suspend-microvolt = <1150000>; regulator-mode = <4>; }; @@ -263,7 +263,7 @@ regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1050000>; + regulator-suspend-microvolt = <1050000>; regulator-mode = <4>; }; @@ -280,7 +280,7 @@ regulator-always-on; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; @@ -296,7 +296,7 @@ regulator-always-on; regulator-state-standby { - regulator-suspend-voltage = <3300000>; + regulator-suspend-microvolt = <3300000>; regulator-on-in-suspend; }; diff --git a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts index 217e9b96c61e5d..20b2497657ae48 100644 --- a/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/microchip/at91-sama7g5ek.dts @@ -293,7 +293,7 @@ regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1150000>; + regulator-suspend-microvolt = <1150000>; regulator-mode = <4>; }; @@ -314,7 +314,7 @@ regulator-state-standby { regulator-on-in-suspend; - regulator-suspend-voltage = <1050000>; + regulator-suspend-microvolt = <1050000>; regulator-mode = <4>; }; @@ -331,7 +331,7 @@ regulator-always-on; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; @@ -346,7 +346,7 @@ regulator-max-microvolt = <3700000>; regulator-state-standby { - regulator-suspend-voltage = <1800000>; + regulator-suspend-microvolt = <1800000>; regulator-on-in-suspend; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi index 3fdece5bd31f9d..5248a058230c86 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ull-tarragon-common.dtsi @@ -805,6 +805,7 @@ &pinctrl_usb_pwr>; dr_mode = "host"; power-active-high; + over-current-active-low; disable-over-current; status = "okay"; }; diff --git a/arch/arm/include/asm/fpu.h b/arch/arm/include/asm/fpu.h new file mode 100644 index 00000000000000..2ae50bdce59b43 --- /dev/null +++ b/arch/arm/include/asm/fpu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef __ASM_FPU_H +#define __ASM_FPU_H + +#include <asm/neon.h> + +#define kernel_fpu_available() cpu_has_neon() +#define kernel_fpu_begin() kernel_neon_begin() +#define kernel_fpu_end() kernel_neon_end() + +#endif /* ! __ASM_FPU_H */ diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h index a3a82b7158d4cb..b766c4b373f647 100644 --- a/arch/arm/include/asm/hugetlb.h +++ b/arch/arm/include/asm/hugetlb.h @@ -15,10 +15,10 @@ #include <asm/hugetlb-3level.h> #include <asm-generic/hugetlb.h> -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif /* _ASM_ARM_HUGETLB_H */ diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index b0a262566eb95a..6b5392e20f4113 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -213,8 +213,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define pmd_pfn(pmd) (__phys_to_pfn(pmd_val(pmd) & PHYS_MASK)) -#define pmd_leaf(pmd) (pmd_val(pmd) & 2) -#define pmd_bad(pmd) (pmd_val(pmd) & 2) +#define pmd_leaf(pmd) (pmd_val(pmd) & PMD_TYPE_SECT) +#define pmd_bad(pmd) pmd_leaf(pmd) #define pmd_present(pmd) (pmd_val(pmd)) #define copy_pmd(pmdpd,pmdps) \ @@ -241,7 +241,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) * define empty stubs for use by pin_page_for_write. */ #define pmd_hugewillfault(pmd) (0) -#define pmd_thp_or_huge(pmd) (0) #endif /* __ASSEMBLY__ */ diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h index 2f35b4eddaa809..e7b666cf006031 100644 --- a/arch/arm/include/asm/pgtable-3level-hwdef.h +++ b/arch/arm/include/asm/pgtable-3level-hwdef.h @@ -14,6 +14,7 @@ * + Level 1/2 descriptor * - common */ +#define PUD_TABLE_BIT (_AT(pmdval_t, 1) << 1) #define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0) #define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0) #define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0) diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 4b1d9eb3908a22..fa5939eb9864ef 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -112,7 +112,7 @@ #ifndef __ASSEMBLY__ #define pud_none(pud) (!pud_val(pud)) -#define pud_bad(pud) (!(pud_val(pud) & 2)) +#define pud_bad(pud) (!(pud_val(pud) & PUD_TABLE_BIT)) #define pud_present(pud) (pud_val(pud)) #define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_TABLE) @@ -137,7 +137,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK); } -#define pmd_bad(pmd) (!(pmd_val(pmd) & 2)) +#define pmd_bad(pmd) (!(pmd_val(pmd) & PMD_TABLE_BIT)) #define copy_pmd(pmdpd,pmdps) \ do { \ @@ -190,7 +190,6 @@ static inline pte_t pte_mkspecial(pte_t pte) #define pmd_dirty(pmd) (pmd_isset((pmd), L_PMD_SECT_DIRTY)) #define pmd_hugewillfault(pmd) (!pmd_young(pmd) || !pmd_write(pmd)) -#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !pmd_table(pmd)) diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index fe28fc1f759d93..dab42d066d068b 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -32,6 +32,7 @@ #include <linux/kallsyms.h> #include <linux/proc_fs.h> #include <linux/export.h> +#include <linux/vmalloc.h> #include <asm/hardware/cache-l2x0.h> #include <asm/hardware/cache-uniphier.h> diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 72c82a4d63ac20..480e307501bb4b 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -26,6 +26,7 @@ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/irq.h> +#include <linux/vmalloc.h> #include <linux/atomic.h> #include <asm/cacheflush.h> diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile index 650404be6768a0..0ca5aae1bcc3e3 100644 --- a/arch/arm/lib/Makefile +++ b/arch/arm/lib/Makefile @@ -40,8 +40,7 @@ $(obj)/csumpartialcopy.o: $(obj)/csumpartialcopygeneric.S $(obj)/csumpartialcopyuser.o: $(obj)/csumpartialcopygeneric.S ifeq ($(CONFIG_KERNEL_MODE_NEON),y) - NEON_FLAGS := -march=armv7-a -mfloat-abi=softfp -mfpu=neon - CFLAGS_xor-neon.o += $(NEON_FLAGS) + CFLAGS_xor-neon.o += $(CC_FLAGS_FPU) obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o endif diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 2f6163f05e9357..c0ac7796d77508 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -56,10 +56,10 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) * to see that it's still huge and whether or not we will * need to fault on write. */ - if (unlikely(pmd_thp_or_huge(*pmd))) { + if (unlikely(pmd_leaf(*pmd))) { ptl = ¤t->mm->page_table_lock; spin_lock(ptl); - if (unlikely(!pmd_thp_or_huge(*pmd) + if (unlikely(!pmd_leaf(*pmd) || pmd_hugewillfault(*pmd))) { spin_unlock(ptl); return 0; diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 71b858c9b10c47..1779e12db0850d 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -21,7 +21,6 @@ KASAN_SANITIZE_physaddr.o := n obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_ALIGNMENT_TRAP) += alignment.o -obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_ARM_PV_FIXUP) += pv-fixup-asm.o obj-$(CONFIG_CPU_ABRT_NOMMU) += abort-nommu.o diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 439dc6a26bb982..bf07afdb2dd9e1 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -226,9 +226,6 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs) } #ifdef CONFIG_MMU -#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) -#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) - static inline bool is_permission_fault(unsigned int fsr) { int fs = fsr_fs(fsr); @@ -294,7 +291,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + fault = 0; + code = SEGV_ACCERR; + goto bad_area; } fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) @@ -319,7 +319,8 @@ lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { - fault = VM_FAULT_BADMAP; + fault = 0; + code = SEGV_MAPERR; goto bad_area; } @@ -327,10 +328,14 @@ retry: * ok, we have a good vm_area for this memory access, check the * permissions on the VMA allow for the fault which occurred. */ - if (!(vma->vm_flags & vm_flags)) - fault = VM_FAULT_BADACCESS; - else - fault = handle_mm_fault(vma, addr & PAGE_MASK, flags, regs); + if (!(vma->vm_flags & vm_flags)) { + mmap_read_unlock(mm); + fault = 0; + code = SEGV_ACCERR; + goto bad_area; + } + + fault = handle_mm_fault(vma, addr & PAGE_MASK, flags, regs); /* If we need to retry but a fatal signal is pending, handle the * signal first. We do not need to release the mmap_lock because @@ -356,12 +361,11 @@ retry: mmap_read_unlock(mm); done: - /* - * Handle the "normal" case first - VM_FAULT_MAJOR - */ - if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS)))) + /* Handle the "normal" case first */ + if (likely(!(fault & VM_FAULT_ERROR))) return 0; + code = SEGV_MAPERR; bad_area: /* * If we are in kernel mode at this point, we @@ -393,8 +397,6 @@ bad_area: * isn't in our memory map.. */ sig = SIGSEGV; - code = fault == VM_FAULT_BADACCESS ? - SEGV_ACCERR : SEGV_MAPERR; } __do_user_fault(addr, fsr, sig, code, regs); diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c deleted file mode 100644 index dd7a0277c5c094..00000000000000 --- a/arch/arm/mm/hugetlbpage.c +++ /dev/null @@ -1,34 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * arch/arm/mm/hugetlbpage.c - * - * Copyright (C) 2012 ARM Ltd. - * - * Based on arch/x86/include/asm/hugetlb.h and Bill Carson's patches - */ - -#include <linux/init.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/hugetlb.h> -#include <linux/pagemap.h> -#include <linux/err.h> -#include <linux/sysctl.h> -#include <asm/mman.h> -#include <asm/tlb.h> -#include <asm/tlbflush.h> - -/* - * On ARM, huge pages are backed by pmd's rather than pte's, so we do a lot - * of type casting from pmd_t * to pte_t *. - */ - -int pud_huge(pud_t pud) -{ - return 0; -} - -int pmd_huge(pmd_t pmd) -{ - return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); -} diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index a0f8a0ca0788ad..d65d0e6ed10ab4 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -34,7 +34,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct vm_area_struct *vma; int do_align = 0; int aliasing = cache_is_vipt_aliasing(); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* * We only need to do colour alignment if either the I or D @@ -68,7 +68,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; @@ -87,7 +86,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long addr = addr0; int do_align = 0; int aliasing = cache_is_vipt_aliasing(); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* * We only need to do colour alignment if either the I or D diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1d672457d02ff3..72b5cd697f5d94 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -871,16 +871,11 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[], } /* dst = src (4 bytes)*/ -static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off, - struct jit_ctx *ctx) { +static inline void emit_a32_mov_r(const s8 dst, const s8 src, struct jit_ctx *ctx) { const s8 *tmp = bpf2a32[TMP_REG_1]; s8 rt; rt = arm_bpf_get_reg32(src, tmp[0], ctx); - if (off && off != 32) { - emit(ARM_LSL_I(rt, rt, 32 - off), ctx); - emit(ARM_ASR_I(rt, rt, 32 - off), ctx); - } arm_bpf_put_reg32(dst, rt, ctx); } @@ -889,15 +884,15 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], const s8 src[], struct jit_ctx *ctx) { if (!is64) { - emit_a32_mov_r(dst_lo, src_lo, 0, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); if (!ctx->prog->aux->verifier_zext) /* Zero out high 4 bytes */ emit_a32_mov_i(dst_hi, 0, ctx); } else if (__LINUX_ARM_ARCH__ < 6 && ctx->cpu_architecture < CPU_ARCH_ARMv5TE) { /* complete 8 byte move */ - emit_a32_mov_r(dst_lo, src_lo, 0, ctx); - emit_a32_mov_r(dst_hi, src_hi, 0, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); + emit_a32_mov_r(dst_hi, src_hi, ctx); } else if (is_stacked(src_lo) && is_stacked(dst_lo)) { const u8 *tmp = bpf2a32[TMP_REG_1]; @@ -917,17 +912,52 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[], struct jit_ctx *ctx) { const s8 *tmp = bpf2a32[TMP_REG_1]; - const s8 *rt; + s8 rs; + s8 rd; - rt = arm_bpf_get_reg64(dst, tmp, ctx); + if (is_stacked(dst_lo)) + rd = tmp[1]; + else + rd = dst_lo; + rs = arm_bpf_get_reg32(src_lo, rd, ctx); + /* rs may be one of src[1], dst[1], or tmp[1] */ + + /* Sign extend rs if needed. If off == 32, lower 32-bits of src are moved to dst and sign + * extension only happens in the upper 64 bits. + */ + if (off != 32) { + /* Sign extend rs into rd */ + emit(ARM_LSL_I(rd, rs, 32 - off), ctx); + emit(ARM_ASR_I(rd, rd, 32 - off), ctx); + } else { + rd = rs; + } + + /* Write rd to dst_lo + * + * Optimization: + * Assume: + * 1. dst == src and stacked. + * 2. off == 32 + * + * In this case src_lo was loaded into rd(tmp[1]) but rd was not sign extended as off==32. + * So, we don't need to write rd back to dst_lo as they have the same value. + * This saves us one str instruction. + */ + if (dst_lo != src_lo || off != 32) + arm_bpf_put_reg32(dst_lo, rd, ctx); - emit_a32_mov_r(dst_lo, src_lo, off, ctx); if (!is64) { if (!ctx->prog->aux->verifier_zext) /* Zero out high 4 bytes */ emit_a32_mov_i(dst_hi, 0, ctx); } else { - emit(ARM_ASR_I(rt[0], rt[1], 31), ctx); + if (is_stacked(dst_hi)) { + emit(ARM_ASR_I(tmp[0], rd, 31), ctx); + arm_bpf_put_reg32(dst_hi, tmp[0], ctx); + } else { + emit(ARM_ASR_I(dst_hi, rd, 31), ctx); + } } } diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index b6c9e01e14f559..2ed7d229c8f96d 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -475,3 +475,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7b11c98b3e84bf..1bc3d2470ad1e5 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -30,6 +30,7 @@ config ARM64 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV + select ARCH_HAS_KERNEL_FPU_SUPPORT if KERNEL_MODE_NEON select ARCH_HAS_KEEPINITRD select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS @@ -205,7 +206,7 @@ config ARM64 select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_EFFICIENT_UNALIGNED_ACCESS - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_ERROR_INJECTION diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 0e075d3c546b48..3e863e5b016909 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -36,7 +36,14 @@ ifeq ($(CONFIG_BROKEN_GAS_INST),y) $(warning Detected assembler with broken .inst; disassembly will be unreliable) endif -KBUILD_CFLAGS += -mgeneral-regs-only \ +# The GCC option -ffreestanding is required in order to compile code containing +# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) +CC_FLAGS_FPU := -ffreestanding +# Enable <arm_neon.h> +CC_FLAGS_FPU += -isystem $(shell $(CC) -print-file-name=include) +CC_FLAGS_NO_FPU := -mgeneral-regs-only + +KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU) \ $(compat_vdso) $(cc_has_k_constraint) KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(compat_vdso) diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index bfc5c81a5bd4eb..8141926e4ef142 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1672,7 +1672,7 @@ <&clk IMX8MP_CLK_MEDIA_MIPI_PHY1_REF_ROOT>, <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>; clock-names = "pclk", "wrap", "phy", "axi"; - assigned-clocks = <&clk IMX8MP_CLK_MEDIA_CAM1_PIX>, + assigned-clocks = <&clk IMX8MP_CLK_MEDIA_CAM2_PIX>, <&clk IMX8MP_CLK_MEDIA_MIPI_PHY1_REF>; assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>, <&clk IMX8MP_CLK_24M>; diff --git a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts index 0c38f7b5176377..234e3b23d7a8d3 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt2712-evb.dts @@ -129,7 +129,7 @@ }; &pio { - eth_default: eth_default { + eth_default: eth-default-pins { tx_pins { pinmux = <MT2712_PIN_71_GBE_TXD3__FUNC_GBE_TXD3>, <MT2712_PIN_72_GBE_TXD2__FUNC_GBE_TXD2>, @@ -156,7 +156,7 @@ }; }; - eth_sleep: eth_sleep { + eth_sleep: eth-sleep-pins { tx_pins { pinmux = <MT2712_PIN_71_GBE_TXD3__FUNC_GPIO71>, <MT2712_PIN_72_GBE_TXD2__FUNC_GPIO72>, @@ -182,14 +182,14 @@ }; }; - usb0_id_pins_float: usb0_iddig { + usb0_id_pins_float: usb0-iddig-pins { pins_iddig { pinmux = <MT2712_PIN_12_IDDIG_P0__FUNC_IDDIG_A>; bias-pull-up; }; }; - usb1_id_pins_float: usb1_iddig { + usb1_id_pins_float: usb1-iddig-pins { pins_iddig { pinmux = <MT2712_PIN_14_IDDIG_P1__FUNC_IDDIG_B>; bias-pull-up; diff --git a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi index 6d218caa198cfd..082672efba0a34 100644 --- a/arch/arm64/boot/dts/mediatek/mt2712e.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt2712e.dtsi @@ -249,10 +249,11 @@ #clock-cells = <1>; }; - infracfg: syscon@10001000 { + infracfg: clock-controller@10001000 { compatible = "mediatek,mt2712-infracfg", "syscon"; reg = <0 0x10001000 0 0x1000>; #clock-cells = <1>; + #reset-cells = <1>; }; pericfg: syscon@10003000 { diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi index 3ee9266fa8e985..917fa39a74f8d7 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi @@ -252,7 +252,7 @@ clock-names = "hif_sel"; }; - cir: cir@10009000 { + cir: ir-receiver@10009000 { compatible = "mediatek,mt7622-cir"; reg = <0 0x10009000 0 0x1000>; interrupts = <GIC_SPI 175 IRQ_TYPE_LEVEL_LOW>; @@ -283,16 +283,14 @@ }; }; - apmixedsys: apmixedsys@10209000 { - compatible = "mediatek,mt7622-apmixedsys", - "syscon"; + apmixedsys: clock-controller@10209000 { + compatible = "mediatek,mt7622-apmixedsys"; reg = <0 0x10209000 0 0x1000>; #clock-cells = <1>; }; - topckgen: topckgen@10210000 { - compatible = "mediatek,mt7622-topckgen", - "syscon"; + topckgen: clock-controller@10210000 { + compatible = "mediatek,mt7622-topckgen"; reg = <0 0x10210000 0 0x1000>; #clock-cells = <1>; }; @@ -515,7 +513,6 @@ <&pericfg CLK_PERI_AUXADC_PD>; clock-names = "therm", "auxadc"; resets = <&pericfg MT7622_PERI_THERM_SW_RST>; - reset-names = "therm"; mediatek,auxadc = <&auxadc>; mediatek,apmixedsys = <&apmixedsys>; nvmem-cells = <&thermal_calibration>; @@ -734,9 +731,8 @@ power-domains = <&scpsys MT7622_POWER_DOMAIN_WB>; }; - ssusbsys: ssusbsys@1a000000 { - compatible = "mediatek,mt7622-ssusbsys", - "syscon"; + ssusbsys: clock-controller@1a000000 { + compatible = "mediatek,mt7622-ssusbsys"; reg = <0 0x1a000000 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -793,9 +789,8 @@ }; }; - pciesys: pciesys@1a100800 { - compatible = "mediatek,mt7622-pciesys", - "syscon"; + pciesys: clock-controller@1a100800 { + compatible = "mediatek,mt7622-pciesys"; reg = <0 0x1a100800 0 0x1000>; #clock-cells = <1>; #reset-cells = <1>; @@ -921,12 +916,13 @@ }; }; - hifsys: syscon@1af00000 { - compatible = "mediatek,mt7622-hifsys", "syscon"; + hifsys: clock-controller@1af00000 { + compatible = "mediatek,mt7622-hifsys"; reg = <0 0x1af00000 0 0x70>; + #clock-cells = <1>; }; - ethsys: syscon@1b000000 { + ethsys: clock-controller@1b000000 { compatible = "mediatek,mt7622-ethsys", "syscon"; reg = <0 0x1b000000 0 0x1000>; @@ -966,9 +962,7 @@ }; eth: ethernet@1b100000 { - compatible = "mediatek,mt7622-eth", - "mediatek,mt2701-eth", - "syscon"; + compatible = "mediatek,mt7622-eth"; reg = <0 0x1b100000 0 0x20000>; interrupts = <GIC_SPI 223 IRQ_TYPE_LEVEL_LOW>, <GIC_SPI 224 IRQ_TYPE_LEVEL_LOW>, diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts index e04b1c0c0ebbfb..ed79ad1ae8716e 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts +++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts @@ -146,19 +146,19 @@ &cpu_thermal { cooling-maps { - cpu-active-high { + map-cpu-active-high { /* active: set fan to cooling level 2 */ cooling-device = <&fan 2 2>; trip = <&cpu_trip_active_high>; }; - cpu-active-med { + map-cpu-active-med { /* active: set fan to cooling level 1 */ cooling-device = <&fan 1 1>; trip = <&cpu_trip_active_med>; }; - cpu-active-low { + map-cpu-active-low { /* active: set fan to cooling level 0 */ cooling-device = <&fan 0 0>; trip = <&cpu_trip_active_low>; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi index b3f416b9a7a4da..559990dcd1d179 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi @@ -332,9 +332,8 @@ reg = <0 0x1100c800 0 0x800>; interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>; clocks = <&infracfg CLK_INFRA_THERM_CK>, - <&infracfg CLK_INFRA_ADC_26M_CK>, - <&infracfg CLK_INFRA_ADC_FRC_CK>; - clock-names = "therm", "auxadc", "adc_32k"; + <&infracfg CLK_INFRA_ADC_26M_CK>; + clock-names = "therm", "auxadc"; nvmem-cells = <&thermal_calibration>; nvmem-cell-names = "calibration-data"; #thermal-sensor-cells = <1>; @@ -492,8 +491,6 @@ compatible = "mediatek,mt7986-ethsys", "syscon"; reg = <0 0x15000000 0 0x1000>; - #address-cells = <1>; - #size-cells = <1>; #clock-cells = <1>; #reset-cells = <1>; }; @@ -556,7 +553,6 @@ <&topckgen CLK_TOP_SGM_325M_SEL>; assigned-clock-parents = <&apmixedsys CLK_APMIXED_NET2PLL>, <&apmixedsys CLK_APMIXED_SGMPLL>; - #reset-cells = <1>; #address-cells = <1>; #size-cells = <0>; mediatek,ethsys = <ðsys>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index 6bd7424ef66c53..100191c6453ba3 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -433,7 +433,6 @@ }; &mt6358_vgpu_reg { - regulator-min-microvolt = <625000>; regulator-max-microvolt = <900000>; regulator-coupled-with = <&mt6358_vsram_gpu_reg>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index 93dfbf1302315d..774ae5d9143f1e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -1637,6 +1637,7 @@ compatible = "mediatek,mt8183-mfgcfg", "syscon"; reg = <0 0x13000000 0 0x1000>; #clock-cells = <1>; + power-domains = <&spm MT8183_POWER_DOMAIN_MFG_ASYNC>; }; gpu: gpu@13040000 { diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi index 3dea28f1d80612..1807e9d6cb0e41 100644 --- a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi @@ -1296,7 +1296,7 @@ * regulator coupling requirements. */ regulator-name = "ppvar_dvdd_vgpu"; - regulator-min-microvolt = <600000>; + regulator-min-microvolt = <500000>; regulator-max-microvolt = <950000>; regulator-ramp-delay = <6250>; regulator-enable-ramp-delay = <200>; diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi index 9b738f6a5d213a..7a704246678f03 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi @@ -1421,7 +1421,7 @@ mt6315_6_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; @@ -1431,7 +1431,7 @@ mt6315_6_vbuck3: vbuck3 { regulator-compatible = "vbuck3"; regulator-name = "Vlcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; @@ -1448,7 +1448,7 @@ mt6315_7_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; - regulator-min-microvolt = <606250>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <800000>; regulator-enable-ramp-delay = <256>; regulator-allowed-modes = <0 1 2>; diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi index 05e401670bced3..84cbdf6e9eb0ca 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi @@ -1464,6 +1464,7 @@ reg = <0 0x14001000 0 0x1000>; interrupts = <GIC_SPI 252 IRQ_TYPE_LEVEL_HIGH 0>; clocks = <&mmsys CLK_MM_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce SUBSYS_1400XXXX 0x1000 0x1000>; mediatek,gce-events = <CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_0>, <CMDQ_EVENT_DISP_STREAM_DONE_ENG_EVENT_1>; power-domains = <&spm MT8192_POWER_DOMAIN_DISP>; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi index f94c07f8b9334e..4a11918da37048 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi @@ -264,6 +264,38 @@ status = "okay"; }; +&cpu0 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu1 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu2 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu3 { + cpu-supply = <&mt6359_vcore_buck_reg>; +}; + +&cpu4 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu5 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu6 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + +&cpu7 { + cpu-supply = <&mt6315_6_vbuck1>; +}; + &dp_intf0 { status = "okay"; @@ -1214,7 +1246,7 @@ mt6315_6_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vbcpu"; - regulator-min-microvolt = <300000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-ramp-delay = <6250>; @@ -1232,7 +1264,7 @@ mt6315_7_vbuck1: vbuck1 { regulator-compatible = "vbuck1"; regulator-name = "Vgpu"; - regulator-min-microvolt = <625000>; + regulator-min-microvolt = <400000>; regulator-max-microvolt = <1193750>; regulator-enable-ramp-delay = <256>; regulator-ramp-delay = <6250>; diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index ea6dc220e1cce2..5d8b68f86ce446 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -2028,6 +2028,7 @@ compatible = "mediatek,mt8195-vppsys0", "syscon"; reg = <0 0x14000000 0 0x1000>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce1 SUBSYS_1400XXXX 0 0x1000>; }; dma-controller@14001000 { @@ -2251,6 +2252,7 @@ compatible = "mediatek,mt8195-vppsys1", "syscon"; reg = <0 0x14f00000 0 0x1000>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce1 SUBSYS_14f0XXXX 0 0x1000>; }; mutex@14f01000 { @@ -3080,6 +3082,7 @@ reg = <0 0x1c01a000 0 0x1000>; mboxes = <&gce0 0 CMDQ_THR_PRIO_4>; #clock-cells = <1>; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0xa000 0x1000>; }; @@ -3261,6 +3264,7 @@ interrupts = <GIC_SPI 658 IRQ_TYPE_LEVEL_HIGH 0>; power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS0>; clocks = <&vdosys0 CLK_VDO0_DISP_MUTEX0>; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c01XXXX 0x6000 0x1000>; mediatek,gce-events = <CMDQ_EVENT_VDO0_DISP_STREAM_DONE_0>; }; @@ -3331,6 +3335,7 @@ power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>; clocks = <&vdosys1 CLK_VDO1_DISP_MUTEX>; clock-names = "vdo1_mutex"; + mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0x1000 0x1000>; mediatek,gce-events = <CMDQ_EVENT_VDO1_STREAM_DONE_ENG_0>; }; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 7e7f0f0fb41ba0..41f51d32611107 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -3707,7 +3707,7 @@ compatible = "qcom,sc7280-adsp-pas"; reg = <0 0x03700000 0 0x100>; - interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&adsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, <&adsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>, <&adsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>, @@ -3944,7 +3944,7 @@ compatible = "qcom,sc7280-cdsp-pas"; reg = <0 0x0a300000 0 0x10000>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&cdsp_smp2p_in 0 IRQ_TYPE_EDGE_RISING>, <&cdsp_smp2p_in 1 IRQ_TYPE_EDGE_RISING>, <&cdsp_smp2p_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sc8180x.dtsi b/arch/arm64/boot/dts/qcom/sc8180x.dtsi index 32afc78d5b769d..053f7861c3cece 100644 --- a/arch/arm64/boot/dts/qcom/sc8180x.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8180x.dtsi @@ -2701,7 +2701,7 @@ resets = <&gcc GCC_USB30_SEC_BCR>; power-domains = <&gcc USB30_SEC_GDSC>; interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, - <&pdc 7 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 40 IRQ_TYPE_LEVEL_HIGH>, <&pdc 10 IRQ_TYPE_EDGE_BOTH>, <&pdc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index a5b194813079e9..d0f82e12289e1b 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -1774,6 +1774,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_4_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie4_phy>; phy-names = "pciephy"; @@ -1872,6 +1873,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_3B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie3b_phy>; phy-names = "pciephy"; @@ -1970,6 +1972,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_3A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie3a_phy>; phy-names = "pciephy"; @@ -2071,6 +2074,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_2B_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie2b_phy>; phy-names = "pciephy"; @@ -2169,6 +2173,7 @@ reset-names = "pci"; power-domains = <&gcc PCIE_2A_GDSC>; + required-opps = <&rpmhpd_opp_nom>; phys = <&pcie2a_phy>; phy-names = "pciephy"; @@ -2641,7 +2646,7 @@ compatible = "qcom,sc8280xp-adsp-pas"; reg = <0 0x03000000 0 0x100>; - interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 162 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, @@ -4977,7 +4982,7 @@ compatible = "qcom,sc8280xp-nsp0-pas"; reg = <0 0x1b300000 0 0x100>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp0_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp0_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp0_in 2 IRQ_TYPE_EDGE_RISING>, @@ -5108,7 +5113,7 @@ compatible = "qcom,sc8280xp-nsp1-pas"; reg = <0 0x21300000 0 0x100>; - interrupts-extended = <&intc GIC_SPI 887 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 887 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp1_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp1_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_nsp1_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index 24bcec3366efd5..0be053555602c0 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -1252,7 +1252,7 @@ compatible = "qcom,sm6350-adsp-pas"; reg = <0 0x03000000 0 0x100>; - interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, @@ -1511,7 +1511,7 @@ compatible = "qcom,sm6350-cdsp-pas"; reg = <0 0x08300000 0 0x10000>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm6375.dtsi b/arch/arm64/boot/dts/qcom/sm6375.dtsi index 4386f8a9c636c1..f40509d91bbda8 100644 --- a/arch/arm64/boot/dts/qcom/sm6375.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6375.dtsi @@ -1561,7 +1561,7 @@ compatible = "qcom,sm6375-adsp-pas"; reg = <0 0x0a400000 0 0x100>; - interrupts-extended = <&intc GIC_SPI 282 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 282 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index 39bd8f0eba1e65..7f2333c9d17d6d 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -3062,7 +3062,7 @@ compatible = "qcom,sm8250-slpi-pas"; reg = <0 0x05c00000 0 0x4000>; - interrupts-extended = <&pdc 9 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 9 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_slpi_in 2 IRQ_TYPE_EDGE_RISING>, @@ -3766,7 +3766,7 @@ compatible = "qcom,sm8250-cdsp-pas"; reg = <0 0x08300000 0 0x10000>; - interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp_in 2 IRQ_TYPE_EDGE_RISING>, @@ -5928,7 +5928,7 @@ compatible = "qcom,sm8250-adsp-pas"; reg = <0 0x17300000 0 0x100>; - interrupts-extended = <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index b86be34a912b94..024d2653cc3075 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -1777,12 +1777,8 @@ ranges = <0x01000000 0x0 0x00000000 0x0 0x60200000 0x0 0x100000>, <0x02000000 0x0 0x60300000 0x0 0x60300000 0x0 0x3d00000>; - /* - * MSIs for BDF (1:0.0) only works with Device ID 0x5980. - * Hence, the IDs are swapped. - */ - msi-map = <0x0 &gic_its 0x5981 0x1>, - <0x100 &gic_its 0x5980 0x1>; + msi-map = <0x0 &gic_its 0x5980 0x1>, + <0x100 &gic_its 0x5981 0x1>; msi-map-mask = <0xff00>; interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>, @@ -1900,12 +1896,8 @@ ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>, <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x1fd00000>; - /* - * MSIs for BDF (1:0.0) only works with Device ID 0x5a00. - * Hence, the IDs are swapped. - */ - msi-map = <0x0 &gic_its 0x5a01 0x1>, - <0x100 &gic_its 0x5a00 0x1>; + msi-map = <0x0 &gic_its 0x5a00 0x1>, + <0x100 &gic_its 0x5a01 0x1>; msi-map-mask = <0xff00>; interrupts = <GIC_SPI 307 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 308 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/qcom/sm8550.dtsi b/arch/arm64/boot/dts/qcom/sm8550.dtsi index 3904348075f679..3348bc06db488a 100644 --- a/arch/arm64/boot/dts/qcom/sm8550.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8550.dtsi @@ -1755,9 +1755,8 @@ <&gem_noc MASTER_APPSS_PROC 0 &cnoc_main SLAVE_PCIE_0 0>; interconnect-names = "pcie-mem", "cpu-pcie"; - /* Entries are reversed due to the unusual ITS DeviceID encoding */ - msi-map = <0x0 &gic_its 0x1401 0x1>, - <0x100 &gic_its 0x1400 0x1>; + msi-map = <0x0 &gic_its 0x1400 0x1>, + <0x100 &gic_its 0x1401 0x1>; iommu-map = <0x0 &apps_smmu 0x1400 0x1>, <0x100 &apps_smmu 0x1401 0x1>; @@ -1867,9 +1866,8 @@ <&gem_noc MASTER_APPSS_PROC 0 &cnoc_main SLAVE_PCIE_1 0>; interconnect-names = "pcie-mem", "cpu-pcie"; - /* Entries are reversed due to the unusual ITS DeviceID encoding */ - msi-map = <0x0 &gic_its 0x1481 0x1>, - <0x100 &gic_its 0x1480 0x1>; + msi-map = <0x0 &gic_its 0x1480 0x1>, + <0x100 &gic_its 0x1481 0x1>; iommu-map = <0x0 &apps_smmu 0x1480 0x1>, <0x100 &apps_smmu 0x1481 0x1>; diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index ba72d8f3842073..eb117866e59ff8 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -2274,9 +2274,8 @@ interrupt-map-mask = <0 0 0 0x7>; #interrupt-cells = <1>; - /* Entries are reversed due to the unusual ITS DeviceID encoding */ - msi-map = <0x0 &gic_its 0x1401 0x1>, - <0x100 &gic_its 0x1400 0x1>; + msi-map = <0x0 &gic_its 0x1400 0x1>, + <0x100 &gic_its 0x1401 0x1>; msi-map-mask = <0xff00>; linux,pci-domain = <0>; @@ -2402,9 +2401,8 @@ interrupt-map-mask = <0 0 0 0x7>; #interrupt-cells = <1>; - /* Entries are reversed due to the unusual ITS DeviceID encoding */ - msi-map = <0x0 &gic_its 0x1481 0x1>, - <0x100 &gic_its 0x1480 0x1>; + msi-map = <0x0 &gic_its 0x1480 0x1>, + <0x100 &gic_its 0x1481 0x1>; msi-map-mask = <0xff00>; linux,pci-domain = <1>; diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index 8e517f76189e19..6b40082bac68ce 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -284,7 +284,7 @@ domain-idle-states { CLUSTER_CL4: cluster-sleep-0 { - compatible = "arm,idle-state"; + compatible = "domain-idle-state"; idle-state-name = "l2-ret"; arm,psci-suspend-param = <0x01000044>; entry-latency-us = <350>; @@ -293,7 +293,7 @@ }; CLUSTER_CL5: cluster-sleep-1 { - compatible = "arm,idle-state"; + compatible = "domain-idle-state"; idle-state-name = "ret-pll-off"; arm,psci-suspend-param = <0x01000054>; entry-latency-us = <2200>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi index 5846a11f0e848f..d5e035823eb5e4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi @@ -663,7 +663,7 @@ camera: &i2c7 { port@1 { reg = <1>; - mipi1_in_panel: endpoint@1 { + mipi1_in_panel: endpoint { remote-endpoint = <&mipi1_out_panel>; }; }; @@ -689,7 +689,6 @@ camera: &i2c7 { ep-gpios = <&gpio0 3 GPIO_ACTIVE_HIGH>; /* PERST# asserted in S3 */ - pcie-reset-suspend = <1>; vpcie3v3-supply = <&wlan_3v3>; vpcie1v8-supply = <&pp1800_pcie>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts index dfb2a0bdea5b73..9586bb12a5d8f5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts @@ -611,7 +611,7 @@ #size-cells = <0>; interface@0 { /* interface 0 of configuration 1 */ - compatible = "usbbda,8156.config1.0"; + compatible = "usbifbda,8156.config1.0"; reg = <0 1>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 054c6a4d1a45f7..294eb2de263deb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -779,7 +779,6 @@ }; &pcie0 { - bus-scan-delay-ms = <1000>; ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts index 2c3984a880af64..f6f15946579ebf 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts @@ -194,6 +194,8 @@ num-lanes = <4>; pinctrl-names = "default"; pinctrl-0 = <&pcie_clkreqn_cpm>; + vpcie3v3-supply = <&vcc3v3_baseboard>; + vpcie12v-supply = <&dc_12v>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index c08e69391c0154..ccbe3a7a1d2c2f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -79,6 +79,26 @@ regulator-max-microvolt = <5000000>; }; + vcca_0v9: vcca-0v9-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcca_0v9"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + vin-supply = <&vcc_1v8>; + }; + + vcca_1v8: vcca-1v8-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcca_1v8"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + vin-supply = <&vcc3v3_sys>; + }; + vdd_log: vdd-log { compatible = "pwm-regulator"; pwms = <&pwm2 0 25000 1>; @@ -416,16 +436,28 @@ gpio1830-supply = <&vcc_1v8>; }; -&pmu_io_domains { - status = "okay"; - pmu1830-supply = <&vcc_1v8>; +&pcie0 { + /* PCIe PHY supplies */ + vpcie0v9-supply = <&vcca_0v9>; + vpcie1v8-supply = <&vcca_1v8>; }; -&pwm2 { - status = "okay"; +&pcie_clkreqn_cpm { + rockchip,pins = + <2 RK_PD2 RK_FUNC_GPIO &pcfg_pull_up>; }; &pinctrl { + pinctrl-names = "default"; + pinctrl-0 = <&q7_thermal_pin>; + + gpios { + q7_thermal_pin: q7-thermal-pin { + rockchip,pins = + <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + i2c8 { i2c8_xfer_a: i2c8-xfer { rockchip,pins = @@ -458,11 +490,20 @@ usb3 { usb3_id: usb3-id { rockchip,pins = - <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; + <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_up>; }; }; }; +&pmu_io_domains { + status = "okay"; + pmu1830-supply = <&vcc_1v8>; +}; + +&pwm2 { + status = "okay"; +}; + &sdhci { /* * Signal integrity isn't great at 200MHz but 100MHz has proven stable diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts index 6ecdf5d283390a..c1194d1e438d0d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts @@ -447,7 +447,6 @@ &pcie2x1 { reset-gpios = <&gpio0 RK_PB6 GPIO_ACTIVE_HIGH>; - disable-gpios = <&gpio0 RK_PA6 GPIO_ACTIVE_HIGH>; vpcie3v3-supply = <&vcc3v3_pcie>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index 7b5f3904ef6104..c87fad2c34cba3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -416,6 +416,8 @@ vccio_sd: LDO_REG5 { regulator-name = "vccio_sd"; + regulator-always-on; + regulator-boot-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; @@ -525,9 +527,9 @@ #address-cells = <1>; #size-cells = <0>; - switch@0 { + switch@1f { compatible = "mediatek,mt7531"; - reg = <0>; + reg = <0x1f>; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts b/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts index a8a4cc190eb32e..a3112d5df2008d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts @@ -523,7 +523,6 @@ &pcie2x1 { reset-gpios = <&gpio3 RK_PC1 GPIO_ACTIVE_HIGH>; - disable-gpios = <&gpio3 RK_PC2 GPIO_ACTIVE_HIGH>; vpcie3v3-supply = <&vcc3v3_mini_pcie>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi index cce1c8e835877c..94ecb9b4f98f88 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi @@ -216,9 +216,9 @@ pinctrl-0 = <&i2c7m0_xfer>; status = "okay"; - es8316: audio-codec@11 { + es8316: audio-codec@10 { compatible = "everest,es8316"; - reg = <0x11>; + reg = <0x10>; assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; assigned-clock-rates = <12288000>; clocks = <&cru I2S0_8CH_MCLKOUT>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts index 1b606ea5b6cf2b..1a604429fb266e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts @@ -485,6 +485,7 @@ pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, <&rk806_dvs2_null>, <&rk806_dvs3_null>; spi-max-frequency = <1000000>; + system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; @@ -506,7 +507,7 @@ #gpio-cells = <2>; rk806_dvs1_null: dvs1-null-pins { - pins = "gpio_pwrctrl2"; + pins = "gpio_pwrctrl1"; function = "pin_fun0"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts index 67414d72e2b6ef..22bbfbe729c11b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts @@ -456,6 +456,7 @@ <&rk806_dvs2_null>, <&rk806_dvs3_null>; pinctrl-names = "default"; spi-max-frequency = <1000000>; + system-power-controller; vcc1-supply = <&vcc4v0_sys>; vcc2-supply = <&vcc4v0_sys>; diff --git a/arch/arm64/include/asm/fpu.h b/arch/arm64/include/asm/fpu.h new file mode 100644 index 00000000000000..2ae50bdce59b43 --- /dev/null +++ b/arch/arm64/include/asm/fpu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef __ASM_FPU_H +#define __ASM_FPU_H + +#include <asm/neon.h> + +#define kernel_fpu_available() cpu_has_neon() +#define kernel_fpu_begin() kernel_neon_begin() +#define kernel_fpu_end() kernel_neon_end() + +#endif /* ! __ASM_FPU_H */ diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 2ddc33d93b13b2..3954cbd2ff56bc 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -18,11 +18,11 @@ extern bool arch_hugetlb_migration_supported(struct hstate *h); #endif -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index afdd56d26ad700..1303d30287dce0 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -49,12 +49,6 @@ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline bool arch_thp_swp_supported(void) -{ - return !system_supports_mte(); -} -#define arch_thp_swp_supported arch_thp_swp_supported - /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page @@ -517,8 +511,6 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd) return pmd; } -#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) - #define pmd_write(pmd) pte_write(pmd_pte(pmd)) #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) @@ -709,7 +701,11 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) +#ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) +#else +#define pud_leaf(pud) false +#endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) @@ -1227,6 +1223,46 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, __ptep_set_wrprotect(mm, address, ptep); } +static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, cydp_t flags) +{ + pte_t old_pte; + + do { + old_pte = pte; + + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + + pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), + pte_val(old_pte), pte_val(pte)); + } while (pte_val(pte) != pte_val(old_pte)); +} + +static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + pte = __ptep_get(ptep); + + if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) + __set_pte(ptep, pte_mkclean(pte_mkold(pte))); + else + __clear_young_dirty_pte(vma, addr, ptep, pte, flags); + + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, @@ -1280,12 +1316,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) -{ - if (system_supports_mte()) - return mte_save_tags(page); - return 0; -} +extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) @@ -1301,11 +1332,7 @@ static inline void arch_swap_invalidate_area(int type) } #define __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) -{ - if (system_supports_mte()) - mte_restore_tags(entry, &folio->page); -} +extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ @@ -1392,6 +1419,9 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); +extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) @@ -1616,6 +1646,17 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } +#define clear_young_dirty_ptes clear_young_dirty_ptes +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) + __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); + else + contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); +} + #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get @@ -1635,6 +1676,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags +#define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 491b2b9bd5536f..1346579f802f7f 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -39,7 +39,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 462 +#define __NR_compat_syscalls 463 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 7118282d1c7976..266b96acc01439 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -929,6 +929,8 @@ __SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr) __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) #define __NR_lsm_list_modules 461 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) +#define __NR_mseal 462 +__SYSCALL(__NR_mseal, sys_mseal) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 9afcc690fe73c2..4a92096db34e0b 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -10,6 +10,7 @@ #include <linux/efi.h> #include <linux/init.h> #include <linux/screen_info.h> +#include <linux/vmalloc.h> #include <asm/efi.h> #include <asm/stacktrace.h> diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 29490be2546bfc..13e6a2829116ca 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -7,10 +7,8 @@ lib-y := clear_user.o delay.o copy_from_user.o \ ifeq ($(CONFIG_KERNEL_MODE_NEON), y) obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o -CFLAGS_REMOVE_xor-neon.o += -mgeneral-regs-only -CFLAGS_xor-neon.o += -ffreestanding -# Enable <arm_neon.h> -CFLAGS_xor-neon.o += -isystem $(shell $(CC) -print-file-name=include) +CFLAGS_xor-neon.o += $(CC_FLAGS_FPU) +CFLAGS_REMOVE_xor-neon.o += $(CC_FLAGS_NO_FPU) endif lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 1b64b4c3f8bf8a..9f9486de0004dd 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -361,6 +361,35 @@ void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes); +void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + /* + * We can safely clear access/dirty without needing to unfold from + * the architectures perspective, even when contpte is set. If the + * range starts or ends midway through a contpte block, we can just + * expand to include the full contpte block. While this is not + * exactly what the core-mm asked for, it tracks access/dirty per + * folio, not per page. And since we only create a contpte block + * when it is covered by a single folio, we can get away with + * clearing access/dirty for the whole block. + */ + unsigned long start = addr; + unsigned long end = start + nr; + + if (pte_cont(__ptep_get(ptep + nr - 1))) + end = ALIGN(end, CONT_PTE_SIZE); + + if (pte_cont(__ptep_get(ptep))) { + start = ALIGN_DOWN(start, CONT_PTE_SIZE); + ptep = contpte_align_down(ptep); + } + + __clear_young_dirty_ptes(vma, start, ptep, end - start, flags); +} +EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); + int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 8251e2fea9c757..451ba7cbd5adb0 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -486,25 +486,6 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) -#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) - -static vm_fault_t __do_page_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long addr, - unsigned int mm_flags, unsigned long vm_flags, - struct pt_regs *regs) -{ - /* - * Ok, we have a good vm_area for this memory access, so we can handle - * it. - * Check that the permissions on the VMA allow for the fault which - * occurred. - */ - if (!(vma->vm_flags & vm_flags)) - return VM_FAULT_BADACCESS; - return handle_mm_fault(vma, addr, mm_flags, regs); -} - static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; @@ -529,6 +510,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; + int si_code; if (kprobe_page_fault(regs, esr)) return 0; @@ -588,7 +570,10 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); - goto lock_mmap; + fault = 0; + si_code = SEGV_ACCERR; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) @@ -613,12 +598,19 @@ lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { - fault = VM_FAULT_BADMAP; - goto done; + fault = 0; + si_code = SEGV_MAPERR; + goto bad_area; } - fault = __do_page_fault(mm, vma, addr, mm_flags, vm_flags, regs); + if (!(vma->vm_flags & vm_flags)) { + mmap_read_unlock(mm); + fault = 0; + si_code = SEGV_ACCERR; + goto bad_area; + } + fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) @@ -637,13 +629,12 @@ retry: mmap_read_unlock(mm); done: - /* - * Handle the "normal" (no error) case first. - */ - if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | - VM_FAULT_BADACCESS)))) + /* Handle the "normal" (no error) case first. */ + if (likely(!(fault & VM_FAULT_ERROR))) return 0; + si_code = SEGV_MAPERR; +bad_area: /* * If we are in kernel mode at this point, we have no context to * handle this fault with. @@ -678,13 +669,8 @@ done: arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { - /* - * Something tried to access memory that isn't in our memory - * map. - */ - arm64_force_sig_fault(SIGSEGV, - fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR, - far, inf->name); + /* Something tried to access memory that out of memory map */ + arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index b872b003a55f3d..3f09ac73cce3b2 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -79,20 +79,6 @@ bool arch_hugetlb_migration_supported(struct hstate *h) } #endif -int pmd_huge(pmd_t pmd) -{ - return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); -} - -int pud_huge(pud_t pud) -{ -#ifndef __PAGETABLE_PMD_FOLDED - return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT); -#else - return 0; -#endif -} - static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { @@ -328,7 +314,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ - if (pud_huge(pud) || !pud_present(pud)) + if (pud_leaf(pud) || !pud_present(pud)) return (pte_t *)pudp; /* table; check the next level */ @@ -340,7 +326,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && pmd_none(pmd)) return NULL; - if (pmd_huge(pmd) || !pmd_present(pmd)) + if (pmd_leaf(pmd) || !pmd_present(pmd)) return (pte_t *)pmdp; if (sz == CONT_PTE_SIZE) diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index a31833e3ddc544..63e8d72f202a3b 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -68,6 +68,13 @@ void mte_invalidate_tags(int type, pgoff_t offset) mte_free_tag_storage(tags); } +static inline void __mte_invalidate_tags(struct page *page) +{ + swp_entry_t entry = page_swap_entry(page); + + mte_invalidate_tags(swp_type(entry), swp_offset(entry)); +} + void mte_invalidate_tags_area(int type) { swp_entry_t entry = swp_entry(type, 0); @@ -83,3 +90,41 @@ void mte_invalidate_tags_area(int type) } xa_unlock(&mte_pages); } + +int arch_prepare_to_swap(struct folio *folio) +{ + long i, nr; + int err; + + if (!system_supports_mte()) + return 0; + + nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) { + err = mte_save_tags(folio_page(folio, i)); + if (err) + goto out; + } + return 0; + +out: + while (i--) + __mte_invalidate_tags(folio_page(folio, i)); + return err; +} + +void arch_swap_restore(swp_entry_t entry, struct folio *folio) +{ + long i, nr; + + if (!system_supports_mte()) + return; + + nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) { + mte_restore_tags(entry, folio_page(folio, i)); + entry.val++; + } +} diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 122021f9bdfc87..13eac43c632dfe 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1844,15 +1844,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, emit_call(enter_prog, ctx); + /* save return value to callee saved register x20 */ + emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ branch = ctx->image + ctx->idx; emit(A64_NOP, ctx); - /* save return value to callee saved register x20 */ - emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); - emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx); if (!p->jited) emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx); diff --git a/arch/csky/abiv1/mmap.c b/arch/csky/abiv1/mmap.c index 6792aca4999917..7f826331d409b2 100644 --- a/arch/csky/abiv1/mmap.c +++ b/arch/csky/abiv1/mmap.c @@ -28,7 +28,12 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int do_align = 0; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = { + .length = len, + .low_limit = mm->mmap_base, + .high_limit = TASK_SIZE, + .align_offset = pgoff << PAGE_SHIFT + }; /* * We only need to do colour alignment if either the I or D @@ -61,11 +66,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; - info.length = len; - info.low_limit = mm->mmap_base; - info.high_limit = TASK_SIZE; info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0; - info.align_offset = pgoff << PAGE_SHIFT; return vm_unmapped_area(&info); } diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index a5f300ec6f2808..13077142ae8251 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -18,6 +18,7 @@ config LOONGARCH select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_KCOV + select ARCH_HAS_KERNEL_FPU_SUPPORT if CPU_HAS_FPU select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL @@ -119,7 +120,7 @@ config LOONGARCH select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN select HAVE_EXIT_THREAD - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION @@ -595,7 +596,7 @@ config ARCH_SELECTS_CRASH_DUMP select RELOCATABLE config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION - def_bool CRASH_CORE + def_bool CRASH_RESERVE config RELOCATABLE bool "Relocatable kernel" diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index df6caf79537a9d..efb5440a43ec4c 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -26,6 +26,9 @@ endif 32bit-emul = elf32loongarch 64bit-emul = elf64loongarch +CC_FLAGS_FPU := -mfpu=64 +CC_FLAGS_NO_FPU := -msoft-float + ifdef CONFIG_UNWINDER_ORC orc_hash_h := arch/$(SRCARCH)/include/generated/asm/orc_hash.h orc_hash_sh := $(srctree)/scripts/orc_hash.sh @@ -59,7 +62,7 @@ ld-emul = $(64bit-emul) cflags-y += -mabi=lp64s endif -cflags-y += -pipe -msoft-float +cflags-y += -pipe $(CC_FLAGS_NO_FPU) LDFLAGS_vmlinux += -static -n -nostdlib # When the assembler supports explicit relocation hint, we must use it. diff --git a/arch/loongarch/include/asm/crash_core.h b/arch/loongarch/include/asm/crash_reserve.h index 218bdbfa527ba8..a1d9b84b1c7d51 100644 --- a/arch/loongarch/include/asm/crash_core.h +++ b/arch/loongarch/include/asm/crash_reserve.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef _LOONGARCH_CRASH_CORE_H -#define _LOONGARCH_CRASH_CORE_H +#ifndef _LOONGARCH_CRASH_RESERVE_H +#define _LOONGARCH_CRASH_RESERVE_H #define CRASH_ALIGN SZ_2M diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h index c2d8962fda00be..3177674228f896 100644 --- a/arch/loongarch/include/asm/fpu.h +++ b/arch/loongarch/include/asm/fpu.h @@ -21,6 +21,7 @@ struct sigcontext; +#define kernel_fpu_available() cpu_has_fpu extern void kernel_fpu_begin(void); extern void kernel_fpu_end(void); diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h index a6a5760da3a332..92636e82957c7e 100644 --- a/arch/loongarch/include/asm/kfence.h +++ b/arch/loongarch/include/asm/kfence.h @@ -10,6 +10,7 @@ #define _ASM_LOONGARCH_KFENCE_H #include <linux/kfence.h> +#include <linux/vmalloc.h> #include <asm/pgtable.h> #include <asm/tlb.h> diff --git a/arch/loongarch/include/asm/perf_event.h b/arch/loongarch/include/asm/perf_event.h index 2a35a0bc2aaabf..52b638059e40b3 100644 --- a/arch/loongarch/include/asm/perf_event.h +++ b/arch/loongarch/include/asm/perf_event.h @@ -7,6 +7,14 @@ #ifndef __LOONGARCH_PERF_EVENT_H__ #define __LOONGARCH_PERF_EVENT_H__ +#include <asm/ptrace.h> + #define perf_arch_bpf_user_pt_regs(regs) (struct user_pt_regs *)regs +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->csr_era = (__ip); \ + (regs)->regs[3] = current_stack_pointer; \ + (regs)->regs[22] = (unsigned long) __builtin_frame_address(0); \ +} + #endif /* __LOONGARCH_PERF_EVENT_H__ */ diff --git a/arch/loongarch/include/asm/tlb.h b/arch/loongarch/include/asm/tlb.h index da7a3b5b9374ae..e071f5e9e85802 100644 --- a/arch/loongarch/include/asm/tlb.h +++ b/arch/loongarch/include/asm/tlb.h @@ -132,8 +132,6 @@ static __always_inline void invtlb_all(u32 op, u32 info, u64 addr) ); } -#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) - static void tlb_flush(struct mmu_gather *tlb); #define tlb_flush tlb_flush diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 0491bf453cd496..cac7cba81b65f7 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -884,4 +884,4 @@ static int __init init_hw_perf_events(void) return 0; } -early_initcall(init_hw_perf_events); +pure_initcall(init_hw_perf_events); diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index 1fc2f6813ea027..97b40defde0608 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -202,10 +202,10 @@ good_area: if (!(vma->vm_flags & VM_WRITE)) goto bad_area; } else { - if (!(vma->vm_flags & VM_READ) && address != exception_era(regs)) - goto bad_area; if (!(vma->vm_flags & VM_EXEC) && address == exception_era(regs)) goto bad_area; + if (!(vma->vm_flags & (VM_READ | VM_WRITE)) && address != exception_era(regs)) + goto bad_area; } /* diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c index 1e76fcb83093dd..12222c56cb5948 100644 --- a/arch/loongarch/mm/hugetlbpage.c +++ b/arch/loongarch/mm/hugetlbpage.c @@ -50,21 +50,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, return (pte_t *) pmd; } -int pmd_huge(pmd_t pmd) -{ - return (pmd_val(pmd) & _PAGE_HUGE) != 0; -} - -int pud_huge(pud_t pud) -{ - return (pud_val(pud) & _PAGE_HUGE) != 0; -} - uint64_t pmd_to_entrylo(unsigned long pmd_val) { uint64_t val; /* PMD as PTE. Must be huge page */ - if (!pmd_huge(__pmd(pmd_val))) + if (!pmd_leaf(__pmd(pmd_val))) panic("%s", __func__); val = pmd_val ^ _PAGE_HUGE; diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c index 89af7c12e8c08d..8890309851351c 100644 --- a/arch/loongarch/mm/mmap.c +++ b/arch/loongarch/mm/mmap.c @@ -25,7 +25,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, struct vm_area_struct *vma; unsigned long addr = addr0; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (unlikely(len > TASK_SIZE)) return -ENOMEM; @@ -83,7 +83,6 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, */ } - info.flags = 0; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; return vm_unmapped_area(&info); diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 7fd43fd4c9f2e2..22a3cbd4c60298 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -461,3 +461,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index b00ab2cabab92a..2b81a6bd78b292 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -467,3 +467,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 516dc7022bd74a..f1aa1bf11166bc 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -68,7 +68,7 @@ config MIPS select HAVE_DYNAMIC_FTRACE select HAVE_EBPF_JIT if !CPU_MICROMIPS select HAVE_EXIT_THREAD - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index 0e196650f4f488..92b7591aac2acd 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -129,7 +129,7 @@ static inline int pmd_none(pmd_t pmd) static inline int pmd_bad(pmd_t pmd) { #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT - /* pmd_huge(pmd) but inline */ + /* pmd_leaf(pmd) but inline */ if (unlikely(pmd_val(pmd) & _PAGE_HUGE)) return 0; #endif diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 20ca48c1b6063e..7c28510b3768f0 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -245,7 +245,7 @@ static inline int pmd_none(pmd_t pmd) static inline int pmd_bad(pmd_t pmd) { #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT - /* pmd_huge(pmd) but inline */ + /* pmd_leaf(pmd) but inline */ if (unlikely(pmd_val(pmd) & _PAGE_HUGE)) return 0; #endif diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c index eabddb89d221fe..c97b089b99029d 100644 --- a/arch/mips/jazz/jazzdma.c +++ b/arch/mips/jazz/jazzdma.c @@ -617,7 +617,7 @@ const struct dma_map_ops jazz_dma_ops = { .sync_sg_for_device = jazz_dma_sync_sg_for_device, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; EXPORT_SYMBOL(jazz_dma_ops); diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 83cfc9eb6b88e6..cc869f5d569318 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -400,3 +400,4 @@ 459 n32 lsm_get_self_attr sys_lsm_get_self_attr 460 n32 lsm_set_self_attr sys_lsm_set_self_attr 461 n32 lsm_list_modules sys_lsm_list_modules +462 n32 mseal sys_mseal diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 532b855df58957..1464c6be6eb3c7 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -376,3 +376,4 @@ 459 n64 lsm_get_self_attr sys_lsm_get_self_attr 460 n64 lsm_set_self_attr sys_lsm_set_self_attr 461 n64 lsm_list_modules sys_lsm_list_modules +462 n64 mseal sys_mseal diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index f45c9530ea93a1..008ebe60263e37 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -449,3 +449,4 @@ 459 o32 lsm_get_self_attr sys_lsm_get_self_attr 460 o32 lsm_set_self_attr sys_lsm_set_self_attr 461 o32 lsm_list_modules sys_lsm_list_modules +462 o32 mseal sys_mseal diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c index 7eaff5b078739b..0b9e15555b59bb 100644 --- a/arch/mips/mm/hugetlbpage.c +++ b/arch/mips/mm/hugetlbpage.c @@ -57,13 +57,3 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, } return (pte_t *) pmd; } - -int pmd_huge(pmd_t pmd) -{ - return (pmd_val(pmd) & _PAGE_HUGE) != 0; -} - -int pud_huge(pud_t pud) -{ - return (pud_val(pud) & _PAGE_HUGE) != 0; -} diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 00fe90c6db3e80..7e11d7b5876107 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -34,7 +34,7 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, struct vm_area_struct *vma; unsigned long addr = addr0; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (unlikely(len > TASK_SIZE)) return -ENOMEM; @@ -92,7 +92,6 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, */ } - info.flags = 0; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; return vm_unmapped_area(&info); diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 4106084e57d728..76f3b9c0a9f0ce 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -326,7 +326,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte) idx = read_c0_index(); #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT /* this could be a huge page */ - if (pmd_huge(*pmdp)) { + if (pmd_leaf(*pmdp)) { unsigned long lo; write_c0_pagemask(PM_HUGE_MASK); ptep = (pte_t *)pmdp; diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 98af719d5f85b2..f7722451276ef4 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -104,7 +104,9 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, struct vm_area_struct *vma, *prev; unsigned long filp_pgoff; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = { + .length = len + }; if (unlikely(len > TASK_SIZE)) return -ENOMEM; @@ -139,7 +141,6 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, return addr; } - info.length = len; info.align_mask = do_color_align ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; info.align_offset = shared_align_offset(filp_pgoff, pgoff); @@ -160,7 +161,6 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp, */ } - info.flags = 0; info.low_limit = mm->mmap_base; info.high_limit = mmap_upper_limit(NULL); return vm_unmapped_area(&info); diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index b236a84c4e127e..b13c21373974c8 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -460,3 +460,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index a9f7e21f66567a..0356199bd9e7e7 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -180,14 +180,3 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, } return changed; } - - -int pmd_huge(pmd_t pmd) -{ - return 0; -} - -int pud_huge(pud_t pud) -{ - return 0; -} diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1c4be337368604..45addf6848ad15 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -137,6 +137,7 @@ config PPC select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_HUGEPD if HUGETLB_PAGE select ARCH_HAS_KCOV + select ARCH_HAS_KERNEL_FPU_SUPPORT if PPC_FPU select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_MEMREMAP_COMPAT_ALIGN if PPC_64S_HASH_MMU @@ -236,7 +237,7 @@ config PPC select HAVE_DYNAMIC_FTRACE_WITH_REGS if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32 select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_DESCRIPTORS if PPC64_ELF_ABI_V1 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 65261cbe5bfdbf..93d89f055b70b7 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -153,6 +153,9 @@ CFLAGS-$(CONFIG_PPC32) += $(call cc-option, $(MULTIPLEWORD)) CFLAGS-$(CONFIG_PPC32) += $(call cc-option,-mno-readonly-in-sdata) +CC_FLAGS_FPU := $(call cc-option,-mhard-float) +CC_FLAGS_NO_FPU := $(call cc-option,-msoft-float) + ifdef CONFIG_FUNCTION_TRACER ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY @@ -174,7 +177,7 @@ asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1) KBUILD_CPPFLAGS += -I $(srctree)/arch/powerpc $(asinstr) KBUILD_AFLAGS += $(AFLAGS-y) -KBUILD_CFLAGS += $(call cc-option,-msoft-float) +KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU) KBUILD_CFLAGS += $(CFLAGS-y) CPP = $(CC) -E $(KBUILD_CFLAGS) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h index 48f21820afe209..baf934578c3a5e 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h @@ -6,26 +6,6 @@ */ #ifndef __ASSEMBLY__ #ifdef CONFIG_HUGETLB_PAGE -static inline int pmd_huge(pmd_t pmd) -{ - /* - * leaf pte for huge page - */ - if (radix_enabled()) - return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); - return 0; -} - -static inline int pud_huge(pud_t pud) -{ - /* - * leaf pte for huge page - */ - if (radix_enabled()) - return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); - return 0; -} - /* * With radix , we have hugepage ptes in the pud and pmd entries. We don't * need to setup hugepage directory for them. Our pte and page directory format diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h index ced7ee8b42fc35..6ac73da7b80e3c 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h @@ -4,31 +4,6 @@ #ifndef __ASSEMBLY__ #ifdef CONFIG_HUGETLB_PAGE -/* - * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have - * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD; - * - * Defined in such a way that we can optimize away code block at build time - * if CONFIG_HUGETLB_PAGE=n. - * - * returns true for pmd migration entries, THP, devmap, hugetlb - * But compile time dependent on CONFIG_HUGETLB_PAGE - */ -static inline int pmd_huge(pmd_t pmd) -{ - /* - * leaf pte for huge page - */ - return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); -} - -static inline int pud_huge(pud_t pud) -{ - /* - * leaf pte for huge page - */ - return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); -} /* * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index fac5615e6bc575..8f9432e3855ae5 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -262,6 +262,18 @@ extern unsigned long __kernel_io_end; extern struct page *vmemmap; extern unsigned long pci_io_base; + +#define pmd_leaf pmd_leaf +static inline bool pmd_leaf(pmd_t pmd) +{ + return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); +} + +#define pud_leaf pud_leaf +static inline bool pud_leaf(pud_t pud) +{ + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); +} #endif /* __ASSEMBLY__ */ #include <asm/book3s/64/hash.h> @@ -1426,20 +1438,5 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va return false; } -/* - * Like pmd_huge(), but works regardless of config options - */ -#define pmd_leaf pmd_leaf -static inline bool pmd_leaf(pmd_t pmd) -{ - return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE)); -} - -#define pud_leaf pud_leaf -static inline bool pud_leaf(pud_t pud) -{ - return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE)); -} - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */ diff --git a/arch/powerpc/include/asm/fpu.h b/arch/powerpc/include/asm/fpu.h new file mode 100644 index 00000000000000..ca584e4bc40f84 --- /dev/null +++ b/arch/powerpc/include/asm/fpu.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef _ASM_POWERPC_FPU_H +#define _ASM_POWERPC_FPU_H + +#include <linux/preempt.h> + +#include <asm/cpu_has_feature.h> +#include <asm/switch_to.h> + +#define kernel_fpu_available() (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) + +static inline void kernel_fpu_begin(void) +{ + preempt_disable(); + enable_kernel_fp(); +} + +static inline void kernel_fpu_end(void) +{ + disable_kernel_fp(); + preempt_enable(); +} + +#endif /* ! _ASM_POWERPC_FPU_H */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 3b72c7ed24cfde..aa5c0fd5edb1c9 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -406,9 +406,5 @@ extern void *abatron_pteptrs[2]; #include <asm/nohash/mmu.h> #endif -#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) -#define __HAVE_ARCH_RESERVED_KERNEL_PAGES -#endif - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 427db14292c9ec..f5f39d4f03c821 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -351,16 +351,6 @@ static inline int hugepd_ok(hugepd_t hpd) #endif } -static inline int pmd_huge(pmd_t pmd) -{ - return 0; -} - -static inline int pud_huge(pud_t pud) -{ - return 0; -} - #define is_hugepd(hpd) (hugepd_ok(hpd)) #endif diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 8920862ffd7916..f0ae39e77e3741 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -216,6 +216,6 @@ const struct dma_map_ops dma_iommu_ops = { .get_required_mask = dma_iommu_get_required_mask, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index d14eda1e858968..ae8c7619e597d9 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1735,8 +1735,3 @@ static void __init fadump_reserve_crash_area(u64 base) memblock_reserve(mstart, msize); } } - -unsigned long __init arch_reserved_kernel_pages(void) -{ - return memblock_reserved_size() / PAGE_SIZE; -} diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 29a8c8e185851b..b70b4f93561fcc 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -26,6 +26,7 @@ #include <linux/iommu.h> #include <linux/sched.h> #include <linux/debugfs.h> +#include <linux/vmalloc.h> #include <asm/io.h> #include <asm/iommu.h> #include <asm/pci-bridge.h> diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 17173b82ca21dc..3656f1ca7a21c6 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -548,3 +548,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c index c0b58afb9a4762..ef3ce37f1bb3ec 100644 --- a/arch/powerpc/mm/book3s64/slice.c +++ b/arch/powerpc/mm/book3s64/slice.c @@ -282,12 +282,10 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm, { int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); unsigned long found, next_end; - struct vm_unmapped_area_info info; - - info.flags = 0; - info.length = len; - info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); - info.align_offset = 0; + struct vm_unmapped_area_info info = { + .length = len, + .align_mask = PAGE_MASK & ((1ul << pshift) - 1), + }; /* * Check till the allow max value for this mmap request */ @@ -326,13 +324,13 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm, { int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT); unsigned long found, prev; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = { + .flags = VM_UNMAPPED_AREA_TOPDOWN, + .length = len, + .align_mask = PAGE_MASK & ((1ul << pshift) - 1), + }; unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr); - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.align_mask = PAGE_MASK & ((1ul << pshift) - 1); - info.align_offset = 0; /* * If we are trying to allocate above DEFAULT_MAP_WINDOW * Add the different to the mmap_base. diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 53335ae21a40ae..21569045249594 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -71,23 +71,26 @@ static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long add return __bad_area_nosemaphore(regs, address, SEGV_MAPERR); } -static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code) +static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code, + struct mm_struct *mm, struct vm_area_struct *vma) { - struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); return __bad_area_nosemaphore(regs, address, si_code); } static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, + struct mm_struct *mm, struct vm_area_struct *vma) { - struct mm_struct *mm = current->mm; int pkey; /* @@ -109,7 +112,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, */ pkey = vma_pkey(vma); - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); /* * If we are in kernel mode, bail out with a SEGV, this will @@ -124,9 +130,10 @@ static noinline int bad_access_pkey(struct pt_regs *regs, unsigned long address, return 0; } -static noinline int bad_access(struct pt_regs *regs, unsigned long address) +static noinline int bad_access(struct pt_regs *regs, unsigned long address, + struct mm_struct *mm, struct vm_area_struct *vma) { - return __bad_area(regs, address, SEGV_ACCERR); + return __bad_area(regs, address, SEGV_ACCERR, mm, vma); } static int do_sigbus(struct pt_regs *regs, unsigned long address, @@ -479,13 +486,13 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(access_pkey_error(is_write, is_exec, (error_code & DSISR_KEYFAULT), vma))) { - vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return bad_access_pkey(regs, address, NULL, vma); } if (unlikely(access_error(is_write, is_exec, vma))) { - vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return bad_access(regs, address, NULL, vma); } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); @@ -521,10 +528,10 @@ retry: if (unlikely(access_pkey_error(is_write, is_exec, (error_code & DSISR_KEYFAULT), vma))) - return bad_access_pkey(regs, address, vma); + return bad_access_pkey(regs, address, mm, vma); if (unlikely(access_error(is_write, is_exec, vma))) - return bad_access(regs, address); + return bad_access(regs, address, mm, vma); /* * If for any reason at all we couldn't handle the fault, diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 3a440004b97d2b..a197d4c2244b32 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -16,6 +16,7 @@ #include <linux/highmem.h> #include <linux/suspend.h> #include <linux/dma-direct.h> +#include <linux/vmalloc.h> #include <asm/swiotlb.h> #include <asm/machdep.h> diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 9b99113cb51a8f..6621cfc3baf86c 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -102,7 +102,7 @@ struct page *p4d_page(p4d_t p4d) { if (p4d_leaf(p4d)) { if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP)) - VM_WARN_ON(!p4d_huge(p4d)); + VM_WARN_ON(!p4d_leaf(p4d)); return pte_page(p4d_pte(p4d)); } return virt_to_page(p4d_pgtable(p4d)); @@ -113,7 +113,7 @@ struct page *pud_page(pud_t pud) { if (pud_leaf(pud)) { if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP)) - VM_WARN_ON(!pud_huge(pud)); + VM_WARN_ON(!pud_leaf(pud)); return pte_page(pud_pte(pud)); } return virt_to_page(pud_pgtable(pud)); @@ -132,7 +132,7 @@ struct page *pmd_page(pmd_t pmd) * enabled so these checks can't be used. */ if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP)) - VM_WARN_ON(!(pmd_leaf(pmd) || pmd_huge(pmd))); + VM_WARN_ON(!pmd_leaf(pmd)); return pte_page(pmd_pte(pmd)); } return virt_to_page(pmd_page_vaddr(pmd)); diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index d6b5f5ecd5152b..56dc6b29a3e769 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -695,7 +695,7 @@ static const struct dma_map_ops ps3_sb_dma_ops = { .unmap_page = ps3_unmap_page, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; @@ -709,7 +709,7 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = { .unmap_page = ps3_unmap_page, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 90ff85c879bfe9..477c1d5e1737ba 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -611,7 +611,7 @@ static const struct dma_map_ops vio_dma_mapping_ops = { .get_required_mask = dma_iommu_get_required_mask, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index be09c8836d56be..bf1a83c09ea059 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -27,6 +27,7 @@ config RISCV select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV + select ARCH_HAS_KERNEL_FPU_SUPPORT if 64BIT && FPU select ARCH_HAS_MEMBARRIER_CALLBACKS select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_MMIOWB @@ -132,7 +133,7 @@ config RISCV select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION select HAVE_EBPF_JIT if MMU - select HAVE_FAST_GUP if MMU + select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION select HAVE_GCC_PLUGINS diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata index 910ba8837add86..2acc7d876e1fb6 100644 --- a/arch/riscv/Kconfig.errata +++ b/arch/riscv/Kconfig.errata @@ -82,14 +82,14 @@ config ERRATA_THEAD Otherwise, please say "N" here to avoid unnecessary overhead. -config ERRATA_THEAD_PBMT - bool "Apply T-Head memory type errata" +config ERRATA_THEAD_MAE + bool "Apply T-Head's memory attribute extension (XTheadMae) errata" depends on ERRATA_THEAD && 64BIT && MMU select RISCV_ALTERNATIVE_EARLY default y help - This will apply the memory type errata to handle the non-standard - memory type bits in page-table-entries on T-Head SoCs. + This will apply the memory attribute extension errata to handle the + non-standard PTE utilization on T-Head SoCs (XTheadMae). If you don't know what to do here, say "Y". diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 5b3115a1985226..032b9dc5afbf3f 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -84,6 +84,9 @@ KBUILD_CFLAGS += -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64i KBUILD_AFLAGS += -march=$(riscv-march-y) +# For C code built with floating-point support, exclude V but keep F and D. +CC_FLAGS_FPU := -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)([^v_]*)v?/\1\2/') + KBUILD_CFLAGS += -mno-save-restore KBUILD_CFLAGS += -DCONFIG_PAGE_OFFSET=$(CONFIG_PAGE_OFFSET) diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi index 45b58b6f3df88e..ccd0ce55aa5301 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi @@ -238,7 +238,6 @@ axp15060: pmic@36 { compatible = "x-powers,axp15060"; reg = <0x36>; - interrupts = <0>; interrupt-controller; #interrupt-cells = <1>; @@ -279,24 +278,6 @@ status = "okay"; }; -&i2srx { - pinctrl-names = "default"; - pinctrl-0 = <&i2srx_pins>; - status = "okay"; -}; - -&i2stx0 { - pinctrl-names = "default"; - pinctrl-0 = <&mclk_ext_pins>; - status = "okay"; -}; - -&i2stx1 { - pinctrl-names = "default"; - pinctrl-0 = <&i2stx1_pins>; - status = "okay"; -}; - &mmc0 { max-frequency = <100000000>; assigned-clocks = <&syscrg JH7110_SYSCLK_SDIO0_SDCARD>; @@ -447,46 +428,6 @@ }; }; - i2srx_pins: i2srx-0 { - clk-sd-pins { - pinmux = <GPIOMUX(38, GPOUT_LOW, - GPOEN_DISABLE, - GPI_SYS_I2SRX_BCLK)>, - <GPIOMUX(63, GPOUT_LOW, - GPOEN_DISABLE, - GPI_SYS_I2SRX_LRCK)>, - <GPIOMUX(38, GPOUT_LOW, - GPOEN_DISABLE, - GPI_SYS_I2STX1_BCLK)>, - <GPIOMUX(63, GPOUT_LOW, - GPOEN_DISABLE, - GPI_SYS_I2STX1_LRCK)>, - <GPIOMUX(61, GPOUT_LOW, - GPOEN_DISABLE, - GPI_SYS_I2SRX_SDIN0)>; - input-enable; - }; - }; - - i2stx1_pins: i2stx1-0 { - sd-pins { - pinmux = <GPIOMUX(44, GPOUT_SYS_I2STX1_SDO0, - GPOEN_ENABLE, - GPI_NONE)>; - bias-disable; - input-disable; - }; - }; - - mclk_ext_pins: mclk-ext-0 { - mclk-ext-pins { - pinmux = <GPIOMUX(4, GPOUT_LOW, - GPOEN_DISABLE, - GPI_SYS_MCLK_EXT)>; - input-enable; - }; - }; - mmc0_pins: mmc0-0 { rst-pins { pinmux = <GPIOMUX(62, GPOUT_SYS_SDIO0_RST, @@ -622,40 +563,6 @@ }; }; - tdm_pins: tdm-0 { - tx-pins { - pinmux = <GPIOMUX(44, GPOUT_SYS_TDM_TXD, - GPOEN_ENABLE, - GPI_NONE)>; - bias-pull-up; - drive-strength = <2>; - input-disable; - input-schmitt-disable; - slew-rate = <0>; - }; - - rx-pins { - pinmux = <GPIOMUX(61, GPOUT_HIGH, - GPOEN_DISABLE, - GPI_SYS_TDM_RXD)>; - input-enable; - }; - - sync-pins { - pinmux = <GPIOMUX(63, GPOUT_HIGH, - GPOEN_DISABLE, - GPI_SYS_TDM_SYNC)>; - input-enable; - }; - - pcmclk-pins { - pinmux = <GPIOMUX(38, GPOUT_HIGH, - GPOEN_DISABLE, - GPI_SYS_TDM_CLK)>; - input-enable; - }; - }; - uart0_pins: uart0-0 { tx-pins { pinmux = <GPIOMUX(5, GPOUT_SYS_UART0_TX, @@ -681,12 +588,6 @@ }; }; -&tdm { - pinctrl-names = "default"; - pinctrl-0 = <&tdm_pins>; - status = "okay"; -}; - &uart0 { pinctrl-names = "default"; pinctrl-0 = <&uart0_pins>; diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index b1c410bbc1aece..bf6a0a6318ee30 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -19,20 +19,26 @@ #include <asm/patch.h> #include <asm/vendorid_list.h> -static bool errata_probe_pbmt(unsigned int stage, - unsigned long arch_id, unsigned long impid) +#define CSR_TH_SXSTATUS 0x5c0 +#define SXSTATUS_MAEE _AC(0x200000, UL) + +static bool errata_probe_mae(unsigned int stage, + unsigned long arch_id, unsigned long impid) { - if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PBMT)) + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_MAE)) return false; if (arch_id != 0 || impid != 0) return false; - if (stage == RISCV_ALTERNATIVES_EARLY_BOOT || - stage == RISCV_ALTERNATIVES_MODULE) - return true; + if (stage != RISCV_ALTERNATIVES_EARLY_BOOT && + stage != RISCV_ALTERNATIVES_MODULE) + return false; + + if (!(csr_read(CSR_TH_SXSTATUS) & SXSTATUS_MAEE)) + return false; - return false; + return true; } /* @@ -140,8 +146,8 @@ static u32 thead_errata_probe(unsigned int stage, { u32 cpu_req_errata = 0; - if (errata_probe_pbmt(stage, archid, impid)) - cpu_req_errata |= BIT(ERRATA_THEAD_PBMT); + if (errata_probe_mae(stage, archid, impid)) + cpu_req_errata |= BIT(ERRATA_THEAD_MAE); errata_probe_cmo(stage, archid, impid); diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index 1f2dbfb8a8bfc8..efd851e1b48321 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -23,7 +23,7 @@ #endif #ifdef CONFIG_ERRATA_THEAD -#define ERRATA_THEAD_PBMT 0 +#define ERRATA_THEAD_MAE 0 #define ERRATA_THEAD_PMU 1 #define ERRATA_THEAD_NUMBER 2 #endif @@ -53,20 +53,20 @@ asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID, \ * in the default case. */ #define ALT_SVPBMT_SHIFT 61 -#define ALT_THEAD_PBMT_SHIFT 59 +#define ALT_THEAD_MAE_SHIFT 59 #define ALT_SVPBMT(_val, prot) \ asm(ALTERNATIVE_2("li %0, 0\t\nnop", \ "li %0, %1\t\nslli %0,%0,%3", 0, \ RISCV_ISA_EXT_SVPBMT, CONFIG_RISCV_ISA_SVPBMT, \ "li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID, \ - ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \ + ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \ : "=r"(_val) \ : "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT), \ - "I"(prot##_THEAD >> ALT_THEAD_PBMT_SHIFT), \ + "I"(prot##_THEAD >> ALT_THEAD_MAE_SHIFT), \ "I"(ALT_SVPBMT_SHIFT), \ - "I"(ALT_THEAD_PBMT_SHIFT)) + "I"(ALT_THEAD_MAE_SHIFT)) -#ifdef CONFIG_ERRATA_THEAD_PBMT +#ifdef CONFIG_ERRATA_THEAD_MAE /* * IO/NOCACHE memory types are handled together with svpbmt, * so on T-Head chips, check if no other memory type is set, @@ -83,11 +83,11 @@ asm volatile(ALTERNATIVE( \ "slli t3, t3, %3\n\t" \ "or %0, %0, t3\n\t" \ "2:", THEAD_VENDOR_ID, \ - ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT) \ + ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \ : "+r"(_val) \ - : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_PBMT_SHIFT), \ - "I"(_PAGE_PMA_THEAD >> ALT_THEAD_PBMT_SHIFT), \ - "I"(ALT_THEAD_PBMT_SHIFT) \ + : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_MAE_SHIFT), \ + "I"(_PAGE_PMA_THEAD >> ALT_THEAD_MAE_SHIFT), \ + "I"(ALT_THEAD_MAE_SHIFT) \ : "t3") #else #define ALT_THEAD_PMA(_val) diff --git a/arch/riscv/include/asm/fpu.h b/arch/riscv/include/asm/fpu.h new file mode 100644 index 00000000000000..91c04c244e12d3 --- /dev/null +++ b/arch/riscv/include/asm/fpu.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef _ASM_RISCV_FPU_H +#define _ASM_RISCV_FPU_H + +#include <asm/switch_to.h> + +#define kernel_fpu_available() has_fpu() + +void kernel_fpu_begin(void); +void kernel_fpu_end(void); + +#endif /* ! _ASM_RISCV_FPU_H */ diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 22deb7a2a6ec4e..b1ce97a9dbfce7 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -5,11 +5,11 @@ #include <asm/cacheflush.h> #include <asm/page.h> -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h); diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 2947423b5082e9..115ac98b8d729d 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -89,7 +89,7 @@ typedef struct page *pgtable_t; #define PTE_FMT "%08lx" #endif -#ifdef CONFIG_64BIT +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) /* * We override this value as its generic definition uses __pa too early in * the boot process (before kernel_map.va_pa_offset is set). diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 9f8ea0e33eb104..f2d5973a011bdd 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -648,6 +648,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd) #define __pud_to_phys(pud) (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT) +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT); @@ -896,7 +897,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) #define PAGE_SHARED __pgprot(0) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL -#define TASK_SIZE 0xffffffffUL +#define TASK_SIZE _AC(-1, UL) #define VMALLOC_START _AC(0, UL) #define VMALLOC_END TASK_SIZE diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 9f2a8e3ff2048e..2902f68dc913aa 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -54,7 +54,7 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_EXT_ZFHMIN (1 << 28) #define RISCV_HWPROBE_EXT_ZIHINTNTL (1 << 29) #define RISCV_HWPROBE_EXT_ZVFH (1 << 30) -#define RISCV_HWPROBE_EXT_ZVFHMIN (1 << 31) +#define RISCV_HWPROBE_EXT_ZVFHMIN (1ULL << 31) #define RISCV_HWPROBE_EXT_ZFA (1ULL << 32) #define RISCV_HWPROBE_EXT_ZTSO (1ULL << 33) #define RISCV_HWPROBE_EXT_ZACAS (1ULL << 34) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 81d94a8ee10f29..5b243d46f4b174 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -67,6 +67,7 @@ obj-$(CONFIG_RISCV_MISALIGNED) += unaligned_access_speed.o obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) += copy-unaligned.o obj-$(CONFIG_FPU) += fpu.o +obj-$(CONFIG_FPU) += kernel_mode_fpu.o obj-$(CONFIG_RISCV_ISA_V) += vector.o obj-$(CONFIG_RISCV_ISA_V) += kernel_mode_vector.o obj-$(CONFIG_SMP) += smpboot.o diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index 54260c16f9912a..11c0d2e0becfe9 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -19,6 +19,7 @@ #include <linux/libfdt.h> #include <linux/types.h> #include <linux/memblock.h> +#include <linux/vmalloc.h> #include <asm/setup.h> int arch_kimage_file_post_load_cleanup(struct kimage *image) diff --git a/arch/riscv/kernel/kernel_mode_fpu.c b/arch/riscv/kernel/kernel_mode_fpu.c new file mode 100644 index 00000000000000..0ac8348876c499 --- /dev/null +++ b/arch/riscv/kernel/kernel_mode_fpu.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 SiFive + */ + +#include <linux/export.h> +#include <linux/preempt.h> + +#include <asm/csr.h> +#include <asm/fpu.h> +#include <asm/processor.h> +#include <asm/switch_to.h> + +void kernel_fpu_begin(void) +{ + preempt_disable(); + fstate_save(current, task_pt_regs(current)); + csr_set(CSR_SSTATUS, SR_FS); +} +EXPORT_SYMBOL_GPL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + csr_clear(CSR_SSTATUS, SR_FS); + fstate_restore(current, task_pt_regs(current)); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_end); diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 2f08c14a933d05..71a8b8945b26fd 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -6,6 +6,7 @@ #include <linux/extable.h> #include <linux/slab.h> #include <linux/stop_machine.h> +#include <linux/vmalloc.h> #include <asm/ptrace.h> #include <linux/uaccess.h> #include <asm/sections.h> diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 3ba1d4dde5dd1a..5224f373380225 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -292,7 +292,10 @@ void handle_page_fault(struct pt_regs *regs) if (unlikely(access_error(cause, vma))) { vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + tsk->thread.bad_cause = cause; + bad_area_nosemaphore(regs, SEGV_ACCERR, addr); + return; } fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs); diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 5ef2a6891158a6..0ebd968b33c997 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -399,16 +399,6 @@ static bool is_napot_size(unsigned long size) #endif /*CONFIG_RISCV_ISA_SVNAPOT*/ -int pud_huge(pud_t pud) -{ - return pud_leaf(pud); -} - -int pmd_huge(pmd_t pmd) -{ - return pmd_leaf(pmd); -} - static bool __hugetlb_valid_size(unsigned long size) { if (size == HPAGE_SIZE) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index fe8e159394d8ee..9687618432031f 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -231,7 +231,7 @@ static void __init setup_bootmem(void) * In 64-bit, any use of __va/__pa before this point is wrong as we * did not know the start of DRAM before. */ - if (IS_ENABLED(CONFIG_64BIT)) + if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base; /* diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 1adf2f39ce59cb..ec9d692838fca5 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -722,6 +722,9 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of if (ret) return ret; + /* store prog start time */ + emit_mv(RV_REG_S1, RV_REG_A0, ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ @@ -729,9 +732,6 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of /* nop reserved for conditional jump */ emit(rv_nop(), ctx); - /* store prog start time */ - emit_mv(RV_REG_S1, RV_REG_A0, ctx); - /* arg1: &args_off */ emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx); if (!p->jited) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8f01ada6845e36..d9aed4c93ee671 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -174,7 +174,7 @@ config S390 select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES select HAVE_EFFICIENT_UNALIGNED_ACCESS - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FENTRY select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API diff --git a/arch/s390/include/asm/dwarf.h b/arch/s390/include/asm/dwarf.h index 4f21ae561e4ddc..390906b8e386e6 100644 --- a/arch/s390/include/asm/dwarf.h +++ b/arch/s390/include/asm/dwarf.h @@ -9,6 +9,7 @@ #define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset #define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset #define CFI_RESTORE .cfi_restore +#define CFI_REL_OFFSET .cfi_rel_offset #ifdef CONFIG_AS_CFI_VAL_OFFSET #define CFI_VAL_OFFSET .cfi_val_offset diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index deb198a610395b..ce5f4fe8be4dce 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -39,11 +39,11 @@ static inline int prepare_hugepage_range(struct file *file, return 0; } -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_arch_1, &page->flags); + clear_bit(PG_arch_1, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 60950e7a25f585..2cb2a2e7b34b83 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1405,6 +1405,7 @@ static inline unsigned long pud_deref(pud_t pud) return (unsigned long)__va(pud_val(pud) & origin_mask); } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { return __pa(pud_deref(pud)) >> PAGE_SHIFT; diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c index 554447768bddc7..bf983513dd333b 100644 --- a/arch/s390/kernel/cert_store.c +++ b/arch/s390/kernel/cert_store.c @@ -21,6 +21,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/sysfs.h> +#include <linux/vmalloc.h> #include <crypto/sha2.h> #include <keys/user-type.h> #include <asm/debug.h> diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 1486350a417751..5d6d381aa0be4a 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -20,6 +20,7 @@ #include <linux/gfp.h> #include <linux/crash_dump.h> #include <linux/debug_locks.h> +#include <linux/vmalloc.h> #include <asm/asm-extable.h> #include <asm/diag.h> #include <asm/ipl.h> diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 095bb86339a7d3..bd0fee24ad10a3 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -464,3 +464,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal sys_mseal diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index 57f62596e53b95..85247ef5a41b89 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -24,8 +24,10 @@ __kernel_\func: CFI_DEF_CFA_OFFSET (STACK_FRAME_OVERHEAD + WRAPPER_FRAME_SIZE) CFI_VAL_OFFSET 15, -STACK_FRAME_OVERHEAD stg %r14,STACK_FRAME_OVERHEAD(%r15) + CFI_REL_OFFSET 14, STACK_FRAME_OVERHEAD brasl %r14,__s390_vdso_\func lg %r14,STACK_FRAME_OVERHEAD(%r15) + CFI_RESTORE 14 aghi %r15,WRAPPER_FRAME_SIZE CFI_DEF_CFA_OFFSET STACK_FRAME_OVERHEAD CFI_RESTORE 15 diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 0c66b32e0f9f1b..65747f15dbec4b 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -325,7 +325,8 @@ static void do_exception(struct pt_regs *regs, int access) goto lock_mmap; if (!(vma->vm_flags & access)) { vma_end_read(vma); - goto lock_mmap; + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return handle_fault_error_nolock(regs, SEGV_ACCERR); } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 094b43b121cd5d..12d22a7fa32fd2 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2661,7 +2661,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, return 0; start = pmd_val(*pmd) & HPAGE_MASK; - end = start + HPAGE_SIZE - 1; + end = start + HPAGE_SIZE; __storage_key_init_range(start, end); set_bit(PG_arch_1, &page->flags); cond_resched(); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index c2e8242bd15dd0..2675aab4acc700 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -139,7 +139,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste) } if (!test_and_set_bit(PG_arch_1, &page->flags)) - __storage_key_init_range(paddr, paddr + size - 1); + __storage_key_init_range(paddr, paddr + size); } void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, @@ -233,16 +233,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return (pte_t *) pmdp; } -int pmd_huge(pmd_t pmd) -{ - return pmd_leaf(pmd); -} - -int pud_huge(pud_t pud) -{ - return pud_leaf(pud); -} - bool __init arch_hugetlb_valid_size(unsigned long size) { if (MACHINE_HAS_EDAT1 && size == PMD_SIZE) @@ -258,14 +248,12 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; - info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; info.high_limit = TASK_SIZE; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; return vm_unmapped_area(&info); } @@ -274,7 +262,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; unsigned long addr; info.flags = VM_UNMAPPED_AREA_TOPDOWN; @@ -282,7 +270,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, info.low_limit = PAGE_SIZE; info.high_limit = current->mm->mmap_base; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -328,7 +315,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, goto check_asce_limit; } - if (mm->get_unmapped_area == arch_get_unmapped_area) + if (!test_bit(MMF_TOPDOWN, &mm->flags)) addr = hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); else diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index b14fc0887654d2..2067569465897b 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -86,7 +86,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (len > TASK_SIZE - mmap_min_addr) return -ENOMEM; @@ -102,7 +102,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, goto check_asce_limit; } - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; @@ -122,7 +121,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* requested length too big for entire address space */ if (len > TASK_SIZE - mmap_min_addr) @@ -185,10 +184,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) */ if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = mmap_base_legacy(random_factor); - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + set_bit(MMF_TOPDOWN, &mm->flags); } } diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index a90499c087f0c5..5398729bfe1b77 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -169,7 +169,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, if (!(vma->vm_flags & VM_WRITE)) goto out_unlock_mmap; - ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl); + ret = follow_pte(vma, mmio_addr, &ptep, &ptl); if (ret) goto out_unlock_mmap; @@ -308,7 +308,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, if (!(vma->vm_flags & VM_WRITE)) goto out_unlock_mmap; - ret = follow_pte(vma->vm_mm, mmio_addr, &ptep, &ptl); + ret = follow_pte(vma, mmio_addr, &ptep, &ptl); if (ret) goto out_unlock_mmap; diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 8b64ca76aa4b4a..94895a387ed523 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -38,7 +38,7 @@ config SUPERH select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DYNAMIC_FTRACE - select HAVE_FAST_GUP if MMU + select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index 4d3ba39e681c4f..75028bd568ba5e 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -27,11 +27,11 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, return *ptep; } -static inline void arch_clear_hugepage_flags(struct page *page) +static inline void arch_clear_hugetlb_flags(struct folio *folio) { - clear_bit(PG_dcache_clean, &page->flags); + clear_bit(PG_dcache_clean, &folio->flags); } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #include <asm-generic/hugetlb.h> diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 86fe269f02203b..bbf83a2db9868d 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -464,3 +464,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 862046f26981b6..9a1e581cd192d1 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -241,13 +241,14 @@ static void sh4_flush_cache_page(void *args) if ((vma->vm_mm == current->active_mm)) vaddr = NULL; else { + struct folio *folio = page_folio(page); /* * Use kmap_coherent or kmap_atomic to do flushes for * another ASID than the current one. */ map_coherent = (current_cpu_data.dcache.n_aliases && - test_bit(PG_dcache_clean, &page->flags) && - page_mapcount(page)); + test_bit(PG_dcache_clean, folio_flags(folio, 0)) && + page_mapped(page)); if (map_coherent) vaddr = kmap_coherent(page, address); else diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index 9bcaa5619eabd1..d8be352e14d20d 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -84,7 +84,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page, { struct folio *folio = page_folio(page); - if (boot_cpu_data.dcache.n_aliases && page_mapcount(page) && + if (boot_cpu_data.dcache.n_aliases && folio_mapped(folio) && test_bit(PG_dcache_clean, &folio->flags)) { void *vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(dst, vfrom, len); diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index 6cb0ad73dbb9e3..ff209b55285ad2 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -70,13 +70,3 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return pte; } - -int pmd_huge(pmd_t pmd) -{ - return 0; -} - -int pud_huge(pud_t pud) -{ - return 0; -} diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c index b82199878b4594..bee329d4149aa7 100644 --- a/arch/sh/mm/mmap.c +++ b/arch/sh/mm/mmap.c @@ -57,7 +57,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int do_colour_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate @@ -88,7 +88,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = TASK_SIZE; @@ -106,7 +105,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct mm_struct *mm = current->mm; unsigned long addr = addr0; int do_colour_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 4d1bafaba942d2..3fe429d73a65b0 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -875,6 +875,7 @@ static inline bool pud_leaf(pud_t pud) return pte_val(pte) & _PAGE_PMD_HUGE; } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { pte_t pte = __pte(pud_val(pud)); @@ -956,7 +957,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr, #ifdef DCACHE_ALIASING_POSSIBLE #define __HAVE_ARCH_MOVE_PTE -#define move_pte(pte, prot, old_addr, new_addr) \ +#define move_pte(pte, old_addr, new_addr) \ ({ \ pte_t newpte = (pte); \ if (tlb_type != hypervisor && pte_present(pte)) { \ diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 082a551897ed8f..08a19727795ca4 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -41,7 +41,7 @@ SYSCALL_DEFINE0(getpagesize) unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate @@ -59,7 +59,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi if (!addr) addr = TASK_UNMAPPED_BASE; - info.flags = 0; info.length = len; info.low_limit = addr; info.high_limit = TASK_SIZE; diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 1e9a9e016237bf..d9c3b34ca74470 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -93,7 +93,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi struct vm_area_struct * vma; unsigned long task_size = TASK_SIZE; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate @@ -126,7 +126,6 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi return addr; } - info.flags = 0; info.length = len; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = min(task_size, VA_EXCLUDE_START); @@ -154,7 +153,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long task_size = STACK_TOP32; unsigned long addr = addr0; int do_color_align; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* This should only ever run for 32-bit processes. */ BUG_ON(!test_thread_flag(TIF_32BIT)); @@ -218,14 +217,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long align_goal, addr = -ENOMEM; - unsigned long (*get_area)(struct file *, unsigned long, - unsigned long, unsigned long, unsigned long); - - get_area = current->mm->get_unmapped_area; if (flags & MAP_FIXED) { /* Ok, don't mess with it. */ - return get_area(NULL, orig_addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, NULL, orig_addr, len, pgoff, flags); } flags &= ~MAP_SHARED; @@ -238,7 +233,8 @@ unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, u align_goal = (64UL * 1024); do { - addr = get_area(NULL, orig_addr, len + (align_goal - PAGE_SIZE), pgoff, flags); + addr = mm_get_unmapped_area(current->mm, NULL, orig_addr, + len + (align_goal - PAGE_SIZE), pgoff, flags); if (!(addr & ~PAGE_MASK)) { addr = (addr + (align_goal - 1UL)) & ~(align_goal - 1UL); break; @@ -256,7 +252,7 @@ unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, u * be obtained. */ if (addr & ~PAGE_MASK) - addr = get_area(NULL, orig_addr, len, pgoff, flags); + addr = mm_get_unmapped_area(current->mm, NULL, orig_addr, len, pgoff, flags); return addr; } @@ -292,7 +288,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) gap == RLIM_INFINITY || sysctl_legacy_va_layout) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); } else { /* We know it's 32-bit */ unsigned long task_size = STACK_TOP32; @@ -303,7 +299,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) gap = (task_size / 6 * 5); mm->mmap_base = PAGE_ALIGN(task_size - gap - random_factor); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + set_bit(MMF_TOPDOWN, &mm->flags); } } diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index b23d59313589aa..ac6c281ccfe029 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -507,3 +507,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index b432500c13a5d8..cc91ca7a1e182c 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -31,17 +31,15 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp, { struct hstate *h = hstate_file(filp); unsigned long task_size = TASK_SIZE; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; if (test_thread_flag(TIF_32BIT)) task_size = STACK_TOP32; - info.flags = 0; info.length = len; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = min(task_size, VA_EXCLUDE_START); info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) { @@ -63,7 +61,7 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, struct hstate *h = hstate_file(filp); struct mm_struct *mm = current->mm; unsigned long addr = addr0; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* This should only ever run for 32-bit processes. */ BUG_ON(!test_thread_flag(TIF_32BIT)); @@ -73,7 +71,6 @@ hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -123,7 +120,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, (!vma || addr + len <= vm_start_gap(vma))) return addr; } - if (mm->get_unmapped_area == arch_get_unmapped_area) + if (!test_bit(MMF_TOPDOWN, &mm->flags)) return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); else @@ -407,18 +404,6 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, return entry; } -int pmd_huge(pmd_t pmd) -{ - return !pmd_none(pmd) && - (pmd_val(pmd) & (_PAGE_VALID|_PAGE_PMD_HUGE)) != _PAGE_VALID; -} - -int pud_huge(pud_t pud) -{ - return !pud_none(pud) && - (pud_val(pud) & (_PAGE_VALID|_PAGE_PUD_HUGE)) != _PAGE_VALID; -} - static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index b44d79d778c718..19642f7ffb52a5 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -183,12 +183,12 @@ static void __set_pmd_acct(struct mm_struct *mm, unsigned long addr, * hugetlb_pte_count. */ if (pmd_val(pmd) & _PAGE_PMD_HUGE) { - if (is_huge_zero_page(pmd_page(pmd))) + if (is_huge_zero_pmd(pmd)) mm->context.hugetlb_pte_count++; else mm->context.thp_pte_count++; } else { - if (is_huge_zero_page(pmd_page(orig))) + if (is_huge_zero_pmd(orig)) mm->context.hugetlb_pte_count--; else mm->context.thp_pte_count--; @@ -259,7 +259,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, * Sanity check pmd before doing the actual decrement. */ if ((pmd_val(entry) & _PAGE_PMD_HUGE) && - !is_huge_zero_page(pmd_page(entry))) + !is_huge_zero_pmd(entry)) (vma->vm_mm)->context.thp_pte_count--; return old; diff --git a/arch/um/include/shared/um_malloc.h b/arch/um/include/shared/um_malloc.h index 13da93284c2c7f..bf503658f08eb3 100644 --- a/arch/um/include/shared/um_malloc.h +++ b/arch/um/include/shared/um_malloc.h @@ -11,7 +11,8 @@ extern void *uml_kmalloc(int size, int flags); extern void kfree(const void *ptr); -extern void *vmalloc(unsigned long size); +extern void *vmalloc_noprof(unsigned long size); +#define vmalloc(...) vmalloc_noprof(__VA_ARGS__) extern void vfree(void *ptr); #endif /* __UM_MALLOC_H__ */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4474bf32d0a497..2e2a69647e5ec7 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -62,6 +62,7 @@ config X86 select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT + select ARCH_CONFIGURES_CPU_MITIGATIONS select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 @@ -83,6 +84,7 @@ config X86 select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 + select ARCH_HAS_KERNEL_FPU_SUPPORT select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS @@ -221,7 +223,7 @@ config X86 select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EISA select HAVE_EXIT_THREAD - select HAVE_FAST_GUP + select HAVE_GUP_FAST select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER @@ -2488,17 +2490,21 @@ config PREFIX_SYMBOLS def_bool y depends on CALL_PADDING && !CFI_CLANG -menuconfig SPECULATION_MITIGATIONS - bool "Mitigations for speculative execution vulnerabilities" +menuconfig CPU_MITIGATIONS + bool "Mitigations for CPU vulnerabilities" default y help - Say Y here to enable options which enable mitigations for - speculative execution hardware vulnerabilities. + Say Y here to enable options which enable mitigations for hardware + vulnerabilities (usually related to speculative execution). + Mitigations can be disabled or restricted to SMT systems at runtime + via the "mitigations" kernel parameter. - If you say N, all mitigations will be disabled. You really - should know what you are doing to say so. + If you say N, all mitigations will be disabled. This CANNOT be + overridden at runtime. -if SPECULATION_MITIGATIONS + Say 'Y', unless you really know what you are doing. + +if CPU_MITIGATIONS config MITIGATION_PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5ab93fcdd691dc..164498b3382ae2 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -74,6 +74,26 @@ KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 +# +# CFLAGS for compiling floating point code inside the kernel. +# +CC_FLAGS_FPU := -msse -msse2 +ifdef CONFIG_CC_IS_GCC +# Stack alignment mismatch, proceed with caution. +# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 +# (8B stack alignment). +# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 +# +# The "-msse" in the first argument is there so that the +# -mpreferred-stack-boundary=3 build error: +# +# -mpreferred-stack-boundary=3 is not between 4 and 12 +# +# can be triggered. Otherwise gcc doesn't complain. +CC_FLAGS_FPU += -mhard-float +CC_FLAGS_FPU += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4) +endif + ifeq ($(CONFIG_X86_KERNEL_IBT),y) # # Kernel IBT has S_CET.NOTRACK_EN=0, as such the compilers must not generate diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 5f8591ce7f25e7..7fd1f57ad3d30c 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -466,3 +466,4 @@ 459 i386 lsm_get_self_attr sys_lsm_get_self_attr 460 i386 lsm_set_self_attr sys_lsm_set_self_attr 461 i386 lsm_list_modules sys_lsm_list_modules +462 i386 mseal sys_mseal diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 7e8d46f4147f57..52df0dec70da6c 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -383,6 +383,7 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 768d73de0d098a..5bc2430e1f3417 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -291,16 +291,18 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { - struct sev_es_save_area *vmsa = (struct sev_es_save_area *) - __get_free_page(GFP_KERNEL | __GFP_ZERO); + struct hv_enable_vp_vtl *start_vp_input; struct sev_es_save_area *cur_vmsa; + struct sev_es_save_area *vmsa; struct desc_ptr gdtr; - u64 ret, retry = 5; - struct hv_enable_vp_vtl *start_vp_input; unsigned long flags; + u64 ret, retry = 5; + struct page *p; - if (!vmsa) + p = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_ZERO, 0); + if (!p) return -ENOMEM; + vmsa = (struct sev_es_save_area *)page_address(p); native_store_gdt(&gdtr); diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index c086699b0d0c59..aa6c8f8ca9588e 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -25,6 +25,7 @@ u64 cc_mkdec(u64 val); void cc_random_init(void); #else #define cc_vendor (CC_VENDOR_NONE) +static const u64 cc_mask = 0; static inline u64 cc_mkenc(u64 val) { diff --git a/arch/x86/include/asm/fpu.h b/arch/x86/include/asm/fpu.h new file mode 100644 index 00000000000000..b2743fe19339a6 --- /dev/null +++ b/arch/x86/include/asm/fpu.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef _ASM_X86_FPU_H +#define _ASM_X86_FPU_H + +#include <asm/fpu/api.h> + +#define kernel_fpu_available() true + +#endif /* ! _ASM_X86_FPU_H */ diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index ace9aa3b78a305..eb17f31b06d25c 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -2,8 +2,8 @@ /* * FPU data structures: */ -#ifndef _ASM_X86_FPU_H -#define _ASM_X86_FPU_H +#ifndef _ASM_X86_FPU_TYPES_H +#define _ASM_X86_FPU_TYPES_H #include <asm/page_types.h> @@ -596,4 +596,4 @@ struct fpu_state_config { /* FPU state configuration information */ extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg; -#endif /* _ASM_X86_FPU_H */ +#endif /* _ASM_X86_FPU_TYPES_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 294cd2a4081812..7452fc193b4f9e 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -42,6 +42,7 @@ #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> #include <asm/shared/io.h> +#include <asm/special_insns.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 315535ffb2582c..65b8e5bb902cc3 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -234,6 +234,7 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } +#define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); @@ -387,23 +388,7 @@ static inline pte_t pte_wrprotect(pte_t pte) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { - bool wp = pte_flags(pte) & _PAGE_UFFD_WP; - -#ifdef CONFIG_DEBUG_VM - /* - * Having write bit for wr-protect-marked present ptes is fatal, - * because it means the uffd-wp bit will be ignored and write will - * just go through. - * - * Use any chance of pgtable walking to verify this (e.g., when - * page swapped out or being migrated for all purposes). It means - * something is already wrong. Tell the admin even before the - * process crashes. We also nail it with wrong pgtable setup. - */ - WARN_ON_ONCE(wp && pte_write(pte)); -#endif - - return wp; + return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) @@ -1200,7 +1185,6 @@ static inline int pgd_none(pgd_t pgd) extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); -extern void memblock_find_dma_reserve(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 7e9db77231ac7f..3c4407271d0838 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -245,6 +245,7 @@ extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#define HAVE_ARCH_UNMAPPED_AREA_VMFLAGS #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0b748ee16b3d94..9abb8cc4cd4747 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -148,7 +148,7 @@ #define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | \ _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \ - _PAGE_DEVMAP | _PAGE_ENC | _PAGE_UFFD_WP) + _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) @@ -173,6 +173,7 @@ enum page_cache_mode { }; #endif +#define _PAGE_CC (_AT(pteval_t, cc_mask)) #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 2ae98f754e5918..c884deca839b2e 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -676,7 +676,7 @@ static const struct dma_map_ops gart_dma_ops = { .get_sgtable = dma_common_get_sgtable, .dma_supported = dma_direct_supported, .get_required_mask = dma_direct_get_required_mask, - .alloc_pages = dma_direct_alloc_pages, + .alloc_pages_op = dma_direct_alloc_pages, .free_pages = dma_direct_free_pages, }; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index cb9eece55904d0..307302af0aeee2 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -459,8 +459,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) case 0x1a: switch (c->x86_model) { - case 0x00 ... 0x0f: - case 0x20 ... 0x2f: + case 0x00 ... 0x2f: case 0x40 ... 0x4f: case 0x70 ... 0x7f: setup_force_cpu_cap(X86_FEATURE_ZEN5); diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index 262f5fb18d74d3..22b65a5f5ec6c4 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -113,7 +113,7 @@ static unsigned long sgx_get_unmapped_area(struct file *file, if (flags & MAP_FIXED) return addr; - return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags); } #ifdef CONFIG_COMPAT diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 166692f2d50111..27892e57c4ef93 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -13,6 +13,7 @@ #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/sysfs.h> +#include <linux/vmalloc.h> #include <asm/sgx.h> #include "driver.h" #include "encl.h" diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index fe0c859873d17e..ade0043ce56efe 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -18,6 +18,7 @@ #include <linux/uaccess.h> #include <linux/smp.h> #include <linux/sched/task_stack.h> +#include <linux/vmalloc.h> #include <asm/cpu_entry_area.h> #include <asm/softirq_stack.h> diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 7062b84dd467d6..6d3d20e3e43a9b 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -139,7 +139,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, log_lvl, d3, d6, d7); } - if (cpu_feature_enabled(X86_FEATURE_OSPKE)) + if (cr4 & X86_CR4_PKE) printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e125e059e2c45d..47e7fcdbdacd5b 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1107,8 +1107,6 @@ void __init setup_arch(char **cmdline_p) */ arch_reserve_crashkernel(); - memblock_find_dma_reserve(); - if (!early_xdbc_setup_hardware()) early_xdbc_register_console(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 8b04958da5e7d6..b4f8fa0f722cd6 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -1203,12 +1203,14 @@ static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt, break; case SVM_EXIT_MONITOR: - if (opcode == 0x010f && modrm == 0xc8) + /* MONITOR and MONITORX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa)) return ES_OK; break; case SVM_EXIT_MWAIT: - if (opcode == 0x010f && modrm == 0xc9) + /* MWAIT and MWAITX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb)) return ES_OK; break; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index cb9fa1d5c66f73..01d7cd85ef9789 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -112,13 +112,21 @@ static void find_start_end(unsigned long addr, unsigned long flags, *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); } +static inline unsigned long stack_guard_placement(vm_flags_t vm_flags) +{ + if (vm_flags & VM_SHADOW_STACK) + return PAGE_SIZE; + + return 0; +} + unsigned long -arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; unsigned long begin, end; if (flags & MAP_FIXED) @@ -137,12 +145,11 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = begin; info.high_limit = end; - info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; + info.start_gap = stack_guard_placement(vm_flags); if (filp) { info.align_mask = get_align_mask(); info.align_offset += get_align_bits(); @@ -151,14 +158,14 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, } unsigned long -arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) +arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr0, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; unsigned long addr = addr0; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -192,6 +199,7 @@ get_unmapped_area: info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); + info.start_gap = stack_guard_placement(vm_flags); /* * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area @@ -203,7 +211,6 @@ get_unmapped_area: if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall()) info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; - info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; if (filp) { info.align_mask = get_align_mask(); @@ -223,3 +230,18 @@ bottomup: */ return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); } + +unsigned long +arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); +} + +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, + const unsigned long len, const unsigned long pgoff, + const unsigned long flags) +{ + return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, flags, 0); +} diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c index 6e8b7e600def57..97e88e58567bf8 100644 --- a/arch/x86/lib/copy_mc.c +++ b/arch/x86/lib/copy_mc.c @@ -4,6 +4,7 @@ #include <linux/jump_label.h> #include <linux/uaccess.h> #include <linux/export.h> +#include <linux/instrumented.h> #include <linux/string.h> #include <linux/types.h> @@ -61,10 +62,20 @@ unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned */ unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len) { - if (copy_mc_fragile_enabled) - return copy_mc_fragile(dst, src, len); - if (static_cpu_has(X86_FEATURE_ERMS)) - return copy_mc_enhanced_fast_string(dst, src, len); + unsigned long ret; + + if (copy_mc_fragile_enabled) { + instrument_memcpy_before(dst, src, len); + ret = copy_mc_fragile(dst, src, len); + instrument_memcpy_after(dst, src, len, ret); + return ret; + } + if (static_cpu_has(X86_FEATURE_ERMS)) { + instrument_memcpy_before(dst, src, len); + ret = copy_mc_enhanced_fast_string(dst, src, len); + instrument_memcpy_after(dst, src, len, ret); + return ret; + } memcpy(dst, src, len); return 0; } @@ -75,6 +86,7 @@ unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, un unsigned long ret; if (copy_mc_fragile_enabled) { + instrument_copy_to_user(dst, src, len); __uaccess_begin(); ret = copy_mc_fragile((__force void *)dst, src, len); __uaccess_end(); @@ -82,6 +94,7 @@ unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, un } if (static_cpu_has(X86_FEATURE_ERMS)) { + instrument_copy_to_user(dst, src, len); __uaccess_begin(); ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len); __uaccess_end(); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 622d12ec7f0851..67b18adc75ddc1 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -20,6 +20,7 @@ #include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <linux/mm_types.h> #include <linux/mm.h> /* find_and_lock_vma() */ +#include <linux/vmalloc.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ @@ -865,14 +866,17 @@ bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, static void __bad_area(struct pt_regs *regs, unsigned long error_code, - unsigned long address, u32 pkey, int si_code) + unsigned long address, struct mm_struct *mm, + struct vm_area_struct *vma, u32 pkey, int si_code) { - struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ - mmap_read_unlock(mm); + if (mm) + mmap_read_unlock(mm); + else + vma_end_read(vma); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } @@ -896,7 +900,8 @@ static inline bool bad_area_access_from_pkeys(unsigned long error_code, static noinline void bad_area_access_error(struct pt_regs *regs, unsigned long error_code, - unsigned long address, struct vm_area_struct *vma) + unsigned long address, struct mm_struct *mm, + struct vm_area_struct *vma) { /* * This OSPKE check is not strictly necessary at runtime. @@ -926,9 +931,9 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, */ u32 pkey = vma_pkey(vma); - __bad_area(regs, error_code, address, pkey, SEGV_PKUERR); + __bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR); } else { - __bad_area(regs, error_code, address, 0, SEGV_ACCERR); + __bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR); } } @@ -1356,8 +1361,9 @@ void do_user_addr_fault(struct pt_regs *regs, goto lock_mmap; if (unlikely(access_error(error_code, vma))) { - vma_end_read(vma); - goto lock_mmap; + bad_area_access_error(regs, error_code, address, NULL, vma); + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + return; } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) @@ -1393,7 +1399,7 @@ retry: * we can handle it.. */ if (unlikely(access_error(error_code, vma))) { - bad_area_access_error(regs, error_code, address, vma); + bad_area_access_error(regs, error_code, address, mm, vma); return; } diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 5804bbae4f0125..807a5859a3c4b3 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -19,41 +19,14 @@ #include <asm/tlbflush.h> #include <asm/elf.h> -/* - * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal - * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. - * Otherwise, returns 0. - */ -int pmd_huge(pmd_t pmd) -{ - return !pmd_none(pmd) && - (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; -} - -/* - * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal - * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. - * Otherwise, returns 0. - */ -int pud_huge(pud_t pud) -{ -#if CONFIG_PGTABLE_LEVELS > 2 - return !pud_none(pud) && - (pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; -#else - return 0; -#endif -} - #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; - info.flags = 0; info.length = len; info.low_limit = get_mmap_base(1); @@ -65,7 +38,6 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW); info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; return vm_unmapped_area(&info); } @@ -74,7 +46,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; @@ -89,7 +61,6 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -141,7 +112,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, } get_unmapped_area: - if (mm->get_unmapped_area == arch_get_unmapped_area) + if (!test_bit(MMF_TOPDOWN, &mm->flags)) return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); else diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 679893ea5e6873..615f0bf4bda61a 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -990,53 +990,6 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) } #endif -/* - * Calculate the precise size of the DMA zone (first 16 MB of RAM), - * and pass it to the MM layer - to help it set zone watermarks more - * accurately. - * - * Done on 64-bit systems only for the time being, although 32-bit systems - * might benefit from this as well. - */ -void __init memblock_find_dma_reserve(void) -{ -#ifdef CONFIG_X86_64 - u64 nr_pages = 0, nr_free_pages = 0; - unsigned long start_pfn, end_pfn; - phys_addr_t start_addr, end_addr; - int i; - u64 u; - - /* - * Iterate over all memory ranges (free and reserved ones alike), - * to calculate the total number of pages in the first 16 MB of RAM: - */ - nr_pages = 0; - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { - start_pfn = min(start_pfn, MAX_DMA_PFN); - end_pfn = min(end_pfn, MAX_DMA_PFN); - - nr_pages += end_pfn - start_pfn; - } - - /* - * Iterate over free memory ranges to calculate the number of free - * pages in the DMA zone, while not counting potential partial - * pages at the beginning or the end of the range: - */ - nr_free_pages = 0; - for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) { - start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN); - end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN); - - if (start_pfn < end_pfn) - nr_free_pages += end_pfn - start_pfn; - } - - set_dma_reserve(nr_pages - nr_free_pages); -#endif -} - void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index c90c20904a6075..a2cabb1c81e1ae 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -129,9 +129,9 @@ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base, void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { if (mmap_is_legacy()) - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); else - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + set_bit(MMF_TOPDOWN, &mm->flags); arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, arch_rnd(mmap64_rnd_bits), task_size_64bit(0), diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 025fd7ea5d69f5..65fda406e6f265 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -24,6 +24,7 @@ #include <linux/memblock.h> #include <linux/init.h> +#include <linux/vmalloc.h> #include <asm/pgtable_areas.h> #include "numa_internal.h" diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 36b603d0cddefc..bdc2a240c2aae6 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -39,6 +39,7 @@ #include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/mm.h> +#include <linux/highmem.h> #include <linux/fs.h> #include <linux/rbtree.h> @@ -947,6 +948,29 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int follow_phys(struct vm_area_struct *vma, unsigned long *prot, + resource_size_t *phys) +{ + pte_t *ptep, pte; + spinlock_t *ptl; + + if (follow_pte(vma, vma->vm_start, &ptep, &ptl)) + return -EINVAL; + + pte = ptep_get(ptep); + + /* Never return PFNs of anon folios in COW mappings. */ + if (vm_normal_folio(vma, vma->vm_start, pte)) { + pte_unmap_unlock(ptep, ptl); + return -EINVAL; + } + + *prot = pgprot_val(pte_pgprot(pte)); + *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; + pte_unmap_unlock(ptep, ptl); + return 0; +} + static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, pgprot_t *pgprot) { @@ -964,7 +988,7 @@ static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, * detect the PFN. If we need the cachemode as well, we're out of luck * for now and have to fail fork(). */ - if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (!follow_phys(vma, &prot, paddr)) { if (pgprot) *pgprot = __pgprot(prot); return 0; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index d007591b80597a..94767c82fc0d72 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -731,7 +731,7 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) return 0; /* Bail out if we are we on a populated non-leaf entry: */ - if (pud_present(*pud) && !pud_huge(*pud)) + if (pud_present(*pud) && !pud_leaf(*pud)) return 0; set_pte((pte_t *)pud, pfn_pte( @@ -760,7 +760,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) } /* Bail out if we are we on a populated non-leaf entry: */ - if (pmd_present(*pmd) && !pmd_huge(*pmd)) + if (pmd_present(*pmd) && !pmd_leaf(*pmd)) return 0; set_pte((pte_t *)pmd, pfn_pte( diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index df5fac428408fe..59cbc94b6e6903 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1807,36 +1807,41 @@ populate_extable: if (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { /* Conservatively check that src_reg + insn->off is a kernel address: - * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE - * src_reg is used as scratch for src_reg += insn->off and restored - * after emit_ldx if necessary + * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE + * and + * src_reg + insn->off < VSYSCALL_ADDR */ - u64 limit = TASK_SIZE_MAX + PAGE_SIZE; + u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR; u8 *end_of_jmp; - /* At end of these emitted checks, insn->off will have been added - * to src_reg, so no need to do relative load with insn->off offset - */ - insn_off = 0; + /* movabsq r10, VSYSCALL_ADDR */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32, + (u32)(long)VSYSCALL_ADDR); - /* movabsq r11, limit */ - EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); - EMIT((u32)limit, 4); - EMIT(limit >> 32, 4); + /* mov src_reg, r11 */ + EMIT_mov(AUX_REG, src_reg); if (insn->off) { - /* add src_reg, insn->off */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); } - /* cmp src_reg, r11 */ - maybe_emit_mod(&prog, src_reg, AUX_REG, true); - EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* sub r11, r10 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); + + /* movabsq r10, limit */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32, + (u32)(long)limit); + + /* cmp r10, r11 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); - /* if unsigned '>=', goto load */ - EMIT2(X86_JAE, 0); + /* if unsigned '>', goto load */ + EMIT2(X86_JA, 0); end_of_jmp = prog; /* xor dst_reg, dst_reg */ @@ -1862,18 +1867,6 @@ populate_extable: /* populate jmp_offset for JMP above */ start_of_ldx[-1] = prog - start_of_ldx; - if (insn->off && src_reg != dst_reg) { - /* sub src_reg, insn->off - * Restore src_reg after "add src_reg, insn->off" in prev - * if statement. But if src_reg == dst_reg, emit_ldx - * above already clobbered src_reg, so no need to restore. - * If add src_reg, insn->off was unnecessary, no need to - * restore either. - */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off); - } - if (!bpf_prog->aux->extable) break; @@ -3473,3 +3466,9 @@ bool bpf_jit_supports_ptr_xchg(void) { return true; } + +/* x86-64 JIT emits its own code to filter user addresses so return 0 here */ +u64 bpf_arch_uaddress_limit(void) +{ + return 0; +} diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index dd116598fb2517..67083fc1b2f563 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -432,3 +432,4 @@ 459 common lsm_get_self_attr sys_lsm_get_self_attr 460 common lsm_set_self_attr sys_lsm_set_self_attr 461 common lsm_list_modules sys_lsm_list_modules +462 common mseal sys_mseal diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 7ec66a79f4723c..23be0e7516cede 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -87,12 +87,13 @@ static inline void *coherent_kvaddr(struct page *page, unsigned long base, void clear_user_highpage(struct page *page, unsigned long vaddr) { + struct folio *folio = page_folio(page); unsigned long paddr; void *kvaddr = coherent_kvaddr(page, TLBTEMP_BASE_1, vaddr, &paddr); preempt_disable(); kmap_invalidate_coherent(page, vaddr); - set_bit(PG_arch_1, &page->flags); + set_bit(PG_arch_1, folio_flags(folio, 0)); clear_page_alias(kvaddr, paddr); preempt_enable(); } @@ -101,6 +102,7 @@ EXPORT_SYMBOL(clear_user_highpage); void copy_user_highpage(struct page *dst, struct page *src, unsigned long vaddr, struct vm_area_struct *vma) { + struct folio *folio = page_folio(dst); unsigned long dst_paddr, src_paddr; void *dst_vaddr = coherent_kvaddr(dst, TLBTEMP_BASE_1, vaddr, &dst_paddr); @@ -109,7 +111,7 @@ void copy_user_highpage(struct page *dst, struct page *src, preempt_disable(); kmap_invalidate_coherent(dst, vaddr); - set_bit(PG_arch_1, &dst->flags); + set_bit(PG_arch_1, folio_flags(folio, 0)); copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr); preempt_enable(); } diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c index 4f974b74883cae..d8b60d6e50a8e7 100644 --- a/arch/xtensa/mm/tlb.c +++ b/arch/xtensa/mm/tlb.c @@ -256,12 +256,13 @@ static int check_tlb_entry(unsigned w, unsigned e, bool dtlb) dtlb ? 'D' : 'I', w, e, r0, r1, pte); if (pte == 0 || !pte_present(__pte(pte))) { struct page *p = pfn_to_page(r1 >> PAGE_SHIFT); - pr_err("page refcount: %d, mapcount: %d\n", - page_count(p), - page_mapcount(p)); - if (!page_count(p)) + struct folio *f = page_folio(p); + + pr_err("folio refcount: %d, mapcount: %d\n", + folio_ref_count(f), folio_mapcount(f)); + if (!folio_ref_count(f)) rc |= TLB_INSANE; - else if (page_mapcount(p)) + else if (folio_mapped(f)) rc |= TLB_SUSPICIOUS; } else { rc |= TLB_INSANE; diff --git a/block/bdev.c b/block/bdev.c index 4dc94145eb5330..da2a167a4d08b6 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -882,7 +882,7 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, goto abort_claiming; ret = -EBUSY; if (!bdev_may_open(bdev, mode)) - goto abort_claiming; + goto put_module; if (bdev_is_partition(bdev)) ret = blkdev_get_part(bdev, mode); else diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c index 38e58960ae036a..2bd42fedb907a9 100644 --- a/block/partitions/ldm.c +++ b/block/partitions/ldm.c @@ -131,8 +131,7 @@ static bool ldm_parse_tocblock (const u8 *data, struct tocblock *toc) ldm_crit ("Cannot find TOCBLOCK, database may be corrupt."); return false; } - strncpy (toc->bitmap1_name, data + 0x24, sizeof (toc->bitmap1_name)); - toc->bitmap1_name[sizeof (toc->bitmap1_name) - 1] = 0; + strscpy_pad(toc->bitmap1_name, data + 0x24, sizeof(toc->bitmap1_name)); toc->bitmap1_start = get_unaligned_be64(data + 0x2E); toc->bitmap1_size = get_unaligned_be64(data + 0x36); @@ -142,8 +141,7 @@ static bool ldm_parse_tocblock (const u8 *data, struct tocblock *toc) TOC_BITMAP1, toc->bitmap1_name); return false; } - strncpy (toc->bitmap2_name, data + 0x46, sizeof (toc->bitmap2_name)); - toc->bitmap2_name[sizeof (toc->bitmap2_name) - 1] = 0; + strscpy_pad(toc->bitmap2_name, data + 0x46, sizeof(toc->bitmap2_name)); toc->bitmap2_start = get_unaligned_be64(data + 0x50); toc->bitmap2_size = get_unaligned_be64(data + 0x58); if (strncmp (toc->bitmap2_name, TOC_BITMAP2, diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c index fe61612992364c..128aef8e5a1999 100644 --- a/drivers/accel/ivpu/ivpu_mmu_context.c +++ b/drivers/accel/ivpu/ivpu_mmu_context.c @@ -6,6 +6,7 @@ #include <linux/bitfield.h> #include <linux/highmem.h> #include <linux/set_memory.h> +#include <linux/vmalloc.h> #include <drm/drm_cache.h> diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 4bfbe55553f410..a40b6f3946efeb 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -170,8 +170,8 @@ show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time); #define GET_BIT_WIDTH(reg) ((reg)->access_width ? (8 << ((reg)->access_width - 1)) : (reg)->bit_width) /* Shift and apply the mask for CPC reads/writes */ -#define MASK_VAL(reg, val) ((val) >> ((reg)->bit_offset & \ - GENMASK(((reg)->bit_width), 0))) +#define MASK_VAL(reg, val) (((val) >> (reg)->bit_offset) & \ + GENMASK(((reg)->bit_width) - 1, 0)) static ssize_t show_feedback_ctrs(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -1002,14 +1002,14 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) } *val = 0; + size = GET_BIT_WIDTH(reg); if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { - u32 width = GET_BIT_WIDTH(reg); u32 val_u32; acpi_status status; status = acpi_os_read_port((acpi_io_address)reg->address, - &val_u32, width); + &val_u32, size); if (ACPI_FAILURE(status)) { pr_debug("Error: Failed to read SystemIO port %llx\n", reg->address); @@ -1018,17 +1018,22 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *val = val_u32; return 0; - } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) { + /* + * For registers in PCC space, the register size is determined + * by the bit width field; the access size is used to indicate + * the PCC subspace id. + */ + size = reg->bit_width; vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); + } else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) return cpc_read_ffh(cpu, reg, val); else return acpi_os_read_memory((acpi_physical_address)reg->address, - val, reg->bit_width); - - size = GET_BIT_WIDTH(reg); + val, size); switch (size) { case 8: @@ -1044,8 +1049,13 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) *val = readq_relaxed(vaddr); break; default: - pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n", - reg->bit_width, pcc_ss_id); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + pr_debug("Error: Cannot read %u bit width from system memory: 0x%llx\n", + size, reg->address); + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + pr_debug("Error: Cannot read %u bit width from PCC for ss: %d\n", + size, pcc_ss_id); + } return -EFAULT; } @@ -1063,12 +1073,13 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; + size = GET_BIT_WIDTH(reg); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) { - u32 width = GET_BIT_WIDTH(reg); acpi_status status; status = acpi_os_write_port((acpi_io_address)reg->address, - (u32)val, width); + (u32)val, size); if (ACPI_FAILURE(status)) { pr_debug("Error: Failed to write SystemIO port %llx\n", reg->address); @@ -1076,17 +1087,22 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) } return 0; - } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM && pcc_ss_id >= 0) { + /* + * For registers in PCC space, the register size is determined + * by the bit width field; the access size is used to indicate + * the PCC subspace id. + */ + size = reg->bit_width; vaddr = GET_PCC_VADDR(reg->address, pcc_ss_id); + } else if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) vaddr = reg_res->sys_mem_vaddr; else if (reg->space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) return cpc_write_ffh(cpu, reg, val); else return acpi_os_write_memory((acpi_physical_address)reg->address, - val, reg->bit_width); - - size = GET_BIT_WIDTH(reg); + val, size); if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) val = MASK_VAL(reg, val); @@ -1105,8 +1121,13 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) writeq_relaxed(val, vaddr); break; default: - pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n", - reg->bit_width, pcc_ss_id); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + pr_debug("Error: Cannot write %u bit width to system memory: 0x%llx\n", + size, reg->address); + } else if (reg->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) { + pr_debug("Error: Cannot write %u bit width to PCC for ss: %d\n", + size, pcc_ss_id); + } ret_val = -EFAULT; break; } diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index cd84af23f7eac8..dd0b40b9bbe8be 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -492,16 +492,14 @@ static int lps0_device_attach(struct acpi_device *adev, unsigned int func_mask; /* - * Avoid evaluating the same _DSM function for two - * different UUIDs and prioritize the MSFT one. + * Log a message if the _DSM function sets for two + * different UUIDs overlap. */ func_mask = lps0_dsm_func_mask & lps0_dsm_func_mask_microsoft; - if (func_mask) { + if (func_mask) acpi_handle_info(adev->handle, "Duplicate LPS0 _DSM functions (mask: 0x%x)\n", func_mask); - lps0_dsm_func_mask &= ~func_mask; - } } } diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 5cb425f6f02d4b..0a34dd3c4f38d2 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -2839,6 +2839,43 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val) EXPORT_SYMBOL_GPL(regmap_read); /** + * regmap_read_bypassed() - Read a value from a single register direct + * from the device, bypassing the cache + * + * @map: Register map to read from + * @reg: Register to be read from + * @val: Pointer to store read value + * + * A value of zero will be returned on success, a negative errno will + * be returned in error cases. + */ +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val) +{ + int ret; + bool bypass, cache_only; + + if (!IS_ALIGNED(reg, map->reg_stride)) + return -EINVAL; + + map->lock(map->lock_arg); + + bypass = map->cache_bypass; + cache_only = map->cache_only; + map->cache_bypass = true; + map->cache_only = false; + + ret = _regmap_read(map, reg, val); + + map->cache_bypass = bypass; + map->cache_only = cache_only; + + map->unlock(map->lock_arg); + + return ret; +} +EXPORT_SYMBOL_GPL(regmap_read_bypassed); + +/** * regmap_raw_read() - Read raw data from the device * * @map: Register map to read from diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index f0639df6cd184a..4cf38f7d3e0a3d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1568,7 +1568,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, * Corresponding ZRAM slot should be locked. */ static int zram_recompress(struct zram *zram, u32 index, struct page *page, - u32 threshold, u32 prio, u32 prio_max) + u64 *num_recomp_pages, u32 threshold, u32 prio, + u32 prio_max) { struct zcomp_strm *zstrm = NULL; unsigned long handle_old; @@ -1645,6 +1646,15 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, if (!zstrm) return 0; + /* + * Decrement the limit (if set) on pages we can recompress, even + * when current recompression was unsuccessful or did not compress + * the page below the threshold, because we still spent resources + * on it. + */ + if (*num_recomp_pages) + *num_recomp_pages -= 1; + if (class_index_new >= class_index_old) { /* * Secondary algorithms failed to re-compress the page @@ -1710,6 +1720,7 @@ static ssize_t recompress_store(struct device *dev, struct zram *zram = dev_to_zram(dev); unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; char *args, *param, *val, *algo = NULL; + u64 num_recomp_pages = ULLONG_MAX; u32 mode = 0, threshold = 0; unsigned long index; struct page *page; @@ -1732,6 +1743,17 @@ static ssize_t recompress_store(struct device *dev, continue; } + if (!strcmp(param, "max_pages")) { + /* + * Limit the number of entries (pages) we attempt to + * recompress. + */ + ret = kstrtoull(val, 10, &num_recomp_pages); + if (ret) + return ret; + continue; + } + if (!strcmp(param, "threshold")) { /* * We will re-compress only idle objects equal or @@ -1788,6 +1810,9 @@ static ssize_t recompress_store(struct device *dev, for (index = 0; index < nr_pages; index++) { int err = 0; + if (!num_recomp_pages) + break; + zram_slot_lock(zram, index); if (!zram_allocated(zram, index)) @@ -1807,8 +1832,8 @@ static ssize_t recompress_store(struct device *dev, zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE)) goto next; - err = zram_recompress(zram, index, page, threshold, - prio, prio_max); + err = zram_recompress(zram, index, page, &num_recomp_pages, + threshold, prio, prio_max); next: zram_slot_unlock(zram, index); if (err) { diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index ac8ebccd350756..812fd2a8f853e1 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 19cfc342fc7bbb..216826c31ee34f 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 06e915b57283f8..e3946f7b736e3c 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 ecbc52eaf10109..0c9c9ee56592dc 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 e9cc8b4786fbfb..6874b72ec59d8d 100644 --- a/drivers/cache/sifive_ccache.c +++ b/drivers/cache/sifive_ccache.c @@ -290,7 +290,7 @@ static int __init sifive_ccache_init(void) struct device_node *np; struct resource res; const struct of_device_id *match; - unsigned long quirks; + unsigned long quirks __maybe_unused; int rc; np = of_find_matching_node_and_match(NULL, sifive_ccache_ids, &match); diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 3c6670cf905f11..9b80e622ae80a8 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -544,7 +544,7 @@ static unsigned long get_unmapped_area_zero(struct file *file, } /* Otherwise flags & MAP_PRIVATE: with no shmem object beneath it */ - return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags); #else return -ENOSYS; #endif diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 8602c02047d048..45c5255bcd11ba 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -768,6 +768,7 @@ static struct clk_smd_rpm *msm8976_clks[] = { static const struct rpm_smd_clk_desc rpm_clk_msm8976 = { .clks = msm8976_clks, + .num_clks = ARRAY_SIZE(msm8976_clks), .icc_clks = bimc_pcnoc_snoc_smmnoc_icc_clks, .num_icc_clks = ARRAY_SIZE(bimc_pcnoc_snoc_smmnoc_icc_clks), }; diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c index e7a4068b9f3906..df9618ab7eea1f 100644 --- a/drivers/clk/qcom/gdsc.c +++ b/drivers/clk/qcom/gdsc.c @@ -487,9 +487,14 @@ int gdsc_register(struct gdsc_desc *desc, if (!scs[i] || !scs[i]->supply) continue; - scs[i]->rsupply = devm_regulator_get(dev, scs[i]->supply); - if (IS_ERR(scs[i]->rsupply)) - return PTR_ERR(scs[i]->rsupply); + scs[i]->rsupply = devm_regulator_get_optional(dev, scs[i]->supply); + if (IS_ERR(scs[i]->rsupply)) { + ret = PTR_ERR(scs[i]->rsupply); + if (ret != -ENODEV) + return ret; + + scs[i]->rsupply = NULL; + } } data->num_domains = num; diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c index 3484e6cc80ad10..503c6f5b20d5c5 100644 --- a/drivers/clk/samsung/clk-exynos-clkout.c +++ b/drivers/clk/samsung/clk-exynos-clkout.c @@ -13,9 +13,9 @@ #include <linux/io.h> #include <linux/of.h> #include <linux/of_address.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pm.h> -#include <linux/property.h> #define EXYNOS_CLKOUT_NR_CLKS 1 #define EXYNOS_CLKOUT_PARENTS 32 @@ -84,17 +84,24 @@ MODULE_DEVICE_TABLE(of, exynos_clkout_ids); static int exynos_clkout_match_parent_dev(struct device *dev, u32 *mux_mask) { const struct exynos_clkout_variant *variant; + const struct of_device_id *match; if (!dev->parent) { dev_err(dev, "not instantiated from MFD\n"); return -EINVAL; } - variant = device_get_match_data(dev->parent); - if (!variant) { + /* + * 'exynos_clkout_ids' arrays is not the ids array matched by + * the dev->parent driver, so of_device_get_match_data() or + * device_get_match_data() cannot be used here. + */ + match = of_match_device(exynos_clkout_ids, dev->parent); + if (!match) { dev_err(dev, "cannot match parent device\n"); return -EINVAL; } + variant = match->data; *mux_mask = variant->mux_mask; diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index f0f54aeccc872b..65185c9fa00134 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -946,25 +946,22 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds, struct cxl_memdev *cxlmd = mds->cxlds.cxlmd; struct device *dev = mds->cxlds.dev; struct cxl_get_event_payload *payload; - struct cxl_mbox_cmd mbox_cmd; u8 log_type = type; u16 nr_rec; mutex_lock(&mds->event.log_lock); payload = mds->event.buf; - mbox_cmd = (struct cxl_mbox_cmd) { - .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, - .payload_in = &log_type, - .size_in = sizeof(log_type), - .payload_out = payload, - .min_out = struct_size(payload, records, 0), - }; - do { int rc, i; - - mbox_cmd.size_out = mds->payload_size; + struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_GET_EVENT_RECORD, + .payload_in = &log_type, + .size_in = sizeof(log_type), + .payload_out = payload, + .size_out = mds->payload_size, + .min_out = struct_size(payload, records, 0), + }; rc = cxl_internal_send_cmd(mds, &mbox_cmd); if (rc) { @@ -1297,7 +1294,6 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlmd->cxlds); struct cxl_mbox_poison_out *po; struct cxl_mbox_poison_in pi; - struct cxl_mbox_cmd mbox_cmd; int nr_records = 0; int rc; @@ -1309,16 +1305,16 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, pi.offset = cpu_to_le64(offset); pi.length = cpu_to_le64(len / CXL_POISON_LEN_MULT); - mbox_cmd = (struct cxl_mbox_cmd) { - .opcode = CXL_MBOX_OP_GET_POISON, - .size_in = sizeof(pi), - .payload_in = &pi, - .size_out = mds->payload_size, - .payload_out = po, - .min_out = struct_size(po, record, 0), - }; - do { + struct cxl_mbox_cmd mbox_cmd = (struct cxl_mbox_cmd){ + .opcode = CXL_MBOX_OP_GET_POISON, + .size_in = sizeof(pi), + .payload_in = &pi, + .size_out = mds->payload_size, + .payload_out = po, + .min_out = struct_size(po, record, 0), + }; + rc = cxl_internal_send_cmd(mds, &mbox_cmd); if (rc) break; diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 93ebedc5ec8ca3..47c126d37b59ab 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -329,14 +329,14 @@ static unsigned long dax_get_unmapped_area(struct file *filp, if ((off + len_align) < off) goto out; - addr_align = current->mm->get_unmapped_area(filp, addr, len_align, - pgoff, flags); + addr_align = mm_get_unmapped_area(current->mm, filp, addr, len_align, + pgoff, flags); if (!IS_ERR_VALUE(addr_align)) { addr_align += (off - addr_align) & (align - 1); return addr_align; } out: - return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags); } static const struct address_space_operations dev_dax_aops = { diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index 42ee360cf4e3db..4fe9d040e37545 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -55,36 +55,14 @@ static LIST_HEAD(kmem_memory_types); static struct memory_dev_type *kmem_find_alloc_memory_type(int adist) { - bool found = false; - struct memory_dev_type *mtype; - - mutex_lock(&kmem_memory_type_lock); - list_for_each_entry(mtype, &kmem_memory_types, list) { - if (mtype->adistance == adist) { - found = true; - break; - } - } - if (!found) { - mtype = alloc_memory_type(adist); - if (!IS_ERR(mtype)) - list_add(&mtype->list, &kmem_memory_types); - } - mutex_unlock(&kmem_memory_type_lock); - - return mtype; + guard(mutex)(&kmem_memory_type_lock); + return mt_find_alloc_memory_type(adist, &kmem_memory_types); } static void kmem_put_memory_types(void) { - struct memory_dev_type *mtype, *mtn; - - mutex_lock(&kmem_memory_type_lock); - list_for_each_entry_safe(mtype, mtn, &kmem_memory_types, list) { - list_del(&mtype->list); - put_memory_type(mtype); - } - mutex_unlock(&kmem_memory_type_lock); + guard(mutex)(&kmem_memory_type_lock); + mt_put_memory_types(&kmem_memory_types); } static int dev_dax_kmem_probe(struct dev_dax *dev_dax) diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c index 78a938969d7d76..1398814d8fbb63 100644 --- a/drivers/dma/idma64.c +++ b/drivers/dma/idma64.c @@ -171,6 +171,10 @@ static irqreturn_t idma64_irq(int irq, void *dev) u32 status_err; unsigned short i; + /* Since IRQ may be shared, check if DMA controller is powered on */ + if (status == GENMASK(31, 0)) + return IRQ_NONE; + dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status); /* Check if we have any interrupt from the DMA controller */ diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 8078ab9acfbc37..c095a2c8f65956 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -342,7 +342,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) if (!evl) return; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = status.tail; h = status.head; @@ -354,9 +354,8 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) set_bit(h, evl->bmap); h = (h + 1) % size; } - spin_unlock(&evl->lock); - drain_workqueue(wq->wq); + mutex_unlock(&evl->lock); } static int idxd_cdev_release(struct inode *node, struct file *filep) diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c index f3f25ee676f30e..ad4245cb301d50 100644 --- a/drivers/dma/idxd/debugfs.c +++ b/drivers/dma/idxd/debugfs.c @@ -66,7 +66,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d) if (!evl || !evl->log) return 0; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = evl_status.tail; @@ -87,7 +87,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d) dump_event_entry(idxd, s, i, &count, processed); } - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); return 0; } diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index ecfdf4a8f1f838..c41ef195eeb9f2 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -775,7 +775,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) goto err_alloc; } - spin_lock(&evl->lock); + mutex_lock(&evl->lock); evl->log = addr; evl->dma = dma_addr; evl->log_size = size; @@ -796,7 +796,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) gencfg.evl_en = 1; iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); return 0; err_alloc: @@ -819,7 +819,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd) if (!gencfg.evl_en) return; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); gencfg.evl_en = 0; iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); @@ -836,7 +836,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd) evl_dma = evl->dma; evl->log = NULL; evl->size = IDXD_EVL_SIZE_MIN; - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); dma_free_coherent(dev, evl_log_size, evl_log, evl_dma); } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index a4099a1e2340fd..7b98944135eb44 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -293,7 +293,7 @@ struct idxd_driver_data { struct idxd_evl { /* Lock to protect event log access. */ - spinlock_t lock; + struct mutex lock; void *log; dma_addr_t dma; /* Total size of event log = number of entries * entry size. */ diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 4954adc6bb609e..264c4e47d7cca5 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -354,7 +354,7 @@ static int idxd_init_evl(struct idxd_device *idxd) if (!evl) return -ENOMEM; - spin_lock_init(&evl->lock); + mutex_init(&evl->lock); evl->size = IDXD_EVL_SIZE_MIN; idxd_name = dev_name(idxd_confdev(idxd)); diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index 348aa21389a9fc..8dc029c8655151 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -363,7 +363,7 @@ static void process_evl_entries(struct idxd_device *idxd) evl_status.bits = 0; evl_status.int_pending = 1; - spin_lock(&evl->lock); + mutex_lock(&evl->lock); /* Clear interrupt pending bit */ iowrite32(evl_status.bits_upper32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32)); @@ -380,7 +380,7 @@ static void process_evl_entries(struct idxd_device *idxd) evl_status.head = h; iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET); - spin_unlock(&evl->lock); + mutex_unlock(&evl->lock); } irqreturn_t idxd_misc_thread(int vec, void *data) diff --git a/drivers/dma/idxd/perfmon.c b/drivers/dma/idxd/perfmon.c index fdda6d60426295..5e94247e1ea703 100644 --- a/drivers/dma/idxd/perfmon.c +++ b/drivers/dma/idxd/perfmon.c @@ -528,14 +528,11 @@ static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node) return 0; target = cpumask_any_but(cpu_online_mask, cpu); - /* migrate events if there is a valid target */ - if (target < nr_cpu_ids) + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &perfmon_dsa_cpu_mask); - else - target = -1; - - perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target); + perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target); + } return 0; } diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c index 4e76c4ec2d3966..e001f4f7aa640f 100644 --- a/drivers/dma/owl-dma.c +++ b/drivers/dma/owl-dma.c @@ -250,7 +250,7 @@ static void pchan_update(struct owl_dma_pchan *pchan, u32 reg, else regval &= ~val; - writel(val, pchan->base + reg); + writel(regval, pchan->base + reg); } static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data) @@ -274,7 +274,7 @@ static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state) else regval &= ~val; - writel(val, od->base + reg); + writel(regval, od->base + reg); } static void dma_writel(struct owl_dma *od, u32 reg, u32 data) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 5f6d7f1e095f90..ad8e3da1b2cd22 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1053,9 +1053,6 @@ static bool _trigger(struct pl330_thread *thrd) thrd->req_running = idx; - if (desc->rqtype == DMA_MEM_TO_DEV || desc->rqtype == DMA_DEV_TO_MEM) - UNTIL(thrd, PL330_STATE_WFP); - return true; } diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index 88547a23825b18..3642508e88bb22 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -746,6 +746,9 @@ static int tegra_dma_get_residual(struct tegra_dma_channel *tdc) bytes_xfer = dma_desc->bytes_xfer + sg_req[dma_desc->sg_idx].len - (wcount * 4); + if (dma_desc->bytes_req == bytes_xfer) + return 0; + residual = dma_desc->bytes_req - (bytes_xfer % dma_desc->bytes_req); return residual; diff --git a/drivers/dma/xilinx/xdma-regs.h b/drivers/dma/xilinx/xdma-regs.h index 98f5f6fb9ff9c7..6ad08878e93862 100644 --- a/drivers/dma/xilinx/xdma-regs.h +++ b/drivers/dma/xilinx/xdma-regs.h @@ -117,6 +117,9 @@ struct xdma_hw_desc { CHAN_CTRL_IE_WRITE_ERROR | \ CHAN_CTRL_IE_DESC_ERROR) +/* bits of the channel status register */ +#define XDMA_CHAN_STATUS_BUSY BIT(0) + #define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START #define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH | \ diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 170017ff2aad6e..313b217388fe95 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -71,6 +71,8 @@ struct xdma_chan { enum dma_transfer_direction dir; struct dma_slave_config cfg; u32 irq; + struct completion last_interrupt; + bool stop_requested; }; /** @@ -376,6 +378,8 @@ static int xdma_xfer_start(struct xdma_chan *xchan) return ret; xchan->busy = true; + xchan->stop_requested = false; + reinit_completion(&xchan->last_interrupt); return 0; } @@ -387,7 +391,6 @@ static int xdma_xfer_start(struct xdma_chan *xchan) static int xdma_xfer_stop(struct xdma_chan *xchan) { int ret; - u32 val; struct xdma_device *xdev = xchan->xdev_hdl; /* clear run stop bit to prevent any further auto-triggering */ @@ -395,13 +398,7 @@ static int xdma_xfer_stop(struct xdma_chan *xchan) CHAN_CTRL_RUN_STOP); if (ret) return ret; - - /* Clear the channel status register */ - ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &val); - if (ret) - return ret; - - return 0; + return ret; } /** @@ -474,6 +471,8 @@ static int xdma_alloc_channels(struct xdma_device *xdev, xchan->xdev_hdl = xdev; xchan->base = base + i * XDMA_CHAN_STRIDE; xchan->dir = dir; + xchan->stop_requested = false; + init_completion(&xchan->last_interrupt); ret = xdma_channel_init(xchan); if (ret) @@ -521,6 +520,7 @@ static int xdma_terminate_all(struct dma_chan *chan) spin_lock_irqsave(&xdma_chan->vchan.lock, flags); xdma_chan->busy = false; + xdma_chan->stop_requested = true; vd = vchan_next_desc(&xdma_chan->vchan); if (vd) { list_del(&vd->node); @@ -542,17 +542,26 @@ static int xdma_terminate_all(struct dma_chan *chan) static void xdma_synchronize(struct dma_chan *chan) { struct xdma_chan *xdma_chan = to_xdma_chan(chan); + struct xdma_device *xdev = xdma_chan->xdev_hdl; + int st = 0; + + /* If the engine continues running, wait for the last interrupt */ + regmap_read(xdev->rmap, xdma_chan->base + XDMA_CHAN_STATUS, &st); + if (st & XDMA_CHAN_STATUS_BUSY) + wait_for_completion_timeout(&xdma_chan->last_interrupt, msecs_to_jiffies(1000)); vchan_synchronize(&xdma_chan->vchan); } /** - * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses - * @sw_desc: tx descriptor state container - * @src_addr: Value for a ->src_addr field of a first descriptor - * @dst_addr: Value for a ->dst_addr field of a first descriptor - * @size: Total size of a contiguous memory block - * @filled_descs_num: Number of filled hardware descriptors for corresponding sw_desc + * xdma_fill_descs() - Fill hardware descriptors for one contiguous memory chunk. + * More than one descriptor will be used if the size is bigger + * than XDMA_DESC_BLEN_MAX. + * @sw_desc: Descriptor container + * @src_addr: First value for the ->src_addr field + * @dst_addr: First value for the ->dst_addr field + * @size: Size of the contiguous memory block + * @filled_descs_num: Index of the first descriptor to take care of in @sw_desc */ static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr, u64 dst_addr, u32 size, u32 filled_descs_num) @@ -704,7 +713,7 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address, desc_num = 0; for (i = 0; i < periods; i++) { desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num); - addr += i * period_size; + addr += period_size; } tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags); @@ -876,6 +885,9 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id) u32 st; bool repeat_tx; + if (xchan->stop_requested) + complete(&xchan->last_interrupt); + spin_lock(&xchan->vchan.lock); /* get submitted request */ diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index b82815e64d24e8..eb0637d90342a6 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -214,7 +214,8 @@ struct xilinx_dpdma_tx_desc { * @running: true if the channel is running * @first_frame: flag for the first frame of stream * @video_group: flag if multi-channel operation is needed for video channels - * @lock: lock to access struct xilinx_dpdma_chan + * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before + * @vchan.lock, if both are to be held. * @desc_pool: descriptor allocation pool * @err_task: error IRQ bottom half handler * @desc: References to descriptors being processed @@ -1097,12 +1098,14 @@ static void xilinx_dpdma_chan_vsync_irq(struct xilinx_dpdma_chan *chan) * Complete the active descriptor, if any, promote the pending * descriptor to active, and queue the next transfer, if any. */ + spin_lock(&chan->vchan.lock); if (chan->desc.active) vchan_cookie_complete(&chan->desc.active->vdesc); chan->desc.active = pending; chan->desc.pending = NULL; xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); out: spin_unlock_irqrestore(&chan->lock, flags); @@ -1264,10 +1267,12 @@ static void xilinx_dpdma_issue_pending(struct dma_chan *dchan) struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan); unsigned long flags; - spin_lock_irqsave(&chan->vchan.lock, flags); + spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); if (vchan_issue_pending(&chan->vchan)) xilinx_dpdma_chan_queue_transfer(chan); - spin_unlock_irqrestore(&chan->vchan.lock, flags); + spin_unlock(&chan->vchan.lock); + spin_unlock_irqrestore(&chan->lock, flags); } static int xilinx_dpdma_config(struct dma_chan *dchan, @@ -1495,7 +1500,9 @@ static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t) XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id); spin_lock_irqsave(&chan->lock, flags); + spin_lock(&chan->vchan.lock); xilinx_dpdma_chan_queue_transfer(chan); + spin_unlock(&chan->vchan.lock); spin_unlock_irqrestore(&chan->lock, flags); } diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 64eaca80d736c5..d0f6693ca14262 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/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c index 5b439d04079c84..50f6503fe49f5e 100644 --- a/drivers/firmware/efi/unaccepted_memory.c +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -4,6 +4,7 @@ #include <linux/memblock.h> #include <linux/spinlock.h> #include <linux/crash_dump.h> +#include <linux/nmi.h> #include <asm/unaccepted_memory.h> /* Protects unaccepted memory bitmap and accepting_list */ @@ -149,6 +150,9 @@ retry: } list_del(&range.list); + + touch_softlockup_watchdog(); + spin_unlock_irqrestore(&unaccepted_memory_lock, flags); } diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index fbeeaee4ac8560..835a19a7a3a09e 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -206,10 +206,12 @@ static int mpfs_auto_update_verify_image(struct fw_upload *fw_uploader) if (ret | response->resp_status) { dev_warn(priv->dev, "Verification of Upgrade Image failed!\n"); ret = ret ? ret : -EBADMSG; + goto free_message; } dev_info(priv->dev, "Verification of Upgrade Image passed!\n"); +free_message: devm_kfree(priv->dev, message); free_response: devm_kfree(priv->dev, response); @@ -265,7 +267,7 @@ static int mpfs_auto_update_set_image_address(struct mpfs_auto_update_priv *priv AUTO_UPDATE_DIRECTORY_WIDTH); memset(buffer + AUTO_UPDATE_BLANK_DIRECTORY, 0x0, AUTO_UPDATE_DIRECTORY_WIDTH); - dev_info(priv->dev, "Writing the image address (%x) to the flash directory (%llx)\n", + dev_info(priv->dev, "Writing the image address (0x%x) to the flash directory (0x%llx)\n", image_address, directory_address); ret = mtd_write(priv->flash, 0x0, erase_size, &bytes_written, (u_char *)buffer); @@ -313,7 +315,7 @@ static int mpfs_auto_update_write_bitstream(struct fw_upload *fw_uploader, const erase.len = round_up(size, (size_t)priv->flash->erasesize); erase.addr = image_address; - dev_info(priv->dev, "Erasing the flash at address (%x)\n", image_address); + dev_info(priv->dev, "Erasing the flash at address (0x%x)\n", image_address); ret = mtd_erase(priv->flash, &erase); if (ret) goto out; @@ -323,7 +325,7 @@ static int mpfs_auto_update_write_bitstream(struct fw_upload *fw_uploader, const * will do all of that itself - including verifying that the bitstream * is valid. */ - dev_info(priv->dev, "Writing the image to the flash at address (%x)\n", image_address); + dev_info(priv->dev, "Writing the image to the flash at address (0x%x)\n", image_address); ret = mtd_write(priv->flash, (loff_t)image_address, size, &bytes_written, data); if (ret) goto out; diff --git a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c index 32188f098ef349..bc550ad0dbe0c7 100644 --- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c +++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c @@ -221,6 +221,19 @@ struct qsee_rsp_uefi_query_variable_info { * alignment of 8 bytes (64 bits) for GUIDs. Our definition of efi_guid_t, * however, has an alignment of 4 byte (32 bits). So far, this seems to work * fine here. See also the comment on the typedef of efi_guid_t. + * + * Note: It looks like uefisecapp is quite picky about how the memory passed to + * it is structured and aligned. In particular the request/response setup used + * for QSEE_CMD_UEFI_GET_VARIABLE. While qcom_qseecom_app_send(), in theory, + * accepts separate buffers/addresses for the request and response parts, in + * practice, however, it seems to expect them to be both part of a larger + * contiguous block. We initially allocated separate buffers for the request + * and response but this caused the QSEE_CMD_UEFI_GET_VARIABLE command to + * either not write any response to the response buffer or outright crash the + * device. Therefore, we now allocate a single contiguous block of DMA memory + * for both and properly align the data using the macros below. In particular, + * request and response structs are aligned at 8 byte (via __reqdata_offs()), + * following the driver that this has been reverse-engineered from. */ #define qcuefi_buf_align_fields(fields...) \ ({ \ @@ -244,6 +257,12 @@ struct qsee_rsp_uefi_query_variable_info { #define __array_offs(type, count, offset) \ __field_impl(sizeof(type) * (count), __alignof__(type), offset) +#define __array_offs_aligned(type, count, align, offset) \ + __field_impl(sizeof(type) * (count), align, offset) + +#define __reqdata_offs(size, offset) \ + __array_offs_aligned(u8, size, 8, offset) + #define __array(type, count) __array_offs(type, count, NULL) #define __field_offs(type, offset) __array_offs(type, 1, offset) #define __field(type) __array_offs(type, 1, NULL) @@ -277,10 +296,15 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e unsigned long buffer_size = *data_size; efi_status_t efi_status = EFI_SUCCESS; unsigned long name_length; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t guid_offs; size_t name_offs; size_t req_size; size_t rsp_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name || !guid) @@ -304,17 +328,19 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e __array(u8, buffer_size) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(rsp_size, &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(rsp_size, GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_GET_VARIABLE; req_data->data_size = buffer_size; @@ -332,7 +358,9 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e memcpy(((void *)req_data) + req_data->guid_offset, guid, req_data->guid_size); - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, rsp_size); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -407,9 +435,7 @@ static efi_status_t qsee_uefi_get_variable(struct qcuefi_client *qcuefi, const e memcpy(data, ((void *)rsp_data) + rsp_data->data_offset, rsp_data->data_size); out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -422,10 +448,15 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e struct qsee_rsp_uefi_set_variable *rsp_data; efi_status_t efi_status = EFI_SUCCESS; unsigned long name_length; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t name_offs; size_t guid_offs; size_t data_offs; size_t req_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name || !guid) @@ -450,17 +481,19 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e __array_offs(u8, data_size, &data_offs) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(sizeof(*rsp_data), &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(sizeof(*rsp_data), GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_SET_VARIABLE; req_data->attributes = attributes; @@ -483,8 +516,9 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e if (data_size) memcpy(((void *)req_data) + req_data->data_offset, data, req_data->data_size); - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, - sizeof(*rsp_data)); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, sizeof(*rsp_data)); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -507,9 +541,7 @@ static efi_status_t qsee_uefi_set_variable(struct qcuefi_client *qcuefi, const e } out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -521,10 +553,15 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, struct qsee_req_uefi_get_next_variable *req_data; struct qsee_rsp_uefi_get_next_variable *rsp_data; efi_status_t efi_status = EFI_SUCCESS; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; size_t guid_offs; size_t name_offs; size_t req_size; size_t rsp_size; + size_t req_offs; + size_t rsp_offs; ssize_t status; if (!name_size || !name || !guid) @@ -545,17 +582,19 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, __array(*name, *name_size / sizeof(*name)) ); - req_data = kzalloc(req_size, GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(req_size, &req_offs) + __reqdata_offs(rsp_size, &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(rsp_size, GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_GET_NEXT_VARIABLE; req_data->guid_offset = guid_offs; @@ -572,7 +611,9 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, goto out_free; } - status = qcom_qseecom_app_send(qcuefi->client, req_data, req_size, rsp_data, rsp_size); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, req_size, + cmd_buf_dma + rsp_offs, rsp_size); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -645,9 +686,7 @@ static efi_status_t qsee_uefi_get_next_variable(struct qcuefi_client *qcuefi, } out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } @@ -659,26 +698,34 @@ static efi_status_t qsee_uefi_query_variable_info(struct qcuefi_client *qcuefi, struct qsee_req_uefi_query_variable_info *req_data; struct qsee_rsp_uefi_query_variable_info *rsp_data; efi_status_t efi_status = EFI_SUCCESS; + dma_addr_t cmd_buf_dma; + size_t cmd_buf_size; + void *cmd_buf; + size_t req_offs; + size_t rsp_offs; int status; - req_data = kzalloc(sizeof(*req_data), GFP_KERNEL); - if (!req_data) { + cmd_buf_size = qcuefi_buf_align_fields( + __reqdata_offs(sizeof(*req_data), &req_offs) + __reqdata_offs(sizeof(*rsp_data), &rsp_offs) + ); + + cmd_buf = qseecom_dma_alloc(qcuefi->client, cmd_buf_size, &cmd_buf_dma, GFP_KERNEL); + if (!cmd_buf) { efi_status = EFI_OUT_OF_RESOURCES; goto out; } - rsp_data = kzalloc(sizeof(*rsp_data), GFP_KERNEL); - if (!rsp_data) { - efi_status = EFI_OUT_OF_RESOURCES; - goto out_free_req; - } + req_data = cmd_buf + req_offs; + rsp_data = cmd_buf + rsp_offs; req_data->command_id = QSEE_CMD_UEFI_QUERY_VARIABLE_INFO; req_data->attributes = attr; req_data->length = sizeof(*req_data); - status = qcom_qseecom_app_send(qcuefi->client, req_data, sizeof(*req_data), rsp_data, - sizeof(*rsp_data)); + status = qcom_qseecom_app_send(qcuefi->client, + cmd_buf_dma + req_offs, sizeof(*req_data), + cmd_buf_dma + rsp_offs, sizeof(*rsp_data)); if (status) { efi_status = EFI_DEVICE_ERROR; goto out_free; @@ -711,9 +758,7 @@ static efi_status_t qsee_uefi_query_variable_info(struct qcuefi_client *qcuefi, *max_variable_size = rsp_data->max_variable_size; out_free: - kfree(rsp_data); -out_free_req: - kfree(req_data); + qseecom_dma_free(qcuefi->client, cmd_buf_size, cmd_buf, cmd_buf_dma); out: return efi_status; } diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c index 520de9b5633abc..90283f160a2286 100644 --- a/drivers/firmware/qcom/qcom_scm.c +++ b/drivers/firmware/qcom/qcom_scm.c @@ -1576,9 +1576,9 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_get_id); /** * qcom_scm_qseecom_app_send() - Send to and receive data from a given QSEE app. * @app_id: The ID of the target app. - * @req: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given ID and read back @@ -1589,33 +1589,13 @@ EXPORT_SYMBOL_GPL(qcom_scm_qseecom_app_get_id); * * Return: Zero on success, nonzero on failure. */ -int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, - size_t rsp_size) +int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { struct qcom_scm_qseecom_resp res = {}; struct qcom_scm_desc desc = {}; - dma_addr_t req_phys; - dma_addr_t rsp_phys; int status; - /* Map request buffer */ - req_phys = dma_map_single(__scm->dev, req, req_size, DMA_TO_DEVICE); - status = dma_mapping_error(__scm->dev, req_phys); - if (status) { - dev_err(__scm->dev, "qseecom: failed to map request buffer\n"); - return status; - } - - /* Map response buffer */ - rsp_phys = dma_map_single(__scm->dev, rsp, rsp_size, DMA_FROM_DEVICE); - status = dma_mapping_error(__scm->dev, rsp_phys); - if (status) { - dma_unmap_single(__scm->dev, req_phys, req_size, DMA_TO_DEVICE); - dev_err(__scm->dev, "qseecom: failed to map response buffer\n"); - return status; - } - - /* Set up SCM call data */ desc.owner = QSEECOM_TZ_OWNER_TZ_APPS; desc.svc = QSEECOM_TZ_SVC_APP_ID_PLACEHOLDER; desc.cmd = QSEECOM_TZ_CMD_APP_SEND; @@ -1623,18 +1603,13 @@ int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, QCOM_SCM_RW, QCOM_SCM_VAL, QCOM_SCM_RW, QCOM_SCM_VAL); desc.args[0] = app_id; - desc.args[1] = req_phys; + desc.args[1] = req; desc.args[2] = req_size; - desc.args[3] = rsp_phys; + desc.args[3] = rsp; desc.args[4] = rsp_size; - /* Perform call */ status = qcom_scm_qseecom_call(&desc, &res); - /* Unmap buffers */ - dma_unmap_single(__scm->dev, rsp_phys, rsp_size, DMA_FROM_DEVICE); - dma_unmap_single(__scm->dev, req_phys, req_size, DMA_TO_DEVICE); - if (status) return status; diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c index 98b8fd16183e41..80cac3a5f97678 100644 --- a/drivers/fpga/dfl-pci.c +++ b/drivers/fpga/dfl-pci.c @@ -78,6 +78,7 @@ static void cci_pci_free_irq(struct pci_dev *pcidev) #define PCIE_DEVICE_ID_SILICOM_PAC_N5011 0x1001 #define PCIE_DEVICE_ID_INTEL_DFL 0xbcce /* PCI Subdevice ID for PCIE_DEVICE_ID_INTEL_DFL */ +#define PCIE_SUBDEVICE_ID_INTEL_D5005 0x138d #define PCIE_SUBDEVICE_ID_INTEL_N6000 0x1770 #define PCIE_SUBDEVICE_ID_INTEL_N6001 0x1771 #define PCIE_SUBDEVICE_ID_INTEL_C6100 0x17d4 @@ -102,6 +103,8 @@ static struct pci_device_id cci_pcie_id_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_SILICOM_DENMARK, PCIE_DEVICE_ID_SILICOM_PAC_N5010),}, {PCI_DEVICE(PCI_VENDOR_ID_SILICOM_DENMARK, PCIE_DEVICE_ID_SILICOM_PAC_N5011),}, {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL, + PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_D5005),}, + {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL, PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_N6000),}, {PCI_DEVICE_SUB(PCI_VENDOR_ID_INTEL, PCIE_DEVICE_ID_INTEL_DFL_VF, PCI_VENDOR_ID_INTEL, PCIE_SUBDEVICE_ID_INTEL_N6000),}, diff --git a/drivers/gpio/gpio-tangier.c b/drivers/gpio/gpio-tangier.c index b75e0b12087ac7..4b29abafecf6a4 100644 --- a/drivers/gpio/gpio-tangier.c +++ b/drivers/gpio/gpio-tangier.c @@ -195,7 +195,8 @@ static int tng_gpio_set_config(struct gpio_chip *chip, unsigned int offset, static void tng_irq_ack(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); void __iomem *gisr; u8 shift; @@ -227,7 +228,8 @@ static void tng_irq_unmask_mask(struct tng_gpio *priv, u32 gpio, bool unmask) static void tng_irq_mask(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); tng_irq_unmask_mask(priv, gpio, false); @@ -236,7 +238,8 @@ static void tng_irq_mask(struct irq_data *d) static void tng_irq_unmask(struct irq_data *d) { - struct tng_gpio *priv = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct tng_gpio *priv = gpiochip_get_data(gc); irq_hw_number_t gpio = irqd_to_hwirq(d); gpiochip_enable_irq(&priv->chip, gpio); diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index d87dd06db40d07..9130c691a2dd32 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -36,12 +36,6 @@ #define TEGRA186_GPIO_SCR_SEC_REN BIT(27) #define TEGRA186_GPIO_SCR_SEC_G1W BIT(9) #define TEGRA186_GPIO_SCR_SEC_G1R BIT(1) -#define TEGRA186_GPIO_FULL_ACCESS (TEGRA186_GPIO_SCR_SEC_WEN | \ - TEGRA186_GPIO_SCR_SEC_REN | \ - TEGRA186_GPIO_SCR_SEC_G1R | \ - TEGRA186_GPIO_SCR_SEC_G1W) -#define TEGRA186_GPIO_SCR_SEC_ENABLE (TEGRA186_GPIO_SCR_SEC_WEN | \ - TEGRA186_GPIO_SCR_SEC_REN) /* control registers */ #define TEGRA186_GPIO_ENABLE_CONFIG 0x00 @@ -177,10 +171,18 @@ static inline bool tegra186_gpio_is_accessible(struct tegra_gpio *gpio, unsigned value = __raw_readl(secure + TEGRA186_GPIO_SCR); - if ((value & TEGRA186_GPIO_SCR_SEC_ENABLE) == 0) - return true; + /* + * When SCR_SEC_[R|W]EN is unset, then we have full read/write access to all the + * registers for given GPIO pin. + * When SCR_SEC[R|W]EN is set, then there is need to further check the accompanying + * SCR_SEC_G1[R|W] bit to determine read/write access to all the registers for given + * GPIO pin. + */ - if ((value & TEGRA186_GPIO_FULL_ACCESS) == TEGRA186_GPIO_FULL_ACCESS) + if (((value & TEGRA186_GPIO_SCR_SEC_REN) == 0 || + ((value & TEGRA186_GPIO_SCR_SEC_REN) && (value & TEGRA186_GPIO_SCR_SEC_G1R))) && + ((value & TEGRA186_GPIO_SCR_SEC_WEN) == 0 || + ((value & TEGRA186_GPIO_SCR_SEC_WEN) && (value & TEGRA186_GPIO_SCR_SEC_G1W)))) return true; return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index df58a6a1a67ec5..2131de36e3dac0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1854,6 +1854,7 @@ err_node_allow: err_bo_create: amdgpu_amdkfd_unreserve_mem_limit(adev, aligned_size, flags, xcp_id); err_reserve_limit: + amdgpu_sync_free(&(*mem)->sync); mutex_destroy(&(*mem)->lock); if (gobj) drm_gem_object_put(gobj); @@ -2900,13 +2901,12 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * amdgpu_sync_create(&sync_obj); - /* Validate BOs and map them to GPUVM (update VM page tables). */ + /* Validate BOs managed by KFD */ list_for_each_entry(mem, &process_info->kfd_bo_list, validate_list) { struct amdgpu_bo *bo = mem->bo; uint32_t domain = mem->domain; - struct kfd_mem_attachment *attachment; struct dma_resv_iter cursor; struct dma_fence *fence; @@ -2931,6 +2931,25 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * goto validate_map_fail; } } + } + + if (failed_size) + pr_debug("0x%lx/0x%lx in system\n", failed_size, total_size); + + /* Validate PDs, PTs and evicted DMABuf imports last. Otherwise BO + * validations above would invalidate DMABuf imports again. + */ + ret = process_validate_vms(process_info, &exec.ticket); + if (ret) { + pr_debug("Validating VMs failed, ret: %d\n", ret); + goto validate_map_fail; + } + + /* Update mappings managed by KFD. */ + list_for_each_entry(mem, &process_info->kfd_bo_list, + validate_list) { + struct kfd_mem_attachment *attachment; + list_for_each_entry(attachment, &mem->attachments, list) { if (!attachment->is_mapped) continue; @@ -2947,18 +2966,6 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * } } - if (failed_size) - pr_debug("0x%lx/0x%lx in system\n", failed_size, total_size); - - /* Validate PDs, PTs and evicted DMABuf imports last. Otherwise BO - * validations above would invalidate DMABuf imports again. - */ - ret = process_validate_vms(process_info, &exec.ticket); - if (ret) { - pr_debug("Validating VMs failed, ret: %d\n", ret); - goto validate_map_fail; - } - /* Update mappings not managed by KFD */ list_for_each_entry(peer_vm, &process_info->vm_list_head, vm_list_node) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index a00cf4756ad0e2..1569bef030eac1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1132,6 +1132,7 @@ void amdgpu_mes_remove_ring(struct amdgpu_device *adev, return; amdgpu_mes_remove_hw_queue(adev, ring->hw_queue_id); + del_timer_sync(&ring->fence_drv.fallback_timer); amdgpu_ring_fini(ring); kfree(ring); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 2099159a693fa0..ce733e3cb35d05 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -605,6 +605,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev, else amdgpu_bo_placement_from_domain(bo, bp->domain); if (bp->type == ttm_bo_type_kernel) + bo->tbo.priority = 2; + else if (!(bp->flags & AMDGPU_GEM_CREATE_DISCARDABLE)) bo->tbo.priority = 1; if (!bp->destroy) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c index 0df97c3e3a700d..f7c73533e336fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umsch_mm.c @@ -774,6 +774,9 @@ static int umsch_mm_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (amdgpu_in_reset(adev) || adev->in_s0ix || adev->in_suspend) + return 0; + return umsch_mm_test(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c index 6695481f870f8a..c23d97d34b7ec5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c @@ -205,7 +205,7 @@ disable_dpm: dpm_ctl &= 0xfffffffe; /* Disable DPM */ WREG32(vpe_get_reg_offset(vpe, 0, vpe->regs.dpm_enable), dpm_ctl); dev_dbg(adev->dev, "%s: disable vpe dpm\n", __func__); - return 0; + return -EINVAL; } int amdgpu_vpe_psp_update_sram(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f90905ef32c76d..701146d649c353 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -9186,7 +9186,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { 7 + /* PIPELINE_SYNC */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* VM_FLUSH */ + 4 + /* VM_FLUSH */ 8 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 4 + /* double SWITCH_BUFFER, @@ -9276,7 +9276,6 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = { 7 + /* gfx_v10_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v10_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v10_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v10_0_ring_emit_ib_compute */ .emit_ib = gfx_v10_0_ring_emit_ib_compute, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index f7325b02a191f7..f00e05aba46a4e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -6192,7 +6192,7 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_gfx = { 7 + /* PIPELINE_SYNC */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* VM_FLUSH */ + 4 + /* VM_FLUSH */ 8 + /* FENCE for VM_FLUSH */ 20 + /* GDS switch */ 5 + /* COND_EXEC */ @@ -6278,7 +6278,6 @@ static const struct amdgpu_ring_funcs gfx_v11_0_ring_funcs_kiq = { 7 + /* gfx_v11_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v11_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v11_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v11_0_ring_emit_ib_compute */ .emit_ib = gfx_v11_0_ring_emit_ib_compute, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 6f97a6d0e6d052..99dbd2341120db 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -6981,7 +6981,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = { 7 + /* gfx_v9_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v9_0_ring_emit_vm_flush */ 8 + 8 + 8 + /* gfx_v9_0_ring_emit_fence x3 for user fence, vm fence */ 7 + /* gfx_v9_0_emit_mem_sync */ 5 + /* gfx_v9_0_emit_wave_limit for updating mmSPI_WCL_PIPE_PERCENT_GFX register */ @@ -7019,7 +7018,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = { 7 + /* gfx_v9_0_ring_emit_pipeline_sync */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 5 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 7 + - 2 + /* gfx_v9_0_ring_emit_vm_flush */ 8 + 8 + 8, /* gfx_v9_0_ring_emit_fence_kiq x3 for user fence, vm fence */ .emit_ib_size = 7, /* gfx_v9_0_ring_emit_ib_compute */ .emit_fence = gfx_v9_0_ring_emit_fence_kiq, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c index 82eab49be82bb9..e708468ac54dd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c @@ -368,7 +368,8 @@ static void sdma_v4_4_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) u32 ref_and_mask = 0; const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg; - ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; + ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 + << (ring->me % adev->sdma.num_inst_per_aid); sdma_v4_4_2_wait_reg_mem(ring, 0, 1, adev->nbio.funcs->get_hdp_flush_done_offset(adev), diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 42f4bd250def62..da01b524b9f2a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -280,17 +280,21 @@ static void sdma_v5_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) u32 ref_and_mask = 0; const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg; - ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; - - amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | - SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | - SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); - amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); - amdgpu_ring_write(ring, ref_and_mask); /* reference */ - amdgpu_ring_write(ring, ref_and_mask); /* mask */ - amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | - SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + if (ring->me > 1) { + amdgpu_asic_flush_hdp(adev, ring); + } else { + ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me; + + amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) | + SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) | + SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */ + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2); + amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2); + amdgpu_ring_write(ring, ref_and_mask); /* reference */ + amdgpu_ring_write(ring, ref_and_mask); /* mask */ + amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) | + SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10)); /* retry count, poll interval */ + } } /** diff --git a/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c b/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c index 769eb8f7bb3c57..09315dd5a1ec95 100644 --- a/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vpe_v6_1.c @@ -144,6 +144,12 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe) WREG32(vpe_get_reg_offset(vpe, j, regVPEC_CNTL), ret); } + /* setup collaborate mode */ + vpe_v6_1_set_collaborate_mode(vpe, true); + /* setup DPM */ + if (amdgpu_vpe_configure_dpm(vpe)) + dev_warn(adev->dev, "VPE failed to enable DPM\n"); + /* * For VPE 6.1.1, still only need to add master's offset, and psp will apply it to slave as well. * Here use instance 0 as master. @@ -159,11 +165,7 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe) adev->vpe.cmdbuf_cpu_addr[0] = f32_offset; adev->vpe.cmdbuf_cpu_addr[1] = f32_cntl; - amdgpu_vpe_psp_update_sram(adev); - vpe_v6_1_set_collaborate_mode(vpe, true); - amdgpu_vpe_configure_dpm(vpe); - - return 0; + return amdgpu_vpe_psp_update_sram(adev); } vpe_hdr = (const struct vpe_firmware_header_v1_0 *)adev->vpe.fw->data; @@ -196,8 +198,6 @@ static int vpe_v6_1_load_microcode(struct amdgpu_vpe *vpe) } vpe_v6_1_halt(vpe, false); - vpe_v6_1_set_collaborate_mode(vpe, true); - amdgpu_vpe_configure_dpm(vpe); return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index bdc01ca9609a7e..5c8d81bfce7ab1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -509,10 +509,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, start = start_mgr << PAGE_SHIFT; end = (last_mgr + 1) << PAGE_SHIFT; + r = amdgpu_amdkfd_reserve_mem_limit(node->adev, + prange->npages * PAGE_SIZE, + KFD_IOC_ALLOC_MEM_FLAGS_VRAM, + node->xcp ? node->xcp->id : 0); + if (r) { + dev_dbg(node->adev->dev, "failed to reserve VRAM, r: %ld\n", r); + return -ENOSPC; + } + r = svm_range_vram_node_new(node, prange, true); if (r) { dev_dbg(node->adev->dev, "fail %ld to alloc vram\n", r); - return r; + goto out; } ttm_res_offset = (start_mgr - prange->start + prange->offset) << PAGE_SHIFT; @@ -545,6 +554,11 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, svm_range_vram_node_free(prange); } +out: + amdgpu_amdkfd_unreserve_mem_limit(node->adev, + prange->npages * PAGE_SIZE, + KFD_IOC_ALLOC_MEM_FLAGS_VRAM, + node->xcp ? node->xcp->id : 0); return r < 0 ? r : 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index b79986412cd839..58c1fe5421934d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1922,6 +1922,8 @@ static int signal_eviction_fence(struct kfd_process *p) rcu_read_lock(); ef = dma_fence_get_rcu_safe(&p->ef); rcu_read_unlock(); + if (!ef) + return -EINVAL; ret = dma_fence_signal(ef); dma_fence_put(ef); @@ -1949,10 +1951,9 @@ static void evict_process_worker(struct work_struct *work) * they are responsible stopping the queues and scheduling * the restore work. */ - if (!signal_eviction_fence(p)) - queue_delayed_work(kfd_restore_wq, &p->restore_work, - msecs_to_jiffies(PROCESS_RESTORE_TIME_MS)); - else + if (signal_eviction_fence(p) || + mod_delayed_work(kfd_restore_wq, &p->restore_work, + msecs_to_jiffies(PROCESS_RESTORE_TIME_MS))) kfd_process_restore_queues(p); pr_debug("Finished evicting pasid 0x%x\n", p->pasid); @@ -2011,9 +2012,9 @@ static void restore_process_worker(struct work_struct *work) if (ret) { pr_debug("Failed to restore BOs of pasid 0x%x, retry after %d ms\n", p->pasid, PROCESS_BACK_OFF_TIME_MS); - ret = queue_delayed_work(kfd_restore_wq, &p->restore_work, - msecs_to_jiffies(PROCESS_BACK_OFF_TIME_MS)); - WARN(!ret, "reschedule restore work failed\n"); + if (mod_delayed_work(kfd_restore_wq, &p->restore_work, + msecs_to_jiffies(PROCESS_RESTORE_TIME_MS))) + kfd_process_restore_queues(p); } } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index f0f7f48af4137a..386875e6eb96ba 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -3426,7 +3426,7 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, mm, KFD_MIGRATE_TRIGGER_PREFETCH); *migrated = !r; - return r; + return 0; } int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence) diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 901d1961b73927..5fcd4f778dc3dd 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -8,7 +8,7 @@ config DRM_AMD_DC depends on BROKEN || !CC_IS_CLANG || ARM64 || RISCV || SPARC64 || X86_64 select SND_HDA_COMPONENT if SND_HDA_CORE # !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752 - select DRM_AMD_DC_FP if (X86 || LOONGARCH || (PPC64 && ALTIVEC) || (ARM64 && KERNEL_MODE_NEON && !CC_IS_CLANG)) + select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && (!ARM64 || !CC_IS_CLANG) help Choose this option if you want to use the new display engine support for AMDGPU. This adds required support for Vega and 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 6d2f60c61decc3..f3f94d109726d3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3029,6 +3029,7 @@ static int dm_resume(void *handle) dc_stream_release(dm_new_crtc_state->stream); dm_new_crtc_state->stream = NULL; } + dm_new_crtc_state->base.color_mgmt_changed = true; } for_each_new_plane_in_state(dm->cached_state, plane, new_plane_state, i) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c index 4ae4720535a56d..e46f8ce41d871c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c @@ -26,16 +26,7 @@ #include "dc_trace.h" -#if defined(CONFIG_X86) -#include <asm/fpu/api.h> -#elif defined(CONFIG_PPC64) -#include <asm/switch_to.h> -#include <asm/cputable.h> -#elif defined(CONFIG_ARM64) -#include <asm/neon.h> -#elif defined(CONFIG_LOONGARCH) -#include <asm/fpu.h> -#endif +#include <linux/fpu.h> /** * DOC: DC FPU manipulation overview @@ -87,20 +78,9 @@ void dc_fpu_begin(const char *function_name, const int line) WARN_ON_ONCE(!in_task()); preempt_disable(); depth = __this_cpu_inc_return(fpu_recursion_depth); - if (depth == 1) { -#if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) + BUG_ON(!kernel_fpu_available()); kernel_fpu_begin(); -#elif defined(CONFIG_PPC64) - if (cpu_has_feature(CPU_FTR_VSX_COMP)) - enable_kernel_vsx(); - else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) - enable_kernel_altivec(); - else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) - enable_kernel_fp(); -#elif defined(CONFIG_ARM64) - kernel_neon_begin(); -#endif } TRACE_DCN_FPU(true, function_name, line, depth); @@ -122,18 +102,7 @@ void dc_fpu_end(const char *function_name, const int line) depth = __this_cpu_dec_return(fpu_recursion_depth); if (depth == 0) { -#if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) kernel_fpu_end(); -#elif defined(CONFIG_PPC64) - if (cpu_has_feature(CPU_FTR_VSX_COMP)) - disable_kernel_vsx(); - else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) - disable_kernel_altivec(); - else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) - disable_kernel_fp(); -#elif defined(CONFIG_ARM64) - kernel_neon_end(); -#endif } else { WARN_ON_ONCE(depth < 0); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index c4a5efd2dda51c..a94b6d546cd1a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -25,40 +25,8 @@ # It provides the general basic services required by other DAL # subcomponents. -ifdef CONFIG_X86 -dml_ccflags-$(CONFIG_CC_IS_GCC) := -mhard-float -dml_ccflags := $(dml_ccflags-y) -msse -endif - -ifdef CONFIG_PPC64 -dml_ccflags := -mhard-float -maltivec -endif - -ifdef CONFIG_ARM64 -dml_rcflags := -mgeneral-regs-only -endif - -ifdef CONFIG_LOONGARCH -dml_ccflags := -mfpu=64 -dml_rcflags := -msoft-float -endif - -ifdef CONFIG_CC_IS_GCC -ifneq ($(call gcc-min-version, 70100),y) -IS_OLD_GCC = 1 -endif -endif - -ifdef CONFIG_X86 -ifdef IS_OLD_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -dml_ccflags += -mpreferred-stack-boundary=4 -else -dml_ccflags += -msse2 -endif -endif +dml_ccflags := $(CC_FLAGS_FPU) +dml_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) diff --git a/drivers/gpu/drm/amd/display/dc/dml2/Makefile b/drivers/gpu/drm/amd/display/dc/dml2/Makefile index acff3449b8d787..4f6c804a26ad6c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml2/Makefile @@ -24,40 +24,8 @@ # # Makefile for dml2. -ifdef CONFIG_X86 -dml2_ccflags-$(CONFIG_CC_IS_GCC) := -mhard-float -dml2_ccflags := $(dml2_ccflags-y) -msse -endif - -ifdef CONFIG_PPC64 -dml2_ccflags := -mhard-float -maltivec -endif - -ifdef CONFIG_ARM64 -dml2_rcflags := -mgeneral-regs-only -endif - -ifdef CONFIG_LOONGARCH -dml2_ccflags := -mfpu=64 -dml2_rcflags := -msoft-float -endif - -ifdef CONFIG_CC_IS_GCC -ifeq ($(call cc-ifversion, -lt, 0701, y), y) -IS_OLD_GCC = 1 -endif -endif - -ifdef CONFIG_X86 -ifdef IS_OLD_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -dml2_ccflags += -mpreferred-stack-boundary=4 -else -dml2_ccflags += -msse2 -endif -endif +dml2_ccflags := $(CC_FLAGS_FPU) +dml2_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index f09b9d49297e81..bbd0169010c2d5 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -4261,6 +4261,13 @@ static int amdgpu_od_set_init(struct amdgpu_device *adev) } } + /* + * If gpu_od is the only member in the list, that means gpu_od is an + * empty directory, so remove it. + */ + if (list_is_singular(&adev->pm.od_kobj_list)) + goto err_out; + return 0; err_out: diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 3957af057d54ff..c977ebe88001df 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -2294,6 +2294,17 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table return sizeof(*gpu_metrics); } +static void smu_v13_0_6_restore_pci_config(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int i; + + for (i = 0; i < 16; i++) + pci_write_config_dword(adev->pdev, i * 4, + adev->pdev->saved_config_space[i]); + pci_restore_msi_state(adev->pdev); +} + static int smu_v13_0_6_mode2_reset(struct smu_context *smu) { int ret = 0, index; @@ -2315,6 +2326,20 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu) /* Restore the config space saved during init */ amdgpu_device_load_pci_state(adev->pdev); + /* Certain platforms have switches which assign virtual BAR values to + * devices. OS uses the virtual BAR values and device behind the switch + * is assgined another BAR value. When device's config space registers + * are queried, switch returns the virtual BAR values. When mode-2 reset + * is performed, switch is unaware of it, and will continue to return + * the same virtual values to the OS.This affects + * pci_restore_config_space() API as it doesn't write the value saved if + * the current value read from config space is the same as what is + * saved. As a workaround, make sure the config space is restored + * always. + */ + if (!(adev->flags & AMD_IS_APU)) + smu_v13_0_6_restore_pci_config(smu); + dev_dbg(smu->adev->dev, "wait for reset ack\n"); do { ret = smu_cmn_wait_for_response(smu); diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index e440f458b6633d..93337543aac32b 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -224,8 +224,8 @@ __drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane, __drm_atomic_helper_plane_duplicate_state(plane, &new_shadow_plane_state->base); - drm_format_conv_state_copy(&shadow_plane_state->fmtcnv_state, - &new_shadow_plane_state->fmtcnv_state); + drm_format_conv_state_copy(&new_shadow_plane_state->fmtcnv_state, + &shadow_plane_state->fmtcnv_state); } EXPORT_SYMBOL(__drm_gem_duplicate_shadow_plane_state); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 734412aae94dde..a9bf426f69b365 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -164,26 +164,6 @@ int etnaviv_gpu_get_param(struct etnaviv_gpu *gpu, u32 param, u64 *value) *value = gpu->identity.eco_id; break; - case ETNAVIV_PARAM_GPU_NN_CORE_COUNT: - *value = gpu->identity.nn_core_count; - break; - - case ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE: - *value = gpu->identity.nn_mad_per_core; - break; - - case ETNAVIV_PARAM_GPU_TP_CORE_COUNT: - *value = gpu->identity.tp_core_count; - break; - - case ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE: - *value = gpu->identity.on_chip_sram_size; - break; - - case ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE: - *value = gpu->identity.axi_sram_size; - break; - default: DBG("%s: invalid param: %u", dev_name(gpu->dev), param); return -EINVAL; @@ -663,8 +643,8 @@ static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) /* Disable TX clock gating on affected core revisions. */ if (etnaviv_is_model_rev(gpu, GC4000, 0x5222) || etnaviv_is_model_rev(gpu, GC2000, 0x5108) || - etnaviv_is_model_rev(gpu, GC2000, 0x6202) || - etnaviv_is_model_rev(gpu, GC2000, 0x6203)) + etnaviv_is_model_rev(gpu, GC7000, 0x6202) || + etnaviv_is_model_rev(gpu, GC7000, 0x6203)) pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX; /* Disable SE and RA clock gating on affected core revisions. */ diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h index 7d5e9158e13c1a..197e0037732ec8 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h @@ -54,18 +54,6 @@ struct etnaviv_chip_identity { /* Number of Neural Network cores. */ u32 nn_core_count; - /* Number of MAD units per Neural Network core. */ - u32 nn_mad_per_core; - - /* Number of Tensor Processing cores. */ - u32 tp_core_count; - - /* Size in bytes of the SRAM inside the NPU. */ - u32 on_chip_sram_size; - - /* Size in bytes of the SRAM across the AXI bus. */ - u32 axi_sram_size; - /* Size of the vertex cache. */ u32 vertex_cache_size; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c index d8e7334de8ceac..8665f2658d51b3 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_hwdb.c @@ -17,10 +17,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 128, .shader_core_count = 1, .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 8, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -52,11 +48,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .register_max = 64, .thread_count = 256, .shader_core_count = 1, - .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 8, .vertex_output_buffer_size = 512, .pixel_pipes = 1, @@ -89,10 +80,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 512, .shader_core_count = 2, .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -125,10 +112,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 512, .shader_core_count = 2, .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -160,11 +143,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .register_max = 64, .thread_count = 512, .shader_core_count = 2, - .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -197,10 +175,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 1024, .shader_core_count = 4, .nn_core_count = 0, - .nn_mad_per_core = 0, - .tp_core_count = 0, - .on_chip_sram_size = 0, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 2, @@ -233,10 +207,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 256, .shader_core_count = 1, .nn_core_count = 8, - .nn_mad_per_core = 64, - .tp_core_count = 4, - .on_chip_sram_size = 524288, - .axi_sram_size = 1048576, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, @@ -269,10 +239,6 @@ static const struct etnaviv_chip_identity etnaviv_chip_identities[] = { .thread_count = 256, .shader_core_count = 1, .nn_core_count = 6, - .nn_mad_per_core = 64, - .tp_core_count = 3, - .on_chip_sram_size = 262144, - .axi_sram_size = 0, .vertex_cache_size = 16, .vertex_output_buffer_size = 1024, .pixel_pipes = 1, diff --git a/drivers/gpu/drm/gma500/Makefile b/drivers/gpu/drm/gma500/Makefile index 4f302cd5e1a6ca..58fed80c7392a0 100644 --- a/drivers/gpu/drm/gma500/Makefile +++ b/drivers/gpu/drm/gma500/Makefile @@ -34,7 +34,6 @@ gma500_gfx-y += \ psb_intel_lvds.o \ psb_intel_modes.o \ psb_intel_sdvo.o \ - psb_lid.o \ psb_irq.o gma500_gfx-$(CONFIG_ACPI) += opregion.o diff --git a/drivers/gpu/drm/gma500/mmu.c b/drivers/gpu/drm/gma500/mmu.c index a70b01ccdf7022..4d78b33eaa8230 100644 --- a/drivers/gpu/drm/gma500/mmu.c +++ b/drivers/gpu/drm/gma500/mmu.c @@ -5,6 +5,7 @@ **************************************************************************/ #include <linux/highmem.h> +#include <linux/vmalloc.h> #include "mmu.h" #include "psb_drv.h" diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c index dcfcd7b89d4a1d..6dece8f0e380f7 100644 --- a/drivers/gpu/drm/gma500/psb_device.c +++ b/drivers/gpu/drm/gma500/psb_device.c @@ -73,8 +73,7 @@ static int psb_backlight_setup(struct drm_device *dev) } psb_intel_lvds_set_brightness(dev, PSB_MAX_BRIGHTNESS); - /* This must occur after the backlight is properly initialised */ - psb_lid_timer_init(dev_priv); + return 0; } @@ -259,8 +258,6 @@ static int psb_chip_setup(struct drm_device *dev) static void psb_chip_teardown(struct drm_device *dev) { - struct drm_psb_private *dev_priv = to_drm_psb_private(dev); - psb_lid_timer_takedown(dev_priv); gma_intel_teardown_gmbus(dev); } diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index c5edfa4aa4ccdd..83c17689c454f7 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -162,7 +162,6 @@ #define PSB_NUM_VBLANKS 2 #define PSB_WATCHDOG_DELAY (HZ * 2) -#define PSB_LID_DELAY (HZ / 10) #define PSB_MAX_BRIGHTNESS 100 @@ -491,11 +490,7 @@ struct drm_psb_private { /* Hotplug handling */ struct work_struct hotplug_work; - /* LID-Switch */ - spinlock_t lid_lock; - struct timer_list lid_timer; struct psb_intel_opregion opregion; - u32 lid_last_state; /* Watchdog */ uint32_t apm_reg; @@ -591,10 +586,6 @@ struct psb_ops { int i2c_bus; /* I2C bus identifier for Moorestown */ }; -/* psb_lid.c */ -extern void psb_lid_timer_init(struct drm_psb_private *dev_priv); -extern void psb_lid_timer_takedown(struct drm_psb_private *dev_priv); - /* modesetting */ extern void psb_modeset_init(struct drm_device *dev); extern void psb_modeset_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/gma500/psb_lid.c b/drivers/gpu/drm/gma500/psb_lid.c deleted file mode 100644 index 58a7fe39263601..00000000000000 --- a/drivers/gpu/drm/gma500/psb_lid.c +++ /dev/null @@ -1,80 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/************************************************************************** - * Copyright (c) 2007, Intel Corporation. - * - * Authors: Thomas Hellstrom <thomas-at-tungstengraphics-dot-com> - **************************************************************************/ - -#include <linux/spinlock.h> - -#include "psb_drv.h" -#include "psb_intel_reg.h" -#include "psb_reg.h" - -static void psb_lid_timer_func(struct timer_list *t) -{ - struct drm_psb_private *dev_priv = from_timer(dev_priv, t, lid_timer); - struct drm_device *dev = (struct drm_device *)&dev_priv->dev; - struct timer_list *lid_timer = &dev_priv->lid_timer; - unsigned long irq_flags; - u32 __iomem *lid_state = dev_priv->opregion.lid_state; - u32 pp_status; - - if (readl(lid_state) == dev_priv->lid_last_state) - goto lid_timer_schedule; - - if ((readl(lid_state)) & 0x01) { - /*lid state is open*/ - REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) | POWER_TARGET_ON); - do { - pp_status = REG_READ(PP_STATUS); - } while ((pp_status & PP_ON) == 0 && - (pp_status & PP_SEQUENCE_MASK) != 0); - - if (REG_READ(PP_STATUS) & PP_ON) { - /*FIXME: should be backlight level before*/ - psb_intel_lvds_set_brightness(dev, 100); - } else { - DRM_DEBUG("LVDS panel never powered up"); - return; - } - } else { - psb_intel_lvds_set_brightness(dev, 0); - - REG_WRITE(PP_CONTROL, REG_READ(PP_CONTROL) & ~POWER_TARGET_ON); - do { - pp_status = REG_READ(PP_STATUS); - } while ((pp_status & PP_ON) == 0); - } - dev_priv->lid_last_state = readl(lid_state); - -lid_timer_schedule: - spin_lock_irqsave(&dev_priv->lid_lock, irq_flags); - if (!timer_pending(lid_timer)) { - lid_timer->expires = jiffies + PSB_LID_DELAY; - add_timer(lid_timer); - } - spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags); -} - -void psb_lid_timer_init(struct drm_psb_private *dev_priv) -{ - struct timer_list *lid_timer = &dev_priv->lid_timer; - unsigned long irq_flags; - - spin_lock_init(&dev_priv->lid_lock); - spin_lock_irqsave(&dev_priv->lid_lock, irq_flags); - - timer_setup(lid_timer, psb_lid_timer_func, 0); - - lid_timer->expires = jiffies + PSB_LID_DELAY; - - add_timer(lid_timer); - spin_unlock_irqrestore(&dev_priv->lid_lock, irq_flags); -} - -void psb_lid_timer_takedown(struct drm_psb_private *dev_priv) -{ - del_timer_sync(&dev_priv->lid_timer); -} - diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 0ba955611dfb54..8780aa24310535 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -5,6 +5,7 @@ */ #include <drm/drm_cache.h> +#include <linux/vmalloc.h> #include "gt/intel_gt.h" #include "gt/intel_tlb.h" diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c index b2a5882b8f81a0..07565701873922 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c @@ -4,6 +4,7 @@ * Copyright © 2016 Intel Corporation */ +#include <linux/vmalloc.h> #include "mock_dmabuf.h" static struct sg_table *mock_map_dma_buf(struct dma_buf_attachment *attachment, diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index bccc3a1200bc6e..1fb6ff77fd8991 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/shmem_fs.h> +#include <linux/vmalloc.h> #include "i915_drv.h" #include "gem/i915_gem_object.h" diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index 4dd52ac2043e7a..d800d267f0e9bd 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -30,6 +30,7 @@ #include <linux/firmware.h> #include <linux/crc32.h> +#include <linux/vmalloc.h> #include "i915_drv.h" #include "gvt.h" diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 094fca9b0e73d1..58cca4906f4135 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -39,6 +39,7 @@ #include "trace.h" #include "gt/intel_gt_regs.h" +#include <linux/vmalloc.h> #if defined(VERBOSE_DEBUG) #define gvt_vdbg_mm(fmt, args...) gvt_dbg_mm(fmt, ##args) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index efcb00472be247..ea9c300927671f 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -52,6 +52,7 @@ #include "display/skl_watermark_regs.h" #include "display/vlv_dsi_pll_regs.h" #include "gt/intel_gt_regs.h" +#include <linux/vmalloc.h> /* XXX FIXME i915 has changed PP_XXX definition */ #define PCH_PP_STATUS _MMIO(0xc7200) diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c index 5b5def6ddef7ae..780762f28aa4fb 100644 --- a/drivers/gpu/drm/i915/gvt/mmio.c +++ b/drivers/gpu/drm/i915/gvt/mmio.c @@ -33,6 +33,7 @@ * */ +#include <linux/vmalloc.h> #include "i915_drv.h" #include "i915_reg.h" #include "gvt.h" diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 08ad1bd651f103..63c751ca411964 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -34,6 +34,7 @@ #include "i915_drv.h" #include "gvt.h" #include "i915_pvinfo.h" +#include <linux/vmalloc.h> void populate_pvinfo_page(struct intel_vgpu *vgpu) { diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c index 9b6d87c8b5831c..5a01d60e51861e 100644 --- a/drivers/gpu/drm/i915/intel_gvt.c +++ b/drivers/gpu/drm/i915/intel_gvt.c @@ -28,6 +28,7 @@ #include "gt/intel_context.h" #include "gt/intel_ring.h" #include "gt/shmem_utils.h" +#include <linux/vmalloc.h> /** * DOC: Intel GVT-g host support diff --git a/drivers/gpu/drm/imagination/pvr_vm_mips.c b/drivers/gpu/drm/imagination/pvr_vm_mips.c index b7fef3c797e6ca..6563dcde109cda 100644 --- a/drivers/gpu/drm/imagination/pvr_vm_mips.c +++ b/drivers/gpu/drm/imagination/pvr_vm_mips.c @@ -14,6 +14,7 @@ #include <linux/err.h> #include <linux/slab.h> #include <linux/types.h> +#include <linux/vmalloc.h> /** * pvr_vm_mips_init() - Initialise MIPS FW pagetable diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 4f2e3feabc0f8a..3e519869b632c6 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -4,6 +4,7 @@ */ #include <linux/dma-buf.h> +#include <linux/vmalloc.h> #include <drm/drm.h> #include <drm/drm_device.h> diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 3421e8389222a4..9ea0c64c26b5c8 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -9,6 +9,7 @@ #include <linux/shmem_fs.h> #include <linux/spinlock.h> #include <linux/pfn_t.h> +#include <linux/vmalloc.h> #include <drm/drm_prime.h> #include <drm/drm_vma_manager.h> diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 578a7c37f00bd7..d776e3f87064fa 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -92,7 +92,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc) */ if (bdev->pool.use_dma_alloc && cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { page_flags |= TTM_TT_FLAG_DECRYPTED; - drm_info(ddev, "TT memory decryption enabled."); + drm_info_once(ddev, "TT memory decryption enabled."); } bo->ttm = bdev->funcs->ttm_tt_create(bo, page_flags); diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c index a07ede668cc161..a165cbcdd27b94 100644 --- a/drivers/gpu/drm/v3d/v3d_bo.c +++ b/drivers/gpu/drm/v3d/v3d_bo.c @@ -21,6 +21,7 @@ #include <linux/dma-buf.h> #include <linux/pfn_t.h> +#include <linux/vmalloc.h> #include "v3d_drv.h" #include "uapi/drm/v3d_drm.h" diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c index ae2de914eb890e..2731f6ded1c28c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c @@ -54,6 +54,7 @@ #include "vmwgfx_drv.h" #include "vmwgfx_binding.h" #include "device_include/svga3d_reg.h" +#include <linux/vmalloc.h> #define VMW_BINDING_RT_BIT 0 #define VMW_BINDING_PS_BIT 1 diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index e5eb21a471a601..00144632c600eb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -204,6 +204,7 @@ int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv, VMW_BO_DOMAIN_VRAM, VMW_BO_DOMAIN_VRAM); buf->places[0].lpfn = PFN_UP(bo->resource->size); + buf->busy_places[0].lpfn = PFN_UP(bo->resource->size); ret = ttm_bo_validate(bo, &buf->placement, &ctx); /* For some reason we didn't end up at the start of vram */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c index 195ff8792e5aba..dd4ca6a9c690bd 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c @@ -31,6 +31,7 @@ #include <drm/ttm/ttm_placement.h> #include <linux/sched/signal.h> +#include <linux/vmalloc.h> bool vmw_supports_3d(struct vmw_private *dev_priv) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c index 829df395c2ed7f..6e6beff9e2621b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c @@ -25,6 +25,7 @@ * **************************************************************************/ +#include <linux/vmalloc.h> #include "vmwgfx_devcaps.h" #include "vmwgfx_drv.h" diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 58fb40c93100a8..bd6cebadf37ee6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -53,6 +53,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/version.h> +#include <linux/vmalloc.h> #define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices" diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index cc3086e649eb5c..2e52d73eba4840 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -35,6 +35,7 @@ #include <linux/sync_file.h> #include <linux/hashtable.h> +#include <linux/vmalloc.h> /* * Helper macro to get dx_ctx_node if available otherwise print an error diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index a1da5678c73140..835d1eed8dd931 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -31,6 +31,7 @@ #include <drm/vmwgfx_drm.h> #include <linux/pci.h> +#include <linux/vmalloc.h> int vmw_getparam_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index a0afe1ba6dd5ce..f9705430ada930 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -378,7 +378,9 @@ static int gt_fw_domain_init(struct xe_gt *gt) err); /* Initialize CCS mode sysfs after early initialization of HW engines */ - xe_gt_ccs_mode_sysfs_init(gt); + err = xe_gt_ccs_mode_sysfs_init(gt); + if (err) + goto err_force_wake; /* * Stash hardware-reported version. Since this register does not exist diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c index 529fc286cd06c6..396aeb5b992424 100644 --- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c +++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c @@ -167,25 +167,20 @@ static void xe_gt_ccs_mode_sysfs_fini(struct drm_device *drm, void *arg) * and it is expected that there are no open drm clients while doing so. * The number of available compute slices is exposed to user through a per-gt * 'num_cslices' sysfs interface. + * + * Returns: Returns error value for failure and 0 for success. */ -void xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt) +int xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); int err; if (!xe_gt_ccs_mode_enabled(gt)) - return; + return 0; err = sysfs_create_files(gt->sysfs, gt_ccs_mode_attrs); - if (err) { - drm_warn(&xe->drm, "Sysfs creation for ccs_mode failed err: %d\n", err); - return; - } + if (err) + return err; - err = drmm_add_action_or_reset(&xe->drm, xe_gt_ccs_mode_sysfs_fini, gt); - if (err) { - sysfs_remove_files(gt->sysfs, gt_ccs_mode_attrs); - drm_warn(&xe->drm, "%s: drmm_add_action_or_reset failed, err: %d\n", - __func__, err); - } + return drmm_add_action_or_reset(&xe->drm, xe_gt_ccs_mode_sysfs_fini, gt); } diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.h b/drivers/gpu/drm/xe/xe_gt_ccs_mode.h index f39975aaaab0db..f8779852cf0d26 100644 --- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.h +++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.h @@ -12,7 +12,7 @@ #include "xe_platform_types.h" void xe_gt_apply_ccs_mode(struct xe_gt *gt); -void xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt); +int xe_gt_ccs_mode_sysfs_init(struct xe_gt *gt); static inline bool xe_gt_ccs_mode_enabled(const struct xe_gt *gt) { diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 355edd4d758af7..7f32547f94b266 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -1054,10 +1054,10 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len) adj_len); break; case XE_GUC_ACTION_GUC2PF_RELAY_FROM_VF: - ret = xe_guc_relay_process_guc2pf(&guc->relay, payload, adj_len); + ret = xe_guc_relay_process_guc2pf(&guc->relay, hxg, hxg_len); break; case XE_GUC_ACTION_GUC2VF_RELAY_FROM_PF: - ret = xe_guc_relay_process_guc2vf(&guc->relay, payload, adj_len); + ret = xe_guc_relay_process_guc2vf(&guc->relay, hxg, hxg_len); break; default: drm_err(&xe->drm, "unexpected action 0x%04x\n", action); diff --git a/drivers/gpu/drm/xe/xe_huc.c b/drivers/gpu/drm/xe/xe_huc.c index b545f850087cd8..6b9b1cbedd379e 100644 --- a/drivers/gpu/drm/xe/xe_huc.c +++ b/drivers/gpu/drm/xe/xe_huc.c @@ -53,7 +53,6 @@ static int huc_alloc_gsc_pkt(struct xe_huc *huc) struct xe_gt *gt = huc_to_gt(huc); struct xe_device *xe = gt_to_xe(gt); struct xe_bo *bo; - int err; /* we use a single object for both input and output */ bo = xe_bo_create_pin_map(xe, gt_to_tile(gt), NULL, @@ -66,13 +65,7 @@ static int huc_alloc_gsc_pkt(struct xe_huc *huc) huc->gsc_pkt = bo; - err = drmm_add_action_or_reset(&xe->drm, free_gsc_pkt, huc); - if (err) { - free_gsc_pkt(&xe->drm, huc); - return err; - } - - return 0; + return drmm_add_action_or_reset(&xe->drm, free_gsc_pkt, huc); } int xe_huc_init(struct xe_huc *huc) diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c index 3ad2b4cfd1f0b2..63112ed975c472 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_gem.c +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -11,6 +11,7 @@ #include <linux/dma-buf.h> #include <linux/scatterlist.h> #include <linux/shmem_fs.h> +#include <linux/vmalloc.h> #include <drm/drm_gem.h> #include <drm/drm_prime.h> diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index e6a8b6d8eab707..3c3c497b6b9114 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 f9cceaeffd0814..da5ea5a23b087c 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 ab5953fc24367a..80e0f23c1c33ec 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 2df1ab3c31cc54..d965382196c69e 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 a49c6affd7c4c4..dd5fc60874ba1d 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/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 12a707ab73f85c..e140cbf8d4c795 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2609,7 +2609,7 @@ static struct syscore_ops hv_synic_syscore_ops = { .resume = hv_synic_resume, }; -static int __init hv_acpi_init(void) +static int __init vmbus_init(void) { int ret; @@ -2620,7 +2620,7 @@ static int __init hv_acpi_init(void) return 0; /* - * Get ACPI resources first. + * Get VMBus resources first. */ ret = platform_driver_register(&vmbus_platform_driver); if (ret) @@ -2707,5 +2707,5 @@ static void __exit vmbus_exit(void) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Microsoft Hyper-V VMBus Driver"); -subsys_initcall(hv_acpi_init); +subsys_initcall(vmbus_init); module_exit(vmbus_exit); diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c index 6136776482e6d8..96a32b21366994 100644 --- a/drivers/hwtracing/coresight/coresight-trbe.c +++ b/drivers/hwtracing/coresight/coresight-trbe.c @@ -17,6 +17,7 @@ #include <asm/barrier.h> #include <asm/cpufeature.h> +#include <linux/vmalloc.h> #include "coresight-self-hosted-trace.h" #include "coresight-trbe.h" diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index cc7f879bb175d4..86c8efecd7c264 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -871,7 +871,7 @@ intel_th_alloc(struct device *dev, const struct intel_th_drvdata *drvdata, if (!th) return ERR_PTR(-ENOMEM); - th->id = ida_simple_get(&intel_th_ida, 0, 0, GFP_KERNEL); + th->id = ida_alloc(&intel_th_ida, GFP_KERNEL); if (th->id < 0) { err = th->id; goto err_alloc; @@ -931,7 +931,7 @@ err_chrdev: "intel_th/output"); err_ida: - ida_simple_remove(&intel_th_ida, th->id); + ida_free(&intel_th_ida, th->id); err_alloc: kfree(th); @@ -964,7 +964,7 @@ void intel_th_free(struct intel_th *th) __unregister_chrdev(th->major, 0, TH_POSSIBLE_OUTPUTS, "intel_th/output"); - ida_simple_remove(&intel_th_ida, th->id); + ida_free(&intel_th_ida, th->id); kfree(th); } diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index ff5c486a1dbb1f..db0d1ac82910e5 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2200,13 +2200,18 @@ static int i2c_check_for_quirks(struct i2c_adapter *adap, struct i2c_msg *msgs, * Returns negative errno, else the number of messages executed. * * Adapter lock must be held when calling this function. No debug logging - * takes place. adap->algo->master_xfer existence isn't checked. + * takes place. */ int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { unsigned long orig_jiffies; int ret, try; + if (!adap->algo->master_xfer) { + dev_dbg(&adap->dev, "I2C level transfers not supported\n"); + return -EOPNOTSUPP; + } + if (WARN_ON(!msgs || num < 1)) return -EINVAL; @@ -2273,11 +2278,6 @@ int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) { int ret; - if (!adap->algo->master_xfer) { - dev_dbg(&adap->dev, "I2C level transfers not supported\n"); - return -EOPNOTSUPP; - } - /* REVISIT the fault reporting model here is weak: * * - When we get an error after receiving N bytes from a slave, diff --git a/drivers/iio/accel/mxc4005.c b/drivers/iio/accel/mxc4005.c index 61839be501c21a..63c3566a533bd8 100644 --- a/drivers/iio/accel/mxc4005.c +++ b/drivers/iio/accel/mxc4005.c @@ -5,6 +5,7 @@ * Copyright (c) 2014, Intel Corporation. */ +#include <linux/delay.h> #include <linux/module.h> #include <linux/i2c.h> #include <linux/iio/iio.h> @@ -27,11 +28,16 @@ #define MXC4005_REG_ZOUT_UPPER 0x07 #define MXC4005_REG_ZOUT_LOWER 0x08 +#define MXC4005_REG_INT_MASK0 0x0A + #define MXC4005_REG_INT_MASK1 0x0B #define MXC4005_REG_INT_MASK1_BIT_DRDYE 0x01 +#define MXC4005_REG_INT_CLR0 0x00 + #define MXC4005_REG_INT_CLR1 0x01 #define MXC4005_REG_INT_CLR1_BIT_DRDYC 0x01 +#define MXC4005_REG_INT_CLR1_SW_RST 0x10 #define MXC4005_REG_CONTROL 0x0D #define MXC4005_REG_CONTROL_MASK_FSR GENMASK(6, 5) @@ -39,6 +45,9 @@ #define MXC4005_REG_DEVICE_ID 0x0E +/* Datasheet does not specify a reset time, this is a conservative guess */ +#define MXC4005_RESET_TIME_US 2000 + enum mxc4005_axis { AXIS_X, AXIS_Y, @@ -62,6 +71,8 @@ struct mxc4005_data { s64 timestamp __aligned(8); } scan; bool trigger_enabled; + unsigned int control; + unsigned int int_mask1; }; /* @@ -113,7 +124,9 @@ static bool mxc4005_is_readable_reg(struct device *dev, unsigned int reg) static bool mxc4005_is_writeable_reg(struct device *dev, unsigned int reg) { switch (reg) { + case MXC4005_REG_INT_CLR0: case MXC4005_REG_INT_CLR1: + case MXC4005_REG_INT_MASK0: case MXC4005_REG_INT_MASK1: case MXC4005_REG_CONTROL: return true; @@ -330,23 +343,20 @@ static int mxc4005_set_trigger_state(struct iio_trigger *trig, { struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig); struct mxc4005_data *data = iio_priv(indio_dev); + unsigned int val; int ret; mutex_lock(&data->mutex); - if (state) { - ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, - MXC4005_REG_INT_MASK1_BIT_DRDYE); - } else { - ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, - ~MXC4005_REG_INT_MASK1_BIT_DRDYE); - } + val = state ? MXC4005_REG_INT_MASK1_BIT_DRDYE : 0; + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, val); if (ret < 0) { mutex_unlock(&data->mutex); dev_err(data->dev, "failed to update reg_int_mask1"); return ret; } + data->int_mask1 = val; data->trigger_enabled = state; mutex_unlock(&data->mutex); @@ -382,6 +392,21 @@ static int mxc4005_chip_init(struct mxc4005_data *data) dev_dbg(data->dev, "MXC4005 chip id %02x\n", reg); + ret = regmap_write(data->regmap, MXC4005_REG_INT_CLR1, + MXC4005_REG_INT_CLR1_SW_RST); + if (ret < 0) + return dev_err_probe(data->dev, ret, "resetting chip\n"); + + fsleep(MXC4005_RESET_TIME_US); + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK0, 0); + if (ret < 0) + return dev_err_probe(data->dev, ret, "writing INT_MASK0\n"); + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, 0); + if (ret < 0) + return dev_err_probe(data->dev, ret, "writing INT_MASK1\n"); + return 0; } @@ -469,6 +494,58 @@ static int mxc4005_probe(struct i2c_client *client) return devm_iio_device_register(&client->dev, indio_dev); } +static int mxc4005_suspend(struct device *dev) +{ + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct mxc4005_data *data = iio_priv(indio_dev); + int ret; + + /* Save control to restore it on resume */ + ret = regmap_read(data->regmap, MXC4005_REG_CONTROL, &data->control); + if (ret < 0) + dev_err(data->dev, "failed to read reg_control\n"); + + return ret; +} + +static int mxc4005_resume(struct device *dev) +{ + struct iio_dev *indio_dev = dev_get_drvdata(dev); + struct mxc4005_data *data = iio_priv(indio_dev); + int ret; + + ret = regmap_write(data->regmap, MXC4005_REG_INT_CLR1, + MXC4005_REG_INT_CLR1_SW_RST); + if (ret) { + dev_err(data->dev, "failed to reset chip: %d\n", ret); + return ret; + } + + fsleep(MXC4005_RESET_TIME_US); + + ret = regmap_write(data->regmap, MXC4005_REG_CONTROL, data->control); + if (ret) { + dev_err(data->dev, "failed to restore control register\n"); + return ret; + } + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK0, 0); + if (ret) { + dev_err(data->dev, "failed to restore interrupt 0 mask\n"); + return ret; + } + + ret = regmap_write(data->regmap, MXC4005_REG_INT_MASK1, data->int_mask1); + if (ret) { + dev_err(data->dev, "failed to restore interrupt 1 mask\n"); + return ret; + } + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(mxc4005_pm_ops, mxc4005_suspend, mxc4005_resume); + static const struct acpi_device_id mxc4005_acpi_match[] = { {"MXC4005", 0}, {"MXC6655", 0}, @@ -496,6 +573,7 @@ static struct i2c_driver mxc4005_driver = { .name = MXC4005_DRV_NAME, .acpi_match_table = mxc4005_acpi_match, .of_match_table = mxc4005_of_match, + .pm = pm_sleep_ptr(&mxc4005_pm_ops), }, .probe = mxc4005_probe, .id_table = mxc4005_id, diff --git a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c index 3b0f9598a7c773..fa205f17bd905f 100644 --- a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c +++ b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c @@ -70,13 +70,13 @@ int inv_sensors_timestamp_update_odr(struct inv_sensors_timestamp *ts, } EXPORT_SYMBOL_NS_GPL(inv_sensors_timestamp_update_odr, IIO_INV_SENSORS_TIMESTAMP); -static bool inv_validate_period(struct inv_sensors_timestamp *ts, uint32_t period, uint32_t mult) +static bool inv_validate_period(struct inv_sensors_timestamp *ts, uint32_t period) { uint32_t period_min, period_max; /* check that period is acceptable */ - period_min = ts->min_period * mult; - period_max = ts->max_period * mult; + period_min = ts->min_period * ts->mult; + period_max = ts->max_period * ts->mult; if (period > period_min && period < period_max) return true; else @@ -84,15 +84,15 @@ static bool inv_validate_period(struct inv_sensors_timestamp *ts, uint32_t perio } static bool inv_update_chip_period(struct inv_sensors_timestamp *ts, - uint32_t mult, uint32_t period) + uint32_t period) { uint32_t new_chip_period; - if (!inv_validate_period(ts, period, mult)) + if (!inv_validate_period(ts, period)) return false; /* update chip internal period estimation */ - new_chip_period = period / mult; + new_chip_period = period / ts->mult; inv_update_acc(&ts->chip_period, new_chip_period); ts->period = ts->mult * ts->chip_period.val; @@ -101,6 +101,9 @@ static bool inv_update_chip_period(struct inv_sensors_timestamp *ts, static void inv_align_timestamp_it(struct inv_sensors_timestamp *ts) { + const int64_t period_min = ts->min_period * ts->mult; + const int64_t period_max = ts->max_period * ts->mult; + int64_t add_max, sub_max; int64_t delta, jitter; int64_t adjust; @@ -108,11 +111,13 @@ static void inv_align_timestamp_it(struct inv_sensors_timestamp *ts) delta = ts->it.lo - ts->timestamp; /* adjust timestamp while respecting jitter */ + add_max = period_max - (int64_t)ts->period; + sub_max = period_min - (int64_t)ts->period; jitter = INV_SENSORS_TIMESTAMP_JITTER((int64_t)ts->period, ts->chip.jitter); if (delta > jitter) - adjust = jitter; + adjust = add_max; else if (delta < -jitter) - adjust = -jitter; + adjust = sub_max; else adjust = 0; @@ -120,16 +125,14 @@ static void inv_align_timestamp_it(struct inv_sensors_timestamp *ts) } void inv_sensors_timestamp_interrupt(struct inv_sensors_timestamp *ts, - uint32_t fifo_period, size_t fifo_nb, - size_t sensor_nb, int64_t timestamp) + size_t sample_nb, int64_t timestamp) { struct inv_sensors_timestamp_interval *it; int64_t delta, interval; - const uint32_t fifo_mult = fifo_period / ts->chip.clock_period; uint32_t period; bool valid = false; - if (fifo_nb == 0) + if (sample_nb == 0) return; /* update interrupt timestamp and compute chip and sensor periods */ @@ -139,14 +142,14 @@ void inv_sensors_timestamp_interrupt(struct inv_sensors_timestamp *ts, delta = it->up - it->lo; if (it->lo != 0) { /* compute period: delta time divided by number of samples */ - period = div_s64(delta, fifo_nb); - valid = inv_update_chip_period(ts, fifo_mult, period); + period = div_s64(delta, sample_nb); + valid = inv_update_chip_period(ts, period); } /* no previous data, compute theoritical value from interrupt */ if (ts->timestamp == 0) { /* elapsed time: sensor period * sensor samples number */ - interval = (int64_t)ts->period * (int64_t)sensor_nb; + interval = (int64_t)ts->period * (int64_t)sample_nb; ts->timestamp = it->up - interval; return; } diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index 01f55cc902faad..060a21c70460d2 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -1289,6 +1289,7 @@ static int adis16475_config_sync_mode(struct adis16475 *st) struct device *dev = &st->adis.spi->dev; const struct adis16475_sync *sync; u32 sync_mode; + u16 val; /* default to internal clk */ st->clk_freq = st->info->int_clk * 1000; @@ -1350,8 +1351,9 @@ static int adis16475_config_sync_mode(struct adis16475 *st) * I'm keeping this for simplicity and avoiding extra variables * in chip_info. */ + val = ADIS16475_SYNC_MODE(sync->sync_mode); ret = __adis_update_bits(&st->adis, ADIS16475_REG_MSG_CTRL, - ADIS16475_SYNC_MODE_MASK, sync->sync_mode); + ADIS16475_SYNC_MODE_MASK, val); if (ret) return ret; diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c index b52f328fd26ce7..9cde9a9337ad00 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c @@ -509,20 +509,20 @@ int inv_icm42600_buffer_fifo_parse(struct inv_icm42600_state *st) return 0; /* handle gyroscope timestamp and FIFO data parsing */ - ts = iio_priv(st->indio_gyro); - inv_sensors_timestamp_interrupt(ts, st->fifo.period, st->fifo.nb.total, - st->fifo.nb.gyro, st->timestamp.gyro); if (st->fifo.nb.gyro > 0) { + ts = iio_priv(st->indio_gyro); + inv_sensors_timestamp_interrupt(ts, st->fifo.nb.gyro, + st->timestamp.gyro); ret = inv_icm42600_gyro_parse_fifo(st->indio_gyro); if (ret) return ret; } /* handle accelerometer timestamp and FIFO data parsing */ - ts = iio_priv(st->indio_accel); - inv_sensors_timestamp_interrupt(ts, st->fifo.period, st->fifo.nb.total, - st->fifo.nb.accel, st->timestamp.accel); if (st->fifo.nb.accel > 0) { + ts = iio_priv(st->indio_accel); + inv_sensors_timestamp_interrupt(ts, st->fifo.nb.accel, + st->timestamp.accel); ret = inv_icm42600_accel_parse_fifo(st->indio_accel); if (ret) return ret; @@ -550,9 +550,7 @@ int inv_icm42600_buffer_hwfifo_flush(struct inv_icm42600_state *st, if (st->fifo.nb.gyro > 0) { ts = iio_priv(st->indio_gyro); - inv_sensors_timestamp_interrupt(ts, st->fifo.period, - st->fifo.nb.total, st->fifo.nb.gyro, - gyro_ts); + inv_sensors_timestamp_interrupt(ts, st->fifo.nb.gyro, gyro_ts); ret = inv_icm42600_gyro_parse_fifo(st->indio_gyro); if (ret) return ret; @@ -560,9 +558,7 @@ int inv_icm42600_buffer_hwfifo_flush(struct inv_icm42600_state *st, if (st->fifo.nb.accel > 0) { ts = iio_priv(st->indio_accel); - inv_sensors_timestamp_interrupt(ts, st->fifo.period, - st->fifo.nb.total, st->fifo.nb.accel, - accel_ts); + inv_sensors_timestamp_interrupt(ts, st->fifo.nb.accel, accel_ts); ret = inv_icm42600_accel_parse_fifo(st->indio_accel); if (ret) return ret; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index d4f9b5d8d28d6d..d404e59eb5e855 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -113,7 +113,7 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) goto end_session; /* Each FIFO data contains all sensors, so same number for FIFO and sensor data */ fifo_period = NSEC_PER_SEC / INV_MPU6050_DIVIDER_TO_FIFO_RATE(st->chip_config.divider); - inv_sensors_timestamp_interrupt(&st->timestamp, fifo_period, nb, nb, pf->timestamp); + inv_sensors_timestamp_interrupt(&st->timestamp, nb, pf->timestamp); inv_sensors_timestamp_apply_odr(&st->timestamp, fifo_period, nb, 0); /* clear internal data buffer for avoiding kernel data leak */ diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index fe8734468ed352..62e9e93d915dc8 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1233,6 +1233,7 @@ const struct bmp280_chip_info bmp380_chip_info = { .chip_id = bmp380_chip_ids, .num_chip_id = ARRAY_SIZE(bmp380_chip_ids), .regmap_config = &bmp380_regmap_config, + .spi_read_extra_byte = true, .start_up_time = 2000, .channels = bmp380_channels, .num_channels = 2, diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c index a444d4b2978b58..4e19ea0b4d3984 100644 --- a/drivers/iio/pressure/bmp280-spi.c +++ b/drivers/iio/pressure/bmp280-spi.c @@ -96,15 +96,10 @@ static int bmp280_spi_probe(struct spi_device *spi) chip_info = spi_get_device_match_data(spi); - switch (chip_info->chip_id[0]) { - case BMP380_CHIP_ID: - case BMP390_CHIP_ID: + if (chip_info->spi_read_extra_byte) bmp_regmap_bus = &bmp380_regmap_bus; - break; - default: + else bmp_regmap_bus = &bmp280_regmap_bus; - break; - } regmap = devm_regmap_init(&spi->dev, bmp_regmap_bus, @@ -127,7 +122,7 @@ static const struct of_device_id bmp280_of_spi_match[] = { { .compatible = "bosch,bmp180", .data = &bmp180_chip_info }, { .compatible = "bosch,bmp181", .data = &bmp180_chip_info }, { .compatible = "bosch,bmp280", .data = &bmp280_chip_info }, - { .compatible = "bosch,bme280", .data = &bmp280_chip_info }, + { .compatible = "bosch,bme280", .data = &bme280_chip_info }, { .compatible = "bosch,bmp380", .data = &bmp380_chip_info }, { .compatible = "bosch,bmp580", .data = &bmp580_chip_info }, { }, @@ -139,7 +134,7 @@ static const struct spi_device_id bmp280_spi_id[] = { { "bmp180", (kernel_ulong_t)&bmp180_chip_info }, { "bmp181", (kernel_ulong_t)&bmp180_chip_info }, { "bmp280", (kernel_ulong_t)&bmp280_chip_info }, - { "bme280", (kernel_ulong_t)&bmp280_chip_info }, + { "bme280", (kernel_ulong_t)&bme280_chip_info }, { "bmp380", (kernel_ulong_t)&bmp380_chip_info }, { "bmp580", (kernel_ulong_t)&bmp580_chip_info }, { } diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h index 4012387d795656..5812a344ed8e88 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -423,6 +423,7 @@ struct bmp280_chip_info { int num_chip_id; const struct regmap_config *regmap_config; + bool spi_read_extra_byte; const struct iio_chan_spec *channels; int num_channels; diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index 455e966eeff390..b27791029fa934 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -439,6 +439,7 @@ static int remove_device_files(struct super_block *sb, return PTR_ERR(dir); } simple_recursive_removal(dir, NULL); + dput(dir); return 0; } diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index f50848ed5575db..6fadaddb2b908f 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -208,6 +208,7 @@ static const struct xpad_device { { 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 }, { 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 }, { 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 }, + { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE }, { 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX }, { 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX }, { 0x0c12, 0x8802, "Zeroplus Xbox Controller", 0, XTYPE_XBOX }, @@ -487,6 +488,7 @@ static const struct usb_device_id xpad_table[] = { { USB_DEVICE(0x0738, 0x4540) }, /* Mad Catz Beat Pad */ XPAD_XBOXONE_VENDOR(0x0738), /* Mad Catz FightStick TE 2 */ XPAD_XBOX360_VENDOR(0x07ff), /* Mad Catz Gamepad */ + XPAD_XBOXONE_VENDOR(0x0b05), /* ASUS controllers */ XPAD_XBOX360_VENDOR(0x0c12), /* Zeroplus X-Box 360 controllers */ XPAD_XBOX360_VENDOR(0x0e6f), /* 0x0e6f Xbox 360 controllers */ XPAD_XBOXONE_VENDOR(0x0e6f), /* 0x0e6f Xbox One controllers */ diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index f482aab420f787..52575ba9a141fe 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -134,13 +134,14 @@ static inline int get_pci_sbdf_id(struct pci_dev *pdev) return PCI_SEG_DEVID_TO_SBDF(seg, devid); } -static inline void *alloc_pgtable_page(int nid, gfp_t gfp) +static inline void *alloc_pgtable_page_noprof(int nid, gfp_t gfp) { struct page *page; - page = alloc_pages_node(nid, gfp | __GFP_ZERO, 0); + page = alloc_pages_node_noprof(nid, gfp | __GFP_ZERO, 0); return page ? page_address(page) : NULL; } +#define alloc_pgtable_page(...) alloc_hooks(alloc_pgtable_page_noprof(__VA_ARGS__)) /* * This must be called after device probe completes. During probe diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index e4cb26f6a9434e..07d087eecc17c3 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1723,7 +1723,7 @@ static const struct dma_map_ops iommu_dma_ops = { .flags = DMA_F_PCI_P2PDMA_SUPPORTED, .alloc = iommu_dma_alloc, .free = iommu_dma_free, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, .alloc_noncontiguous = iommu_dma_alloc_noncontiguous, .free_noncontiguous = iommu_dma_free_noncontiguous, diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 2a537cbfcb0772..5f7d3db3afd824 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -4567,13 +4567,8 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq irqd_set_resend_when_in_progress(irq_get_irq_data(virq + i)); } - if (err) { - if (i > 0) - its_vpe_irq_domain_free(domain, virq, i); - - its_lpi_free(bitmap, base, nr_ids); - its_free_prop_table(vprop_page); - } + if (err) + its_vpe_irq_domain_free(domain, virq, i); return err; } diff --git a/drivers/md/dm-vdo/murmurhash3.c b/drivers/md/dm-vdo/murmurhash3.c index 01d2743444ec6c..3a989efae1420a 100644 --- a/drivers/md/dm-vdo/murmurhash3.c +++ b/drivers/md/dm-vdo/murmurhash3.c @@ -137,7 +137,7 @@ void murmurhash3_128(const void *key, const int len, const u32 seed, void *out) break; default: break; - }; + } } /* finalization */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 56aa2a8b9d7153..7d0746b37c8ec7 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -765,7 +765,7 @@ static struct table_device *open_table_device(struct mapped_device *md, return td; out_blkdev_put: - fput(bdev_file); + __fput_sync(bdev_file); out_free_td: kfree(td); return ERR_PTR(r); @@ -778,7 +778,13 @@ static void close_table_device(struct table_device *td, struct mapped_device *md { if (md->disk->slave_dir) bd_unlink_disk_holder(td->dm_dev.bdev, md->disk); - fput(td->dm_dev.bdev_file); + + /* Leverage async fput() if DMF_DEFERRED_REMOVE set */ + if (unlikely(test_bit(DMF_DEFERRED_REMOVE, &md->flags))) + fput(td->dm_dev.bdev_file); + else + __fput_sync(td->dm_dev.bdev_file); + put_dax(td->dm_dev.dax_dev); list_del(&td->list); kfree(td); diff --git a/drivers/media/cec/platform/sti/stih-cec.c b/drivers/media/cec/platform/sti/stih-cec.c index a20fc5c0c88d0e..99978a7c8d9b70 100644 --- a/drivers/media/cec/platform/sti/stih-cec.c +++ b/drivers/media/cec/platform/sti/stih-cec.c @@ -6,6 +6,7 @@ */ #include <linux/clk.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/mfd/syscon.h> #include <linux/module.h> diff --git a/drivers/media/rc/mtk-cir.c b/drivers/media/rc/mtk-cir.c index 4e294e59d3cba8..b2f82b2d1c8d40 100644 --- a/drivers/media/rc/mtk-cir.c +++ b/drivers/media/rc/mtk-cir.c @@ -8,6 +8,7 @@ #include <linux/clk.h> #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/io.h> #include <linux/of.h> #include <linux/platform_device.h> #include <linux/reset.h> diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c index 96ae0294ac102a..fc5fd392717720 100644 --- a/drivers/media/rc/serial_ir.c +++ b/drivers/media/rc/serial_ir.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/errno.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/serial_reg.h> #include <linux/types.h> diff --git a/drivers/media/rc/st_rc.c b/drivers/media/rc/st_rc.c index 28477aa955635d..988b09191c4c74 100644 --- a/drivers/media/rc/st_rc.c +++ b/drivers/media/rc/st_rc.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/clk.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> diff --git a/drivers/media/rc/sunxi-cir.c b/drivers/media/rc/sunxi-cir.c index bf58c965ead8cf..b49df8355e6b39 100644 --- a/drivers/media/rc/sunxi-cir.c +++ b/drivers/media/rc/sunxi-cir.c @@ -12,6 +12,7 @@ #include <linux/clk.h> #include <linux/interrupt.h> +#include <linux/io.h> #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 572333ead5fb8b..4bd4f32bcdabb8 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -758,15 +758,6 @@ static int at24_probe(struct i2c_client *client) } pm_runtime_enable(dev); - at24->nvmem = devm_nvmem_register(dev, &nvmem_config); - if (IS_ERR(at24->nvmem)) { - pm_runtime_disable(dev); - if (!pm_runtime_status_suspended(dev)) - regulator_disable(at24->vcc_reg); - return dev_err_probe(dev, PTR_ERR(at24->nvmem), - "failed to register nvmem\n"); - } - /* * Perform a one-byte test read to verify that the chip is functional, * unless powering on the device is to be avoided during probe (i.e. @@ -782,6 +773,15 @@ static int at24_probe(struct i2c_client *client) } } + at24->nvmem = devm_nvmem_register(dev, &nvmem_config); + if (IS_ERR(at24->nvmem)) { + pm_runtime_disable(dev); + if (!pm_runtime_status_suspended(dev)) + regulator_disable(at24->vcc_reg); + return dev_err_probe(dev, PTR_ERR(at24->nvmem), + "failed to register nvmem\n"); + } + /* If this a SPD EEPROM, probe for DDR3 thermal sensor */ if (cdata == &at24_data_spd) at24_probe_temp_sensor(client); diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index aac36750d2c54a..c3a6657dcd4a29 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -115,6 +115,8 @@ #define MEI_DEV_ID_ARL_S 0x7F68 /* Arrow Lake Point S */ #define MEI_DEV_ID_ARL_H 0x7770 /* Arrow Lake Point H */ +#define MEI_DEV_ID_LNL_M 0xA870 /* Lunar Lake Point M */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index c39718042e2e0c..7f59dd38c32f52 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -122,6 +122,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_S, MEI_ME_PCH15_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_ARL_H, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)}, + /* required last entry */ {0, } }; diff --git a/drivers/misc/mei/pxp/mei_pxp.c b/drivers/misc/mei/pxp/mei_pxp.c index b1e4c23b31a329..49abc95677cdac 100644 --- a/drivers/misc/mei/pxp/mei_pxp.c +++ b/drivers/misc/mei/pxp/mei_pxp.c @@ -236,8 +236,11 @@ static int mei_pxp_component_match(struct device *dev, int subcomponent, pdev = to_pci_dev(dev); - if (pdev->class != (PCI_CLASS_DISPLAY_VGA << 8) || - pdev->vendor != PCI_VENDOR_ID_INTEL) + if (pdev->vendor != PCI_VENDOR_ID_INTEL) + return 0; + + if (pdev->class != (PCI_CLASS_DISPLAY_VGA << 8) && + pdev->class != (PCI_CLASS_DISPLAY_OTHER << 8)) return 0; if (subcomponent != I915_COMPONENT_PXP) diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c index b88d6dec209f57..9a5f75163acaee 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -300,6 +300,7 @@ static void moxart_transfer_pio(struct moxart_host *host) remain = sgm->length; if (remain > host->data_len) remain = host->data_len; + sgm->consumed = 0; if (data->flags & MMC_DATA_WRITE) { while (remain > 0) { diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index 668e0aceeebac9..e113b99a3eab59 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -2694,6 +2694,11 @@ static __maybe_unused int sdhci_msm_runtime_suspend(struct device *dev) struct sdhci_host *host = dev_get_drvdata(dev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); + unsigned long flags; + + spin_lock_irqsave(&host->lock, flags); + host->runtime_suspended = true; + spin_unlock_irqrestore(&host->lock, flags); /* Drop the performance vote */ dev_pm_opp_set_rate(dev, 0); @@ -2708,6 +2713,7 @@ static __maybe_unused int sdhci_msm_runtime_resume(struct device *dev) struct sdhci_host *host = dev_get_drvdata(dev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); + unsigned long flags; int ret; ret = clk_bulk_prepare_enable(ARRAY_SIZE(msm_host->bulk_clks), @@ -2726,7 +2732,15 @@ static __maybe_unused int sdhci_msm_runtime_resume(struct device *dev) dev_pm_opp_set_rate(dev, msm_host->clk_rate); - return sdhci_msm_ice_resume(msm_host); + ret = sdhci_msm_ice_resume(msm_host); + if (ret) + return ret; + + spin_lock_irqsave(&host->lock, flags); + host->runtime_suspended = false; + spin_unlock_irqrestore(&host->lock, flags); + + return ret; } static const struct dev_pm_ops sdhci_msm_pm_ops = { diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index 1d8f5a76096aeb..f2e4a93ed1d61a 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -626,6 +626,7 @@ static int th1520_execute_tuning(struct sdhci_host *host, u32 opcode) /* perform tuning */ sdhci_start_tuning(host); + host->tuning_loop_count = 128; host->tuning_err = __sdhci_execute_tuning(host, opcode); if (host->tuning_err) { /* disable auto-tuning upon tuning error */ diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 5887feb347a4e4..0de87bc6384054 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -900,7 +900,7 @@ static struct nvmem_device *mtd_otp_nvmem_register(struct mtd_info *mtd, config.name = compatible; config.id = NVMEM_DEVID_AUTO; config.owner = THIS_MODULE; - config.add_legacy_fixed_of_cells = true; + config.add_legacy_fixed_of_cells = !mtd_type_is_nand(mtd); config.type = NVMEM_TYPE_OTP; config.root_only = true; config.ignore_wp = true; diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c index a8d12c71f987be..1b2ec0fec60c7a 100644 --- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c @@ -857,7 +857,7 @@ static inline void brcmnand_read_data_bus(struct brcmnand_controller *ctrl, struct brcmnand_soc *soc = ctrl->soc; int i; - if (soc->read_data_bus) { + if (soc && soc->read_data_bus) { soc->read_data_bus(soc, flash_cache, buffer, fc_words); } else { for (i = 0; i < fc_words; i++) diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 5243fab9face00..8db7fc42457111 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -53,7 +53,7 @@ static unsigned long doc_locations[] __initdata = { 0xe8000, 0xea000, 0xec000, 0xee000, #endif #endif - 0xffffffff }; +}; static struct mtd_info *doclist = NULL; @@ -1554,7 +1554,7 @@ static int __init init_nanddoc(void) if (ret < 0) return ret; } else { - for (i = 0; (doc_locations[i] != 0xffffffff); i++) { + for (i = 0; i < ARRAY_SIZE(doc_locations); i++) { doc_probe(doc_locations[i]); } } diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index b079605c84d382..b8cff9240b286c 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -2815,7 +2815,7 @@ static int qcom_misc_cmd_type_exec(struct nand_chip *chip, const struct nand_sub host->cfg0_raw & ~(7 << CW_PER_PAGE)); nandc_set_reg(chip, NAND_DEV0_CFG1, host->cfg1_raw); instrs = 3; - } else { + } else if (q_op.cmd_reg != OP_RESET_DEVICE) { return 0; } @@ -2830,9 +2830,8 @@ static int qcom_misc_cmd_type_exec(struct nand_chip *chip, const struct nand_sub nandc_set_reg(chip, NAND_EXEC_CMD, 1); write_reg_dma(nandc, NAND_FLASH_CMD, instrs, NAND_BAM_NEXT_SGL); - (q_op.cmd_reg == OP_BLOCK_ERASE) ? write_reg_dma(nandc, NAND_DEV0_CFG0, - 2, NAND_BAM_NEXT_SGL) : read_reg_dma(nandc, - NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); + if (q_op.cmd_reg == OP_BLOCK_ERASE) + write_reg_dma(nandc, NAND_DEV0_CFG0, 2, NAND_BAM_NEXT_SGL); write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL); read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL); diff --git a/drivers/mux/core.c b/drivers/mux/core.c index 7758161129320f..78c0022697ec7c 100644 --- a/drivers/mux/core.c +++ b/drivers/mux/core.c @@ -64,7 +64,7 @@ static void mux_chip_release(struct device *dev) { struct mux_chip *mux_chip = to_mux_chip(dev); - ida_simple_remove(&mux_ida, mux_chip->id); + ida_free(&mux_ida, mux_chip->id); kfree(mux_chip); } @@ -111,7 +111,7 @@ struct mux_chip *mux_chip_alloc(struct device *dev, mux_chip->dev.of_node = dev->of_node; dev_set_drvdata(&mux_chip->dev, mux_chip); - mux_chip->id = ida_simple_get(&mux_ida, 0, 0, GFP_KERNEL); + mux_chip->id = ida_alloc(&mux_ida, GFP_KERNEL); if (mux_chip->id < 0) { int err = mux_chip->id; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c95787cb908673..59b5dd0e2f41d2 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 86deeb347cbc1d..ddadeb9bfdaeed 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -25,10 +25,25 @@ #define MV88E6250_PORT_STS_PORTMODE_PHY_100_HALF 0x0900 #define MV88E6250_PORT_STS_PORTMODE_PHY_10_FULL 0x0a00 #define MV88E6250_PORT_STS_PORTMODE_PHY_100_FULL 0x0b00 -#define MV88E6250_PORT_STS_PORTMODE_MII_10_HALF 0x0c00 -#define MV88E6250_PORT_STS_PORTMODE_MII_100_HALF 0x0d00 -#define MV88E6250_PORT_STS_PORTMODE_MII_10_FULL 0x0e00 -#define MV88E6250_PORT_STS_PORTMODE_MII_100_FULL 0x0f00 +/* - Modes with PHY suffix use output instead of input clock + * - Modes without RMII or RGMII use MII + * - Modes without speed do not have a fixed speed specified in the manual + * ("DC to x MHz" - variable clock support?) + */ +#define MV88E6250_PORT_STS_PORTMODE_MII_DISABLED 0x0000 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_RGMII 0x0100 +#define MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL_PHY 0x0200 +#define MV88E6250_PORT_STS_PORTMODE_MII_200_RMII_FULL_PHY 0x0400 +#define MV88E6250_PORT_STS_PORTMODE_MII_DUAL_100_RMII_FULL 0x0600 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL 0x0700 +#define MV88E6250_PORT_STS_PORTMODE_MII_HALF 0x0800 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_HALF_PHY 0x0900 +#define MV88E6250_PORT_STS_PORTMODE_MII_FULL 0x0a00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_100_RMII_FULL_PHY 0x0b00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_HALF_PHY 0x0c00 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_HALF_PHY 0x0d00 +#define MV88E6250_PORT_STS_PORTMODE_MII_10_FULL_PHY 0x0e00 +#define MV88E6250_PORT_STS_PORTMODE_MII_100_FULL_PHY 0x0f00 #define MV88E6XXX_PORT_STS_LINK 0x0800 #define MV88E6XXX_PORT_STS_DUPLEX 0x0400 #define MV88E6XXX_PORT_STS_SPEED_MASK 0x0300 diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index 72ea97c5d5d424..82768b0e90262b 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 3e4fb3c3e8342a..1be6d14030bcff 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 57e61f9631678e..2c2ee79c4d7795 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 | @@ -13037,6 +13029,16 @@ static void bnxt_rx_ring_reset(struct bnxt *bp) bnxt_rtnl_unlock_sp(bp); } +static void bnxt_fw_fatal_close(struct bnxt *bp) +{ + bnxt_tx_disable(bp); + bnxt_disable_napi(bp); + bnxt_disable_int_sync(bp); + bnxt_free_irq(bp); + bnxt_clear_int_mode(bp); + pci_disable_device(bp->pdev); +} + static void bnxt_fw_reset_close(struct bnxt *bp) { bnxt_ulp_stop(bp); @@ -13050,12 +13052,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp) pci_read_config_word(bp->pdev, PCI_SUBSYSTEM_ID, &val); if (val == 0xffff) bp->fw_reset_min_dsecs = 0; - bnxt_tx_disable(bp); - bnxt_disable_napi(bp); - bnxt_disable_int_sync(bp); - bnxt_free_irq(bp); - bnxt_clear_int_mode(bp); - pci_disable_device(bp->pdev); + bnxt_fw_fatal_close(bp); } __bnxt_close_nic(bp, true, false); bnxt_vf_reps_free(bp); @@ -15373,6 +15370,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, { struct net_device *netdev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(netdev); + bool abort = false; netdev_info(netdev, "PCI I/O error detected\n"); @@ -15381,16 +15379,27 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, bnxt_ulp_stop(bp); - if (state == pci_channel_io_perm_failure) { + if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + netdev_err(bp->dev, "Firmware reset already in progress\n"); + abort = true; + } + + if (abort || state == pci_channel_io_perm_failure) { rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; } - if (state == pci_channel_io_frozen) + /* Link is not reliable anymore if state is pci_channel_io_frozen + * so we disable bus master to prevent any potential bad DMAs before + * freeing kernel memory. + */ + if (state == pci_channel_io_frozen) { set_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state); + bnxt_fw_fatal_close(bp); + } if (netif_running(netdev)) - bnxt_close(netdev); + __bnxt_close_nic(bp, true, true); if (pci_is_enabled(pdev)) pci_disable_device(pdev); @@ -15474,6 +15483,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) } reset_exit: + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); bnxt_clear_reservations(bp, true); rtnl_unlock(); diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c index 7246e13dd559fc..97291bfbeea589 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c +++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c @@ -312,7 +312,7 @@ bnad_debugfs_write_regrd(struct file *file, const char __user *buf, void *kern_buf; /* Copy the user space buf */ - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); @@ -372,7 +372,7 @@ bnad_debugfs_write_regwr(struct file *file, const char __user *buf, void *kern_buf; /* Copy the user space buf */ - kern_buf = memdup_user(buf, nbytes); + kern_buf = memdup_user_nul(buf, nbytes); if (IS_ERR(kern_buf)) return PTR_ERR(kern_buf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 48b9ddb2b1b38b..ffb9f9f15c5232 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 ef2440f3abf8b6..166832a4213a28 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_debugfs.c b/drivers/net/ethernet/intel/ice/ice_debugfs.c index d252d98218d084..9fc0fd95a13d8f 100644 --- a/drivers/net/ethernet/intel/ice/ice_debugfs.c +++ b/drivers/net/ethernet/intel/ice/ice_debugfs.c @@ -171,7 +171,7 @@ ice_debugfs_module_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 8) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -257,7 +257,7 @@ ice_debugfs_nr_messages_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 4) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -332,7 +332,7 @@ ice_debugfs_enable_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 2) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); @@ -428,7 +428,7 @@ ice_debugfs_log_size_write(struct file *filp, const char __user *buf, if (*ppos != 0 || count > 5) return -EINVAL; - cmd_buf = memdup_user(buf, count); + cmd_buf = memdup_user_nul(buf, count); if (IS_ERR(cmd_buf)) return PTR_ERR(cmd_buf); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 21d26e19338a69..d10a4be965b591 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 90316dc5863087..6bc56c7c181e48 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 bf240c5daf8657..3929b25b6ae6eb 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 35ad40a803cb64..4d975d620a8e4b 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/octeon_ep/octep_pfvf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c index 2e2c3be8a0b429..e6eb98d70f3c42 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_pfvf_mbox.c @@ -15,6 +15,7 @@ #include <linux/io.h> #include <linux/pci.h> #include <linux/etherdevice.h> +#include <linux/vmalloc.h> #include "octep_config.h" #include "octep_main.h" diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_mbox.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_mbox.c index 2eab21e43048a1..445b626efe11d7 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_mbox.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_mbox.c @@ -7,6 +7,7 @@ #include <linux/types.h> #include <linux/pci.h> #include <linux/netdevice.h> +#include <linux/vmalloc.h> #include "octep_vf_config.h" #include "octep_vf_main.h" diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 2500f5ba4f5a42..881d704644fbee 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -999,12 +999,10 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, u16 pcifunc; int ret, lf; - cmd_buf = memdup_user(buffer, count + 1); + cmd_buf = memdup_user_nul(buffer, count); if (IS_ERR(cmd_buf)) return -ENOMEM; - cmd_buf[count] = '\0'; - cmd_buf_tmp = strchr(cmd_buf, '\n'); if (cmd_buf_tmp) { *cmd_buf_tmp = '\0'; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index be709f83f3318c..e8b73b9d75e311 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2181,7 +2181,6 @@ void rvu_npc_freemem(struct rvu *rvu) kfree(pkind->rsrc.bmap); npc_mcam_rsrcs_deinit(rvu); - kfree(mcam->counters.bmap); if (rvu->kpu_prfl_addr) iounmap(rvu->kpu_prfl_addr); else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index b2cabd6ab86cb9..cc9bcc42003242 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -1640,6 +1640,7 @@ static const struct macsec_ops macsec_offload_ops = { .mdo_add_secy = mlx5e_macsec_add_secy, .mdo_upd_secy = mlx5e_macsec_upd_secy, .mdo_del_secy = mlx5e_macsec_del_secy, + .rx_uses_md_dst = true, }; bool mlx5e_macsec_handle_tx_skb(struct mlx5e_macsec *macsec, struct sk_buff *skb) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e4d7739bd7c888..4a79c0d7e7ad85 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 53b150b7ae4e70..6c06b059276084 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 af99bf17eb36de..f42a1b1c936873 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 f20052776b3f2e..92a406f02eae74 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 462bf448497d33..79a1d860651253 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/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 2729a2c5acf9cc..11021c34e47e7c 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -3,6 +3,7 @@ #include <net/mana/gdma.h> #include <net/mana/hw_channel.h> +#include <linux/vmalloc.h> static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id) { diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index fcb756d77681cb..9b1f639f64a10c 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2722,19 +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; } @@ -2744,9 +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/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index c66618d91c28fe..f89716b1cfb640 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 cf7b73f8f45072..b69af69a1ccd36 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 6dff2c85682d8b..6fae161cbcb822 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 2fa511227eac84..93295916b1d2b8 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -20,8 +20,6 @@ #include "txgbe_phy.h" #include "txgbe_hw.h" -#define TXGBE_I2C_CLK_DEV_NAME "i2c_dw" - static int txgbe_swnodes_register(struct txgbe *txgbe) { struct txgbe_nodes *nodes = &txgbe->nodes; @@ -573,8 +571,8 @@ static int txgbe_clock_register(struct txgbe *txgbe) char clk_name[32]; struct clk *clk; - snprintf(clk_name, sizeof(clk_name), "%s.%d", - TXGBE_I2C_CLK_DEV_NAME, pci_dev_id(pdev)); + snprintf(clk_name, sizeof(clk_name), "i2c_designware.%d", + pci_dev_id(pdev)); clk = clk_register_fixed_rate(NULL, clk_name, NULL, 0, 156250000); if (IS_ERR(clk)) @@ -636,7 +634,7 @@ static int txgbe_i2c_register(struct txgbe *txgbe) info.parent = &pdev->dev; info.fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_I2C]); - info.name = TXGBE_I2C_CLK_DEV_NAME; + info.name = "i2c_designware"; info.id = pci_dev_id(pdev); info.res = &DEFINE_RES_IRQ(pdev->irq); diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index ba4704c2c640b8..e62d6cbdf9bc64 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/macsec.c b/drivers/net/macsec.c index 0206b84284ab5e..ff016c11b4a038 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 fa8c6fdcf30181..d7aaefb5226b62 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 0f3a1538a8b8ee..f4f9412d0cd7e2 100644 --- a/drivers/net/phy/mediatek-ge-soc.c +++ b/drivers/net/phy/mediatek-ge-soc.c @@ -216,6 +216,9 @@ #define MTK_PHY_LED_ON_LINK1000 BIT(0) #define MTK_PHY_LED_ON_LINK100 BIT(1) #define MTK_PHY_LED_ON_LINK10 BIT(2) +#define MTK_PHY_LED_ON_LINK (MTK_PHY_LED_ON_LINK10 |\ + MTK_PHY_LED_ON_LINK100 |\ + MTK_PHY_LED_ON_LINK1000) #define MTK_PHY_LED_ON_LINKDOWN BIT(3) #define MTK_PHY_LED_ON_FDX BIT(4) /* Full duplex */ #define MTK_PHY_LED_ON_HDX BIT(5) /* Half duplex */ @@ -231,6 +234,12 @@ #define MTK_PHY_LED_BLINK_100RX BIT(3) #define MTK_PHY_LED_BLINK_10TX BIT(4) #define MTK_PHY_LED_BLINK_10RX BIT(5) +#define MTK_PHY_LED_BLINK_RX (MTK_PHY_LED_BLINK_10RX |\ + MTK_PHY_LED_BLINK_100RX |\ + MTK_PHY_LED_BLINK_1000RX) +#define MTK_PHY_LED_BLINK_TX (MTK_PHY_LED_BLINK_10TX |\ + MTK_PHY_LED_BLINK_100TX |\ + MTK_PHY_LED_BLINK_1000TX) #define MTK_PHY_LED_BLINK_COLLISION BIT(6) #define MTK_PHY_LED_BLINK_RX_CRC_ERR BIT(7) #define MTK_PHY_LED_BLINK_RX_IDLE_ERR BIT(8) @@ -1247,11 +1256,9 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, if (blink < 0) return -EIO; - if ((on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 | - MTK_PHY_LED_ON_LINK10)) || - (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX | - MTK_PHY_LED_BLINK_10RX | MTK_PHY_LED_BLINK_1000TX | - MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX))) + if ((on & (MTK_PHY_LED_ON_LINK | MTK_PHY_LED_ON_FDX | MTK_PHY_LED_ON_HDX | + MTK_PHY_LED_ON_LINKDOWN)) || + (blink & (MTK_PHY_LED_BLINK_RX | MTK_PHY_LED_BLINK_TX))) set_bit(bit_netdev, &priv->led_state); else clear_bit(bit_netdev, &priv->led_state); @@ -1269,7 +1276,7 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, if (!rules) return 0; - if (on & (MTK_PHY_LED_ON_LINK1000 | MTK_PHY_LED_ON_LINK100 | MTK_PHY_LED_ON_LINK10)) + if (on & MTK_PHY_LED_ON_LINK) *rules |= BIT(TRIGGER_NETDEV_LINK); if (on & MTK_PHY_LED_ON_LINK10) @@ -1287,10 +1294,10 @@ static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, if (on & MTK_PHY_LED_ON_HDX) *rules |= BIT(TRIGGER_NETDEV_HALF_DUPLEX); - if (blink & (MTK_PHY_LED_BLINK_1000RX | MTK_PHY_LED_BLINK_100RX | MTK_PHY_LED_BLINK_10RX)) + if (blink & MTK_PHY_LED_BLINK_RX) *rules |= BIT(TRIGGER_NETDEV_RX); - if (blink & (MTK_PHY_LED_BLINK_1000TX | MTK_PHY_LED_BLINK_100TX | MTK_PHY_LED_BLINK_10TX)) + if (blink & MTK_PHY_LED_BLINK_TX) *rules |= BIT(TRIGGER_NETDEV_TX); return 0; @@ -1323,15 +1330,19 @@ static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index, on |= MTK_PHY_LED_ON_LINK1000; if (rules & BIT(TRIGGER_NETDEV_RX)) { - blink |= MTK_PHY_LED_BLINK_10RX | - MTK_PHY_LED_BLINK_100RX | - MTK_PHY_LED_BLINK_1000RX; + blink |= (on & MTK_PHY_LED_ON_LINK) ? + (((on & MTK_PHY_LED_ON_LINK10) ? MTK_PHY_LED_BLINK_10RX : 0) | + ((on & MTK_PHY_LED_ON_LINK100) ? MTK_PHY_LED_BLINK_100RX : 0) | + ((on & MTK_PHY_LED_ON_LINK1000) ? MTK_PHY_LED_BLINK_1000RX : 0)) : + MTK_PHY_LED_BLINK_RX; } if (rules & BIT(TRIGGER_NETDEV_TX)) { - blink |= MTK_PHY_LED_BLINK_10TX | - MTK_PHY_LED_BLINK_100TX | - MTK_PHY_LED_BLINK_1000TX; + blink |= (on & MTK_PHY_LED_ON_LINK) ? + (((on & MTK_PHY_LED_ON_LINK10) ? MTK_PHY_LED_BLINK_10TX : 0) | + ((on & MTK_PHY_LED_ON_LINK100) ? MTK_PHY_LED_BLINK_100TX : 0) | + ((on & MTK_PHY_LED_ON_LINK1000) ? MTK_PHY_LED_BLINK_1000TX : 0)) : + MTK_PHY_LED_BLINK_TX; } if (blink || on) @@ -1344,9 +1355,7 @@ static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index, MTK_PHY_LED0_ON_CTRL, MTK_PHY_LED_ON_FDX | MTK_PHY_LED_ON_HDX | - MTK_PHY_LED_ON_LINK10 | - MTK_PHY_LED_ON_LINK100 | - MTK_PHY_LED_ON_LINK1000, + MTK_PHY_LED_ON_LINK, on); if (ret) diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 752f821a19901f..df9d767cb52424 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1456,21 +1456,16 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* Skip IP alignment pseudo header */ skb_pull(skb, 2); - skb->truesize = SKB_TRUESIZE(pkt_len_plus_padd); ax88179_rx_checksum(skb, pkt_hdr); return 1; } - ax_skb = skb_clone(skb, GFP_ATOMIC); + ax_skb = netdev_alloc_skb_ip_align(dev->net, pkt_len); if (!ax_skb) return 0; - skb_trim(ax_skb, pkt_len); + skb_put(ax_skb, pkt_len); + memcpy(ax_skb->data, skb->data + 2, pkt_len); - /* Skip IP alignment pseudo header */ - skb_pull(ax_skb, 2); - - skb->truesize = pkt_len_plus_padd + - SKB_DATA_ALIGN(sizeof(struct sk_buff)); ax88179_rx_checksum(ax_skb, pkt_hdr); usbnet_skb_return(dev, ax_skb); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index edc34402e787f9..a5469cf5cf6706 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1368,6 +1368,9 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a9, 0)}, /* Telit FN920C04 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 3495591a5c29b2..ba319fc2195719 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 a6a37d67a50ad5..9f4bf41a3d41e4 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 072b0a5827d19f..eca1457caa0cad 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 9b79279fd76cad..dbbcb2d0968c09 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 4863a3c746406e..d84d7e955bb021 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 9f69e04594e49c..fe5bba8561d0c6 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 f3e3986b4c72f2..11559563ae3816 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 b55fe320633c74..59e1fc0018df3f 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 7eb17f46a8153d..9e1a34e23af26e 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/of/module.c b/drivers/of/module.c index f58e624953a20f..780fd82a7ecc58 100644 --- a/drivers/of/module.c +++ b/drivers/of/module.c @@ -29,14 +29,15 @@ ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len) csize = snprintf(str, len, "of:N%pOFn%c%s", np, 'T', of_node_get_device_type(np)); tsize = csize; + if (csize >= len) + csize = len > 0 ? len - 1 : 0; len -= csize; - if (str) - str += csize; + str += csize; of_property_for_each_string(np, "compatible", p, compat) { csize = strlen(compat) + 1; tsize += csize; - if (csize > len) + if (csize >= len) continue; csize = snprintf(str, len, "C%s", compat); diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c index 9ce0d20a6c5812..feef537257d057 100644 --- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -1022,7 +1022,7 @@ static const struct dma_map_ops ccio_ops = { .map_sg = ccio_map_sg, .unmap_sg = ccio_unmap_sg, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index 784037837f65e0..fc3863c09f83d3 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -1090,7 +1090,7 @@ static const struct dma_map_ops sba_ops = { .map_sg = sba_map_sg, .unmap_sg = sba_unmap_sg, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, }; diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index b700f52b7b6799..11fcb1867118c3 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -110,8 +110,10 @@ static int imx8_pcie_phy_power_on(struct phy *phy) /* Source clock from SoC internal PLL */ writel(ANA_PLL_CLK_OUT_TO_EXT_IO_SEL, imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG062); - writel(AUX_PLL_REFCLK_SEL_SYS_PLL, - imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG063); + if (imx8_phy->drvdata->variant != IMX8MM) { + writel(AUX_PLL_REFCLK_SEL_SYS_PLL, + imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG063); + } val = ANA_AUX_RX_TX_SEL_TX | ANA_AUX_TX_TERM; writel(val | ANA_AUX_RX_TERM_GND_EN, imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG064); diff --git a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c index 41162d7228c919..1d1db1737422a8 100644 --- a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c @@ -603,7 +603,7 @@ static void comphy_gbe_phy_init(struct mvebu_a3700_comphy_lane *lane, u16 val; fix_idx = 0; - for (addr = 0; addr < 512; addr++) { + for (addr = 0; addr < ARRAY_SIZE(gbe_phy_init); addr++) { /* * All PHY register values are defined in full for 3.125Gbps * SERDES speed. The values required for 1.25 Gbps are almost @@ -611,11 +611,12 @@ static void comphy_gbe_phy_init(struct mvebu_a3700_comphy_lane *lane, * comparison to 3.125 Gbps values. These register values are * stored in "gbe_phy_init_fix" array. */ - if (!is_1gbps && gbe_phy_init_fix[fix_idx].addr == addr) { + if (!is_1gbps && + fix_idx < ARRAY_SIZE(gbe_phy_init_fix) && + gbe_phy_init_fix[fix_idx].addr == addr) { /* Use new value */ val = gbe_phy_init_fix[fix_idx].value; - if (fix_idx < ARRAY_SIZE(gbe_phy_init_fix)) - fix_idx++; + fix_idx++; } else { val = gbe_phy_init[addr]; } diff --git a/drivers/phy/qualcomm/phy-qcom-m31.c b/drivers/phy/qualcomm/phy-qcom-m31.c index 03fb0d4b75d744..20d4c020a83c1f 100644 --- a/drivers/phy/qualcomm/phy-qcom-m31.c +++ b/drivers/phy/qualcomm/phy-qcom-m31.c @@ -297,7 +297,7 @@ static int m31usb_phy_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(qphy->phy), "failed to create phy\n"); - qphy->vreg = devm_regulator_get(dev, "vdda-phy"); + qphy->vreg = devm_regulator_get(dev, "vdd"); if (IS_ERR(qphy->vreg)) return dev_err_probe(dev, PTR_ERR(qphy->vreg), "failed to get vreg\n"); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 7d585a4bbbba95..c21cdb8dbfe746 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -77,6 +77,7 @@ enum qphy_reg_layout { QPHY_COM_BIAS_EN_CLKBUFLR_EN, QPHY_DP_PHY_STATUS, + QPHY_DP_PHY_VCO_DIV, QPHY_TX_TX_POL_INV, QPHY_TX_TX_DRV_LVL, @@ -102,6 +103,7 @@ static const unsigned int qmp_v3_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, [QPHY_DP_PHY_STATUS] = QSERDES_V3_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V3_DP_PHY_VCO_DIV, [QPHY_TX_TX_POL_INV] = QSERDES_V3_TX_TX_POL_INV, [QPHY_TX_TX_DRV_LVL] = QSERDES_V3_TX_TX_DRV_LVL, @@ -126,6 +128,7 @@ static const unsigned int qmp_v45_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V4_COM_BIAS_EN_CLKBUFLR_EN, [QPHY_DP_PHY_STATUS] = QSERDES_V4_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V4_DP_PHY_VCO_DIV, [QPHY_TX_TX_POL_INV] = QSERDES_V4_TX_TX_POL_INV, [QPHY_TX_TX_DRV_LVL] = QSERDES_V4_TX_TX_DRV_LVL, @@ -150,6 +153,7 @@ static const unsigned int qmp_v5_5nm_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V5_COM_BIAS_EN_CLKBUFLR_EN, [QPHY_DP_PHY_STATUS] = QSERDES_V5_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V5_DP_PHY_VCO_DIV, [QPHY_TX_TX_POL_INV] = QSERDES_V5_5NM_TX_TX_POL_INV, [QPHY_TX_TX_DRV_LVL] = QSERDES_V5_5NM_TX_TX_DRV_LVL, @@ -174,6 +178,7 @@ static const unsigned int qmp_v6_usb3phy_regs_layout[QPHY_LAYOUT_SIZE] = { [QPHY_COM_BIAS_EN_CLKBUFLR_EN] = QSERDES_V6_COM_PLL_BIAS_EN_CLK_BUFLR_EN, [QPHY_DP_PHY_STATUS] = QSERDES_V6_DP_PHY_STATUS, + [QPHY_DP_PHY_VCO_DIV] = QSERDES_V6_DP_PHY_VCO_DIV, [QPHY_TX_TX_POL_INV] = QSERDES_V6_TX_TX_POL_INV, [QPHY_TX_TX_DRV_LVL] = QSERDES_V6_TX_TX_DRV_LVL, @@ -2150,9 +2155,9 @@ static bool qmp_combo_configure_dp_mode(struct qmp_combo *qmp) writel(val, qmp->dp_dp_phy + QSERDES_DP_PHY_PD_CTL); if (reverse) - writel(0x4c, qmp->pcs + QSERDES_DP_PHY_MODE); + writel(0x4c, qmp->dp_dp_phy + QSERDES_DP_PHY_MODE); else - writel(0x5c, qmp->pcs + QSERDES_DP_PHY_MODE); + writel(0x5c, qmp->dp_dp_phy + QSERDES_DP_PHY_MODE); return reverse; } @@ -2162,6 +2167,7 @@ static int qmp_combo_configure_dp_clocks(struct qmp_combo *qmp) const struct phy_configure_opts_dp *dp_opts = &qmp->dp_opts; u32 phy_vco_div; unsigned long pixel_freq; + const struct qmp_phy_cfg *cfg = qmp->cfg; switch (dp_opts->link_rate) { case 1620: @@ -2184,7 +2190,7 @@ static int qmp_combo_configure_dp_clocks(struct qmp_combo *qmp) /* Other link rates aren't supported */ return -EINVAL; } - writel(phy_vco_div, qmp->dp_dp_phy + QSERDES_V4_DP_PHY_VCO_DIV); + writel(phy_vco_div, qmp->dp_dp_phy + cfg->regs[QPHY_DP_PHY_VCO_DIV]); clk_set_rate(qmp->dp_link_hw.clk, dp_opts->link_rate * 100000); clk_set_rate(qmp->dp_pixel_hw.clk, pixel_freq); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v5.h b/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v5.h index f5cfacf9be964e..181057421c113f 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v5.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v5.h @@ -7,6 +7,7 @@ #define QCOM_PHY_QMP_DP_PHY_V5_H_ /* Only for QMP V5 PHY - DP PHY registers */ +#define QSERDES_V5_DP_PHY_VCO_DIV 0x070 #define QSERDES_V5_DP_PHY_AUX_INTERRUPT_STATUS 0x0d8 #define QSERDES_V5_DP_PHY_STATUS 0x0dc diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v6.h index 01a20d3be4b812..fa967a1af058f7 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-dp-phy-v6.h @@ -7,6 +7,7 @@ #define QCOM_PHY_QMP_DP_PHY_V6_H_ /* Only for QMP V6 PHY - DP PHY registers */ +#define QSERDES_V6_DP_PHY_VCO_DIV 0x070 #define QSERDES_V6_DP_PHY_AUX_INTERRUPT_STATUS 0x0e0 #define QSERDES_V6_DP_PHY_STATUS 0x0e4 diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig index a34f67bb7e61ad..b60a4b60451e5c 100644 --- a/drivers/phy/rockchip/Kconfig +++ b/drivers/phy/rockchip/Kconfig @@ -87,6 +87,7 @@ config PHY_ROCKCHIP_SAMSUNG_HDPTX tristate "Rockchip Samsung HDMI/eDP Combo PHY driver" depends on (ARCH_ROCKCHIP || COMPILE_TEST) && OF select GENERIC_PHY + select RATIONAL help Enable this to support the Rockchip HDMI/eDP Combo PHY with Samsung IP block. diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c index 76b9cf417591de..bf74e429ff46e7 100644 --- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c +++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c @@ -125,12 +125,15 @@ struct rockchip_combphy_grfcfg { }; struct rockchip_combphy_cfg { + unsigned int num_phys; + unsigned int phy_ids[3]; const struct rockchip_combphy_grfcfg *grfcfg; int (*combphy_cfg)(struct rockchip_combphy_priv *priv); }; struct rockchip_combphy_priv { u8 type; + int id; void __iomem *mmio; int num_clks; struct clk_bulk_data *clks; @@ -320,7 +323,7 @@ static int rockchip_combphy_probe(struct platform_device *pdev) struct rockchip_combphy_priv *priv; const struct rockchip_combphy_cfg *phy_cfg; struct resource *res; - int ret; + int ret, id; phy_cfg = of_device_get_match_data(dev); if (!phy_cfg) { @@ -338,6 +341,15 @@ static int rockchip_combphy_probe(struct platform_device *pdev) return ret; } + /* find the phy-id from the io address */ + priv->id = -ENODEV; + for (id = 0; id < phy_cfg->num_phys; id++) { + if (res->start == phy_cfg->phy_ids[id]) { + priv->id = id; + break; + } + } + priv->dev = dev; priv->type = PHY_NONE; priv->cfg = phy_cfg; @@ -562,6 +574,12 @@ static const struct rockchip_combphy_grfcfg rk3568_combphy_grfcfgs = { }; static const struct rockchip_combphy_cfg rk3568_combphy_cfgs = { + .num_phys = 3, + .phy_ids = { + 0xfe820000, + 0xfe830000, + 0xfe840000, + }, .grfcfg = &rk3568_combphy_grfcfgs, .combphy_cfg = rk3568_combphy_cfg, }; @@ -578,8 +596,14 @@ static int rk3588_combphy_cfg(struct rockchip_combphy_priv *priv) rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_pcie, true); rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_pcie, true); rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_pcie, true); - rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l0_sel, true); - rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l1_sel, true); + switch (priv->id) { + case 1: + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l0_sel, true); + break; + case 2: + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l1_sel, true); + break; + } break; case PHY_TYPE_USB3: /* Set SSC downward spread spectrum */ @@ -736,6 +760,12 @@ static const struct rockchip_combphy_grfcfg rk3588_combphy_grfcfgs = { }; static const struct rockchip_combphy_cfg rk3588_combphy_cfgs = { + .num_phys = 3, + .phy_ids = { + 0xfee00000, + 0xfee10000, + 0xfee20000, + }, .grfcfg = &rk3588_combphy_grfcfgs, .combphy_cfg = rk3588_combphy_cfg, }; diff --git a/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c b/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c index 121e5961ce1147..9857ee45b89e0d 100644 --- a/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c +++ b/drivers/phy/rockchip/phy-rockchip-snps-pcie3.c @@ -40,6 +40,8 @@ #define RK3588_BIFURCATION_LANE_0_1 BIT(0) #define RK3588_BIFURCATION_LANE_2_3 BIT(1) #define RK3588_LANE_AGGREGATION BIT(2) +#define RK3588_PCIE1LN_SEL_EN (GENMASK(1, 0) << 16) +#define RK3588_PCIE30_PHY_MODE_EN (GENMASK(2, 0) << 16) struct rockchip_p3phy_ops; @@ -132,7 +134,7 @@ static const struct rockchip_p3phy_ops rk3568_ops = { static int rockchip_p3phy_rk3588_init(struct rockchip_p3phy_priv *priv) { u32 reg = 0; - u8 mode = 0; + u8 mode = RK3588_LANE_AGGREGATION; /* default */ int ret; /* Deassert PCIe PMA output clamp mode */ @@ -140,31 +142,24 @@ static int rockchip_p3phy_rk3588_init(struct rockchip_p3phy_priv *priv) /* Set bifurcation if needed */ for (int i = 0; i < priv->num_lanes; i++) { - if (!priv->lanes[i]) - mode |= (BIT(i) << 3); - if (priv->lanes[i] > 1) - mode |= (BIT(i) >> 1); - } - - if (!mode) - reg = RK3588_LANE_AGGREGATION; - else { - if (mode & (BIT(0) | BIT(1))) - reg |= RK3588_BIFURCATION_LANE_0_1; - - if (mode & (BIT(2) | BIT(3))) - reg |= RK3588_BIFURCATION_LANE_2_3; + mode &= ~RK3588_LANE_AGGREGATION; + if (priv->lanes[i] == 3) + mode |= RK3588_BIFURCATION_LANE_0_1; + if (priv->lanes[i] == 4) + mode |= RK3588_BIFURCATION_LANE_2_3; } - regmap_write(priv->phy_grf, RK3588_PCIE3PHY_GRF_CMN_CON0, (0x7<<16) | reg); + reg = mode; + regmap_write(priv->phy_grf, RK3588_PCIE3PHY_GRF_CMN_CON0, + RK3588_PCIE30_PHY_MODE_EN | reg); /* Set pcie1ln_sel in PHP_GRF_PCIESEL_CON */ if (!IS_ERR(priv->pipe_grf)) { - reg = (mode & (BIT(6) | BIT(7))) >> 6; + reg = mode & (RK3588_BIFURCATION_LANE_0_1 | RK3588_BIFURCATION_LANE_2_3); if (reg) regmap_write(priv->pipe_grf, PHP_GRF_PCIESEL_CON, - (reg << 16) | reg); + RK3588_PCIE1LN_SEL_EN | reg); } reset_control_deassert(priv->p30phy); diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c index 13cd614e12a1d3..751fecd466e3e3 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -69,7 +69,6 @@ struct tusb1210 { struct delayed_work chg_det_work; struct notifier_block psy_nb; struct power_supply *psy; - struct power_supply *charger; #endif }; @@ -236,19 +235,24 @@ static const char * const tusb1210_chargers[] = { static bool tusb1210_get_online(struct tusb1210 *tusb) { + struct power_supply *charger = NULL; union power_supply_propval val; - int i; + bool online = false; + int i, ret; - for (i = 0; i < ARRAY_SIZE(tusb1210_chargers) && !tusb->charger; i++) - tusb->charger = power_supply_get_by_name(tusb1210_chargers[i]); + for (i = 0; i < ARRAY_SIZE(tusb1210_chargers) && !charger; i++) + charger = power_supply_get_by_name(tusb1210_chargers[i]); - if (!tusb->charger) + if (!charger) return false; - if (power_supply_get_property(tusb->charger, POWER_SUPPLY_PROP_ONLINE, &val)) - return false; + ret = power_supply_get_property(charger, POWER_SUPPLY_PROP_ONLINE, &val); + if (ret == 0) + online = val.intval; + + power_supply_put(charger); - return val.intval; + return online; } static void tusb1210_chg_det_work(struct work_struct *work) @@ -473,9 +477,6 @@ static void tusb1210_remove_charger_detect(struct tusb1210 *tusb) cancel_delayed_work_sync(&tusb->chg_det_work); power_supply_unregister(tusb->psy); } - - if (tusb->charger) - power_supply_put(tusb->charger); } #else static void tusb1210_probe_charger_detect(struct tusb1210 *tusb) { } diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index ac97724c59bae9..4e87f5b875c0e8 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -231,6 +231,7 @@ static const unsigned int byt_score_pins_map[BYT_NGPIO_SCORE] = { /* SCORE groups */ static const unsigned int byt_score_uart1_pins[] = { 70, 71, 72, 73 }; static const unsigned int byt_score_uart2_pins[] = { 74, 75, 76, 77 }; +static const unsigned int byt_score_uart3_pins[] = { 57, 61 }; static const unsigned int byt_score_pwm0_pins[] = { 94 }; static const unsigned int byt_score_pwm1_pins[] = { 95 }; @@ -278,37 +279,38 @@ static const unsigned int byt_score_plt_clk5_pins[] = { 101 }; static const unsigned int byt_score_smbus_pins[] = { 51, 52, 53 }; static const struct intel_pingroup byt_score_groups[] = { - PIN_GROUP("uart1_grp", byt_score_uart1_pins, 1), - PIN_GROUP("uart2_grp", byt_score_uart2_pins, 1), - PIN_GROUP("pwm0_grp", byt_score_pwm0_pins, 1), - PIN_GROUP("pwm1_grp", byt_score_pwm1_pins, 1), - PIN_GROUP("ssp2_grp", byt_score_ssp2_pins, 1), - PIN_GROUP("sio_spi_grp", byt_score_sio_spi_pins, 1), - PIN_GROUP("i2c5_grp", byt_score_i2c5_pins, 1), - PIN_GROUP("i2c6_grp", byt_score_i2c6_pins, 1), - PIN_GROUP("i2c4_grp", byt_score_i2c4_pins, 1), - PIN_GROUP("i2c3_grp", byt_score_i2c3_pins, 1), - PIN_GROUP("i2c2_grp", byt_score_i2c2_pins, 1), - PIN_GROUP("i2c1_grp", byt_score_i2c1_pins, 1), - PIN_GROUP("i2c0_grp", byt_score_i2c0_pins, 1), - PIN_GROUP("ssp0_grp", byt_score_ssp0_pins, 1), - PIN_GROUP("ssp1_grp", byt_score_ssp1_pins, 1), - PIN_GROUP("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values), - PIN_GROUP("sdio_grp", byt_score_sdio_pins, 1), - PIN_GROUP("emmc_grp", byt_score_emmc_pins, 1), - PIN_GROUP("lpc_grp", byt_score_ilb_lpc_pins, 1), - PIN_GROUP("sata_grp", byt_score_sata_pins, 1), - PIN_GROUP("plt_clk0_grp", byt_score_plt_clk0_pins, 1), - PIN_GROUP("plt_clk1_grp", byt_score_plt_clk1_pins, 1), - PIN_GROUP("plt_clk2_grp", byt_score_plt_clk2_pins, 1), - PIN_GROUP("plt_clk3_grp", byt_score_plt_clk3_pins, 1), - PIN_GROUP("plt_clk4_grp", byt_score_plt_clk4_pins, 1), - PIN_GROUP("plt_clk5_grp", byt_score_plt_clk5_pins, 1), - PIN_GROUP("smbus_grp", byt_score_smbus_pins, 1), + PIN_GROUP_GPIO("uart1_grp", byt_score_uart1_pins, 1), + PIN_GROUP_GPIO("uart2_grp", byt_score_uart2_pins, 1), + PIN_GROUP_GPIO("uart3_grp", byt_score_uart3_pins, 1), + PIN_GROUP_GPIO("pwm0_grp", byt_score_pwm0_pins, 1), + PIN_GROUP_GPIO("pwm1_grp", byt_score_pwm1_pins, 1), + PIN_GROUP_GPIO("ssp2_grp", byt_score_ssp2_pins, 1), + PIN_GROUP_GPIO("sio_spi_grp", byt_score_sio_spi_pins, 1), + PIN_GROUP_GPIO("i2c5_grp", byt_score_i2c5_pins, 1), + PIN_GROUP_GPIO("i2c6_grp", byt_score_i2c6_pins, 1), + PIN_GROUP_GPIO("i2c4_grp", byt_score_i2c4_pins, 1), + PIN_GROUP_GPIO("i2c3_grp", byt_score_i2c3_pins, 1), + PIN_GROUP_GPIO("i2c2_grp", byt_score_i2c2_pins, 1), + PIN_GROUP_GPIO("i2c1_grp", byt_score_i2c1_pins, 1), + PIN_GROUP_GPIO("i2c0_grp", byt_score_i2c0_pins, 1), + PIN_GROUP_GPIO("ssp0_grp", byt_score_ssp0_pins, 1), + PIN_GROUP_GPIO("ssp1_grp", byt_score_ssp1_pins, 1), + PIN_GROUP_GPIO("sdcard_grp", byt_score_sdcard_pins, byt_score_sdcard_mux_values), + PIN_GROUP_GPIO("sdio_grp", byt_score_sdio_pins, 1), + PIN_GROUP_GPIO("emmc_grp", byt_score_emmc_pins, 1), + PIN_GROUP_GPIO("lpc_grp", byt_score_ilb_lpc_pins, 1), + PIN_GROUP_GPIO("sata_grp", byt_score_sata_pins, 1), + PIN_GROUP_GPIO("plt_clk0_grp", byt_score_plt_clk0_pins, 1), + PIN_GROUP_GPIO("plt_clk1_grp", byt_score_plt_clk1_pins, 1), + PIN_GROUP_GPIO("plt_clk2_grp", byt_score_plt_clk2_pins, 1), + PIN_GROUP_GPIO("plt_clk3_grp", byt_score_plt_clk3_pins, 1), + PIN_GROUP_GPIO("plt_clk4_grp", byt_score_plt_clk4_pins, 1), + PIN_GROUP_GPIO("plt_clk5_grp", byt_score_plt_clk5_pins, 1), + PIN_GROUP_GPIO("smbus_grp", byt_score_smbus_pins, 1), }; static const char * const byt_score_uart_groups[] = { - "uart1_grp", "uart2_grp", + "uart1_grp", "uart2_grp", "uart3_grp", }; static const char * const byt_score_pwm_groups[] = { "pwm0_grp", "pwm1_grp", @@ -332,12 +334,14 @@ static const char * const byt_score_plt_clk_groups[] = { }; static const char * const byt_score_smbus_groups[] = { "smbus_grp" }; static const char * const byt_score_gpio_groups[] = { - "uart1_grp", "uart2_grp", "pwm0_grp", "pwm1_grp", "ssp0_grp", - "ssp1_grp", "ssp2_grp", "sio_spi_grp", "i2c0_grp", "i2c1_grp", - "i2c2_grp", "i2c3_grp", "i2c4_grp", "i2c5_grp", "i2c6_grp", - "sdcard_grp", "sdio_grp", "emmc_grp", "lpc_grp", "sata_grp", - "plt_clk0_grp", "plt_clk1_grp", "plt_clk2_grp", "plt_clk3_grp", - "plt_clk4_grp", "plt_clk5_grp", "smbus_grp", + "uart1_grp_gpio", "uart2_grp_gpio", "uart3_grp_gpio", "pwm0_grp_gpio", + "pwm1_grp_gpio", "ssp0_grp_gpio", "ssp1_grp_gpio", "ssp2_grp_gpio", + "sio_spi_grp_gpio", "i2c0_grp_gpio", "i2c1_grp_gpio", "i2c2_grp_gpio", + "i2c3_grp_gpio", "i2c4_grp_gpio", "i2c5_grp_gpio", "i2c6_grp_gpio", + "sdcard_grp_gpio", "sdio_grp_gpio", "emmc_grp_gpio", "lpc_grp_gpio", + "sata_grp_gpio", "plt_clk0_grp_gpio", "plt_clk1_grp_gpio", + "plt_clk2_grp_gpio", "plt_clk3_grp_gpio", "plt_clk4_grp_gpio", + "plt_clk5_grp_gpio", "smbus_grp_gpio", }; static const struct intel_function byt_score_functions[] = { @@ -456,8 +460,8 @@ static const struct intel_pingroup byt_sus_groups[] = { PIN_GROUP("usb_oc_grp_gpio", byt_sus_usb_over_current_pins, byt_sus_usb_over_current_gpio_mode_values), PIN_GROUP("usb_ulpi_grp_gpio", byt_sus_usb_ulpi_pins, byt_sus_usb_ulpi_gpio_mode_values), PIN_GROUP("pcu_spi_grp_gpio", byt_sus_pcu_spi_pins, byt_sus_pcu_spi_gpio_mode_values), - PIN_GROUP("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1), - PIN_GROUP("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1), + PIN_GROUP_GPIO("pmu_clk1_grp", byt_sus_pmu_clk1_pins, 1), + PIN_GROUP_GPIO("pmu_clk2_grp", byt_sus_pmu_clk2_pins, 1), }; static const char * const byt_sus_usb_groups[] = { @@ -469,7 +473,7 @@ static const char * const byt_sus_pmu_clk_groups[] = { }; static const char * const byt_sus_gpio_groups[] = { "usb_oc_grp_gpio", "usb_ulpi_grp_gpio", "pcu_spi_grp_gpio", - "pmu_clk1_grp", "pmu_clk2_grp", + "pmu_clk1_grp_gpio", "pmu_clk2_grp_gpio", }; static const struct intel_function byt_sus_functions[] = { diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h index fde65e18cd145e..6981e2fab93f34 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.h +++ b/drivers/pinctrl/intel/pinctrl-intel.h @@ -179,6 +179,10 @@ struct intel_community { .modes = __builtin_choose_expr(__builtin_constant_p((m)), NULL, (m)), \ } +#define PIN_GROUP_GPIO(n, p, m) \ + PIN_GROUP(n, p, m), \ + PIN_GROUP(n "_gpio", p, 0) + #define FUNCTION(n, g) \ { \ .func = PINCTRL_PINFUNCTION((n), (g), ARRAY_SIZE(g)), \ diff --git a/drivers/platform/x86/uv_sysfs.c b/drivers/platform/x86/uv_sysfs.c index 38d1b692d3c0aa..40e0108771893b 100644 --- a/drivers/platform/x86/uv_sysfs.c +++ b/drivers/platform/x86/uv_sysfs.c @@ -11,6 +11,7 @@ #include <linux/device.h> #include <linux/slab.h> #include <linux/kobject.h> +#include <linux/vmalloc.h> #include <asm/uv/bios.h> #include <asm/uv/uv.h> #include <asm/uv/uv_hub.h> diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index 1305cba61edd4b..aca123783efccd 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -588,7 +588,7 @@ static const struct regulator_ops mt6360_chg_otg_ops = { }; static const struct regulator_desc mt6360_otg_rdesc = { - .of_match = "usb-otg-vbus", + .of_match = "usb-otg-vbus-regulator", .name = "usb-otg-vbus", .ops = &mt6360_chg_otg_ops, .owner = THIS_MODULE, diff --git a/drivers/power/supply/rt9455_charger.c b/drivers/power/supply/rt9455_charger.c index c345a77f9f78c0..e4dbacd50a437d 100644 --- a/drivers/power/supply/rt9455_charger.c +++ b/drivers/power/supply/rt9455_charger.c @@ -192,6 +192,7 @@ static const int rt9455_voreg_values[] = { 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000, 4450000 }; +#if IS_ENABLED(CONFIG_USB_PHY) /* * When the charger is in boost mode, REG02[7:2] represent boost output * voltage. @@ -207,6 +208,7 @@ static const int rt9455_boost_voltage_values[] = { 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, 5600000, }; +#endif /* REG07[3:0] (VMREG) in uV */ static const int rt9455_vmreg_values[] = { diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c index 42f93d4c6ee329..af972cdc04b53c 100644 --- a/drivers/pps/clients/pps_parport.c +++ b/drivers/pps/clients/pps_parport.c @@ -148,7 +148,7 @@ static void parport_attach(struct parport *port) return; } - index = ida_simple_get(&pps_client_index, 0, 0, GFP_KERNEL); + index = ida_alloc(&pps_client_index, GFP_KERNEL); memset(&pps_client_cb, 0, sizeof(pps_client_cb)); pps_client_cb.private = device; pps_client_cb.irq_func = parport_irq; @@ -188,7 +188,7 @@ err_release_dev: err_unregister_dev: parport_unregister_device(device->pardev); err_free: - ida_simple_remove(&pps_client_index, index); + ida_free(&pps_client_index, index); kfree(device); } @@ -208,7 +208,7 @@ static void parport_detach(struct parport *port) pps_unregister_source(device->pps); parport_release(pardev); parport_unregister_device(pardev); - ida_simple_remove(&pps_client_index, device->index); + ida_free(&pps_client_index, device->index); kfree(device); } diff --git a/drivers/regulator/irq_helpers.c b/drivers/regulator/irq_helpers.c index fe7ae0f3f46af9..5ab1a0befe12f7 100644 --- a/drivers/regulator/irq_helpers.c +++ b/drivers/regulator/irq_helpers.c @@ -352,6 +352,9 @@ void *regulator_irq_helper(struct device *dev, h->irq = irq; h->desc = *d; + h->desc.name = devm_kstrdup(dev, d->name, GFP_KERNEL); + if (!h->desc.name) + return ERR_PTR(-ENOMEM); ret = init_rdev_state(dev, h, rdev, common_errs, per_rdev_errs, rdev_amount); diff --git a/drivers/regulator/mt6360-regulator.c b/drivers/regulator/mt6360-regulator.c index ad6587a378d09c..24cc9fc94e900a 100644 --- a/drivers/regulator/mt6360-regulator.c +++ b/drivers/regulator/mt6360-regulator.c @@ -319,15 +319,15 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } } -#define MT6360_REGULATOR_DESC(_name, _sname, ereg, emask, vreg, vmask, \ - mreg, mmask, streg, stmask, vranges, \ - vcnts, offon_delay, irq_tbls) \ +#define MT6360_REGULATOR_DESC(match, _name, _sname, ereg, emask, vreg, \ + vmask, mreg, mmask, streg, stmask, \ + vranges, vcnts, offon_delay, irq_tbls) \ { \ .desc = { \ .name = #_name, \ .supply_name = #_sname, \ .id = MT6360_REGULATOR_##_name, \ - .of_match = of_match_ptr(#_name), \ + .of_match = of_match_ptr(match), \ .regulators_node = of_match_ptr("regulator"), \ .of_map_mode = mt6360_regulator_of_map_mode, \ .owner = THIS_MODULE, \ @@ -351,21 +351,29 @@ static unsigned int mt6360_regulator_of_map_mode(unsigned int hw_mode) } static const struct mt6360_regulator_desc mt6360_regulator_descs[] = { - MT6360_REGULATOR_DESC(BUCK1, BUCK1_VIN, 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04, + MT6360_REGULATOR_DESC("buck1", BUCK1, BUCK1_VIN, + 0x117, 0x40, 0x110, 0xff, 0x117, 0x30, 0x117, 0x04, buck_vout_ranges, 256, 0, buck1_irq_tbls), - MT6360_REGULATOR_DESC(BUCK2, BUCK2_VIN, 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04, + MT6360_REGULATOR_DESC("buck2", BUCK2, BUCK2_VIN, + 0x127, 0x40, 0x120, 0xff, 0x127, 0x30, 0x127, 0x04, buck_vout_ranges, 256, 0, buck2_irq_tbls), - MT6360_REGULATOR_DESC(LDO6, LDO_VIN3, 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04, + MT6360_REGULATOR_DESC("ldo6", LDO6, LDO_VIN3, + 0x137, 0x40, 0x13B, 0xff, 0x137, 0x30, 0x137, 0x04, ldo_vout_ranges1, 256, 0, ldo6_irq_tbls), - MT6360_REGULATOR_DESC(LDO7, LDO_VIN3, 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04, + MT6360_REGULATOR_DESC("ldo7", LDO7, LDO_VIN3, + 0x131, 0x40, 0x135, 0xff, 0x131, 0x30, 0x131, 0x04, ldo_vout_ranges1, 256, 0, ldo7_irq_tbls), - MT6360_REGULATOR_DESC(LDO1, LDO_VIN1, 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04, + MT6360_REGULATOR_DESC("ldo1", LDO1, LDO_VIN1, + 0x217, 0x40, 0x21B, 0xff, 0x217, 0x30, 0x217, 0x04, ldo_vout_ranges2, 256, 0, ldo1_irq_tbls), - MT6360_REGULATOR_DESC(LDO2, LDO_VIN1, 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04, + MT6360_REGULATOR_DESC("ldo2", LDO2, LDO_VIN1, + 0x211, 0x40, 0x215, 0xff, 0x211, 0x30, 0x211, 0x04, ldo_vout_ranges2, 256, 0, ldo2_irq_tbls), - MT6360_REGULATOR_DESC(LDO3, LDO_VIN1, 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04, + MT6360_REGULATOR_DESC("ldo3", LDO3, LDO_VIN1, + 0x205, 0x40, 0x209, 0xff, 0x205, 0x30, 0x205, 0x04, ldo_vout_ranges2, 256, 100, ldo3_irq_tbls), - MT6360_REGULATOR_DESC(LDO5, LDO_VIN2, 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04, + MT6360_REGULATOR_DESC("ldo5", LDO5, LDO_VIN2, + 0x20B, 0x40, 0x20F, 0x7f, 0x20B, 0x30, 0x20B, 0x04, ldo_vout_ranges3, 128, 100, ldo5_irq_tbls), }; diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c index 656fe330d38f0a..063e12c08e75f7 100644 --- a/drivers/regulator/qcom-refgen-regulator.c +++ b/drivers/regulator/qcom-refgen-regulator.c @@ -140,6 +140,7 @@ static const struct of_device_id qcom_refgen_match_table[] = { { .compatible = "qcom,sm8250-refgen-regulator", .data = &sm8250_refgen_desc }, { } }; +MODULE_DEVICE_TABLE(of, qcom_refgen_match_table); static struct platform_driver qcom_refgen_driver = { .probe = qcom_refgen_probe, diff --git a/drivers/regulator/vqmmc-ipq4019-regulator.c b/drivers/regulator/vqmmc-ipq4019-regulator.c index 086da36abc0b49..4955616517ce9c 100644 --- a/drivers/regulator/vqmmc-ipq4019-regulator.c +++ b/drivers/regulator/vqmmc-ipq4019-regulator.c @@ -84,6 +84,7 @@ static const struct of_device_id regulator_ipq4019_of_match[] = { { .compatible = "qcom,vqmmc-ipq4019-regulator", }, {}, }; +MODULE_DEVICE_TABLE(of, regulator_ipq4019_of_match); static struct platform_driver ipq4019_regulator_driver = { .probe = ipq4019_regulator_probe, diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index 37173cb0f5f5a2..c57694be9bd32e 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -162,7 +162,8 @@ struct raw3270_request *raw3270_request_alloc(size_t size) /* * Setup ccw. */ - rq->ccw.cda = virt_to_dma32(rq->buffer); + if (rq->buffer) + rq->ccw.cda = virt_to_dma32(rq->buffer); rq->ccw.flags = CCW_FLAG_SLI; return rq; @@ -188,7 +189,8 @@ int raw3270_request_reset(struct raw3270_request *rq) return -EBUSY; rq->ccw.cmd_code = 0; rq->ccw.count = 0; - rq->ccw.cda = virt_to_dma32(rq->buffer); + if (rq->buffer) + rq->ccw.cda = virt_to_dma32(rq->buffer); rq->ccw.flags = CCW_FLAG_SLI; rq->rescnt = 0; rq->rc = 0; diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index d32ad46318cb09..dabb91f0f75df9 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -7,6 +7,8 @@ * */ +#include <linux/vmalloc.h> + #include "mpi3mr.h" /** diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 58fdf679341dc6..65cdc8b77e3585 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3120,6 +3120,7 @@ static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer) { struct scsi_device *sdp = sdkp->device; const struct scsi_io_group_descriptor *desc, *start, *end; + u16 permanent_stream_count_old; struct scsi_sense_hdr sshdr; struct scsi_mode_data data; int res; @@ -3140,12 +3141,13 @@ static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer) for (desc = start; desc < end; desc++) if (!desc->st_enble || !sd_is_perm_stream(sdkp, desc - start)) break; + permanent_stream_count_old = sdkp->permanent_stream_count; sdkp->permanent_stream_count = desc - start; if (sdkp->rscs && sdkp->permanent_stream_count < 2) sd_printk(KERN_INFO, sdkp, "Unexpected: RSCS has been set and the permanent stream count is %u\n", sdkp->permanent_stream_count); - else if (sdkp->permanent_stream_count) + else if (sdkp->permanent_stream_count != permanent_stream_count_old) sd_printk(KERN_INFO, sdkp, "permanent stream count = %d\n", sdkp->permanent_stream_count); } diff --git a/drivers/soc/mediatek/Kconfig b/drivers/soc/mediatek/Kconfig index 50c664b65f4d44..1b7afb19ccd637 100644 --- a/drivers/soc/mediatek/Kconfig +++ b/drivers/soc/mediatek/Kconfig @@ -72,6 +72,7 @@ config MTK_SOCINFO tristate "MediaTek SoC Information" default y depends on NVMEM_MTK_EFUSE + select SOC_BUS help The MediaTek SoC Information (mtk-socinfo) driver provides information about the SoC to the userspace including the diff --git a/drivers/soc/mediatek/mtk-svs.c b/drivers/soc/mediatek/mtk-svs.c index c832f5c670bcf0..9a91298c125397 100644 --- a/drivers/soc/mediatek/mtk-svs.c +++ b/drivers/soc/mediatek/mtk-svs.c @@ -1768,6 +1768,7 @@ static int svs_bank_resource_setup(struct svs_platform *svsp) const struct svs_bank_pdata *bdata; struct svs_bank *svsb; struct dev_pm_opp *opp; + char tz_name_buf[20]; unsigned long freq; int count, ret; u32 idx, i; @@ -1819,10 +1820,12 @@ static int svs_bank_resource_setup(struct svs_platform *svsp) } if (!IS_ERR_OR_NULL(bdata->tzone_name)) { - svsb->tzd = thermal_zone_get_zone_by_name(bdata->tzone_name); + snprintf(tz_name_buf, ARRAY_SIZE(tz_name_buf), + "%s-thermal", bdata->tzone_name); + svsb->tzd = thermal_zone_get_zone_by_name(tz_name_buf); if (IS_ERR(svsb->tzd)) { dev_err(svsb->dev, "cannot get \"%s\" thermal zone\n", - bdata->tzone_name); + tz_name_buf); return PTR_ERR(svsb->tzd); } } diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index 7cd24bd8e2248e..6bcf8e75273c4e 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -130,6 +130,19 @@ static void amd_sdw_set_frameshape(struct amd_sdw_manager *amd_manager) writel(frame_size, amd_manager->mmio + ACP_SW_FRAMESIZE); } +static void amd_sdw_wake_enable(struct amd_sdw_manager *amd_manager, bool enable) +{ + u32 wake_ctrl; + + wake_ctrl = readl(amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11); + if (enable) + wake_ctrl |= AMD_SDW_WAKE_INTR_MASK; + else + wake_ctrl &= ~AMD_SDW_WAKE_INTR_MASK; + + writel(wake_ctrl, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11); +} + static void amd_sdw_ctl_word_prep(u32 *lower_word, u32 *upper_word, struct sdw_msg *msg, int cmd_offset) { @@ -1095,6 +1108,7 @@ static int __maybe_unused amd_suspend(struct device *dev) } if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + amd_sdw_wake_enable(amd_manager, false); return amd_sdw_clock_stop(amd_manager); } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { /* @@ -1121,6 +1135,7 @@ static int __maybe_unused amd_suspend_runtime(struct device *dev) return 0; } if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + amd_sdw_wake_enable(amd_manager, true); return amd_sdw_clock_stop(amd_manager); } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { ret = amd_sdw_clock_stop(amd_manager); diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h index 418b679e0b1a68..707065468e05a0 100644 --- a/drivers/soundwire/amd_manager.h +++ b/drivers/soundwire/amd_manager.h @@ -152,7 +152,7 @@ #define AMD_SDW0_EXT_INTR_MASK 0x200000 #define AMD_SDW1_EXT_INTR_MASK 4 #define AMD_SDW_IRQ_MASK_0TO7 0x77777777 -#define AMD_SDW_IRQ_MASK_8TO11 0x000d7777 +#define AMD_SDW_IRQ_MASK_8TO11 0x000c7777 #define AMD_SDW_IRQ_ERROR_MASK 0xff #define AMD_SDW_MAX_FREQ_NUM 1 #define AMD_SDW0_MAX_TX_PORTS 3 @@ -190,6 +190,7 @@ #define AMD_SDW_CLK_RESUME_REQ 2 #define AMD_SDW_CLK_RESUME_DONE 3 #define AMD_SDW_WAKE_STAT_MASK BIT(16) +#define AMD_SDW_WAKE_INTR_MASK BIT(16) static u32 amd_sdw_freq_tbl[AMD_SDW_MAX_FREQ_NUM] = { AMD_SDW_DEFAULT_CLK_FREQ, diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c index 7cc219d78551ad..e358ac5b450977 100644 --- a/drivers/spi/spi-axi-spi-engine.c +++ b/drivers/spi/spi-axi-spi-engine.c @@ -623,7 +623,7 @@ static int spi_engine_probe(struct platform_device *pdev) version = readl(spi_engine->base + ADI_AXI_REG_VERSION); if (ADI_AXI_PCORE_VER_MAJOR(version) != 1) { - dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n", + dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%u\n", ADI_AXI_PCORE_VER_MAJOR(version), ADI_AXI_PCORE_VER_MINOR(version), ADI_AXI_PCORE_VER_PATCH(version)); diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c index 35ef5e8e2ffd25..77e9738e42f60e 100644 --- a/drivers/spi/spi-hisi-kunpeng.c +++ b/drivers/spi/spi-hisi-kunpeng.c @@ -151,8 +151,6 @@ static const struct debugfs_reg32 hisi_spi_regs[] = { HISI_SPI_DBGFS_REG("ENR", HISI_SPI_ENR), HISI_SPI_DBGFS_REG("FIFOC", HISI_SPI_FIFOC), HISI_SPI_DBGFS_REG("IMR", HISI_SPI_IMR), - HISI_SPI_DBGFS_REG("DIN", HISI_SPI_DIN), - HISI_SPI_DBGFS_REG("DOUT", HISI_SPI_DOUT), HISI_SPI_DBGFS_REG("SR", HISI_SPI_SR), HISI_SPI_DBGFS_REG("RISR", HISI_SPI_RISR), HISI_SPI_DBGFS_REG("ISR", HISI_SPI_ISR), diff --git a/drivers/staging/media/atomisp/pci/hmm/hmm.c b/drivers/staging/media/atomisp/pci/hmm/hmm.c index bb12644fd033b5..3e2899ad85174f 100644 --- a/drivers/staging/media/atomisp/pci/hmm/hmm.c +++ b/drivers/staging/media/atomisp/pci/hmm/hmm.c @@ -205,7 +205,7 @@ static ia_css_ptr __hmm_alloc(size_t bytes, enum hmm_bo_type type, } dev_dbg(atomisp_dev, "pages: 0x%08x (%zu bytes), type: %d, vmalloc %p\n", - bo->start, bytes, type, vmalloc); + bo->start, bytes, type, vmalloc_noprof); return bo->start; diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 0e1262a077aea3..e7da2fca11a48c 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -51,13 +51,15 @@ static ssize_t disable_show(struct device *dev, struct usb_port *port_dev = to_usb_port(dev); struct usb_device *hdev = to_usb_device(dev->parent->parent); struct usb_hub *hub = usb_hub_to_struct_hub(hdev); - struct usb_interface *intf = to_usb_interface(hub->intfdev); + struct usb_interface *intf = to_usb_interface(dev->parent); int port1 = port_dev->portnum; u16 portstatus, unused; bool disabled; int rc; struct kernfs_node *kn; + if (!hub) + return -ENODEV; hub_get(hub); rc = usb_autopm_get_interface(intf); if (rc < 0) @@ -101,12 +103,14 @@ static ssize_t disable_store(struct device *dev, struct device_attribute *attr, struct usb_port *port_dev = to_usb_port(dev); struct usb_device *hdev = to_usb_device(dev->parent->parent); struct usb_hub *hub = usb_hub_to_struct_hub(hdev); - struct usb_interface *intf = to_usb_interface(hub->intfdev); + struct usb_interface *intf = to_usb_interface(dev->parent); int port1 = port_dev->portnum; bool disabled; int rc; struct kernfs_node *kn; + if (!hub) + return -ENODEV; rc = kstrtobool(buf, &disabled); if (rc) return rc; diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 31684cdaaae305..100041320e8dd2 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -104,6 +104,27 @@ static int dwc3_get_dr_mode(struct dwc3 *dwc) return 0; } +void dwc3_enable_susphy(struct dwc3 *dwc, bool enable) +{ + u32 reg; + + reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); + if (enable && !dwc->dis_u3_susphy_quirk) + reg |= DWC3_GUSB3PIPECTL_SUSPHY; + else + reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; + + dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), reg); + + reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + if (enable && !dwc->dis_u2_susphy_quirk) + reg |= DWC3_GUSB2PHYCFG_SUSPHY; + else + reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; + + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); +} + void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode) { u32 reg; @@ -585,11 +606,8 @@ static int dwc3_core_ulpi_init(struct dwc3 *dwc) */ static int dwc3_phy_setup(struct dwc3 *dwc) { - unsigned int hw_mode; u32 reg; - hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); - reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); /* @@ -599,21 +617,16 @@ static int dwc3_phy_setup(struct dwc3 *dwc) reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX; /* - * Above 1.94a, it is recommended to set DWC3_GUSB3PIPECTL_SUSPHY - * to '0' during coreConsultant configuration. So default value - * will be '0' when the core is reset. Application needs to set it - * to '1' after the core initialization is completed. - */ - if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) - reg |= DWC3_GUSB3PIPECTL_SUSPHY; - - /* - * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be cleared after - * power-on reset, and it can be set after core initialization, which is - * after device soft-reset during initialization. + * Above DWC_usb3.0 1.94a, it is recommended to set + * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration. + * So default value will be '0' when the core is reset. Application + * needs to set it to '1' after the core initialization is completed. + * + * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be + * cleared after power-on reset, and it can be set after core + * initialization. */ - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD) - reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; + reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; if (dwc->u2ss_inp3_quirk) reg |= DWC3_GUSB3PIPECTL_U2SSINP3OK; @@ -639,9 +652,6 @@ static int dwc3_phy_setup(struct dwc3 *dwc) if (dwc->tx_de_emphasis_quirk) reg |= DWC3_GUSB3PIPECTL_TX_DEEPH(dwc->tx_de_emphasis); - if (dwc->dis_u3_susphy_quirk) - reg &= ~DWC3_GUSB3PIPECTL_SUSPHY; - if (dwc->dis_del_phy_power_chg_quirk) reg &= ~DWC3_GUSB3PIPECTL_DEPOCHANGE; @@ -689,24 +699,15 @@ static int dwc3_phy_setup(struct dwc3 *dwc) } /* - * Above 1.94a, it is recommended to set DWC3_GUSB2PHYCFG_SUSPHY to - * '0' during coreConsultant configuration. So default value will - * be '0' when the core is reset. Application needs to set it to - * '1' after the core initialization is completed. - */ - if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) - reg |= DWC3_GUSB2PHYCFG_SUSPHY; - - /* - * For DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared after - * power-on reset, and it can be set after core initialization, which is - * after device soft-reset during initialization. + * Above DWC_usb3.0 1.94a, it is recommended to set + * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration. + * So default value will be '0' when the core is reset. Application + * needs to set it to '1' after the core initialization is completed. + * + * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared + * after power-on reset, and it can be set after core initialization. */ - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD) - reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; - - if (dwc->dis_u2_susphy_quirk) - reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; + reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; if (dwc->dis_enblslpm_quirk) reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM; @@ -1227,21 +1228,6 @@ static int dwc3_core_init(struct dwc3 *dwc) if (ret) goto err_exit_phy; - if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && - !DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) { - if (!dwc->dis_u3_susphy_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); - reg |= DWC3_GUSB3PIPECTL_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), reg); - } - - if (!dwc->dis_u2_susphy_quirk) { - reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); - reg |= DWC3_GUSB2PHYCFG_SUSPHY; - dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); - } - } - dwc3_core_setup_global_control(dwc); dwc3_core_num_eps(dwc); diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 7e80dd3d466b88..180dd8d29287c6 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1580,6 +1580,7 @@ int dwc3_event_buffers_setup(struct dwc3 *dwc); void dwc3_event_buffers_cleanup(struct dwc3 *dwc); int dwc3_core_soft_reset(struct dwc3 *dwc); +void dwc3_enable_susphy(struct dwc3 *dwc, bool enable); #if IS_ENABLED(CONFIG_USB_DWC3_HOST) || IS_ENABLED(CONFIG_USB_DWC3_DUAL_ROLE) int dwc3_host_init(struct dwc3 *dwc); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 4df2661f66751b..f94f68f1e7d2b7 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2924,6 +2924,7 @@ static int __dwc3_gadget_start(struct dwc3 *dwc) dwc3_ep0_out_start(dwc); dwc3_gadget_enable_irq(dwc); + dwc3_enable_susphy(dwc, true); return 0; @@ -4690,6 +4691,7 @@ void dwc3_gadget_exit(struct dwc3 *dwc) if (!dwc->gadget) return; + dwc3_enable_susphy(dwc, false); usb_del_gadget(dwc->gadget); dwc3_gadget_free_endpoints(dwc); usb_put_gadget(dwc->gadget); diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c index 0204787df81d50..a171b27a7845af 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -10,10 +10,13 @@ #include <linux/irq.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/usb.h> +#include <linux/usb/hcd.h> #include "../host/xhci-port.h" #include "../host/xhci-ext-caps.h" #include "../host/xhci-caps.h" +#include "../host/xhci-plat.h" #include "core.h" #define XHCI_HCSPARAMS1 0x4 @@ -57,6 +60,24 @@ static void dwc3_power_off_all_roothub_ports(struct dwc3 *dwc) } } +static void dwc3_xhci_plat_start(struct usb_hcd *hcd) +{ + struct platform_device *pdev; + struct dwc3 *dwc; + + if (!usb_hcd_is_primary_hcd(hcd)) + return; + + pdev = to_platform_device(hcd->self.controller); + dwc = dev_get_drvdata(pdev->dev.parent); + + dwc3_enable_susphy(dwc, true); +} + +static const struct xhci_plat_priv dwc3_xhci_plat_quirk = { + .plat_start = dwc3_xhci_plat_start, +}; + static void dwc3_host_fill_xhci_irq_res(struct dwc3 *dwc, int irq, char *name) { @@ -167,6 +188,11 @@ int dwc3_host_init(struct dwc3 *dwc) } } + ret = platform_device_add_data(xhci, &dwc3_xhci_plat_quirk, + sizeof(struct xhci_plat_priv)); + if (ret) + goto err; + ret = platform_device_add(xhci); if (ret) { dev_err(dwc->dev, "failed to register xHCI device\n"); @@ -192,6 +218,7 @@ void dwc3_host_exit(struct dwc3 *dwc) if (dwc->sys_wakeup) device_init_wakeup(&dwc->xhci->dev, false); + dwc3_enable_susphy(dwc, false); platform_device_unregister(dwc->xhci); dwc->xhci = NULL; } diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 0ace45b66a31c4..0e151b54aae82a 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2112,7 +2112,7 @@ unknown: buf[5] = 0x01; switch (ctrl->bRequestType & USB_RECIP_MASK) { case USB_RECIP_DEVICE: - if (w_index != 0x4 || (w_value >> 8)) + if (w_index != 0x4 || (w_value & 0xff)) break; buf[6] = w_index; /* Number of ext compat interfaces */ @@ -2128,9 +2128,9 @@ unknown: } break; case USB_RECIP_INTERFACE: - if (w_index != 0x5 || (w_value >> 8)) + if (w_index != 0x5 || (w_value & 0xff)) break; - interface = w_value & 0xFF; + interface = w_value >> 8; if (interface >= MAX_CONFIG_INTERFACES || !os_desc_cfg->interface[interface]) break; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index f855f1fc8e5e14..a057cbedf3c9b3 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -852,6 +852,7 @@ static void ffs_user_copy_worker(struct work_struct *work) work); int ret = io_data->status; bool kiocb_has_eventfd = io_data->kiocb->ki_flags & IOCB_EVENTFD; + unsigned long flags; if (io_data->read && ret > 0) { kthread_use_mm(io_data->mm); @@ -864,6 +865,11 @@ static void ffs_user_copy_worker(struct work_struct *work) if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd) eventfd_signal(io_data->ffs->ffs_eventfd); + spin_lock_irqsave(&io_data->ffs->eps_lock, flags); + usb_ep_free_request(io_data->ep, io_data->req); + io_data->req = NULL; + spin_unlock_irqrestore(&io_data->ffs->eps_lock, flags); + if (io_data->read) kfree(io_data->to_free); ffs_free_buffer(io_data); @@ -877,7 +883,6 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep, struct ffs_data *ffs = io_data->ffs; io_data->status = req->status ? req->status : req->actual; - usb_ep_free_request(_ep, req); INIT_WORK(&io_data->work, ffs_user_copy_worker); queue_work(ffs->io_completion_wq, &io_data->work); @@ -3806,7 +3811,7 @@ static int ffs_func_setup(struct usb_function *f, __ffs_event_add(ffs, FUNCTIONFS_SETUP); spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags); - return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; + return ffs->ev.setup.wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; } static bool ffs_func_req_match(struct usb_function *f, diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 7e704b2bcfd1ce..a4377df612f51e 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -92,10 +92,10 @@ static int __uvcg_iter_item_entries(const char *page, size_t len, while (pg - page < len) { i = 0; - while (i < sizeof(buf) && (pg - page < len) && + while (i < bufsize && (pg - page < len) && *pg != '\0' && *pg != '\n') buf[i++] = *pg++; - if (i == sizeof(buf)) { + if (i == bufsize) { ret = -EINVAL; goto out_free_buf; } diff --git a/drivers/usb/host/xhci-plat.h b/drivers/usb/host/xhci-plat.h index 2d15386f2c504b..6475130eac4b38 100644 --- a/drivers/usb/host/xhci-plat.h +++ b/drivers/usb/host/xhci-plat.h @@ -8,7 +8,9 @@ #ifndef _XHCI_PLAT_H #define _XHCI_PLAT_H -#include "xhci.h" /* for hcd_to_xhci() */ +struct device; +struct platform_device; +struct usb_hcd; struct xhci_plat_priv { const char *firmware_name; diff --git a/drivers/usb/host/xhci-rzv2m.c b/drivers/usb/host/xhci-rzv2m.c index ec65b24eafa868..4f59867d7117cf 100644 --- a/drivers/usb/host/xhci-rzv2m.c +++ b/drivers/usb/host/xhci-rzv2m.c @@ -6,6 +6,7 @@ */ #include <linux/usb/rzv2m_usb3drd.h> +#include "xhci.h" #include "xhci-plat.h" #include "xhci-rzv2m.h" diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c index e48412cdcb0fb5..d3958c061a972c 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c @@ -104,14 +104,18 @@ static int qcom_pmic_typec_probe(struct platform_device *pdev) ret = tcpm->port_start(tcpm, tcpm->tcpm_port); if (ret) - goto fwnode_remove; + goto port_unregister; ret = tcpm->pdphy_start(tcpm, tcpm->tcpm_port); if (ret) - goto fwnode_remove; + goto port_stop; return 0; +port_stop: + tcpm->port_stop(tcpm); +port_unregister: + tcpm_unregister_port(tcpm->tcpm_port); fwnode_remove: fwnode_remove_software_node(tcpm->tcpc.fwnode); diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c index 6560f4fc98d5a3..5b7f52b74a40aa 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c @@ -475,10 +475,8 @@ static int qcom_pmic_typec_pdphy_enable(struct pmic_typec_pdphy *pmic_typec_pdph qcom_pmic_typec_pdphy_reset_off(pmic_typec_pdphy); done: - if (ret) { - regulator_disable(pmic_typec_pdphy->vdd_pdphy); + if (ret) dev_err(dev, "pdphy_enable fail %d\n", ret); - } return ret; } @@ -524,12 +522,17 @@ static int qcom_pmic_typec_pdphy_start(struct pmic_typec *tcpm, ret = pmic_typec_pdphy_reset(pmic_typec_pdphy); if (ret) - return ret; + goto err_disable_vdd_pdhy; for (i = 0; i < pmic_typec_pdphy->nr_irqs; i++) enable_irq(pmic_typec_pdphy->irq_data[i].irq); return 0; + +err_disable_vdd_pdhy: + regulator_disable(pmic_typec_pdphy->vdd_pdphy); + + return ret; } static void qcom_pmic_typec_pdphy_stop(struct pmic_typec *tcpm) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index b246067e074bc0..6cb96a1e8b7df4 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/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c index 68e8f006dfdbf7..c51f5e4c3dd6d2 100644 --- a/drivers/vfio/pci/pds/dirty.c +++ b/drivers/vfio/pci/pds/dirty.c @@ -3,6 +3,7 @@ #include <linux/interval_tree.h> #include <linux/vfio.h> +#include <linux/vmalloc.h> #include <linux/pds/pds_common.h> #include <linux/pds/pds_core_if.h> diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index b5c15fe8f9fcf9..3a0218171cfaa0 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -518,7 +518,7 @@ static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm, spinlock_t *ptl; int ret; - ret = follow_pte(vma->vm_mm, vaddr, &ptep, &ptl); + ret = follow_pte(vma, vaddr, &ptep, &ptl); if (ret) { bool unlocked = false; @@ -532,7 +532,7 @@ static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm, if (ret) return ret; - ret = follow_pte(vma->vm_mm, vaddr, &ptep, &ptl); + ret = follow_pte(vma, vaddr, &ptep, &ptl); if (ret) return ret; } diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index dae96c9f61cf87..806ecd32219b69 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -196,7 +196,7 @@ err_mutex_unlock: */ static vm_fault_t fb_deferred_io_page_mkwrite(struct fb_info *info, struct vm_fault *vmf) { - unsigned long offset = vmf->address - vmf->vma->vm_start; + unsigned long offset = vmf->pgoff << PAGE_SHIFT; struct page *page = vmf->page; file_update_time(vmf->vma->vm_file); diff --git a/drivers/virt/acrn/mm.c b/drivers/virt/acrn/mm.c index fa5d9ca6be5706..db8ff1d0ac23ce 100644 --- a/drivers/virt/acrn/mm.c +++ b/drivers/virt/acrn/mm.c @@ -12,6 +12,7 @@ #include <linux/io.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include "acrn_drv.h" @@ -155,43 +156,82 @@ int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) { struct vm_memory_region_batch *regions_info; - int nr_pages, i = 0, order, nr_regions = 0; + int nr_pages, i, order, nr_regions = 0; struct vm_memory_mapping *region_mapping; struct vm_memory_region_op *vm_region; struct page **pages = NULL, *page; void *remap_vaddr; int ret, pinned; u64 user_vm_pa; - unsigned long pfn; struct vm_area_struct *vma; if (!vm || !memmap) return -EINVAL; + /* Get the page number of the map region */ + nr_pages = memmap->len >> PAGE_SHIFT; + if (!nr_pages) + return -EINVAL; + mmap_read_lock(current->mm); vma = vma_lookup(current->mm, memmap->vma_base); if (vma && ((vma->vm_flags & VM_PFNMAP) != 0)) { + unsigned long start_pfn, cur_pfn; + spinlock_t *ptl; + bool writable; + pte_t *ptep; + if ((memmap->vma_base + memmap->len) > vma->vm_end) { mmap_read_unlock(current->mm); return -EINVAL; } - ret = follow_pfn(vma, memmap->vma_base, &pfn); + for (i = 0; i < nr_pages; i++) { + ret = follow_pte(vma, memmap->vma_base + i * PAGE_SIZE, + &ptep, &ptl); + if (ret) + break; + + cur_pfn = pte_pfn(ptep_get(ptep)); + if (i == 0) + start_pfn = cur_pfn; + writable = !!pte_write(ptep_get(ptep)); + pte_unmap_unlock(ptep, ptl); + + /* Disallow write access if the PTE is not writable. */ + if (!writable && + (memmap->attr & ACRN_MEM_ACCESS_WRITE)) { + ret = -EFAULT; + break; + } + + /* Disallow refcounted pages. */ + if (pfn_valid(cur_pfn) && + !PageReserved(pfn_to_page(cur_pfn))) { + ret = -EFAULT; + break; + } + + /* Disallow non-contiguous ranges. */ + if (cur_pfn != start_pfn + i) { + ret = -EINVAL; + break; + } + } mmap_read_unlock(current->mm); - if (ret < 0) { + + if (ret) { dev_dbg(acrn_dev.this_device, "Failed to lookup PFN at VMA:%pK.\n", (void *)memmap->vma_base); return ret; } return acrn_mm_region_add(vm, memmap->user_vm_pa, - PFN_PHYS(pfn), memmap->len, + PFN_PHYS(start_pfn), memmap->len, ACRN_MEM_TYPE_WB, memmap->attr); } mmap_read_unlock(current->mm); - /* Get the page number of the map region */ - nr_pages = memmap->len >> PAGE_SHIFT; pages = vzalloc(array_size(nr_pages, sizeof(*pages))); if (!pages) return -ENOMEM; @@ -235,12 +275,11 @@ int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) mutex_unlock(&vm->regions_mapping_lock); /* Calculate count of vm_memory_region_op */ - while (i < nr_pages) { + for (i = 0; i < nr_pages; i += 1 << order) { page = pages[i]; VM_BUG_ON_PAGE(PageTail(page), page); order = compound_order(page); nr_regions++; - i += 1 << order; } /* Prepare the vm_memory_region_batch */ @@ -257,8 +296,7 @@ int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) regions_info->vmid = vm->vmid; regions_info->regions_gpa = virt_to_phys(vm_region); user_vm_pa = memmap->user_vm_pa; - i = 0; - while (i < nr_pages) { + for (i = 0; i < nr_pages; i += 1 << order) { u32 region_size; page = pages[i]; @@ -274,7 +312,6 @@ int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap) vm_region++; user_vm_pa += region_size; - i += 1 << order; } /* Inform the ACRN Hypervisor to set up EPT mappings */ diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 8e322329444237..e8355f55a8f7e8 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -21,6 +21,7 @@ #include <linux/bitmap.h> #include <linux/lockdep.h> #include <linux/log2.h> +#include <linux/vmalloc.h> #include <acpi/acpi_numa.h> diff --git a/drivers/xen/grant-dma-ops.c b/drivers/xen/grant-dma-ops.c index 76f6f26265a3b8..29257d2639dbf0 100644 --- a/drivers/xen/grant-dma-ops.c +++ b/drivers/xen/grant-dma-ops.c @@ -282,7 +282,7 @@ static int xen_grant_dma_supported(struct device *dev, u64 mask) static const struct dma_map_ops xen_grant_dma_ops = { .alloc = xen_grant_dma_alloc, .free = xen_grant_dma_free, - .alloc_pages = xen_grant_dma_alloc_pages, + .alloc_pages_op = xen_grant_dma_alloc_pages, .free_pages = xen_grant_dma_free_pages, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 0e6c6c25d154f5..1c4ef5111651d6 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -403,7 +403,7 @@ const struct dma_map_ops xen_swiotlb_dma_ops = { .dma_supported = xen_swiotlb_dma_supported, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, .max_mapping_size = swiotlb_max_mapping_size, }; diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 9defa12208f98a..1775fcc7f0e8ef 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -179,13 +179,14 @@ extern int v9fs_vfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); -extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid); +extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, + bool new); extern const struct inode_operations v9fs_dir_inode_operations_dotl; extern const struct inode_operations v9fs_file_inode_operations_dotl; extern const struct inode_operations v9fs_symlink_inode_operations_dotl; extern const struct netfs_request_ops v9fs_req_ops; extern struct inode *v9fs_fid_iget_dotl(struct super_block *sb, - struct p9_fid *fid); + struct p9_fid *fid, bool new); /* other default globals */ #define V9FS_PORT 564 @@ -224,12 +225,12 @@ static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses) */ static inline struct inode * v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid, - struct super_block *sb) + struct super_block *sb, bool new) { if (v9fs_proto_dotl(v9ses)) - return v9fs_fid_iget_dotl(sb, fid); + return v9fs_fid_iget_dotl(sb, fid, new); else - return v9fs_fid_iget(sb, fid); + return v9fs_fid_iget(sb, fid, new); } #endif diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 47bd77199e20c8..7a3308d776060e 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -364,7 +364,8 @@ void v9fs_evict_inode(struct inode *inode) clear_inode(inode); } -struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid) +struct inode * +v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, bool new) { dev_t rdev; int retval; @@ -376,8 +377,18 @@ struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid) inode = iget_locked(sb, QID2INO(&fid->qid)); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) - return inode; + if (!(inode->i_state & I_NEW)) { + if (!new) { + goto done; + } else { + p9_debug(P9_DEBUG_VFS, "WARNING: Inode collision %ld\n", + inode->i_ino); + iput(inode); + remove_inode_hash(inode); + inode = iget_locked(sb, QID2INO(&fid->qid)); + WARN_ON(!(inode->i_state & I_NEW)); + } + } /* * initialize the inode with the stat info @@ -401,11 +412,11 @@ struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid) v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); +done: return inode; error: iget_failed(inode); return ERR_PTR(retval); - } /** @@ -437,8 +448,15 @@ static int v9fs_at_to_dotl_flags(int flags) */ static void v9fs_dec_count(struct inode *inode) { - if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) - drop_nlink(inode); + if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) { + if (inode->i_nlink) { + drop_nlink(inode); + } else { + p9_debug(P9_DEBUG_VFS, + "WARNING: unexpected i_nlink zero %d inode %ld\n", + inode->i_nlink, inode->i_ino); + } + } } /** @@ -489,6 +507,9 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags) } else v9fs_dec_count(inode); + if (inode->i_nlink <= 0) /* no more refs unhash it */ + remove_inode_hash(inode); + v9fs_invalidate_inode_attr(inode); v9fs_invalidate_inode_attr(dir); @@ -554,7 +575,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, /* * instantiate inode and assign the unopened fid to the dentry */ - inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb); + inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, true); if (IS_ERR(inode)) { err = PTR_ERR(inode); p9_debug(P9_DEBUG_VFS, @@ -683,7 +704,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, else if (IS_ERR(fid)) inode = ERR_CAST(fid); else - inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb); + inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, false); /* * If we had a rename on the server and a parallel lookup * for the new name, then make sure we instantiate with diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 55dde186041a38..c61b97bd13b9a7 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 55e67e36ae682b..f52fdf42945cf1 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -139,7 +139,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, else sb->s_d_op = &v9fs_dentry_operations; - inode = v9fs_get_inode_from_fid(v9ses, fid, sb); + inode = v9fs_get_inode_from_fid(v9ses, fid, sb, true); if (IS_ERR(inode)) { retval = PTR_ERR(inode); goto release_sb; diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index fadb1078903d29..a200442010025a 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -470,7 +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/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index 085987435a5ea3..f7fbfccd2b1e4d 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -1504,7 +1504,8 @@ enum btree_id_flags { BIT_ULL(KEY_TYPE_stripe)) \ x(reflink, 7, BTREE_ID_EXTENTS|BTREE_ID_DATA, \ BIT_ULL(KEY_TYPE_reflink_v)| \ - BIT_ULL(KEY_TYPE_indirect_inline_data)) \ + BIT_ULL(KEY_TYPE_indirect_inline_data)| \ + BIT_ULL(KEY_TYPE_error)) \ x(subvolumes, 8, 0, \ BIT_ULL(KEY_TYPE_subvolume)) \ x(snapshots, 9, 0, \ diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index ecbd9598f69fd0..791470b0c65455 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -1587,7 +1587,7 @@ static int bch2_gc_write_reflink_key(struct btree_trans *trans, struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); ret = PTR_ERR_OR_ZERO(new); if (ret) - return ret; + goto out; if (!r->refcount) new->k.type = KEY_TYPE_deleted; @@ -1595,6 +1595,7 @@ static int bch2_gc_write_reflink_key(struct btree_trans *trans, *bkey_refcount(bkey_i_to_s(new)) = cpu_to_le64(r->refcount); ret = bch2_trans_update(trans, iter, new, 0); } +out: fsck_err: printbuf_exit(&buf); return ret; diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index 9678b2375bedde..debb0edc3455af 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -888,7 +888,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, -BCH_ERR_btree_node_read_err_fixable, c, NULL, b, i, btree_node_bkey_bad_u64s, - "bad k->u64s %u (min %u max %lu)", k->u64s, + "bad k->u64s %u (min %u max %zu)", k->u64s, bkeyp_key_u64s(&b->format, k), U8_MAX - BKEY_U64s + bkeyp_key_u64s(&b->format, k))) goto drop_this_key; diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 88a3582a32757e..e8c1c530cd95f5 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -842,8 +842,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, * Newest freed entries are at the end of the list - once we hit one * that's too new to be freed, we can bail out: */ - scanned += bc->nr_freed_nonpcpu; - list_for_each_entry_safe(ck, t, &bc->freed_nonpcpu, list) { if (!poll_state_synchronize_srcu(&c->btree_trans_barrier, ck->btree_trans_barrier_seq)) @@ -857,11 +855,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, bc->nr_freed_nonpcpu--; } - if (scanned >= nr) - goto out; - - scanned += bc->nr_freed_pcpu; - list_for_each_entry_safe(ck, t, &bc->freed_pcpu, list) { if (!poll_state_synchronize_srcu(&c->btree_trans_barrier, ck->btree_trans_barrier_seq)) @@ -875,9 +868,6 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, bc->nr_freed_pcpu--; } - if (scanned >= nr) - goto out; - rcu_read_lock(); tbl = rht_dereference_rcu(bc->table.tbl, &bc->table); if (bc->shrink_iter >= tbl->size) @@ -893,12 +883,12 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, next = rht_dereference_bucket_rcu(pos->next, tbl, bc->shrink_iter); ck = container_of(pos, struct bkey_cached, hash); - if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) + if (test_bit(BKEY_CACHED_DIRTY, &ck->flags)) { goto next; - - if (test_bit(BKEY_CACHED_ACCESSED, &ck->flags)) + } else if (test_bit(BKEY_CACHED_ACCESSED, &ck->flags)) { clear_bit(BKEY_CACHED_ACCESSED, &ck->flags); - else if (bkey_cached_lock_for_evict(ck)) { + goto next; + } else if (bkey_cached_lock_for_evict(ck)) { bkey_cached_evict(bc, ck); bkey_cached_free(bc, ck); } @@ -916,7 +906,6 @@ 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_node_scan.c b/fs/bcachefs/btree_node_scan.c index 866bd278439f8b..c60794264da289 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -302,6 +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; diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index e0c982a4195c76..c69b233c41bb3d 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -321,9 +321,9 @@ struct bkey_cached { struct btree_bkey_cached_common c; unsigned long flags; + unsigned long btree_trans_barrier_seq; u16 u64s; bool valid; - u32 btree_trans_barrier_seq; struct bkey_cached_key key; struct rhash_head hash; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index 6030c396754f6f..b4efd8cc4d1a2b 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -1960,7 +1960,11 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans, if ((flags & BCH_WATERMARK_MASK) == BCH_WATERMARK_interior_updates) return 0; - flags &= ~BCH_WATERMARK_MASK; + if ((flags & BCH_WATERMARK_MASK) <= BCH_WATERMARK_reclaim) { + flags &= ~BCH_WATERMARK_MASK; + flags |= BCH_WATERMARK_btree; + flags |= BCH_TRANS_COMMIT_journal_reclaim; + } b = trans->paths[path].l[level].b; diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index 72781aad6ba70c..4d14f19f51850e 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -232,13 +232,15 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a /* We need request_key() to be called before we punt to kthread: */ opt_set(thr->opts, nostart, true); + bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops); + thr->c = bch2_fs_open(devs.data, arg.nr_devs, thr->opts); if (!IS_ERR(thr->c) && thr->c->opts.errors == BCH_ON_ERROR_panic) thr->c->opts.errors = BCH_ON_ERROR_ro; - ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_offline_fsck_ops); + ret = __bch2_run_thread_with_stdio(&thr->thr); out: darray_for_each(devs, i) kfree(*i); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index b5ea9fa1259d14..fce690007edfce 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 9aa28b52ab926c..eb1f9d6f5a196e 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -1723,7 +1723,7 @@ static void journal_write_endio(struct bio *bio) percpu_ref_put(&ca->io_ref); } -static CLOSURE_CALLBACK(do_journal_write) +static CLOSURE_CALLBACK(journal_write_submit) { closure_type(w, struct journal_buf, io); struct journal *j = container_of(w, struct journal, buf[w->idx]); @@ -1768,6 +1768,44 @@ static CLOSURE_CALLBACK(do_journal_write) continue_at(cl, journal_write_done, j->wq); } +static CLOSURE_CALLBACK(journal_write_preflush) +{ + closure_type(w, struct journal_buf, io); + struct journal *j = container_of(w, struct journal, buf[w->idx]); + struct bch_fs *c = container_of(j, struct bch_fs, journal); + + if (j->seq_ondisk + 1 != le64_to_cpu(w->data->seq)) { + spin_lock(&j->lock); + closure_wait(&j->async_wait, cl); + spin_unlock(&j->lock); + + continue_at(cl, journal_write_preflush, j->wq); + return; + } + + if (w->separate_flush) { + for_each_rw_member(c, ca) { + percpu_ref_get(&ca->io_ref); + + struct journal_device *ja = &ca->journal; + struct bio *bio = &ja->bio[w->idx]->bio; + bio_reset(bio, ca->disk_sb.bdev, + REQ_OP_WRITE|REQ_SYNC|REQ_META|REQ_PREFLUSH); + bio->bi_end_io = journal_write_endio; + bio->bi_private = ca; + closure_bio_submit(bio, cl); + } + + continue_at(cl, journal_write_submit, j->wq); + } else { + /* + * no need to punt to another work item if we're not waiting on + * preflushes + */ + journal_write_submit(&cl->work); + } +} + static int bch2_journal_write_prep(struct journal *j, struct journal_buf *w) { struct bch_fs *c = container_of(j, struct bch_fs, journal); @@ -2033,23 +2071,9 @@ CLOSURE_CALLBACK(bch2_journal_write) goto err; if (!JSET_NO_FLUSH(w->data)) - closure_wait_event(&j->async_wait, j->seq_ondisk + 1 == le64_to_cpu(w->data->seq)); - - if (!JSET_NO_FLUSH(w->data) && w->separate_flush) { - for_each_rw_member(c, ca) { - percpu_ref_get(&ca->io_ref); - - struct journal_device *ja = &ca->journal; - struct bio *bio = &ja->bio[w->idx]->bio; - bio_reset(bio, ca->disk_sb.bdev, - REQ_OP_WRITE|REQ_SYNC|REQ_META|REQ_PREFLUSH); - bio->bi_end_io = journal_write_endio; - bio->bi_private = ca; - closure_bio_submit(bio, cl); - } - } - - continue_at(cl, do_journal_write, j->wq); + continue_at(cl, journal_write_preflush, j->wq); + else + continue_at(cl, journal_write_submit, j->wq); return; no_io: continue_at(cl, journal_write_done, j->wq); diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 0f328aba9760ba..be5b4761932700 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -249,7 +249,10 @@ int bch2_journal_replay(struct bch_fs *c) struct journal_key *k = *kp; - replay_now_at(j, k->journal_seq); + if (k->journal_seq) + replay_now_at(j, k->journal_seq); + else + replay_now_at(j, j->replay_journal_seq_end); ret = commit_do(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc| diff --git a/fs/bcachefs/sb-clean.c b/fs/bcachefs/sb-clean.c index 5980ba2563fe9f..35ca3f138de6fa 100644 --- a/fs/bcachefs/sb-clean.c +++ b/fs/bcachefs/sb-clean.c @@ -29,6 +29,14 @@ int bch2_sb_clean_validate_late(struct bch_fs *c, struct bch_sb_field_clean *cle for (entry = clean->start; entry < (struct jset_entry *) vstruct_end(&clean->field); entry = vstruct_next(entry)) { + if (vstruct_end(entry) > vstruct_end(&clean->field)) { + bch_err(c, "journal entry (u64s %u) overran end of superblock clean section (u64s %u) by %zu", + le16_to_cpu(entry->u64s), le32_to_cpu(clean->field.u64s), + (u64 *) vstruct_end(entry) - (u64 *) vstruct_end(&clean->field)); + bch2_sb_error_count(c, BCH_FSCK_ERR_sb_clean_entry_overrun); + return -BCH_ERR_fsck_repair_unimplemented; + } + ret = bch2_journal_entry_validate(c, NULL, entry, le16_to_cpu(c->disk_sb.sb->version), BCH_SB_BIG_ENDIAN(c->disk_sb.sb), diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h index 4ca6e7b0d8aaed..06c7a644f4a442 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -271,7 +271,8 @@ x(btree_root_unreadable_and_scan_found_nothing, 263) \ x(snapshot_node_missing, 264) \ x(dup_backpointer_to_bad_csum_extent, 265) \ - x(btree_bitmap_not_marked, 266) + x(btree_bitmap_not_marked, 266) \ + x(sb_clean_entry_overrun, 267) enum bch_sb_error_id { #define x(t, n) BCH_FSCK_ERR_##t = n, diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c index 522a969345e528..5b8e621ac5eb57 100644 --- a/fs/bcachefs/sb-members.c +++ b/fs/bcachefs/sb-members.c @@ -463,8 +463,8 @@ static void __bch2_dev_btree_bitmap_mark(struct bch_sb_field_members_v2 *mi, uns m->btree_bitmap_shift += resize; } - for (unsigned bit = sectors >> m->btree_bitmap_shift; - bit << m->btree_bitmap_shift < end; + for (unsigned bit = start >> m->btree_bitmap_shift; + (u64) bit << m->btree_bitmap_shift < end; bit++) bitmap |= BIT_ULL(bit); diff --git a/fs/bcachefs/sb-members.h b/fs/bcachefs/sb-members.h index b27c3e4467cf28..5efa64eca5f85a 100644 --- a/fs/bcachefs/sb-members.h +++ b/fs/bcachefs/sb-members.h @@ -235,11 +235,11 @@ static inline bool bch2_dev_btree_bitmap_marked_sectors(struct bch_dev *ca, u64 { u64 end = start + sectors; - if (end > 64 << ca->mi.btree_bitmap_shift) + if (end > 64ULL << ca->mi.btree_bitmap_shift) return false; - for (unsigned bit = sectors >> ca->mi.btree_bitmap_shift; - bit << ca->mi.btree_bitmap_shift < end; + for (unsigned bit = start >> ca->mi.btree_bitmap_shift; + (u64) bit << ca->mi.btree_bitmap_shift < end; bit++) if (!(ca->mi.btree_allocated_bitmap & BIT_ULL(bit))) return false; diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index 8daf80a38d60c6..88e214c609bb2b 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -544,6 +544,7 @@ static void __bch2_fs_free(struct bch_fs *c) bch2_find_btree_nodes_exit(&c->found_btree_nodes); bch2_free_pending_node_rewrites(c); + bch2_fs_allocator_background_exit(c); bch2_fs_sb_errors_exit(c); bch2_fs_counters_exit(c); bch2_fs_snapshots_exit(c); diff --git a/fs/bcachefs/thread_with_file.c b/fs/bcachefs/thread_with_file.c index 940db15d6a939b..b1af7ac430f662 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 af54ea8f5b0ff8..1d63d14d7dcae8 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/binfmt_elf.c b/fs/binfmt_elf.c index 5397b552fbeb54..ac178ad388239a 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1928,7 +1928,7 @@ static void free_note_info(struct elf_note_info *info) threads = t->next; WARN_ON(t->notes[0].data && t->notes[0].data != &t->prstatus); for (i = 1; i < info->thread_notes; ++i) - kfree(t->notes[i].data); + kvfree(t->notes[i].data); kfree(t); } kfree(info->psinfo.data); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index c1e6a5bbeeaffe..58110c96866736 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -2776,20 +2776,14 @@ struct btrfs_data_container *init_data_container(u32 total_bytes) size_t alloc_bytes; alloc_bytes = max_t(size_t, total_bytes, sizeof(*data)); - data = kvmalloc(alloc_bytes, GFP_KERNEL); + data = kvzalloc(alloc_bytes, GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); - if (total_bytes >= sizeof(*data)) { + if (total_bytes >= sizeof(*data)) data->bytes_left = total_bytes - sizeof(*data); - data->bytes_missing = 0; - } else { + else data->bytes_missing = sizeof(*data) - total_bytes; - data->bytes_left = 0; - } - - data->elem_cnt = 0; - data->elem_missed = 0; return data; } diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 445f7716f1e2f7..24a048210b1571 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 c65fe5de40220d..7fed887e700c4e 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 | diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 55f3ba6a831ca1..0493272a7668ed 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3758,15 +3758,43 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) goto drop_write; } - down_write(&fs_info->subvol_sem); - switch (sa->cmd) { case BTRFS_QUOTA_CTL_ENABLE: case BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA: + down_write(&fs_info->subvol_sem); ret = btrfs_quota_enable(fs_info, sa); + up_write(&fs_info->subvol_sem); break; case BTRFS_QUOTA_CTL_DISABLE: + /* + * Lock the cleaner mutex to prevent races with concurrent + * relocation, because relocation may be building backrefs for + * blocks of the quota root while we are deleting the root. This + * is like dropping fs roots of deleted snapshots/subvolumes, we + * need the same protection. + * + * This also prevents races between concurrent tasks trying to + * disable quotas, because we will unlock and relock + * qgroup_ioctl_lock across BTRFS_FS_QUOTA_ENABLED changes. + * + * We take this here because we have the dependency of + * + * inode_lock -> subvol_sem + * + * because of rename. With relocation we can prealloc extents, + * so that makes the dependency chain + * + * cleaner_mutex -> inode_lock -> subvol_sem + * + * so we must take the cleaner_mutex here before we take the + * subvol_sem. The deadlock can't actually happen, but this + * quiets lockdep. + */ + mutex_lock(&fs_info->cleaner_mutex); + down_write(&fs_info->subvol_sem); ret = btrfs_quota_disable(fs_info); + up_write(&fs_info->subvol_sem); + mutex_unlock(&fs_info->cleaner_mutex); break; default: ret = -EINVAL; @@ -3774,7 +3802,6 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg) } kfree(sa); - up_write(&fs_info->subvol_sem); drop_write: mnt_drop_write_file(file); return ret; diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c index c96dd66fd0f722..210d9c82e2ae05 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 cf8820ce7aa297..364acc9bbe730c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1342,16 +1342,10 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) lockdep_assert_held_write(&fs_info->subvol_sem); /* - * Lock the cleaner mutex to prevent races with concurrent relocation, - * because relocation may be building backrefs for blocks of the quota - * root while we are deleting the root. This is like dropping fs roots - * of deleted snapshots/subvolumes, we need the same protection. - * - * This also prevents races between concurrent tasks trying to disable - * quotas, because we will unlock and relock qgroup_ioctl_lock across - * BTRFS_FS_QUOTA_ENABLED changes. + * Relocation will mess with backrefs, so make sure we have the + * cleaner_mutex held to protect us from relocate. */ - mutex_lock(&fs_info->cleaner_mutex); + lockdep_assert_held(&fs_info->cleaner_mutex); mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) @@ -1373,9 +1367,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); + /* + * We have nothing held here and no trans handle, just return the error + * if there is one. + */ ret = flush_reservations(fs_info); if (ret) - goto out_unlock_cleaner; + return ret; /* * 1 For the root item @@ -1439,9 +1437,6 @@ out: btrfs_end_transaction(trans); else if (trans) ret = btrfs_commit_transaction(trans); -out_unlock_cleaner: - mutex_unlock(&fs_info->cleaner_mutex); - return ret; } diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index fa25004ab04e7b..4b22cfe9a98cb0 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 253cce7ffecfe5..47b5d301038eed 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -847,6 +847,11 @@ static int test_case_7(struct btrfs_fs_info *fs_info) goto out; } + if (em->block_start != SZ_32K + SZ_4K) { + test_err("em->block_start is %llu, expected 36K", em->block_start); + goto out; + } + free_extent_map(em); read_lock(&em_tree->lock); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f15591f3e54fa4..ef6bd2f4251b52 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3455,6 +3455,7 @@ again: * alignment and size). */ ret = -EUCLEAN; + mutex_unlock(&fs_info->reclaim_bgs_lock); goto error; } diff --git a/fs/buffer.c b/fs/buffer.c index 4f73d23c2c4691..ed698caa8834b2 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -687,30 +687,37 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) } EXPORT_SYMBOL(mark_buffer_dirty_inode); -/* - * Add a page to the dirty page list. - * - * It is a sad fact of life that this function is called from several places - * deeply under spinlocking. It may not sleep. - * - * If the page has buffers, the uptodate buffers are set dirty, to preserve - * dirty-state coherency between the page and the buffers. It the page does - * not have buffers then when they are later attached they will all be set - * dirty. - * - * The buffers are dirtied before the page is dirtied. There's a small race - * window in which a writepage caller may see the page cleanness but not the - * buffer dirtiness. That's fine. If this code were to set the page dirty - * before the buffers, a concurrent writepage caller could clear the page dirty - * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean - * page on the dirty page list. - * - * We use i_private_lock to lock against try_to_free_buffers while using the - * page's buffer list. Also use this to protect against clean buffers being - * added to the page after it was set dirty. - * - * FIXME: may need to call ->reservepage here as well. That's rather up to the - * address_space though. +/** + * block_dirty_folio - Mark a folio as dirty. + * @mapping: The address space containing this folio. + * @folio: The folio to mark dirty. + * + * Filesystems which use buffer_heads can use this function as their + * ->dirty_folio implementation. Some filesystems need to do a little + * work before calling this function. Filesystems which do not use + * buffer_heads should call filemap_dirty_folio() instead. + * + * If the folio has buffers, the uptodate buffers are set dirty, to + * preserve dirty-state coherency between the folio and the buffers. + * Buffers added to a dirty folio are created dirty. + * + * The buffers are dirtied before the folio is dirtied. There's a small + * race window in which writeback may see the folio cleanness but not the + * buffer dirtiness. That's fine. If this code were to set the folio + * dirty before the buffers, writeback could clear the folio dirty flag, + * see a bunch of clean buffers and we'd end up with dirty buffers/clean + * folio on the dirty folio list. + * + * We use i_private_lock to lock against try_to_free_buffers() while + * using the folio's buffer list. This also prevents clean buffers + * being added to the folio after it was set dirty. + * + * Context: May only be called from process context. Does not sleep. + * Caller must ensure that @folio cannot be truncated during this call, + * typically by holding the folio lock or having a page in the folio + * mapped and holding the page table lock. + * + * Return: True if the folio was dirtied; false if it was already dirtied. */ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) { @@ -1219,26 +1226,28 @@ void mark_buffer_write_io_error(struct buffer_head *bh) } EXPORT_SYMBOL(mark_buffer_write_io_error); -/* - * Decrement a buffer_head's reference count. If all buffers against a page - * have zero reference count, are clean and unlocked, and if the page is clean - * and unlocked then try_to_free_buffers() may strip the buffers from the page - * in preparation for freeing it (sometimes, rarely, buffers are removed from - * a page but it ends up not being freed, and buffers may later be reattached). +/** + * __brelse - Release a buffer. + * @bh: The buffer to release. + * + * This variant of brelse() can be called if @bh is guaranteed to not be NULL. */ -void __brelse(struct buffer_head * buf) +void __brelse(struct buffer_head *bh) { - if (atomic_read(&buf->b_count)) { - put_bh(buf); + if (atomic_read(&bh->b_count)) { + put_bh(bh); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); -/* - * bforget() is like brelse(), except it discards any - * potentially dirty data. +/** + * __bforget - Discard any dirty data in a buffer. + * @bh: The buffer to forget. + * + * This variant of bforget() can be called if @bh is guaranteed to not + * be NULL. */ void __bforget(struct buffer_head *bh) { @@ -1415,6 +1424,11 @@ EXPORT_SYMBOL(__find_get_block); * @size: The size of buffer_heads for this @bdev. * @gfp: The memory allocation flags to use. * + * The returned buffer head has its reference count incremented, but is + * not locked. The caller should call brelse() when it has finished + * with the buffer. The buffer may not be uptodate. If needed, the + * caller can bring it uptodate either by reading it or overwriting it. + * * Return: The buffer head, or NULL if memory could not be allocated. */ struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, @@ -1446,20 +1460,29 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) EXPORT_SYMBOL(__breadahead); /** - * __bread_gfp() - reads a specified block and returns the bh - * @bdev: the block_device to read from - * @block: number of block - * @size: size (in bytes) to read - * @gfp: page allocation flag - * - * Reads a specified block, and returns buffer head that contains it. - * The page cache can be allocated from non-movable area - * not to prevent page migration if you set gfp to zero. - * It returns NULL if the block was unreadable. + * __bread_gfp() - Read a block. + * @bdev: The block device to read from. + * @block: Block number in units of block size. + * @size: The block size of this device in bytes. + * @gfp: Not page allocation flags; see below. + * + * You are not expected to call this function. You should use one of + * sb_bread(), sb_bread_unmovable() or __bread(). + * + * Read a specified block, and return the buffer head that refers to it. + * If @gfp is 0, the memory will be allocated using the block device's + * default GFP flags. If @gfp is __GFP_MOVABLE, the memory may be + * allocated from a movable area. Do not pass in a complete set of + * GFP flags. + * + * The returned buffer head has its refcount increased. The caller should + * call brelse() when it has finished with the buffer. + * + * Context: May sleep waiting for I/O. + * Return: NULL if the block was unreadable. */ -struct buffer_head * -__bread_gfp(struct block_device *bdev, sector_t block, - unsigned size, gfp_t gfp) +struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block, + unsigned size, gfp_t gfp) { struct buffer_head *bh; @@ -2861,26 +2884,6 @@ int sync_dirty_buffer(struct buffer_head *bh) } EXPORT_SYMBOL(sync_dirty_buffer); -/* - * try_to_free_buffers() checks if all the buffers on this particular folio - * are unused, and releases them if so. - * - * Exclusion against try_to_free_buffers may be obtained by either - * locking the folio or by holding its mapping's i_private_lock. - * - * If the folio is dirty but all the buffers are clean then we need to - * be sure to mark the folio clean as well. This is because the folio - * may be against a block device, and a later reattachment of buffers - * to a dirty folio will set *all* buffers dirty. Which would corrupt - * filesystem data on the same device. - * - * The same applies to regular filesystem folios: if all the buffers are - * clean then we set the folio clean and proceed. To do that, we require - * total exclusion from block_dirty_folio(). That is obtained with - * i_private_lock. - * - * try_to_free_buffers() is non-blocking. - */ static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | @@ -2914,6 +2917,30 @@ failed: return false; } +/** + * try_to_free_buffers - Release buffers attached to this folio. + * @folio: The folio. + * + * If any buffers are in use (dirty, under writeback, elevated refcount), + * no buffers will be freed. + * + * If the folio is dirty but all the buffers are clean then we need to + * be sure to mark the folio clean as well. This is because the folio + * may be against a block device, and a later reattachment of buffers + * to a dirty folio will set *all* buffers dirty. Which would corrupt + * filesystem data on the same device. + * + * The same applies to regular filesystem folios: if all the buffers are + * clean then we set the folio clean and proceed. To do that, we require + * total exclusion from block_dirty_folio(). That is obtained with + * i_private_lock. + * + * Exclusion against try_to_free_buffers may be obtained by either + * locking the folio or by holding its mapping's i_private_lock. + * + * Context: Process context. @folio must be locked. Will not sleep. + * Return: true if all buffers attached to this folio were freed. + */ bool try_to_free_buffers(struct folio *folio) { struct address_space * const mapping = folio->mapping; diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index b4002aea7cdb9d..40de69860dcf97 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -284,7 +284,7 @@ static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh, const struct inode **inode_ret, u64 *lblk_num_ret) { - struct page *page = bh->b_page; + struct folio *folio = bh->b_folio; const struct address_space *mapping; const struct inode *inode; @@ -292,13 +292,13 @@ static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh, * The ext4 journal (jbd2) can submit a buffer_head it directly created * for a non-pagecache page. fscrypt doesn't care about these. */ - mapping = page_mapping(page); + mapping = folio_mapping(folio); if (!mapping) return false; inode = mapping->host; *inode_ret = inode; - *lblk_num_ret = ((u64)page->index << (PAGE_SHIFT - inode->i_blkbits)) + + *lblk_num_ret = ((u64)folio->index << (PAGE_SHIFT - inode->i_blkbits)) + (bh_offset(bh) >> inode->i_blkbits); return true; } diff --git a/fs/dax.c b/fs/dax.c index 423fc1607dfae5..becb4a6920c6aa 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1207,17 +1207,17 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, struct vm_area_struct *vma = vmf->vma; struct inode *inode = mapping->host; pgtable_t pgtable = NULL; - struct page *zero_page; + struct folio *zero_folio; spinlock_t *ptl; pmd_t pmd_entry; pfn_t pfn; - zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm); + zero_folio = mm_get_huge_zero_folio(vmf->vma->vm_mm); - if (unlikely(!zero_page)) + if (unlikely(!zero_folio)) goto fallback; - pfn = page_to_pfn_t(zero_page); + pfn = page_to_pfn_t(&zero_folio->page); *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_PMD | DAX_ZERO_PAGE); @@ -1237,17 +1237,17 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); mm_inc_nr_ptes(vma->vm_mm); } - pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot); + pmd_entry = mk_pmd(&zero_folio->page, vmf->vma->vm_page_prot); pmd_entry = pmd_mkhuge(pmd_entry); set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry); spin_unlock(ptl); - trace_dax_pmd_load_hole(inode, vmf, zero_page, *entry); + trace_dax_pmd_load_hole(inode, vmf, zero_folio, *entry); return VM_FAULT_NOPAGE; fallback: if (pgtable) pte_free(vma->vm_mm, pgtable); - trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry); + trace_dax_pmd_load_hole_fallback(inode, vmf, zero_folio, *entry); return VM_FAULT_FALLBACK; } #else diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 8aff1a724805a6..62da538d91cbd4 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -151,7 +151,7 @@ static int erofs_fscache_read_io_async(struct fscache_cookie *cookie, if (WARN_ON(len == 0)) source = NETFS_INVALID_READ; if (source != NETFS_READ_FROM_CACHE) { - erofs_err(NULL, "prepare_read failed (source %d)", source); + erofs_err(NULL, "prepare_ondemand_read failed (source %d)", source); return -EIO; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 39c67119f43bfd..d28ccfc0352b1a 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -84,13 +84,6 @@ struct erofs_dev_context { bool flatdev; }; -struct erofs_fs_context { - struct erofs_mount_opts opt; - struct erofs_dev_context *devs; - char *fsid; - char *domain_id; -}; - /* all filesystem-wide lz4 configurations */ struct erofs_sb_lz4_info { /* # of pages needed for EROFS lz4 rolling decompression */ diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c0eb139adb07a8..30b49b2eee5340 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -370,18 +370,18 @@ out: return ret; } -static void erofs_default_options(struct erofs_fs_context *ctx) +static void erofs_default_options(struct erofs_sb_info *sbi) { #ifdef CONFIG_EROFS_FS_ZIP - ctx->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND; - ctx->opt.max_sync_decompress_pages = 3; - ctx->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO; + sbi->opt.cache_strategy = EROFS_ZIP_CACHE_READAROUND; + sbi->opt.max_sync_decompress_pages = 3; + sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_AUTO; #endif #ifdef CONFIG_EROFS_FS_XATTR - set_opt(&ctx->opt, XATTR_USER); + set_opt(&sbi->opt, XATTR_USER); #endif #ifdef CONFIG_EROFS_FS_POSIX_ACL - set_opt(&ctx->opt, POSIX_ACL); + set_opt(&sbi->opt, POSIX_ACL); #endif } @@ -426,16 +426,16 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) { #ifdef CONFIG_FS_DAX - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; switch (mode) { case EROFS_MOUNT_DAX_ALWAYS: - set_opt(&ctx->opt, DAX_ALWAYS); - clear_opt(&ctx->opt, DAX_NEVER); + set_opt(&sbi->opt, DAX_ALWAYS); + clear_opt(&sbi->opt, DAX_NEVER); return true; case EROFS_MOUNT_DAX_NEVER: - set_opt(&ctx->opt, DAX_NEVER); - clear_opt(&ctx->opt, DAX_ALWAYS); + set_opt(&sbi->opt, DAX_NEVER); + clear_opt(&sbi->opt, DAX_ALWAYS); return true; default: DBG_BUGON(1); @@ -450,7 +450,7 @@ static bool erofs_fc_set_dax_mode(struct fs_context *fc, unsigned int mode) static int erofs_fc_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; struct fs_parse_result result; struct erofs_device_info *dif; int opt, ret; @@ -463,9 +463,9 @@ static int erofs_fc_parse_param(struct fs_context *fc, case Opt_user_xattr: #ifdef CONFIG_EROFS_FS_XATTR if (result.boolean) - set_opt(&ctx->opt, XATTR_USER); + set_opt(&sbi->opt, XATTR_USER); else - clear_opt(&ctx->opt, XATTR_USER); + clear_opt(&sbi->opt, XATTR_USER); #else errorfc(fc, "{,no}user_xattr options not supported"); #endif @@ -473,16 +473,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, case Opt_acl: #ifdef CONFIG_EROFS_FS_POSIX_ACL if (result.boolean) - set_opt(&ctx->opt, POSIX_ACL); + set_opt(&sbi->opt, POSIX_ACL); else - clear_opt(&ctx->opt, POSIX_ACL); + clear_opt(&sbi->opt, POSIX_ACL); #else errorfc(fc, "{,no}acl options not supported"); #endif break; case Opt_cache_strategy: #ifdef CONFIG_EROFS_FS_ZIP - ctx->opt.cache_strategy = result.uint_32; + sbi->opt.cache_strategy = result.uint_32; #else errorfc(fc, "compression not supported, cache_strategy ignored"); #endif @@ -504,27 +504,27 @@ static int erofs_fc_parse_param(struct fs_context *fc, kfree(dif); return -ENOMEM; } - down_write(&ctx->devs->rwsem); - ret = idr_alloc(&ctx->devs->tree, dif, 0, 0, GFP_KERNEL); - up_write(&ctx->devs->rwsem); + down_write(&sbi->devs->rwsem); + ret = idr_alloc(&sbi->devs->tree, dif, 0, 0, GFP_KERNEL); + up_write(&sbi->devs->rwsem); if (ret < 0) { kfree(dif->path); kfree(dif); return ret; } - ++ctx->devs->extra_devices; + ++sbi->devs->extra_devices; break; #ifdef CONFIG_EROFS_FS_ONDEMAND case Opt_fsid: - kfree(ctx->fsid); - ctx->fsid = kstrdup(param->string, GFP_KERNEL); - if (!ctx->fsid) + kfree(sbi->fsid); + sbi->fsid = kstrdup(param->string, GFP_KERNEL); + if (!sbi->fsid) return -ENOMEM; break; case Opt_domain_id: - kfree(ctx->domain_id); - ctx->domain_id = kstrdup(param->string, GFP_KERNEL); - if (!ctx->domain_id) + kfree(sbi->domain_id); + sbi->domain_id = kstrdup(param->string, GFP_KERNEL); + if (!sbi->domain_id) return -ENOMEM; break; #else @@ -581,8 +581,7 @@ static const struct export_operations erofs_export_ops = { static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; - struct erofs_sb_info *sbi; - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = EROFS_SB(sb); int err; sb->s_magic = EROFS_SUPER_MAGIC; @@ -590,19 +589,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_op = &erofs_sops; - sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); - if (!sbi) - return -ENOMEM; - - sb->s_fs_info = sbi; - sbi->opt = ctx->opt; - sbi->devs = ctx->devs; - ctx->devs = NULL; - sbi->fsid = ctx->fsid; - ctx->fsid = NULL; - sbi->domain_id = ctx->domain_id; - ctx->domain_id = NULL; - sbi->blkszbits = PAGE_SHIFT; if (erofs_is_fscache_mode(sb)) { sb->s_blocksize = PAGE_SIZE; @@ -706,9 +692,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) static int erofs_fc_get_tree(struct fs_context *fc) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; - if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && ctx->fsid) + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) return get_tree_nodev(fc, erofs_fc_fill_super); return get_tree_bdev(fc, erofs_fc_fill_super); @@ -718,19 +704,19 @@ static int erofs_fc_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct erofs_sb_info *sbi = EROFS_SB(sb); - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *new_sbi = fc->s_fs_info; DBG_BUGON(!sb_rdonly(sb)); - if (ctx->fsid || ctx->domain_id) + if (new_sbi->fsid || new_sbi->domain_id) erofs_info(sb, "ignoring reconfiguration for fsid|domain_id."); - if (test_opt(&ctx->opt, POSIX_ACL)) + if (test_opt(&new_sbi->opt, POSIX_ACL)) fc->sb_flags |= SB_POSIXACL; else fc->sb_flags &= ~SB_POSIXACL; - sbi->opt = ctx->opt; + sbi->opt = new_sbi->opt; fc->sb_flags |= SB_RDONLY; return 0; @@ -761,12 +747,15 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) static void erofs_fc_free(struct fs_context *fc) { - struct erofs_fs_context *ctx = fc->fs_private; + struct erofs_sb_info *sbi = fc->s_fs_info; - erofs_free_dev_context(ctx->devs); - kfree(ctx->fsid); - kfree(ctx->domain_id); - kfree(ctx); + if (!sbi) + return; + + erofs_free_dev_context(sbi->devs); + kfree(sbi->fsid); + kfree(sbi->domain_id); + kfree(sbi); } static const struct fs_context_operations erofs_context_ops = { @@ -778,38 +767,35 @@ static const struct fs_context_operations erofs_context_ops = { static int erofs_init_fs_context(struct fs_context *fc) { - struct erofs_fs_context *ctx; + struct erofs_sb_info *sbi; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) return -ENOMEM; - ctx->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL); - if (!ctx->devs) { - kfree(ctx); + + sbi->devs = kzalloc(sizeof(struct erofs_dev_context), GFP_KERNEL); + if (!sbi->devs) { + kfree(sbi); return -ENOMEM; } - fc->fs_private = ctx; + fc->s_fs_info = sbi; - idr_init(&ctx->devs->tree); - init_rwsem(&ctx->devs->rwsem); - erofs_default_options(ctx); + idr_init(&sbi->devs->tree); + init_rwsem(&sbi->devs->rwsem); + erofs_default_options(sbi); fc->ops = &erofs_context_ops; return 0; } static void erofs_kill_sb(struct super_block *sb) { - struct erofs_sb_info *sbi; + struct erofs_sb_info *sbi = EROFS_SB(sb); - if (erofs_is_fscache_mode(sb)) + if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) kill_anon_super(sb); else kill_block_super(sb); - sbi = EROFS_SB(sb); - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); fs_put_dax(sbi->dax_dev, NULL); erofs_fscache_unregister_fs(sb); diff --git a/fs/exec.c b/fs/exec.c index cf1df7f16e55cc..0c5f06d08c355a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -67,6 +67,7 @@ #include <linux/time_namespace.h> #include <linux/user_events.h> #include <linux/rseq.h> +#include <linux/ksm.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -268,6 +269,14 @@ static int __bprm_mm_init(struct linux_binprm *bprm) } /* + * Need to be called with mmap write lock + * held, to avoid race with ksmd. + */ + err = ksm_execve(mm); + if (err) + goto err_ksm; + + /* * Place the stack at the largest stack address the architecture * supports. Later, we'll move this to an appropriate place. We don't * use STACK_TOP because that can depend on attributes which aren't @@ -288,6 +297,8 @@ static int __bprm_mm_init(struct linux_binprm *bprm) bprm->p = vma->vm_end - sizeof(void *); return 0; err: + ksm_exit(mm); +err_ksm: mmap_write_unlock(mm); err_free: bprm->vma = NULL; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index d9494b5fc7c185..961e6ff77c7235 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -4082,11 +4082,12 @@ const struct address_space_operations f2fs_dblock_aops = { void f2fs_clear_page_cache_dirty_tag(struct page *page) { - struct address_space *mapping = page_mapping(page); + struct folio *folio = page_folio(page); + struct address_space *mapping = folio->mapping; unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); - __xa_clear_mark(&mapping->i_pages, page_index(page), + __xa_clear_mark(&mapping->i_pages, folio->index, PAGECACHE_TAG_DIRTY); xa_unlock_irqrestore(&mapping->i_pages, flags); } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 00235b8a1823af..acbec5bdd5210a 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -269,6 +269,18 @@ enum { PARSE_INVALID = 1, PARSE_NOT_LONGNAME, PARSE_EOF, }; /** * fat_parse_long - Parse extended directory entry. * + * @dir: Pointer to the inode that represents the directory. + * @pos: On input, contains the starting position to read from. + * On output, updated with the new position. + * @bh: Pointer to the buffer head that may be used for reading directory + * entries. May be updated. + * @de: On input, points to the current directory entry. + * On output, points to the next directory entry. + * @unicode: Pointer to a buffer where the parsed Unicode long filename will be + * stored. + * @nr_slots: Pointer to a variable that will store the number of longname + * slots found. + * * This function returns zero on success, negative value on error, or one of * the following: * diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 6502c7e776d195..2f4e88552d3f28 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -176,14 +176,12 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; - info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; info.high_limit = arch_get_mmap_end(addr, len, flags); info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; return vm_unmapped_area(&info); } @@ -192,14 +190,13 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -249,11 +246,11 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, } /* - * Use mm->get_unmapped_area value as a hint to use topdown routine. + * Use MMF_TOPDOWN flag as a hint to use topdown routine. * If architectures have special needs, they should define their own * version of hugetlb_get_unmapped_area. */ - if (mm->get_unmapped_area == arch_get_unmapped_area_topdown) + if (test_bit(MMF_TOPDOWN, &mm->flags)) return hugetlb_get_unmapped_area_topdown(file, addr, len, pgoff, flags); return hugetlb_get_unmapped_area_bottomup(file, addr, len, diff --git a/fs/ioctl.c b/fs/ioctl.c index 1d5abfdf0f22a6..fb0628e680c40f 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -769,7 +769,7 @@ static int ioctl_getfsuuid(struct file *file, void __user *argp) struct fsuuid2 u = { .len = sb->s_uuid_len, }; if (!sb->s_uuid_len) - return -ENOIOCTLCMD; + return -ENOTTY; memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len); @@ -781,7 +781,7 @@ static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp) struct super_block *sb = file_inode(file)->i_sb; if (!strlen(sb->s_sysfs_name)) - return -ENOIOCTLCMD; + return -ENOTTY; struct fs_sysfs_path u = {}; diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 9a0d32e4b422ad..267b622d923b1f 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -164,7 +164,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, enum netfs_how_to_modify howto; enum netfs_folio_trace trace; unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC; - ssize_t written = 0, ret; + ssize_t written = 0, ret, ret2; loff_t i_size, pos = iocb->ki_pos, from, to; size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; bool maybe_trouble = false; @@ -172,15 +172,14 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) || iocb->ki_flags & (IOCB_DSYNC | IOCB_SYNC)) ) { - if (pos < i_size_read(inode)) { - ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count); - if (ret < 0) { - goto out; - } - } - wbc_attach_fdatawrite_inode(&wbc, mapping->host); + ret = filemap_write_and_wait_range(mapping, pos, pos + iter->count); + if (ret < 0) { + wbc_detach_inode(&wbc); + goto out; + } + wreq = netfs_begin_writethrough(iocb, iter->count); if (IS_ERR(wreq)) { wbc_detach_inode(&wbc); @@ -395,10 +394,12 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, out: if (unlikely(wreq)) { - ret = netfs_end_writethrough(wreq, iocb); + ret2 = netfs_end_writethrough(wreq, iocb); wbc_detach_inode(&wbc); - if (ret == -EIOCBQUEUED) - return ret; + if (ret2 == -EIOCBQUEUED) + return ret2; + if (ret == 0) + ret = ret2; } iocb->ki_pos += written; diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h index 5aa776b5a3e7f8..b17a9eb9b1488b 100644 --- a/fs/nfs/iostat.h +++ b/fs/nfs/iostat.h @@ -46,10 +46,7 @@ static inline void nfs_add_stats(const struct inode *inode, nfs_add_server_stats(NFS_SERVER(inode), stat, addend); } -static inline struct nfs_iostats __percpu *nfs_alloc_iostats(void) -{ - return alloc_percpu(struct nfs_iostats); -} +#define nfs_alloc_iostats() alloc_percpu(struct nfs_iostats) static inline void nfs_free_iostats(struct nfs_iostats __percpu *stats) { diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 87c9547989f69e..e88aca0c6e8ef1 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 1955481832e037..a644460f3a5e7a 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3515,6 +3515,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.exp = exp; args.dentry = dentry; args.ignore_crossmnt = (ignore_crossmnt != 0); + args.acl = NULL; /* * Make a local copy of the attribute bitmap that can be modified. @@ -3573,7 +3574,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, } else args.fhp = fhp; - args.acl = NULL; if (attrmask[0] & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 01c6f344564693..2ed0fcf879fd17 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/btree.c b/fs/nilfs2/btree.c index 65659fa0372e6c..a139970e48041d 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -1857,13 +1857,22 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree, } /** - * nilfs_btree_convert_and_insert - - * @bmap: - * @key: - * @ptr: - * @keys: - * @ptrs: - * @n: + * nilfs_btree_convert_and_insert - Convert and insert entries into a B-tree + * @btree: NILFS B-tree structure + * @key: Key of the new entry to be inserted + * @ptr: Pointer (block number) associated with the key to be inserted + * @keys: Array of keys to be inserted in addition to @key + * @ptrs: Array of pointers associated with @keys + * @n: Number of keys and pointers in @keys and @ptrs + * + * This function is used to insert a new entry specified by @key and @ptr, + * along with additional entries specified by @keys and @ptrs arrays, into a + * NILFS B-tree. + * It prepares the necessary changes by allocating the required blocks and any + * necessary intermediate nodes. It converts configurations from other forms of + * block mapping (the one that currently exists is direct mapping) to a B-tree. + * + * Return: 0 on success or a negative error code on failure. */ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree, __u64 key, __u64 ptr, diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index bf9a11d5881722..1c9ae36a03abe9 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -175,6 +175,7 @@ int nilfs_init_gcinode(struct inode *inode) /** * nilfs_remove_all_gcinodes() - remove all unprocessed gc inodes + * @nilfs: NILFS filesystem instance */ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs) { diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 2e29b98ba8bab2..728e90be3570b7 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -335,8 +335,8 @@ void __nilfs_error(struct super_block *sb, const char *function, extern struct nilfs_super_block * nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **); -extern int nilfs_store_magic_and_option(struct super_block *, - struct nilfs_super_block *, char *); +extern int nilfs_store_magic(struct super_block *sb, + struct nilfs_super_block *sbp); extern int nilfs_check_feature_compatibility(struct super_block *, struct nilfs_super_block *); extern void nilfs_set_log_cursor(struct nilfs_super_block *, diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 49a70c68bf3c06..e48372618ac400 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -563,6 +563,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, * checkpoint * @nilfs: nilfs object * @sb: super block instance + * @root: NILFS root instance * @ri: pointer to a nilfs_recovery_info */ static int nilfs_do_roll_forward(struct the_nilfs *nilfs, diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index ac24ed109ce935..e835e1f5a71201 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -29,13 +29,13 @@ #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> -#include <linux/parser.h> #include <linux/crc32.h> #include <linux/vfs.h> #include <linux/writeback.h> #include <linux/seq_file.h> #include <linux/mount.h> #include <linux/fs_context.h> +#include <linux/fs_parser.h> #include "nilfs.h" #include "export.h" #include "mdt.h" @@ -61,7 +61,6 @@ struct kmem_cache *nilfs_segbuf_cachep; struct kmem_cache *nilfs_btree_path_cache; static int nilfs_setup_super(struct super_block *sb, int is_mount); -static int nilfs_remount(struct super_block *sb, int *flags, char *data); void __nilfs_msg(struct super_block *sb, const char *fmt, ...) { @@ -702,105 +701,98 @@ static const struct super_operations nilfs_sops = { .freeze_fs = nilfs_freeze, .unfreeze_fs = nilfs_unfreeze, .statfs = nilfs_statfs, - .remount_fs = nilfs_remount, .show_options = nilfs_show_options }; enum { - Opt_err_cont, Opt_err_panic, Opt_err_ro, - Opt_barrier, Opt_nobarrier, Opt_snapshot, Opt_order, Opt_norecovery, - Opt_discard, Opt_nodiscard, Opt_err, + Opt_err, Opt_barrier, Opt_snapshot, Opt_order, Opt_norecovery, + Opt_discard, }; -static match_table_t tokens = { - {Opt_err_cont, "errors=continue"}, - {Opt_err_panic, "errors=panic"}, - {Opt_err_ro, "errors=remount-ro"}, - {Opt_barrier, "barrier"}, - {Opt_nobarrier, "nobarrier"}, - {Opt_snapshot, "cp=%u"}, - {Opt_order, "order=%s"}, - {Opt_norecovery, "norecovery"}, - {Opt_discard, "discard"}, - {Opt_nodiscard, "nodiscard"}, - {Opt_err, NULL} +static const struct constant_table nilfs_param_err[] = { + {"continue", NILFS_MOUNT_ERRORS_CONT}, + {"panic", NILFS_MOUNT_ERRORS_PANIC}, + {"remount-ro", NILFS_MOUNT_ERRORS_RO}, + {} }; -static int parse_options(char *options, struct super_block *sb, int is_remount) -{ - struct the_nilfs *nilfs = sb->s_fs_info; - char *p; - substring_t args[MAX_OPT_ARGS]; - - if (!options) - return 1; - - while ((p = strsep(&options, ",")) != NULL) { - int token; +static const struct fs_parameter_spec nilfs_param_spec[] = { + fsparam_enum ("errors", Opt_err, nilfs_param_err), + fsparam_flag_no ("barrier", Opt_barrier), + fsparam_u64 ("cp", Opt_snapshot), + fsparam_string ("order", Opt_order), + fsparam_flag ("norecovery", Opt_norecovery), + fsparam_flag_no ("discard", Opt_discard), + {} +}; - if (!*p) - continue; +struct nilfs_fs_context { + unsigned long ns_mount_opt; + __u64 cno; +}; - token = match_token(p, tokens, args); - switch (token) { - case Opt_barrier: - nilfs_set_opt(nilfs, BARRIER); - break; - case Opt_nobarrier: +static int nilfs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct nilfs_fs_context *nilfs = fc->fs_private; + int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE; + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, nilfs_param_spec, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_barrier: + if (result.negated) nilfs_clear_opt(nilfs, BARRIER); - break; - case Opt_order: - if (strcmp(args[0].from, "relaxed") == 0) - /* Ordered data semantics */ - nilfs_clear_opt(nilfs, STRICT_ORDER); - else if (strcmp(args[0].from, "strict") == 0) - /* Strict in-order semantics */ - nilfs_set_opt(nilfs, STRICT_ORDER); - else - return 0; - break; - case Opt_err_panic: - nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_PANIC); - break; - case Opt_err_ro: - nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_RO); - break; - case Opt_err_cont: - nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_CONT); - break; - case Opt_snapshot: - if (is_remount) { - nilfs_err(sb, - "\"%s\" option is invalid for remount", - p); - return 0; - } - break; - case Opt_norecovery: - nilfs_set_opt(nilfs, NORECOVERY); - break; - case Opt_discard: - nilfs_set_opt(nilfs, DISCARD); - break; - case Opt_nodiscard: - nilfs_clear_opt(nilfs, DISCARD); - break; - default: - nilfs_err(sb, "unrecognized mount option \"%s\"", p); - return 0; + else + nilfs_set_opt(nilfs, BARRIER); + break; + case Opt_order: + if (strcmp(param->string, "relaxed") == 0) + /* Ordered data semantics */ + nilfs_clear_opt(nilfs, STRICT_ORDER); + else if (strcmp(param->string, "strict") == 0) + /* Strict in-order semantics */ + nilfs_set_opt(nilfs, STRICT_ORDER); + else + return -EINVAL; + break; + case Opt_err: + nilfs->ns_mount_opt &= ~NILFS_MOUNT_ERROR_MODE; + nilfs->ns_mount_opt |= result.uint_32; + break; + case Opt_snapshot: + if (is_remount) { + struct super_block *sb = fc->root->d_sb; + + nilfs_err(sb, + "\"%s\" option is invalid for remount", + param->key); + return -EINVAL; + } + if (result.uint_64 == 0) { + nilfs_err(NULL, + "invalid option \"cp=0\": invalid checkpoint number 0"); + return -EINVAL; } + nilfs->cno = result.uint_64; + break; + case Opt_norecovery: + nilfs_set_opt(nilfs, NORECOVERY); + break; + case Opt_discard: + if (result.negated) + nilfs_clear_opt(nilfs, DISCARD); + else + nilfs_set_opt(nilfs, DISCARD); + break; + default: + return -EINVAL; } - return 1; -} - -static inline void -nilfs_set_default_options(struct super_block *sb, - struct nilfs_super_block *sbp) -{ - struct the_nilfs *nilfs = sb->s_fs_info; - nilfs->ns_mount_opt = - NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER; + return 0; } static int nilfs_setup_super(struct super_block *sb, int is_mount) @@ -857,9 +849,8 @@ struct nilfs_super_block *nilfs_read_super_block(struct super_block *sb, return (struct nilfs_super_block *)((char *)(*pbh)->b_data + offset); } -int nilfs_store_magic_and_option(struct super_block *sb, - struct nilfs_super_block *sbp, - char *data) +int nilfs_store_magic(struct super_block *sb, + struct nilfs_super_block *sbp) { struct the_nilfs *nilfs = sb->s_fs_info; @@ -870,14 +861,12 @@ int nilfs_store_magic_and_option(struct super_block *sb, sb->s_flags |= SB_NOATIME; #endif - nilfs_set_default_options(sb, sbp); - nilfs->ns_resuid = le16_to_cpu(sbp->s_def_resuid); nilfs->ns_resgid = le16_to_cpu(sbp->s_def_resgid); nilfs->ns_interval = le32_to_cpu(sbp->s_c_interval); nilfs->ns_watermark = le32_to_cpu(sbp->s_c_block_max); - return !parse_options(data, sb, 0) ? -EINVAL : 0; + return 0; } int nilfs_check_feature_compatibility(struct super_block *sb, @@ -1035,17 +1024,17 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno) /** * nilfs_fill_super() - initialize a super block instance * @sb: super_block - * @data: mount options - * @silent: silent mode flag + * @fc: filesystem context * * This function is called exclusively by nilfs->ns_mount_mutex. * So, the recovery process is protected from other simultaneous mounts. */ static int -nilfs_fill_super(struct super_block *sb, void *data, int silent) +nilfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct the_nilfs *nilfs; struct nilfs_root *fsroot; + struct nilfs_fs_context *ctx = fc->fs_private; __u64 cno; int err; @@ -1055,10 +1044,13 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = nilfs; - err = init_nilfs(nilfs, sb, (char *)data); + err = init_nilfs(nilfs, sb); if (err) goto failed_nilfs; + /* Copy in parsed mount options */ + nilfs->ns_mount_opt = ctx->ns_mount_opt; + sb->s_op = &nilfs_sops; sb->s_export_op = &nilfs_export_ops; sb->s_root = NULL; @@ -1117,34 +1109,25 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) return err; } -static int nilfs_remount(struct super_block *sb, int *flags, char *data) +static int nilfs_reconfigure(struct fs_context *fc) { + struct nilfs_fs_context *ctx = fc->fs_private; + struct super_block *sb = fc->root->d_sb; struct the_nilfs *nilfs = sb->s_fs_info; - unsigned long old_sb_flags; - unsigned long old_mount_opt; int err; sync_filesystem(sb); - old_sb_flags = sb->s_flags; - old_mount_opt = nilfs->ns_mount_opt; - - if (!parse_options(data, sb, 1)) { - err = -EINVAL; - goto restore_opts; - } - sb->s_flags = (sb->s_flags & ~SB_POSIXACL); err = -EINVAL; if (!nilfs_valid_fs(nilfs)) { nilfs_warn(sb, "couldn't remount because the filesystem is in an incomplete recovery state"); - goto restore_opts; + goto ignore_opts; } - - if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) + if ((bool)(fc->sb_flags & SB_RDONLY) == sb_rdonly(sb)) goto out; - if (*flags & SB_RDONLY) { + if (fc->sb_flags & SB_RDONLY) { sb->s_flags |= SB_RDONLY; /* @@ -1172,138 +1155,67 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) "couldn't remount RDWR because of unsupported optional features (%llx)", (unsigned long long)features); err = -EROFS; - goto restore_opts; + goto ignore_opts; } sb->s_flags &= ~SB_RDONLY; root = NILFS_I(d_inode(sb->s_root))->i_root; err = nilfs_attach_log_writer(sb, root); - if (err) - goto restore_opts; + if (err) { + sb->s_flags |= SB_RDONLY; + goto ignore_opts; + } down_write(&nilfs->ns_sem); nilfs_setup_super(sb, true); up_write(&nilfs->ns_sem); } out: - return 0; - - restore_opts: - sb->s_flags = old_sb_flags; - nilfs->ns_mount_opt = old_mount_opt; - return err; -} - -struct nilfs_super_data { - __u64 cno; - int flags; -}; - -static int nilfs_parse_snapshot_option(const char *option, - const substring_t *arg, - struct nilfs_super_data *sd) -{ - unsigned long long val; - const char *msg = NULL; - int err; - - if (!(sd->flags & SB_RDONLY)) { - msg = "read-only option is not specified"; - goto parse_error; - } - - err = kstrtoull(arg->from, 0, &val); - if (err) { - if (err == -ERANGE) - msg = "too large checkpoint number"; - else - msg = "malformed argument"; - goto parse_error; - } else if (val == 0) { - msg = "invalid checkpoint number 0"; - goto parse_error; - } - sd->cno = val; - return 0; - -parse_error: - nilfs_err(NULL, "invalid option \"%s\": %s", option, msg); - return 1; -} - -/** - * nilfs_identify - pre-read mount options needed to identify mount instance - * @data: mount options - * @sd: nilfs_super_data - */ -static int nilfs_identify(char *data, struct nilfs_super_data *sd) -{ - char *p, *options = data; - substring_t args[MAX_OPT_ARGS]; - int token; - int ret = 0; - - do { - p = strsep(&options, ","); - if (p != NULL && *p) { - token = match_token(p, tokens, args); - if (token == Opt_snapshot) - ret = nilfs_parse_snapshot_option(p, &args[0], - sd); - } - if (!options) - break; - BUG_ON(options == data); - *(options - 1) = ','; - } while (!ret); - return ret; -} + sb->s_flags = (sb->s_flags & ~SB_POSIXACL); + /* Copy over parsed remount options */ + nilfs->ns_mount_opt = ctx->ns_mount_opt; -static int nilfs_set_bdev_super(struct super_block *s, void *data) -{ - s->s_dev = *(dev_t *)data; return 0; -} -static int nilfs_test_bdev_super(struct super_block *s, void *data) -{ - return !(s->s_iflags & SB_I_RETIRED) && s->s_dev == *(dev_t *)data; + ignore_opts: + return err; } -static struct dentry * -nilfs_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data) +static int +nilfs_get_tree(struct fs_context *fc) { - struct nilfs_super_data sd = { .flags = flags }; + struct nilfs_fs_context *ctx = fc->fs_private; struct super_block *s; dev_t dev; int err; - if (nilfs_identify(data, &sd)) - return ERR_PTR(-EINVAL); + if (ctx->cno && !(fc->sb_flags & SB_RDONLY)) { + nilfs_err(NULL, + "invalid option \"cp=%llu\": read-only option is not specified", + ctx->cno); + return -EINVAL; + } - err = lookup_bdev(dev_name, &dev); + err = lookup_bdev(fc->source, &dev); if (err) - return ERR_PTR(err); + return err; - s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, flags, - &dev); + s = sget_dev(fc, dev); if (IS_ERR(s)) - return ERR_CAST(s); + return PTR_ERR(s); if (!s->s_root) { - err = setup_bdev_super(s, flags, NULL); + err = setup_bdev_super(s, fc->sb_flags, fc); if (!err) - err = nilfs_fill_super(s, data, - flags & SB_SILENT ? 1 : 0); + err = nilfs_fill_super(s, fc); if (err) goto failed_super; s->s_flags |= SB_ACTIVE; - } else if (!sd.cno) { + } else if (!ctx->cno) { if (nilfs_tree_is_busy(s->s_root)) { - if ((flags ^ s->s_flags) & SB_RDONLY) { + if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { nilfs_err(s, "the device already has a %s mount.", sb_rdonly(s) ? "read-only" : "read/write"); @@ -1312,37 +1224,75 @@ nilfs_mount(struct file_system_type *fs_type, int flags, } } else { /* - * Try remount to setup mount states if the current + * Try reconfigure to setup mount states if the current * tree is not mounted and only snapshots use this sb. + * + * Since nilfs_reconfigure() requires fc->root to be + * set, set it first and release it on failure. */ - err = nilfs_remount(s, &flags, data); - if (err) + fc->root = dget(s->s_root); + err = nilfs_reconfigure(fc); + if (err) { + dput(fc->root); + fc->root = NULL; /* prevent double release */ goto failed_super; + } + return 0; } } - if (sd.cno) { + if (ctx->cno) { struct dentry *root_dentry; - err = nilfs_attach_snapshot(s, sd.cno, &root_dentry); + err = nilfs_attach_snapshot(s, ctx->cno, &root_dentry); if (err) goto failed_super; - return root_dentry; + fc->root = root_dentry; + return 0; } - return dget(s->s_root); + fc->root = dget(s->s_root); + return 0; failed_super: deactivate_locked_super(s); - return ERR_PTR(err); + return err; +} + +static void nilfs_free_fc(struct fs_context *fc) +{ + kfree(fc->fs_private); +} + +static const struct fs_context_operations nilfs_context_ops = { + .parse_param = nilfs_parse_param, + .get_tree = nilfs_get_tree, + .reconfigure = nilfs_reconfigure, + .free = nilfs_free_fc, +}; + +static int nilfs_init_fs_context(struct fs_context *fc) +{ + struct nilfs_fs_context *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->ns_mount_opt = NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER; + fc->fs_private = ctx; + fc->ops = &nilfs_context_ops; + + return 0; } struct file_system_type nilfs_fs_type = { .owner = THIS_MODULE, .name = "nilfs2", - .mount = nilfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, + .init_fs_context = nilfs_init_fs_context, + .parameters = nilfs_param_spec, }; MODULE_ALIAS_FS("nilfs2"); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 2ae2c1bbf6d17c..db322068678f40 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -659,7 +659,6 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, * init_nilfs - initialize a NILFS instance. * @nilfs: the_nilfs structure * @sb: super block - * @data: mount options * * init_nilfs() performs common initialization per block device (e.g. * reading the super block, getting disk layout information, initializing @@ -668,7 +667,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, * Return Value: On success, 0 is returned. On error, a negative error * code is returned. */ -int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) +int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb) { struct nilfs_super_block *sbp; int blocksize; @@ -686,7 +685,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto out; - err = nilfs_store_magic_and_option(sb, sbp, data); + err = nilfs_store_magic(sb, sbp); if (err) goto failed_sbh; diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index cd4ae1b8ae165a..85da0629415dfe 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -219,10 +219,6 @@ THE_NILFS_FNS(PURGING, purging) #define nilfs_set_opt(nilfs, opt) \ ((nilfs)->ns_mount_opt |= NILFS_MOUNT_##opt) #define nilfs_test_opt(nilfs, opt) ((nilfs)->ns_mount_opt & NILFS_MOUNT_##opt) -#define nilfs_write_opt(nilfs, mask, opt) \ - ((nilfs)->ns_mount_opt = \ - (((nilfs)->ns_mount_opt & ~NILFS_MOUNT_##mask) | \ - NILFS_MOUNT_##opt)) \ /** * struct nilfs_root - nilfs root object @@ -276,7 +272,7 @@ static inline int nilfs_sb_will_flip(struct the_nilfs *nilfs) void nilfs_set_last_segment(struct the_nilfs *, sector_t, u64, __u64); struct the_nilfs *alloc_nilfs(struct super_block *sb); void destroy_nilfs(struct the_nilfs *nilfs); -int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data); +int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb); int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb); unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs); void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs); diff --git a/fs/ntfs3/Kconfig b/fs/ntfs3/Kconfig index cdfdf51e55d797..7bc31d69f680dd 100644 --- a/fs/ntfs3/Kconfig +++ b/fs/ntfs3/Kconfig @@ -46,3 +46,12 @@ config NTFS3_FS_POSIX_ACL NOTE: this is linux only feature. Windows will ignore these ACLs. If you don't know what Access Control Lists are, say N. + +config NTFS_FS + tristate "NTFS file system support" + select NTFS3_FS + select BUFFER_HEAD + select NLS + help + This config option is here only for backward compatibility. NTFS + filesystem is now handled by the NTFS3 driver. diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 5cf3d9decf646b..263635199b60d3 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -616,4 +616,11 @@ const struct file_operations ntfs_dir_operations = { .compat_ioctl = ntfs_compat_ioctl, #endif }; + +const struct file_operations ntfs_legacy_dir_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate_shared = ntfs_readdir, + .open = ntfs_file_open, +}; // clang-format on diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 5418662c80d887..b73969e05052ae 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -1236,4 +1236,12 @@ const struct file_operations ntfs_file_operations = { .fallocate = ntfs_fallocate, .release = ntfs_file_release, }; + +const struct file_operations ntfs_legacy_file_operations = { + .llseek = generic_file_llseek, + .read_iter = ntfs_file_read_iter, + .splice_read = ntfs_file_splice_read, + .open = ntfs_file_open, + .release = ntfs_file_release, +}; // clang-format on diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index eb7a8c9fba0183..d273eda1cf45d6 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -440,7 +440,10 @@ end_enum: * Usually a hard links to directories are disabled. */ inode->i_op = &ntfs_dir_inode_operations; - inode->i_fop = &ntfs_dir_operations; + if (is_legacy_ntfs(inode->i_sb)) + inode->i_fop = &ntfs_legacy_dir_operations; + else + inode->i_fop = &ntfs_dir_operations; ni->i_valid = 0; } else if (S_ISLNK(mode)) { ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; @@ -450,7 +453,10 @@ end_enum: } else if (S_ISREG(mode)) { ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; inode->i_op = &ntfs_file_inode_operations; - inode->i_fop = &ntfs_file_operations; + if (is_legacy_ntfs(inode->i_sb)) + inode->i_fop = &ntfs_legacy_file_operations; + else + inode->i_fop = &ntfs_file_operations; inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; if (ino != MFT_REC_MFT) @@ -1614,7 +1620,10 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, if (S_ISDIR(mode)) { inode->i_op = &ntfs_dir_inode_operations; - inode->i_fop = &ntfs_dir_operations; + if (is_legacy_ntfs(inode->i_sb)) + inode->i_fop = &ntfs_legacy_dir_operations; + else + inode->i_fop = &ntfs_dir_operations; } else if (S_ISLNK(mode)) { inode->i_op = &ntfs_link_inode_operations; inode->i_fop = NULL; @@ -1623,7 +1632,10 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, inode_nohighmem(inode); } else if (S_ISREG(mode)) { inode->i_op = &ntfs_file_inode_operations; - inode->i_fop = &ntfs_file_operations; + if (is_legacy_ntfs(inode->i_sb)) + inode->i_fop = &ntfs_legacy_file_operations; + else + inode->i_fop = &ntfs_file_operations; inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; init_rwsem(&ni->file.run_lock); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 79356fd29a1414..5f4d288c6adfb9 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -493,6 +493,7 @@ struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni, struct ntfs_fnd *fnd); bool dir_is_empty(struct inode *dir); extern const struct file_operations ntfs_dir_operations; +extern const struct file_operations ntfs_legacy_dir_operations; /* Globals from file.c */ int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, @@ -507,6 +508,7 @@ long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg); extern const struct inode_operations ntfs_special_inode_operations; extern const struct inode_operations ntfs_file_inode_operations; extern const struct file_operations ntfs_file_operations; +extern const struct file_operations ntfs_legacy_file_operations; /* Globals from frecord.c */ void ni_remove_mi(struct ntfs_inode *ni, struct mft_inode *mi); @@ -1154,4 +1156,6 @@ static inline void le64_sub_cpu(__le64 *var, u64 val) *var = cpu_to_le64(le64_to_cpu(*var) - val); } +bool is_legacy_ntfs(struct super_block *sb); + #endif /* _LINUX_NTFS3_NTFS_FS_H */ diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 9df7c20d066f61..b26d95a8d3274d 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -408,6 +408,12 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) struct ntfs_mount_options *new_opts = fc->fs_private; int ro_rw; + /* If ntfs3 is used as legacy ntfs enforce read-only mode. */ + if (is_legacy_ntfs(sb)) { + fc->sb_flags |= SB_RDONLY; + goto out; + } + ro_rw = sb_rdonly(sb) && !(fc->sb_flags & SB_RDONLY); if (ro_rw && (sbi->flags & NTFS_FLAGS_NEED_REPLAY)) { errorf(fc, @@ -427,8 +433,6 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) fc, "ntfs3: Cannot use different iocharset when remounting!"); - sync_filesystem(sb); - if (ro_rw && (sbi->volume.flags & VOLUME_FLAG_DIRTY) && !new_opts->force) { errorf(fc, @@ -436,6 +440,8 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) return -EINVAL; } +out: + sync_filesystem(sb); swap(sbi->options, fc->fs_private); return 0; @@ -1613,6 +1619,8 @@ load_root: } #endif + if (is_legacy_ntfs(sb)) + sb->s_flags |= SB_RDONLY; return 0; put_inode_out: @@ -1730,7 +1738,7 @@ static const struct fs_context_operations ntfs_context_ops = { * This will called when mount/remount. We will first initialize * options so that if remount we can use just that. */ -static int ntfs_init_fs_context(struct fs_context *fc) +static int __ntfs_init_fs_context(struct fs_context *fc) { struct ntfs_mount_options *opts; struct ntfs_sb_info *sbi; @@ -1778,6 +1786,11 @@ free_opts: return -ENOMEM; } +static int ntfs_init_fs_context(struct fs_context *fc) +{ + return __ntfs_init_fs_context(fc); +} + static void ntfs3_kill_sb(struct super_block *sb) { struct ntfs_sb_info *sbi = sb->s_fs_info; @@ -1798,6 +1811,50 @@ static struct file_system_type ntfs_fs_type = { .kill_sb = ntfs3_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; + +#if IS_ENABLED(CONFIG_NTFS_FS) +static int ntfs_legacy_init_fs_context(struct fs_context *fc) +{ + int ret; + + ret = __ntfs_init_fs_context(fc); + /* If ntfs3 is used as legacy ntfs enforce read-only mode. */ + fc->sb_flags |= SB_RDONLY; + return ret; +} + +static struct file_system_type ntfs_legacy_fs_type = { + .owner = THIS_MODULE, + .name = "ntfs", + .init_fs_context = ntfs_legacy_init_fs_context, + .parameters = ntfs_fs_parameters, + .kill_sb = ntfs3_kill_sb, + .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, +}; +MODULE_ALIAS_FS("ntfs"); + +static inline void register_as_ntfs_legacy(void) +{ + int err = register_filesystem(&ntfs_legacy_fs_type); + if (err) + pr_warn("ntfs3: Failed to register legacy ntfs filesystem driver: %d\n", err); +} + +static inline void unregister_as_ntfs_legacy(void) +{ + unregister_filesystem(&ntfs_legacy_fs_type); +} +bool is_legacy_ntfs(struct super_block *sb) +{ + return sb->s_type == &ntfs_legacy_fs_type; +} +#else +static inline void register_as_ntfs_legacy(void) {} +static inline void unregister_as_ntfs_legacy(void) {} +bool is_legacy_ntfs(struct super_block *sb) { return false; } +#endif + + // clang-format on static int __init init_ntfs_fs(void) @@ -1832,6 +1889,7 @@ static int __init init_ntfs_fs(void) goto out1; } + register_as_ntfs_legacy(); err = register_filesystem(&ntfs_fs_type); if (err) goto out; @@ -1849,6 +1907,7 @@ static void __exit exit_ntfs_fs(void) rcu_barrier(); kmem_cache_destroy(ntfs_inode_cachep); unregister_filesystem(&ntfs_fs_type); + unregister_as_ntfs_legacy(); ntfs3_exit_bitmap(); #ifdef CONFIG_PROC_FS diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index b82185075de7df..f0467d3b3c880e 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2283,8 +2283,6 @@ unlock: ocfs2_inode_unlock(inode, 1); brelse(di_bh); out: - if (ret < 0) - ret = -EIO; return ret; } diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 5c04dde99981c7..2018501b224937 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -1274,7 +1274,7 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len, { struct dlm_query_nodeinfo *qn; struct dlm_ctxt *dlm = NULL; - int locked = 0, status = -EINVAL; + int status = -EINVAL; qn = (struct dlm_query_nodeinfo *) msg->buf; @@ -1290,12 +1290,11 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len, } spin_lock(&dlm->spinlock); - locked = 1; if (dlm->joining_node != qn->qn_nodenum) { mlog(ML_ERROR, "Node %d queried nodes on domain %s but " "joining node is %d\n", qn->qn_nodenum, qn->qn_domain, dlm->joining_node); - goto bail; + goto unlock; } /* Support for node query was added in 1.1 */ @@ -1305,14 +1304,14 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len, "but active dlm protocol is %d.%d\n", qn->qn_nodenum, qn->qn_domain, dlm->dlm_locking_proto.pv_major, dlm->dlm_locking_proto.pv_minor); - goto bail; + goto unlock; } status = dlm_match_nodes(dlm, qn); +unlock: + spin_unlock(&dlm->spinlock); bail: - if (locked) - spin_unlock(&dlm->spinlock); spin_unlock(&dlm_domain_lock); return status; @@ -1528,7 +1527,6 @@ static void dlm_send_join_asserts(struct dlm_ctxt *dlm, { int status, node, live; - status = 0; node = -1; while ((node = find_next_bit(node_map, O2NM_MAX_NODES, node + 1)) < O2NM_MAX_NODES) { diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index b8b6a191b5cb50..96b684763b3906 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -255,9 +255,9 @@ static struct dentry *ocfs2_fh_to_dentry(struct super_block *sb, if (fh_len < 3 || fh_type > 2) return NULL; - handle.ih_blkno = (u64)le32_to_cpu(fid->raw[0]) << 32; - handle.ih_blkno |= (u64)le32_to_cpu(fid->raw[1]); - handle.ih_generation = le32_to_cpu(fid->raw[2]); + handle.ih_blkno = (u64)le32_to_cpu((__force __le32)fid->raw[0]) << 32; + handle.ih_blkno |= (u64)le32_to_cpu((__force __le32)fid->raw[1]); + handle.ih_generation = le32_to_cpu((__force __le32)fid->raw[2]); return ocfs2_get_dentry(sb, &handle); } @@ -269,9 +269,9 @@ static struct dentry *ocfs2_fh_to_parent(struct super_block *sb, if (fh_type != 2 || fh_len < 6) return NULL; - parent.ih_blkno = (u64)le32_to_cpu(fid->raw[3]) << 32; - parent.ih_blkno |= (u64)le32_to_cpu(fid->raw[4]); - parent.ih_generation = le32_to_cpu(fid->raw[5]); + parent.ih_blkno = (u64)le32_to_cpu((__force __le32)fid->raw[3]) << 32; + parent.ih_blkno |= (u64)le32_to_cpu((__force __le32)fid->raw[4]); + parent.ih_generation = le32_to_cpu((__force __le32)fid->raw[5]); return ocfs2_get_dentry(sb, &parent); } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 0da8e7bd32616f..ccc57038a9779f 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1936,6 +1936,8 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, inode_lock(inode); + /* Wait all existing dio workers, newcomers will block on i_rwsem */ + inode_dio_wait(inode); /* * This prevents concurrent writes on other nodes */ diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 999111bfc27178..2cc5c99fe94167 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1621,6 +1621,7 @@ static struct super_block *ocfs2_inode_cache_get_super(struct ocfs2_caching_info } static void ocfs2_inode_cache_lock(struct ocfs2_caching_info *ci) +__acquires(&oi->ip_lock) { struct ocfs2_inode_info *oi = cache_info_to_inode(ci); @@ -1628,6 +1629,7 @@ static void ocfs2_inode_cache_lock(struct ocfs2_caching_info *ci) } static void ocfs2_inode_cache_unlock(struct ocfs2_caching_info *ci) +__releases(&oi->ip_lock) { struct ocfs2_inode_info *oi = cache_info_to_inode(ci); diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index b1550ba73f9634..71beef7f8a60b6 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -125,6 +125,7 @@ int ocfs2_fileattr_set(struct mnt_idmap *idmap, ocfs2_inode->ip_attr = flags; ocfs2_set_inode_flags(inode); + inode_set_ctime_current(inode); status = ocfs2_mark_inode_dirty(handle, inode, bh); if (status < 0) diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index c803c10dd97ef1..5df34561c551c6 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -212,14 +212,15 @@ static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb) void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb, unsigned int num_clusters) { - spin_lock(&osb->osb_lock); - if (osb->local_alloc_state == OCFS2_LA_DISABLED || - osb->local_alloc_state == OCFS2_LA_THROTTLED) - if (num_clusters >= osb->local_alloc_default_bits) { + if (num_clusters >= osb->local_alloc_default_bits) { + spin_lock(&osb->osb_lock); + if (osb->local_alloc_state == OCFS2_LA_DISABLED || + osb->local_alloc_state == OCFS2_LA_THROTTLED) { cancel_delayed_work(&osb->la_enable_wq); osb->local_alloc_state = OCFS2_LA_ENABLED; } - spin_unlock(&osb->osb_lock); + spin_unlock(&osb->osb_lock); + } } void ocfs2_la_enable_worker(struct work_struct *work) @@ -335,7 +336,7 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb) "found = %u, set = %u, taken = %u, off = %u\n", num_used, le32_to_cpu(alloc->id1.bitmap1.i_used), le32_to_cpu(alloc->id1.bitmap1.i_total), - OCFS2_LOCAL_ALLOC(alloc)->la_bm_off); + le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off)); status = -EINVAL; goto bail; @@ -863,14 +864,8 @@ static int ocfs2_local_alloc_find_clear_bits(struct ocfs2_super *osb, numfound = bitoff = startoff = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) != -1) { - if (bitoff == left) { - /* mlog(0, "bitoff (%d) == left", bitoff); */ - break; - } - /* mlog(0, "Found a zero: bitoff = %d, startoff = %d, " - "numfound = %d\n", bitoff, startoff, numfound);*/ - + while ((bitoff = ocfs2_find_next_zero_bit(bitmap, left, startoff)) < + left) { /* Ok, we found a zero bit... is it contig. or do we * start over?*/ if (bitoff == startoff) { @@ -976,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) - != -1) { - if ((bit_off < left) && (bit_off == start)) { + while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) < + left) { + if (bit_off == start) { count++; start++; continue; @@ -1002,8 +997,7 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, goto bail; } } - if (bit_off >= left) - break; + count = 1; start = bit_off + 1; } @@ -1220,7 +1214,7 @@ retry_enospc: OCFS2_LOCAL_ALLOC(alloc)->la_bitmap); trace_ocfs2_local_alloc_new_window_result( - OCFS2_LOCAL_ALLOC(alloc)->la_bm_off, + le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off), le32_to_cpu(alloc->id1.bitmap1.i_total)); bail: diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 1f9ed117e78b61..f9d6a4f9ca9219 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -685,7 +685,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, } ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh, - goal_bit, len); + goal_bit, len, 0, 0); if (ret) { ocfs2_rollback_alloc_dinode_counts(gb_inode, gb_bh, len, le16_to_cpu(gd->bg_chain)); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 9221a33f917b81..4d1ea8703fcdf3 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -566,7 +566,7 @@ static int __ocfs2_mknod_locked(struct inode *dir, fe->i_last_eb_blk = 0; strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE); fe->i_flags |= cpu_to_le32(OCFS2_VALID_FL); - ktime_get_real_ts64(&ts); + ktime_get_coarse_real_ts64(&ts); fe->i_atime = fe->i_ctime = fe->i_mtime = cpu_to_le64(ts.tv_sec); fe->i_mtime_nsec = fe->i_ctime_nsec = fe->i_atime_nsec = @@ -797,6 +797,7 @@ static int ocfs2_link(struct dentry *old_dentry, ocfs2_set_links_count(fe, inode->i_nlink); fe->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); fe->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); err = ocfs2_add_entry(handle, dentry, inode, @@ -993,6 +994,7 @@ static int ocfs2_unlink(struct inode *dir, drop_nlink(inode); drop_nlink(inode); ocfs2_set_links_count(fe, inode->i_nlink); + ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 7aebdbf5cc0a56..c93689b568fe08 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -883,7 +883,8 @@ struct ocfs2_group_desc __le16 bg_free_bits_count; /* Free bits count */ __le16 bg_chain; /* What chain I am in. */ /*10*/ __le32 bg_generation; - __le32 bg_reserved1; + __le16 bg_contig_free_bits; /* max contig free bits length */ + __le16 bg_reserved1; __le64 bg_next_group; /* Next group in my list, in blocks */ /*20*/ __le64 bg_parent_dinode; /* dinode which owns me, in diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 3f80a56d0d603c..1f303b1adf1ab9 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -630,7 +630,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode, rb->rf_records.rl_count = cpu_to_le16(ocfs2_refcount_recs_per_rb(osb->sb)); spin_lock(&osb->osb_lock); - rb->rf_generation = osb->s_next_generation++; + rb->rf_generation = cpu_to_le32(osb->s_next_generation++); spin_unlock(&osb->osb_lock); ocfs2_journal_dirty(handle, new_bh); diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c index a9d1296d736dc4..1fe61974d9f023 100644 --- a/fs/ocfs2/reservations.c +++ b/fs/ocfs2/reservations.c @@ -414,7 +414,7 @@ static int ocfs2_resmap_find_free_bits(struct ocfs2_reservation_map *resmap, start = search_start; while ((offset = ocfs2_find_next_zero_bit(bitmap, resmap->m_bitmap_len, - start)) != -1) { + start)) < resmap->m_bitmap_len) { /* Search reached end of the region */ if (offset >= (search_start + search_len)) break; diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index d65d43c61857a4..c4a4016d3866a3 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -91,6 +91,8 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, u16 cl_bpc = le16_to_cpu(cl->cl_bpc); u16 cl_cpg = le16_to_cpu(cl->cl_cpg); u16 old_bg_clusters; + u16 contig_bits; + __le16 old_bg_contig_free_bits; trace_ocfs2_update_last_group_and_inode(new_clusters, first_new_cluster); @@ -122,6 +124,11 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, le16_add_cpu(&group->bg_free_bits_count, -1 * backups); } + contig_bits = ocfs2_find_max_contig_free_bits(group->bg_bitmap, + le16_to_cpu(group->bg_bits), 0); + old_bg_contig_free_bits = group->bg_contig_free_bits; + group->bg_contig_free_bits = cpu_to_le16(contig_bits); + ocfs2_journal_dirty(handle, group_bh); /* update the inode accordingly. */ @@ -160,6 +167,7 @@ out_rollback: le16_add_cpu(&group->bg_free_bits_count, backups); le16_add_cpu(&group->bg_bits, -1 * num_bits); le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits); + group->bg_contig_free_bits = old_bg_contig_free_bits; } out: if (ret) diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 166c8918c825a6..f7b483f0de2add 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -50,6 +50,10 @@ struct ocfs2_suballoc_result { u64 sr_blkno; /* The first allocated block */ unsigned int sr_bit_offset; /* The bit in the bg */ unsigned int sr_bits; /* How many bits we claimed */ + unsigned int sr_max_contig_bits; /* The length for contiguous + * free bits, only available + * for cluster group + */ }; static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res) @@ -1272,6 +1276,26 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, return ret; } +u16 ocfs2_find_max_contig_free_bits(void *bitmap, + u16 total_bits, u16 start) +{ + u16 offset, free_bits; + u16 contig_bits = 0; + + while (start < total_bits) { + offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start); + if (offset == total_bits) + break; + + start = ocfs2_find_next_bit(bitmap, total_bits, offset); + free_bits = start - offset; + if (contig_bits < free_bits) + contig_bits = free_bits; + } + + return contig_bits; +} + static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, struct buffer_head *bg_bh, unsigned int bits_wanted, @@ -1280,6 +1304,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, { void *bitmap; u16 best_offset, best_size; + u16 prev_best_size = 0; int offset, start, found, status = 0; struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; @@ -1290,10 +1315,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, found = start = best_offset = best_size = 0; bitmap = bg->bg_bitmap; - while((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) != -1) { - if (offset == total_bits) - break; - + while ((offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start)) < + total_bits) { if (!ocfs2_test_bg_bit_allocatable(bg_bh, offset)) { /* We found a zero, but we can't use it as it * hasn't been put to disk yet! */ @@ -1308,6 +1331,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, /* got a zero after some ones */ found = 1; start = offset + 1; + prev_best_size = best_size; } if (found > best_size) { best_size = found; @@ -1320,6 +1344,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb, } } + /* best_size will be allocated, we save prev_best_size */ + res->sr_max_contig_bits = prev_best_size; if (best_size) { res->sr_bit_offset = best_offset; res->sr_bits = best_size; @@ -1337,11 +1363,16 @@ int ocfs2_block_group_set_bits(handle_t *handle, struct ocfs2_group_desc *bg, struct buffer_head *group_bh, unsigned int bit_off, - unsigned int num_bits) + unsigned int num_bits, + unsigned int max_contig_bits, + int fastpath) { int status; void *bitmap = bg->bg_bitmap; int journal_type = OCFS2_JOURNAL_ACCESS_WRITE; + unsigned int start = bit_off + num_bits; + u16 contig_bits; + struct ocfs2_super *osb = OCFS2_SB(alloc_inode->i_sb); /* All callers get the descriptor via * ocfs2_read_group_descriptor(). Any corruption is a code bug. */ @@ -1373,6 +1404,29 @@ int ocfs2_block_group_set_bits(handle_t *handle, while(num_bits--) ocfs2_set_bit(bit_off++, bitmap); + /* + * this is optimize path, caller set old contig value + * in max_contig_bits to bypass finding action. + */ + if (fastpath) { + bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits); + } else if (ocfs2_is_cluster_bitmap(alloc_inode)) { + /* + * Usually, the block group bitmap allocates only 1 bit + * at a time, while the cluster group allocates n bits + * each time. Therefore, we only save the contig bits for + * the cluster group. + */ + contig_bits = ocfs2_find_max_contig_free_bits(bitmap, + le16_to_cpu(bg->bg_bits), start); + if (contig_bits > max_contig_bits) + max_contig_bits = contig_bits; + bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits); + ocfs2_local_alloc_seen_free_bits(osb, max_contig_bits); + } else { + bg->bg_contig_free_bits = 0; + } + ocfs2_journal_dirty(handle, group_bh); bail: @@ -1486,7 +1540,12 @@ static int ocfs2_cluster_group_search(struct inode *inode, BUG_ON(!ocfs2_is_cluster_bitmap(inode)); - if (gd->bg_free_bits_count) { + if (le16_to_cpu(gd->bg_contig_free_bits) && + le16_to_cpu(gd->bg_contig_free_bits) < bits_wanted) + return -ENOSPC; + + /* ->bg_contig_free_bits may un-initialized, so compare again */ + if (le16_to_cpu(gd->bg_free_bits_count) >= bits_wanted) { max_bits = le16_to_cpu(gd->bg_bits); /* Tail groups in cluster bitmaps which aren't cpg @@ -1530,13 +1589,6 @@ static int ocfs2_cluster_group_search(struct inode *inode, * of bits. */ if (min_bits <= res->sr_bits) search = 0; /* success */ - else if (res->sr_bits) { - /* - * Don't show bits which we'll be returning - * for allocation to the local alloc bitmap. - */ - ocfs2_local_alloc_seen_free_bits(osb, res->sr_bits); - } } return search; @@ -1555,7 +1607,7 @@ static int ocfs2_block_group_search(struct inode *inode, BUG_ON(min_bits != 1); BUG_ON(ocfs2_is_cluster_bitmap(inode)); - if (bg->bg_free_bits_count) { + if (le16_to_cpu(bg->bg_free_bits_count) >= bits_wanted) { ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb), group_bh, bits_wanted, le16_to_cpu(bg->bg_bits), @@ -1715,7 +1767,8 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac, } ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh, - res->sr_bit_offset, res->sr_bits); + res->sr_bit_offset, res->sr_bits, + res->sr_max_contig_bits, 0); if (ret < 0) { ocfs2_rollback_alloc_dinode_counts(alloc_inode, ac->ac_bh, res->sr_bits, @@ -1849,7 +1902,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, bg, group_bh, res->sr_bit_offset, - res->sr_bits); + res->sr_bits, + res->sr_max_contig_bits, + 0); if (status < 0) { ocfs2_rollback_alloc_dinode_counts(alloc_inode, ac->ac_bh, res->sr_bits, chain); @@ -1951,7 +2006,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) { if (i == victim) continue; - if (!cl->cl_recs[i].c_free) + if (le32_to_cpu(cl->cl_recs[i].c_free) < bits_wanted) continue; ac->ac_chain = i; @@ -2163,7 +2218,9 @@ int ocfs2_claim_new_inode_at_loc(handle_t *handle, bg, bg_bh, res->sr_bit_offset, - res->sr_bits); + res->sr_bits, + res->sr_max_contig_bits, + 0); if (ret < 0) { ocfs2_rollback_alloc_dinode_counts(ac->ac_inode, ac->ac_bh, res->sr_bits, chain); @@ -2382,11 +2439,13 @@ static int ocfs2_block_group_clear_bits(handle_t *handle, struct buffer_head *group_bh, unsigned int bit_off, unsigned int num_bits, + unsigned int max_contig_bits, void (*undo_fn)(unsigned int bit, unsigned long *bmap)) { int status; unsigned int tmp; + u16 contig_bits; struct ocfs2_group_desc *undo_bg = NULL; struct journal_head *jh; @@ -2433,6 +2492,20 @@ static int ocfs2_block_group_clear_bits(handle_t *handle, num_bits); } + /* + * TODO: even 'num_bits == 1' (the worst case, release 1 cluster), + * we still need to rescan whole bitmap. + */ + if (ocfs2_is_cluster_bitmap(alloc_inode)) { + contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap, + le16_to_cpu(bg->bg_bits), 0); + if (contig_bits > max_contig_bits) + max_contig_bits = contig_bits; + bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits); + } else { + bg->bg_contig_free_bits = 0; + } + if (undo_fn) spin_unlock(&jh->b_state_lock); @@ -2459,6 +2532,7 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle, struct ocfs2_chain_list *cl = &fe->id2.i_chain; struct buffer_head *group_bh = NULL; struct ocfs2_group_desc *group; + __le16 old_bg_contig_free_bits = 0; /* The alloc_bh comes from ocfs2_free_dinode() or * ocfs2_free_clusters(). The callers have all locked the @@ -2483,9 +2557,11 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle, BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits)); + if (ocfs2_is_cluster_bitmap(alloc_inode)) + old_bg_contig_free_bits = group->bg_contig_free_bits; status = ocfs2_block_group_clear_bits(handle, alloc_inode, group, group_bh, - start_bit, count, undo_fn); + start_bit, count, 0, undo_fn); if (status < 0) { mlog_errno(status); goto bail; @@ -2496,7 +2572,8 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle, if (status < 0) { mlog_errno(status); ocfs2_block_group_set_bits(handle, alloc_inode, group, group_bh, - start_bit, count); + start_bit, count, + le16_to_cpu(old_bg_contig_free_bits), 1); goto bail; } diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index 9c74eace3adc15..b481b834857d33 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -79,12 +79,16 @@ void ocfs2_rollback_alloc_dinode_counts(struct inode *inode, struct buffer_head *di_bh, u32 num_bits, u16 chain); +u16 ocfs2_find_max_contig_free_bits(void *bitmap, + u16 total_bits, u16 start); int ocfs2_block_group_set_bits(handle_t *handle, struct inode *alloc_inode, struct ocfs2_group_desc *bg, struct buffer_head *group_bh, unsigned int bit_off, - unsigned int num_bits); + unsigned int num_bits, + unsigned int max_contig_bits, + int fastpath); int ocfs2_claim_metadata(handle_t *handle, struct ocfs2_alloc_context *ac, diff --git a/fs/proc/inode.c b/fs/proc/inode.c index dcd513dccf55cb..d19434e2a58e71 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -451,15 +451,13 @@ pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned lo unsigned long len, unsigned long pgoff, unsigned long flags) { - typeof_member(struct proc_ops, proc_get_unmapped_area) get_area; + if (pde->proc_ops->proc_get_unmapped_area) + return pde->proc_ops->proc_get_unmapped_area(file, orig_addr, len, pgoff, flags); - get_area = pde->proc_ops->proc_get_unmapped_area; #ifdef CONFIG_MMU - if (!get_area) - get_area = current->mm->get_unmapped_area; + return mm_get_unmapped_area(current->mm, file, orig_addr, len, pgoff, flags); #endif - if (get_area) - return get_area(file, orig_addr, len, pgoff, flags); + return orig_addr; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 45af9a989d4040..245171d9164be3 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -89,8 +89,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "SwapTotal: ", i.totalswap); show_val_kb(m, "SwapFree: ", i.freeswap); #ifdef CONFIG_ZSWAP - seq_printf(m, "Zswap: %8lu kB\n", - (unsigned long)(zswap_pool_total_size >> 10)); + show_val_kb(m, "Zswap: ", zswap_total_pages()); seq_printf(m, "Zswapped: %8lu kB\n", (unsigned long)atomic_read(&zswap_stored_pages) << (PAGE_SHIFT - 10)); diff --git a/fs/proc/page.c b/fs/proc/page.c index 195b077c0facbf..2fb64bdb64eb1d 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -67,7 +67,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, */ ppage = pfn_to_online_page(pfn); - if (!ppage || PageSlab(ppage) || page_has_type(ppage)) + if (!ppage) pcount = 0; else pcount = page_mapcount(ppage); @@ -107,10 +107,13 @@ static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit) return ((kflags >> kbit) & 1) << ubit; } -u64 stable_page_flags(struct page *page) +u64 stable_page_flags(const struct page *page) { - u64 k; - u64 u; + const struct folio *folio; + unsigned long k; + unsigned long mapping; + bool is_anon; + u64 u = 0; /* * pseudo flag: KPF_NOPAGE @@ -118,52 +121,47 @@ u64 stable_page_flags(struct page *page) */ if (!page) return 1 << KPF_NOPAGE; + folio = page_folio(page); - k = page->flags; - u = 0; + k = folio->flags; + mapping = (unsigned long)folio->mapping; + is_anon = mapping & PAGE_MAPPING_ANON; /* * pseudo flags for the well known (anonymous) memory mapped pages - * - * Note that page->_mapcount is overloaded in SLAB, so the - * simple test in page_mapped() is not enough. */ - if (!PageSlab(page) && page_mapped(page)) + if (page_mapped(page)) u |= 1 << KPF_MMAP; - if (PageAnon(page)) + if (is_anon) { u |= 1 << KPF_ANON; - if (PageKsm(page)) - u |= 1 << KPF_KSM; + if (mapping & PAGE_MAPPING_KSM) + u |= 1 << KPF_KSM; + } /* * compound pages: export both head/tail info * they together define a compound page's start/end pos and order */ - if (PageHead(page)) - u |= 1 << KPF_COMPOUND_HEAD; - if (PageTail(page)) + if (page == &folio->page) + u |= kpf_copy_bit(k, KPF_COMPOUND_HEAD, PG_head); + else u |= 1 << KPF_COMPOUND_TAIL; - if (PageHuge(page)) + if (folio_test_hugetlb(folio)) u |= 1 << KPF_HUGE; /* - * PageTransCompound can be true for non-huge compound pages (slab - * pages or pages allocated by drivers with __GFP_COMP) because it - * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon + * We need to check PageLRU/PageAnon * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page)) { - struct page *head = compound_head(page); - - if (PageLRU(head) || PageAnon(head)) + else if (folio_test_large(folio)) { + if ((k & (1 << PG_lru)) || is_anon) u |= 1 << KPF_THP; - else if (is_huge_zero_page(head)) { + else if (is_huge_zero_folio(folio)) { u |= 1 << KPF_ZERO_PAGE; u |= 1 << KPF_THP; } } else if (is_zero_pfn(page_to_pfn(page))) u |= 1 << KPF_ZERO_PAGE; - /* * Caveats on high order pages: PG_buddy and PG_slab will only be set * on the head page. @@ -177,16 +175,17 @@ u64 stable_page_flags(struct page *page) u |= 1 << KPF_OFFLINE; if (PageTable(page)) u |= 1 << KPF_PGTABLE; + if (folio_test_slab(folio)) + u |= 1 << KPF_SLAB; - if (page_is_idle(page)) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) + u |= kpf_copy_bit(k, KPF_IDLE, PG_idle); +#else + if (folio_test_idle(folio)) u |= 1 << KPF_IDLE; +#endif u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); - - u |= kpf_copy_bit(k, KPF_SLAB, PG_slab); - if (PageTail(page) && PageSlab(page)) - u |= 1 << KPF_SLAB; - u |= kpf_copy_bit(k, KPF_ERROR, PG_error); u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty); u |= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate); @@ -197,7 +196,8 @@ u64 stable_page_flags(struct page *page) u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active); u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim); - if (PageSwapCache(page)) +#define SWAPCACHE ((1 << PG_swapbacked) | (1 << PG_swapcache)) + if ((k & SWAPCACHE) == SWAPCACHE) u |= 1 << KPF_SWAPCACHE; u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked); @@ -205,7 +205,10 @@ u64 stable_page_flags(struct page *page) u |= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked); #ifdef CONFIG_MEMORY_FAILURE - u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison); + if (u & (1 << KPF_HUGE)) + u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison); + else + u |= kpf_copy_bit(page->flags, KPF_HWPOISON, PG_hwpoison); #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED @@ -231,7 +234,6 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, { const unsigned long max_dump_pfn = get_max_dump_pfn(); u64 __user *out = (u64 __user *)buf; - struct page *ppage; unsigned long src = *ppos; unsigned long pfn; ssize_t ret = 0; @@ -248,9 +250,9 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, * TODO: ZONE_DEVICE support requires to identify * memmaps that were actually initialized. */ - ppage = pfn_to_online_page(pfn); + struct page *page = pfn_to_online_page(pfn); - if (put_user(stable_page_flags(ppage), out)) { + if (put_user(stable_page_flags(page), out)) { ret = -EFAULT; break; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 23fbab954c20b6..81fbecfe5ff6c7 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -411,14 +411,14 @@ struct mem_size_stats { }; static void smaps_page_accumulate(struct mem_size_stats *mss, - struct page *page, unsigned long size, unsigned long pss, + struct folio *folio, unsigned long size, unsigned long pss, bool dirty, bool locked, bool private) { mss->pss += pss; - if (PageAnon(page)) + if (folio_test_anon(folio)) mss->pss_anon += pss; - else if (PageSwapBacked(page)) + else if (folio_test_swapbacked(folio)) mss->pss_shmem += pss; else mss->pss_file += pss; @@ -426,7 +426,7 @@ static void smaps_page_accumulate(struct mem_size_stats *mss, if (locked) mss->pss_locked += pss; - if (dirty || PageDirty(page)) { + if (dirty || folio_test_dirty(folio)) { mss->pss_dirty += pss; if (private) mss->private_dirty += size; @@ -444,6 +444,7 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, bool compound, bool young, bool dirty, bool locked, bool migration) { + struct folio *folio = page_folio(page); int i, nr = compound ? compound_nr(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -451,27 +452,28 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, * First accumulate quantities that depend only on |size| and the type * of the compound page. */ - if (PageAnon(page)) { + if (folio_test_anon(folio)) { mss->anonymous += size; - if (!PageSwapBacked(page) && !dirty && !PageDirty(page)) + if (!folio_test_swapbacked(folio) && !dirty && + !folio_test_dirty(folio)) mss->lazyfree += size; } - if (PageKsm(page)) + if (folio_test_ksm(folio)) mss->ksm += size; mss->resident += size; /* Accumulate the size in pages that have been accessed. */ - if (young || page_is_young(page) || PageReferenced(page)) + if (young || folio_test_young(folio) || folio_test_referenced(folio)) mss->referenced += size; /* * Then accumulate quantities that may depend on sharing, or that may * differ page-by-page. * - * page_count(page) == 1 guarantees the page is mapped exactly once. + * refcount == 1 guarantees the page is mapped exactly once. * If any subpage of the compound page mapped with PTE it would elevate - * page_count(). + * the refcount. * * The page_mapcount() is called to get a snapshot of the mapcount. * Without holding the page lock this snapshot can be slightly wrong as @@ -480,9 +482,9 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, * especially for migration entries. Treat regular migration entries * as mapcount == 1. */ - if ((page_count(page) == 1) || migration) { - smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty, - locked, true); + if ((folio_ref_count(folio) == 1) || migration) { + smaps_page_accumulate(mss, folio, size, size << PSS_SHIFT, + dirty, locked, true); return; } for (i = 0; i < nr; i++, page++) { @@ -490,8 +492,8 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, unsigned long pss = PAGE_SIZE << PSS_SHIFT; if (mapcount >= 2) pss /= mapcount; - smaps_page_accumulate(mss, page, PAGE_SIZE, pss, dirty, locked, - mapcount < 2); + smaps_page_accumulate(mss, folio, PAGE_SIZE, pss, + dirty, locked, mapcount < 2); } } @@ -576,6 +578,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; + struct folio *folio; bool migration = false; if (pmd_present(*pmd)) { @@ -590,11 +593,12 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, } if (IS_ERR_OR_NULL(page)) return; - if (PageAnon(page)) + folio = page_folio(page); + if (folio_test_anon(folio)) mss->anonymous_thp += HPAGE_PMD_SIZE; - else if (PageSwapBacked(page)) + else if (folio_test_swapbacked(folio)) mss->shmem_thp += HPAGE_PMD_SIZE; - else if (is_zone_device_page(page)) + else if (folio_is_zone_device(folio)) /* pass */; else mss->file_thp += HPAGE_PMD_SIZE; @@ -726,19 +730,20 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; - struct page *page = NULL; - pte_t ptent = ptep_get(pte); + pte_t ptent = huge_ptep_get(pte); + struct folio *folio = NULL; if (pte_present(ptent)) { - page = vm_normal_page(vma, addr, ptent); + folio = page_folio(pte_page(ptent)); } else if (is_swap_pte(ptent)) { swp_entry_t swpent = pte_to_swp_entry(ptent); if (is_pfn_swap_entry(swpent)) - page = pfn_swap_entry_to_page(swpent); + folio = pfn_swap_entry_folio(swpent); } - if (page) { - if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte)) + if (folio) { + if (folio_likely_mapped_shared(folio) || + hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); @@ -866,8 +871,8 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %8u\n", - !!thp_vma_allowable_orders(vma, vma->vm_flags, true, false, - true, THP_ORDERS_ALL)); + !!thp_vma_allowable_orders(vma, vma->vm_flags, + TVA_SMAPS | TVA_ENFORCE_SYSFS, THP_ORDERS_ALL)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); @@ -1161,7 +1166,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, struct vm_area_struct *vma = walk->vma; pte_t *pte, ptent; spinlock_t *ptl; - struct page *page; + struct folio *folio; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { @@ -1173,12 +1178,12 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, if (!pmd_present(*pmd)) goto out; - page = pmd_page(*pmd); + folio = pmd_folio(*pmd); /* Clear accessed and referenced bits. */ pmdp_test_and_clear_young(vma, addr, pmd); - test_and_clear_page_young(page); - ClearPageReferenced(page); + folio_test_clear_young(folio); + folio_clear_referenced(folio); out: spin_unlock(ptl); return 0; @@ -1200,14 +1205,14 @@ out: if (!pte_present(ptent)) continue; - page = vm_normal_page(vma, addr, ptent); - if (!page) + folio = vm_normal_folio(vma, addr, ptent); + if (!folio) continue; /* Clear accessed and referenced bits. */ ptep_test_and_clear_young(vma, addr, pte); - test_and_clear_page_young(page); - ClearPageReferenced(page); + folio_test_clear_young(folio); + folio_clear_referenced(folio); } pte_unmap_unlock(pte - 1, ptl); cond_resched(); @@ -1574,12 +1579,13 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, pte = huge_ptep_get(ptep); if (pte_present(pte)) { - struct page *page = pte_page(pte); + struct folio *folio = page_folio(pte_page(pte)); - if (!PageAnon(page)) + if (!folio_test_anon(folio)) flags |= PM_FILE; - if (page_mapcount(page) == 1) + if (!folio_likely_mapped_shared(folio) && + !hugetlb_pmd_shared(ptep)) flags |= PM_MMAP_EXCLUSIVE; if (huge_pte_uffd_wp(pte)) @@ -2547,28 +2553,29 @@ struct numa_maps_private { static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty, unsigned long nr_pages) { + struct folio *folio = page_folio(page); int count = page_mapcount(page); md->pages += nr_pages; - if (pte_dirty || PageDirty(page)) + if (pte_dirty || folio_test_dirty(folio)) md->dirty += nr_pages; - if (PageSwapCache(page)) + if (folio_test_swapcache(folio)) md->swapcache += nr_pages; - if (PageActive(page) || PageUnevictable(page)) + if (folio_test_active(folio) || folio_test_unevictable(folio)) md->active += nr_pages; - if (PageWriteback(page)) + if (folio_test_writeback(folio)) md->writeback += nr_pages; - if (PageAnon(page)) + if (folio_test_anon(folio)) md->anon += nr_pages; if (count > md->mapcount_max) md->mapcount_max = count; - md->node[page_to_nid(page)] += nr_pages; + md->node[folio_nid(folio)] += nr_pages; } static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 1fb213f379a5b6..5d08d4d159d30b 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -1370,9 +1370,8 @@ static void vmcoredd_write_header(void *buf, struct vmcoredd_data *data, vdd_hdr->n_descsz = size + sizeof(vdd_hdr->dump_name); vdd_hdr->n_type = NT_VMCOREDD; - strncpy((char *)vdd_hdr->name, VMCOREDD_NOTE_NAME, - sizeof(vdd_hdr->name)); - memcpy(vdd_hdr->dump_name, data->dump_name, sizeof(vdd_hdr->dump_name)); + strscpy_pad(vdd_hdr->name, VMCOREDD_NOTE_NAME); + strscpy_pad(vdd_hdr->dump_name, data->dump_name); } /** diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index c7a1aa3c882b02..b45c7edc3225e4 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -35,7 +35,7 @@ static unsigned long ramfs_mmu_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { - return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags); } const struct file_operations ramfs_file_operations = { diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index d41eedbff674ab..39277c37185cac 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 d6669ce4ae87f0..6ff35570db813a 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1190,6 +1190,7 @@ struct cifs_fattr { */ struct cifs_tcon { struct list_head tcon_list; + int debug_id; /* Debugging for tracing */ int tc_count; struct list_head rlist; /* reconnect list */ spinlock_t tc_lock; /* protect anything here that is not protected */ @@ -1276,7 +1277,9 @@ struct cifs_tcon { __u32 max_cached_dirs; #ifdef CONFIG_CIFS_FSCACHE u64 resource_id; /* server resource id */ + bool fscache_acquired; /* T if we've tried acquiring a cookie */ struct fscache_volume *fscache; /* cookie for share */ + struct mutex fscache_lock; /* Prevent regetting a cookie */ #endif struct list_head pending_opens; /* list of incomplete opens */ struct cached_fids *cfids; diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index c0513fbb8a59d4..c46d418c1c0c3e 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -882,7 +882,7 @@ typedef struct smb_com_open_rsp { __u8 OplockLevel; __u16 Fid; __le32 CreateAction; - struct_group(common_attributes, + struct_group_attr(common_attributes, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; @@ -2266,7 +2266,7 @@ typedef struct { /* QueryFileInfo/QueryPathinfo (also for SetPath/SetFile) data buffer formats */ /******************************************************************************/ typedef struct { /* data block encoding of response to level 263 QPathInfo */ - struct_group(common_attributes, + struct_group_attr(common_attributes, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 8e0a348f1f660e..fbc358c09da3b1 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 4e35970681bf05..7a16e12f5da879 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -1943,7 +1943,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) } /* no need to setup directory caching on IPC share, so pass in false */ - tcon = tcon_info_alloc(false); + tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_ipc); if (tcon == NULL) return -ENOMEM; @@ -1960,7 +1960,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (rc) { cifs_server_dbg(VFS, "failed to connect to IPC (rc=%d)\n", rc); - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc_fail); goto out; } @@ -2043,7 +2043,7 @@ void __cifs_put_smb_ses(struct cifs_ses *ses) * files on session close, as specified in MS-SMB2 3.3.5.6 Receiving an * SMB2 LOGOFF Request. */ - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc); if (do_logoff) { xid = get_xid(); rc = server->ops->logoff(xid, ses); @@ -2432,6 +2432,8 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) continue; } ++tcon->tc_count; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_find); spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); return tcon; @@ -2441,7 +2443,7 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) } void -cifs_put_tcon(struct cifs_tcon *tcon) +cifs_put_tcon(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace) { unsigned int xid; struct cifs_ses *ses; @@ -2457,6 +2459,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count); spin_lock(&cifs_tcp_ses_lock); spin_lock(&tcon->tc_lock); + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count - 1, trace); if (--tcon->tc_count > 0) { spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); @@ -2493,7 +2496,7 @@ cifs_put_tcon(struct cifs_tcon *tcon) _free_xid(xid); cifs_fscache_release_super_cookie(tcon); - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free); cifs_put_smb_ses(ses); } @@ -2547,7 +2550,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) nohandlecache = ctx->nohandlecache; else nohandlecache = true; - tcon = tcon_info_alloc(!nohandlecache); + tcon = tcon_info_alloc(!nohandlecache, netfs_trace_tcon_ref_new); if (tcon == NULL) { rc = -ENOMEM; goto out_fail; @@ -2737,7 +2740,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) return tcon; out_fail: - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free_fail); return ERR_PTR(rc); } @@ -2754,7 +2757,7 @@ cifs_put_tlink(struct tcon_link *tlink) } if (!IS_ERR(tlink_tcon(tlink))) - cifs_put_tcon(tlink_tcon(tlink)); + cifs_put_tcon(tlink_tcon(tlink), netfs_trace_tcon_ref_put_tlink); kfree(tlink); } @@ -3319,7 +3322,7 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx) int rc = 0; if (mnt_ctx->tcon) - cifs_put_tcon(mnt_ctx->tcon); + cifs_put_tcon(mnt_ctx->tcon, netfs_trace_tcon_ref_put_mnt_ctx); else if (mnt_ctx->ses) cifs_put_smb_ses(mnt_ctx->ses); else if (mnt_ctx->server) diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 6c727d8c31e870..3bbac925d0766b 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -748,6 +748,16 @@ static int smb3_fs_context_validate(struct fs_context *fc) /* set the port that we got earlier */ cifs_set_port((struct sockaddr *)&ctx->dstaddr, ctx->port); + if (ctx->uid_specified && !ctx->forceuid_specified) { + ctx->override_uid = 1; + pr_notice("enabling forceuid mount option implicitly because uid= option is specified\n"); + } + + if (ctx->gid_specified && !ctx->forcegid_specified) { + ctx->override_gid = 1; + pr_notice("enabling forcegid mount option implicitly because gid= option is specified\n"); + } + if (ctx->override_uid && !ctx->uid_specified) { ctx->override_uid = 0; pr_notice("ignoring forceuid mount option specified with no uid= option\n"); @@ -1019,12 +1029,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->override_uid = 0; else ctx->override_uid = 1; + ctx->forceuid_specified = true; break; case Opt_forcegid: if (result.negated) ctx->override_gid = 0; else ctx->override_gid = 1; + ctx->forcegid_specified = true; break; case Opt_perm: if (result.negated) diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index a947bddeba273e..cf577ec0dd0ac4 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -165,6 +165,8 @@ enum cifs_param { }; struct smb3_fs_context { + bool forceuid_specified; + bool forcegid_specified; bool uid_specified; bool cruid_specified; bool gid_specified; diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index 340efce8f05295..1a895e6243ee9a 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/misc.c b/fs/smb/client/misc.c index 7d15a1969b8184..07c468ddb88a89 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -111,9 +111,10 @@ sesInfoFree(struct cifs_ses *buf_to_free) } struct cifs_tcon * -tcon_info_alloc(bool dir_leases_enabled) +tcon_info_alloc(bool dir_leases_enabled, enum smb3_tcon_ref_trace trace) { struct cifs_tcon *ret_buf; + static atomic_t tcon_debug_id; ret_buf = kzalloc(sizeof(*ret_buf), GFP_KERNEL); if (!ret_buf) @@ -130,7 +131,8 @@ tcon_info_alloc(bool dir_leases_enabled) atomic_inc(&tconInfoAllocCount); ret_buf->status = TID_NEW; - ++ret_buf->tc_count; + ret_buf->debug_id = atomic_inc_return(&tcon_debug_id); + ret_buf->tc_count = 1; spin_lock_init(&ret_buf->tc_lock); INIT_LIST_HEAD(&ret_buf->openFileList); INIT_LIST_HEAD(&ret_buf->tcon_list); @@ -139,17 +141,22 @@ tcon_info_alloc(bool dir_leases_enabled) atomic_set(&ret_buf->num_local_opens, 0); atomic_set(&ret_buf->num_remote_opens, 0); ret_buf->stats_from_time = ktime_get_real_seconds(); +#ifdef CONFIG_CIFS_FSCACHE + mutex_init(&ret_buf->fscache_lock); +#endif + trace_smb3_tcon_ref(ret_buf->debug_id, ret_buf->tc_count, trace); return ret_buf; } void -tconInfoFree(struct cifs_tcon *tcon) +tconInfoFree(struct cifs_tcon *tcon, enum smb3_tcon_ref_trace trace) { if (tcon == NULL) { cifs_dbg(FYI, "Null buffer passed to tconInfoFree\n"); return; } + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, trace); free_cached_dirs(tcon->cfids); atomic_dec(&tconInfoAllocCount); kfree(tcon->nativeFileSystem); diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index cc72be5a93a933..677ef6f99a5be4 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 78c94d0350fe99..28f0b7d19d534b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2915,8 +2915,11 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, tcon = list_first_entry_or_null(&ses->tcon_list, struct cifs_tcon, tcon_list); - if (tcon) + if (tcon) { tcon->tc_count++; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_dfs_refer); + } spin_unlock(&cifs_tcp_ses_lock); } @@ -2980,6 +2983,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, /* ipc tcons are not refcounted */ spin_lock(&cifs_tcp_ses_lock); tcon->tc_count--; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_dec_dfs_refer); /* tc_count can never go negative */ WARN_ON(tcon->tc_count < 0); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 86c647a947ccd1..a5efce03cb58e2 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4138,6 +4138,8 @@ void smb2_reconnect_server(struct work_struct *work) list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->need_reconnect || tcon->need_reopen_files) { tcon->tc_count++; + trace_smb3_tcon_ref(tcon->debug_id, tcon->tc_count, + netfs_trace_tcon_ref_get_reconnect_server); list_add_tail(&tcon->rlist, &tmp_list); tcon_selected = true; } @@ -4176,14 +4178,14 @@ void smb2_reconnect_server(struct work_struct *work) if (tcon->ipc) cifs_put_smb_ses(tcon->ses); else - cifs_put_tcon(tcon); + cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_reconnect_server); } if (!ses_exist) goto done; /* allocate a dummy tcon struct used for reconnect */ - tcon = tcon_info_alloc(false); + tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_reconnect_server); if (!tcon) { resched = true; list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) { @@ -4206,7 +4208,7 @@ void smb2_reconnect_server(struct work_struct *work) list_del_init(&ses->rlist); cifs_put_smb_ses(ses); } - tconInfoFree(tcon); + tconInfoFree(tcon, netfs_trace_tcon_ref_free_reconnect_server); done: cifs_dbg(FYI, "Reconnecting tcons and channels finished\n"); diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index c72a3b2886b7ff..2fccf0d4f53d27 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -320,7 +320,7 @@ struct smb2_file_reparse_point_info { } __packed; struct smb2_file_network_open_info { - struct_group(network_open_info, + struct_group_attr(network_open_info, __packed, __le64 CreationTime; __le64 LastAccessTime; __le64 LastWriteTime; diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 1d6e54f7879e6a..02135a6053051e 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 5e83cb9da9028e..604e52876cd2d9 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/client/transport.c b/fs/smb/client/transport.c index 994d7019343297..ddf1a3aafee5c6 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -909,12 +909,15 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) list_del_init(&mid->qhead); mid->mid_flags |= MID_DELETED; } + spin_unlock(&server->mid_lock); cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n", __func__, mid->mid, mid->mid_state); rc = -EIO; + goto sync_mid_done; } spin_unlock(&server->mid_lock); +sync_mid_done: release_mid(mid); return rc; } @@ -1057,9 +1060,11 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) index = (uint)atomic_inc_return(&ses->chan_seq); index %= ses->chan_count; } + + server = ses->chans[index].server; spin_unlock(&ses->chan_lock); - return ses->chans[index].server; + return server; } int diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 1b594307c9d5a0..202ff912815604 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 686b321c5a8bb5..f4e55199938d58 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 c0788188aa82fa..c67fbc8d6683ef 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 5723bbf372d7cc..355824151c2d88 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 22f0f3db3ac92d..51b1b0bed616ee 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/namei.c b/fs/squashfs/namei.c index 11e4539b9eae4c..65aae7e2a859d0 100644 --- a/fs/squashfs/namei.c +++ b/fs/squashfs/namei.c @@ -62,27 +62,21 @@ */ static int get_dir_index_using_name(struct super_block *sb, u64 *next_block, int *next_offset, u64 index_start, - int index_offset, int i_count, const char *name, - int len) + int index_offset, int i_count, const char *name) { struct squashfs_sb_info *msblk = sb->s_fs_info; int i, length = 0, err; unsigned int size; struct squashfs_dir_index *index; - char *str; TRACE("Entered get_dir_index_using_name, i_count %d\n", i_count); - index = kmalloc(sizeof(*index) + SQUASHFS_NAME_LEN * 2 + 2, GFP_KERNEL); + index = kmalloc(sizeof(*index) + SQUASHFS_NAME_LEN + 1, GFP_KERNEL); if (index == NULL) { ERROR("Failed to allocate squashfs_dir_index\n"); goto out; } - str = &index->name[SQUASHFS_NAME_LEN + 1]; - strncpy(str, name, len); - str[len] = '\0'; - for (i = 0; i < i_count; i++) { err = squashfs_read_metadata(sb, index, &index_start, &index_offset, sizeof(*index)); @@ -101,7 +95,7 @@ static int get_dir_index_using_name(struct super_block *sb, index->name[size] = '\0'; - if (strcmp(index->name, str) > 0) + if (strcmp(index->name, name) > 0) break; length = le32_to_cpu(index->index); @@ -153,7 +147,7 @@ static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry, length = get_dir_index_using_name(dir->i_sb, &block, &offset, squashfs_i(dir)->dir_idx_start, squashfs_i(dir)->dir_idx_offset, - squashfs_i(dir)->dir_idx_cnt, name, len); + squashfs_i(dir)->dir_idx_cnt, name); while (length < i_size_read(dir)) { /* diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 60dcfafdc11a84..d2c3879745e535 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -657,7 +657,10 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) struct userfaultfd_fork_ctx *fctx; octx = vma->vm_userfaultfd_ctx.ctx; - if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { + if (!octx) + return 0; + + if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) { vma_start_write(vma); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); @@ -895,6 +898,10 @@ static int userfaultfd_release(struct inode *inode, struct file *file) prev = vma; continue; } + /* Reset ptes for the whole vma range if wr-protected */ + if (userfaultfd_wp(vma)) + uffd_wp_range(vma, vma->vm_start, + vma->vm_end - vma->vm_start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; vma = vma_modify_flags_uffd(&vmi, prev, vma, vma->vm_start, vma->vm_end, new_flags, diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h index 600d4e2641dae1..62cac266a1c89e 100644 --- a/include/acpi/platform/aclinuxex.h +++ b/include/acpi/platform/aclinuxex.h @@ -47,26 +47,19 @@ acpi_status acpi_os_terminate(void); * However, boot has (system_state != SYSTEM_RUNNING) * to quiet __might_sleep() in kmalloc() and resume does not. */ -static inline void *acpi_os_allocate(acpi_size size) -{ - return kmalloc(size, irqs_disabled()? GFP_ATOMIC : GFP_KERNEL); -} +#define acpi_os_allocate(_size) \ + kmalloc(_size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL) -static inline void *acpi_os_allocate_zeroed(acpi_size size) -{ - return kzalloc(size, irqs_disabled()? GFP_ATOMIC : GFP_KERNEL); -} +#define acpi_os_allocate_zeroed(_size) \ + kzalloc(_size, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL) static inline void acpi_os_free(void *memory) { kfree(memory); } -static inline void *acpi_os_acquire_object(acpi_cache_t * cache) -{ - return kmem_cache_zalloc(cache, - irqs_disabled()? GFP_ATOMIC : GFP_KERNEL); -} +#define acpi_os_acquire_object(_cache) \ + kmem_cache_zalloc(_cache, irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL) static inline acpi_thread_id acpi_os_get_thread_id(void) { diff --git a/include/asm-generic/codetag.lds.h b/include/asm-generic/codetag.lds.h new file mode 100644 index 00000000000000..64f536b803802e --- /dev/null +++ b/include/asm-generic/codetag.lds.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_GENERIC_CODETAG_LDS_H +#define __ASM_GENERIC_CODETAG_LDS_H + +#define SECTION_WITH_BOUNDARIES(_name) \ + . = ALIGN(8); \ + __start_##_name = .; \ + KEEP(*(_name)) \ + __stop_##_name = .; + +#define CODETAG_SECTIONS() \ + SECTION_WITH_BOUNDARIES(alloc_tags) + +#endif /* __ASM_GENERIC_CODETAG_LDS_H */ diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index bac63e874c7bf9..80de699bf6af4b 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -9,6 +9,7 @@ #include <asm/page.h> /* I/O is all done through memory accesses */ #include <linux/string.h> /* for memset() and memcpy() */ +#include <linux/sizes.h> #include <linux/types.h> #include <linux/instruction_pointer.h> @@ -991,7 +992,6 @@ static inline void iowrite64_rep(volatile void __iomem *addr, #ifdef __KERNEL__ -#include <linux/vmalloc.h> #define __io_virt(x) ((void __force *)(x)) /* diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 879e5f8aa5e92a..7c48f5fbf8aa79 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -16,15 +16,16 @@ * * Return: pointer to the allocated memory or %NULL on error */ -static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm) +static inline pte_t *__pte_alloc_one_kernel_noprof(struct mm_struct *mm) { - struct ptdesc *ptdesc = pagetable_alloc(GFP_PGTABLE_KERNEL & + struct ptdesc *ptdesc = pagetable_alloc_noprof(GFP_PGTABLE_KERNEL & ~__GFP_HIGHMEM, 0); if (!ptdesc) return NULL; return ptdesc_address(ptdesc); } +#define __pte_alloc_one_kernel(...) alloc_hooks(__pte_alloc_one_kernel_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** @@ -33,10 +34,11 @@ static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm) * * Return: pointer to the allocated memory or %NULL on error */ -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) +static inline pte_t *pte_alloc_one_kernel_noprof(struct mm_struct *mm) { - return __pte_alloc_one_kernel(mm); + return __pte_alloc_one_kernel_noprof(mm); } +#define pte_alloc_one_kernel(...) alloc_hooks(pte_alloc_one_kernel_noprof(__VA_ARGS__)) #endif /** @@ -61,11 +63,11 @@ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) * * Return: `struct page` referencing the ptdesc or %NULL on error */ -static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) +static inline pgtable_t __pte_alloc_one_noprof(struct mm_struct *mm, gfp_t gfp) { struct ptdesc *ptdesc; - ptdesc = pagetable_alloc(gfp, 0); + ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pte_ctor(ptdesc)) { @@ -75,6 +77,7 @@ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) return ptdesc_page(ptdesc); } +#define __pte_alloc_one(...) alloc_hooks(__pte_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** @@ -85,10 +88,11 @@ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) * * Return: `struct page` referencing the ptdesc or %NULL on error */ -static inline pgtable_t pte_alloc_one(struct mm_struct *mm) +static inline pgtable_t pte_alloc_one_noprof(struct mm_struct *mm) { - return __pte_alloc_one(mm, GFP_PGTABLE_USER); + return __pte_alloc_one_noprof(mm, GFP_PGTABLE_USER); } +#define pte_alloc_one(...) alloc_hooks(pte_alloc_one_noprof(__VA_ARGS__)) #endif /* @@ -124,14 +128,14 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) * * Return: pointer to the allocated memory or %NULL on error */ -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) +static inline pmd_t *pmd_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { struct ptdesc *ptdesc; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; - ptdesc = pagetable_alloc(gfp, 0); + ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pmd_ctor(ptdesc)) { @@ -140,6 +144,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) } return ptdesc_address(ptdesc); } +#define pmd_alloc_one(...) alloc_hooks(pmd_alloc_one_noprof(__VA_ARGS__)) #endif #ifndef __HAVE_ARCH_PMD_FREE @@ -157,7 +162,7 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) #if CONFIG_PGTABLE_LEVELS > 3 -static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr) +static inline pud_t *__pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; struct ptdesc *ptdesc; @@ -166,13 +171,14 @@ static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr) gfp = GFP_PGTABLE_KERNEL; gfp &= ~__GFP_HIGHMEM; - ptdesc = pagetable_alloc(gfp, 0); + ptdesc = pagetable_alloc_noprof(gfp, 0); if (!ptdesc) return NULL; pagetable_pud_ctor(ptdesc); return ptdesc_address(ptdesc); } +#define __pud_alloc_one(...) alloc_hooks(__pud_alloc_one_noprof(__VA_ARGS__)) #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** @@ -184,10 +190,11 @@ static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr) * * Return: pointer to the allocated memory or %NULL on error */ -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) +static inline pud_t *pud_alloc_one_noprof(struct mm_struct *mm, unsigned long addr) { - return __pud_alloc_one(mm, addr); + return __pud_alloc_one_noprof(mm, addr); } +#define pud_alloc_one(...) alloc_hooks(pud_alloc_one_noprof(__VA_ARGS__)) #endif static inline void __pud_free(struct mm_struct *mm, pud_t *pud) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index e8449be6205829..a6dc516a56bf9a 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -50,6 +50,8 @@ * [__nosave_begin, __nosave_end] for the nosave data */ +#include <asm-generic/codetag.lds.h> + #ifndef LOAD_OFFSET #define LOAD_OFFSET 0 #endif @@ -366,6 +368,7 @@ . = ALIGN(8); \ BOUNDED_SECTION_BY(__dyndbg_classes, ___dyndbg_classes) \ BOUNDED_SECTION_BY(__dyndbg, ___dyndbg) \ + CODETAG_SECTIONS() \ LIKELY_PROFILE() \ BRANCH_PROFILE() \ TRACE_PRINTKS() \ diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 5d61f576cfc860..e5181cc9b7c563 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -578,19 +578,20 @@ static inline void ahash_request_set_tfm(struct ahash_request *req, * * Return: allocated request handle in case of success, or NULL if out of memory */ -static inline struct ahash_request *ahash_request_alloc( +static inline struct ahash_request *ahash_request_alloc_noprof( struct crypto_ahash *tfm, gfp_t gfp) { struct ahash_request *req; - req = kmalloc(sizeof(struct ahash_request) + - crypto_ahash_reqsize(tfm), gfp); + req = kmalloc_noprof(sizeof(struct ahash_request) + + crypto_ahash_reqsize(tfm), gfp); if (likely(req)) ahash_request_set_tfm(req, tfm); return req; } +#define ahash_request_alloc(...) alloc_hooks(ahash_request_alloc_noprof(__VA_ARGS__)) /** * ahash_request_free() - zeroize and free the request data structure diff --git a/include/crypto/internal/acompress.h b/include/crypto/internal/acompress.h index 4ac46bafba9d7c..2a67793f52ad87 100644 --- a/include/crypto/internal/acompress.h +++ b/include/crypto/internal/acompress.h @@ -69,15 +69,16 @@ static inline void acomp_request_complete(struct acomp_req *req, crypto_request_complete(&req->base, err); } -static inline struct acomp_req *__acomp_request_alloc(struct crypto_acomp *tfm) +static inline struct acomp_req *__acomp_request_alloc_noprof(struct crypto_acomp *tfm) { struct acomp_req *req; - req = kzalloc(sizeof(*req) + crypto_acomp_reqsize(tfm), GFP_KERNEL); + req = kzalloc_noprof(sizeof(*req) + crypto_acomp_reqsize(tfm), GFP_KERNEL); if (likely(req)) acomp_request_set_tfm(req, tfm); return req; } +#define __acomp_request_alloc(...) alloc_hooks(__acomp_request_alloc_noprof(__VA_ARGS__)) static inline void __acomp_request_free(struct acomp_req *req) { diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index c8857d7bdb37f1..6c5330e316b0e2 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -861,19 +861,20 @@ static inline struct skcipher_request *skcipher_request_cast( * * Return: allocated request handle in case of success, or NULL if out of memory */ -static inline struct skcipher_request *skcipher_request_alloc( +static inline struct skcipher_request *skcipher_request_alloc_noprof( struct crypto_skcipher *tfm, gfp_t gfp) { struct skcipher_request *req; - req = kmalloc(sizeof(struct skcipher_request) + - crypto_skcipher_reqsize(tfm), gfp); + req = kmalloc_noprof(sizeof(struct skcipher_request) + + crypto_skcipher_reqsize(tfm), gfp); if (likely(req)) skcipher_request_set_tfm(req, tfm); return req; } +#define skcipher_request_alloc(...) alloc_hooks(skcipher_request_alloc_noprof(__VA_ARGS__)) /** * skcipher_request_free() - zeroize and free request data structure diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h new file mode 100644 index 00000000000000..afc9e259a2d354 --- /dev/null +++ b/include/linux/alloc_tag.h @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * allocation tagging + */ +#ifndef _LINUX_ALLOC_TAG_H +#define _LINUX_ALLOC_TAG_H + +#include <linux/bug.h> +#include <linux/codetag.h> +#include <linux/container_of.h> +#include <linux/preempt.h> +#include <asm/percpu.h> +#include <linux/cpumask.h> +#include <linux/static_key.h> +#include <linux/irqflags.h> + +struct alloc_tag_counters { + u64 bytes; + u64 calls; +}; + +/* + * An instance of this structure is created in a special ELF section at every + * allocation callsite. At runtime, the special section is treated as + * an array of these. Embedded codetag utilizes codetag framework. + */ +struct alloc_tag { + struct codetag ct; + struct alloc_tag_counters __percpu *counters; +} __aligned(8); + +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + +#define CODETAG_EMPTY ((void *)1) + +static inline bool is_codetag_empty(union codetag_ref *ref) +{ + return ref->ct == CODETAG_EMPTY; +} + +static inline void set_codetag_empty(union codetag_ref *ref) +{ + if (ref) + ref->ct = CODETAG_EMPTY; +} + +#else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + +static inline bool is_codetag_empty(union codetag_ref *ref) { return false; } +static inline void set_codetag_empty(union codetag_ref *ref) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +struct codetag_bytes { + struct codetag *ct; + s64 bytes; +}; + +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep); + +static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct) +{ + return container_of(ct, struct alloc_tag, ct); +} + +#ifdef ARCH_NEEDS_WEAK_PER_CPU +/* + * When percpu variables are required to be defined as weak, static percpu + * variables can't be used inside a function (see comments for DECLARE_PER_CPU_SECTION). + * Instead we will accound all module allocations to a single counter. + */ +DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section("alloc_tags") = { \ + .ct = CODE_TAG_INIT, \ + .counters = &_shared_alloc_tag }; + +#else /* ARCH_NEEDS_WEAK_PER_CPU */ + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr); \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section("alloc_tags") = { \ + .ct = CODE_TAG_INIT, \ + .counters = &_alloc_tag_cntr }; + +#endif /* ARCH_NEEDS_WEAK_PER_CPU */ + +DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + mem_alloc_profiling_key); + +static inline bool mem_alloc_profiling_enabled(void) +{ + return static_branch_maybe(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + &mem_alloc_profiling_key); +} + +static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) +{ + struct alloc_tag_counters v = { 0, 0 }; + struct alloc_tag_counters *counter; + int cpu; + + for_each_possible_cpu(cpu) { + counter = per_cpu_ptr(tag->counters, cpu); + v.bytes += counter->bytes; + v.calls += counter->calls; + } + + return v; +} + +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG +static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) +{ + WARN_ONCE(ref && ref->ct, + "alloc_tag was not cleared (got tag for %s:%u)\n", + ref->ct->filename, ref->ct->lineno); + + WARN_ONCE(!tag, "current->alloc_tag not set"); +} + +static inline void alloc_tag_sub_check(union codetag_ref *ref) +{ + WARN_ONCE(ref && !ref->ct, "alloc_tag was not set\n"); +} +#else +static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) {} +static inline void alloc_tag_sub_check(union codetag_ref *ref) {} +#endif + +/* Caller should verify both ref and tag to be valid */ +static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + ref->ct = &tag->ct; + /* + * We need in increment the call counter every time we have a new + * allocation or when we split a large allocation into smaller ones. + * Each new reference for every sub-allocation needs to increment call + * counter because when we free each part the counter will be decremented. + */ + this_cpu_inc(tag->counters->calls); +} + +static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + + __alloc_tag_ref_set(ref, tag); +} + +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) +{ + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + + __alloc_tag_ref_set(ref, tag); + this_cpu_add(tag->counters->bytes, bytes); +} + +static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) +{ + struct alloc_tag *tag; + + alloc_tag_sub_check(ref); + if (!ref || !ref->ct) + return; + + if (is_codetag_empty(ref)) { + ref->ct = NULL; + return; + } + + tag = ct_to_alloc_tag(ref->ct); + + this_cpu_sub(tag->counters->bytes, bytes); + this_cpu_dec(tag->counters->calls); + + ref->ct = NULL; +} + +#define alloc_tag_record(p) ((p) = current->alloc_tag) + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +#define DEFINE_ALLOC_TAG(_alloc_tag) +static inline bool mem_alloc_profiling_enabled(void) { return false; } +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, + size_t bytes) {} +static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} +#define alloc_tag_record(p) do {} while (0) + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#define alloc_hooks_tag(_tag, _do_alloc) \ +({ \ + struct alloc_tag * __maybe_unused _old = alloc_tag_save(_tag); \ + typeof(_do_alloc) _res = _do_alloc; \ + alloc_tag_restore(_tag, _old); \ + _res; \ +}) + +#define alloc_hooks(_do_alloc) \ +({ \ + DEFINE_ALLOC_TAG(_alloc_tag); \ + alloc_hooks_tag(&_alloc_tag, _do_alloc); \ +}) + +#endif /* _LINUX_ALLOC_TAG_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2ba557e067fe69..ffeb71e7215457 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -254,16 +254,12 @@ static inline unsigned long __ffs64(u64 word) */ static inline unsigned long fns(unsigned long word, unsigned int n) { - unsigned int bit; + unsigned int i; - while (word) { - bit = __ffs(word); - if (n-- == 0) - return bit; - __clear_bit(bit, &word); - } + for (i = 0; word && i < n; i++) + word &= word - 1; - return BITS_PER_LONG; + return word ? __ffs(word) : BITS_PER_LONG; } /** diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 890e152d553ea3..a86da1f38b3c34 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2244,31 +2244,14 @@ void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else -static inline void * -bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, - int node) -{ - return kmalloc_node(size, flags, node); -} - -static inline void * -bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) -{ - return kzalloc(size, flags); -} - -static inline void * -bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) -{ - return kvcalloc(n, size, flags); -} - -static inline void __percpu * -bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, - gfp_t flags) -{ - return __alloc_percpu_gfp(size, align, flags); -} +#define bpf_map_kmalloc_node(_map, _size, _flags, _node) \ + kmalloc_node(_size, _flags, _node) +#define bpf_map_kzalloc(_map, _size, _flags) \ + kzalloc(_size, _flags) +#define bpf_map_kvcalloc(_map, _n, _size, _flags) \ + kvcalloc(_n, _size, _flags) +#define bpf_map_alloc_percpu(_map, _size, _align, _flags) \ + __alloc_percpu_gfp(_size, _align, _flags) #endif static inline int diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 79b2f78eec1a06..1af241525a17cf 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -65,9 +65,9 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); } -static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) +static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len) { - void *p = kvmalloc(len, GFP_USER | __GFP_NOWARN); + void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -77,6 +77,7 @@ static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) } return p; } +#define kvmemdup_bpfptr(...) alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__)) static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) { diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index d78454a4dd1f0f..a1c0bdd0cca66b 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -303,12 +303,38 @@ static inline void put_bh(struct buffer_head *bh) atomic_dec(&bh->b_count); } +/** + * brelse - Release a buffer. + * @bh: The buffer to release. + * + * Decrement a buffer_head's reference count. If @bh is NULL, this + * function is a no-op. + * + * If all buffers on a folio have zero reference count, are clean + * and unlocked, and if the folio is unlocked and not under writeback + * then try_to_free_buffers() may strip the buffers from the folio in + * preparation for freeing it (sometimes, rarely, buffers are removed + * from a folio but it ends up not being freed, and buffers may later + * be reattached). + * + * Context: Any context. + */ static inline void brelse(struct buffer_head *bh) { if (bh) __brelse(bh); } +/** + * bforget - Discard any dirty data in a buffer. + * @bh: The buffer to forget. + * + * Call this function instead of brelse() if the data written to a buffer + * no longer needs to be written back. It will clear the buffer's dirty + * flag so writeback of this buffer will be skipped. + * + * Context: Any context. + */ static inline void bforget(struct buffer_head *bh) { if (bh) @@ -437,17 +463,21 @@ static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[], } /** - * __bread() - reads a specified block and returns the bh - * @bdev: the block_device to read from - * @block: number of block - * @size: size (in bytes) to read + * __bread() - Read a block. + * @bdev: The block device to read from. + * @block: Block number in units of block size. + * @size: The block size of this device in bytes. * - * Reads a specified block, and returns buffer head that contains it. - * The page cache is allocated from movable area so that it can be migrated. - * It returns NULL if the block was unreadable. + * Read a specified block, and return the buffer head that refers + * to it. The memory is allocated from the movable area so that it can + * be migrated. The returned buffer head has its refcount increased. + * The caller should call brelse() when it has finished with the buffer. + * + * Context: May sleep waiting for I/O. + * Return: NULL if the block was unreadable. */ -static inline struct buffer_head * -__bread(struct block_device *bdev, sector_t block, unsigned size) +static inline struct buffer_head *__bread(struct block_device *bdev, + sector_t block, unsigned size) { return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } diff --git a/include/linux/codetag.h b/include/linux/codetag.h new file mode 100644 index 00000000000000..c2a579ccd45588 --- /dev/null +++ b/include/linux/codetag.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * code tagging framework + */ +#ifndef _LINUX_CODETAG_H +#define _LINUX_CODETAG_H + +#include <linux/types.h> + +struct codetag_iterator; +struct codetag_type; +struct codetag_module; +struct seq_buf; +struct module; + +/* + * An instance of this structure is created in a special ELF section at every + * code location being tagged. At runtime, the special section is treated as + * an array of these. + */ +struct codetag { + unsigned int flags; /* used in later patches */ + unsigned int lineno; + const char *modname; + const char *function; + const char *filename; +} __aligned(8); + +union codetag_ref { + struct codetag *ct; +}; + +struct codetag_type_desc { + const char *section; + size_t tag_size; + void (*module_load)(struct codetag_type *cttype, + struct codetag_module *cmod); + bool (*module_unload)(struct codetag_type *cttype, + struct codetag_module *cmod); +}; + +struct codetag_iterator { + struct codetag_type *cttype; + struct codetag_module *cmod; + unsigned long mod_id; + struct codetag *ct; +}; + +#ifdef MODULE +#define CT_MODULE_NAME KBUILD_MODNAME +#else +#define CT_MODULE_NAME NULL +#endif + +#define CODE_TAG_INIT { \ + .modname = CT_MODULE_NAME, \ + .function = __func__, \ + .filename = __FILE__, \ + .lineno = __LINE__, \ + .flags = 0, \ +} + +void codetag_lock_module_list(struct codetag_type *cttype, bool lock); +bool codetag_trylock_module_list(struct codetag_type *cttype); +struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype); +struct codetag *codetag_next_ct(struct codetag_iterator *iter); + +void codetag_to_text(struct seq_buf *out, struct codetag *ct); + +struct codetag_type * +codetag_register_type(const struct codetag_type_desc *desc); + +#if defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) +void codetag_load_module(struct module *mod); +bool codetag_unload_module(struct module *mod); +#else +static inline void codetag_load_module(struct module *mod) {} +static inline bool codetag_unload_module(struct module *mod) { return true; } +#endif + +#endif /* _LINUX_CODETAG_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 2abaa3a825a9ec..8f8236317d5b15 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -278,6 +278,17 @@ struct ftrace_likely_data { # define __no_kcsan #endif +#ifdef __SANITIZE_MEMORY__ +/* + * Similarly to KASAN and KCSAN, KMSAN loses function attributes of inlined + * functions, therefore disabling KMSAN checks also requires disabling inlining. + * + * __no_sanitize_or_inline effectively prevents KMSAN from reporting errors + * within the function and marks all its outputs as initialized. + */ +# define __no_sanitize_or_inline __no_kmsan_checks notrace __maybe_unused +#endif + #ifndef __no_sanitize_or_inline #define __no_sanitize_or_inline __always_inline #endif diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 272e4e79e15c48..861c3bfc5f1700 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -221,7 +221,18 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +#ifdef CONFIG_CPU_MITIGATIONS extern bool cpu_mitigations_off(void); extern bool cpu_mitigations_auto_nosmt(void); +#else +static inline bool cpu_mitigations_off(void) +{ + return true; +} +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return false; +} +#endif #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1c29947db84899..04536a29f10fc4 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -1017,11 +1017,6 @@ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); -static inline void reset_cpu_possible_mask(void) -{ - bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS); -} - static inline void set_cpu_possible(unsigned int cpu, bool possible) { diff --git a/include/linux/damon.h b/include/linux/damon.h index 886d07294f4e7c..f7da65e1ac041e 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -297,6 +297,7 @@ struct damos_stat { * enum damos_filter_type - Type of memory for &struct damos_filter * @DAMOS_FILTER_TYPE_ANON: Anonymous pages. * @DAMOS_FILTER_TYPE_MEMCG: Specific memcg's pages. + * @DAMOS_FILTER_TYPE_YOUNG: Recently accessed pages. * @DAMOS_FILTER_TYPE_ADDR: Address range. * @DAMOS_FILTER_TYPE_TARGET: Data Access Monitoring target. * @NR_DAMOS_FILTER_TYPES: Number of filter types. @@ -315,6 +316,7 @@ struct damos_stat { enum damos_filter_type { DAMOS_FILTER_TYPE_ANON, DAMOS_FILTER_TYPE_MEMCG, + DAMOS_FILTER_TYPE_YOUNG, DAMOS_FILTER_TYPE_ADDR, DAMOS_FILTER_TYPE_TARGET, NR_DAMOS_FILTER_TYPES, diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 4bdf0b96da2831..ad9e2506c2f401 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -86,10 +86,8 @@ dma_fence_chain_contained(struct dma_fence *fence) * * Returns a new struct dma_fence_chain object or NULL on failure. */ -static inline struct dma_fence_chain *dma_fence_chain_alloc(void) -{ - return kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); -}; +#define dma_fence_chain_alloc() \ + ((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL)) /** * dma_fence_chain_free diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 4abc60f0420928..9ee319851b5f63 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -29,7 +29,7 @@ struct dma_map_ops { unsigned long attrs); void (*free)(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs); - struct page *(*alloc_pages)(struct device *dev, size_t size, + struct page *(*alloc_pages_op)(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 224645f17c333b..297231854ada51 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/filter.h b/include/linux/filter.h index c99bc3df2d28e3..219ee7a7687443 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -963,6 +963,7 @@ bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 5c28298a98bec8..366243ee96096d 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -10,6 +10,7 @@ #define __QCOM_QSEECOM_H #include <linux/auxiliary_bus.h> +#include <linux/dma-mapping.h> #include <linux/types.h> #include <linux/firmware/qcom/qcom_scm.h> @@ -25,11 +26,56 @@ struct qseecom_client { }; /** + * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. + * @client: The QSEECOM client device. + * + * Returns the SCM device under which the provided QSEECOM client device + * operates. This function is intended to be used for DMA allocations. + */ +static inline struct device *qseecom_scm_dev(struct qseecom_client *client) +{ + return client->aux_dev.dev.parent->parent; +} + +/** + * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. + * @client: The QSEECOM client to allocate the memory for. + * @size: The number of bytes to allocate. + * @dma_handle: Pointer to where the DMA address should be stored. + * @gfp: Allocation flags. + * + * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for + * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. + */ +static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); +} + +/** + * dma_free_coherent() - Free QSEECOM DMA memory. + * @client: The QSEECOM client for which the memory has been allocated. + * @size: The number of bytes allocated. + * @cpu_addr: Virtual memory address to free. + * @dma_handle: DMA memory address to free. + * + * Wrapper function for dma_free_coherent(), freeing memory previously + * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for + * details. + */ +static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, + void *cpu_addr, dma_addr_t dma_handle) +{ + return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); +} + +/** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. - * @req: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given client and read @@ -43,8 +89,9 @@ struct qseecom_client { * * Return: Zero on success, nonzero on failure. */ -static inline int qcom_qseecom_app_send(struct qseecom_client *client, void *req, size_t req_size, - void *rsp, size_t rsp_size) +static inline int qcom_qseecom_app_send(struct qseecom_client *client, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size); } diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index ccaf288460546a..aaa19f93ac4306 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -118,8 +118,8 @@ bool qcom_scm_lmh_dcvsh_available(void); #ifdef CONFIG_QCOM_QSEECOM int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id); -int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, - size_t rsp_size); +int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size); #else /* CONFIG_QCOM_QSEECOM */ @@ -128,9 +128,9 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) return -EINVAL; } -static inline int qcom_scm_qseecom_app_send(u32 app_id, void *req, - size_t req_size, void *rsp, - size_t rsp_size) +static inline int qcom_scm_qseecom_app_send(u32 app_id, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return -EINVAL; } diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 6aeebe0a677704..b24d62bad0b329 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -725,9 +725,9 @@ __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) return __real_memchr_inv(p, c, size); } -extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup) +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup_noprof) __realloc_size(2); -__FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp) +__FORTIFY_INLINE void *kmemdup_noprof(const void * const POS0 p, size_t size, gfp_t gfp) { const size_t p_size = __struct_size(p); @@ -737,6 +737,7 @@ __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, NULL); return __real_kmemdup(p, size, gfp); } +#define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) /** * strcpy - Copy a string into another string buffer diff --git a/include/linux/fpu.h b/include/linux/fpu.h new file mode 100644 index 00000000000000..2fb63e22913bcf --- /dev/null +++ b/include/linux/fpu.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_FPU_H +#define _LINUX_FPU_H + +#ifdef _LINUX_FPU_COMPILATION_UNIT +#error FP code must be compiled separately. See Documentation/core-api/floating-point.rst. +#endif + +#include <asm/fpu.h> + +#endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 8dfd53b52744a4..4f2e2e5b6ab114 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3085,11 +3085,7 @@ int setattr_should_drop_sgid(struct mnt_idmap *idmap, * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ -static inline void * -alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp) -{ - return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp); -} +#define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c775ea3c601558..450c2cbcf04b8d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -6,6 +6,8 @@ #include <linux/mmzone.h> #include <linux/topology.h> +#include <linux/alloc_tag.h> +#include <linux/sched.h> struct vm_area_struct; struct mempolicy; @@ -175,42 +177,46 @@ static inline void arch_free_page(struct page *page, int order) { } static inline void arch_alloc_page(struct page *page, int order) { } #endif -struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, +struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); -struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, +#define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) + +struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); +#define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) -unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, +unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, struct list_head *page_list, struct page **page_array); +#define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) -unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, +unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); +#define alloc_pages_bulk_array_mempolicy(...) \ + alloc_hooks(alloc_pages_bulk_array_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ -static inline unsigned long -alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list) -{ - return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list, NULL); -} +#define alloc_pages_bulk_list(_gfp, _nr_pages, _list) \ + __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _list, NULL) -static inline unsigned long -alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_array) -{ - return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array); -} +#define alloc_pages_bulk_array(_gfp, _nr_pages, _page_array) \ + __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, NULL, _page_array) static inline unsigned long -alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) +alloc_pages_bulk_array_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, + struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array); + return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, NULL, page_array); } +#define alloc_pages_bulk_array_node(...) \ + alloc_hooks(alloc_pages_bulk_array_node_noprof(__VA_ARGS__)) + static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); @@ -230,82 +236,104 @@ static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) * online. For more general interface, see alloc_pages_node(). */ static inline struct page * -__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) +__alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask); - return __alloc_pages(gfp_mask, order, nid, NULL); + return __alloc_pages_noprof(gfp_mask, order, nid, NULL); } +#define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) + static inline -struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid) +struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp); - return __folio_alloc(gfp, order, nid, NULL); + return __folio_alloc_noprof(gfp, order, nid, NULL); } +#define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) + /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ -static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, - unsigned int order) +static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, + unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return __alloc_pages_node(nid, gfp_mask, order); + return __alloc_pages_node_noprof(nid, gfp_mask, order); } +#define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) + #ifdef CONFIG_NUMA -struct page *alloc_pages(gfp_t gfp, unsigned int order); -struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, +struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); +struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); -struct folio *folio_alloc(gfp_t gfp, unsigned int order); -struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, +struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); +struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); #else -static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) +static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { - return alloc_pages_node(numa_node_id(), gfp_mask, order); + return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } -static inline struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, +static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { - return alloc_pages(gfp, order); + return alloc_pages_noprof(gfp, order); } -static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) +static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ - folio_alloc(gfp, order) +#define vma_alloc_folio_noprof(gfp, order, vma, addr, hugepage) \ + folio_alloc_noprof(gfp, order) #endif + +#define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) +#define alloc_pages_mpol(...) alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__)) +#define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) +#define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) + #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -static inline struct page *alloc_page_vma(gfp_t gfp, + +static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { - struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false); + struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr, false); return &folio->page; } +#define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) + +extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); +#define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) -extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); -extern unsigned long get_zeroed_page(gfp_t gfp_mask); +extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); +#define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) + +void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); +#define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) -void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); void free_pages_exact(void *virt, size_t size); -__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); -#define __get_free_page(gfp_mask) \ - __get_free_pages((gfp_mask), 0) +__meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); +#define alloc_pages_exact_nid(...) \ + alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) + +#define __get_free_page(gfp_mask) \ + __get_free_pages((gfp_mask), 0) -#define __get_dma_pages(gfp_mask, order) \ - __get_free_pages((gfp_mask) | GFP_DMA, (order)) +#define __get_dma_pages(gfp_mask, order) \ + __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); @@ -374,10 +402,14 @@ extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ -extern int alloc_contig_range(unsigned long start, unsigned long end, +extern int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); -extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, - int nid, nodemask_t *nodemask); +#define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) + +extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask); +#define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) + #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 13becafe41df00..313be4ad79fd97 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -55,6 +55,9 @@ enum { #ifdef CONFIG_LOCKDEP ___GFP_NOLOCKDEP_BIT, #endif +#ifdef CONFIG_SLAB_OBJ_EXT + ___GFP_NO_OBJ_EXT_BIT, +#endif ___GFP_LAST_BIT }; @@ -95,6 +98,11 @@ enum { #else #define ___GFP_NOLOCKDEP 0 #endif +#ifdef CONFIG_SLAB_OBJ_EXT +#define ___GFP_NO_OBJ_EXT BIT(___GFP_NO_OBJ_EXT_BIT) +#else +#define ___GFP_NO_OBJ_EXT 0 +#endif /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) @@ -135,12 +143,15 @@ enum { * node with no fallbacks or placement policy enforcements. * * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. + * + * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) #define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) +#define __GFP_NO_OBJ_EXT ((__force gfp_t)___GFP_NO_OBJ_EXT) /** * DOC: Watermark modifiers diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index 7118ac28d46879..ca70eeb6393e7f 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -149,10 +149,8 @@ static inline int hid_bpf_connect_device(struct hid_device *hdev) { return 0; } static inline void hid_bpf_disconnect_device(struct hid_device *hdev) {} static inline void hid_bpf_destroy_device(struct hid_device *hid) {} static inline void hid_bpf_device_init(struct hid_device *hid) {} -static inline u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size) -{ - return kmemdup(rdesc, *size, GFP_KERNEL); -} +#define call_hid_bpf_rdesc_fixup(_hdev, _rdesc, _size) \ + ((u8 *)kmemdup(_rdesc, *(_size), GFP_KERNEL)) #endif /* CONFIG_HID_BPF */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index de0c8910507690..c8d3ec116e291b 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -64,9 +64,6 @@ ssize_t single_hugepage_flag_show(struct kobject *kobj, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; -#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) -#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) - /* * Mask of all large folio orders supported for anonymous THP; all orders up to * and including PMD_ORDER, except order-0 (which is not "huge") and order-1 @@ -84,17 +81,32 @@ extern struct kobj_attribute shmem_enabled_attr; */ #define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE) -#define thp_vma_allowable_order(vma, vm_flags, smaps, in_pf, enforce_sysfs, order) \ - (!!thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, enforce_sysfs, BIT(order))) +#define TVA_SMAPS (1 << 0) /* Will be used for procfs */ +#define TVA_IN_PF (1 << 1) /* Page fault handler */ +#define TVA_ENFORCE_SYSFS (1 << 2) /* Obey sysfs configuration */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \ + (!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order))) + +#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES #define HPAGE_PMD_SHIFT PMD_SHIFT -#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) +#define HPAGE_PUD_SHIFT PUD_SHIFT +#else +#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) +#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) +#endif + +#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) +#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) +#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) -#define HPAGE_PUD_SHIFT PUD_SHIFT -#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) +#define HPAGE_PUD_ORDER (HPAGE_PUD_SHIFT-PAGE_SHIFT) +#define HPAGE_PUD_NR (1<<HPAGE_PUD_ORDER) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) +#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE extern unsigned long transparent_hugepage_flags; extern unsigned long huge_anon_orders_always; @@ -210,17 +222,15 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma) } unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders); /** * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma * @vma: the vm area to check * @vm_flags: use these vm_flags instead of vma->vm_flags - * @smaps: whether answer will be used for smaps file - * @in_pf: whether answer will be used by page fault handler - * @enforce_sysfs: whether sysfs config should be taken into account + * @tva_flags: Which TVA flags to honour * @orders: bitfield of all orders to consider * * Calculates the intersection of the requested hugepage orders and the allowed @@ -233,12 +243,12 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, */ static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders) { /* Optimization to check if required orders are enabled early. */ - if (enforce_sysfs && vma_is_anonymous(vma)) { + if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) { unsigned long mask = READ_ONCE(huge_anon_orders_always); if (vm_flags & VM_HUGEPAGE) @@ -252,8 +262,30 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, return 0; } - return __thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, - enforce_sysfs, orders); + return __thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders); +} + +enum mthp_stat_item { + MTHP_STAT_ANON_FAULT_ALLOC, + MTHP_STAT_ANON_FAULT_FALLBACK, + MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, + MTHP_STAT_ANON_SWPOUT, + MTHP_STAT_ANON_SWPOUT_FALLBACK, + __MTHP_STAT_COUNT +}; + +struct mthp_stat { + unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; +}; + +DECLARE_PER_CPU(struct mthp_stat, mthp_stats); + +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ + if (order <= 0 || order > PMD_ORDER) + return; + + this_cpu_inc(mthp_stats.stats[order][item]); } #define transparent_hugepage_use_zero_page() \ @@ -262,8 +294,10 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); +unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags); -void folio_prep_large_rmappable(struct folio *folio); bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); @@ -344,17 +378,15 @@ static inline bool folio_test_pmd_mappable(struct folio *folio) struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); -struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags, struct dev_pagemap **pgmap); vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); -extern struct page *huge_zero_page; +extern struct folio *huge_zero_folio; extern unsigned long huge_zero_pfn; -static inline bool is_huge_zero_page(struct page *page) +static inline bool is_huge_zero_folio(const struct folio *folio) { - return READ_ONCE(huge_zero_page) == page; + return READ_ONCE(huge_zero_folio) == folio; } static inline bool is_huge_zero_pmd(pmd_t pmd) @@ -367,8 +399,8 @@ static inline bool is_huge_zero_pud(pud_t pud) return false; } -struct page *mm_get_huge_zero_page(struct mm_struct *mm); -void mm_put_huge_zero_page(struct mm_struct *mm); +struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); +void mm_put_huge_zero_folio(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) @@ -378,13 +410,6 @@ static inline bool thp_migration_supported(void) } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ -#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) -#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) -#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; }) - -#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) -#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) -#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) static inline bool folio_test_pmd_mappable(struct folio *folio) { @@ -404,19 +429,25 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, } static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders) { return 0; } -static inline void folio_prep_large_rmappable(struct folio *folio) {} - #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL +static inline unsigned long +thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) +{ + return 0; +} + static inline bool can_split_folio(struct folio *folio, int *pextra_pins) { @@ -483,7 +514,7 @@ static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) return 0; } -static inline bool is_huge_zero_page(struct page *page) +static inline bool is_huge_zero_folio(const struct folio *folio) { return false; } @@ -498,7 +529,7 @@ static inline bool is_huge_zero_pud(pud_t pud) return false; } -static inline void mm_put_huge_zero_page(struct mm_struct *mm) +static inline void mm_put_huge_zero_folio(struct mm_struct *mm) { return; } @@ -509,12 +540,6 @@ static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) -{ - return NULL; -} - static inline bool thp_migration_supported(void) { return false; @@ -535,16 +560,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order) #define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0) #define split_folio(f) split_folio_to_order(f, 0) -/* - * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to - * limitations in the implementation like arm64 MTE can override this to - * false - */ -#ifndef arch_thp_swp_supported -static inline bool arch_thp_swp_supported(void) -{ - return true; -} -#endif - #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 77b30a8c6076b6..68244bb3637a87 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -174,8 +174,11 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); +bool hugetlbfs_pagecache_present(struct hstate *h, + struct vm_area_struct *vma, + unsigned long address); -struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage); +struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; @@ -272,13 +275,9 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); - -int pmd_huge(pmd_t pmd); -int pud_huge(pud_t pud); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); - bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); @@ -298,8 +297,8 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } -static inline struct address_space *hugetlb_page_mapping_lock_write( - struct page *hpage) +static inline struct address_space *hugetlb_folio_mapping_lock_write( + struct folio *folio) { return NULL; } @@ -329,13 +328,6 @@ static inline void hugetlb_zap_end( { } -static inline struct page *hugetlb_follow_page_mask( - struct vm_area_struct *vma, unsigned long address, unsigned int flags, - unsigned int *page_mask) -{ - BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/ -} - static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, @@ -399,16 +391,6 @@ static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } -static inline int pmd_huge(pmd_t pmd) -{ - return 0; -} - -static inline int pud_huge(pud_t pud) -{ - return 0; -} - static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { @@ -493,16 +475,6 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } #endif /* !CONFIG_HUGETLB_PAGE */ -/* - * hugepages at page global directory. If arch support - * hugepages at pgd level, they need to define this. - */ -#ifndef pgd_huge -#define pgd_huge(x) 0 -#endif -#ifndef p4d_huge -#define p4d_huge(x) 0 -#endif #ifndef pgd_write static inline int pgd_write(pgd_t pgd) @@ -747,7 +719,8 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask, gfp_t gfp_mask); + nodemask_t *nmask, gfp_t gfp_mask, + bool allow_alloc_fallback); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, @@ -859,9 +832,9 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, #define is_hugepage_only_range is_hugepage_only_range #endif -#ifndef arch_clear_hugepage_flags -static inline void arch_clear_hugepage_flags(struct page *page) { } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#ifndef arch_clear_hugetlb_flags +static inline void arch_clear_hugetlb_flags(struct folio *folio) { } +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte @@ -888,8 +861,8 @@ static inline int hstate_index(struct hstate *h) return h - hstates; } -extern int dissolve_free_huge_page(struct page *page); -extern int dissolve_free_huge_pages(unsigned long start_pfn, +int dissolve_free_hugetlb_folio(struct folio *folio); +int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE @@ -970,6 +943,30 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) return modified_mask; } +static inline bool htlb_allow_alloc_fallback(int reason) +{ + bool allowed_fallback = false; + + /* + * Note: the memory offline, memory failure and migration syscalls will + * be allowed to fallback to other nodes due to lack of a better chioce, + * that might break the per-node hugetlb pool. While other cases will + * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. + */ + switch (reason) { + case MR_MEMORY_HOTPLUG: + case MR_MEMORY_FAILURE: + case MR_SYSCALL: + case MR_MEMPOLICY_MBIND: + allowed_fallback = true; + break; + default: + break; + } + + return allowed_fallback; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -1065,7 +1062,8 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask, gfp_t gfp_mask) + nodemask_t *nmask, gfp_t gfp_mask, + bool allow_alloc_fallback) { return NULL; } @@ -1150,12 +1148,12 @@ static inline int hstate_index(struct hstate *h) return 0; } -static inline int dissolve_free_huge_page(struct page *page) +static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } -static inline int dissolve_free_huge_pages(unsigned long start_pfn, +static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; @@ -1181,6 +1179,11 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) return 0; } +static inline bool htlb_allow_alloc_fallback(int reason) +{ + return false; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -1221,6 +1224,12 @@ static inline void hugetlb_register_node(struct node *node) static inline void hugetlb_unregister_node(struct node *node) { } + +static inline bool hugetlbfs_pagecache_present( + struct hstate *h, struct vm_area_struct *vma, unsigned long address) +{ + return false; +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, diff --git a/include/linux/iio/common/inv_sensors_timestamp.h b/include/linux/iio/common/inv_sensors_timestamp.h index a47d304d1ba7c4..8d506f1e9df292 100644 --- a/include/linux/iio/common/inv_sensors_timestamp.h +++ b/include/linux/iio/common/inv_sensors_timestamp.h @@ -71,8 +71,7 @@ int inv_sensors_timestamp_update_odr(struct inv_sensors_timestamp *ts, uint32_t period, bool fifo); void inv_sensors_timestamp_interrupt(struct inv_sensors_timestamp *ts, - uint32_t fifo_period, size_t fifo_nb, - size_t sensor_nb, int64_t timestamp); + size_t sample_nb, int64_t timestamp); static inline int64_t inv_sensors_timestamp_pop(struct inv_sensors_timestamp *ts) { diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 1b608e00290aa1..711a1f0d1a735d 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -148,6 +148,41 @@ instrument_copy_from_user_after(const void *to, const void __user *from, } /** + * instrument_memcpy_before - add instrumentation before non-instrumented memcpy + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * + * Instrument memory accesses that happen in custom memcpy implementations. The + * instrumentation should be inserted before the memcpy call. + */ +static __always_inline void instrument_memcpy_before(void *to, const void *from, + unsigned long n) +{ + kasan_check_write(to, n); + kasan_check_read(from, n); + kcsan_check_write(to, n); + kcsan_check_read(from, n); +} + +/** + * instrument_memcpy_after - add instrumentation after non-instrumented memcpy + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * @left: number of bytes not copied (if known) + * + * Instrument memory accesses that happen in custom memcpy implementations. The + * instrumentation should be inserted after the memcpy call. + */ +static __always_inline void instrument_memcpy_after(void *to, const void *from, + unsigned long n, + unsigned long left) +{ + kmsan_memmove(to, from, n - left); +} + +/** * instrument_get_user() - add instrumentation to get_user()-like macros * @to: destination variable, may not be address-taken * diff --git a/include/linux/io.h b/include/linux/io.h index 235ba7d80a8f0d..e8ee40ee1843b2 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -6,6 +6,7 @@ #ifndef _LINUX_IO_H #define _LINUX_IO_H +#include <linux/sizes.h> #include <linux/types.h> #include <linux/init.h> #include <linux/bug.h> diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 971f3e826e1528..9512fe33266841 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1586,10 +1586,8 @@ void jbd2_journal_put_journal_head(struct journal_head *jh); */ extern struct kmem_cache *jbd2_handle_cache; -static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) -{ - return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); -} +#define jbd2_alloc_handle(_gfp_flags) \ + ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { @@ -1602,10 +1600,8 @@ static inline void jbd2_free_handle(handle_t *handle) */ extern struct kmem_cache *jbd2_inode_cache; -static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags) -{ - return kmem_cache_alloc(jbd2_inode_cache, gfp_flags); -} +#define jbd2_alloc_inode(_gfp_flags) \ + ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 060835bb82d52f..f31bd304df4518 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -461,10 +461,8 @@ static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { extern bool kexec_file_dbg_print; -#define kexec_dprintk(fmt, ...) \ - printk("%s" fmt, \ - kexec_file_dbg_print ? KERN_INFO : KERN_DEBUG, \ - ##__VA_ARGS__) +#define kexec_dprintk(fmt, arg...) \ + do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0) #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 0b35a41440ff13..6b28d642f3325e 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -36,10 +36,15 @@ * to lock the reader. */ -#include <linux/kernel.h> +#include <linux/array_size.h> #include <linux/spinlock.h> #include <linux/stddef.h> -#include <linux/scatterlist.h> +#include <linux/types.h> + +#include <asm/barrier.h> +#include <asm/errno.h> + +struct scatterlist; struct __kfifo { unsigned int in; diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h index c4cae333deec5f..e1082dc40abc2c 100644 --- a/include/linux/kmsan-checks.h +++ b/include/linux/kmsan-checks.h @@ -61,6 +61,17 @@ void kmsan_check_memory(const void *address, size_t size); void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy, size_t left); +/** + * kmsan_memmove() - Notify KMSAN about a data copy within kernel. + * @to: destination address in the kernel. + * @from: source address in the kernel. + * @size: number of bytes to copy. + * + * Invoked after non-instrumented version (e.g. implemented using assembly + * code) of memmove()/memcpy() is called, in order to copy KMSAN's metadata. + */ +void kmsan_memmove(void *to, const void *from, size_t to_copy); + #else static inline void kmsan_poison_memory(const void *address, size_t size, @@ -78,6 +89,10 @@ static inline void kmsan_copy_to_user(void __user *to, const void *from, { } +static inline void kmsan_memmove(void *to, const void *from, size_t to_copy) +{ +} + #endif #endif /* _LINUX_KMSAN_CHECKS_H */ diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 401348e9f92b4e..52c63a9c5a9cdf 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -45,16 +45,16 @@ static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - int ret; + if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) + return __ksm_enter(mm); - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { - ret = __ksm_enter(mm); - if (ret) - return ret; - } + return 0; +} - if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) - set_bit(MMF_VM_MERGE_ANY, &mm->flags); +static inline int ksm_execve(struct mm_struct *mm) +{ + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + return __ksm_enter(mm); return 0; } @@ -81,15 +81,9 @@ struct folio *ksm_might_need_to_copy(struct folio *folio, void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); - -#ifdef CONFIG_MEMORY_FAILURE -void collect_procs_ksm(struct page *page, struct list_head *to_kill, - int force_early); -#endif - -#ifdef CONFIG_PROC_FS +void collect_procs_ksm(struct folio *folio, struct page *page, + struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); -#endif /* CONFIG_PROC_FS */ #else /* !CONFIG_KSM */ @@ -107,6 +101,11 @@ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) return 0; } +static inline int ksm_execve(struct mm_struct *mm) +{ + return 0; +} + static inline void ksm_exit(struct mm_struct *mm) { } @@ -115,12 +114,10 @@ static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } -#ifdef CONFIG_MEMORY_FAILURE -static inline void collect_procs_ksm(struct page *page, +static inline void collect_procs_ksm(struct folio *folio, struct page *page, struct list_head *to_kill, int force_early) { } -#endif #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 394fd0a887ae75..9aba0d0462ca69 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -349,15 +349,32 @@ struct mem_cgroup { extern struct mem_cgroup *root_mem_cgroup; enum page_memcg_data_flags { - /* page->memcg_data is a pointer to an objcgs vector */ - MEMCG_DATA_OBJCGS = (1UL << 0), + /* page->memcg_data is a pointer to an slabobj_ext vector */ + MEMCG_DATA_OBJEXTS = (1UL << 0), /* page has been accounted as a non-slab kernel page */ MEMCG_DATA_KMEM = (1UL << 1), /* the next bit after the last actual flag */ __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; -#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) +#define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS + +#else /* CONFIG_MEMCG */ + +#define __FIRST_OBJEXT_FLAG (1UL << 0) + +#endif /* CONFIG_MEMCG */ + +enum objext_flags { + /* slabobj_ext vector failed to allocate */ + OBJEXTS_ALLOC_FAIL = __FIRST_OBJEXT_FLAG, + /* the next bit after the last actual flag */ + __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), +}; + +#define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1) + +#ifdef CONFIG_MEMCG static inline bool folio_memcg_kmem(struct folio *folio); @@ -388,10 +405,10 @@ static inline struct mem_cgroup *__folio_memcg(struct folio *folio) unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* @@ -409,10 +426,10 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); - return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* @@ -469,11 +486,11 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; - objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return obj_cgroup_memcg(objcg); } - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* @@ -506,17 +523,17 @@ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) */ unsigned long memcg_data = READ_ONCE(folio->memcg_data); - if (memcg_data & MEMCG_DATA_OBJCGS) + if (memcg_data & MEMCG_DATA_OBJEXTS) return NULL; if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; - objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return obj_cgroup_memcg(objcg); } - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } static inline struct mem_cgroup *page_memcg_check(struct page *page) @@ -552,7 +569,7 @@ retry: static inline bool folio_memcg_kmem(struct folio *folio) { VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); - VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio); return folio->memcg_data & MEMCG_DATA_KMEM; } @@ -818,7 +835,8 @@ static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, static inline void obj_cgroup_put(struct obj_cgroup *objcg) { - percpu_ref_put(&objcg->refcnt); + if (objcg) + percpu_ref_put(&objcg->refcnt); } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) @@ -1059,8 +1077,6 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void mem_cgroup_flush_stats(struct mem_cgroup *memcg); void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg); -void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, - int val); void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, @@ -1073,16 +1089,6 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, local_irq_restore(flags); } -static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_memcg_lruvec_state(lruvec, idx, val); - local_irq_restore(flags); -} - void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); @@ -1576,11 +1582,6 @@ static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { } -static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ -} - static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { @@ -1632,6 +1633,19 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, } #endif /* CONFIG_MEMCG */ +/* + * Extended information for slab objects stored as an array in page->memcg_data + * if MEMCG_DATA_OBJEXTS is set. + */ +struct slabobj_ext { +#ifdef CONFIG_MEMCG_KMEM + struct obj_cgroup *objcg; +#endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + union codetag_ref ref; +#endif +} __aligned(8); + static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) { __mod_lruvec_kmem_state(p, idx, 1); diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 69e78190008271..0d70788558f463 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -48,6 +48,9 @@ int mt_calc_adistance(int node, int *adist); int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source); int mt_perf_to_adistance(struct access_coordinate *perf, int *adist); +struct memory_dev_type *mt_find_alloc_memory_type(int adist, + struct list_head *memory_types); +void mt_put_memory_types(struct list_head *memory_types); #ifdef CONFIG_MIGRATION int next_demotion_node(int node); void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); @@ -136,5 +139,15 @@ static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adis { return -EIO; } + +static inline struct memory_dev_type *mt_find_alloc_memory_type(int adist, + struct list_head *memory_types) +{ + return NULL; +} + +static inline void mt_put_memory_types(struct list_head *memory_types) +{ +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 931b118336f48c..1add16f216124d 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -167,7 +167,8 @@ extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); -int mpol_misplaced(struct folio *, struct vm_area_struct *, unsigned long); +int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, + unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) @@ -282,7 +283,7 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol) #endif static inline int mpol_misplaced(struct folio *folio, - struct vm_area_struct *vma, + struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ diff --git a/include/linux/mempool.h b/include/linux/mempool.h index 16c5cc807ff6b4..7b151441341b4c 100644 --- a/include/linux/mempool.h +++ b/include/linux/mempool.h @@ -5,6 +5,8 @@ #ifndef _LINUX_MEMPOOL_H #define _LINUX_MEMPOOL_H +#include <linux/sched.h> +#include <linux/alloc_tag.h> #include <linux/wait.h> #include <linux/compiler.h> @@ -39,18 +41,32 @@ void mempool_exit(mempool_t *pool); int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int node_id); -int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + +int mempool_init_noprof(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); +#define mempool_init(...) \ + alloc_hooks(mempool_init_noprof(__VA_ARGS__)) extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); -extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, + +extern mempool_t *mempool_create_node_noprof(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int nid); +#define mempool_create_node(...) \ + alloc_hooks(mempool_create_node_noprof(__VA_ARGS__)) + +#define mempool_create(_min_nr, _alloc_fn, _free_fn, _pool_data) \ + mempool_create_node(_min_nr, _alloc_fn, _free_fn, _pool_data, \ + GFP_KERNEL, NUMA_NO_NODE) extern int mempool_resize(mempool_t *pool, int new_min_nr); extern void mempool_destroy(mempool_t *pool); -extern void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) __malloc; + +extern void *mempool_alloc_noprof(mempool_t *pool, gfp_t gfp_mask) __malloc; +#define mempool_alloc(...) \ + alloc_hooks(mempool_alloc_noprof(__VA_ARGS__)) + extern void *mempool_alloc_preallocated(mempool_t *pool) __malloc; extern void mempool_free(void *element, mempool_t *pool); @@ -62,19 +78,10 @@ extern void mempool_free(void *element, mempool_t *pool); void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data); void mempool_free_slab(void *element, void *pool_data); -static inline int -mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc) -{ - return mempool_init(pool, min_nr, mempool_alloc_slab, - mempool_free_slab, (void *) kc); -} - -static inline mempool_t * -mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) -{ - return mempool_create(min_nr, mempool_alloc_slab, mempool_free_slab, - (void *) kc); -} +#define mempool_init_slab_pool(_pool, _min_nr, _kc) \ + mempool_init(_pool, (_min_nr), mempool_alloc_slab, mempool_free_slab, (void *)(_kc)) +#define mempool_create_slab_pool(_min_nr, _kc) \ + mempool_create((_min_nr), mempool_alloc_slab, mempool_free_slab, (void *)(_kc)) /* * a mempool_alloc_t and a mempool_free_t to kmalloc and kfree the @@ -83,17 +90,12 @@ mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kfree(void *element, void *pool_data); -static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size) -{ - return mempool_init(pool, min_nr, mempool_kmalloc, - mempool_kfree, (void *) size); -} - -static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size) -{ - return mempool_create(min_nr, mempool_kmalloc, mempool_kfree, - (void *) size); -} +#define mempool_init_kmalloc_pool(_pool, _min_nr, _size) \ + mempool_init(_pool, (_min_nr), mempool_kmalloc, mempool_kfree, \ + (void *)(unsigned long)(_size)) +#define mempool_create_kmalloc_pool(_min_nr, _size) \ + mempool_create((_min_nr), mempool_kmalloc, mempool_kfree, \ + (void *)(unsigned long)(_size)) void *mempool_kvmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kvfree(void *element, void *pool_data); @@ -115,16 +117,11 @@ static inline mempool_t *mempool_create_kvmalloc_pool(int min_nr, size_t size) void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data); void mempool_free_pages(void *element, void *pool_data); -static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order) -{ - return mempool_init(pool, min_nr, mempool_alloc_pages, - mempool_free_pages, (void *)(long)order); -} - -static inline mempool_t *mempool_create_page_pool(int min_nr, int order) -{ - return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages, - (void *)(long)order); -} +#define mempool_init_page_pool(_pool, _min_nr, _order) \ + mempool_init(_pool, (_min_nr), mempool_alloc_pages, \ + mempool_free_pages, (void *)(long)(_order)) +#define mempool_create_page_pool(_min_nr, _order) \ + mempool_create((_min_nr), mempool_alloc_pages, \ + mempool_free_pages, (void *)(long)(_order)) #endif /* _LINUX_MEMPOOL_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b0ee64225de9c..9849dfda44d43c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -5,6 +5,7 @@ #include <linux/errno.h> #include <linux/mmdebug.h> #include <linux/gfp.h> +#include <linux/pgalloc_tag.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> @@ -1199,7 +1200,7 @@ static inline int is_vmalloc_or_module_addr(const void *x) * debugging purposes - it does not include PTE-mapped sub-pages; look * at folio_mapcount() or page_mapcount() instead. */ -static inline int folio_entire_mapcount(struct folio *folio) +static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_entire_mapcount) + 1; @@ -1223,48 +1224,60 @@ static inline void page_mapcount_reset(struct page *page) * a large folio, it includes the number of times this page is mapped * as part of that folio. * - * The result is undefined for pages which cannot be mapped into userspace. - * For example SLAB or special types of pages. See function page_has_type(). - * They use this field in struct page differently. + * Will report 0 for pages which cannot be mapped into userspace, eg + * slab, page tables and similar. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; + /* Handle page_has_type() pages */ + if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) + mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); return mapcount; } -int folio_total_mapcount(struct folio *folio); +static inline int folio_large_mapcount(const struct folio *folio) +{ + VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); + return atomic_read(&folio->_large_mapcount) + 1; +} /** - * folio_mapcount() - Calculate the number of mappings of this folio. + * folio_mapcount() - Number of mappings of this folio. * @folio: The folio. * - * A large folio tracks both how many times the entire folio is mapped, - * and how many times each individual page in the folio is mapped. - * This function calculates the total number of times the folio is - * mapped. + * The folio mapcount corresponds to the number of present user page table + * entries that reference any part of a folio. Each such present user page + * table entry must be paired with exactly on folio reference. + * + * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts + * exactly once. + * + * For hugetlb folios, each abstracted "hugetlb" user page table entry that + * references the entire folio counts exactly once, even when such special + * page table entries are comprised of multiple ordinary page table entries. + * + * Will report 0 for pages which cannot be mapped into userspace, such as + * slab, page tables and similar. * * Return: The number of times this folio is mapped. */ -static inline int folio_mapcount(struct folio *folio) +static inline int folio_mapcount(const struct folio *folio) { - if (likely(!folio_test_large(folio))) - return atomic_read(&folio->_mapcount) + 1; - return folio_total_mapcount(folio); -} + int mapcount; -static inline bool folio_large_is_mapped(struct folio *folio) -{ - /* - * Reading _entire_mapcount below could be omitted if hugetlb - * participated in incrementing nr_pages_mapped when compound mapped. - */ - return atomic_read(&folio->_nr_pages_mapped) > 0 || - atomic_read(&folio->_entire_mapcount) >= 0; + if (likely(!folio_test_large(folio))) { + mapcount = atomic_read(&folio->_mapcount) + 1; + /* Handle page_has_type() pages */ + if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) + mapcount = 0; + return mapcount; + } + return folio_large_mapcount(folio); } /** @@ -1273,11 +1286,9 @@ static inline bool folio_large_is_mapped(struct folio *folio) * * Return: True if any page in this folio is referenced by user page tables. */ -static inline bool folio_mapped(struct folio *folio) +static inline bool folio_mapped(const struct folio *folio) { - if (likely(!folio_test_large(folio))) - return atomic_read(&folio->_mapcount) >= 0; - return folio_large_is_mapped(folio); + return folio_mapcount(folio) >= 1; } /* @@ -1285,11 +1296,9 @@ static inline bool folio_mapped(struct folio *folio) * For compound page it returns true if any sub-page of compound page is mapped, * even if this particular sub-page is not itself mapped by any PTE or PMD. */ -static inline bool page_mapped(struct page *page) +static inline bool page_mapped(const struct page *page) { - if (likely(!PageCompound(page))) - return atomic_read(&page->_mapcount) >= 0; - return folio_large_is_mapped(page_folio(page)); + return folio_mapped(page_folio(page)); } static inline struct page *virt_to_head_page(const void *x) @@ -1315,8 +1324,6 @@ void folio_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); -void destroy_large_folio(struct folio *folio); - /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { @@ -1434,27 +1441,22 @@ vm_fault_t finish_fault(struct vm_fault *vmf); #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -bool __put_devmap_managed_page_refs(struct page *page, int refs); -static inline bool put_devmap_managed_page_refs(struct page *page, int refs) +bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); +static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { if (!static_branch_unlikely(&devmap_managed_key)) return false; - if (!is_zone_device_page(page)) + if (!folio_is_zone_device(folio)) return false; - return __put_devmap_managed_page_refs(page, refs); + return __put_devmap_managed_folio_refs(folio, refs); } #else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_page_refs(struct page *page, int refs) +static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { return false; } #endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_page(struct page *page) -{ - return put_devmap_managed_page_refs(page, 1); -} - /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) @@ -1573,7 +1575,7 @@ static inline void put_page(struct page *page) * For some devmap managed pages we need to catch refcount transition * from 2 to 1: */ - if (put_devmap_managed_page(&folio->page)) + if (put_devmap_managed_folio_refs(folio, 1)) return; folio_put(folio); } @@ -2067,7 +2069,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone, * * Return: A positive power of two. */ -static inline long folio_nr_pages(struct folio *folio) +static inline long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; @@ -2162,21 +2164,64 @@ static inline size_t folio_size(struct folio *folio) } /** - * folio_estimated_sharers - Estimate the number of sharers of a folio. + * folio_likely_mapped_shared - Estimate if the folio is mapped into the page + * tables of more than one MM * @folio: The folio. * - * folio_estimated_sharers() aims to serve as a function to efficiently - * estimate the number of processes sharing a folio. This is done by - * looking at the precise mapcount of the first subpage in the folio, and - * assuming the other subpages are the same. This may not be true for large - * folios. If you want exact mapcounts for exact calculations, look at - * page_mapcount() or folio_total_mapcount(). + * This function checks if the folio is currently mapped into more than one + * MM ("mapped shared"), or if the folio is only mapped into a single MM + * ("mapped exclusively"). + * + * As precise information is not easily available for all folios, this function + * estimates the number of MMs ("sharers") that are currently mapping a folio + * using the number of times the first page of the folio is currently mapped + * into page tables. + * + * For small anonymous folios (except KSM folios) and anonymous hugetlb folios, + * the return value will be exactly correct, because they can only be mapped + * at most once into an MM, and they cannot be partially mapped. + * + * For other folios, the result can be fuzzy: + * #. For partially-mappable large folios (THP), the return value can wrongly + * indicate "mapped exclusively" (false negative) when the folio is + * only partially mapped into at least one MM. + * #. For pagecache folios (including hugetlb), the return value can wrongly + * indicate "mapped shared" (false positive) when two VMAs in the same MM + * cover the same file range. + * #. For (small) KSM folios, the return value can wrongly indicate "mapped + * shared" (false positive), when the folio is mapped multiple times into + * the same MM. + * + * Further, this function only considers current page table mappings that + * are tracked using the folio mapcount(s). * - * Return: The estimated number of processes sharing a folio. + * This function does not consider: + * #. If the folio might get mapped in the (near) future (e.g., swapcache, + * pagecache, temporary unmapping for migration). + * #. If the folio is mapped differently (VM_PFNMAP). + * #. If hugetlb page table sharing applies. Callers might want to check + * hugetlb_pmd_shared(). + * + * Return: Whether the folio is estimated to be mapped into more than one MM. */ -static inline int folio_estimated_sharers(struct folio *folio) +static inline bool folio_likely_mapped_shared(struct folio *folio) { - return page_mapcount(folio_page(folio, 0)); + int mapcount = folio_mapcount(folio); + + /* Only partially-mappable folios require more care. */ + if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) + return mapcount > 1; + + /* A single mapping implies "mapped exclusively". */ + if (mapcount <= 1) + return false; + + /* If any page is mapped more than once we treat it "mapped shared". */ + if (folio_entire_mapcount(folio) || mapcount > folio_nr_pages(folio)) + return true; + + /* Let's guess based on the first subpage. */ + return atomic_read(&folio->_mapcount) > 0; } #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE @@ -2391,12 +2436,8 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -int follow_pte(struct mm_struct *mm, unsigned long address, +int follow_pte(struct vm_area_struct *vma, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); -int follow_pfn(struct vm_area_struct *vma, unsigned long address, - unsigned long *pfn); -int follow_phys(struct vm_area_struct *vma, unsigned long address, - unsigned int flags, unsigned long *prot, resource_size_t *phys); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); @@ -2550,7 +2591,7 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, MM_CP_UFFD_WP_RESOLVE) bool vma_needs_dirty_tracking(struct vm_area_struct *vma); -int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); +bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { /* @@ -2857,12 +2898,13 @@ static inline bool pagetable_is_reserved(struct ptdesc *pt) * * Return: The ptdesc describing the allocated page tables. */ -static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int order) +static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order) { - struct page *page = alloc_pages(gfp | __GFP_COMP, order); + struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order); return page_ptdesc(page); } +#define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__)) /** * pagetable_free - Free pagetables @@ -3132,6 +3174,14 @@ extern void reserve_bootmem_region(phys_addr_t start, /* Free the reserved page into the buddy system, so it gets managed. */ static inline void free_reserved_page(struct page *page) { + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } ClearPageReserved(page); init_page_count(page); __free_page(page); @@ -3193,8 +3243,6 @@ static inline unsigned long get_num_physpages(void) */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); -unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, - unsigned long end_pfn); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, @@ -3210,7 +3258,6 @@ static inline int early_pfn_to_nid(unsigned long pfn) extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif -extern void set_dma_reserve(unsigned long new_dma_reserve); extern void mem_init(void); extern void __init mmap_init(void); @@ -3222,9 +3269,6 @@ static inline void show_mem(void) extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); -#ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES -extern unsigned long arch_reserved_kernel_pages(void); -#endif extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); @@ -3383,7 +3427,16 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); -extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); +unsigned long +__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); + +static inline unsigned long +get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + return __get_unmapped_area(file, addr, len, pgoff, flags, 0); +} extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, @@ -3429,6 +3482,7 @@ struct vm_unmapped_area_info { unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; + unsigned long start_gap; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); @@ -3722,7 +3776,14 @@ DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, - &init_on_free); + &init_on_free); +} + +DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); +static inline bool want_init_mlocked_on_free(void) +{ + return static_branch_maybe(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, + &init_mlocked_on_free); } extern bool _debug_pagealloc_enabled_early; @@ -3785,24 +3846,22 @@ static inline bool page_is_guard(struct page *page) return PageGuard(page); } -bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order, - int migratetype); +bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline bool set_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) + unsigned int order) { if (!debug_guardpage_enabled()) return false; - return __set_page_guard(zone, page, order, migratetype); + return __set_page_guard(zone, page, order); } -void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order, - int migratetype); +void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline void clear_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) + unsigned int order) { if (!debug_guardpage_enabled()) return; - __clear_page_guard(zone, page, order, migratetype); + __clear_page_guard(zone, page, order); } #else /* CONFIG_DEBUG_PAGEALLOC */ @@ -3812,9 +3871,9 @@ static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) { return false; } + unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) {} + unsigned int order) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA @@ -3969,7 +4028,6 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE @@ -4202,4 +4260,7 @@ static inline bool pfn_is_unaccepted_memory(unsigned long pfn) return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); } +void vma_pgtable_walk_begin(struct vm_area_struct *vma); +void vma_pgtable_walk_end(struct vm_area_struct *vma); + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5240bd7bca338c..24323c7d0bd484 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -169,7 +169,7 @@ struct page { /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; -#ifdef CONFIG_MEMCG +#ifdef CONFIG_SLAB_OBJ_EXT unsigned long memcg_data; #endif @@ -289,7 +289,8 @@ typedef struct { * @virtual: Virtual address in the kernel direct map. * @_last_cpupid: IDs of last CPU and last process that accessed the folio. * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). - * @_nr_pages_mapped: Do not use directly, call folio_mapcount(). + * @_large_mapcount: Do not use directly, call folio_mapcount(). + * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. @@ -331,7 +332,7 @@ struct folio { }; atomic_t _mapcount; atomic_t _refcount; -#ifdef CONFIG_MEMCG +#ifdef CONFIG_SLAB_OBJ_EXT unsigned long memcg_data; #endif #if defined(WANT_PAGE_VIRTUAL) @@ -348,8 +349,8 @@ struct folio { struct { unsigned long _flags_1; unsigned long _head_1; - unsigned long _folio_avail; /* public: */ + atomic_t _large_mapcount; atomic_t _entire_mapcount; atomic_t _nr_pages_mapped; atomic_t _pincount; @@ -671,6 +672,9 @@ struct vm_area_struct { }; #ifdef CONFIG_PER_VMA_LOCK + /* Flag to indicate areas detached from the mm->mm_mt tree */ + bool detached; + /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) @@ -687,9 +691,6 @@ struct vm_area_struct { */ int vm_lock_seq; struct vma_lock *vm_lock; - - /* Flag to indicate areas detached from the mm->mm_mt tree */ - bool detached; #endif /* @@ -777,11 +778,7 @@ struct mm_struct { } ____cacheline_aligned_in_smp; struct maple_tree mm_mt; -#ifdef CONFIG_MMU - unsigned long (*get_unmapped_area) (struct file *filp, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags); -#endif + unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES @@ -1170,14 +1167,15 @@ static inline void mm_init_cid(struct mm_struct *mm) cpumask_clear(mm_cidmask(mm)); } -static inline int mm_alloc_cid(struct mm_struct *mm) +static inline int mm_alloc_cid_noprof(struct mm_struct *mm) { - mm->pcpu_cid = alloc_percpu(struct mm_cid); + mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); if (!mm->pcpu_cid) return -ENOMEM; mm_init_cid(mm); return 0; } +#define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) static inline void mm_destroy_cid(struct mm_struct *mm) { @@ -1370,6 +1368,15 @@ enum fault_flag { typedef unsigned int __bitwise zap_flags_t; +/* Flags for clear_young_dirty_ptes(). */ +typedef int __bitwise cydp_t; + +/* Clear the access bit */ +#define CYDP_CLEAR_YOUNG ((__force cydp_t)BIT(0)) + +/* Clear the dirty bit */ +#define CYDP_CLEAR_DIRTY ((__force cydp_t)BIT(1)) + /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 8d38dcb6d044cb..de9dc20b01ba74 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -60,16 +60,14 @@ static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) #endif /* CONFIG_TRACING */ -static inline void mmap_assert_locked(struct mm_struct *mm) +static inline void mmap_assert_locked(const struct mm_struct *mm) { - lockdep_assert_held(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); + rwsem_assert_held(&mm->mmap_lock); } -static inline void mmap_assert_write_locked(struct mm_struct *mm) +static inline void mmap_assert_write_locked(const struct mm_struct *mm) { - lockdep_assert_held_write(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); + rwsem_assert_held_write(&mm->mmap_lock); } #ifdef CONFIG_PER_VMA_LOCK diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 652d77805e99df..104078afe0b16f 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -109,7 +109,6 @@ enum pageflags { PG_active, PG_workingset, PG_error, - PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, PG_reserved, @@ -190,7 +189,6 @@ enum pageflags { /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_error, - PG_hugetlb = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; @@ -458,30 +456,51 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) +#define FOLIO_TEST_FLAG_FALSE(name) \ +static inline bool folio_test_##name(const struct folio *folio) \ +{ return false; } +#define FOLIO_SET_FLAG_NOOP(name) \ +static inline void folio_set_##name(struct folio *folio) { } +#define FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void folio_clear_##name(struct folio *folio) { } +#define __FOLIO_SET_FLAG_NOOP(name) \ +static inline void __folio_set_##name(struct folio *folio) { } +#define __FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void __folio_clear_##name(struct folio *folio) { } +#define FOLIO_TEST_SET_FLAG_FALSE(name) \ +static inline bool folio_test_set_##name(struct folio *folio) \ +{ return false; } +#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ +static inline bool folio_test_clear_##name(struct folio *folio) \ +{ return false; } + +#define FOLIO_FLAG_FALSE(name) \ +FOLIO_TEST_FLAG_FALSE(name) \ +FOLIO_SET_FLAG_NOOP(name) \ +FOLIO_CLEAR_FLAG_NOOP(name) + #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ +FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_set_##lname(struct folio *folio) { } \ +FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_clear_##lname(struct folio *folio) { } \ +FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void __folio_clear_##lname(struct folio *folio) { } \ +__FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ -static inline bool folio_test_set_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ -static inline bool folio_test_clear_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ @@ -493,9 +512,9 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) -PAGEFLAG(Referenced, referenced, PF_HEAD) - TESTCLEARFLAG(Referenced, referenced, PF_HEAD) - __SETPAGEFLAG(Referenced, referenced, PF_HEAD) +FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) + __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) @@ -504,7 +523,6 @@ PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) -__PAGEFLAG(Slab, slab, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ @@ -608,12 +626,19 @@ PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif -#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) +#ifdef CONFIG_PAGE_IDLE_FLAG +#ifdef CONFIG_64BIT FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif +/* See page_idle.h for !64BIT workaround */ +#else /* !CONFIG_PAGE_IDLE_FLAG */ +FOLIO_FLAG_FALSE(young) +FOLIO_TEST_CLEAR_FLAG_FALSE(young) +FOLIO_FLAG_FALSE(idle) +#endif /* * PageReported() is used to track reported free pages within the Buddy @@ -668,7 +693,7 @@ static __always_inline bool folio_mapping_flags(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; } -static __always_inline int PageMappingFlags(const struct page *page) +static __always_inline bool PageMappingFlags(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } @@ -689,7 +714,7 @@ static __always_inline bool __folio_test_movable(const struct folio *folio) PAGE_MAPPING_MOVABLE; } -static __always_inline int __PageMovable(const struct page *page) +static __always_inline bool __PageMovable(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; @@ -716,7 +741,7 @@ static __always_inline bool PageKsm(const struct page *page) TESTPAGEFLAG_FALSE(Ksm, ksm) #endif -u64 stable_page_flags(struct page *page); +u64 stable_page_flags(const struct page *page); /** * folio_xor_flags_has_waiters - Change some folio flags. @@ -764,7 +789,7 @@ static inline bool folio_test_uptodate(const struct folio *folio) return ret; } -static inline int PageUptodate(const struct page *page) +static inline bool PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } @@ -848,36 +873,13 @@ static inline void ClearPageCompound(struct page *page) BUG_ON(!PageHead(page)); ClearPageHead(page); } -PAGEFLAG(LargeRmappable, large_rmappable, PF_SECOND) +FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) #else -TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) +FOLIO_FLAG_FALSE(large_rmappable) #endif #define PG_head_mask ((1UL << PG_head)) -#ifdef CONFIG_HUGETLB_PAGE -int PageHuge(const struct page *page); -SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) -CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) - -/** - * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs - * @folio: The folio to test. - * - * Context: Any context. Caller should have a reference on the folio to - * prevent it from being turned into a tail page. - * Return: True for hugetlbfs folios, false for anon folios or folios - * belonging to other filesystems. - */ -static inline bool folio_test_hugetlb(const struct folio *folio) -{ - return folio_test_large(folio) && - test_bit(PG_hugetlb, const_folio_flags(folio, 1)); -} -#else -TESTPAGEFLAG_FALSE(Huge, hugetlb) -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -934,33 +936,23 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* - * Check if a page is currently marked HWPoisoned. Note that this check is - * best effort only and inherently racy: there is no way to synchronize with - * failing hardware. - */ -static inline bool is_page_hwpoison(struct page *page) -{ - if (PageHWPoison(page)) - return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); -} - -/* - * For pages that are never mapped to userspace (and aren't PageSlab), + * For pages that are never mapped to userspace, * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and - * low bits so that an underflow or overflow of page_mapcount() won't be + * low bits so that an underflow or overflow of _mapcount won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of page_mapcount */ +/* Reserve 0x0000007f to catch underflows of _mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 #define PG_table 0x00000200 #define PG_guard 0x00000400 +#define PG_hugetlb 0x00000800 +#define PG_slab 0x00001000 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -977,35 +969,38 @@ static inline int page_has_type(const struct page *page) return page_type_has_type(page->page_type); } +#define FOLIO_TYPE_OPS(lname, fname) \ +static __always_inline bool folio_test_##fname(const struct folio *folio)\ +{ \ + return folio_test_type(folio, PG_##lname); \ +} \ +static __always_inline void __folio_set_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ + folio->page.page_type &= ~PG_##lname; \ +} \ +static __always_inline void __folio_clear_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ + folio->page.page_type |= PG_##lname; \ +} + #define PAGE_TYPE_OPS(uname, lname, fname) \ +FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ -static __always_inline int folio_test_##fname(const struct folio *folio)\ -{ \ - return folio_test_type(folio, PG_##lname); \ -} \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ -static __always_inline void __folio_set_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ - folio->page.page_type &= ~PG_##lname; \ -} \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ -} \ -static __always_inline void __folio_clear_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ - folio->page.page_type |= PG_##lname; \ -} \ +} /* * PageBuddy() indicates that the page is free and in the buddy system @@ -1052,14 +1047,67 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) -extern bool is_free_buddy_page(struct page *page); +FOLIO_TYPE_OPS(slab, slab) + +/** + * PageSlab - Determine if the page belongs to the slab allocator + * @page: The page to test. + * + * Context: Any context. + * Return: True for slab pages, false for any other kind of page. + */ +static inline bool PageSlab(const struct page *page) +{ + return folio_test_slab(page_folio(page)); +} + +#ifdef CONFIG_HUGETLB_PAGE +FOLIO_TYPE_OPS(hugetlb, hugetlb) +#else +FOLIO_TEST_FLAG_FALSE(hugetlb) +#endif + +/** + * PageHuge - Determine if the page belongs to hugetlbfs + * @page: The page to test. + * + * Context: Any context. + * Return: True for hugetlbfs pages, false for anon pages or pages + * belonging to other filesystems. + */ +static inline bool PageHuge(const struct page *page) +{ + return folio_test_hugetlb(page_folio(page)); +} + +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(const struct page *page) +{ + const struct folio *folio; + + if (PageHWPoison(page)) + return true; + folio = page_folio(page); + return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); +} + +bool is_free_buddy_page(const struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); - VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + /* + * HugeTLB stores this information on the head page; THP keeps it per + * page + */ + if (PageHuge(page)) + page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } @@ -1098,7 +1146,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ - 1UL << PG_slab | 1UL << PG_active | \ + 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* @@ -1118,7 +1166,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_hugetlb | 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 4ac34392823a9c..c16db006709073 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -34,8 +34,9 @@ static inline bool is_migrate_isolate(int migratetype) #define REPORT_FAILURE 0x2 void set_pageblock_migratetype(struct page *page, int migratetype); -int move_freepages_block(struct zone *zone, struct page *page, - int migratetype, int *num_movable); + +bool move_freepages_block_isolate(struct zone *zone, struct page *page, + int migratetype); int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, int migratetype, int flags, gfp_t gfp_flags); diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index be98564191e676..e4b48a0dda2446 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -4,7 +4,6 @@ #include <linux/types.h> #include <linux/stacktrace.h> -#include <linux/stackdepot.h> struct pglist_data; @@ -78,7 +77,7 @@ static inline void page_ext_init(void) } #endif -extern struct page_ext *page_ext_get(struct page *page); +extern struct page_ext *page_ext_get(const struct page *page); extern void page_ext_put(struct page_ext *page_ext); static inline void *page_ext_data(struct page_ext *page_ext, @@ -118,7 +117,7 @@ static inline void page_ext_init_flatmem(void) { } -static inline struct page_ext *page_ext_get(struct page *page) +static inline struct page_ext *page_ext_get(const struct page *page) { return NULL; } diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index d8f34484064302..89ca0d5dc1e71d 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -6,14 +6,12 @@ #include <linux/page-flags.h> #include <linux/page_ext.h> -#ifdef CONFIG_PAGE_IDLE_FLAG - -#ifndef CONFIG_64BIT +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) /* * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ -static inline bool folio_test_young(struct folio *folio) +static inline bool folio_test_young(const struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_young; @@ -52,7 +50,7 @@ static inline bool folio_test_clear_young(struct folio *folio) return page_young; } -static inline bool folio_test_idle(struct folio *folio) +static inline bool folio_test_idle(const struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_idle; @@ -60,7 +58,7 @@ static inline bool folio_test_idle(struct folio *folio) if (unlikely(!page_ext)) return false; - page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); return page_idle; @@ -87,61 +85,5 @@ static inline void folio_clear_idle(struct folio *folio) clear_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); } -#endif /* !CONFIG_64BIT */ - -#else /* !CONFIG_PAGE_IDLE_FLAG */ - -static inline bool folio_test_young(struct folio *folio) -{ - return false; -} - -static inline void folio_set_young(struct folio *folio) -{ -} - -static inline bool folio_test_clear_young(struct folio *folio) -{ - return false; -} - -static inline bool folio_test_idle(struct folio *folio) -{ - return false; -} - -static inline void folio_set_idle(struct folio *folio) -{ -} - -static inline void folio_clear_idle(struct folio *folio) -{ -} - -#endif /* CONFIG_PAGE_IDLE_FLAG */ - -static inline bool page_is_young(struct page *page) -{ - return folio_test_young(page_folio(page)); -} - -static inline void set_page_young(struct page *page) -{ - folio_set_young(page_folio(page)); -} - -static inline bool test_and_clear_page_young(struct page *page) -{ - return folio_test_clear_young(page_folio(page)); -} - -static inline bool page_is_idle(struct page *page) -{ - return folio_test_idle(page_folio(page)); -} - -static inline void set_page_idle(struct page *page) -{ - folio_set_idle(page_folio(page)); -} +#endif /* CONFIG_PAGE_IDLE_FLAG && !64BIT */ #endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index d7c2d33baa7f8e..1acf5bac7f503b 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -139,20 +139,15 @@ static inline void folio_ref_sub(struct folio *folio, int nr) page_ref_sub(&folio->page, nr); } -static inline int page_ref_sub_return(struct page *page, int nr) +static inline int folio_ref_sub_return(struct folio *folio, int nr) { - int ret = atomic_sub_return(nr, &page->_refcount); + int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) - __page_ref_mod_and_return(page, -nr, ret); + __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } -static inline int folio_ref_sub_return(struct folio *folio, int nr) -{ - return page_ref_sub_return(&folio->page, nr); -} - static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 3f2409b968ec65..547e82cdc89a44 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -28,7 +28,7 @@ enum pageblock_bits { NR_PAGEBLOCK_BITS }; -#ifdef CONFIG_HUGETLB_PAGE +#if defined(CONFIG_HUGETLB_PAGE) #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE @@ -45,7 +45,11 @@ extern unsigned int pageblock_order; #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ -#else /* CONFIG_HUGETLB_PAGE */ +#elif defined(CONFIG_TRANSPARENT_HUGEPAGE) + +#define pageblock_order min_t(unsigned int, HPAGE_PMD_ORDER, MAX_PAGE_ORDER) + +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */ #define pageblock_order MAX_PAGE_ORDER diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2df35e65557d27..4e85f33721c42f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -399,7 +399,6 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) #endif } -struct address_space *page_mapping(struct page *); struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); @@ -542,24 +541,22 @@ static inline void *detach_page_private(struct page *page) #endif #ifdef CONFIG_NUMA -struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order); +struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order); #else -static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) +static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { - return folio_alloc(gfp, order); + return folio_alloc_noprof(gfp, order); } #endif +#define filemap_alloc_folio(...) \ + alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__)) + static inline struct page *__page_cache_alloc(gfp_t gfp) { return &filemap_alloc_folio(gfp, 0)->page; } -static inline struct page *page_cache_alloc(struct address_space *x) -{ - return __page_cache_alloc(mapping_gfp_mask(x)); -} - static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; @@ -1144,11 +1141,6 @@ void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); void folio_wait_stable(struct folio *folio); void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); -static inline void __set_page_dirty(struct page *page, - struct address_space *mapping, int warn) -{ - __folio_mark_dirty(page_folio(page), mapping, warn); -} void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) @@ -1160,7 +1152,6 @@ static inline void folio_cancel_dirty(struct folio *folio) bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -int __set_page_dirty_nobuffers(struct page *page); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_MIGRATION diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h index 30581e2e04cc1f..5802e1deef24b5 100644 --- a/include/linux/pds/pds_common.h +++ b/include/linux/pds/pds_common.h @@ -4,6 +4,8 @@ #ifndef _PDS_COMMON_H_ #define _PDS_COMMON_H_ +#include <linux/notifier.h> + #define PDS_CORE_DRV_NAME "pds_core" /* the device's internal addressing uses up to 52 bits */ diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 8c677f185901bc..03053de557cf60 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -2,6 +2,7 @@ #ifndef __LINUX_PERCPU_H #define __LINUX_PERCPU_H +#include <linux/alloc_tag.h> #include <linux/mmdebug.h> #include <linux/preempt.h> #include <linux/smp.h> @@ -9,12 +10,17 @@ #include <linux/pfn.h> #include <linux/init.h> #include <linux/cleanup.h> +#include <linux/sched.h> #include <asm/percpu.h> /* enough to cover all DEFINE_PER_CPUs in modules */ #ifdef CONFIG_MODULES +#ifdef CONFIG_MEM_ALLOC_PROFILING +#define PERCPU_MODULE_RESERVE (8 << 13) +#else #define PERCPU_MODULE_RESERVE (8 << 10) +#endif #else #define PERCPU_MODULE_RESERVE 0 #endif @@ -121,7 +127,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif -extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); extern bool is_kernel_percpu_address(unsigned long addr); @@ -129,14 +134,16 @@ extern bool is_kernel_percpu_address(unsigned long addr); extern void __init setup_per_cpu_areas(void); #endif -extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); -extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); -extern void free_percpu(void __percpu *__pdata); +extern void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, + gfp_t gfp) __alloc_size(1); extern size_t pcpu_alloc_size(void __percpu *__pdata); -DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) - -extern phys_addr_t per_cpu_ptr_to_phys(void *addr); +#define __alloc_percpu_gfp(_size, _align, _gfp) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, false, _gfp)) +#define __alloc_percpu(_size, _align) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, false, GFP_KERNEL)) +#define __alloc_reserved_percpu(_size, _align) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, true, GFP_KERNEL)) #define alloc_percpu_gfp(type, gfp) \ (typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type), \ @@ -144,6 +151,15 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #define alloc_percpu(type) \ (typeof(type) __percpu *)__alloc_percpu(sizeof(type), \ __alignof__(type)) +#define alloc_percpu_noprof(type) \ + ((typeof(type) __percpu *)pcpu_alloc_noprof(sizeof(type), \ + __alignof__(type), false, GFP_KERNEL)) + +extern void free_percpu(void __percpu *__pdata); + +DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) + +extern phys_addr_t per_cpu_ptr_to_phys(void *addr); extern unsigned long pcpu_nr_pages(void); diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h new file mode 100644 index 00000000000000..86ba5d33e43bdf --- /dev/null +++ b/include/linux/pgalloc_tag.h @@ -0,0 +1,132 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * page allocation tagging + */ +#ifndef _LINUX_PGALLOC_TAG_H +#define _LINUX_PGALLOC_TAG_H + +#include <linux/alloc_tag.h> + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +#include <linux/page_ext.h> + +extern struct page_ext_operations page_alloc_tagging_ops; + +static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext) +{ + return (void *)page_ext + page_alloc_tagging_ops.offset; +} + +static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref) +{ + return (void *)ref - page_alloc_tagging_ops.offset; +} + +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline union codetag_ref *get_page_tag_ref(struct page *page) +{ + if (page) { + struct page_ext *page_ext = page_ext_get(page); + + if (page_ext) + return codetag_ref_from_page_ext(page_ext); + } + return NULL; +} + +static inline void put_page_tag_ref(union codetag_ref *ref) +{ + page_ext_put(page_ext_from_codetag_ref(ref)); +} + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_add(ref, task->alloc_tag, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_sub(ref, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_split(struct page *page, unsigned int nr) +{ + int i; + struct page_ext *page_ext; + union codetag_ref *ref; + struct alloc_tag *tag; + + if (!mem_alloc_profiling_enabled()) + return; + + page_ext = page_ext_get(page); + if (unlikely(!page_ext)) + return; + + ref = codetag_ref_from_page_ext(page_ext); + if (!ref->ct) + goto out; + + tag = ct_to_alloc_tag(ref->ct); + page_ext = page_ext_next(page_ext); + for (i = 1; i < nr; i++) { + /* Set new reference to point to the original tag */ + alloc_tag_ref_set(codetag_ref_from_page_ext(page_ext), tag); + page_ext = page_ext_next(page_ext); + } +out: + page_ext_put(page_ext); +} + +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) +{ + struct alloc_tag *tag = NULL; + + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + alloc_tag_sub_check(ref); + if (ref && ref->ct) + tag = ct_to_alloc_tag(ref->ct); + put_page_tag_ref(ref); + } + + return tag; +} + +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) +{ + if (mem_alloc_profiling_enabled() && tag) + this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); +} + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } +static inline void put_page_tag_ref(union codetag_ref *ref) {} +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) {} +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} +static inline void pgalloc_tag_split(struct page *page, unsigned int nr) {} +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#endif /* _LINUX_PGALLOC_TAG_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 85fc7554cd52bc..18019f037baeca 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -50,6 +50,8 @@ #define pmd_pgtable(pmd) pmd_page(pmd) #endif +#define pmd_folio(pmd) page_folio(pmd_page(pmd)) + /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * @@ -149,9 +151,7 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ -#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) -#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE @@ -459,6 +459,50 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif +#ifndef clear_young_dirty_ptes +/** + * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the + * same folio as old/clean. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to mark old/clean. + * @flags: Flags to modify the PTE batch semantics. + * + * May be overridden by the architecture; otherwise, implemented by + * get_and_clear/modify/set for each pte in the range. + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + if (flags == CYDP_CLEAR_YOUNG) + ptep_test_and_clear_young(vma, addr, ptep); + else { + pte = ptep_get_and_clear(vma->vm_mm, addr, ptep); + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + set_pte_at(vma->vm_mm, addr, ptep, pte); + } + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -708,6 +752,35 @@ static inline void pte_clear_not_present_full(struct mm_struct *mm, } #endif +#ifndef clear_not_present_full_ptes +/** + * clear_not_present_full_ptes - Clear multiple not present PTEs which are + * consecutive in the pgtable. + * @mm: Address space the ptes represent. + * @addr: Address of the first pte. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear. + * @full: Whether we are clearing a full mm. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over pte_clear_not_present_full(). + * + * Context: The caller holds the page table lock. The PTEs are all not present. + * The PTEs are all in the same PMD. + */ +static inline void clear_not_present_full_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, unsigned int nr, int full) +{ + for (;;) { + pte_clear_not_present_full(mm, addr, ptep, full); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, @@ -1052,7 +1125,7 @@ static inline int arch_unmap_one(struct mm_struct *mm, * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) +static inline int arch_prepare_to_swap(struct folio *folio) { return 0; } @@ -1079,7 +1152,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif #ifndef __HAVE_ARCH_MOVE_PTE -#define move_pte(pte, prot, old_addr, new_addr) (pte) +#define move_pte(pte, old_addr, new_addr) (pte) #endif #ifndef pte_accessible @@ -1770,11 +1843,25 @@ typedef unsigned int pgtbl_mod_mask; #endif /* - * p?d_leaf() - true if this entry is a final mapping to a physical address. - * This differs from p?d_huge() by the fact that they are always available (if - * the architecture supports large pages at the appropriate level) even - * if CONFIG_HUGETLB_PAGE is not defined. - * Only meaningful when called on a valid entry. + * pXd_leaf() is the API to check whether a pgtable entry is a huge page + * mapping. It should work globally across all archs, without any + * dependency on CONFIG_* options. For architectures that do not support + * huge mappings on specific levels, below fallbacks will be used. + * + * A leaf pgtable entry should always imply the following: + * + * - It is a "present" entry. IOW, before using this API, please check it + * with pXd_present() first. NOTE: it may not always mean the "present + * bit" is set. For example, PROT_NONE entries are always "present". + * + * - It should _never_ be a swap entry of any type. Above "present" check + * should have guarded this, but let's be crystal clear on this. + * + * - It should contain a huge PFN, which points to a huge page larger than + * PAGE_SIZE of the platform. The PFN format isn't important here. + * + * - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(), + * pXd_devmap(), or hugetlb mappings). */ #ifndef pgd_leaf #define pgd_leaf(x) false @@ -1806,6 +1893,20 @@ typedef unsigned int pgtbl_mod_mask; #endif /* + * We always define pmd_pfn for all archs as it's used in lots of generic + * code. Now it happens too for pud_pfn (and can happen for larger + * mappings too in the future; we're not there yet). Instead of defining + * it for all archs (like pmd_pfn), provide a fallback. + * + * Note that returning 0 here means any arch that didn't define this can + * get severely wrong when it hits a real pud leaf. It's arch's + * responsibility to properly define it when a huge pud is possible. + */ +#ifndef pud_pfn +#define pud_pfn(x) 0 +#endif + +/* * Some architectures have MMUs that are configurable or selectable at boot * time. These lead to variable PTRS_PER_x. For statically allocated arrays it * helps to have a static maximum value. diff --git a/include/linux/profile.h b/include/linux/profile.h index 11db1ec516e272..04ae5ebcb637aa 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -18,13 +18,8 @@ struct proc_dir_entry; struct notifier_block; #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) -void create_prof_cpu_mask(void); int create_proc_profile(void); #else -static inline void create_prof_cpu_mask(void) -{ -} - static inline int create_proc_profile(void) { return 0; diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 808f9d3ee54654..fd037c127bb071 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -464,11 +464,11 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, /* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See * documentation for vmalloc for which of them are legal. */ -static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) +static inline void **__ptr_ring_init_queue_alloc_noprof(unsigned int size, gfp_t gfp) { if (size > KMALLOC_MAX_SIZE / sizeof(void *)) return NULL; - return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO); + return kvmalloc_array_noprof(size, sizeof(void *), gfp | __GFP_ZERO); } static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) @@ -484,9 +484,9 @@ static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) r->batch = 1; } -static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) +static inline int ptr_ring_init_noprof(struct ptr_ring *r, int size, gfp_t gfp) { - r->queue = __ptr_ring_init_queue_alloc(size, gfp); + r->queue = __ptr_ring_init_queue_alloc_noprof(size, gfp); if (!r->queue) return -ENOMEM; @@ -497,6 +497,7 @@ static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) return 0; } +#define ptr_ring_init(...) alloc_hooks(ptr_ring_init_noprof(__VA_ARGS__)) /* * Return entries into ring. Destroy entries that don't fit. @@ -587,11 +588,11 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ -static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, +static inline int ptr_ring_resize_noprof(struct ptr_ring *r, int size, gfp_t gfp, void (*destroy)(void *)) { unsigned long flags; - void **queue = __ptr_ring_init_queue_alloc(size, gfp); + void **queue = __ptr_ring_init_queue_alloc_noprof(size, gfp); void **old; if (!queue) @@ -609,6 +610,7 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, return 0; } +#define ptr_ring_resize(...) alloc_hooks(ptr_ring_resize_noprof(__VA_ARGS__)) /* * Note: producer lock is nested within consumer lock, so if you @@ -616,21 +618,21 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ -static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, - unsigned int nrings, - int size, - gfp_t gfp, void (*destroy)(void *)) +static inline int ptr_ring_resize_multiple_noprof(struct ptr_ring **rings, + unsigned int nrings, + int size, + gfp_t gfp, void (*destroy)(void *)) { unsigned long flags; void ***queues; int i; - queues = kmalloc_array(nrings, sizeof(*queues), gfp); + queues = kmalloc_array_noprof(nrings, sizeof(*queues), gfp); if (!queues) goto noqueues; for (i = 0; i < nrings; ++i) { - queues[i] = __ptr_ring_init_queue_alloc(size, gfp); + queues[i] = __ptr_ring_init_queue_alloc_noprof(size, gfp); if (!queues[i]) goto nomem; } @@ -660,6 +662,8 @@ nomem: noqueues: return -ENOMEM; } +#define ptr_ring_resize_multiple(...) \ + alloc_hooks(ptr_ring_resize_multiple_noprof(__VA_ARGS__)) static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *)) { diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b743241cfb7caa..d470303b1bbbbe 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1230,6 +1230,7 @@ int regmap_multi_reg_write_bypassed(struct regmap *map, int regmap_raw_write_async(struct regmap *map, unsigned int reg, const void *val, size_t val_len); int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_noinc_read(struct regmap *map, unsigned int reg, @@ -1739,6 +1740,13 @@ static inline int regmap_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_read_bypassed(struct regmap *map, unsigned int reg, + unsigned int *val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4660582a33022f..ed180ca419dad9 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -320,13 +320,13 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) static inline int devm_regulator_get_enable(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline int devm_regulator_get_enable_optional(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline struct regulator *__must_check diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index b6f3797277ff83..015c8298bebc45 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -9,6 +9,7 @@ #ifndef _LINUX_RHASHTABLE_TYPES_H #define _LINUX_RHASHTABLE_TYPES_H +#include <linux/alloc_tag.h> #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/mutex.h> @@ -88,6 +89,9 @@ struct rhashtable { struct mutex mutex; spinlock_t lock; atomic_t nelems; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif }; /** @@ -127,9 +131,12 @@ struct rhashtable_iter { bool end_of_table; }; -int rhashtable_init(struct rhashtable *ht, +int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params); -int rhltable_init(struct rhltable *hlt, +#define rhashtable_init(...) alloc_hooks(rhashtable_init_noprof(__VA_ARGS__)) + +int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params); +#define rhltable_init(...) alloc_hooks(rhltable_init_noprof(__VA_ARGS__)) #endif /* _LINUX_RHASHTABLE_TYPES_H */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b7944a833668a7..7229b9baf20d87 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -273,6 +273,7 @@ static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, ClearPageAnonExclusive(&folio->page); } atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); return 0; } @@ -284,7 +285,7 @@ static inline int hugetlb_try_share_anon_rmap(struct folio *folio) VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio); /* Paired with the memory barrier in try_grab_folio(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) @@ -295,7 +296,7 @@ static inline int hugetlb_try_share_anon_rmap(struct folio *folio) * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } @@ -306,6 +307,7 @@ static inline void hugetlb_add_file_rmap(struct folio *folio) VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); } static inline void hugetlb_remove_rmap(struct folio *folio) @@ -313,21 +315,31 @@ static inline void hugetlb_remove_rmap(struct folio *folio) VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); atomic_dec(&folio->_entire_mapcount); + atomic_dec(&folio->_large_mapcount); } static __always_inline void __folio_dup_file_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level) { + const int orig_nr_pages = nr_pages; + __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: + if (!folio_test_large(folio)) { + atomic_inc(&page->_mapcount); + break; + } + do { atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); + atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); break; } } @@ -347,8 +359,12 @@ static inline void folio_dup_file_rmap_ptes(struct folio *folio, { __folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE); } -#define folio_dup_file_rmap_pte(folio, page) \ - folio_dup_file_rmap_ptes(folio, page, 1) + +static __always_inline void folio_dup_file_rmap_pte(struct folio *folio, + struct page *page) +{ + __folio_dup_file_rmap(folio, page, 1, RMAP_LEVEL_PTE); +} /** * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio @@ -373,6 +389,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *src_vma, enum rmap_level level) { + const int orig_nr_pages = nr_pages; bool maybe_pinned; int i; @@ -401,11 +418,20 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, if (PageAnonExclusive(page + i)) return -EBUSY; } + + if (!folio_test_large(folio)) { + if (PageAnonExclusive(page)) + ClearPageAnonExclusive(page); + atomic_inc(&page->_mapcount); + break; + } + do { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); + atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: if (PageAnonExclusive(page)) { @@ -414,6 +440,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, ClearPageAnonExclusive(page); } atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); break; } return 0; @@ -448,8 +475,13 @@ static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio, return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma, RMAP_LEVEL_PTE); } -#define folio_try_dup_anon_rmap_pte(folio, page, vma) \ - folio_try_dup_anon_rmap_ptes(folio, page, 1, vma) + +static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, + struct page *page, struct vm_area_struct *src_vma) +{ + return __folio_try_dup_anon_rmap(folio, page, 1, src_vma, + RMAP_LEVEL_PTE); +} /** * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range @@ -541,7 +573,7 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, */ /* Paired with the memory barrier in try_grab_folio(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) @@ -552,7 +584,7 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } @@ -698,7 +730,7 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); +unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs diff --git a/include/linux/sched.h b/include/linux/sched.h index 3c2abbc587b49c..4118b3f959c324 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -770,6 +770,10 @@ struct task_struct { unsigned int flags; unsigned int ptrace; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif + #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; @@ -810,6 +814,7 @@ struct task_struct { struct task_group *sched_task_group; #endif + #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. @@ -2187,4 +2192,23 @@ static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } extern void sched_set_stop_task(int cpu, struct task_struct *stop); +#ifdef CONFIG_MEM_ALLOC_PROFILING +static inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) +{ + swap(current->alloc_tag, tag); + return tag; +} + +static inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) +{ +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); +#endif + current->alloc_tag = old; +} +#else +#define alloc_tag_save(_tag) NULL +#define alloc_tag_restore(_tag, _old) do {} while (0) +#endif + #endif diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 02f5090ffea29c..e62ff805cfc950 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -92,9 +92,12 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_VM_MERGE_ANY 30 #define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) +#define MMF_TOPDOWN 31 /* mm searches top down by default */ +#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) + #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ - MMF_VM_MERGE_ANY_MASK) + MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) static inline unsigned long mmf_init_flags(unsigned long flags) { diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index b6543f9d78d6b8..91546493c43da2 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,6 +8,7 @@ #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> +#include <linux/sched/coredump.h> /* * Routines for handling mm_structs @@ -186,6 +187,27 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); +unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags); + +unsigned long +arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags); +unsigned long +arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t); + +unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, + struct file *filp, + unsigned long addr, + unsigned long len, + unsigned long pgoff, + unsigned long flags, + vm_flags_t vm_flags); + unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index acf7e1a3f3def9..e918f96881f569 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -6,25 +6,8 @@ extern const struct address_space_operations secretmem_aops; -static inline bool folio_is_secretmem(struct folio *folio) +static inline bool secretmem_mapping(struct address_space *mapping) { - struct address_space *mapping; - - /* - * Using folio_mapping() is quite slow because of the actual call - * instruction. - * We know that secretmem pages are not compound, so we can - * save a couple of cycles here. - */ - if (folio_test_large(folio)) - return false; - - mapping = (struct address_space *) - ((unsigned long)folio->mapping & ~PAGE_MAPPING_FLAGS); - - if (!mapping || mapping != folio->mapping) - return false; - return mapping->a_ops == &secretmem_aops; } @@ -38,7 +21,7 @@ static inline bool vma_is_secretmem(struct vm_area_struct *vma) return false; } -static inline bool folio_is_secretmem(struct folio *folio) +static inline bool secretmem_mapping(struct address_space *mapping) { return false; } diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index e2d45b7cb61980..926496c9cc9c3b 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -177,10 +177,11 @@ static inline int skb_array_peek_len_any(struct skb_array *a) return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag); } -static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp) +static inline int skb_array_init_noprof(struct skb_array *a, int size, gfp_t gfp) { - return ptr_ring_init(&a->ring, size, gfp); + return ptr_ring_init_noprof(&a->ring, size, gfp); } +#define skb_array_init(...) alloc_hooks(skb_array_init_noprof(__VA_ARGS__)) static void __skb_array_destroy_skb(void *ptr) { @@ -198,15 +199,17 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } -static inline int skb_array_resize_multiple(struct skb_array **rings, - int nrings, unsigned int size, - gfp_t gfp) +static inline int skb_array_resize_multiple_noprof(struct skb_array **rings, + int nrings, unsigned int size, + gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); - return ptr_ring_resize_multiple((struct ptr_ring **)rings, - nrings, size, gfp, - __skb_array_destroy_skb); + return ptr_ring_resize_multiple_noprof((struct ptr_ring **)rings, + nrings, size, gfp, + __skb_array_destroy_skb); } +#define skb_array_resize_multiple(...) \ + alloc_hooks(skb_array_resize_multiple_noprof(__VA_ARGS__)) static inline void skb_array_cleanup(struct skb_array *a) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d24aec064e888..b72920c9887b73 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3371,7 +3371,7 @@ void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); * * %NULL is returned if there is no free memory. */ -static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, +static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. @@ -3384,13 +3384,11 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; - return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); + return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } +#define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) -static inline struct page *dev_alloc_pages(unsigned int order) -{ - return __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, order); -} +#define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx @@ -3400,15 +3398,13 @@ static inline struct page *dev_alloc_pages(unsigned int order) * * %NULL is returned if there is no free memory. */ -static inline struct page *__dev_alloc_page(gfp_t gfp_mask) +static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { - return __dev_alloc_pages(gfp_mask, 0); + return __dev_alloc_pages_noprof(gfp_mask, 0); } +#define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) -static inline struct page *dev_alloc_page(void) -{ - return dev_alloc_pages(0); -} +#define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd27998a..df848425e05414 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -410,11 +410,9 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg); -static inline struct sk_psock_link *sk_psock_init_link(void) -{ - return kzalloc(sizeof(struct sk_psock_link), - GFP_ATOMIC | __GFP_NOWARN); -} +#define sk_psock_init_link() \ + ((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link), \ + GFP_ATOMIC | __GFP_NOWARN)) static inline void sk_psock_free_link(struct sk_psock_link *link) { @@ -461,10 +459,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/include/linux/slab.h b/include/linux/slab.h index e53cbfa1832558..4cc37ef22aaed1 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -56,6 +56,9 @@ enum _slab_flag_bits { #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, +#ifdef CONFIG_SLAB_OBJ_EXT + _SLAB_NO_OBJ_EXT, +#endif _SLAB_FLAGS_LAST_BIT }; @@ -202,6 +205,13 @@ enum _slab_flag_bits { #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ +/* Slab created using create_boot_cache */ +#ifdef CONFIG_SLAB_OBJ_EXT +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) +#else +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED +#endif + /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -261,7 +271,10 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __realloc_size(2); +void * __must_check krealloc_noprof(const void *objp, size_t new_size, + gfp_t flags) __realloc_size(2); +#define krealloc(...) alloc_hooks(krealloc_noprof(__VA_ARGS__)) + void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); @@ -513,7 +526,10 @@ static __always_inline unsigned int __kmalloc_index(size_t size, static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) -void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); +#include <linux/alloc_tag.h> + +void *__kmalloc_noprof(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); +#define __kmalloc(...) alloc_hooks(__kmalloc_noprof(__VA_ARGS__)) /** * kmem_cache_alloc - Allocate an object @@ -525,9 +541,14 @@ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_siz * * Return: pointer to the new object or %NULL in case of error */ -void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc; -void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, - gfp_t gfpflags) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_noprof(struct kmem_cache *cachep, + gfp_t flags) __assume_slab_alignment __malloc; +#define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__)) + +void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) __assume_slab_alignment __malloc; +#define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) + void kmem_cache_free(struct kmem_cache *s, void *objp); /* @@ -538,29 +559,40 @@ void kmem_cache_free(struct kmem_cache *s, void *objp); * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); -int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p); + +int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p); +#define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__)) static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } -void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment +void *__kmalloc_node_noprof(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __alloc_size(1); -void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment - __malloc; +#define __kmalloc_node(...) alloc_hooks(__kmalloc_node_noprof(__VA_ARGS__)) -void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) +void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, + int node) __assume_slab_alignment __malloc; +#define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) + +void *kmalloc_trace_noprof(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); -void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_kmalloc_alignment +void *kmalloc_node_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) __assume_kmalloc_alignment __alloc_size(4); -void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment +#define kmalloc_trace(...) alloc_hooks(kmalloc_trace_noprof(__VA_ARGS__)) + +#define kmalloc_node_trace(...) alloc_hooks(kmalloc_node_trace_noprof(__VA_ARGS__)) + +void *kmalloc_large_noprof(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); +#define kmalloc_large(...) alloc_hooks(kmalloc_large_noprof(__VA_ARGS__)) -void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_alignment +void *kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) __assume_page_alignment __alloc_size(1); +#define kmalloc_large_node(...) alloc_hooks(kmalloc_large_node_noprof(__VA_ARGS__)) /** * kmalloc - allocate kernel memory @@ -616,37 +648,39 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * Try really hard to succeed the allocation but fail * eventually. */ -static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large(size, flags); + return kmalloc_large_noprof(size, flags); index = kmalloc_index(size); - return kmalloc_trace( + return kmalloc_trace_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } - return __kmalloc(size, flags); + return __kmalloc_noprof(size, flags); } +#define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) -static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large_node(size, flags, node); + return kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); - return kmalloc_node_trace( + return kmalloc_node_trace_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } - return __kmalloc_node(size, flags, node); + return __kmalloc_node_noprof(size, flags, node); } +#define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * kmalloc_array - allocate memory for an array. @@ -654,16 +688,17 @@ static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t fla * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc(bytes, flags); - return __kmalloc(bytes, flags); + return kmalloc_noprof(bytes, flags); + return kmalloc_noprof(bytes, flags); } +#define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) /** * krealloc_array - reallocate memory for an array. @@ -672,18 +707,19 @@ static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_ * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p, - size_t new_n, - size_t new_size, - gfp_t flags) +static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, + size_t new_n, + size_t new_size, + gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; - return krealloc(p, bytes, flags); + return krealloc_noprof(p, bytes, flags); } +#define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__)) /** * kcalloc - allocate memory for an array. The memory is set to zero. @@ -691,16 +727,12 @@ static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p, * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flags) -{ - return kmalloc_array(n, size, flags | __GFP_ZERO); -} +#define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO) -void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, +void *kmalloc_node_track_caller_noprof(size_t size, gfp_t flags, int node, unsigned long caller) __alloc_size(1); -#define kmalloc_node_track_caller(size, flags, node) \ - __kmalloc_node_track_caller(size, flags, node, \ - _RET_IP_) +#define kmalloc_node_track_caller(...) \ + alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_)) /* * kmalloc_track_caller is a special version of kmalloc that records the @@ -710,11 +742,12 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, * allocator where we care about the real place the memory allocation * request comes from. */ -#define kmalloc_track_caller(size, flags) \ - __kmalloc_node_track_caller(size, flags, \ - NUMA_NO_NODE, _RET_IP_) +#define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE) -static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, +#define kmalloc_track_caller_noprof(...) \ + kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_) + +static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; @@ -722,75 +755,58 @@ static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc_node(bytes, flags, node); - return __kmalloc_node(bytes, flags, node); + return kmalloc_node_noprof(bytes, flags, node); + return __kmalloc_node_noprof(bytes, flags, node); } +#define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__)) -static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) -{ - return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); -} +#define kcalloc_node(_n, _size, _flags, _node) \ + kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node) /* * Shortcuts */ -static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) -{ - return kmem_cache_alloc(k, flags | __GFP_ZERO); -} +#define kmem_cache_zalloc(_k, _flags) kmem_cache_alloc(_k, (_flags)|__GFP_ZERO) /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1) void *kzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) { - return kmalloc(size, flags | __GFP_ZERO); + return kmalloc_noprof(size, flags | __GFP_ZERO); } +#define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) +#define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) -/** - * kzalloc_node - allocate zeroed memory from a particular memory node. - * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate (see kmalloc). - * @node: memory node from which to allocate - */ -static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int node) -{ - return kmalloc_node(size, flags | __GFP_ZERO, node); -} +extern void *kvmalloc_node_noprof(size_t size, gfp_t flags, int node) __alloc_size(1); +#define kvmalloc_node(...) alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__)) -extern void *kvmalloc_node(size_t size, gfp_t flags, int node) __alloc_size(1); -static inline __alloc_size(1) void *kvmalloc(size_t size, gfp_t flags) -{ - return kvmalloc_node(size, flags, NUMA_NO_NODE); -} -static inline __alloc_size(1) void *kvzalloc_node(size_t size, gfp_t flags, int node) -{ - return kvmalloc_node(size, flags | __GFP_ZERO, node); -} -static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags) -{ - return kvmalloc(size, flags | __GFP_ZERO); -} +#define kvmalloc(_size, _flags) kvmalloc_node(_size, _flags, NUMA_NO_NODE) +#define kvmalloc_noprof(_size, _flags) kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE) +#define kvzalloc(_size, _flags) kvmalloc(_size, _flags|__GFP_ZERO) -static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +#define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, _flags|__GFP_ZERO, _node) + +static inline __alloc_size(1, 2) void *kvmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return kvmalloc(bytes, flags); + return kvmalloc_node_noprof(bytes, flags, NUMA_NO_NODE); } -static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags) -{ - return kvmalloc_array(n, size, flags | __GFP_ZERO); -} +#define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__)) +#define kvcalloc(_n, _size, _flags) kvmalloc_array(_n, _size, _flags|__GFP_ZERO) +#define kvcalloc_noprof(_n, _size, _flags) kvmalloc_array_noprof(_n, _size, _flags|__GFP_ZERO) -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) +extern void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags) __realloc_size(3); +#define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__)) + extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T)) diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 317200cd3a603e..fc5a206c40435f 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -117,9 +117,9 @@ static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) return copy_to_sockptr_offset(dst, 0, src, size); } -static inline void *memdup_sockptr(sockptr_t src, size_t len) +static inline void *memdup_sockptr_noprof(sockptr_t src, size_t len) { - void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); + void *p = kmalloc_track_caller_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -129,10 +129,11 @@ static inline void *memdup_sockptr(sockptr_t src, size_t len) } return p; } +#define memdup_sockptr(...) alloc_hooks(memdup_sockptr_noprof(__VA_ARGS__)) -static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) +static inline void *memdup_sockptr_nul_noprof(sockptr_t src, size_t len) { - char *p = kmalloc_track_caller(len + 1, GFP_KERNEL); + char *p = kmalloc_track_caller_noprof(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -143,6 +144,7 @@ static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) p[len] = '\0'; return p; } +#define memdup_sockptr_nul(...) alloc_hooks(memdup_sockptr_nul_noprof(__VA_ARGS__)) static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { diff --git a/include/linux/string.h b/include/linux/string.h index 9ba8b4597009c9..793c27ad7c0d21 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -282,7 +282,9 @@ extern void kfree_const(const void *x); extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); -extern void *kmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); +extern void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) __realloc_size(2); +#define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) + extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp); diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24cd199dd6f3a9..d33bab33099ab0 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/swap.h b/include/linux/swap.h index f53d608daa0131..11c53692f65fb7 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -259,7 +259,20 @@ struct swap_cluster_info { }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ -#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ + +/* + * The first page in the swap file is the swap header, which is always marked + * bad to prevent it from being allocated as an entry. This also prevents the + * cluster to which it belongs being marked free. Therefore 0 is safe to use as + * a sentinel to indicate next is not valid in percpu_cluster. + */ +#define SWAP_NEXT_INVALID 0 + +#ifdef CONFIG_THP_SWAP +#define SWAP_NR_ORDERS (PMD_ORDER + 1) +#else +#define SWAP_NR_ORDERS 1 +#endif /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from @@ -267,8 +280,7 @@ struct swap_cluster_info { * throughput. */ struct percpu_cluster { - struct swap_cluster_info index; /* Current cluster index */ - unsigned int next; /* Likely next allocation offset */ + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; struct swap_cluster_list { @@ -394,10 +406,13 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) +#define MIN_SWAPPINESS 0 +#define MAX_SWAPPINESS 200 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options); + unsigned int reclaim_options, + int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, @@ -462,14 +477,14 @@ swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); -extern int free_swap_and_cache(swp_entry_t); +extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); @@ -518,8 +533,9 @@ static inline void put_swap_device(struct swap_info_struct *si) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); -/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ -#define free_swap_and_cache(e) is_pfn_swap_entry(e) +static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) +{ +} static inline void free_swap_cache(struct folio *folio) { @@ -587,14 +603,10 @@ static inline int add_swap_extent(struct swap_info_struct *sis, } #endif /* CONFIG_SWAP */ -#ifdef CONFIG_THP_SWAP -extern int split_swap_cluster(swp_entry_t entry); -#else -static inline int split_swap_cluster(swp_entry_t entry) +static inline void free_swap_and_cache(swp_entry_t entry) { - return 0; + free_swap_and_cache_nr(entry, 1); } -#endif #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e619ac10cd234c..9104952d323d1d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -821,6 +821,7 @@ asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); +asmlinkage long sys_mseal(unsigned long start, size_t len, unsigned long flags); asmlinkage long sys_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 98ea90e90439d8..e4a631ec430bb7 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -2,6 +2,8 @@ #ifndef _LINUX_VMALLOC_H #define _LINUX_VMALLOC_H +#include <linux/alloc_tag.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/list.h> @@ -138,26 +140,54 @@ extern unsigned long vmalloc_nr_pages(void); static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif -extern void *vmalloc(unsigned long size) __alloc_size(1); -extern void *vzalloc(unsigned long size) __alloc_size(1); -extern void *vmalloc_user(unsigned long size) __alloc_size(1); -extern void *vmalloc_node(unsigned long size, int node) __alloc_size(1); -extern void *vzalloc_node(unsigned long size, int node) __alloc_size(1); -extern void *vmalloc_32(unsigned long size) __alloc_size(1); -extern void *vmalloc_32_user(unsigned long size) __alloc_size(1); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask) __alloc_size(1); -extern void *__vmalloc_node_range(unsigned long size, unsigned long align, +extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); +#define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) + +extern void *vzalloc_noprof(unsigned long size) __alloc_size(1); +#define vzalloc(...) alloc_hooks(vzalloc_noprof(__VA_ARGS__)) + +extern void *vmalloc_user_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_user(...) alloc_hooks(vmalloc_user_noprof(__VA_ARGS__)) + +extern void *vmalloc_node_noprof(unsigned long size, int node) __alloc_size(1); +#define vmalloc_node(...) alloc_hooks(vmalloc_node_noprof(__VA_ARGS__)) + +extern void *vzalloc_node_noprof(unsigned long size, int node) __alloc_size(1); +#define vzalloc_node(...) alloc_hooks(vzalloc_node_noprof(__VA_ARGS__)) + +extern void *vmalloc_32_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_32(...) alloc_hooks(vmalloc_32_noprof(__VA_ARGS__)) + +extern void *vmalloc_32_user_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_32_user(...) alloc_hooks(vmalloc_32_user_noprof(__VA_ARGS__)) + +extern void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define __vmalloc(...) alloc_hooks(__vmalloc_noprof(__VA_ARGS__)) + +extern void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) __alloc_size(1); -void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, +#define __vmalloc_node_range(...) alloc_hooks(__vmalloc_node_range_noprof(__VA_ARGS__)) + +void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define __vmalloc_node(...) alloc_hooks(__vmalloc_node_noprof(__VA_ARGS__)) + +void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define vmalloc_huge(...) alloc_hooks(vmalloc_huge_noprof(__VA_ARGS__)) + +extern void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +#define __vmalloc_array(...) alloc_hooks(__vmalloc_array_noprof(__VA_ARGS__)) + +extern void *vmalloc_array_noprof(size_t n, size_t size) __alloc_size(1, 2); +#define vmalloc_array(...) alloc_hooks(vmalloc_array_noprof(__VA_ARGS__)) + +extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +#define __vcalloc(...) alloc_hooks(__vcalloc_noprof(__VA_ARGS__)) -extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); -extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); -extern void *__vcalloc(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); -extern void *vcalloc(size_t n, size_t size) __alloc_size(1, 2); +extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); +#define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 343906a98d6eed..735eae6e272cba 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -487,14 +487,6 @@ static inline void node_stat_sub_folio(struct folio *folio, mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } -static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, - int migratetype) -{ - __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); - if (is_migrate_cma(migratetype)) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); -} - extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9845cb62e40b2d..112d806ddbe49d 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -355,6 +355,7 @@ int dirtytime_interval_handler(struct ctl_table *table, int write, void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +unsigned long cgwb_calc_thresh(struct bdi_writeback *wb); void wb_update_bandwidth(struct bdi_writeback *wb); diff --git a/include/linux/xarray.h b/include/linux/xarray.h index cb571dfcf4b167..d2e4d36246890c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -12,14 +12,18 @@ #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <linux/err.h> #include <linux/gfp.h> #include <linux/kconfig.h> -#include <linux/kernel.h> +#include <linux/limits.h> +#include <linux/lockdep.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> +struct list_lru; + /* * The bottom two bits of the entry determine how the XArray interprets * the contents: @@ -1146,7 +1150,7 @@ static inline void xa_release(struct xarray *xa, unsigned long index) #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 -#define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) +#define XA_MARK_LONGS BITS_TO_LONGS(XA_CHUNK_SIZE) /* * @count is the count of every non-NULL element in the ->slots array @@ -1548,6 +1552,7 @@ void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); +int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else @@ -1556,6 +1561,11 @@ static inline int xa_get_order(struct xarray *xa, unsigned long index) return 0; } +static inline int xas_get_order(struct xa_state *xas) +{ + return 0; +} + static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 3296438eec0620..a67d62b796980a 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -53,7 +53,7 @@ void *zpool_map_handle(struct zpool *pool, unsigned long handle, void zpool_unmap_handle(struct zpool *pool, unsigned long handle); -u64 zpool_get_total_size(struct zpool *pool); +u64 zpool_get_total_pages(struct zpool *pool); /** @@ -91,7 +91,7 @@ struct zpool_driver { enum zpool_mapmode mm); void (*unmap)(void *pool, unsigned long handle); - u64 (*total_size)(void *pool); + u64 (*total_pages)(void *pool); }; void zpool_register_driver(struct zpool_driver *driver); diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 341aea4900704c..2a85b941db975d 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -7,7 +7,6 @@ struct lruvec; -extern u64 zswap_pool_total_size; extern atomic_t zswap_stored_pages; #ifdef CONFIG_ZSWAP @@ -27,6 +26,7 @@ struct zswap_lruvec_state { atomic_long_t nr_zswap_protected; }; +unsigned long zswap_total_pages(void); bool zswap_store(struct folio *folio); bool zswap_load(struct folio *folio); void zswap_invalidate(swp_entry_t swp); diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 627ea8e2d91598..3dee0b2721aa40 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -85,6 +85,9 @@ enum unix_socket_lock_class { U_LOCK_NORMAL, U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ + U_LOCK_GC_LISTENER, /* used for listening socket while determining gc + * candidates to close a small race window. + */ }; static inline void unix_state_lock_nested(struct sock *sk, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 56fb42df44a333..e8f581f3f3ce6d 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/mac80211.h b/include/net/mac80211.h index 353488ab94a294..2d7f87bc5324b4 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 dbd22180cc5c34..de216cbc6b059f 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/netlabel.h b/include/net/netlabel.h index f3ab0b8a4b18ad..c31bd96dafdbac 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -274,15 +274,17 @@ struct netlbl_calipso_ops { * on success, NULL on failure. * */ -static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc(gfp_t flags) +static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc_noprof(gfp_t flags) { struct netlbl_lsm_cache *cache; - cache = kzalloc(sizeof(*cache), flags); + cache = kzalloc_noprof(sizeof(*cache), flags); if (cache) refcount_set(&cache->refcount, 1); return cache; } +#define netlbl_secattr_cache_alloc(...) \ + alloc_hooks(netlbl_secattr_cache_alloc_noprof(__VA_ARGS__)) /** * netlbl_secattr_cache_free - Frees a netlbl_lsm_cache struct @@ -311,10 +313,11 @@ static inline void netlbl_secattr_cache_free(struct netlbl_lsm_cache *cache) * on failure. * */ -static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc(gfp_t flags) +static inline struct netlbl_lsm_catmap *netlbl_catmap_alloc_noprof(gfp_t flags) { - return kzalloc(sizeof(struct netlbl_lsm_catmap), flags); + return kzalloc_noprof(sizeof(struct netlbl_lsm_catmap), flags); } +#define netlbl_catmap_alloc(...) alloc_hooks(netlbl_catmap_alloc_noprof(__VA_ARGS__)) /** * netlbl_catmap_free - Free a LSM secattr catmap @@ -376,10 +379,11 @@ static inline void netlbl_secattr_destroy(struct netlbl_lsm_secattr *secattr) * pointer on success, or NULL on failure. * */ -static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc(gfp_t flags) +static inline struct netlbl_lsm_secattr *netlbl_secattr_alloc_noprof(gfp_t flags) { - return kzalloc(sizeof(struct netlbl_lsm_secattr), flags); + return kzalloc_noprof(sizeof(struct netlbl_lsm_secattr), flags); } +#define netlbl_secattr_alloc(...) alloc_hooks(netlbl_secattr_alloc_noprof(__VA_ARGS__)) /** * netlbl_secattr_free - Frees a netlbl_lsm_secattr struct diff --git a/include/net/netlink.h b/include/net/netlink.h index c19ff921b661ad..972b5484fa6fc4 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -1891,10 +1891,11 @@ static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla) * @src: netlink attribute to duplicate from * @gfp: GFP mask */ -static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp) +static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp) { - return kmemdup(nla_data(src), nla_len(src), gfp); + return kmemdup_noprof(nla_data(src), nla_len(src), gfp); } +#define nla_memdup(...) alloc_hooks(nla_memdup_noprof(__VA_ARGS__)) /** * nla_nest_start_noflag - Start a new level of nested attributes diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 004e651e6067e7..29495c331d20e9 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -127,12 +127,12 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb, } static inline struct request_sock * -reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, +reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) { struct request_sock *req; - req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN); + req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN); if (!req) return NULL; req->rsk_listener = NULL; @@ -157,6 +157,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, return req; } +#define reqsk_alloc(...) alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__)) static inline void __reqsk_free(struct request_sock *req) { diff --git a/include/net/sock.h b/include/net/sock.h index f57bfd8a2ad2de..b4b553df7870c0 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/tcx.h b/include/net/tcx.h index 04be9377785d77..72a3e75e539fb0 100644 --- a/include/net/tcx.h +++ b/include/net/tcx.h @@ -75,9 +75,9 @@ tcx_entry_fetch(struct net_device *dev, bool ingress) return rcu_dereference_rtnl(dev->tcx_egress); } -static inline struct bpf_mprog_entry *tcx_entry_create(void) +static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { - struct tcx_entry *tcx = kzalloc(sizeof(*tcx), GFP_KERNEL); + struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); @@ -85,6 +85,7 @@ static inline struct bpf_mprog_entry *tcx_entry_create(void) } return NULL; } +#define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { diff --git a/include/net/tls.h b/include/net/tls.h index 340ad43971e471..33f657d3c0510a 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/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h index 2e58d5e6ac0e46..d678929441933b 100644 --- a/include/rdma/rdmavt_qp.h +++ b/include/rdma/rdmavt_qp.h @@ -11,6 +11,7 @@ #include <rdma/ib_verbs.h> #include <rdma/rdmavt_cq.h> #include <rdma/rvt-abi.h> +#include <linux/vmalloc.h> /* * Atomic bit definitions for r_aflags. */ diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h index e0629699b56338..1a3c6f66f62055 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -267,6 +267,7 @@ struct cs35l56_base { bool fw_patched; bool secured; bool can_hibernate; + bool fw_owns_asp1; bool cal_data_valid; s8 cal_index; struct cirrus_amp_cal_data cal_data; @@ -283,6 +284,7 @@ extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC]; extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC]; int cs35l56_set_patch(struct cs35l56_base *cs35l56_base); +int cs35l56_init_asp1_regs_for_driver_control(struct cs35l56_base *cs35l56_base); int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base); int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command); int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base); diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h index 1af9e68193920d..234b5baea69c8e 100644 --- a/include/sound/emu10k1.h +++ b/include/sound/emu10k1.h @@ -1684,8 +1684,8 @@ struct snd_emu1010 { unsigned int clock_fallback; unsigned int optical_in; /* 0:SPDIF, 1:ADAT */ unsigned int optical_out; /* 0:SPDIF, 1:ADAT */ - struct work_struct firmware_work; - struct work_struct clock_work; + struct work_struct work; + struct mutex lock; }; struct snd_emu10k1 { @@ -1834,6 +1834,9 @@ unsigned int snd_emu10k1_ptr20_read(struct snd_emu10k1 * emu, unsigned int reg, void snd_emu10k1_ptr20_write(struct snd_emu10k1 *emu, unsigned int reg, unsigned int chn, unsigned int data); int snd_emu10k1_spi_write(struct snd_emu10k1 * emu, unsigned int data); int snd_emu10k1_i2c_write(struct snd_emu10k1 *emu, u32 reg, u32 value); +static inline void snd_emu1010_fpga_lock(struct snd_emu10k1 *emu) { mutex_lock(&emu->emu1010.lock); }; +static inline void snd_emu1010_fpga_unlock(struct snd_emu10k1 *emu) { mutex_unlock(&emu->emu1010.lock); }; +void snd_emu1010_fpga_write_lock(struct snd_emu10k1 *emu, u32 reg, u32 value); void snd_emu1010_fpga_write(struct snd_emu10k1 *emu, u32 reg, u32 value); void snd_emu1010_fpga_read(struct snd_emu10k1 *emu, u32 reg, u32 *value); void snd_emu1010_fpga_link_dst_src_write(struct snd_emu10k1 *emu, u32 dst, u32 src); diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h index 97b09fcf7e5287..86fe6aecff1e79 100644 --- a/include/trace/events/fs_dax.h +++ b/include/trace/events/fs_dax.h @@ -62,14 +62,14 @@ DEFINE_PMD_FAULT_EVENT(dax_pmd_fault_done); DECLARE_EVENT_CLASS(dax_pmd_load_hole_class, TP_PROTO(struct inode *inode, struct vm_fault *vmf, - struct page *zero_page, + struct folio *zero_folio, void *radix_entry), - TP_ARGS(inode, vmf, zero_page, radix_entry), + TP_ARGS(inode, vmf, zero_folio, radix_entry), TP_STRUCT__entry( __field(unsigned long, ino) __field(unsigned long, vm_flags) __field(unsigned long, address) - __field(struct page *, zero_page) + __field(struct folio *, zero_folio) __field(void *, radix_entry) __field(dev_t, dev) ), @@ -78,17 +78,17 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class, __entry->ino = inode->i_ino; __entry->vm_flags = vmf->vma->vm_flags; __entry->address = vmf->address; - __entry->zero_page = zero_page; + __entry->zero_folio = zero_folio; __entry->radix_entry = radix_entry; ), - TP_printk("dev %d:%d ino %#lx %s address %#lx zero_page %p " + TP_printk("dev %d:%d ino %#lx %s address %#lx zero_folio %p " "radix_entry %#lx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->vm_flags & VM_SHARED ? "shared" : "private", __entry->address, - __entry->zero_page, + __entry->zero_folio, (unsigned long)__entry->radix_entry ) ) @@ -96,8 +96,8 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class, #define DEFINE_PMD_LOAD_HOLE_EVENT(name) \ DEFINE_EVENT(dax_pmd_load_hole_class, name, \ TP_PROTO(struct inode *inode, struct vm_fault *vmf, \ - struct page *zero_page, void *radix_entry), \ - TP_ARGS(inode, vmf, zero_page, radix_entry)) + struct folio *zero_folio, void *radix_entry), \ + TP_ARGS(inode, vmf, zero_folio, radix_entry)) DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole); DEFINE_PMD_LOAD_HOLE_EVENT(dax_pmd_load_hole_fallback); diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 6e2ef1d4b0028d..ab576898a1264d 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -174,10 +174,10 @@ TRACE_EVENT(mm_collapse_huge_page_swapin, TRACE_EVENT(mm_khugepaged_scan_file, - TP_PROTO(struct mm_struct *mm, struct page *page, struct file *file, + TP_PROTO(struct mm_struct *mm, struct folio *folio, struct file *file, int present, int swap, int result), - TP_ARGS(mm, page, file, present, swap, result), + TP_ARGS(mm, folio, file, present, swap, result), TP_STRUCT__entry( __field(struct mm_struct *, mm) @@ -190,7 +190,7 @@ TRACE_EVENT(mm_khugepaged_scan_file, TP_fast_assign( __entry->mm = mm; - __entry->pfn = page ? page_to_pfn(page) : -1; + __entry->pfn = folio ? folio_pfn(folio) : -1; __assign_str(filename, file->f_path.dentry->d_iname); __entry->present = present; __entry->swap = swap; @@ -207,10 +207,10 @@ TRACE_EVENT(mm_khugepaged_scan_file, ); TRACE_EVENT(mm_khugepaged_collapse_file, - TP_PROTO(struct mm_struct *mm, struct page *hpage, pgoff_t index, + TP_PROTO(struct mm_struct *mm, struct folio *new_folio, pgoff_t index, bool is_shmem, unsigned long addr, struct file *file, int nr, int result), - TP_ARGS(mm, hpage, index, addr, is_shmem, file, nr, result), + TP_ARGS(mm, new_folio, index, addr, is_shmem, file, nr, result), TP_STRUCT__entry( __field(struct mm_struct *, mm) __field(unsigned long, hpfn) @@ -224,7 +224,7 @@ TRACE_EVENT(mm_khugepaged_collapse_file, TP_fast_assign( __entry->mm = mm; - __entry->hpfn = hpage ? page_to_pfn(hpage) : -1; + __entry->hpfn = new_folio ? folio_pfn(new_folio) : -1; __entry->index = index; __entry->addr = addr; __entry->is_shmem = is_shmem; diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index d801409b33cfec..e46d6e82765e71 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -107,7 +107,6 @@ DEF_PAGEFLAG_NAME(lru), \ DEF_PAGEFLAG_NAME(active), \ DEF_PAGEFLAG_NAME(workingset), \ - DEF_PAGEFLAG_NAME(slab), \ DEF_PAGEFLAG_NAME(owner_priv_1), \ DEF_PAGEFLAG_NAME(arch_1), \ DEF_PAGEFLAG_NAME(reserved), \ @@ -135,6 +134,8 @@ IF_HAVE_PG_ARCH_X(arch_3) #define DEF_PAGETYPE_NAME(_name) { PG_##_name, __stringify(_name) } #define __def_pagetype_names \ + DEF_PAGETYPE_NAME(slab), \ + DEF_PAGETYPE_NAME(hugetlb), \ DEF_PAGETYPE_NAME(offline), \ DEF_PAGETYPE_NAME(guard), \ DEF_PAGETYPE_NAME(table), \ diff --git a/include/trace/events/page_ref.h b/include/trace/events/page_ref.h index 8a99c1cd417b81..fe33a255b7d093 100644 --- a/include/trace/events/page_ref.h +++ b/include/trace/events/page_ref.h @@ -30,7 +30,7 @@ DECLARE_EVENT_CLASS(page_ref_mod_template, __entry->pfn = page_to_pfn(page); __entry->flags = page->flags; __entry->count = page_ref_count(page); - __entry->mapcount = page_mapcount(page); + __entry->mapcount = atomic_read(&page->_mapcount); __entry->mapping = page->mapping; __entry->mt = get_pageblock_migratetype(page); __entry->val = v; @@ -79,7 +79,7 @@ DECLARE_EVENT_CLASS(page_ref_mod_and_test_template, __entry->pfn = page_to_pfn(page); __entry->flags = page->flags; __entry->count = page_ref_count(page); - __entry->mapcount = page_mapcount(page); + __entry->mapcount = atomic_read(&page->_mapcount); __entry->mapping = page->mapping; __entry->mt = get_pageblock_migratetype(page); __entry->val = v; diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 75f00965ab1586..d983c48a3b6af1 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) #define __NR_lsm_list_modules 461 __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) +#define __NR_mseal 462 +__SYSCALL(__NR_mseal, sys_mseal) + #undef __NR_syscalls -#define __NR_syscalls 462 +#define __NR_syscalls 463 /* * 32 bit systems traditionally used different diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h index d87410a8443aae..af024d90453ddc 100644 --- a/include/uapi/drm/etnaviv_drm.h +++ b/include/uapi/drm/etnaviv_drm.h @@ -77,11 +77,6 @@ struct drm_etnaviv_timespec { #define ETNAVIV_PARAM_GPU_PRODUCT_ID 0x1c #define ETNAVIV_PARAM_GPU_CUSTOMER_ID 0x1d #define ETNAVIV_PARAM_GPU_ECO_ID 0x1e -#define ETNAVIV_PARAM_GPU_NN_CORE_COUNT 0x1f -#define ETNAVIV_PARAM_GPU_NN_MAD_PER_CORE 0x20 -#define ETNAVIV_PARAM_GPU_TP_CORE_COUNT 0x21 -#define ETNAVIV_PARAM_GPU_ON_CHIP_SRAM_SIZE 0x22 -#define ETNAVIV_PARAM_GPU_AXI_SRAM_SIZE 0x23 #define ETNA_MAX_PIPES 4 diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 43c51698195ceb..842bf1201ac414 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -57,7 +57,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_FEATURES, /* u64 */ VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ - VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_SIZE_MAX, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, /* u16 */ @@ -70,8 +70,8 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */ - VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, /* u8 */ - VDPA_ATTR_DEV_BLK_CFG_FLUSH, /* u8 */ + VDPA_ATTR_DEV_BLK_READ_ONLY, /* u8 */ + VDPA_ATTR_DEV_BLK_FLUSH, /* u8 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, diff --git a/init/Kconfig b/init/Kconfig index aa02aec6aa7d29..0a021d6b4939ae 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -929,6 +929,9 @@ config NUMA_BALANCING_DEFAULT_ENABLED If set, automatic NUMA balancing will be enabled if running on a NUMA machine. +config SLAB_OBJ_EXT + bool + menuconfig CGROUPS bool "Control Group support" select KERNFS @@ -962,6 +965,7 @@ config MEMCG bool "Memory controller" select PAGE_COUNTER select EVENTFD + select SLAB_OBJ_EXT help Provides control over the memory footprint of tasks in a cgroup. @@ -1899,11 +1903,11 @@ config RUST bool "Rust support" depends on HAVE_RUST depends on RUST_IS_AVAILABLE + depends on !CFI_CLANG depends on !MODVERSIONS depends on !GCC_PLUGINS depends on !RANDSTRUCT depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE - select CONSTRUCTORS help Enables Rust support in the kernel. diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 425f4bcf4b77e0..22c7f41ff6422a 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -29,7 +29,6 @@ static struct ctl_table kern_do_mounts_initrd_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { } }; static __init int kernel_do_mounts_initrd_sysctls_init(void) diff --git a/init/main.c b/init/main.c index 5dcf5274c09c7a..3f956c6beb3d8c 100644 --- a/init/main.c +++ b/init/main.c @@ -327,7 +327,7 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size, { struct xbc_node *knode, *vnode; char *end = buf + size; - const char *val; + const char *val, *q; int ret; xbc_node_for_each_key_value(root, knode, val) { @@ -345,8 +345,14 @@ static int __init xbc_snprint_cmdline(char *buf, size_t size, continue; } xbc_array_for_each_value(vnode, val) { - ret = snprintf(buf, rest(buf, end), "%s=\"%s\" ", - xbc_namebuf, val); + /* + * For prettier and more readable /proc/cmdline, only + * quote the value when necessary, i.e. when it contains + * whitespace. + */ + q = strpbrk(val, " \t\r\n") ? "\"" : ""; + ret = snprintf(buf, rest(buf, end), "%s=%s%s%s ", + xbc_namebuf, q, val, q); if (ret < 0) return ret; buf += ret; @@ -878,6 +884,19 @@ static void __init print_unknown_bootoptions(void) memblock_free(unknown_options, len); } +static void __init early_numa_node_init(void) +{ +#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID +#ifndef cpu_to_node + int cpu; + + /* The early_cpu_to_node() should be ready here. */ + for_each_possible_cpu(cpu) + set_cpu_numa_node(cpu, early_cpu_to_node(cpu)); +#endif +#endif +} + asmlinkage __visible __init __no_sanitize_address __noreturn __no_stack_protector void start_kernel(void) { @@ -908,6 +927,7 @@ void start_kernel(void) setup_nr_cpu_ids(); setup_per_cpu_areas(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + early_numa_node_init(); boot_cpu_hotplug_init(); pr_notice("Kernel command line: %s\n", saved_command_line); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index c170a2b8d2cf21..d5edfb8444d78f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3525,7 +3525,7 @@ static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp, #else addr = 0UL; #endif - return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags); } #else /* !CONFIG_MMU */ diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 45cb1dabce29ae..0867535af96fb0 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -178,7 +178,6 @@ static struct ctl_table ipc_sysctls[] = { .extra2 = SYSCTL_INT_MAX, }, #endif - {} }; static struct ctl_table_set *set_lookup(struct ctl_table_root *root) diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index 21fba3a6edaf7a..22ec532c7fa119 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -64,7 +64,6 @@ static struct ctl_table mq_sysctls[] = { .extra1 = &msg_maxsize_limit_min, .extra2 = &msg_maxsize_limit_max, }, - {} }; static struct ctl_table_set *set_lookup(struct ctl_table_root *root) diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 343c3456c8ddf0..16dbf4f6b77fa5 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -314,7 +314,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad return -EINVAL; } - ret = current->mm->get_unmapped_area(filp, addr, len * 2, 0, flags); + ret = mm_get_unmapped_area(current->mm, filp, addr, len * 2, 0, flags); if (IS_ERR_VALUE(ret)) return ret; if ((ret >> 32) == ((ret + len - 1) >> 32)) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 696bc55de8e82e..1ea5ce5bb59933 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2942,6 +2942,15 @@ bool __weak bpf_jit_supports_arena(void) return false; } +u64 __weak bpf_arch_uaddress_limit(void) +{ +#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) + return TASK_SIZE; +#else + return 0; +#endif +} + /* Return TRUE if the JIT backend satisfies the following two conditions: * 1) JIT backend supports atomic_xchg() on pointer-sized words. * 2) Under the specific arch, the implementation of xchg() is the same diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index 550f02e2cb1327..a546aba46d5da9 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -759,8 +759,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } - if (ma->objcg) - obj_cgroup_put(ma->objcg); + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } if (ma->caches) { @@ -776,8 +775,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } - if (ma->objcg) - obj_cgroup_put(ma->objcg); + obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c287925471f68e..9cb89e875f0d3f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -980,7 +980,7 @@ static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr if (map->ops->map_get_unmapped_area) return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); #ifdef CONFIG_MMU - return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags); #else return addr; #endif diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 98188379d5c77d..cb7ad1f795e18b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18289,8 +18289,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose(env, "fd %d is not pointing to valid bpf_map\n", - insn[0].imm); + verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } @@ -19676,6 +19675,36 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto next_insn; } + /* Make it impossible to de-reference a userspace address */ + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) { + struct bpf_insn *patch = &insn_buf[0]; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + goto next_insn; + + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + if (insn->off) + *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); + *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); + *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); + *patch++ = *insn; + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); + + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; + } + /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || diff --git a/kernel/cpu.c b/kernel/cpu.c index 07ad53b7f11952..63447eb85dab6b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -3196,6 +3196,7 @@ void __init boot_cpu_hotplug_init(void) this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } +#ifdef CONFIG_CPU_MITIGATIONS /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. @@ -3206,9 +3207,7 @@ enum cpu_mitigations { CPU_MITIGATIONS_AUTO_NOSMT, }; -static enum cpu_mitigations cpu_mitigations __ro_after_init = - IS_ENABLED(CONFIG_SPECULATION_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : - CPU_MITIGATIONS_OFF; +static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { @@ -3224,7 +3223,6 @@ static int __init mitigations_parse_cmdline(char *arg) return 0; } -early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) @@ -3239,3 +3237,11 @@ bool cpu_mitigations_auto_nosmt(void) return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); +#else +static int __init mitigations_parse_cmdline(char *arg) +{ + pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); + return 0; +} +#endif +early_param("mitigations", mitigations_parse_cmdline); diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 78b5dc7cee3ab7..1e7ac977f7c0b4 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -4,6 +4,8 @@ * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/buildid.h> #include <linux/init.h> #include <linux/utsname.h> diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index 066668799f7572..5b2722a93a48ca 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -109,7 +109,7 @@ static int __init parse_crashkernel_mem(char *cmdline, size = memparse(cur, &tmp); if (cur == tmp) { - pr_warn("Memory value expected\n"); + pr_warn("crashkernel: Memory value expected\n"); return -EINVAL; } cur = tmp; @@ -132,7 +132,7 @@ static int __init parse_crashkernel_mem(char *cmdline, cur++; *crash_base = memparse(cur, &tmp); if (cur == tmp) { - pr_warn("Memory value expected after '@'\n"); + pr_warn("crahskernel: Memory value expected after '@'\n"); return -EINVAL; } } diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 58db8fd70471a1..5e2d51e1cdf694 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -570,9 +570,9 @@ static struct page *__dma_alloc_pages(struct device *dev, size_t size, size = PAGE_ALIGN(size); if (dma_alloc_direct(dev, ops)) return dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp); - if (!ops->alloc_pages) + if (!ops->alloc_pages_op) return NULL; - return ops->alloc_pages(dev, size, dma_handle, dir, gfp); + return ops->alloc_pages_op(dev, size, dma_handle, dir, gfp); } struct page *dma_alloc_pages(struct device *dev, size_t size, diff --git a/kernel/events/core.c b/kernel/events/core.c index 724e6d7e128f37..c5a0dc1f135f02 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7539,7 +7539,7 @@ static u64 perf_get_pgtable_size(struct mm_struct *mm, unsigned long addr) { u64 size = 0; -#ifdef CONFIG_HAVE_FAST_GUP +#ifdef CONFIG_HAVE_GUP_FAST pgd_t *pgdp, pgd; p4d_t *p4dp, p4d; pud_t *pudp, pud; @@ -7587,7 +7587,7 @@ again: if (pte_present(pte)) size = pte_leaf_size(pte); pte_unmap(ptep); -#endif /* CONFIG_HAVE_FAST_GUP */ +#endif /* CONFIG_HAVE_GUP_FAST */ return size; } diff --git a/kernel/fork.c b/kernel/fork.c index aebb3e6c96dc62..99076dbe27d83f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1344,7 +1344,7 @@ static inline void __mmput(struct mm_struct *mm) ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); - mm_put_huge_zero_page(mm); + mm_put_huge_zero_folio(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index 8a689b4ff4f982..2f84896a7bcbdf 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -82,7 +82,7 @@ static struct test_item test_items[] = { ITEM_FUNC(kallsyms_test_func_static), ITEM_FUNC(kallsyms_test_func), ITEM_FUNC(kallsyms_test_func_weak), - ITEM_FUNC(vmalloc), + ITEM_FUNC(vmalloc_noprof), ITEM_FUNC(vfree), #ifdef CONFIG_KALLSYMS_ALL ITEM_DATA(kallsyms_test_var_bss_static), diff --git a/kernel/kcov.c b/kernel/kcov.c index f9ac2e9e460fc8..c3124f6d5536b7 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -627,7 +627,8 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, mode = kcov_get_mode(remote_arg->trace_mode); if (mode < 0) return mode; - if (remote_arg->area_size > LONG_MAX / sizeof(unsigned long)) + if ((unsigned long)remote_arg->area_size > + LONG_MAX / sizeof(unsigned long)) return -EINVAL; kcov->mode = mode; t->kcov = kcov; diff --git a/kernel/module/main.c b/kernel/module/main.c index e1e8a7a9d6c193..2d25eebc549dbe 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -56,6 +56,7 @@ #include <linux/dynamic_debug.h> #include <linux/audit.h> #include <linux/cfi.h> +#include <linux/codetag.h> #include <linux/debugfs.h> #include <uapi/linux/module.h> #include "internal.h" @@ -1210,15 +1211,19 @@ static void *module_memory_alloc(unsigned int size, enum mod_mem_type type) return module_alloc(size); } -static void module_memory_free(void *ptr, enum mod_mem_type type) +static void module_memory_free(void *ptr, enum mod_mem_type type, + bool unload_codetags) { + if (!unload_codetags && mod_mem_type_is_core_data(type)) + return; + if (mod_mem_use_vmalloc(type)) vfree(ptr); else module_memfree(ptr); } -static void free_mod_mem(struct module *mod) +static void free_mod_mem(struct module *mod, bool unload_codetags) { for_each_mod_mem_type(type) { struct module_memory *mod_mem = &mod->mem[type]; @@ -1229,19 +1234,27 @@ static void free_mod_mem(struct module *mod) /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod_mem->base, mod_mem->size); if (mod_mem->size) - module_memory_free(mod_mem->base, type); + module_memory_free(mod_mem->base, type, + unload_codetags); } /* MOD_DATA hosts mod, so free it at last */ lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size); - module_memory_free(mod->mem[MOD_DATA].base, MOD_DATA); + module_memory_free(mod->mem[MOD_DATA].base, MOD_DATA, unload_codetags); } /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { + bool unload_codetags; + trace_module_free(mod); + unload_codetags = codetag_unload_module(mod); + if (!unload_codetags) + pr_warn("%s: memory allocation(s) from the module still alive, cannot unload cleanly\n", + mod->name); + mod_sysfs_teardown(mod); /* @@ -1283,7 +1296,7 @@ static void free_module(struct module *mod) kfree(mod->args); percpu_modfree(mod); - free_mod_mem(mod); + free_mod_mem(mod, unload_codetags); } void *__symbol_get(const char *symbol) @@ -2296,7 +2309,7 @@ static int move_module(struct module *mod, struct load_info *info) return 0; out_enomem: for (t--; t >= 0; t--) - module_memory_free(mod->mem[t].base, t); + module_memory_free(mod->mem[t].base, t, true); return ret; } @@ -2426,7 +2439,7 @@ static void module_deallocate(struct module *mod, struct load_info *info) percpu_modfree(mod); module_arch_freeing_init(mod); - free_mod_mem(mod); + free_mod_mem(mod, true); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -2995,6 +3008,8 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Get rid of temporary copy. */ free_copy(info, flags); + codetag_load_module(mod); + /* Done! */ trace_module_load(mod); diff --git a/kernel/profile.c b/kernel/profile.c index 8a77769bc4b4cb..2b775cc5c28f96 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -344,49 +344,6 @@ void profile_tick(int type) #include <linux/seq_file.h> #include <linux/uaccess.h> -static int prof_cpu_mask_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%*pb\n", cpumask_pr_args(prof_cpu_mask)); - return 0; -} - -static int prof_cpu_mask_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, prof_cpu_mask_proc_show, NULL); -} - -static ssize_t prof_cpu_mask_proc_write(struct file *file, - const char __user *buffer, size_t count, loff_t *pos) -{ - cpumask_var_t new_value; - int err; - - if (!zalloc_cpumask_var(&new_value, GFP_KERNEL)) - return -ENOMEM; - - err = cpumask_parse_user(buffer, count, new_value); - if (!err) { - cpumask_copy(prof_cpu_mask, new_value); - err = count; - } - free_cpumask_var(new_value); - return err; -} - -static const struct proc_ops prof_cpu_mask_proc_ops = { - .proc_open = prof_cpu_mask_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = single_release, - .proc_write = prof_cpu_mask_proc_write, -}; - -void create_prof_cpu_mask(void) -{ - /* create /proc/irq/prof_cpu_mask */ - proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops); -} - /* * This function accesses profiling information. The returned data is * binary: the sampling step and the actual contents of the profile diff --git a/kernel/regset.c b/kernel/regset.c index 586823786f397f..b2871fa68b2a7f 100644 --- a/kernel/regset.c +++ b/kernel/regset.c @@ -16,14 +16,14 @@ static int __regset_get(struct task_struct *target, if (size > regset->n * regset->size) size = regset->n * regset->size; if (!p) { - to_free = p = kzalloc(size, GFP_KERNEL); + to_free = p = kvzalloc(size, GFP_KERNEL); if (!p) return -ENOMEM; } res = regset->regset_get(target, regset, (struct membuf){.p = p, .left = size}); if (res < 0) { - kfree(to_free); + kvfree(to_free); return res; } *data = p; @@ -71,6 +71,6 @@ int copy_regset_to_user(struct task_struct *target, ret = regset_get_alloc(target, regset, size, &buf); if (ret > 0) ret = copy_to_user(data, buf, ret) ? -EFAULT : 0; - kfree(buf); + kvfree(buf); return ret; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 03be0d1330a6b2..c62805dbd6088b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -696,15 +696,21 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * * XXX could add max_slice to the augmented data to track this. */ -static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) +static s64 entity_lag(u64 avruntime, struct sched_entity *se) { - s64 lag, limit; + s64 vlag, limit; + + vlag = avruntime - se->vruntime; + limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); + return clamp(vlag, -limit, limit); +} + +static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ SCHED_WARN_ON(!se->on_rq); - lag = avg_vruntime(cfs_rq) - se->vruntime; - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); - se->vlag = clamp(lag, -limit, limit); + se->vlag = entity_lag(avg_vruntime(cfs_rq), se); } /* @@ -3676,11 +3682,10 @@ static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif -static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, +static void reweight_eevdf(struct sched_entity *se, u64 avruntime, unsigned long weight) { unsigned long old_weight = se->load.weight; - u64 avruntime = avg_vruntime(cfs_rq); s64 vlag, vslice; /* @@ -3761,7 +3766,7 @@ static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, * = V - vl' */ if (avruntime != se->vruntime) { - vlag = (s64)(avruntime - se->vruntime); + vlag = entity_lag(avruntime, se); vlag = div_s64(vlag * old_weight, weight); se->vruntime = avruntime - vlag; } @@ -3787,25 +3792,26 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { bool curr = cfs_rq->curr == se; + u64 avruntime; if (se->on_rq) { /* commit outstanding execution time */ - if (curr) - update_curr(cfs_rq); - else + update_curr(cfs_rq); + avruntime = avg_vruntime(cfs_rq); + if (!curr) __dequeue_entity(cfs_rq, se); update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); - if (!se->on_rq) { + if (se->on_rq) { + reweight_eevdf(se, avruntime, weight); + } else { /* * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), * we need to scale se->vlag when w_i changes. */ se->vlag = div_s64(se->vlag * se->load.weight, weight); - } else { - reweight_eevdf(cfs_rq, se, weight); } update_load_set(&se->load, weight); diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 373d42c707bc5d..5891e715f00d02 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -46,7 +46,16 @@ int housekeeping_any_cpu(enum hk_type type) if (cpu < nr_cpu_ids) return cpu; - return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask); + cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask); + if (likely(cpu < nr_cpu_ids)) + return cpu; + /* + * Unless we have another problem this can only happen + * at boot time before start_secondary() brings the 1st + * housekeeping CPU up. + */ + WARN_ON_ONCE(system_state == SYSTEM_RUNNING || + type != HK_TYPE_TIMER); } } return smp_processor_id(); @@ -109,6 +118,7 @@ static void __init housekeeping_setup_type(enum hk_type type, static int __init housekeeping_setup(char *str, unsigned long flags) { cpumask_var_t non_housekeeping_mask, housekeeping_staging; + unsigned int first_cpu; int err = 0; if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) { @@ -129,7 +139,8 @@ static int __init housekeeping_setup(char *str, unsigned long flags) cpumask_andnot(housekeeping_staging, cpu_possible_mask, non_housekeeping_mask); - if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) { + first_cpu = cpumask_first_and(cpu_present_mask, housekeeping_staging); + if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) { __cpumask_set_cpu(smp_processor_id(), housekeeping_staging); __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); if (!housekeeping.flags) { @@ -138,6 +149,9 @@ static int __init housekeeping_setup(char *str, unsigned long flags) } } + if (cpumask_empty(non_housekeeping_mask)) + goto free_housekeeping_staging; + if (!housekeeping.flags) { /* First setup call ("nohz_full=" or "isolcpus=") */ enum hk_type type; diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index faad00cce269c3..d7eee421d4bc33 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -196,6 +196,7 @@ COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); COND_SYSCALL(set_mempolicy_home_node); COND_SYSCALL(cachestat); +COND_SYSCALL(mseal); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index d5d94510afd3f8..8fd292d34d8984 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -524,8 +524,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, if (!buts->buf_size || !buts->buf_nr) return -EINVAL; - strncpy(buts->name, name, BLKTRACE_BDEV_SIZE); - buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0'; + strscpy_pad(buts->name, name, BLKTRACE_BDEV_SIZE); /* * some device names have larger paths - convert the slashes diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index f95516cd45bbe2..1d5eadd9dd61cd 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -198,18 +198,18 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PG_private); VMCOREINFO_NUMBER(PG_swapcache); VMCOREINFO_NUMBER(PG_swapbacked); - VMCOREINFO_NUMBER(PG_slab); +#define PAGE_SLAB_MAPCOUNT_VALUE (~PG_slab) + VMCOREINFO_NUMBER(PAGE_SLAB_MAPCOUNT_VALUE); #ifdef CONFIG_MEMORY_FAILURE VMCOREINFO_NUMBER(PG_hwpoison); #endif VMCOREINFO_NUMBER(PG_head_mask); #define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(PG_hugetlb); +#define PAGE_HUGETLB_MAPCOUNT_VALUE (~PG_hugetlb) + VMCOREINFO_NUMBER(PAGE_HUGETLB_MAPCOUNT_VALUE); #define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); -#endif #ifdef CONFIG_KALLSYMS VMCOREINFO_SYMBOL(kallsyms_names); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c63a5fbf1f1c2b..c4b6b77f36bf81 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -375,7 +375,7 @@ config DEBUG_INFO_SPLIT Incompatible with older versions of ccache. config DEBUG_INFO_BTF - bool "Generate BTF typeinfo" + bool "Generate BTF type information" depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST depends on BPF_SYSCALL @@ -408,7 +408,8 @@ config PAHOLE_HAS_LANG_EXCLUDE using DEBUG_INFO_BTF_MODULES. config DEBUG_INFO_BTF_MODULES - def_bool y + bool "Generate BTF type information for kernel modules" + default y depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF help Generate compact split BTF type information for kernel modules. @@ -968,6 +969,37 @@ config DEBUG_STACKOVERFLOW If in doubt, say "N". +config CODE_TAGGING + bool + select KALLSYMS + +config MEM_ALLOC_PROFILING + bool "Enable memory allocation profiling" + default n + depends on PROC_FS + depends on !DEBUG_FORCE_WEAK_PER_CPU + select CODE_TAGGING + select PAGE_EXTENSION + select SLAB_OBJ_EXT + help + Track allocation source code and record total allocation size + initiated at that code location. The mechanism can be used to track + memory leaks with a low performance and memory impact. + +config MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT + bool "Enable memory allocation profiling by default" + default y + depends on MEM_ALLOC_PROFILING + +config MEM_ALLOC_PROFILING_DEBUG + bool "Memory allocation profiler debugging" + default n + depends on MEM_ALLOC_PROFILING + select MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT + help + Adds warnings with helpful error messages for memory allocation + profiling. + source "lib/Kconfig.kasan" source "lib/Kconfig.kfence" source "lib/Kconfig.kmsan" @@ -2890,7 +2922,7 @@ config TEST_FREE_PAGES config TEST_FPU tristate "Test floating point operations in kernel space" - depends on X86 && !KCOV_INSTRUMENT_ALL + depends on ARCH_HAS_KERNEL_FPU_SUPPORT && !KCOV_INSTRUMENT_ALL help Enable this option to add /sys/kernel/debug/selftest_helpers/test_fpu which will trigger a sequence of floating point operations. This is used diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index b5c0e6576749dc..537e1b3f57340c 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -122,6 +122,7 @@ config KDB_DEFAULT_ENABLE config KDB_KEYBOARD bool "KGDB_KDB: keyboard as input device" depends on VT && KGDB_KDB && !PARISC + depends on HAS_IOPORT default n help KDB can use a PS/2 type keyboard for an input device diff --git a/lib/Makefile b/lib/Makefile index ffc6b2341b45a5..1f6c51420bf6b3 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -110,30 +110,10 @@ CFLAGS_test_fprobe.o += $(CC_FLAGS_FTRACE) obj-$(CONFIG_FPROBE_SANITY_TEST) += test_fprobe.o obj-$(CONFIG_TEST_OBJPOOL) += test_objpool.o -# -# CFLAGS for compiling floating point code inside the kernel. x86/Makefile turns -# off the generation of FPU/SSE* instructions for kernel proper but FPU_FLAGS -# get appended last to CFLAGS and thus override those previous compiler options. -# -FPU_CFLAGS := -msse -msse2 -ifdef CONFIG_CC_IS_GCC -# Stack alignment mismatch, proceed with caution. -# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 -# (8B stack alignment). -# See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 -# -# The "-msse" in the first argument is there so that the -# -mpreferred-stack-boundary=3 build error: -# -# -mpreferred-stack-boundary=3 is not between 4 and 12 -# -# can be triggered. Otherwise gcc doesn't complain. -FPU_CFLAGS += -mhard-float -FPU_CFLAGS += $(call cc-option,-msse -mpreferred-stack-boundary=3,-mpreferred-stack-boundary=4) -endif - obj-$(CONFIG_TEST_FPU) += test_fpu.o -CFLAGS_test_fpu.o += $(FPU_CFLAGS) +test_fpu-y := test_fpu_glue.o test_fpu_impl.o +CFLAGS_test_fpu_impl.o += $(CC_FLAGS_FPU) +CFLAGS_REMOVE_test_fpu_impl.o += $(CC_FLAGS_NO_FPU) # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module, # so we can't just use obj-$(CONFIG_KUNIT). @@ -233,6 +213,9 @@ obj-$(CONFIG_OF_RECONFIG_NOTIFIER_ERROR_INJECT) += \ of-reconfig-notifier-error-inject.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +obj-$(CONFIG_CODE_TAGGING) += codetag.o +obj-$(CONFIG_MEM_ALLOC_PROFILING) += alloc_tag.o + lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c new file mode 100644 index 00000000000000..531dbe2f545635 --- /dev/null +++ b/lib/alloc_tag.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/alloc_tag.h> +#include <linux/fs.h> +#include <linux/gfp.h> +#include <linux/module.h> +#include <linux/page_ext.h> +#include <linux/proc_fs.h> +#include <linux/seq_buf.h> +#include <linux/seq_file.h> + +static struct codetag_type *alloc_tag_cttype; + +DEFINE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); +EXPORT_SYMBOL(_shared_alloc_tag); + +DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + mem_alloc_profiling_key); + +static void *allocinfo_start(struct seq_file *m, loff_t *pos) +{ + struct codetag_iterator *iter; + struct codetag *ct; + loff_t node = *pos; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + m->private = iter; + if (!iter) + return NULL; + + codetag_lock_module_list(alloc_tag_cttype, true); + *iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(iter)) != NULL && node) + node--; + + return ct ? iter : NULL; +} + +static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)arg; + struct codetag *ct = codetag_next_ct(iter); + + (*pos)++; + if (!ct) + return NULL; + + return iter; +} + +static void allocinfo_stop(struct seq_file *m, void *arg) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)m->private; + + if (iter) { + codetag_lock_module_list(alloc_tag_cttype, false); + kfree(iter); + } +} + +static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) +{ + struct alloc_tag *tag = ct_to_alloc_tag(ct); + struct alloc_tag_counters counter = alloc_tag_read(tag); + s64 bytes = counter.bytes; + + seq_buf_printf(out, "%12lli %8llu ", bytes, counter.calls); + codetag_to_text(out, ct); + seq_buf_putc(out, ' '); + seq_buf_putc(out, '\n'); +} + +static int allocinfo_show(struct seq_file *m, void *arg) +{ + struct codetag_iterator *iter = (struct codetag_iterator *)arg; + char *bufp; + size_t n = seq_get_buf(m, &bufp); + struct seq_buf buf; + + seq_buf_init(&buf, bufp, n); + alloc_tag_to_text(&buf, iter->ct); + seq_commit(m, seq_buf_used(&buf)); + return 0; +} + +static const struct seq_operations allocinfo_seq_op = { + .start = allocinfo_start, + .next = allocinfo_next, + .stop = allocinfo_stop, + .show = allocinfo_show, +}; + +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep) +{ + struct codetag_iterator iter; + struct codetag *ct; + struct codetag_bytes n; + unsigned int i, nr = 0; + + if (can_sleep) + codetag_lock_module_list(alloc_tag_cttype, true); + else if (!codetag_trylock_module_list(alloc_tag_cttype)) + return 0; + + iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(&iter))) { + struct alloc_tag_counters counter = alloc_tag_read(ct_to_alloc_tag(ct)); + + n.ct = ct; + n.bytes = counter.bytes; + + for (i = 0; i < nr; i++) + if (n.bytes > tags[i].bytes) + break; + + if (i < count) { + nr -= nr == count; + memmove(&tags[i + 1], + &tags[i], + sizeof(tags[0]) * (nr - i)); + nr++; + tags[i] = n; + } + } + + codetag_lock_module_list(alloc_tag_cttype, false); + + return nr; +} + +static void __init procfs_init(void) +{ + proc_create_seq("allocinfo", 0400, NULL, &allocinfo_seq_op); +} + +static bool alloc_tag_module_unload(struct codetag_type *cttype, + struct codetag_module *cmod) +{ + struct codetag_iterator iter = codetag_get_ct_iter(cttype); + struct alloc_tag_counters counter; + bool module_unused = true; + struct alloc_tag *tag; + struct codetag *ct; + + for (ct = codetag_next_ct(&iter); ct; ct = codetag_next_ct(&iter)) { + if (iter.cmod != cmod) + continue; + + tag = ct_to_alloc_tag(ct); + counter = alloc_tag_read(tag); + + if (WARN(counter.bytes, + "%s:%u module %s func:%s has %llu allocated at module unload", + ct->filename, ct->lineno, ct->modname, ct->function, counter.bytes)) + module_unused = false; + } + + return module_unused; +} + +#ifdef CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT +static bool mem_profiling_support __meminitdata = true; +#else +static bool mem_profiling_support __meminitdata; +#endif + +static int __init setup_early_mem_profiling(char *str) +{ + bool enable; + + if (!str || !str[0]) + return -EINVAL; + + if (!strncmp(str, "never", 5)) { + enable = false; + mem_profiling_support = false; + } else { + int res; + + res = kstrtobool(str, &enable); + if (res) + return res; + + mem_profiling_support = true; + } + + if (enable != static_key_enabled(&mem_alloc_profiling_key)) { + if (enable) + static_branch_enable(&mem_alloc_profiling_key); + else + static_branch_disable(&mem_alloc_profiling_key); + } + + return 0; +} +early_param("sysctl.vm.mem_profiling", setup_early_mem_profiling); + +static __init bool need_page_alloc_tagging(void) +{ + return mem_profiling_support; +} + +static __init void init_page_alloc_tagging(void) +{ +} + +struct page_ext_operations page_alloc_tagging_ops = { + .size = sizeof(union codetag_ref), + .need = need_page_alloc_tagging, + .init = init_page_alloc_tagging, +}; +EXPORT_SYMBOL(page_alloc_tagging_ops); + +static struct ctl_table memory_allocation_profiling_sysctls[] = { + { + .procname = "mem_profiling", + .data = &mem_alloc_profiling_key, +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + .mode = 0444, +#else + .mode = 0644, +#endif + .proc_handler = proc_do_static_key, + }, + { } +}; + +static int __init alloc_tag_init(void) +{ + const struct codetag_type_desc desc = { + .section = "alloc_tags", + .tag_size = sizeof(struct alloc_tag), + .module_unload = alloc_tag_module_unload, + }; + + alloc_tag_cttype = codetag_register_type(&desc); + if (IS_ERR(alloc_tag_cttype)) + return PTR_ERR(alloc_tag_cttype); + + if (!mem_profiling_support) + memory_allocation_profiling_sysctls[0].mode = 0444; + register_sysctl_init("vm", memory_allocation_profiling_sysctls); + procfs_init(); + + return 0; +} +module_init(alloc_tag_init); diff --git a/lib/build_OID_registry b/lib/build_OID_registry index d7fc32ea8ac224..56d8bafeb848b0 100755 --- a/lib/build_OID_registry +++ b/lib/build_OID_registry @@ -8,6 +8,7 @@ # use strict; +use Cwd qw(abs_path); my @names = (); my @oids = (); @@ -17,6 +18,8 @@ if ($#ARGV != 1) { exit(2); } +my $abs_srctree = abs_path($ENV{'srctree'}); + # # Open the file to read from # @@ -35,7 +38,7 @@ close IN_FILE || die; # open C_FILE, ">$ARGV[1]" or die; print C_FILE "/*\n"; -print C_FILE " * Automatically generated by ", $0, ". Do not edit\n"; +print C_FILE " * Automatically generated by ", $0 =~ s#^\Q$abs_srctree/\E##r, ". Do not edit\n"; print C_FILE " */\n"; # diff --git a/lib/codetag.c b/lib/codetag.c new file mode 100644 index 00000000000000..5ace625f2328f2 --- /dev/null +++ b/lib/codetag.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/codetag.h> +#include <linux/idr.h> +#include <linux/kallsyms.h> +#include <linux/module.h> +#include <linux/seq_buf.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +struct codetag_type { + struct list_head link; + unsigned int count; + struct idr mod_idr; + struct rw_semaphore mod_lock; /* protects mod_idr */ + struct codetag_type_desc desc; +}; + +struct codetag_range { + struct codetag *start; + struct codetag *stop; +}; + +struct codetag_module { + struct module *mod; + struct codetag_range range; +}; + +static DEFINE_MUTEX(codetag_lock); +static LIST_HEAD(codetag_types); + +void codetag_lock_module_list(struct codetag_type *cttype, bool lock) +{ + if (lock) + down_read(&cttype->mod_lock); + else + up_read(&cttype->mod_lock); +} + +bool codetag_trylock_module_list(struct codetag_type *cttype) +{ + return down_read_trylock(&cttype->mod_lock) != 0; +} + +struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype) +{ + struct codetag_iterator iter = { + .cttype = cttype, + .cmod = NULL, + .mod_id = 0, + .ct = NULL, + }; + + return iter; +} + +static inline struct codetag *get_first_module_ct(struct codetag_module *cmod) +{ + return cmod->range.start < cmod->range.stop ? cmod->range.start : NULL; +} + +static inline +struct codetag *get_next_module_ct(struct codetag_iterator *iter) +{ + struct codetag *res = (struct codetag *) + ((char *)iter->ct + iter->cttype->desc.tag_size); + + return res < iter->cmod->range.stop ? res : NULL; +} + +struct codetag *codetag_next_ct(struct codetag_iterator *iter) +{ + struct codetag_type *cttype = iter->cttype; + struct codetag_module *cmod; + struct codetag *ct; + + lockdep_assert_held(&cttype->mod_lock); + + if (unlikely(idr_is_empty(&cttype->mod_idr))) + return NULL; + + ct = NULL; + while (true) { + cmod = idr_find(&cttype->mod_idr, iter->mod_id); + + /* If module was removed move to the next one */ + if (!cmod) + cmod = idr_get_next_ul(&cttype->mod_idr, + &iter->mod_id); + + /* Exit if no more modules */ + if (!cmod) + break; + + if (cmod != iter->cmod) { + iter->cmod = cmod; + ct = get_first_module_ct(cmod); + } else + ct = get_next_module_ct(iter); + + if (ct) + break; + + iter->mod_id++; + } + + iter->ct = ct; + return ct; +} + +void codetag_to_text(struct seq_buf *out, struct codetag *ct) +{ + if (ct->modname) + seq_buf_printf(out, "%s:%u [%s] func:%s", + ct->filename, ct->lineno, + ct->modname, ct->function); + else + seq_buf_printf(out, "%s:%u func:%s", + ct->filename, ct->lineno, ct->function); +} + +static inline size_t range_size(const struct codetag_type *cttype, + const struct codetag_range *range) +{ + return ((char *)range->stop - (char *)range->start) / + cttype->desc.tag_size; +} + +#ifdef CONFIG_MODULES +static void *get_symbol(struct module *mod, const char *prefix, const char *name) +{ + DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN); + const char *buf; + void *ret; + + seq_buf_printf(&sb, "%s%s", prefix, name); + if (seq_buf_has_overflowed(&sb)) + return NULL; + + buf = seq_buf_str(&sb); + preempt_disable(); + ret = mod ? + (void *)find_kallsyms_symbol_value(mod, buf) : + (void *)kallsyms_lookup_name(buf); + preempt_enable(); + + return ret; +} + +static struct codetag_range get_section_range(struct module *mod, + const char *section) +{ + return (struct codetag_range) { + get_symbol(mod, "__start_", section), + get_symbol(mod, "__stop_", section), + }; +} + +static int codetag_module_init(struct codetag_type *cttype, struct module *mod) +{ + struct codetag_range range; + struct codetag_module *cmod; + int err; + + range = get_section_range(mod, cttype->desc.section); + if (!range.start || !range.stop) { + pr_warn("Failed to load code tags of type %s from the module %s\n", + cttype->desc.section, + mod ? mod->name : "(built-in)"); + return -EINVAL; + } + + /* Ignore empty ranges */ + if (range.start == range.stop) + return 0; + + BUG_ON(range.start > range.stop); + + cmod = kmalloc(sizeof(*cmod), GFP_KERNEL); + if (unlikely(!cmod)) + return -ENOMEM; + + cmod->mod = mod; + cmod->range = range; + + down_write(&cttype->mod_lock); + err = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL); + if (err >= 0) { + cttype->count += range_size(cttype, &range); + if (cttype->desc.module_load) + cttype->desc.module_load(cttype, cmod); + } + up_write(&cttype->mod_lock); + + if (err < 0) { + kfree(cmod); + return err; + } + + return 0; +} + +void codetag_load_module(struct module *mod) +{ + struct codetag_type *cttype; + + if (!mod) + return; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) + codetag_module_init(cttype, mod); + mutex_unlock(&codetag_lock); +} + +bool codetag_unload_module(struct module *mod) +{ + struct codetag_type *cttype; + bool unload_ok = true; + + if (!mod) + return true; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + struct codetag_module *found = NULL; + struct codetag_module *cmod; + unsigned long mod_id, tmp; + + down_write(&cttype->mod_lock); + idr_for_each_entry_ul(&cttype->mod_idr, cmod, tmp, mod_id) { + if (cmod->mod && cmod->mod == mod) { + found = cmod; + break; + } + } + if (found) { + if (cttype->desc.module_unload) + if (!cttype->desc.module_unload(cttype, cmod)) + unload_ok = false; + + cttype->count -= range_size(cttype, &cmod->range); + idr_remove(&cttype->mod_idr, mod_id); + kfree(cmod); + } + up_write(&cttype->mod_lock); + } + mutex_unlock(&codetag_lock); + + return unload_ok; +} + +#else /* CONFIG_MODULES */ +static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { return 0; } +#endif /* CONFIG_MODULES */ + +struct codetag_type * +codetag_register_type(const struct codetag_type_desc *desc) +{ + struct codetag_type *cttype; + int err; + + BUG_ON(desc->tag_size <= 0); + + cttype = kzalloc(sizeof(*cttype), GFP_KERNEL); + if (unlikely(!cttype)) + return ERR_PTR(-ENOMEM); + + cttype->desc = *desc; + idr_init(&cttype->mod_idr); + init_rwsem(&cttype->mod_lock); + + err = codetag_module_init(cttype, NULL); + if (unlikely(err)) { + kfree(cttype); + return ERR_PTR(err); + } + + mutex_lock(&codetag_lock); + list_add_tail(&cttype->link, &codetag_types); + mutex_unlock(&codetag_lock); + + return cttype; +} diff --git a/lib/devres.c b/lib/devres.c index fe0c63caeb6892..4fc152de6d8bb1 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/bug.h> #include <linux/device.h> -#include <linux/err.h> -#include <linux/io.h> -#include <linux/gfp.h> +#include <linux/errno.h> #include <linux/export.h> +#include <linux/gfp_types.h> +#include <linux/io.h> +#include <linux/ioport.h> #include <linux/of_address.h> +#include <linux/types.h> enum devm_ioremap_type { DEVM_IOREMAP = 0, @@ -125,12 +128,13 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res, resource_size_t size; void __iomem *dest_ptr; char *pretty_name; + int ret; BUG_ON(!dev); if (!res || resource_type(res) != IORESOURCE_MEM) { - dev_err(dev, "invalid resource %pR\n", res); - return IOMEM_ERR_PTR(-EINVAL); + ret = dev_err_probe(dev, -EINVAL, "invalid resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } if (type == DEVM_IOREMAP && res->flags & IORESOURCE_MEM_NONPOSTED) @@ -144,20 +148,20 @@ __devm_ioremap_resource(struct device *dev, const struct resource *res, else pretty_name = devm_kstrdup(dev, dev_name(dev), GFP_KERNEL); if (!pretty_name) { - dev_err(dev, "can't generate pretty name for resource %pR\n", res); - return IOMEM_ERR_PTR(-ENOMEM); + ret = dev_err_probe(dev, -ENOMEM, "can't generate pretty name for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } if (!devm_request_mem_region(dev, res->start, size, pretty_name)) { - dev_err(dev, "can't request region for resource %pR\n", res); - return IOMEM_ERR_PTR(-EBUSY); + ret = dev_err_probe(dev, -EBUSY, "can't request region for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } dest_ptr = __devm_ioremap(dev, res->start, size, type); if (!dest_ptr) { - dev_err(dev, "ioremap failed for resource %pR\n", res); devm_release_mem_region(dev, res->start, size); - dest_ptr = IOMEM_ERR_PTR(-ENOMEM); + ret = dev_err_probe(dev, -ENOMEM, "ioremap failed for resource %pR\n", res); + return IOMEM_ERR_PTR(ret); } return dest_ptr; diff --git a/lib/kfifo.c b/lib/kfifo.c index 12f5a347aa1370..15acdee4a8f325 100644 --- a/lib/kfifo.c +++ b/lib/kfifo.c @@ -5,13 +5,13 @@ * Copyright (C) 2009/2010 Stefani Seibold <stefani@seibold.net> */ -#include <linux/kernel.h> -#include <linux/export.h> -#include <linux/slab.h> #include <linux/err.h> +#include <linux/export.h> +#include <linux/kfifo.h> #include <linux/log2.h> +#include <linux/scatterlist.h> +#include <linux/slab.h> #include <linux/uaccess.h> -#include <linux/kfifo.h> /* * internal helper to calculate the unused elements in a fifo diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 55e1b35bf877ea..2d7d27e6ae3c69 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5109,18 +5109,18 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, if (size == 0 || max - min < size - 1) return -EINVAL; - if (mas_is_start(mas)) { + if (mas_is_start(mas)) mas_start(mas); - mas->offset = mas_data_end(mas); - } else if (mas->offset >= 2) { - mas->offset -= 2; - } else if (!mas_rewind_node(mas)) { + else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; - } - /* Empty set. */ - if (mas_is_none(mas) || mas_is_ptr(mas)) + if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); + else if (mas->offset >= 2) + mas->offset -= 2; + else + mas->offset = mas_data_end(mas); + /* The start of the window can only be within these values. */ mas->index = min; diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile index 385a94aa0b999b..0e88bfe6445bfb 100644 --- a/lib/raid6/Makefile +++ b/lib/raid6/Makefile @@ -33,25 +33,6 @@ CFLAGS_REMOVE_vpermxor8.o += -msoft-float endif endif -# The GCC option -ffreestanding is required in order to compile code containing -# ARM/NEON intrinsics in a non C99-compliant environment (such as the kernel) -ifeq ($(CONFIG_KERNEL_MODE_NEON),y) -NEON_FLAGS := -ffreestanding -# Enable <arm_neon.h> -NEON_FLAGS += -isystem $(shell $(CC) -print-file-name=include) -ifeq ($(ARCH),arm) -NEON_FLAGS += -march=armv7-a -mfloat-abi=softfp -mfpu=neon -endif -CFLAGS_recov_neon_inner.o += $(NEON_FLAGS) -ifeq ($(ARCH),arm64) -CFLAGS_REMOVE_recov_neon_inner.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon2.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon4.o += -mgeneral-regs-only -CFLAGS_REMOVE_neon8.o += -mgeneral-regs-only -endif -endif - quiet_cmd_unroll = UNROLL $@ cmd_unroll = $(AWK) -v N=$* -f $(srctree)/$(src)/unroll.awk < $< > $@ @@ -75,10 +56,16 @@ targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c $(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) -CFLAGS_neon1.o += $(NEON_FLAGS) -CFLAGS_neon2.o += $(NEON_FLAGS) -CFLAGS_neon4.o += $(NEON_FLAGS) -CFLAGS_neon8.o += $(NEON_FLAGS) +CFLAGS_neon1.o += $(CC_FLAGS_FPU) +CFLAGS_neon2.o += $(CC_FLAGS_FPU) +CFLAGS_neon4.o += $(CC_FLAGS_FPU) +CFLAGS_neon8.o += $(CC_FLAGS_FPU) +CFLAGS_recov_neon_inner.o += $(CC_FLAGS_FPU) +CFLAGS_REMOVE_neon1.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon2.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon4.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_neon8.o += $(CC_FLAGS_NO_FPU) +CFLAGS_REMOVE_recov_neon_inner.o += $(CC_FLAGS_NO_FPU) targets += neon1.c neon2.c neon4.c neon8.c $(obj)/neon%.c: $(src)/neon.uc $(src)/unroll.awk FORCE $(call if_changed,unroll) diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 6ae2ba8e06a213..dbbed19f8fff99 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -130,7 +130,8 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht, if (ntbl) return ntbl; - ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC); + ntbl = alloc_hooks_tag(ht->alloc_tag, + kmalloc_noprof(PAGE_SIZE, GFP_ATOMIC|__GFP_ZERO)); if (ntbl && leaf) { for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++) @@ -157,7 +158,8 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht, size = sizeof(*tbl) + sizeof(tbl->buckets[0]); - tbl = kzalloc(size, gfp); + tbl = alloc_hooks_tag(ht->alloc_tag, + kmalloc_noprof(size, gfp|__GFP_ZERO)); if (!tbl) return NULL; @@ -181,7 +183,9 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, int i; static struct lock_class_key __key; - tbl = kvzalloc(struct_size(tbl, buckets, nbuckets), gfp); + tbl = alloc_hooks_tag(ht->alloc_tag, + kvmalloc_node_noprof(struct_size(tbl, buckets, nbuckets), + gfp|__GFP_ZERO, NUMA_NO_NODE)); size = nbuckets; @@ -1016,7 +1020,7 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) * .obj_hashfn = my_hash_fn, * }; */ -int rhashtable_init(struct rhashtable *ht, +int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params) { struct bucket_table *tbl; @@ -1031,6 +1035,8 @@ int rhashtable_init(struct rhashtable *ht, spin_lock_init(&ht->lock); memcpy(&ht->p, params, sizeof(*params)); + alloc_tag_record(ht->alloc_tag); + if (params->min_size) ht->p.min_size = roundup_pow_of_two(params->min_size); @@ -1076,7 +1082,7 @@ int rhashtable_init(struct rhashtable *ht, return 0; } -EXPORT_SYMBOL_GPL(rhashtable_init); +EXPORT_SYMBOL_GPL(rhashtable_init_noprof); /** * rhltable_init - initialize a new hash list table @@ -1087,15 +1093,15 @@ EXPORT_SYMBOL_GPL(rhashtable_init); * * See documentation for rhashtable_init. */ -int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params) +int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params) { int err; - err = rhashtable_init(&hlt->ht, params); + err = rhashtable_init_noprof(&hlt->ht, params); hlt->ht.rhlist = true; return err; } -EXPORT_SYMBOL_GPL(rhltable_init); +EXPORT_SYMBOL_GPL(rhltable_init_noprof); static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj, void (*free_fn)(void *ptr, void *arg), diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 68b45c82c37a69..7bc2220fea8058 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -1124,7 +1124,7 @@ static ssize_t extract_user_to_sg(struct iov_iter *iter, do { res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, extraction_flags, &off); - if (res < 0) + if (res <= 0) goto failed; len = res; diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 68c97387aa54e2..cd8f2345528510 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -627,10 +627,10 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries, /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic - * contexts and I/O. + * contexts, I/O, nolockdep. */ alloc_flags &= ~GFP_ZONEMASK; - alloc_flags &= (GFP_ATOMIC | GFP_KERNEL); + alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP); alloc_flags |= __GFP_NOWARN; page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER); if (page) diff --git a/lib/test_fpu.h b/lib/test_fpu.h new file mode 100644 index 00000000000000..4459807084bcee --- /dev/null +++ b/lib/test_fpu.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _LIB_TEST_FPU_H +#define _LIB_TEST_FPU_H + +int test_fpu(void); + +#endif diff --git a/lib/test_fpu.c b/lib/test_fpu_glue.c index e82db19fed84ac..eef282a2715f21 100644 --- a/lib/test_fpu.c +++ b/lib/test_fpu_glue.c @@ -17,39 +17,9 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/debugfs.h> -#include <asm/fpu/api.h> +#include <linux/fpu.h> -static int test_fpu(void) -{ - /* - * This sequence of operations tests that rounding mode is - * to nearest and that denormal numbers are supported. - * Volatile variables are used to avoid compiler optimizing - * the calculations away. - */ - volatile double a, b, c, d, e, f, g; - - a = 4.0; - b = 1e-15; - c = 1e-310; - - /* Sets precision flag */ - d = a + b; - - /* Result depends on rounding mode */ - e = a + b / 2; - - /* Denormal and very large values */ - f = b / c; - - /* Depends on denormal support */ - g = a + c * f; - - if (d > a && e > a && g > a) - return 0; - else - return -EINVAL; -} +#include "test_fpu.h" static int test_fpu_get(void *data, u64 *val) { @@ -68,6 +38,9 @@ static struct dentry *selftest_dir; static int __init test_fpu_init(void) { + if (!kernel_fpu_available()) + return -EINVAL; + selftest_dir = debugfs_create_dir("selftest_helpers", NULL); if (!selftest_dir) return -ENOMEM; diff --git a/lib/test_fpu_impl.c b/lib/test_fpu_impl.c new file mode 100644 index 00000000000000..777894dbbe86fa --- /dev/null +++ b/lib/test_fpu_impl.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/errno.h> + +#include "test_fpu.h" + +int test_fpu(void) +{ + /* + * This sequence of operations tests that rounding mode is + * to nearest and that denormal numbers are supported. + * Volatile variables are used to avoid compiler optimizing + * the calculations away. + */ + volatile double a, b, c, d, e, f, g; + + a = 4.0; + b = 1e-15; + c = 1e-310; + + /* Sets precision flag */ + d = a + b; + + /* Result depends on rounding mode */ + e = a + b / 2; + + /* Denormal and very large values */ + f = b / c; + + /* Depends on denormal support */ + g = a + c * f; + + if (d > a && e > a && g > a) + return 0; + else + return -EINVAL; +} diff --git a/lib/test_hexdump.c b/lib/test_hexdump.c index b916801f23a896..fe2682bb21e6dc 100644 --- a/lib/test_hexdump.c +++ b/lib/test_hexdump.c @@ -113,7 +113,7 @@ static void __init test_hexdump_prepare_test(size_t len, int rowsize, *p++ = ' '; } while (p < test + rs * 2 + rs / gs + 1); - strncpy(p, data_a, l); + memcpy(p, data_a, l); p += l; } diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 717dcb83012733..b823ba7cb6a156 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -1226,8 +1226,8 @@ static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) unsigned long *src_pfns; unsigned long *dst_pfns; - src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); - dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + src_pfns = kvcalloc(npages, sizeof(*src_pfns), GFP_KERNEL | __GFP_NOFAIL); + dst_pfns = kvcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL | __GFP_NOFAIL); migrate_device_range(src_pfns, start_pfn, npages); for (i = 0; i < npages; i++) { @@ -1250,8 +1250,8 @@ static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) } migrate_device_pages(src_pfns, dst_pfns, npages); migrate_device_finalize(src_pfns, dst_pfns, npages); - kfree(src_pfns); - kfree(dst_pfns); + kvfree(src_pfns); + kvfree(dst_pfns); } /* Removes free pages from the free list so they can't be re-allocated */ diff --git a/lib/test_xarray.c b/lib/test_xarray.c index ebe2af2e072db3..0aea6a85099d53 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -744,15 +744,20 @@ static noinline void check_xa_multi_store_adv_add(struct xarray *xa, do { xas_lock_irq(&xas); - xas_store(&xas, p); - XA_BUG_ON(xa, xas_error(&xas)); - XA_BUG_ON(xa, xa_load(xa, index) != p); - xas_unlock_irq(&xas); + /* + * In our selftest case the only failure we can expect is for + * there not to be enough memory as we're not mimicking the + * entire page cache, so verify that's the only error we can run + * into here. The xas_nomem() which follows will ensure to fix + * that condition for us so to chug on on the loop. + */ + XA_BUG_ON(xa, xas_error(&xas) && xas_error(&xas) != -ENOMEM); } while (xas_nomem(&xas, GFP_KERNEL)); XA_BUG_ON(xa, xas_error(&xas)); + XA_BUG_ON(xa, xa_load(xa, index) != p); } /* mimics page_cache_delete() */ @@ -1984,6 +1989,97 @@ static noinline void check_get_order(struct xarray *xa) } } +static noinline void check_xas_get_order(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + unsigned int order; + unsigned long i, j; + + for (order = 0; order < max_order; order++) { + for (i = 0; i < 10; i++) { + xas_set_order(&xas, i << order, order); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(i)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + for (j = i << order; j < (i + 1) << order; j++) { + xas_set_order(&xas, j, 0); + rcu_read_lock(); + xas_load(&xas); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + rcu_read_unlock(); + } + + xas_lock(&xas); + xas_set_order(&xas, i << order, order); + xas_store(&xas, NULL); + xas_unlock(&xas); + } + } +} + +static noinline void check_xas_conflict_get_order(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + void *entry; + int only_once; + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + unsigned int order; + unsigned long i, j, k; + + for (order = 0; order < max_order; order++) { + for (i = 0; i < 10; i++) { + xas_set_order(&xas, i << order, order); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(i)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + /* + * Ensure xas_get_order works with xas_for_each_conflict. + */ + j = i << order; + for (k = 0; k < order; k++) { + only_once = 0; + xas_set_order(&xas, j + (1 << k), k); + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + only_once++; + } + XA_BUG_ON(xa, only_once != 1); + xas_unlock(&xas); + } + + if (order < max_order - 1) { + only_once = 0; + xas_set_order(&xas, (i & ~1UL) << order, order + 1); + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, xas_get_order(&xas) != order); + only_once++; + } + XA_BUG_ON(xa, only_once != 1); + xas_unlock(&xas); + } + + xas_set_order(&xas, i << order, order); + xas_lock(&xas); + xas_store(&xas, NULL); + xas_unlock(&xas); + } + } +} + + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -2035,6 +2131,8 @@ static int xarray_checks(void) check_multi_store(&array); check_multi_store_advanced(&array); check_get_order(&array); + check_xas_get_order(&array); + check_xas_conflict_get_order(&array); check_xa_alloc(); check_find(&array); check_find_entry(&array); diff --git a/lib/xarray.c b/lib/xarray.c index 39f07bfc4dccac..1c87d871cacfa0 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -200,7 +200,8 @@ static void *xas_start(struct xa_state *xas) return entry; } -static void *xas_descend(struct xa_state *xas, struct xa_node *node) +static __always_inline void *xas_descend(struct xa_state *xas, + struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); @@ -1750,39 +1751,52 @@ unlock: EXPORT_SYMBOL(xa_store_range); /** - * xa_get_order() - Get the order of an entry. - * @xa: XArray. - * @index: Index of the entry. + * xas_get_order() - Get the order of an entry. + * @xas: XArray operation state. + * + * Called after xas_load, the xas should not be in an error state. * * Return: A number between 0 and 63 indicating the order of the entry. */ -int xa_get_order(struct xarray *xa, unsigned long index) +int xas_get_order(struct xa_state *xas) { - XA_STATE(xas, xa, index); - void *entry; int order = 0; - rcu_read_lock(); - entry = xas_load(&xas); - - if (!entry) - goto unlock; - - if (!xas.xa_node) - goto unlock; + if (!xas->xa_node) + return 0; for (;;) { - unsigned int slot = xas.xa_offset + (1 << order); + unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; - if (!xa_is_sibling(xas.xa_node->slots[slot])) + if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } - order += xas.xa_node->shift; -unlock: + order += xas->xa_node->shift; + return order; +} +EXPORT_SYMBOL_GPL(xas_get_order); + +/** + * xa_get_order() - Get the order of an entry. + * @xa: XArray. + * @index: Index of the entry. + * + * Return: A number between 0 and 63 indicating the order of the entry. + */ +int xa_get_order(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + int order = 0; + void *entry; + + rcu_read_lock(); + entry = xas_load(&xas); + if (entry) + order = xas_get_order(&xas); rcu_read_unlock(); return order; diff --git a/mm/Kconfig b/mm/Kconfig index b1448aa81e15f4..50df323eaecef0 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -473,7 +473,7 @@ config ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP config HAVE_MEMBLOCK_PHYS_MAP bool -config HAVE_FAST_GUP +config HAVE_GUP_FAST depends on MMU bool @@ -850,6 +850,12 @@ config READ_ONLY_THP_FOR_FS endif # TRANSPARENT_HUGEPAGE # +# The architecture supports pgtable leaves that is larger than PAGE_SIZE +# +config PGTABLE_HAS_HUGE_LEAVES + def_bool TRANSPARENT_HUGEPAGE || HUGETLB_PAGE + +# # UP and nommu archs use km based percpu allocator # config NEED_PER_CPU_KM diff --git a/mm/Makefile b/mm/Makefile index 4abb40b911ec43..25da205becdd24 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -5,6 +5,7 @@ KASAN_SANITIZE_slab_common.o := n KASAN_SANITIZE_slub.o := n +KASAN_SANITIZE_kmemleak.o := n KCSAN_SANITIZE_kmemleak.o := n # These produce frequent data race reports: most of them are due to races on @@ -42,6 +43,10 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH mmu-$(CONFIG_MMU) += process_vm_access.o endif +ifdef CONFIG_64BIT +mmu-$(CONFIG_MMU) += mseal.o +endif + obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page-writeback.o folio-compat.o \ readahead.o swap.o truncate.o vmscan.o shrinker.o \ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 5f2be8c8df11f1..e61bbb1bd62218 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -39,6 +39,19 @@ struct workqueue_struct *bdi_wq; #include <linux/debugfs.h> #include <linux/seq_file.h> +struct wb_stats { + unsigned long nr_dirty; + unsigned long nr_io; + unsigned long nr_more_io; + unsigned long nr_dirty_time; + unsigned long nr_writeback; + unsigned long nr_reclaimable; + unsigned long nr_dirtied; + unsigned long nr_written; + unsigned long dirty_thresh; + unsigned long wb_thresh; +}; + static struct dentry *bdi_debug_root; static void bdi_debug_init(void) @@ -46,31 +59,68 @@ static void bdi_debug_init(void) bdi_debug_root = debugfs_create_dir("bdi", NULL); } -static int bdi_debug_stats_show(struct seq_file *m, void *v) +static void collect_wb_stats(struct wb_stats *stats, + struct bdi_writeback *wb) { - struct backing_dev_info *bdi = m->private; - struct bdi_writeback *wb = &bdi->wb; - unsigned long background_thresh; - unsigned long dirty_thresh; - unsigned long wb_thresh; - unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time; struct inode *inode; - nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) - nr_dirty++; + stats->nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) - nr_io++; + stats->nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) - nr_more_io++; + stats->nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) if (inode->i_state & I_DIRTY_TIME) - nr_dirty_time++; + stats->nr_dirty_time++; spin_unlock(&wb->list_lock); + stats->nr_writeback += wb_stat(wb, WB_WRITEBACK); + stats->nr_reclaimable += wb_stat(wb, WB_RECLAIMABLE); + stats->nr_dirtied += wb_stat(wb, WB_DIRTIED); + stats->nr_written += wb_stat(wb, WB_WRITTEN); + stats->wb_thresh += wb_calc_thresh(wb, stats->dirty_thresh); +} + +#ifdef CONFIG_CGROUP_WRITEBACK +static void bdi_collect_stats(struct backing_dev_info *bdi, + struct wb_stats *stats) +{ + struct bdi_writeback *wb; + + rcu_read_lock(); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { + if (!wb_tryget(wb)) + continue; + + collect_wb_stats(stats, wb); + wb_put(wb); + } + rcu_read_unlock(); +} +#else +static void bdi_collect_stats(struct backing_dev_info *bdi, + struct wb_stats *stats) +{ + collect_wb_stats(stats, &bdi->wb); +} +#endif + +static int bdi_debug_stats_show(struct seq_file *m, void *v) +{ + struct backing_dev_info *bdi = m->private; + unsigned long background_thresh; + unsigned long dirty_thresh; + struct wb_stats stats; + unsigned long tot_bw; + global_dirty_limits(&background_thresh, &dirty_thresh); - wb_thresh = wb_calc_thresh(wb, dirty_thresh); + + memset(&stats, 0, sizeof(stats)); + stats.dirty_thresh = dirty_thresh; + bdi_collect_stats(bdi, &stats); + tot_bw = atomic_long_read(&bdi->tot_write_bandwidth); seq_printf(m, "BdiWriteback: %10lu kB\n" @@ -87,37 +137,114 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", - (unsigned long) K(wb_stat(wb, WB_WRITEBACK)), - (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)), - K(wb_thresh), + K(stats.nr_writeback), + K(stats.nr_reclaimable), + K(stats.wb_thresh), K(dirty_thresh), K(background_thresh), - (unsigned long) K(wb_stat(wb, WB_DIRTIED)), - (unsigned long) K(wb_stat(wb, WB_WRITTEN)), - (unsigned long) K(wb->write_bandwidth), - nr_dirty, - nr_io, - nr_more_io, - nr_dirty_time, + K(stats.nr_dirtied), + K(stats.nr_written), + K(tot_bw), + stats.nr_dirty, + stats.nr_io, + stats.nr_more_io, + stats.nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->wb.state); return 0; } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); +static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, + struct wb_stats *stats) +{ + + seq_printf(m, + "WbCgIno: %10lu\n" + "WbWriteback: %10lu kB\n" + "WbReclaimable: %10lu kB\n" + "WbDirtyThresh: %10lu kB\n" + "WbDirtied: %10lu kB\n" + "WbWritten: %10lu kB\n" + "WbWriteBandwidth: %10lu kBps\n" + "b_dirty: %10lu\n" + "b_io: %10lu\n" + "b_more_io: %10lu\n" + "b_dirty_time: %10lu\n" + "state: %10lx\n\n", +#ifdef CONFIG_CGROUP_WRITEBACK + cgroup_ino(wb->memcg_css->cgroup), +#else + 1ul, +#endif + K(stats->nr_writeback), + K(stats->nr_reclaimable), + K(stats->wb_thresh), + K(stats->nr_dirtied), + K(stats->nr_written), + K(wb->avg_write_bandwidth), + stats->nr_dirty, + stats->nr_io, + stats->nr_more_io, + stats->nr_dirty_time, + wb->state); +} + +static int cgwb_debug_stats_show(struct seq_file *m, void *v) +{ + struct backing_dev_info *bdi = m->private; + unsigned long background_thresh; + unsigned long dirty_thresh; + struct bdi_writeback *wb; + + global_dirty_limits(&background_thresh, &dirty_thresh); + + rcu_read_lock(); + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { + struct wb_stats stats = { .dirty_thresh = dirty_thresh }; + + if (!wb_tryget(wb)) + continue; + + collect_wb_stats(&stats, wb); + + /* + * Calculate thresh of wb in writeback cgroup which is min of + * thresh in global domain and thresh in cgroup domain. Drop + * rcu lock because cgwb_calc_thresh may sleep in + * cgroup_rstat_flush. We can do so here because we have a ref. + */ + if (mem_cgroup_wb_domain(wb)) { + rcu_read_unlock(); + stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb)); + rcu_read_lock(); + } + + wb_stats_show(m, wb, &stats); + + wb_put(wb); + } + rcu_read_unlock(); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats); + static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); + debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi, + &cgwb_debug_stats_fops); } static void bdi_debug_unregister(struct backing_dev_info *bdi) { debugfs_remove_recursive(bdi->debug_dir); } -#else +#else /* CONFIG_DEBUG_FS */ static inline void bdi_debug_init(void) { } @@ -128,7 +255,7 @@ static inline void bdi_debug_register(struct backing_dev_info *bdi, static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } -#endif +#endif /* CONFIG_DEBUG_FS */ static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, @@ -388,7 +515,7 @@ static void wb_update_bandwidth_workfn(struct work_struct *work) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, gfp_t gfp) { - int i, err; + int err; memset(wb, 0, sizeof(*wb)); @@ -416,18 +543,10 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, if (err) return err; - for (i = 0; i < NR_WB_STAT_ITEMS; i++) { - err = percpu_counter_init(&wb->stat[i], 0, gfp); - if (err) - goto out_destroy_stat; - } - - return 0; + err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS); + if (err) + fprop_local_destroy_percpu(&wb->completions); -out_destroy_stat: - while (i--) - percpu_counter_destroy(&wb->stat[i]); - fprop_local_destroy_percpu(&wb->completions); return err; } @@ -460,13 +579,8 @@ static void wb_shutdown(struct bdi_writeback *wb) static void wb_exit(struct bdi_writeback *wb) { - int i; - WARN_ON(delayed_work_pending(&wb->dwork)); - - for (i = 0; i < NR_WB_STAT_ITEMS; i++) - percpu_counter_destroy(&wb->stat[i]); - + percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS); fprop_local_destroy_percpu(&wb->completions); } diff --git a/mm/cma.c b/mm/cma.c index 01f5a8f71ddfa7..3e9724716bad87 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -182,10 +182,6 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, if (!size || !memblock_is_region_reserved(base, size)) return -EINVAL; - /* alignment should be aligned with order_per_bit */ - if (!IS_ALIGNED(CMA_MIN_ALIGNMENT_PAGES, 1 << order_per_bit)) - return -EINVAL; - /* ensure minimal alignment required by mm core */ if (!IS_ALIGNED(base | size, CMA_MIN_ALIGNMENT_BYTES)) return -EINVAL; diff --git a/mm/compaction.c b/mm/compaction.c index 807b58e6eb68b3..e731d45befc780 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1851,7 +1851,7 @@ static void isolate_freepages(struct compact_control *cc) * This is a migrate-callback that "allocates" freepages by taking pages * from the isolated freelists in the block we are migrating to. */ -static struct folio *compaction_alloc(struct folio *src, unsigned long data) +static struct folio *compaction_alloc_noprof(struct folio *src, unsigned long data) { struct compact_control *cc = (struct compact_control *)data; struct folio *dst; @@ -1898,6 +1898,11 @@ again: return page_rmappable_folio(&dst->page); } +static struct folio *compaction_alloc(struct folio *src, unsigned long data) +{ + return alloc_hooks(compaction_alloc_noprof(src, data)); +} + /* * This is a migrate-callback that "frees" freepages back to the isolated * freelist. All pages on the freelist are from the same zone, so there is no @@ -3345,7 +3350,6 @@ static struct ctl_table vm_compaction[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - { } }; static int __init kcompactd_init(void) diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 5e6dc312072cd0..5685ba485097d2 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -16,8 +16,8 @@ #include "../internal.h" #include "ops-common.h" -static bool __damon_pa_mkold(struct folio *folio, struct vm_area_struct *vma, - unsigned long addr, void *arg) +static bool damon_folio_mkold_one(struct folio *folio, + struct vm_area_struct *vma, unsigned long addr, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0); @@ -31,33 +31,38 @@ static bool __damon_pa_mkold(struct folio *folio, struct vm_area_struct *vma, return true; } -static void damon_pa_mkold(unsigned long paddr) +static void damon_folio_mkold(struct folio *folio) { - struct folio *folio = damon_get_folio(PHYS_PFN(paddr)); struct rmap_walk_control rwc = { - .rmap_one = __damon_pa_mkold, + .rmap_one = damon_folio_mkold_one, .anon_lock = folio_lock_anon_vma_read, }; bool need_lock; - if (!folio) - return; - if (!folio_mapped(folio) || !folio_raw_mapping(folio)) { folio_set_idle(folio); - goto out; + return; } need_lock = !folio_test_anon(folio) || folio_test_ksm(folio); if (need_lock && !folio_trylock(folio)) - goto out; + return; rmap_walk(folio, &rwc); if (need_lock) folio_unlock(folio); -out: +} + +static void damon_pa_mkold(unsigned long paddr) +{ + struct folio *folio = damon_get_folio(PHYS_PFN(paddr)); + + if (!folio) + return; + + damon_folio_mkold(folio); folio_put(folio); } @@ -79,8 +84,8 @@ static void damon_pa_prepare_access_checks(struct damon_ctx *ctx) } } -static bool __damon_pa_young(struct folio *folio, struct vm_area_struct *vma, - unsigned long addr, void *arg) +static bool damon_folio_young_one(struct folio *folio, + struct vm_area_struct *vma, unsigned long addr, void *arg) { bool *accessed = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0); @@ -111,38 +116,44 @@ static bool __damon_pa_young(struct folio *folio, struct vm_area_struct *vma, return *accessed == false; } -static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz) +static bool damon_folio_young(struct folio *folio) { - struct folio *folio = damon_get_folio(PHYS_PFN(paddr)); bool accessed = false; struct rmap_walk_control rwc = { .arg = &accessed, - .rmap_one = __damon_pa_young, + .rmap_one = damon_folio_young_one, .anon_lock = folio_lock_anon_vma_read, }; bool need_lock; - if (!folio) - return false; - if (!folio_mapped(folio) || !folio_raw_mapping(folio)) { if (folio_test_idle(folio)) - accessed = false; + return false; else - accessed = true; - goto out; + return true; } need_lock = !folio_test_anon(folio) || folio_test_ksm(folio); if (need_lock && !folio_trylock(folio)) - goto out; + return false; rmap_walk(folio, &rwc); if (need_lock) folio_unlock(folio); -out: + return accessed; +} + +static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz) +{ + struct folio *folio = damon_get_folio(PHYS_PFN(paddr)); + bool accessed; + + if (!folio) + return false; + + accessed = damon_folio_young(folio); *folio_sz = folio_size(folio); folio_put(folio); return accessed; @@ -203,6 +214,11 @@ static bool __damos_pa_filter_out(struct damos_filter *filter, matched = filter->memcg_id == mem_cgroup_id(memcg); rcu_read_unlock(); break; + case DAMOS_FILTER_TYPE_YOUNG: + matched = damon_folio_young(folio); + if (matched) + damon_folio_mkold(folio); + break; default: break; } diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 53a90ac678fb98..bea5bc52846a69 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -343,6 +343,7 @@ static struct damon_sysfs_scheme_filter *damon_sysfs_scheme_filter_alloc(void) static const char * const damon_sysfs_scheme_filter_type_strs[] = { "anon", "memcg", + "young", "addr", "target", }; diff --git a/mm/debug.c b/mm/debug.c index c1c1a6a484e4c0..69e524c3e6012e 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -55,25 +55,17 @@ static void __dump_folio(struct folio *folio, struct page *page, unsigned long pfn, unsigned long idx) { struct address_space *mapping = folio_mapping(folio); - int mapcount = 0; + int mapcount = atomic_read(&page->_mapcount); char *type = ""; - /* - * page->_mapcount space in struct page is used by slab pages to - * encode own info, and we must avoid calling page_folio() again. - */ - if (!folio_test_slab(folio)) { - mapcount = atomic_read(&page->_mapcount) + 1; - if (folio_test_large(folio)) - mapcount += folio_entire_mapcount(folio); - } - + mapcount = page_type_has_type(mapcount) ? 0 : mapcount + 1; pr_warn("page: refcount:%d mapcount:%d mapping:%p index:%#lx pfn:%#lx\n", folio_ref_count(folio), mapcount, mapping, folio->index + idx, pfn); if (folio_test_large(folio)) { - pr_warn("head: order:%u entire_mapcount:%d nr_pages_mapped:%d pincount:%d\n", + pr_warn("head: order:%u mapcount:%d entire_mapcount:%d nr_pages_mapped:%d pincount:%d\n", folio_order(folio), + folio_mapcount(folio), folio_entire_mapcount(folio), folio_nr_pages_mapped(folio), atomic_read(&folio->_pincount)); @@ -99,7 +91,8 @@ static void __dump_folio(struct folio *folio, struct page *page, */ pr_warn("%sflags: %pGp%s\n", type, &folio->flags, is_migrate_cma_folio(folio, pfn) ? " CMA" : ""); - pr_warn("page_type: %pGt\n", &folio->page.page_type); + if (page_has_type(&folio->page)) + pr_warn("page_type: %pGt\n", &folio->page.page_type); print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, @@ -180,9 +173,6 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { pr_emerg("mm %px task_size %lu\n" -#ifdef CONFIG_MMU - "get_unmapped_area %px\n" -#endif "mmap_base %lu mmap_legacy_base %lu\n" "pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" @@ -208,9 +198,6 @@ void dump_mm(const struct mm_struct *mm) "def_flags: %#lx(%pGv)\n", mm, mm->task_size, -#ifdef CONFIG_MMU - mm->get_unmapped_area, -#endif mm->mmap_base, mm->mmap_legacy_base, mm->pgd, atomic_read(&mm->mm_users), atomic_read(&mm->mm_count), diff --git a/mm/debug_page_alloc.c b/mm/debug_page_alloc.c index 6755f0c9d4a398..d46acf989dde88 100644 --- a/mm/debug_page_alloc.c +++ b/mm/debug_page_alloc.c @@ -32,8 +32,7 @@ static int __init debug_guardpage_minorder_setup(char *buf) } early_param("debug_guardpage_minorder", debug_guardpage_minorder_setup); -bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order, - int migratetype) +bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order) { if (order >= debug_guardpage_minorder()) return false; @@ -41,19 +40,12 @@ bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order, __SetPageGuard(page); INIT_LIST_HEAD(&page->buddy_list); set_page_private(page, order); - /* Guard pages are not available for any usage */ - if (!is_migrate_isolate(migratetype)) - __mod_zone_freepage_state(zone, -(1 << order), migratetype); return true; } -void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order, - int migratetype) +void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order) { __ClearPageGuard(page); - set_page_private(page, 0); - if (!is_migrate_isolate(migratetype)) - __mod_zone_freepage_state(zone, (1 << order), migratetype); } diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 65c19025da3dfe..f1c9a2c5abc04c 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -30,6 +30,7 @@ #include <linux/start_kernel.h> #include <linux/sched/mm.h> #include <linux/io.h> +#include <linux/vmalloc.h> #include <asm/cacheflush.h> #include <asm/pgalloc.h> diff --git a/mm/filemap.c b/mm/filemap.c index 30de18c4fd28a9..ec273b00ce5fd6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -168,7 +168,7 @@ static void filemap_unaccount_folio(struct address_space *mapping, add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); if (mapping_exiting(mapping) && !folio_test_large(folio)) { - int mapcount = page_mapcount(&folio->page); + int mapcount = folio_mapcount(folio); if (folio_ref_count(folio) >= mapcount + 2) { /* @@ -852,23 +852,18 @@ noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, index); - bool huge = folio_test_hugetlb(folio); - bool charged = false; - long nr = 1; + void *alloced_shadow = NULL; + int alloced_order = 0; + bool huge; + long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); mapping_set_update(&xas, mapping); - if (!huge) { - int error = mem_cgroup_charge(folio, NULL, gfp); - if (error) - return error; - charged = true; - } - VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); xas_set_order(&xas, index, folio_order(folio)); + huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; @@ -876,13 +871,10 @@ noinline int __filemap_add_folio(struct address_space *mapping, folio->mapping = mapping; folio->index = xas.xa_index; - do { - unsigned int order = xa_get_order(xas.xa, xas.xa_index); + for (;;) { + int order = -1, split_order = 0; void *entry, *old = NULL; - if (order > folio_order(folio)) - xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), - order, gfp); xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; @@ -890,19 +882,33 @@ noinline int __filemap_add_folio(struct address_space *mapping, xas_set_err(&xas, -EEXIST); goto unlock; } + /* + * If a larger entry exists, + * it will be the first and only entry iterated. + */ + if (order == -1) + order = xas_get_order(&xas); + } + + /* entry may have changed before we re-acquire the lock */ + if (alloced_order && (old != alloced_shadow || order != alloced_order)) { + xas_destroy(&xas); + alloced_order = 0; } if (old) { - if (shadowp) - *shadowp = old; - /* entry may have been split before we acquired lock */ - order = xa_get_order(xas.xa, xas.xa_index); - if (order > folio_order(folio)) { + if (order > 0 && order > folio_order(folio)) { /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); + if (!alloced_order) { + split_order = order; + goto unlock; + } xas_split(&xas, old, order); xas_reset(&xas); } + if (shadowp) + *shadowp = old; } xas_store(&xas, folio); @@ -918,9 +924,24 @@ noinline int __filemap_add_folio(struct address_space *mapping, __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } + unlock: xas_unlock_irq(&xas); - } while (xas_nomem(&xas, gfp)); + + /* split needed, alloc here and retry. */ + if (split_order) { + xas_split_alloc(&xas, old, split_order, gfp); + if (xas_error(&xas)) + goto error; + alloced_shadow = old; + alloced_order = split_order; + xas_reset(&xas); + continue; + } + + if (!xas_nomem(&xas, gfp)) + break; + } if (xas_error(&xas)) goto error; @@ -928,8 +949,6 @@ unlock: trace_mm_filemap_add_to_page_cache(folio); return 0; error: - if (charged) - mem_cgroup_uncharge(folio); folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ folio_put_refs(folio, nr); @@ -943,11 +962,16 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio, void *shadow = NULL; int ret; + ret = mem_cgroup_charge(folio, NULL, gfp); + if (ret) + return ret; + __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); - if (unlikely(ret)) + if (unlikely(ret)) { + mem_cgroup_uncharge(folio); __folio_clear_locked(folio); - else { + } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like @@ -966,7 +990,7 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio, EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA -struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) +struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { int n; struct folio *folio; @@ -981,9 +1005,9 @@ struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) return folio; } - return folio_alloc(gfp, order); + return folio_alloc_noprof(gfp, order); } -EXPORT_SYMBOL(filemap_alloc_folio); +EXPORT_SYMBOL(filemap_alloc_folio_noprof); #endif /* @@ -1786,7 +1810,7 @@ EXPORT_SYMBOL(page_cache_prev_miss); * C. Return the page to the page allocator * * This means that any page may have its reference count temporarily - * increased by a speculative page cache (or fast GUP) lookup as it can + * increased by a speculative page cache (or GUP-fast) lookup as it can * be allocated by another user before the RCU grace period expires. * Because the refcount temporarily acquired here may end up being the * last refcount on the page, any page allocation must be freeable by @@ -3207,7 +3231,8 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; - ptep = pte_offset_map(vmf->pmd, vmf->address); + ptep = pte_offset_map_nolock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; @@ -3481,7 +3506,7 @@ skip: static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, - unsigned int *mmap_miss) + unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = folio_page(folio, start); @@ -3492,7 +3517,15 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, if (PageHWPoison(page + count)) goto skip; - (*mmap_miss)++; + /* + * If there are too many folios that are recently evicted + * in a file, they will probably continue to be evicted. + * In such situation, read-ahead is only a waste of IO. + * Don't decrease mmap_miss in this scenario to make sure + * we can stop read-ahead. + */ + if (!folio_test_workingset(folio)) + (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be @@ -3507,6 +3540,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, skip: if (count) { set_pte_range(vmf, folio, page, count, addr); + *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; @@ -3521,6 +3555,7 @@ skip: if (count) { set_pte_range(vmf, folio, page, count, addr); + *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; @@ -3533,7 +3568,7 @@ skip: static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, struct folio *folio, unsigned long addr, - unsigned int *mmap_miss) + unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = &folio->page; @@ -3541,7 +3576,9 @@ static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, if (PageHWPoison(page)) return ret; - (*mmap_miss)++; + /* See comment of filemap_map_folio_range() */ + if (!folio_test_workingset(folio)) + (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be @@ -3555,6 +3592,7 @@ static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, ret = VM_FAULT_NOPAGE; set_pte_range(vmf, folio, page, 1, addr); + (*rss)++; folio_ref_inc(folio); return ret; @@ -3571,7 +3609,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; - unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved; + unsigned long rss = 0; + unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); @@ -3590,6 +3629,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, folio_put(folio); goto out; } + + folio_type = mm_counter_file(folio); do { unsigned long end; @@ -3601,15 +3642,16 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, if (!folio_test_large(folio)) ret |= filemap_map_order0_folio(vmf, - folio, addr, &mmap_miss); + folio, addr, &rss, &mmap_miss); else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, - nr_pages, &mmap_miss); + nr_pages, &rss, &mmap_miss); folio_unlock(folio); folio_put(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); + add_mm_counter(vma->vm_mm, folio_type, rss); pte_unmap_unlock(vmf->pte, vmf->ptl); out: rcu_read_unlock(); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 50412014f16f72..f05906006b3c33 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -10,12 +10,6 @@ #include <linux/swap.h> #include "internal.h" -struct address_space *page_mapping(struct page *page) -{ - return folio_mapping(page_folio(page)); -} -EXPORT_SYMBOL(page_mapping); - void unlock_page(struct page *page) { return folio_unlock(page_folio(page)); @@ -58,12 +52,6 @@ bool set_page_dirty(struct page *page) } EXPORT_SYMBOL(set_page_dirty); -int __set_page_dirty_nobuffers(struct page *page) -{ - return filemap_dirty_folio(page_mapping(page), page_folio(page)); -} -EXPORT_SYMBOL(__set_page_dirty_nobuffers); - bool clear_page_dirty_for_io(struct page *page) { return folio_clear_dirty_for_io(page_folio(page)); diff --git a/mm/gup.c b/mm/gup.c index 1611e73b1121b1..2f7baf96f65593 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -89,7 +89,7 @@ retry: * belongs to this folio. */ if (unlikely(page_folio(page) != folio)) { - if (!put_devmap_managed_page_refs(&folio->page, refs)) + if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); goto retry; } @@ -156,7 +156,7 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) */ if (unlikely((flags & FOLL_LONGTERM) && !folio_is_longterm_pinnable(folio))) { - if (!put_devmap_managed_page_refs(&folio->page, refs)) + if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); return NULL; } @@ -198,7 +198,7 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) refs *= GUP_PIN_COUNTING_BIAS; } - if (!put_devmap_managed_page_refs(&folio->page, refs)) + if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); } @@ -440,7 +440,7 @@ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, } EXPORT_SYMBOL(unpin_user_page_range_dirty_lock); -static void unpin_user_pages_lockless(struct page **pages, unsigned long npages) +static void gup_fast_unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; @@ -500,22 +500,329 @@ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) } #ifdef CONFIG_MMU + +#if defined(CONFIG_ARCH_HAS_HUGEPD) || defined(CONFIG_HAVE_GUP_FAST) +static int record_subpages(struct page *page, unsigned long sz, + unsigned long addr, unsigned long end, + struct page **pages) +{ + struct page *start_page; + int nr; + + start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT); + for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) + pages[nr] = nth_page(start_page, nr); + + return nr; +} +#endif /* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */ + +#ifdef CONFIG_ARCH_HAS_HUGEPD +static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, + unsigned long sz) +{ + unsigned long __boundary = (addr + sz) & ~(sz-1); + return (__boundary - 1 < end - 1) ? __boundary : end; +} + +static int gup_fast_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) +{ + unsigned long pte_end; + struct page *page; + struct folio *folio; + pte_t pte; + int refs; + + pte_end = (addr + sz) & ~(sz-1); + if (pte_end < end) + end = pte_end; + + pte = huge_ptep_get(ptep); + + if (!pte_access_permitted(pte, flags & FOLL_WRITE)) + return 0; + + /* hugepages are never "special" */ + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + page = pte_page(pte); + refs = record_subpages(page, sz, addr, end, pages + *nr); + + folio = try_grab_folio(page, refs, flags); + if (!folio) + return 0; + + if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { + gup_put_folio(folio, refs, flags); + return 0; + } + + if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) { + gup_put_folio(folio, refs, flags); + return 0; + } + + *nr += refs; + folio_set_referenced(folio); + return 1; +} + +/* + * NOTE: currently GUP for a hugepd is only possible on hugetlbfs file + * systems on Power, which does not have issue with folio writeback against + * GUP updates. When hugepd will be extended to support non-hugetlbfs or + * even anonymous memory, we need to do extra check as what we do with most + * of the other folios. See writable_file_mapping_allowed() and + * gup_fast_folio_allowed() for more information. + */ +static int gup_fast_hugepd(hugepd_t hugepd, unsigned long addr, + unsigned int pdshift, unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + pte_t *ptep; + unsigned long sz = 1UL << hugepd_shift(hugepd); + unsigned long next; + + ptep = hugepte_offset(hugepd, addr, pdshift); + do { + next = hugepte_addr_end(addr, end, sz); + if (!gup_fast_hugepte(ptep, sz, addr, end, flags, pages, nr)) + return 0; + } while (ptep++, addr = next, addr != end); + + return 1; +} + +static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, + unsigned long addr, unsigned int pdshift, + unsigned int flags, + struct follow_page_context *ctx) +{ + struct page *page; + struct hstate *h; + spinlock_t *ptl; + int nr = 0, ret; + pte_t *ptep; + + /* Only hugetlb supports hugepd */ + if (WARN_ON_ONCE(!is_vm_hugetlb_page(vma))) + return ERR_PTR(-EFAULT); + + h = hstate_vma(vma); + ptep = hugepte_offset(hugepd, addr, pdshift); + ptl = huge_pte_lock(h, vma->vm_mm, ptep); + ret = gup_fast_hugepd(hugepd, addr, pdshift, addr + PAGE_SIZE, + flags, &page, &nr); + spin_unlock(ptl); + + if (ret) { + WARN_ON_ONCE(nr != 1); + ctx->page_mask = (1U << huge_page_order(h)) - 1; + return page; + } + + return NULL; +} +#else /* CONFIG_ARCH_HAS_HUGEPD */ +static inline int gup_fast_hugepd(hugepd_t hugepd, unsigned long addr, + unsigned int pdshift, unsigned long end, unsigned int flags, + struct page **pages, int *nr) +{ + return 0; +} + +static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, + unsigned long addr, unsigned int pdshift, + unsigned int flags, + struct follow_page_context *ctx) +{ + return NULL; +} +#endif /* CONFIG_ARCH_HAS_HUGEPD */ + + static struct page *no_page_table(struct vm_area_struct *vma, - unsigned int flags) + unsigned int flags, unsigned long address) { + if (!(flags & FOLL_DUMP)) + return NULL; + /* - * When core dumping an enormous anonymous area that nobody - * has touched so far, we don't want to allocate unnecessary pages or + * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it. */ - if ((flags & FOLL_DUMP) && - (vma_is_anonymous(vma) || !vma->vm_ops->fault)) + if (is_vm_hugetlb_page(vma)) { + struct hstate *h = hstate_vma(vma); + + if (!hugetlbfs_pagecache_present(h, vma, address)) + return ERR_PTR(-EFAULT); + } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) { + return ERR_PTR(-EFAULT); + } + + return NULL; +} + +#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES +static struct page *follow_huge_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, + int flags, struct follow_page_context *ctx) +{ + struct mm_struct *mm = vma->vm_mm; + struct page *page; + pud_t pud = *pudp; + unsigned long pfn = pud_pfn(pud); + int ret; + + assert_spin_locked(pud_lockptr(mm, pudp)); + + if ((flags & FOLL_WRITE) && !pud_write(pud)) + return NULL; + + if (!pud_present(pud)) + return NULL; + + pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; + + if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && + pud_devmap(pud)) { + /* + * device mapped pages can only be returned if the caller + * will manage the page reference count. + * + * At least one of FOLL_GET | FOLL_PIN must be set, so + * assert that here: + */ + if (!(flags & (FOLL_GET | FOLL_PIN))) + return ERR_PTR(-EEXIST); + + if (flags & FOLL_TOUCH) + touch_pud(vma, addr, pudp, flags & FOLL_WRITE); + + ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap); + if (!ctx->pgmap) + return ERR_PTR(-EFAULT); + } + + page = pfn_to_page(pfn); + + if (!pud_devmap(pud) && !pud_write(pud) && + gup_must_unshare(vma, flags, page)) + return ERR_PTR(-EMLINK); + + ret = try_grab_page(page, flags); + if (ret) + page = ERR_PTR(ret); + else + ctx->page_mask = HPAGE_PUD_NR - 1; + + return page; +} + +/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ +static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) +{ + /* If the pmd is writable, we can write to the page. */ + if (pmd_write(pmd)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) + return false; + return !userfaultfd_huge_pmd_wp(vma, pmd); +} + +static struct page *follow_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags, + struct follow_page_context *ctx) +{ + struct mm_struct *mm = vma->vm_mm; + pmd_t pmdval = *pmd; + struct page *page; + int ret; + + assert_spin_locked(pmd_lockptr(mm, pmd)); + + page = pmd_page(pmdval); + if ((flags & FOLL_WRITE) && + !can_follow_write_pmd(pmdval, page, vma, flags)) + return NULL; + + /* Avoid dumping huge zero page */ + if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval)) return ERR_PTR(-EFAULT); + + if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) + return NULL; + + if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page)) + return ERR_PTR(-EMLINK); + + VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && + !PageAnonExclusive(page), page); + + ret = try_grab_page(page, flags); + if (ret) + return ERR_PTR(ret); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) + touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; + ctx->page_mask = HPAGE_PMD_NR - 1; + + return page; +} + +#else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ +static struct page *follow_huge_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, + int flags, struct follow_page_context *ctx) +{ + return NULL; +} + +static struct page *follow_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags, + struct follow_page_context *ctx) +{ return NULL; } +#endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, pte_t *pte, unsigned int flags) @@ -593,7 +900,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; @@ -685,7 +992,7 @@ no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } static struct page *follow_pmd_mask(struct vm_area_struct *vma, @@ -701,42 +1008,45 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, pmd = pmd_offset(pudp, address); pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); + if (unlikely(is_hugepd(__hugepd(pmd_val(pmdval))))) + return follow_hugepd(vma, __hugepd(pmd_val(pmdval)), + address, PMD_SHIFT, flags, ctx); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } - if (likely(!pmd_trans_huge(pmdval))) + if (likely(!pmd_leaf(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_present(*pmd))) { + pmdval = *pmd; + if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl); - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } - if (unlikely(!pmd_trans_huge(*pmd))) { + if (unlikely(!pmd_leaf(pmdval))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } - if (flags & FOLL_SPLIT_PMD) { + if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) { spin_unlock(ptl); split_huge_pmd(vma, pmd, address); /* If pmd was left empty, stuff a page table in there quickly */ return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) : follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } - page = follow_trans_huge_pmd(vma, address, pmd, flags); + page = follow_huge_pmd(vma, address, pmd, flags, ctx); spin_unlock(ptl); - ctx->page_mask = HPAGE_PMD_NR - 1; return page; } @@ -745,26 +1055,30 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned int flags, struct follow_page_context *ctx) { - pud_t *pud; + pud_t *pudp, pud; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; - pud = pud_offset(p4dp, address); - if (pud_none(*pud)) - return no_page_table(vma, flags); - if (pud_devmap(*pud)) { - ptl = pud_lock(mm, pud); - page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap); + pudp = pud_offset(p4dp, address); + pud = READ_ONCE(*pudp); + if (!pud_present(pud)) + return no_page_table(vma, flags, address); + if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) + return follow_hugepd(vma, __hugepd(pud_val(pud)), + address, PUD_SHIFT, flags, ctx); + if (pud_leaf(pud)) { + ptl = pud_lock(mm, pudp); + page = follow_huge_pud(vma, address, pudp, flags, ctx); spin_unlock(ptl); if (page) return page; - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } - if (unlikely(pud_bad(*pud))) - return no_page_table(vma, flags); + if (unlikely(pud_bad(pud))) + return no_page_table(vma, flags, address); - return follow_pmd_mask(vma, address, pud, flags, ctx); + return follow_pmd_mask(vma, address, pudp, flags, ctx); } static struct page *follow_p4d_mask(struct vm_area_struct *vma, @@ -772,16 +1086,20 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned int flags, struct follow_page_context *ctx) { - p4d_t *p4d; + p4d_t *p4dp, p4d; - p4d = p4d_offset(pgdp, address); - if (p4d_none(*p4d)) - return no_page_table(vma, flags); - BUILD_BUG_ON(p4d_huge(*p4d)); - if (unlikely(p4d_bad(*p4d))) - return no_page_table(vma, flags); + p4dp = p4d_offset(pgdp, address); + p4d = READ_ONCE(*p4dp); + BUILD_BUG_ON(p4d_leaf(p4d)); - return follow_pud_mask(vma, address, p4d, flags, ctx); + if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) + return follow_hugepd(vma, __hugepd(p4d_val(p4d)), + address, P4D_SHIFT, flags, ctx); + + if (!p4d_present(p4d) || p4d_bad(p4d)) + return no_page_table(vma, flags, address); + + return follow_pud_mask(vma, address, p4dp, flags, ctx); } /** @@ -814,24 +1132,24 @@ static struct page *follow_page_mask(struct vm_area_struct *vma, { pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; + struct page *page; - ctx->page_mask = 0; - - /* - * Call hugetlb_follow_page_mask for hugetlb vmas as it will use - * special hugetlb page table walking code. This eliminates the - * need to check for hugetlb entries in the general walking code. - */ - if (is_vm_hugetlb_page(vma)) - return hugetlb_follow_page_mask(vma, address, flags, - &ctx->page_mask); + vma_pgtable_walk_begin(vma); + ctx->page_mask = 0; pgd = pgd_offset(mm, address); - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return no_page_table(vma, flags); + if (unlikely(is_hugepd(__hugepd(pgd_val(*pgd))))) + page = follow_hugepd(vma, __hugepd(pgd_val(*pgd)), + address, PGDIR_SHIFT, flags, ctx); + else if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + page = no_page_table(vma, flags, address); + else + page = follow_p4d_mask(vma, address, pgd, flags, ctx); + + vma_pgtable_walk_end(vma); - return follow_p4d_mask(vma, address, pgd, flags, ctx); + return page; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, @@ -2144,6 +2462,7 @@ static int migrate_longterm_unpinnable_pages( struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_NOWARN, + .reason = MR_LONGTERM_PIN, }; if (migrate_pages(movable_page_list, alloc_migration_target, @@ -2431,7 +2750,7 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, EXPORT_SYMBOL(get_user_pages_unlocked); /* - * Fast GUP + * GUP-fast * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be @@ -2445,7 +2764,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * * Another way to achieve this is to batch up page table containing pages * belonging to more than one mm_user, then rcu_sched a callback to free those - * pages. Disabling interrupts will allow the fast_gup walker to both block + * pages. Disabling interrupts will allow the gup_fast() walker to both block * the rcu_sched callback, and an IPI that we broadcast for splitting THPs * (which is a relatively rare event). The code below adopts this strategy. * @@ -2463,15 +2782,17 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ -#ifdef CONFIG_HAVE_FAST_GUP +#ifdef CONFIG_HAVE_GUP_FAST /* - * Used in the GUP-fast path to determine whether a pin is permitted for a - * specific folio. + * Used in the GUP-fast path to determine whether GUP is permitted to work on + * a specific folio. * * This call assumes the caller has pinned the folio, that the lowest page table * level still points to this folio, and that interrupts have been disabled. * + * GUP-fast must reject all secretmem folios. + * * Writing to pinned file-backed dirty tracked folios is inherently problematic * (see comment describing the writable_file_mapping_allowed() function). We * therefore try to avoid the most egregious case of a long-term mapping doing @@ -2481,25 +2802,34 @@ EXPORT_SYMBOL(get_user_pages_unlocked); * in the fast path, so instead we whitelist known good cases and if in doubt, * fall back to the slow path. */ -static bool folio_fast_pin_allowed(struct folio *folio, unsigned int flags) +static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags) { + bool reject_file_backed = false; struct address_space *mapping; + bool check_secretmem = false; unsigned long mapping_flags; /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the one we disallow. */ - if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) != + if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) == (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) - return true; + reject_file_backed = true; + + /* We hold a folio reference, so we can safely access folio fields. */ + + /* secretmem folios are always order-0 folios. */ + if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio)) + check_secretmem = true; - /* The folio is pinned, so we can safely access folio fields. */ + if (!reject_file_backed && !check_secretmem) + return true; if (WARN_ON_ONCE(folio_test_slab(folio))) return false; - /* hugetlb mappings do not require dirty-tracking. */ + /* hugetlb neither requires dirty-tracking nor can be secretmem. */ if (folio_test_hugetlb(folio)) return true; @@ -2535,50 +2865,48 @@ static bool folio_fast_pin_allowed(struct folio *folio, unsigned int flags) /* * At this point, we know the mapping is non-null and points to an - * address_space object. The only remaining whitelisted file system is - * shmem. + * address_space object. */ - return shmem_mapping(mapping); + if (check_secretmem && secretmem_mapping(mapping)) + return false; + /* The only remaining allowed file system is shmem. */ + return !reject_file_backed || shmem_mapping(mapping); } -static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start, - unsigned int flags, - struct page **pages) +static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start, + unsigned int flags, struct page **pages) { while ((*nr) - nr_start) { - struct page *page = pages[--(*nr)]; + struct folio *folio = page_folio(pages[--(*nr)]); - ClearPageReferenced(page); - if (flags & FOLL_PIN) - unpin_user_page(page); - else - put_page(page); + folio_clear_referenced(folio); + gup_put_folio(folio, 1, flags); } } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* - * Fast-gup relies on pte change detection to avoid concurrent pgtable + * GUP-fast relies on pte change detection to avoid concurrent pgtable * operations. * - * To pin the page, fast-gup needs to do below in order: + * To pin the page, GUP-fast needs to do below in order: * (1) pin the page (by prefetching pte), then (2) check pte not changed. * * For the rest of pgtable operations where pgtable updates can be racy - * with fast-gup, we need to do (1) clear pte, then (2) check whether page + * with GUP-fast, we need to do (1) clear pte, then (2) check whether page * is pinned. * * Above will work for all pte-level operations, including THP split. * - * For THP collapse, it's a bit more complicated because fast-gup may be + * For THP collapse, it's a bit more complicated because GUP-fast may be * walking a pgtable page that is being freed (pte is still valid but pmd * can be cleared already). To avoid race in such condition, we need to * also check pmd here to make sure pmd doesn't change (corresponds to * pmdp_collapse_flush() in the THP collapse code path). */ -static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; @@ -2611,7 +2939,7 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) @@ -2624,18 +2952,13 @@ static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, if (!folio) goto pte_unmap; - if (unlikely(folio_is_secretmem(folio))) { - gup_put_folio(folio, 1, flags); - goto pte_unmap; - } - if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } - if (!folio_fast_pin_allowed(folio, flags)) { + if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } @@ -2680,44 +3003,45 @@ pte_unmap: * * For a futex to be placed on a THP tail page, get_futex_key requires a * get_user_pages_fast_only implementation that can pin pages. Thus it's still - * useful to have gup_huge_pmd even if we can't operate on ptes. + * useful to have gup_fast_pmd_leaf even if we can't operate on ptes. */ -static int gup_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) -static int __gup_device_huge(unsigned long pfn, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, int *nr) { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; do { + struct folio *folio; struct page *page = pfn_to_page(pfn); pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } - SetPageReferenced(page); - pages[*nr] = page; - if (unlikely(try_grab_page(page, flags))) { - undo_dev_pagemap(nr, nr_start, flags, pages); + folio = try_grab_folio(page, 1, flags); + if (!folio) { + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } + folio_set_referenced(folio); + pages[*nr] = page; (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); @@ -2726,156 +3050,62 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr, return addr == end; } -static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) + if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } -static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - if (!__gup_device_huge(fault_pfn, addr, end, flags, pages, nr)) + if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { - undo_dev_pagemap(nr, nr_start, flags, pages); + gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } #else -static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { BUILD_BUG(); return 0; } -static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { BUILD_BUG(); return 0; } #endif -static int record_subpages(struct page *page, unsigned long addr, - unsigned long end, struct page **pages) -{ - int nr; - - for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) - pages[nr] = nth_page(page, nr); - - return nr; -} - -#ifdef CONFIG_ARCH_HAS_HUGEPD -static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, - unsigned long sz) -{ - unsigned long __boundary = (addr + sz) & ~(sz-1); - return (__boundary - 1 < end - 1) ? __boundary : end; -} - -static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) -{ - unsigned long pte_end; - struct page *page; - struct folio *folio; - pte_t pte; - int refs; - - pte_end = (addr + sz) & ~(sz-1); - if (pte_end < end) - end = pte_end; - - pte = huge_ptep_get(ptep); - - if (!pte_access_permitted(pte, flags & FOLL_WRITE)) - return 0; - - /* hugepages are never "special" */ - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - page = nth_page(pte_page(pte), (addr & (sz - 1)) >> PAGE_SHIFT); - refs = record_subpages(page, addr, end, pages + *nr); - - folio = try_grab_folio(page, refs, flags); - if (!folio) - return 0; - - if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { - gup_put_folio(folio, refs, flags); - return 0; - } - - if (!folio_fast_pin_allowed(folio, flags)) { - gup_put_folio(folio, refs, flags); - return 0; - } - - if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) { - gup_put_folio(folio, refs, flags); - return 0; - } - - *nr += refs; - folio_set_referenced(folio); - return 1; -} - -static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned int pdshift, unsigned long end, unsigned int flags, - struct page **pages, int *nr) -{ - pte_t *ptep; - unsigned long sz = 1UL << hugepd_shift(hugepd); - unsigned long next; - - ptep = hugepte_offset(hugepd, addr, pdshift); - do { - next = hugepte_addr_end(addr, end, sz); - if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr)) - return 0; - } while (ptep++, addr = next, addr != end); - - return 1; -} -#else -static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned int pdshift, unsigned long end, unsigned int flags, - struct page **pages, int *nr) -{ - return 0; -} -#endif /* CONFIG_ARCH_HAS_HUGEPD */ - -static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { struct page *page; struct folio *folio; @@ -2887,12 +3117,12 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; - return __gup_device_huge_pmd(orig, pmdp, addr, end, flags, - pages, nr); + return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags, + pages, nr); } - page = nth_page(pmd_page(orig), (addr & ~PMD_MASK) >> PAGE_SHIFT); - refs = record_subpages(page, addr, end, pages + *nr); + page = pmd_page(orig); + refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) @@ -2903,7 +3133,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } - if (!folio_fast_pin_allowed(folio, flags)) { + if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } @@ -2917,9 +3147,9 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 1; } -static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { struct page *page; struct folio *folio; @@ -2931,12 +3161,12 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; - return __gup_device_huge_pud(orig, pudp, addr, end, flags, - pages, nr); + return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags, + pages, nr); } - page = nth_page(pud_page(orig), (addr & ~PUD_MASK) >> PAGE_SHIFT); - refs = record_subpages(page, addr, end, pages + *nr); + page = pud_page(orig); + refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) @@ -2947,7 +3177,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } - if (!folio_fast_pin_allowed(folio, flags)) { + if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } @@ -2962,9 +3192,9 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 1; } -static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, - unsigned long end, unsigned int flags, - struct page **pages, int *nr) +static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { int refs; struct page *page; @@ -2975,8 +3205,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, BUILD_BUG_ON(pgd_devmap(orig)); - page = nth_page(pgd_page(orig), (addr & ~PGDIR_MASK) >> PAGE_SHIFT); - refs = record_subpages(page, addr, end, pages + *nr); + page = pgd_page(orig); + refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) @@ -2992,7 +3222,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; } - if (!folio_fast_pin_allowed(folio, flags)) { + if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } @@ -3002,8 +3232,9 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 1; } -static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long next; pmd_t *pmdp; @@ -3016,13 +3247,12 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo if (!pmd_present(pmd)) return 0; - if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || - pmd_devmap(pmd))) { - /* See gup_pte_range() */ + if (unlikely(pmd_leaf(pmd))) { + /* See gup_fast_pte_range() */ if (pmd_protnone(pmd)) return 0; - if (!gup_huge_pmd(pmd, pmdp, addr, next, flags, + if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags, pages, nr)) return 0; @@ -3031,18 +3261,20 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned lo * architecture have different format for hugetlbfs * pmd format and THP pmd format */ - if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr, - PMD_SHIFT, next, flags, pages, nr)) + if (!gup_fast_hugepd(__hugepd(pmd_val(pmd)), addr, + PMD_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) + } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, + pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); return 1; } -static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long next; pud_t *pudp; @@ -3054,23 +3286,25 @@ static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned lo next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; - if (unlikely(pud_huge(pud) || pud_devmap(pud))) { - if (!gup_huge_pud(pud, pudp, addr, next, flags, - pages, nr)) + if (unlikely(pud_leaf(pud))) { + if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags, + pages, nr)) return 0; } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { - if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, - PUD_SHIFT, next, flags, pages, nr)) + if (!gup_fast_hugepd(__hugepd(pud_val(pud)), addr, + PUD_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr)) + } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, + pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } -static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, - unsigned int flags, struct page **pages, int *nr) +static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, + unsigned long end, unsigned int flags, struct page **pages, + int *nr) { unsigned long next; p4d_t *p4dp; @@ -3080,21 +3314,22 @@ static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned lo p4d_t p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); - if (p4d_none(p4d)) + if (!p4d_present(p4d)) return 0; - BUILD_BUG_ON(p4d_huge(p4d)); + BUILD_BUG_ON(p4d_leaf(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { - if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, - P4D_SHIFT, next, flags, pages, nr)) + if (!gup_fast_hugepd(__hugepd(p4d_val(p4d)), addr, + P4D_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) + } else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, + pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); return 1; } -static void gup_pgd_range(unsigned long addr, unsigned long end, +static void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; @@ -3107,24 +3342,25 @@ static void gup_pgd_range(unsigned long addr, unsigned long end, next = pgd_addr_end(addr, end); if (pgd_none(pgd)) return; - if (unlikely(pgd_huge(pgd))) { - if (!gup_huge_pgd(pgd, pgdp, addr, next, flags, - pages, nr)) + if (unlikely(pgd_leaf(pgd))) { + if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags, + pages, nr)) return; } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { - if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, - PGDIR_SHIFT, next, flags, pages, nr)) + if (!gup_fast_hugepd(__hugepd(pgd_val(pgd)), addr, + PGDIR_SHIFT, next, flags, pages, nr)) return; - } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) + } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, + pages, nr)) return; } while (pgdp++, addr = next, addr != end); } #else -static inline void gup_pgd_range(unsigned long addr, unsigned long end, +static inline void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { } -#endif /* CONFIG_HAVE_FAST_GUP */ +#endif /* CONFIG_HAVE_GUP_FAST */ #ifndef gup_fast_permitted /* @@ -3137,16 +3373,14 @@ static bool gup_fast_permitted(unsigned long start, unsigned long end) } #endif -static unsigned long lockless_pages_from_mm(unsigned long start, - unsigned long end, - unsigned int gup_flags, - struct page **pages) +static unsigned long gup_fast(unsigned long start, unsigned long end, + unsigned int gup_flags, struct page **pages) { unsigned long flags; int nr_pinned = 0; unsigned seq; - if (!IS_ENABLED(CONFIG_HAVE_FAST_GUP) || + if (!IS_ENABLED(CONFIG_HAVE_GUP_FAST) || !gup_fast_permitted(start, end)) return 0; @@ -3168,16 +3402,16 @@ static unsigned long lockless_pages_from_mm(unsigned long start, * that come from THPs splitting. */ local_irq_save(flags); - gup_pgd_range(start, end, gup_flags, pages, &nr_pinned); + gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned); local_irq_restore(flags); /* * When pinning pages for DMA there could be a concurrent write protect - * from fork() via copy_page_range(), in this case always fail fast GUP. + * from fork() via copy_page_range(), in this case always fail GUP-fast. */ if (gup_flags & FOLL_PIN) { if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { - unpin_user_pages_lockless(pages, nr_pinned); + gup_fast_unpin_user_pages(pages, nr_pinned); return 0; } else { sanity_check_pinned_pages(pages, nr_pinned); @@ -3186,10 +3420,8 @@ static unsigned long lockless_pages_from_mm(unsigned long start, return nr_pinned; } -static int internal_get_user_pages_fast(unsigned long start, - unsigned long nr_pages, - unsigned int gup_flags, - struct page **pages) +static int gup_fast_fallback(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages) { unsigned long len, end; unsigned long nr_pinned; @@ -3217,7 +3449,7 @@ static int internal_get_user_pages_fast(unsigned long start, if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; - nr_pinned = lockless_pages_from_mm(start, end, gup_flags, pages); + nr_pinned = gup_fast(start, end, gup_flags, pages); if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) return nr_pinned; @@ -3271,7 +3503,7 @@ int get_user_pages_fast_only(unsigned long start, int nr_pages, FOLL_GET | FOLL_FAST_ONLY)) return -EINVAL; - return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); + return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); @@ -3302,7 +3534,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET)) return -EINVAL; - return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); + return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); @@ -3330,7 +3562,7 @@ int pin_user_pages_fast(unsigned long start, int nr_pages, { if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; - return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); + return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); diff --git a/mm/hmm.c b/mm/hmm.c index 277ddcab4947d9..93aebd9cc130ea 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -424,22 +424,17 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end, walk->action = ACTION_CONTINUE; pud = READ_ONCE(*pudp); - if (pud_none(pud)) { + if (!pud_present(pud)) { spin_unlock(ptl); return hmm_vma_walk_hole(start, end, -1, walk); } - if (pud_huge(pud) && pud_devmap(pud)) { + if (pud_leaf(pud) && pud_devmap(pud)) { unsigned long i, npages, pfn; unsigned int required_fault; unsigned long *hmm_pfns; unsigned long cpu_flags; - if (!pud_present(pud)) { - spin_unlock(ptl); - return hmm_vma_walk_hole(start, end, -1, walk); - } - i = (addr - range->start) >> PAGE_SHIFT; npages = (end - addr) >> PAGE_SHIFT; hmm_pfns = &range->hmm_pfns[i]; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 89f58c7603b255..8261b56693978f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -38,6 +38,7 @@ #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> #include <linux/compat.h> +#include <linux/pgalloc_tag.h> #include <asm/tlb.h> #include <asm/pgalloc.h> @@ -73,17 +74,20 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc); static atomic_t huge_zero_refcount; -struct page *huge_zero_page __read_mostly; +struct folio *huge_zero_folio __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; unsigned long huge_anon_orders_always __read_mostly; unsigned long huge_anon_orders_madvise __read_mostly; unsigned long huge_anon_orders_inherit __read_mostly; unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders) { + bool smaps = tva_flags & TVA_SMAPS; + bool in_pf = tva_flags & TVA_IN_PF; + bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS; /* Check the intersection of requested and supported orders. */ orders &= vma_is_anonymous(vma) ? THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE; @@ -191,24 +195,24 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, static bool get_huge_zero_page(void) { - struct page *zero_page; + struct folio *zero_folio; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) return true; - zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, + zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); - if (!zero_page) { + if (!zero_folio) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); return false; } preempt_disable(); - if (cmpxchg(&huge_zero_page, NULL, zero_page)) { + if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) { preempt_enable(); - __free_pages(zero_page, compound_order(zero_page)); + folio_put(zero_folio); goto retry; } - WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); + WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio)); /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); @@ -226,10 +230,10 @@ static void put_huge_zero_page(void) BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } -struct page *mm_get_huge_zero_page(struct mm_struct *mm) +struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) { if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) - return READ_ONCE(huge_zero_page); + return READ_ONCE(huge_zero_folio); if (!get_huge_zero_page()) return NULL; @@ -237,10 +241,10 @@ struct page *mm_get_huge_zero_page(struct mm_struct *mm) if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) put_huge_zero_page(); - return READ_ONCE(huge_zero_page); + return READ_ONCE(huge_zero_folio); } -void mm_put_huge_zero_page(struct mm_struct *mm) +void mm_put_huge_zero_folio(struct mm_struct *mm) { if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) put_huge_zero_page(); @@ -257,10 +261,10 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, struct shrink_control *sc) { if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { - struct page *zero_page = xchg(&huge_zero_page, NULL); - BUG_ON(zero_page == NULL); + struct folio *zero_folio = xchg(&huge_zero_folio, NULL); + BUG_ON(zero_folio == NULL); WRITE_ONCE(huge_zero_pfn, ~0UL); - __free_pages(zero_page, compound_order(zero_page)); + folio_put(zero_folio); return HPAGE_PMD_NR; } @@ -525,6 +529,52 @@ static const struct kobj_type thpsize_ktype = { .sysfs_ops = &kobj_sysfs_ops, }; +DEFINE_PER_CPU(struct mthp_stat, mthp_stats) = {{{0}}}; + +static unsigned long sum_mthp_stat(int order, enum mthp_stat_item item) +{ + unsigned long sum = 0; + int cpu; + + for_each_possible_cpu(cpu) { + struct mthp_stat *this = &per_cpu(mthp_stats, cpu); + + sum += this->stats[order][item]; + } + + return sum; +} + +#define DEFINE_MTHP_STAT_ATTR(_name, _index) \ +static ssize_t _name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ +{ \ + int order = to_thpsize(kobj)->order; \ + \ + return sysfs_emit(buf, "%lu\n", sum_mthp_stat(order, _index)); \ +} \ +static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); +DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); +DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); +DEFINE_MTHP_STAT_ATTR(anon_swpout, MTHP_STAT_ANON_SWPOUT); +DEFINE_MTHP_STAT_ATTR(anon_swpout_fallback, MTHP_STAT_ANON_SWPOUT_FALLBACK); + +static struct attribute *stats_attrs[] = { + &anon_fault_alloc_attr.attr, + &anon_fault_fallback_attr.attr, + &anon_fault_fallback_charge_attr.attr, + &anon_swpout_attr.attr, + &anon_swpout_fallback_attr.attr, + NULL, +}; + +static struct attribute_group stats_attr_group = { + .name = "stats", + .attrs = stats_attrs, +}; + static struct thpsize *thpsize_create(int order, struct kobject *parent) { unsigned long size = (PAGE_SIZE << order) / SZ_1K; @@ -548,6 +598,12 @@ static struct thpsize *thpsize_create(int order, struct kobject *parent) return ERR_PTR(ret); } + ret = sysfs_create_group(&thpsize->kobj, &stats_attr_group); + if (ret) { + kobject_put(&thpsize->kobj); + return ERR_PTR(ret); + } + thpsize->order = order; return thpsize; } @@ -788,27 +844,19 @@ struct deferred_split *get_deferred_split_queue(struct folio *folio) } #endif -void folio_prep_large_rmappable(struct folio *folio) -{ - if (!folio || !folio_test_large(folio)) - return; - if (folio_order(folio) > 1) - INIT_LIST_HEAD(&folio->_deferred_list); - folio_set_large_rmappable(folio); -} - -static inline bool is_transparent_hugepage(struct folio *folio) +static inline bool is_transparent_hugepage(const struct folio *folio) { if (!folio_test_large(folio)) return false; - return is_huge_zero_page(&folio->page) || + return is_huge_zero_folio(folio) || folio_test_large_rmappable(folio); } static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, - loff_t off, unsigned long flags, unsigned long size) + loff_t off, unsigned long flags, unsigned long size, + vm_flags_t vm_flags) { loff_t off_end = off + len; loff_t off_align = round_up(off, size); @@ -824,8 +872,8 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, if (len_pad < len || (off + len_pad) < off) return 0; - ret = current->mm->get_unmapped_area(filp, addr, len_pad, - off >> PAGE_SHIFT, flags); + ret = mm_get_unmapped_area_vmflags(current->mm, filp, addr, len_pad, + off >> PAGE_SHIFT, flags, vm_flags); /* * The failure might be due to length padding. The caller will retry @@ -843,25 +891,32 @@ static unsigned long __thp_get_unmapped_area(struct file *filp, off_sub = (off - ret) & (size - 1); - if (current->mm->get_unmapped_area == arch_get_unmapped_area_topdown && - !off_sub) + if (test_bit(MMF_TOPDOWN, ¤t->mm->flags) && !off_sub) return ret + size; ret += off_sub; return ret; } -unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) { unsigned long ret; loff_t off = (loff_t)pgoff << PAGE_SHIFT; - ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE); + ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE, vm_flags); if (ret) return ret; - return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); + return mm_get_unmapped_area_vmflags(current->mm, filp, addr, len, pgoff, flags, + vm_flags); +} + +unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + return thp_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); } EXPORT_SYMBOL_GPL(thp_get_unmapped_area); @@ -880,6 +935,8 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, folio_put(folio); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); return VM_FAULT_FALLBACK; } folio_throttle_swaprate(folio, gfp); @@ -929,6 +986,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, mm_inc_nr_ptes(vma->vm_mm); spin_unlock(vmf->ptl); count_vm_event(THP_FAULT_ALLOC); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } @@ -979,14 +1037,14 @@ gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma) } /* Caller must hold page table lock. */ -static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, +static void set_huge_zero_folio(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, - struct page *zero_page) + struct folio *zero_folio) { pmd_t entry; if (!pmd_none(*pmd)) return; - entry = mk_pmd(zero_page, vma->vm_page_prot); + entry = mk_pmd(&zero_folio->page, vma->vm_page_prot); entry = pmd_mkhuge(entry); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); @@ -999,24 +1057,27 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) gfp_t gfp; struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + vm_fault_t ret; if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return VM_FAULT_FALLBACK; - if (unlikely(anon_vma_prepare(vma))) - return VM_FAULT_OOM; + ret = vmf_anon_prepare(vmf); + if (ret) + return ret; khugepaged_enter_vma(vma, vma->vm_flags); if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm) && transparent_hugepage_use_zero_page()) { pgtable_t pgtable; - struct page *zero_page; + struct folio *zero_folio; vm_fault_t ret; + pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) return VM_FAULT_OOM; - zero_page = mm_get_huge_zero_page(vma->vm_mm); - if (unlikely(!zero_page)) { + zero_folio = mm_get_huge_zero_folio(vma->vm_mm); + if (unlikely(!zero_folio)) { pte_free(vma->vm_mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1034,8 +1095,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { - set_huge_zero_page(pgtable, vma->vm_mm, vma, - haddr, vmf->pmd, zero_page); + set_huge_zero_folio(pgtable, vma->vm_mm, vma, + haddr, vmf->pmd, zero_folio); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); } @@ -1049,6 +1110,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true); if (unlikely(!folio)) { count_vm_event(THP_FAULT_FALLBACK); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp); @@ -1228,8 +1290,8 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, bool write) +void touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, bool write) { pmd_t _pmd; @@ -1344,11 +1406,11 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ if (is_huge_zero_pmd(pmd)) { /* - * get_huge_zero_page() will never allocate a new page here, - * since we already have a zero page to copy. It just takes a - * reference. + * mm_get_huge_zero_folio() will never allocate a new + * folio here, since we already have a zero page to + * copy. It just takes a reference. */ - mm_get_huge_zero_page(dst_mm); + mm_get_huge_zero_folio(dst_mm); goto out_zero_page; } @@ -1385,8 +1447,8 @@ out: } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -static void touch_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, bool write) +void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, bool write) { pud_t _pud; @@ -1398,49 +1460,6 @@ static void touch_pud(struct vm_area_struct *vma, unsigned long addr, update_mmu_cache_pud(vma, addr, pud); } -struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags, struct dev_pagemap **pgmap) -{ - unsigned long pfn = pud_pfn(*pud); - struct mm_struct *mm = vma->vm_mm; - struct page *page; - int ret; - - assert_spin_locked(pud_lockptr(mm, pud)); - - if (flags & FOLL_WRITE && !pud_write(*pud)) - return NULL; - - if (pud_present(*pud) && pud_devmap(*pud)) - /* pass */; - else - return NULL; - - if (flags & FOLL_TOUCH) - touch_pud(vma, addr, pud, flags & FOLL_WRITE); - - /* - * device mapped pages can only be returned if the - * caller will manage the page reference count. - * - * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here: - */ - if (!(flags & (FOLL_GET | FOLL_PIN))) - return ERR_PTR(-EEXIST); - - pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; - *pgmap = get_dev_pagemap(pfn, *pgmap); - if (!*pgmap) - return ERR_PTR(-EFAULT); - page = pfn_to_page(pfn); - - ret = try_grab_page(page, flags); - if (ret) - page = ERR_PTR(ret); - - return page; -} - int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma) @@ -1627,88 +1646,6 @@ static inline bool can_change_pmd_writable(struct vm_area_struct *vma, return pmd_dirty(pmd); } -/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ -static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, - struct vm_area_struct *vma, - unsigned int flags) -{ - /* If the pmd is writable, we can write to the page. */ - if (pmd_write(pmd)) - return true; - - /* Maybe FOLL_FORCE is set to override it? */ - if (!(flags & FOLL_FORCE)) - return false; - - /* But FOLL_FORCE has no effect on shared mappings */ - if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) - return false; - - /* ... or read-only private ones */ - if (!(vma->vm_flags & VM_MAYWRITE)) - return false; - - /* ... or already writable ones that just need to take a write fault */ - if (vma->vm_flags & VM_WRITE) - return false; - - /* - * See can_change_pte_writable(): we broke COW and could map the page - * writable if we have an exclusive anonymous page ... - */ - if (!page || !PageAnon(page) || !PageAnonExclusive(page)) - return false; - - /* ... and a write-fault isn't required for other reasons. */ - if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) - return false; - return !userfaultfd_huge_pmd_wp(vma, pmd); -} - -struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, - pmd_t *pmd, - unsigned int flags) -{ - struct mm_struct *mm = vma->vm_mm; - struct page *page; - int ret; - - assert_spin_locked(pmd_lockptr(mm, pmd)); - - page = pmd_page(*pmd); - VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); - - if ((flags & FOLL_WRITE) && - !can_follow_write_pmd(*pmd, page, vma, flags)) - return NULL; - - /* Avoid dumping huge zero page */ - if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) - return ERR_PTR(-EFAULT); - - if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) - return NULL; - - if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page)) - return ERR_PTR(-EMLINK); - - VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && - !PageAnonExclusive(page), page); - - ret = try_grab_page(page, flags); - if (ret) - return ERR_PTR(ret); - - if (flags & FOLL_TOUCH) - touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); - - page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; - VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); - - return page; -} - /* NUMA hinting page fault entry point for trans huge pmds */ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { @@ -1754,7 +1691,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) */ if (node_is_toptier(nid)) last_cpupid = folio_last_cpupid(folio); - target_nid = numa_migrate_prep(folio, vma, haddr, nid, &flags); + target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags); if (target_nid == NUMA_NO_NODE) { folio_put(folio); goto out_map; @@ -1824,12 +1761,12 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, goto out; } - folio = pfn_folio(pmd_pfn(orig_pmd)); + folio = pmd_folio(orig_pmd); /* * If other processes are mapping this folio, we couldn't discard * the folio unless they all do MADV_FREE so let's skip the folio. */ - if (folio_estimated_sharers(folio) != 1) + if (folio_likely_mapped_shared(folio)) goto out; if (!folio_trylock(folio)) @@ -1915,7 +1852,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, folio = page_folio(page); folio_remove_rmap_pmd(folio, page, vma); - VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); + WARN_ON_ONCE(folio_mapcount(folio) < 0); VM_BUG_ON_PAGE(!PageHead(page), page); } else if (thp_migration_supported()) { swp_entry_t entry; @@ -2094,7 +2031,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (pmd_protnone(*pmd)) goto unlock; - folio = page_folio(pmd_page(*pmd)); + folio = pmd_folio(*pmd); toptier = node_is_toptier(folio_nid(folio)); /* * Skip scanning top tier node if normal numa @@ -2268,7 +2205,7 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm } folio_move_anon_rmap(src_folio, dst_vma); - WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + 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 */ @@ -2513,12 +2450,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, * for this pmd), then we flush the SMP TLB and finally we write the * non-huge version of the pmd entry with pmd_populate. */ - old_pmd = pmdp_invalidate(vma, haddr, pmd); - pmd_migration = is_pmd_migration_entry(old_pmd); + pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) { swp_entry_t entry; + old_pmd = *pmd; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); @@ -2529,6 +2466,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { + old_pmd = pmdp_invalidate(vma, haddr, pmd); page = pmd_page(old_pmd); folio = page_folio(page); if (pmd_dirty(old_pmd)) { @@ -2671,7 +2609,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * It's safe to call pmd_page when folio is set because it's * guaranteed that pmd is present. */ - if (folio && folio != page_folio(pmd_page(*pmd))) + if (folio && folio != pmd_folio(*pmd)) goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); } @@ -2863,7 +2801,7 @@ static void __split_huge_page_tail(struct folio *folio, int tail, clear_compound_head(page_tail); if (new_order) { prep_compound_page(page_tail, new_order); - folio_prep_large_rmappable(new_folio); + folio_set_large_rmappable(new_folio); } /* Finally unfreeze refcount. Additional reference from page cache. */ @@ -2946,6 +2884,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, /* Caller disabled irqs, so they are still disabled here */ split_page_owner(head, order, new_order); + pgalloc_tag_split(head, 1 << order); /* See comment in __split_huge_page_tail() */ if (folio_test_anon(folio)) { @@ -2967,9 +2906,6 @@ static void __split_huge_page(struct page *page, struct list_head *list, shmem_uncharge(folio->mapping->host, nr_dropped); remap_page(folio, nr); - if (folio_test_swapcache(folio)) - split_swap_cluster(folio->swap); - /* * set page to its compound_head when split to non order-0 pages, so * we can skip unlocking it below, since PG_locked is transferred to @@ -3013,28 +2949,48 @@ bool can_split_folio(struct folio *folio, int *pextra_pins) } /* - * This function splits huge page into pages in @new_order. @page can point to - * any subpage of huge page to split. Split doesn't change the position of - * @page. + * This function splits a large folio into smaller folios of order @new_order. + * @page can point to any page of the large folio to split. The split operation + * does not change the position of @page. + * + * Prerequisites: + * + * 1) The caller must hold a reference on the @page's owning folio, also known + * as the large folio. + * + * 2) The large folio must be locked. * - * NOTE: order-1 anonymous folio is not supported because _deferred_list, - * which is used by partially mapped folios, is stored in subpage 2 and an - * order-1 folio only has subpage 0 and 1. File-backed order-1 folios are OK, - * since they do not use _deferred_list. + * 3) The folio must not be pinned. Any unexpected folio references, including + * GUP pins, will result in the folio not getting split; instead, the caller + * will receive an -EAGAIN. * - * Only caller must hold pin on the @page, otherwise split fails with -EBUSY. - * The huge page must be locked. + * 4) @new_order > 1, usually. Splitting to order-1 anonymous folios is not + * supported for non-file-backed folios, because folio->_deferred_list, which + * is used by partially mapped folios, is stored in subpage 2, but an order-1 + * folio only has subpages 0 and 1. File-backed order-1 folios are supported, + * since they do not use _deferred_list. + * + * After splitting, the caller's folio reference will be transferred to @page, + * resulting in a raised refcount of @page after this call. The other pages may + * be freed if they are not mapped. * * If @list is null, tail pages will be added to LRU list, otherwise, to @list. * - * Pages in new_order will inherit mapping, flags, and so on from the hugepage. + * Pages in @new_order will inherit the mapping, flags, and so on from the + * huge page. + * + * Returns 0 if the huge page was split successfully. + * + * Returns -EAGAIN if the folio has unexpected reference (e.g., GUP) or if + * the folio was concurrently removed from the page cache. * - * GUP pin and PG_locked transferred to @page or the compound page @page belongs - * to. Rest subpages can be freed if they are not mapped. + * Returns -EBUSY when trying to split the huge zeropage, if the folio is + * under writeback, if fs-specific folio metadata cannot currently be + * released, or if some unexpected race happened (e.g., anon VMA disappeared, + * truncation). * - * Returns 0 if the hugepage is split successfully. - * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under - * us. + * Returns -EINVAL when trying to split to an order that is incompatible + * with the folio. Splitting to order 0 is compatible with all folios. */ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order) @@ -3045,6 +3001,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; + bool is_thp = folio_test_pmd_mappable(folio); int extra_pins, ret; pgoff_t end; bool is_hzp; @@ -3080,7 +3037,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, } - is_hzp = is_huge_zero_page(&folio->page); + is_hzp = is_huge_zero_folio(folio); if (is_hzp) { pr_warn_ratelimited("Called split_huge_page for huge zero page\n"); return -EBUSY; @@ -3223,7 +3180,8 @@ out_unlock: i_mmap_unlock_read(mapping); out: xas_destroy(&xas); - count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); + if (is_thp) + count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); return ret; } @@ -3285,7 +3243,8 @@ void deferred_split_folio(struct folio *folio) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (list_empty(&folio->_deferred_list)) { - count_vm_event(THP_DEFERRED_SPLIT_PAGE); + if (folio_test_pmd_mappable(folio)) + count_vm_event(THP_DEFERRED_SPLIT_PAGE); list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 31d00eee028f11..417fc5cdb6eebd 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1517,7 +1517,7 @@ static void __destroy_compound_gigantic_folio(struct folio *folio, struct page *p; atomic_set(&folio->_entire_mapcount, 0); - atomic_set(&folio->_nr_pages_mapped, 0); + atomic_set(&folio->_large_mapcount, 0); atomic_set(&folio->_pincount, 0); for (i = 1; i < nr_pages; i++) { @@ -1619,19 +1619,11 @@ static inline void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { } #endif -static inline void __clear_hugetlb_destructor(struct hstate *h, - struct folio *folio) -{ - lockdep_assert_held(&hugetlb_lock); - - folio_clear_hugetlb(folio); -} - /* * Remove hugetlb folio from lists. - * If vmemmap exists for the folio, update dtor so that the folio appears - * as just a compound page. Otherwise, wait until after allocating vmemmap - * to update dtor. + * If vmemmap exists for the folio, clear the hugetlb flag so that the + * folio appears as just a compound page. Otherwise, wait until after + * allocating vmemmap to clear the flag. * * A reference is held on the folio, except in the case of demote. * @@ -1662,12 +1654,12 @@ static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, } /* - * We can only clear the hugetlb destructor after allocating vmemmap + * We can only clear the hugetlb flag after allocating vmemmap * pages. Otherwise, someone (memory error handling) may try to write * to tail struct pages. */ if (!folio_test_hugetlb_vmemmap_optimized(folio)) - __clear_hugetlb_destructor(h, folio); + __folio_clear_hugetlb(folio); /* * In the case of demote we do not ref count the page as it will soon @@ -1711,7 +1703,7 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, h->surplus_huge_pages_node[nid]++; } - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above @@ -1734,14 +1726,14 @@ static void add_hugetlb_folio(struct hstate *h, struct folio *folio, */ return; - arch_clear_hugepage_flags(&folio->page); + arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } static void __update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio) { - bool clear_dtor = folio_test_hugetlb_vmemmap_optimized(folio); + bool clear_flag = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; @@ -1754,11 +1746,11 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, return; /* - * If folio is not vmemmap optimized (!clear_dtor), then the folio + * If folio is not vmemmap optimized (!clear_flag), then the folio * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio * can only be passed hugetlb pages and will BUG otherwise. */ - if (clear_dtor && hugetlb_vmemmap_restore_folio(h, folio)) { + if (clear_flag && hugetlb_vmemmap_restore_folio(h, folio)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the @@ -1779,11 +1771,11 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, /* * If vmemmap pages were allocated above, then we need to clear the - * hugetlb destructor under the hugetlb lock. + * hugetlb flag under the hugetlb lock. */ - if (clear_dtor) { + if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); - __clear_hugetlb_destructor(h, folio); + __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } @@ -1796,7 +1788,8 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, destroy_compound_gigantic_folio(folio, huge_page_order(h)); free_gigantic_folio(folio, huge_page_order(h)); } else { - __free_pages(&folio->page, huge_page_order(h)); + INIT_LIST_HEAD(&folio->_deferred_list); + folio_put(folio); } } @@ -1884,7 +1877,7 @@ static void bulk_vmemmap_restore_error(struct hstate *h, list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); - __clear_hugetlb_destructor(h, folio); + __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); @@ -1909,7 +1902,7 @@ static void bulk_vmemmap_restore_error(struct hstate *h, } else { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); - __clear_hugetlb_destructor(h, folio); + __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); @@ -1942,14 +1935,14 @@ retry: * should only be pages on the non_hvo_folios list. * Do note that the non_hvo_folios list could be empty. * Without HVO enabled, ret will be 0 and there is no need to call - * __clear_hugetlb_destructor as this was done previously. + * __folio_clear_hugetlb as this was done previously. */ VM_WARN_ON(!list_empty(folio_list)); VM_WARN_ON(ret < 0); if (!list_empty(&non_hvo_folios) && ret) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(folio, &non_hvo_folios, lru) - __clear_hugetlb_destructor(h, folio); + __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } @@ -1974,7 +1967,7 @@ void free_huge_folio(struct folio *folio) { /* * Can't pass hstate in here because it is called from the - * compound page destructor. + * generic mm code. */ struct hstate *h = folio_hstate(folio); int nid = folio_nid(folio); @@ -2031,7 +2024,7 @@ void free_huge_folio(struct folio *folio) spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else { - arch_clear_hugepage_flags(&folio->page); + arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } @@ -2049,7 +2042,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { - folio_set_hugetlb(folio); + __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); @@ -2124,10 +2117,10 @@ static bool __prep_compound_gigantic_folio(struct folio *folio, set_compound_head(p, &folio->page); } __folio_set_head(folio); - /* we rely on prep_new_hugetlb_folio to set the destructor */ + /* we rely on prep_new_hugetlb_folio to set the hugetlb flag */ folio_set_order(folio, order); atomic_set(&folio->_entire_mapcount, -1); - atomic_set(&folio->_nr_pages_mapped, 0); + atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_pincount, 0); return true; @@ -2160,31 +2153,15 @@ static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, } /* - * PageHuge() only returns true for hugetlbfs pages, but not for normal or - * transparent huge pages. See the PageTransHuge() documentation for more - * details. - */ -int PageHuge(const struct page *page) -{ - const struct folio *folio; - - if (!PageCompound(page)) - return 0; - folio = page_folio(page); - return folio_test_hugetlb(folio); -} -EXPORT_SYMBOL_GPL(PageHuge); - -/* * Find and lock address space (mapping) in write mode. * - * Upon entry, the page is locked which means that page_mapping() is + * Upon entry, the folio is locked which means that folio_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ -struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) +struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio) { - struct address_space *mapping = page_mapping(hpage); + struct address_space *mapping = folio_mapping(folio); if (!mapping) return mapping; @@ -2200,13 +2177,13 @@ static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, nodemask_t *node_alloc_noretry) { int order = huge_page_order(h); - struct page *page; + struct folio *folio; bool alloc_try_hard = true; bool retry = true; /* - * By default we always try hard to allocate the page with - * __GFP_RETRY_MAYFAIL flag. However, if we are allocating pages in + * By default we always try hard to allocate the folio with + * __GFP_RETRY_MAYFAIL flag. However, if we are allocating folios in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. @@ -2219,43 +2196,42 @@ static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, if (nid == NUMA_NO_NODE) nid = numa_mem_id(); retry: - page = __alloc_pages(gfp_mask, order, nid, nmask); + folio = __folio_alloc(gfp_mask, order, nid, nmask); - /* Freeze head page */ - if (page && !page_ref_freeze(page, 1)) { - __free_pages(page, order); + if (folio && !folio_ref_freeze(folio, 1)) { + folio_put(folio); if (retry) { /* retry once */ retry = false; goto retry; } /* WOW! twice in a row. */ - pr_warn("HugeTLB head page unexpected inflated ref count\n"); - page = NULL; + pr_warn("HugeTLB unexpected inflated folio ref count\n"); + folio = NULL; } /* - * If we did not specify __GFP_RETRY_MAYFAIL, but still got a page this - * indicates an overall state change. Clear bit so that we resume - * normal 'try hard' allocations. + * If we did not specify __GFP_RETRY_MAYFAIL, but still got a + * folio this indicates an overall state change. Clear bit so + * that we resume normal 'try hard' allocations. */ - if (node_alloc_noretry && page && !alloc_try_hard) + if (node_alloc_noretry && folio && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* - * If we tried hard to get a page but failed, set bit so that + * If we tried hard to get a folio but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ - if (node_alloc_noretry && !page && alloc_try_hard) + if (node_alloc_noretry && !folio && alloc_try_hard) node_set(nid, *node_alloc_noretry); - if (!page) { + if (!folio) { __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); return NULL; } __count_vm_event(HTLB_BUDDY_PGALLOC); - return page_folio(page); + return folio; } static struct folio *__alloc_fresh_hugetlb_folio(struct hstate *h, @@ -2401,8 +2377,8 @@ static struct folio *remove_pool_hugetlb_folio(struct hstate *h, } /* - * Dissolve a given free hugepage into free buddy pages. This function does - * nothing for in-use hugepages and non-hugepages. + * Dissolve a given free hugetlb folio into free buddy pages. This function + * does nothing for in-use hugetlb folios and non-hugetlb folios. * This function returns values like below: * * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages @@ -2414,10 +2390,9 @@ static struct folio *remove_pool_hugetlb_folio(struct hstate *h, * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ -int dissolve_free_huge_page(struct page *page) +int dissolve_free_hugetlb_folio(struct folio *folio) { int rc = -EBUSY; - struct folio *folio = page_folio(page); retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ @@ -2494,13 +2469,13 @@ out: * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. - * Also note that if dissolve_free_huge_page() returns with an error, all - * free hugepages that were dissolved before that error are lost. + * Also note that if dissolve_free_hugetlb_folio() returns with an error, all + * free hugetlb folios that were dissolved before that error are lost. */ -int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) +int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; - struct page *page; + struct folio *folio; int rc = 0; unsigned int order; struct hstate *h; @@ -2513,8 +2488,8 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) order = min(order, huge_page_order(h)); for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { - page = pfn_to_page(pfn); - rc = dissolve_free_huge_page(page); + folio = pfn_folio(pfn); + rc = dissolve_free_hugetlb_folio(folio); if (rc) break; } @@ -2621,7 +2596,7 @@ struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask, gfp_t gfp_mask) + nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { spin_lock_irq(&hugetlb_lock); if (available_huge_pages(h)) { @@ -2636,6 +2611,10 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, } spin_unlock_irq(&hugetlb_lock); + /* We cannot fallback to other nodes, as we could break the per-node pool. */ + if (!allow_alloc_fallback) + gfp_mask |= __GFP_THISNODE; + return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } @@ -3268,9 +3247,12 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); - if (deferred_reserve) + if (deferred_reserve) { + spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); + spin_unlock_irq(&hugetlb_lock); + } } if (!memcg_charge_ret) @@ -5045,7 +5027,6 @@ static struct ctl_table hugetlb_table[] = { .mode = 0644, .proc_handler = hugetlb_overcommit_handler, }, - { } }; static void hugetlb_sysctl_init(void) @@ -5936,19 +5917,18 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ -static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, unsigned int flags, - struct folio *pagecache_folio, spinlock_t *ptl, +static vm_fault_t hugetlb_wp(struct folio *pagecache_folio, struct vm_fault *vmf) { - const bool unshare = flags & FAULT_FLAG_UNSHARE; - pte_t pte = huge_ptep_get(ptep); + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; + pte_t pte = huge_ptep_get(vmf->pte); struct hstate *h = hstate_vma(vma); struct folio *old_folio; struct folio *new_folio; int outside_reserve = 0; vm_fault_t ret = 0; - unsigned long haddr = address & huge_page_mask(h); struct mmu_notifier_range range; /* @@ -5971,7 +5951,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { - set_huge_ptep_writable(vma, haddr, ptep); + set_huge_ptep_writable(vma, vmf->address, vmf->pte); return 0; } @@ -5990,7 +5970,7 @@ retry_avoidcopy: SetPageAnonExclusive(&old_folio->page); } if (likely(!unshare)) - set_huge_ptep_writable(vma, haddr, ptep); + set_huge_ptep_writable(vma, vmf->address, vmf->pte); delayacct_wpcopy_end(); return 0; @@ -6017,8 +5997,8 @@ retry_avoidcopy: * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ - spin_unlock(ptl); - new_folio = alloc_hugetlb_folio(vma, haddr, outside_reserve); + spin_unlock(vmf->ptl); + new_folio = alloc_hugetlb_folio(vma, vmf->address, outside_reserve); if (IS_ERR(new_folio)) { /* @@ -6043,19 +6023,21 @@ retry_avoidcopy: * * Reacquire both after unmap operation. */ - idx = vma_hugecache_offset(h, vma, haddr); + idx = vma_hugecache_offset(h, vma, vmf->address); hash = hugetlb_fault_mutex_hash(mapping, idx); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); - unmap_ref_private(mm, vma, &old_folio->page, haddr); + unmap_ref_private(mm, vma, &old_folio->page, + vmf->address); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); - spin_lock(ptl); - ptep = hugetlb_walk(vma, haddr, huge_page_size(h)); - if (likely(ptep && - pte_same(huge_ptep_get(ptep), pte))) + spin_lock(vmf->ptl); + vmf->pte = hugetlb_walk(vma, vmf->address, + huge_page_size(h)); + if (likely(vmf->pte && + pte_same(huge_ptep_get(vmf->pte), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table @@ -6077,37 +6059,38 @@ retry_avoidcopy: if (unlikely(ret)) goto out_release_all; - if (copy_user_large_folio(new_folio, old_folio, address, vma)) { + if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) { ret = VM_FAULT_HWPOISON_LARGE; goto out_release_all; } __folio_mark_uptodate(new_folio); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, - haddr + huge_page_size(h)); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address, + vmf->address + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ - spin_lock(ptl); - ptep = hugetlb_walk(vma, haddr, huge_page_size(h)); - if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { + spin_lock(vmf->ptl); + vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); + if (likely(vmf->pte && pte_same(huge_ptep_get(vmf->pte), pte))) { pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare); /* Break COW or unshare */ - huge_ptep_clear_flush(vma, haddr, ptep); + huge_ptep_clear_flush(vma, vmf->address, vmf->pte); hugetlb_remove_rmap(old_folio); - hugetlb_add_new_anon_rmap(new_folio, vma, haddr); + hugetlb_add_new_anon_rmap(new_folio, vma, vmf->address); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); - set_huge_pte_at(mm, haddr, ptep, newpte, huge_page_size(h)); + set_huge_pte_at(mm, vmf->address, vmf->pte, newpte, + huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; } - spin_unlock(ptl); + spin_unlock(vmf->ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: /* @@ -6115,12 +6098,12 @@ out_release_all: * unshare) */ if (new_folio != old_folio) - restore_reserve_on_error(h, vma, haddr, new_folio); + restore_reserve_on_error(h, vma, vmf->address, new_folio); folio_put(new_folio); out_release_old: folio_put(old_folio); - spin_lock(ptl); /* Caller expects lock to be held */ + spin_lock(vmf->ptl); /* Caller expects lock to be held */ delayacct_wpcopy_end(); return ret; @@ -6129,8 +6112,8 @@ out_release_old: /* * Return whether there is a pagecache page to back given address within VMA. */ -static bool hugetlbfs_pagecache_present(struct hstate *h, - struct vm_area_struct *vma, unsigned long address) +bool hugetlbfs_pagecache_present(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = linear_page_index(vma, address); @@ -6206,23 +6189,19 @@ static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, return same; } -static vm_fault_t hugetlb_no_page(struct mm_struct *mm, - struct vm_area_struct *vma, - struct address_space *mapping, pgoff_t idx, - unsigned long address, pte_t *ptep, - pte_t old_pte, unsigned int flags, +static vm_fault_t hugetlb_no_page(struct address_space *mapping, struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; int anon_rmap = 0; unsigned long size; struct folio *folio; pte_t new_pte; - spinlock_t *ptl; - unsigned long haddr = address & huge_page_mask(h); bool new_folio, new_pagecache_folio = false; - u32 hash = hugetlb_fault_mutex_hash(mapping, idx); + u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); /* * Currently, we are forced to kill the process in the event the @@ -6241,10 +6220,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * before we get page_table_lock. */ new_folio = false; - folio = filemap_lock_hugetlb_folio(h, mapping, idx); + folio = filemap_lock_hugetlb_folio(h, mapping, vmf->pgoff); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); - if (idx >= size) + if (vmf->pgoff >= size) goto out; /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { @@ -6265,7 +6244,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * never happen on the page after UFFDIO_COPY has * correctly installed the page and returned. */ - if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + if (!hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } @@ -6274,7 +6253,13 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, VM_UFFD_MISSING); } - folio = alloc_hugetlb_folio(vma, haddr, 0); + if (!(vma->vm_flags & VM_MAYSHARE)) { + ret = vmf_anon_prepare(vmf); + if (unlikely(ret)) + goto out; + } + + folio = alloc_hugetlb_folio(vma, vmf->address, 0); if (IS_ERR(folio)) { /* * Returning error will result in faulting task being @@ -6288,18 +6273,20 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * here. Before returning error, get ptl and make * sure there really is no pte entry. */ - if (hugetlb_pte_stable(h, mm, ptep, old_pte)) + if (hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) ret = vmf_error(PTR_ERR(folio)); else ret = 0; goto out; } - clear_huge_page(&folio->page, address, pages_per_huge_page(h)); + clear_huge_page(&folio->page, vmf->real_address, + pages_per_huge_page(h)); __folio_mark_uptodate(folio); new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { - int err = hugetlb_add_to_page_cache(folio, mapping, idx); + int err = hugetlb_add_to_page_cache(folio, mapping, + vmf->pgoff); if (err) { /* * err can't be -EEXIST which implies someone @@ -6308,17 +6295,15 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ - restore_reserve_on_error(h, vma, haddr, folio); + restore_reserve_on_error(h, vma, vmf->address, + folio); folio_put(folio); + ret = VM_FAULT_SIGBUS; goto out; } new_pagecache_folio = true; } else { folio_lock(folio); - - ret = vmf_anon_prepare(vmf); - if (unlikely(ret)) - goto backout_unlocked; anon_rmap = 1; } } else { @@ -6338,7 +6323,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, folio_unlock(folio); folio_put(folio); /* See comment in userfaultfd_missing() block above */ - if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + if (!hugetlb_pte_stable(h, mm, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } @@ -6353,23 +6338,23 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * any allocations necessary to record that reservation occur outside * the spinlock. */ - if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { - if (vma_needs_reservation(h, vma, haddr) < 0) { + if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { + if (vma_needs_reservation(h, vma, vmf->address) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ - vma_end_reservation(h, vma, haddr); + vma_end_reservation(h, vma, vmf->address); } - ptl = huge_pte_lock(h, mm, ptep); + vmf->ptl = huge_pte_lock(h, mm, vmf->pte); ret = 0; /* If pte changed from under us, retry */ - if (!pte_same(huge_ptep_get(ptep), old_pte)) + if (!pte_same(huge_ptep_get(vmf->pte), vmf->orig_pte)) goto backout; if (anon_rmap) - hugetlb_add_new_anon_rmap(folio, vma, haddr); + hugetlb_add_new_anon_rmap(folio, vma, vmf->address); else hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE) @@ -6378,17 +6363,17 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * If this pte was previously wr-protected, keep it wr-protected even * if populated. */ - if (unlikely(pte_marker_uffd_wp(old_pte))) + if (unlikely(pte_marker_uffd_wp(vmf->orig_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); - set_huge_pte_at(mm, haddr, ptep, new_pte, huge_page_size(h)); + set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); - if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { + if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_wp(mm, vma, address, ptep, flags, folio, ptl, vmf); + ret = hugetlb_wp(folio, vmf); } - spin_unlock(ptl); + spin_unlock(vmf->ptl); /* * Only set hugetlb_migratable in newly allocated pages. Existing pages @@ -6405,10 +6390,10 @@ out: return ret; backout: - spin_unlock(ptl); + spin_unlock(vmf->ptl); backout_unlocked: if (new_folio && !new_pagecache_folio) - restore_reserve_on_error(h, vma, haddr, folio); + restore_reserve_on_error(h, vma, vmf->address, folio); folio_unlock(folio); folio_put(folio); @@ -6442,8 +6427,6 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { - pte_t *ptep, entry; - spinlock_t *ptl; vm_fault_t ret; u32 hash; struct folio *folio = NULL; @@ -6451,13 +6434,13 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, struct hstate *h = hstate_vma(vma); struct address_space *mapping; int need_wait_lock = 0; - unsigned long haddr = address & huge_page_mask(h); struct vm_fault vmf = { .vma = vma, - .address = haddr, + .address = address & huge_page_mask(h), .real_address = address, .flags = flags, - .pgoff = vma_hugecache_offset(h, vma, haddr), + .pgoff = vma_hugecache_offset(h, vma, + address & huge_page_mask(h)), /* TODO: Track hugetlb faults using vm_fault */ /* @@ -6477,22 +6460,22 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, /* * Acquire vma lock before calling huge_pte_alloc and hold - * until finished with ptep. This prevents huge_pmd_unshare from - * being called elsewhere and making the ptep no longer valid. + * until finished with vmf.pte. This prevents huge_pmd_unshare from + * being called elsewhere and making the vmf.pte no longer valid. */ hugetlb_vma_lock_read(vma); - ptep = huge_pte_alloc(mm, vma, haddr, huge_page_size(h)); - if (!ptep) { + vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h)); + if (!vmf.pte) { hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return VM_FAULT_OOM; } - entry = huge_ptep_get(ptep); - if (huge_pte_none_mostly(entry)) { - if (is_pte_marker(entry)) { + vmf.orig_pte = huge_ptep_get(vmf.pte); + if (huge_pte_none_mostly(vmf.orig_pte)) { + if (is_pte_marker(vmf.orig_pte)) { pte_marker marker = - pte_marker_get(pte_to_swp_entry(entry)); + pte_marker_get(pte_to_swp_entry(vmf.orig_pte)); if (marker & PTE_MARKER_POISONED) { ret = VM_FAULT_HWPOISON_LARGE; @@ -6506,21 +6489,20 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ - return hugetlb_no_page(mm, vma, mapping, vmf.pgoff, address, - ptep, entry, flags, &vmf); + return hugetlb_no_page(mapping, &vmf); } ret = 0; /* - * entry could be a migration/hwpoison entry at this point, so this - * check prevents the kernel from going below assuming that we have - * an active hugepage in pagecache. This goto expects the 2nd page - * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will - * properly handle it. + * vmf.orig_pte could be a migration/hwpoison vmf.orig_pte at this + * point, so this check prevents the kernel from going below assuming + * that we have an active hugepage in pagecache. This goto expects + * the 2nd page fault, and is_hugetlb_entry_(migration|hwpoisoned) + * check will properly handle it. */ - if (!pte_present(entry)) { - if (unlikely(is_hugetlb_entry_migration(entry))) { + if (!pte_present(vmf.orig_pte)) { + if (unlikely(is_hugetlb_entry_migration(vmf.orig_pte))) { /* * Release the hugetlb fault lock now, but retain * the vma lock, because it is needed to guard the @@ -6529,9 +6511,9 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * be released there. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); - migration_entry_wait_huge(vma, ptep); + migration_entry_wait_huge(vma, vmf.pte); return 0; - } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) + } else if (unlikely(is_hugetlb_entry_hwpoisoned(vmf.orig_pte))) ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; @@ -6545,13 +6527,13 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * determine if a reservation has been consumed. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && - !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(entry)) { - if (vma_needs_reservation(h, vma, haddr) < 0) { + !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) { + if (vma_needs_reservation(h, vma, vmf.address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ - vma_end_reservation(h, vma, haddr); + vma_end_reservation(h, vma, vmf.address); pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, vmf.pgoff); @@ -6559,17 +6541,17 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, pagecache_folio = NULL; } - ptl = huge_pte_lock(h, mm, ptep); + vmf.ptl = huge_pte_lock(h, mm, vmf.pte); /* Check for a racing update before calling hugetlb_wp() */ - if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) + if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(vmf.pte)))) goto out_ptl; /* Handle userfault-wp first, before trying to lock more pages */ - if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) && - (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { + if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(vmf.pte)) && + (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) { if (!userfaultfd_wp_async(vma)) { - spin_unlock(ptl); + spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); @@ -6579,18 +6561,18 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, return handle_userfault(&vmf, VM_UFFD_WP); } - entry = huge_pte_clear_uffd_wp(entry); - set_huge_pte_at(mm, haddr, ptep, entry, + vmf.orig_pte = huge_pte_clear_uffd_wp(vmf.orig_pte); + set_huge_pte_at(mm, vmf.address, vmf.pte, vmf.orig_pte, huge_page_size(hstate_vma(vma))); /* Fallthrough to CoW */ } /* - * hugetlb_wp() requires page locks of pte_page(entry) and + * hugetlb_wp() requires page locks of pte_page(vmf.orig_pte) and * pagecache_folio, so here we need take the former one * when folio != pagecache_folio or !pagecache_folio. */ - folio = page_folio(pte_page(entry)); + folio = page_folio(pte_page(vmf.orig_pte)); if (folio != pagecache_folio) if (!folio_trylock(folio)) { need_wait_lock = 1; @@ -6600,24 +6582,23 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, folio_get(folio); if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { - if (!huge_pte_write(entry)) { - ret = hugetlb_wp(mm, vma, address, ptep, flags, - pagecache_folio, ptl, &vmf); + if (!huge_pte_write(vmf.orig_pte)) { + ret = hugetlb_wp(pagecache_folio, &vmf); goto out_put_page; } else if (likely(flags & FAULT_FLAG_WRITE)) { - entry = huge_pte_mkdirty(entry); + vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte); } } - entry = pte_mkyoung(entry); - if (huge_ptep_set_access_flags(vma, haddr, ptep, entry, + vmf.orig_pte = pte_mkyoung(vmf.orig_pte); + if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte, flags & FAULT_FLAG_WRITE)) - update_mmu_cache(vma, haddr, ptep); + update_mmu_cache(vma, vmf.address, vmf.pte); out_put_page: if (folio != pagecache_folio) folio_unlock(folio); folio_put(folio); out_ptl: - spin_unlock(ptl); + spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); @@ -6653,7 +6634,13 @@ static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); - folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask); + /* + * This is used to allocate a temporary hugetlb to hold the copied + * content, which will then be copied again to the final hugetlb + * consuming a reservation. Set the alloc_fallback to false to indicate + * that breaking the per-node hugetlb pool is not allowed in this case. + */ + folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false); mpol_cond_put(mpol); return folio; @@ -6883,77 +6870,6 @@ out_release_nounlock: } #endif /* CONFIG_USERFAULTFD */ -struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned int *page_mask) -{ - struct hstate *h = hstate_vma(vma); - struct mm_struct *mm = vma->vm_mm; - unsigned long haddr = address & huge_page_mask(h); - struct page *page = NULL; - spinlock_t *ptl; - pte_t *pte, entry; - int ret; - - hugetlb_vma_lock_read(vma); - pte = hugetlb_walk(vma, haddr, huge_page_size(h)); - if (!pte) - goto out_unlock; - - ptl = huge_pte_lock(h, mm, pte); - entry = huge_ptep_get(pte); - if (pte_present(entry)) { - page = pte_page(entry); - - if (!huge_pte_write(entry)) { - if (flags & FOLL_WRITE) { - page = NULL; - goto out; - } - - if (gup_must_unshare(vma, flags, page)) { - /* Tell the caller to do unsharing */ - page = ERR_PTR(-EMLINK); - goto out; - } - } - - page = nth_page(page, ((address & ~huge_page_mask(h)) >> PAGE_SHIFT)); - - /* - * Note that page may be a sub-page, and with vmemmap - * optimizations the page struct may be read only. - * try_grab_page() will increase the ref count on the - * head page, so this will be OK. - * - * try_grab_page() should always be able to get the page here, - * because we hold the ptl lock and have verified pte_present(). - */ - ret = try_grab_page(page, flags); - - if (WARN_ON_ONCE(ret)) { - page = ERR_PTR(ret); - goto out; - } - - *page_mask = (1U << huge_page_order(h)) - 1; - } -out: - spin_unlock(ptl); -out_unlock: - hugetlb_vma_unlock_read(vma); - - /* - * Fixup retval for dump requests: if pagecache doesn't exist, - * don't try to allocate a new page but just skip it. - */ - if (!page && (flags & FOLL_DUMP) && - !hugetlbfs_pagecache_present(h, vma, address)) - page = ERR_PTR(-EFAULT); - - return page; -} - long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) @@ -7877,9 +7793,9 @@ void __init hugetlb_cma_reserve(int order) * huge page demotion. */ res = cma_declare_contiguous_nid(0, size, 0, - PAGE_SIZE << HUGETLB_PAGE_ORDER, - 0, false, name, - &hugetlb_cma[nid], nid); + PAGE_SIZE << HUGETLB_PAGE_ORDER, + HUGETLB_PAGE_ORDER, false, name, + &hugetlb_cma[nid], nid); if (res) { pr_warn("hugetlb_cma: reservation failed: err %d, node %d", res, nid); diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index aa4486bd390493..e20339a346b935 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -308,7 +308,7 @@ static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, { if (hugetlb_cgroup_disabled() || !h_cg) return; - + lockdep_assert_held(&hugetlb_lock); __set_hugetlb_cgroup(folio, h_cg, rsvd); if (!rsvd) { unsigned long usage = diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index da177e49d95648..b9a55322e52ce9 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -679,7 +679,6 @@ static struct ctl_table hugetlb_vmemmap_sysctls[] = { .mode = 0644, .proc_handler = proc_dobool, }, - { } }; static int __init hugetlb_vmemmap_init(void) diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index d0548e382b6ba2..c9d653f51e45bb 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -15,7 +15,7 @@ static int hwpoison_inject(void *data, u64 val) { unsigned long pfn = val; struct page *p; - struct page *hpage; + struct folio *folio; int err; if (!capable(CAP_SYS_ADMIN)) @@ -25,16 +25,17 @@ static int hwpoison_inject(void *data, u64 val) return -ENXIO; p = pfn_to_page(pfn); - hpage = compound_head(p); + folio = page_folio(p); if (!hwpoison_filter_enable) goto inject; - shake_page(hpage); + shake_folio(folio); /* * This implies unable to support non-LRU pages except free page. */ - if (!PageLRU(hpage) && !PageHuge(p) && !is_free_buddy_page(p)) + if (!folio_test_lru(folio) && !folio_test_hugetlb(folio) && + !is_free_buddy_page(p)) return 0; /* @@ -42,7 +43,7 @@ static int hwpoison_inject(void *data, u64 val) * the targeted owner (or on a free page). * memory_failure() will redo the check reliably inside page lock. */ - err = hwpoison_filter(hpage); + err = hwpoison_filter(&folio->page); if (err) return 0; diff --git a/mm/internal.h b/mm/internal.h index 07ad2675a88b47..c5552d35d99551 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -11,6 +11,8 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> +#include <linux/swap.h> +#include <linux/swapops.h> #include <linux/tracepoint-defs.h> struct folio_batch; @@ -70,13 +72,30 @@ void page_writeback_init(void); /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. + * + * Don't use this function outside of debugging code. */ -static inline int folio_nr_pages_mapped(struct folio *folio) +static inline int folio_nr_pages_mapped(const struct folio *folio) { return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } -static inline void *folio_raw_mapping(struct folio *folio) +/* + * Retrieve the first entry of a folio based on a provided entry within the + * folio. We cannot rely on folio->swap as there is no guarantee that it has + * been initialized. Used for calling arch_swap_restore() + */ +static inline swp_entry_t folio_swap(swp_entry_t entry, + const struct folio *folio) +{ + swp_entry_t swap = { + .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), + }; + + return swap; +} + +static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; @@ -113,6 +132,10 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. + * @any_young: Optional pointer to indicate whether any entry except the + * first one is young. + * @any_dirty: Optional pointer to indicate whether any entry except the + * first one is dirty. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. @@ -128,16 +151,20 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, - bool *any_writable) + bool *any_writable, bool *any_young, bool *any_dirty) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; - bool writable; + bool writable, young, dirty; int nr; if (any_writable) *any_writable = false; + if (any_young) + *any_young = false; + if (any_dirty) + *any_dirty = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); @@ -151,6 +178,10 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); + if (any_young) + young = !!pte_young(pte); + if (any_dirty) + dirty = !!pte_dirty(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) @@ -166,6 +197,10 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, if (any_writable) *any_writable |= writable; + if (any_young) + *any_young |= young; + if (any_dirty) + *any_dirty |= dirty; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); @@ -174,6 +209,68 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, return min(ptep - start_ptep, max_nr); } + +/** + * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. + * @pte: The initial pte state; is_swap_pte(pte) must be true and + * non_swap_entry() must be false. + * + * Increments the swap offset, while maintaining all other fields, including + * swap type, and any swp pte bits. The resulting pte is returned. + */ +static inline pte_t pte_next_swp_offset(pte_t pte) +{ + swp_entry_t entry = pte_to_swp_entry(pte); + pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), + (swp_offset(entry) + 1))); + + if (pte_swp_soft_dirty(pte)) + new = pte_swp_mksoft_dirty(new); + if (pte_swp_exclusive(pte)) + new = pte_swp_mkexclusive(new); + if (pte_swp_uffd_wp(pte)) + new = pte_swp_mkuffd_wp(new); + + return new; +} + +/** + * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries + * @start_ptep: Page table pointer for the first entry. + * @max_nr: The maximum number of table entries to consider. + * @pte: Page table entry for the first entry. + * + * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs + * containing swap entries all with consecutive offsets and targeting the same + * swap type, all with matching swp pte bits. + * + * max_nr must be at least one and must be limited by the caller so scanning + * cannot exceed a single page table. + * + * Return: the number of table entries in the batch. + */ +static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) +{ + pte_t expected_pte = pte_next_swp_offset(pte); + const pte_t *end_ptep = start_ptep + max_nr; + pte_t *ptep = start_ptep + 1; + + VM_WARN_ON(max_nr < 1); + VM_WARN_ON(!is_swap_pte(pte)); + VM_WARN_ON(non_swap_entry(pte_to_swp_entry(pte))); + + while (ptep < end_ptep) { + pte = ptep_get(ptep); + + if (!pte_same(pte, expected_pte)) + break; + + expected_pte = pte_next_swp_offset(expected_pte); + ptep++; + } + + return ptep - start_ptep; +} #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, @@ -491,6 +588,7 @@ extern void __putback_isolated_page(struct page *page, unsigned int order, extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); +extern void kernel_init_pages(struct page *page, int numpages); /* * This will have no effect, other than possibly generating a warning, if the @@ -513,7 +611,8 @@ static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; - folio_prep_large_rmappable(folio); + if (folio && folio_test_large(folio)) + folio_set_large_rmappable(folio); return folio; } @@ -522,9 +621,12 @@ static inline void prep_compound_head(struct page *page, unsigned int order) struct folio *folio = (struct folio *)page; folio_set_order(folio, order); + atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); + if (order > 1) + INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) @@ -559,10 +661,6 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int); - -int split_free_page(struct page *free_page, - unsigned int order, unsigned long split_pfn_offset); - #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* @@ -789,13 +887,17 @@ void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); -/* - * Return the start of user virtual address at the specific offset within - * a vma. +/** + * vma_address - Find the virtual address a page range is mapped at + * @vma: The vma which maps this object. + * @pgoff: The page offset within its object. + * @nr_pages: The number of pages to consider. + * + * If any page in this range is mapped by this VMA, return the first address + * where any of these pages appear. Otherwise, return -EFAULT. */ -static inline unsigned long -vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages, - struct vm_area_struct *vma) +static inline unsigned long vma_address(struct vm_area_struct *vma, + pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; @@ -815,18 +917,6 @@ vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages, } /* - * Return the start of user virtual address of a page within a vma. - * Returns -EFAULT if all of the page is outside the range of vma. - * If page is a compound head, the entire compound page is considered. - */ -static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) -{ - VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ - return vma_pgoff_address(page_to_pgoff(page), compound_nr(page), vma); -} - -/* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ @@ -947,6 +1037,7 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask) /* * mm/memory-failure.c */ +void shake_folio(struct folio *folio); extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; @@ -1040,17 +1131,13 @@ static inline bool is_migrate_highatomic(enum migratetype migratetype) return migratetype == MIGRATE_HIGHATOMIC; } -static inline bool is_migrate_highatomic_page(struct page *page) -{ - return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC; -} - void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; + enum migrate_reason reason; }; /* @@ -1087,10 +1174,10 @@ void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); -int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma, +int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int page_nid, int *flags); -void free_zone_device_page(struct page *page); +void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_page(struct page *page); /* @@ -1102,9 +1189,10 @@ int __must_check try_grab_page(struct page *page, unsigned int flags); /* * mm/huge_memory.c */ -struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, - unsigned int flags); +void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, bool write); +void touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, bool write); /* * mm/mmap.c @@ -1189,20 +1277,10 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma, } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* - * During GUP-fast we might not get called on the head page for a - * hugetlb page that is mapped using cont-PTE, because GUP-fast does - * not work with the abstracted hugetlb PTEs that always point at the - * head page. For hugetlb, PageAnonExclusive only applies on the head - * page (as it cannot be partially COW-shared), so lookup the head page. - */ - if (unlikely(!PageHead(page) && PageHuge(page))) - page = compound_head(page); - - /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. */ @@ -1245,6 +1323,35 @@ static inline void vma_iter_config(struct vma_iterator *vmi, __mas_set_range(&vmi->mas, index, last - 1); } +static inline void vma_iter_reset(struct vma_iterator *vmi) +{ + mas_reset(&vmi->mas); +} + +static inline +struct vm_area_struct *vma_iter_prev_range_limit(struct vma_iterator *vmi, unsigned long min) +{ + return mas_prev_range(&vmi->mas, min); +} + +static inline +struct vm_area_struct *vma_iter_next_range_limit(struct vma_iterator *vmi, unsigned long max) +{ + return mas_next_range(&vmi->mas, max); +} + +static inline int vma_iter_area_lowest(struct vma_iterator *vmi, unsigned long min, + unsigned long max, unsigned long size) +{ + return mas_empty_area(&vmi->mas, min, max - 1, size); +} + +static inline int vma_iter_area_highest(struct vma_iterator *vmi, unsigned long min, + unsigned long max, unsigned long size) +{ + return mas_empty_area_rev(&vmi->mas, min, max - 1, size); +} + /* * VMA Iterator functions shared between nommu and mmap */ @@ -1328,6 +1435,43 @@ void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); +#ifdef CONFIG_64BIT +/* VM is sealed, in vm_flags */ +#define VM_SEALED _BITUL(63) +#endif + +#ifdef CONFIG_64BIT +static inline int can_do_mseal(unsigned long flags) +{ + if (flags) + return -EINVAL; + + return 0; +} + +bool can_modify_mm(struct mm_struct *mm, unsigned long start, + unsigned long end); +bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, + unsigned long end, int behavior); +#else +static inline int can_do_mseal(unsigned long flags) +{ + return -EPERM; +} + +static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start, + unsigned long end) +{ + return true; +} + +static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, + unsigned long end, int behavior) +{ + return true; +} +#endif + #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 2b994092a2d430..9958ebc15d3830 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -16,6 +16,7 @@ #include <linux/static_key.h> #include <linux/string.h> #include <linux/types.h> +#include <linux/vmalloc.h> #include "kasan.h" diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 8350f5c06f2e0a..964b8482275ba0 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -595,9 +595,9 @@ static unsigned long kfence_init_pool(void) continue; __folio_set_slab(slab_folio(slab)); -#ifdef CONFIG_MEMCG - slab->memcg_data = (unsigned long)&kfence_metadata_init[i / 2 - 1].objcg | - MEMCG_DATA_OBJCGS; +#ifdef CONFIG_MEMCG_KMEM + slab->obj_exts = (unsigned long)&kfence_metadata_init[i / 2 - 1].obj_exts | + MEMCG_DATA_OBJEXTS; #endif } @@ -645,8 +645,8 @@ reset_slab: if (!i || (i % 2)) continue; -#ifdef CONFIG_MEMCG - slab->memcg_data = 0; +#ifdef CONFIG_MEMCG_KMEM + slab->obj_exts = 0; #endif __folio_clear_slab(slab_folio(slab)); } @@ -1139,8 +1139,8 @@ void __kfence_free(void *addr) { struct kfence_metadata *meta = addr_to_metadata((unsigned long)addr); -#ifdef CONFIG_MEMCG - KFENCE_WARN_ON(meta->objcg); +#ifdef CONFIG_MEMCG_KMEM + KFENCE_WARN_ON(meta->obj_exts.objcg); #endif /* * If the objects of the cache are SLAB_TYPESAFE_BY_RCU, defer freeing diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index f46fbb03062b9c..084f5f36e8e76a 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -97,8 +97,8 @@ struct kfence_metadata { struct kfence_track free_track; /* For updating alloc_covered on frees. */ u32 alloc_stack_hash; -#ifdef CONFIG_MEMCG - struct obj_cgroup *objcg; +#ifdef CONFIG_MEMCG_KMEM + struct slabobj_ext obj_exts; #endif }; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 38830174608fba..774a97e6e2da39 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -453,7 +453,7 @@ void khugepaged_enter_vma(struct vm_area_struct *vma, { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_flags_enabled()) { - if (thp_vma_allowable_order(vma, vm_flags, false, false, true, + if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } @@ -583,7 +583,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); - if (page_mapcount(page) > 1) { + /* See hpage_collapse_scan_pmd(). */ + if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { @@ -767,7 +768,7 @@ static void __collapse_huge_page_copy_failed(pte_t *pte, * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. * * @pte: starting of the PTEs to copy from - * @page: the new hugepage to copy contents to + * @folio: the new hugepage to copy contents to * @pmd: pointer to the new hugepage's PMD * @orig_pmd: the original raw pages' PMD * @vma: the original raw pages' virtual memory area @@ -775,33 +776,29 @@ static void __collapse_huge_page_copy_failed(pte_t *pte, * @ptl: lock on raw pages' PTEs * @compound_pagelist: list that stores compound pages */ -static int __collapse_huge_page_copy(pte_t *pte, - struct page *page, - pmd_t *pmd, - pmd_t orig_pmd, - struct vm_area_struct *vma, - unsigned long address, - spinlock_t *ptl, - struct list_head *compound_pagelist) +static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, + pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, + unsigned long address, spinlock_t *ptl, + struct list_head *compound_pagelist) { - struct page *src_page; - pte_t *_pte; - pte_t pteval; - unsigned long _address; + unsigned int i; int result = SCAN_SUCCEED; /* * Copying pages' contents is subject to memory poison at any iteration. */ - for (_pte = pte, _address = address; _pte < pte + HPAGE_PMD_NR; - _pte++, page++, _address += PAGE_SIZE) { - pteval = ptep_get(_pte); + for (i = 0; i < HPAGE_PMD_NR; i++) { + pte_t pteval = ptep_get(pte + i); + struct page *page = folio_page(folio, i); + unsigned long src_addr = address + i * PAGE_SIZE; + struct page *src_page; + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { - clear_user_highpage(page, _address); + clear_user_highpage(page, src_addr); continue; } src_page = pte_page(pteval); - if (copy_mc_user_highpage(page, src_page, _address, vma) > 0) { + if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) { result = SCAN_COPY_MC; break; } @@ -891,20 +888,6 @@ static int hpage_collapse_find_target_node(struct collapse_control *cc) } #endif -static bool hpage_collapse_alloc_folio(struct folio **folio, gfp_t gfp, int node, - nodemask_t *nmask) -{ - *folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, nmask); - - if (unlikely(!*folio)) { - count_vm_event(THP_COLLAPSE_ALLOC_FAILED); - return false; - } - - count_vm_event(THP_COLLAPSE_ALLOC); - return true; -} - /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. @@ -917,6 +900,7 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, struct collapse_control *cc) { struct vm_area_struct *vma; + unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; @@ -927,8 +911,7 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; - if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, - cc->is_khugepaged, PMD_ORDER)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then @@ -1059,7 +1042,7 @@ out: return result; } -static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, +static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : @@ -1067,20 +1050,23 @@ static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, int node = hpage_collapse_find_target_node(cc); struct folio *folio; - if (!hpage_collapse_alloc_folio(&folio, gfp, node, &cc->alloc_nmask)) { - *hpage = NULL; + folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); + if (!folio) { + *foliop = NULL; + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; } + count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); - *hpage = NULL; + *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); - *hpage = folio_page(folio, 0); + *foliop = folio; return SCAN_SUCCEED; } @@ -1093,7 +1079,6 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, pte_t *pte; pgtable_t pgtable; struct folio *folio; - struct page *hpage; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; struct vm_area_struct *vma; @@ -1109,7 +1094,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, */ mmap_read_unlock(mm); - result = alloc_charge_hpage(&hpage, mm, cc); + result = alloc_charge_folio(&folio, mm, cc); if (result != SCAN_SUCCEED) goto out_nolock; @@ -1169,7 +1154,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * - * Parallel fast GUP is fine since fast GUP will back off when + * Parallel GUP-fast is fine since GUP-fast will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); @@ -1208,14 +1193,13 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, */ anon_vma_unlock_write(vma->anon_vma); - result = __collapse_huge_page_copy(pte, hpage, pmd, _pmd, + result = __collapse_huge_page_copy(pte, folio, pmd, _pmd, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); if (unlikely(result != SCAN_SUCCEED)) goto out_up_write; - folio = page_folio(hpage); /* * The smp_wmb() inside __folio_mark_uptodate() ensures the * copy_huge_page writes become visible before the set_pmd_at() @@ -1224,7 +1208,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); - _pmd = mk_huge_pmd(hpage, vma->vm_page_prot); + _pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); @@ -1236,14 +1220,14 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, update_mmu_cache_pmd(vma, address, pmd); spin_unlock(pmd_ptl); - hpage = NULL; + folio = NULL; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: - if (hpage) - put_page(hpage); + if (folio) + folio_put(folio); trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } @@ -1334,8 +1318,20 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, result = SCAN_PAGE_NULL; goto out_unmap; } + folio = page_folio(page); + + if (!folio_test_anon(folio)) { + result = SCAN_PAGE_ANON; + goto out_unmap; + } - if (page_mapcount(page) > 1) { + /* + * We treat a single page as shared if any part of the THP + * is shared. "False negatives" from + * folio_likely_mapped_shared() are not expected to matter + * much in practice. + */ + if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { @@ -1345,7 +1341,6 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, } } - folio = page_folio(page); /* * Record which node the original page is from and save this * information to cc->node_load[]. @@ -1366,16 +1361,12 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, result = SCAN_PAGE_LOCK; goto out_unmap; } - if (!folio_test_anon(folio)) { - result = SCAN_PAGE_ANON; - goto out_unmap; - } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: - * it may see total_mapcount > refcount in some cases? + * it may see folio_mapcount() > folio_ref_count(). * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check @@ -1510,8 +1501,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ - if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false, - PMD_ORDER)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ @@ -1797,29 +1787,26 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; - struct page *hpage; - struct page *page; - struct page *tmp; - struct folio *folio; + struct page *dst; + struct folio *folio, *tmp, *new_folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); - int nr = 0; VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); - result = alloc_charge_hpage(&hpage, mm, cc); + result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; - __SetPageLocked(hpage); + __folio_set_locked(new_folio); if (is_shmem) - __SetPageSwapBacked(hpage); - hpage->index = start; - hpage->mapping = mapping; + __folio_set_swapbacked(new_folio); + new_folio->index = start; + new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is @@ -1839,11 +1826,11 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, for (index = start; index < end; index++) { xas_set(&xas, index); - page = xas_load(&xas); + folio = xas_load(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { - if (!page) { + if (!folio) { /* * Stop if extent has been truncated or * hole-punched, and is now completely @@ -1859,7 +1846,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, continue; } - if (xa_is_value(page) || !PageUptodate(page)) { + if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, @@ -1869,28 +1856,27 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, } /* drain lru cache to help isolate_lru_page() */ lru_add_drain(); - page = folio_file_page(folio, index); - } else if (trylock_page(page)) { - get_page(page); + } else if (folio_trylock(folio)) { + folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ - if (!page || xa_is_value(page)) { + if (!folio || xa_is_value(folio)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain lru cache to help isolate_lru_page() */ lru_add_drain(); - page = find_lock_page(mapping, index); - if (unlikely(page == NULL)) { + folio = filemap_lock_folio(mapping, index); + if (IS_ERR(folio)) { result = SCAN_FAIL; goto xa_unlocked; } - } else if (PageDirty(page)) { + } else if (folio_test_dirty(folio)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't @@ -1908,12 +1894,12 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; - } else if (PageWriteback(page)) { + } else if (folio_test_writeback(folio)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; - } else if (trylock_page(page)) { - get_page(page); + } else if (folio_trylock(folio)) { + folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; @@ -1922,35 +1908,31 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, } /* - * The page must be locked, so we can drop the i_pages lock + * The folio must be locked, so we can drop the i_pages lock * without racing with truncate. */ - VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - /* make sure the page is up to date */ - if (unlikely(!PageUptodate(page))) { + /* make sure the folio is up to date */ + if (unlikely(!folio_test_uptodate(folio))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before - * we locked the first page, then a THP might be there already. + * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ - if (PageTransCompound(page)) { - struct page *head = compound_head(page); - - result = compound_order(head) == HPAGE_PMD_ORDER && - head->index == start + if (folio_test_large(folio)) { + result = folio_order(folio) == HPAGE_PMD_ORDER && + folio->index == start /* Maybe PMD-mapped */ ? SCAN_PTE_MAPPED_HUGEPAGE : SCAN_PAGE_COMPOUND; goto out_unlock; } - folio = page_folio(page); - if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; @@ -1960,7 +1942,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this - * page is dirty because it hasn't been flushed + * folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; @@ -1984,33 +1966,34 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, xas_lock_irq(&xas); - VM_BUG_ON_PAGE(page != xa_load(xas.xa, index), page); + VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio); /* - * We control three references to the page: + * We control three references to the folio: * - we hold a pin on it; * - one reference from page cache; - * - one from isolate_lru_page; - * If those are the only references, then any new usage of the - * page will have to fetch it from the page cache. That requires - * locking the page to handle truncate, so any new usage will be - * blocked until we unlock page after collapse/during rollback. + * - one from lru_isolate_folio; + * If those are the only references, then any new usage + * of the folio will have to fetch it from the page + * cache. That requires locking the folio to handle + * truncate, so any new usage will be blocked until we + * unlock folio after collapse/during rollback. */ - if (page_count(page) != 3) { + if (folio_ref_count(folio) != 3) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); - putback_lru_page(page); + folio_putback_lru(folio); goto out_unlock; } /* - * Accumulate the pages that are being collapsed. + * Accumulate the folios that are being collapsed. */ - list_add_tail(&page->lru, &pagelist); + list_add_tail(&folio->lru, &pagelist); continue; out_unlock: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); goto xa_unlocked; } @@ -2049,23 +2032,27 @@ xa_unlocked: } /* - * The old pages are locked, so they won't change anymore. + * The old folios are locked, so they won't change anymore. */ index = start; - list_for_each_entry(page, &pagelist, lru) { - while (index < page->index) { - clear_highpage(hpage + (index % HPAGE_PMD_NR)); + dst = folio_page(new_folio, 0); + list_for_each_entry(folio, &pagelist, lru) { + while (index < folio->index) { + clear_highpage(dst); index++; + dst++; } - if (copy_mc_highpage(hpage + (page->index % HPAGE_PMD_NR), page) > 0) { + if (copy_mc_highpage(dst, folio_page(folio, 0)) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; + dst++; } while (index < end) { - clear_highpage(hpage + (index % HPAGE_PMD_NR)); + clear_highpage(dst); index++; + dst++; } if (nr_none) { @@ -2093,16 +2080,17 @@ xa_unlocked: } /* - * If userspace observed a missing page in a VMA with a MODE_MISSING - * userfaultfd, then it might expect a UFFD_EVENT_PAGEFAULT for that - * page. If so, we need to roll back to avoid suppressing such an - * event. Since wp/minor userfaultfds don't give userspace any - * guarantees that the kernel doesn't fill a missing page with a zero - * page, so they don't matter here. + * If userspace observed a missing page in a VMA with + * a MODE_MISSING userfaultfd, then it might expect a + * UFFD_EVENT_PAGEFAULT for that page. If so, we need to + * roll back to avoid suppressing such an event. Since + * wp/minor userfaultfds don't give userspace any + * guarantees that the kernel doesn't fill a missing + * page with a zero page, so they don't matter here. * - * Any userfaultfds registered after this point will not be able to - * observe any missing pages due to the previously inserted retry - * entries. + * Any userfaultfds registered after this point will + * not be able to observe any missing pages due to the + * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { @@ -2127,33 +2115,32 @@ immap_locked: xas_lock_irq(&xas); } - folio = page_folio(hpage); - nr = folio_nr_pages(folio); if (is_shmem) - __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); + __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else - __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); + __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_none); + __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ - __lruvec_stat_mod_folio(folio, NR_SHMEM, nr_none); + __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* - * Mark hpage as uptodate before inserting it into the page cache so - * that it isn't mistaken for an fallocated but unwritten page. + * Mark new_folio as uptodate before inserting it into the + * page cache so that it isn't mistaken for an fallocated but + * unwritten page. */ - folio_mark_uptodate(folio); - folio_ref_add(folio, HPAGE_PMD_NR - 1); + folio_mark_uptodate(new_folio); + folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) - folio_mark_dirty(folio); - folio_add_lru(folio); + folio_mark_dirty(new_folio); + folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); - xas_store(&xas, folio); + xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); @@ -2164,18 +2151,18 @@ immap_locked: retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; - folio_unlock(folio); + folio_unlock(new_folio); /* - * The collapse has succeeded, so free the old pages. + * The collapse has succeeded, so free the old folios. */ - list_for_each_entry_safe(page, tmp, &pagelist, lru) { - list_del(&page->lru); - page->mapping = NULL; - ClearPageActive(page); - ClearPageUnevictable(page); - unlock_page(page); - folio_put_refs(page_folio(page), 3); + list_for_each_entry_safe(folio, tmp, &pagelist, lru) { + list_del(&folio->lru); + folio->mapping = NULL; + folio_clear_active(folio); + folio_clear_unevictable(folio); + folio_unlock(folio); + folio_put_refs(folio, 3); } goto out; @@ -2189,11 +2176,11 @@ rollback: shmem_uncharge(mapping->host, nr_none); } - list_for_each_entry_safe(page, tmp, &pagelist, lru) { - list_del(&page->lru); - unlock_page(page); - putback_lru_page(page); - put_page(page); + list_for_each_entry_safe(folio, tmp, &pagelist, lru) { + list_del(&folio->lru); + folio_unlock(folio); + folio_putback_lru(folio); + folio_put(folio); } /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM @@ -2209,13 +2196,13 @@ rollback: smp_mb(); } - hpage->mapping = NULL; + new_folio->mapping = NULL; - unlock_page(hpage); - put_page(hpage); + folio_unlock(new_folio); + folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); - trace_mm_khugepaged_collapse_file(mm, hpage, index, is_shmem, addr, file, nr, result); + trace_mm_khugepaged_collapse_file(mm, new_folio, index, is_shmem, addr, file, HPAGE_PMD_NR, result); return result; } @@ -2223,7 +2210,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { - struct page *page = NULL; + struct folio *folio = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; @@ -2235,11 +2222,11 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); rcu_read_lock(); - xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) { + if (xas_retry(&xas, folio)) continue; - if (xa_is_value(page)) { + if (xa_is_value(folio)) { ++swap; if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { @@ -2254,11 +2241,9 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, * TODO: khugepaged should compact smaller compound pages * into a PMD sized page */ - if (PageTransCompound(page)) { - struct page *head = compound_head(page); - - result = compound_order(head) == HPAGE_PMD_ORDER && - head->index == start + if (folio_test_large(folio)) { + result = folio_order(folio) == HPAGE_PMD_ORDER && + folio->index == start /* Maybe PMD-mapped */ ? SCAN_PTE_MAPPED_HUGEPAGE : SCAN_PAGE_COMPOUND; @@ -2271,28 +2256,29 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, break; } - node = page_to_nid(page); + node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; - if (!PageLRU(page)) { + if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; break; } - if (page_count(page) != - 1 + page_mapcount(page) + page_has_private(page)) { + if (folio_ref_count(folio) != + 1 + folio_mapcount(folio) + folio_test_private(folio)) { result = SCAN_PAGE_COUNT; break; } /* - * We probably should check if the page is referenced here, but - * nobody would transfer pte_young() to PageReferenced() for us. - * And rmap walk here is just too costly... + * We probably should check if the folio is referenced + * here, but nobody would transfer pte_young() to + * folio_test_referenced() for us. And rmap walk here + * is just too costly... */ present++; @@ -2314,7 +2300,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, } } - trace_mm_khugepaged_scan_file(mm, page, file, present, swap, result); + trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result); return result; } #else @@ -2376,8 +2362,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, progress++; break; } - if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, - true, PMD_ORDER)) { + if (!thp_vma_allowable_order(vma, vma->vm_flags, + TVA_ENFORCE_SYSFS, PMD_ORDER)) { skip: progress++; continue; @@ -2714,8 +2700,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, *prev = vma; - if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false, - PMD_ORDER)) + if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 6a540c2b27c524..fdcf01f622028f 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -158,9 +158,9 @@ struct kmemleak_object { int count; /* checksum for detecting modified objects */ u32 checksum; + depot_stack_handle_t trace_handle; /* memory ranges to be scanned inside an object (empty for all) */ struct hlist_head area_list; - depot_stack_handle_t trace_handle; unsigned long jiffies; /* creation timestamp */ pid_t pid; /* pid of the current task */ char comm[TASK_COMM_LEN]; /* executable name */ @@ -463,7 +463,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) /* try the slab allocator first */ if (object_cache) { - object = kmem_cache_alloc(object_cache, gfp_kmemleak_mask(gfp)); + object = kmem_cache_alloc_noprof(object_cache, gfp_kmemleak_mask(gfp)); if (object) return object; } @@ -947,7 +947,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) untagged_objp = (unsigned long)kasan_reset_tag((void *)object->pointer); if (scan_area_cache) - area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp)); + area = kmem_cache_alloc_noprof(scan_area_cache, gfp_kmemleak_mask(gfp)); raw_spin_lock_irqsave(&object->lock, flags); if (!area) { diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c index 0b09daa188ef6c..22e8657800effb 100644 --- a/mm/kmsan/hooks.c +++ b/mm/kmsan/hooks.c @@ -285,6 +285,17 @@ void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy, } EXPORT_SYMBOL(kmsan_copy_to_user); +void kmsan_memmove(void *to, const void *from, size_t size) +{ + if (!kmsan_enabled || kmsan_in_runtime()) + return; + + kmsan_enter_runtime(); + kmsan_internal_memmove_metadata(to, (void *)from, size); + kmsan_leave_runtime(); +} +EXPORT_SYMBOL(kmsan_memmove); + /* Helper function to check an URB. */ void kmsan_handle_urb(const struct urb *urb, bool is_out) { diff --git a/mm/ksm.c b/mm/ksm.c index 8c001819cf10f5..e1034bf1c937e9 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -890,14 +890,14 @@ static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node) free_stable_node(stable_node); } -enum get_ksm_page_flags { - GET_KSM_PAGE_NOLOCK, - GET_KSM_PAGE_LOCK, - GET_KSM_PAGE_TRYLOCK +enum ksm_get_folio_flags { + KSM_GET_FOLIO_NOLOCK, + KSM_GET_FOLIO_LOCK, + KSM_GET_FOLIO_TRYLOCK }; /* - * get_ksm_page: checks if the page indicated by the stable node + * ksm_get_folio: checks if the page indicated by the stable node * is still its ksm page, despite having held no reference to it. * In which case we can trust the content of the page, and it * returns the gotten page; but if the page has now been zapped, @@ -915,10 +915,10 @@ enum get_ksm_page_flags { * a page to put something that might look like our key in page->mapping. * is on its way to being freed; but it is an anomaly to bear in mind. */ -static struct page *get_ksm_page(struct ksm_stable_node *stable_node, - enum get_ksm_page_flags flags) +static struct folio *ksm_get_folio(struct ksm_stable_node *stable_node, + enum ksm_get_folio_flags flags) { - struct page *page; + struct folio *folio; void *expected_mapping; unsigned long kpfn; @@ -926,8 +926,8 @@ static struct page *get_ksm_page(struct ksm_stable_node *stable_node, PAGE_MAPPING_KSM); again: kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */ - page = pfn_to_page(kpfn); - if (READ_ONCE(page->mapping) != expected_mapping) + folio = pfn_folio(kpfn); + if (READ_ONCE(folio->mapping) != expected_mapping) goto stale; /* @@ -940,41 +940,41 @@ again: * in folio_migrate_mapping(), it might still be our page, * in which case it's essential to keep the node. */ - while (!get_page_unless_zero(page)) { + while (!folio_try_get(folio)) { /* * Another check for page->mapping != expected_mapping would * work here too. We have chosen the !PageSwapCache test to * optimize the common case, when the page is or is about to * be freed: PageSwapCache is cleared (under spin_lock_irq) * in the ref_freeze section of __remove_mapping(); but Anon - * page->mapping reset to NULL later, in free_pages_prepare(). + * folio->mapping reset to NULL later, in free_pages_prepare(). */ - if (!PageSwapCache(page)) + if (!folio_test_swapcache(folio)) goto stale; cpu_relax(); } - if (READ_ONCE(page->mapping) != expected_mapping) { - put_page(page); + if (READ_ONCE(folio->mapping) != expected_mapping) { + folio_put(folio); goto stale; } - if (flags == GET_KSM_PAGE_TRYLOCK) { - if (!trylock_page(page)) { - put_page(page); + if (flags == KSM_GET_FOLIO_TRYLOCK) { + if (!folio_trylock(folio)) { + folio_put(folio); return ERR_PTR(-EBUSY); } - } else if (flags == GET_KSM_PAGE_LOCK) - lock_page(page); + } else if (flags == KSM_GET_FOLIO_LOCK) + folio_lock(folio); - if (flags != GET_KSM_PAGE_NOLOCK) { - if (READ_ONCE(page->mapping) != expected_mapping) { - unlock_page(page); - put_page(page); + if (flags != KSM_GET_FOLIO_NOLOCK) { + if (READ_ONCE(folio->mapping) != expected_mapping) { + folio_unlock(folio); + folio_put(folio); goto stale; } } - return page; + return folio; stale: /* @@ -998,16 +998,16 @@ static void remove_rmap_item_from_tree(struct ksm_rmap_item *rmap_item) { if (rmap_item->address & STABLE_FLAG) { struct ksm_stable_node *stable_node; - struct page *page; + struct folio *folio; stable_node = rmap_item->head; - page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); - if (!page) + folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); + if (!folio) goto out; hlist_del(&rmap_item->hlist); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (!hlist_empty(&stable_node->hlist)) ksm_pages_sharing--; @@ -1094,11 +1094,11 @@ static inline struct ksm_stable_node *page_stable_node(struct page *page) return folio_stable_node(page_folio(page)); } -static inline void set_page_stable_node(struct page *page, - struct ksm_stable_node *stable_node) +static inline void folio_set_stable_node(struct folio *folio, + struct ksm_stable_node *stable_node) { - VM_BUG_ON_PAGE(PageAnon(page) && PageAnonExclusive(page), page); - page->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); + VM_WARN_ON_FOLIO(folio_test_anon(folio) && PageAnonExclusive(&folio->page), folio); + folio->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); } #ifdef CONFIG_SYSFS @@ -1107,13 +1107,13 @@ static inline void set_page_stable_node(struct page *page, */ static int remove_stable_node(struct ksm_stable_node *stable_node) { - struct page *page; + struct folio *folio; int err; - page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); - if (!page) { + folio = ksm_get_folio(stable_node, KSM_GET_FOLIO_LOCK); + if (!folio) { /* - * get_ksm_page did remove_node_from_stable_tree itself. + * ksm_get_folio did remove_node_from_stable_tree itself. */ return 0; } @@ -1124,22 +1124,22 @@ static int remove_stable_node(struct ksm_stable_node *stable_node) * merge_across_nodes/max_page_sharing be switched. */ err = -EBUSY; - if (!page_mapped(page)) { + if (!folio_mapped(folio)) { /* - * The stable node did not yet appear stale to get_ksm_page(), - * since that allows for an unmapped ksm page to be recognized + * The stable node did not yet appear stale to ksm_get_folio(), + * since that allows for an unmapped ksm folio to be recognized * right up until it is freed; but the node is safe to remove. - * This page might be in an LRU cache waiting to be freed, - * or it might be PageSwapCache (perhaps under writeback), + * This folio might be in an LRU cache waiting to be freed, + * or it might be in the swapcache (perhaps under writeback), * or it might have been removed from swapcache a moment ago. */ - set_page_stable_node(page, NULL); + folio_set_stable_node(folio, NULL); remove_node_from_stable_tree(stable_node); err = 0; } - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return err; } @@ -1275,23 +1275,24 @@ static u32 calc_checksum(struct page *page) return checksum; } -static int write_protect_page(struct vm_area_struct *vma, struct page *page, +static int write_protect_page(struct vm_area_struct *vma, struct folio *folio, pte_t *orig_pte) { struct mm_struct *mm = vma->vm_mm; - DEFINE_PAGE_VMA_WALK(pvmw, page, vma, 0, 0); + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, 0, 0); int swapped; int err = -EFAULT; struct mmu_notifier_range range; bool anon_exclusive; pte_t entry; - pvmw.address = page_address_in_vma(page, vma); + if (WARN_ON_ONCE(folio_test_large(folio))) + return err; + + pvmw.address = page_address_in_vma(&folio->page, vma); if (pvmw.address == -EFAULT) goto out; - BUG_ON(PageTransCompound(page)); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, pvmw.address, pvmw.address + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); @@ -1301,12 +1302,12 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, if (WARN_ONCE(!pvmw.pte, "Unexpected PMD mapping?")) goto out_unlock; - anon_exclusive = PageAnonExclusive(page); + anon_exclusive = PageAnonExclusive(&folio->page); entry = ptep_get(pvmw.pte); if (pte_write(entry) || pte_dirty(entry) || anon_exclusive || mm_tlb_flush_pending(mm)) { - swapped = PageSwapCache(page); - flush_cache_page(vma, pvmw.address, page_to_pfn(page)); + swapped = folio_test_swapcache(folio); + flush_cache_page(vma, pvmw.address, folio_pfn(folio)); /* * Ok this is tricky, when get_user_pages_fast() run it doesn't * take any lock, therefore the check that we are going to make @@ -1326,20 +1327,20 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, * Check that no O_DIRECT or similar I/O is in progress on the * page */ - if (page_mapcount(page) + 1 + swapped != page_count(page)) { + if (folio_mapcount(folio) + 1 + swapped != folio_ref_count(folio)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (anon_exclusive && - folio_try_share_anon_rmap_pte(page_folio(page), page)) { + folio_try_share_anon_rmap_pte(folio, &folio->page)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } if (pte_dirty(entry)) - set_page_dirty(page); + folio_mark_dirty(folio); entry = pte_mkclean(entry); if (pte_write(entry)) @@ -1505,14 +1506,14 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, * ptes are necessarily already write-protected. But in either * case, we need to lock and check page_count is not raised. */ - if (write_protect_page(vma, page, &orig_pte) == 0) { + if (write_protect_page(vma, page_folio(page), &orig_pte) == 0) { if (!kpage) { /* * While we hold page lock, upgrade page from * PageAnon+anon_vma to PageKsm+NULL stable_node: * stable_tree_insert() will update stable_node. */ - set_page_stable_node(page, NULL); + folio_set_stable_node(page_folio(page), NULL); mark_page_accessed(page); /* * Page reclaim just frees a clean page with no dirty @@ -1617,14 +1618,14 @@ bool is_page_sharing_candidate(struct ksm_stable_node *stable_node) return __is_page_sharing_candidate(stable_node, 0); } -static struct page *stable_node_dup(struct ksm_stable_node **_stable_node_dup, - struct ksm_stable_node **_stable_node, - struct rb_root *root, - bool prune_stale_stable_nodes) +static struct folio *stable_node_dup(struct ksm_stable_node **_stable_node_dup, + struct ksm_stable_node **_stable_node, + struct rb_root *root, + bool prune_stale_stable_nodes) { struct ksm_stable_node *dup, *found = NULL, *stable_node = *_stable_node; struct hlist_node *hlist_safe; - struct page *_tree_page, *tree_page = NULL; + struct folio *folio, *tree_folio = NULL; int nr = 0; int found_rmap_hlist_len; @@ -1643,24 +1644,24 @@ static struct page *stable_node_dup(struct ksm_stable_node **_stable_node_dup, * We must walk all stable_node_dup to prune the stale * stable nodes during lookup. * - * get_ksm_page can drop the nodes from the + * ksm_get_folio can drop the nodes from the * stable_node->hlist if they point to freed pages * (that's why we do a _safe walk). The "dup" * stable_node parameter itself will be freed from * under us if it returns NULL. */ - _tree_page = get_ksm_page(dup, GET_KSM_PAGE_NOLOCK); - if (!_tree_page) + folio = ksm_get_folio(dup, KSM_GET_FOLIO_NOLOCK); + if (!folio) continue; nr += 1; if (is_page_sharing_candidate(dup)) { if (!found || dup->rmap_hlist_len > found_rmap_hlist_len) { if (found) - put_page(tree_page); + folio_put(tree_folio); found = dup; found_rmap_hlist_len = found->rmap_hlist_len; - tree_page = _tree_page; + tree_folio = folio; /* skip put_page for found dup */ if (!prune_stale_stable_nodes) @@ -1668,7 +1669,7 @@ static struct page *stable_node_dup(struct ksm_stable_node **_stable_node_dup, continue; } } - put_page(_tree_page); + folio_put(folio); } if (found) { @@ -1733,7 +1734,7 @@ static struct page *stable_node_dup(struct ksm_stable_node **_stable_node_dup, } *_stable_node_dup = found; - return tree_page; + return tree_folio; } static struct ksm_stable_node *stable_node_dup_any(struct ksm_stable_node *stable_node, @@ -1750,7 +1751,7 @@ static struct ksm_stable_node *stable_node_dup_any(struct ksm_stable_node *stabl } /* - * Like for get_ksm_page, this function can free the *_stable_node and + * Like for ksm_get_folio, this function can free the *_stable_node and * *_stable_node_dup if the returned tree_page is NULL. * * It can also free and overwrite *_stable_node with the found @@ -1763,16 +1764,16 @@ static struct ksm_stable_node *stable_node_dup_any(struct ksm_stable_node *stabl * function and will be overwritten in all cases, the caller doesn't * need to initialize it. */ -static struct page *__stable_node_chain(struct ksm_stable_node **_stable_node_dup, - struct ksm_stable_node **_stable_node, - struct rb_root *root, - bool prune_stale_stable_nodes) +static struct folio *__stable_node_chain(struct ksm_stable_node **_stable_node_dup, + struct ksm_stable_node **_stable_node, + struct rb_root *root, + bool prune_stale_stable_nodes) { struct ksm_stable_node *stable_node = *_stable_node; if (!is_stable_node_chain(stable_node)) { if (is_page_sharing_candidate(stable_node)) { *_stable_node_dup = stable_node; - return get_ksm_page(stable_node, GET_KSM_PAGE_NOLOCK); + return ksm_get_folio(stable_node, KSM_GET_FOLIO_NOLOCK); } /* * _stable_node_dup set to NULL means the stable_node @@ -1785,24 +1786,24 @@ static struct page *__stable_node_chain(struct ksm_stable_node **_stable_node_du prune_stale_stable_nodes); } -static __always_inline struct page *chain_prune(struct ksm_stable_node **s_n_d, - struct ksm_stable_node **s_n, - struct rb_root *root) +static __always_inline struct folio *chain_prune(struct ksm_stable_node **s_n_d, + struct ksm_stable_node **s_n, + struct rb_root *root) { return __stable_node_chain(s_n_d, s_n, root, true); } -static __always_inline struct page *chain(struct ksm_stable_node **s_n_d, - struct ksm_stable_node *s_n, - struct rb_root *root) +static __always_inline struct folio *chain(struct ksm_stable_node **s_n_d, + struct ksm_stable_node *s_n, + struct rb_root *root) { struct ksm_stable_node *old_stable_node = s_n; - struct page *tree_page; + struct folio *tree_folio; - tree_page = __stable_node_chain(s_n_d, &s_n, root, false); + tree_folio = __stable_node_chain(s_n_d, &s_n, root, false); /* not pruning dups so s_n cannot have changed */ VM_BUG_ON(s_n != old_stable_node); - return tree_page; + return tree_folio; } /* @@ -1822,28 +1823,30 @@ static struct page *stable_tree_search(struct page *page) struct rb_node *parent; struct ksm_stable_node *stable_node, *stable_node_dup, *stable_node_any; struct ksm_stable_node *page_node; + struct folio *folio; - page_node = page_stable_node(page); + folio = page_folio(page); + page_node = folio_stable_node(folio); if (page_node && page_node->head != &migrate_nodes) { /* ksm page forked */ - get_page(page); - return page; + folio_get(folio); + return &folio->page; } - nid = get_kpfn_nid(page_to_pfn(page)); + nid = get_kpfn_nid(folio_pfn(folio)); root = root_stable_tree + nid; again: new = &root->rb_node; parent = NULL; while (*new) { - struct page *tree_page; + struct folio *tree_folio; int ret; cond_resched(); stable_node = rb_entry(*new, struct ksm_stable_node, node); stable_node_any = NULL; - tree_page = chain_prune(&stable_node_dup, &stable_node, root); + tree_folio = chain_prune(&stable_node_dup, &stable_node, root); /* * NOTE: stable_node may have been freed by * chain_prune() if the returned stable_node_dup is @@ -1877,14 +1880,14 @@ again: * write protected at all times. Any will work * fine to continue the walk. */ - tree_page = get_ksm_page(stable_node_any, - GET_KSM_PAGE_NOLOCK); + tree_folio = ksm_get_folio(stable_node_any, + KSM_GET_FOLIO_NOLOCK); } VM_BUG_ON(!stable_node_dup ^ !!stable_node_any); - if (!tree_page) { + if (!tree_folio) { /* * If we walked over a stale stable_node, - * get_ksm_page() will call rb_erase() and it + * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate @@ -1894,8 +1897,8 @@ again: goto again; } - ret = memcmp_pages(page, tree_page); - put_page(tree_page); + ret = memcmp_pages(page, &tree_folio->page); + folio_put(tree_folio); parent = *new; if (ret < 0) @@ -1906,12 +1909,15 @@ again: if (page_node) { VM_BUG_ON(page_node->head != &migrate_nodes); /* - * Test if the migrated page should be merged - * into a stable node dup. If the mapcount is - * 1 we can migrate it with another KSM page - * without adding it to the chain. + * If the mapcount of our migrated KSM folio is + * at most 1, we can merge it with another + * KSM folio where we know that we have space + * for one more mapping without exceeding the + * ksm_max_page_sharing limit: see + * chain_prune(). This way, we can avoid adding + * this stable node to the chain. */ - if (page_mapcount(page) > 1) + if (folio_mapcount(folio) > 1) goto chain_append; } @@ -1938,26 +1944,26 @@ again: * It would be more elegant to return stable_node * than kpage, but that involves more changes. */ - tree_page = get_ksm_page(stable_node_dup, - GET_KSM_PAGE_TRYLOCK); + tree_folio = ksm_get_folio(stable_node_dup, + KSM_GET_FOLIO_TRYLOCK); - if (PTR_ERR(tree_page) == -EBUSY) + if (PTR_ERR(tree_folio) == -EBUSY) return ERR_PTR(-EBUSY); - if (unlikely(!tree_page)) + if (unlikely(!tree_folio)) /* * The tree may have been rebalanced, * so re-evaluate parent and new. */ goto again; - unlock_page(tree_page); + folio_unlock(tree_folio); if (get_kpfn_nid(stable_node_dup->kpfn) != NUMA(stable_node_dup->nid)) { - put_page(tree_page); + folio_put(tree_folio); goto replace; } - return tree_page; + return &tree_folio->page; } } @@ -1970,8 +1976,8 @@ again: rb_insert_color(&page_node->node, root); out: if (is_page_sharing_candidate(page_node)) { - get_page(page); - return page; + folio_get(folio); + return &folio->page; } else return NULL; @@ -1996,12 +2002,12 @@ replace: &page_node->node, root); if (is_page_sharing_candidate(page_node)) - get_page(page); + folio_get(folio); else - page = NULL; + folio = NULL; } else { rb_erase(&stable_node_dup->node, root); - page = NULL; + folio = NULL; } } else { VM_BUG_ON(!is_stable_node_chain(stable_node)); @@ -2012,16 +2018,16 @@ replace: DO_NUMA(page_node->nid = nid); stable_node_chain_add_dup(page_node, stable_node); if (is_page_sharing_candidate(page_node)) - get_page(page); + folio_get(folio); else - page = NULL; + folio = NULL; } else { - page = NULL; + folio = NULL; } } stable_node_dup->head = &migrate_nodes; list_add(&stable_node_dup->list, stable_node_dup->head); - return page; + return &folio->page; chain_append: /* stable_node_dup could be null if it reached the limit */ @@ -2064,7 +2070,7 @@ chain_append: * This function returns the stable tree node just allocated on success, * NULL otherwise. */ -static struct ksm_stable_node *stable_tree_insert(struct page *kpage) +static struct ksm_stable_node *stable_tree_insert(struct folio *kfolio) { int nid; unsigned long kpfn; @@ -2074,7 +2080,7 @@ static struct ksm_stable_node *stable_tree_insert(struct page *kpage) struct ksm_stable_node *stable_node, *stable_node_dup, *stable_node_any; bool need_chain = false; - kpfn = page_to_pfn(kpage); + kpfn = folio_pfn(kfolio); nid = get_kpfn_nid(kpfn); root = root_stable_tree + nid; again: @@ -2082,13 +2088,13 @@ again: new = &root->rb_node; while (*new) { - struct page *tree_page; + struct folio *tree_folio; int ret; cond_resched(); stable_node = rb_entry(*new, struct ksm_stable_node, node); stable_node_any = NULL; - tree_page = chain(&stable_node_dup, stable_node, root); + tree_folio = chain(&stable_node_dup, stable_node, root); if (!stable_node_dup) { /* * Either all stable_node dups were full in @@ -2110,14 +2116,14 @@ again: * write protected at all times. Any will work * fine to continue the walk. */ - tree_page = get_ksm_page(stable_node_any, - GET_KSM_PAGE_NOLOCK); + tree_folio = ksm_get_folio(stable_node_any, + KSM_GET_FOLIO_NOLOCK); } VM_BUG_ON(!stable_node_dup ^ !!stable_node_any); - if (!tree_page) { + if (!tree_folio) { /* * If we walked over a stale stable_node, - * get_ksm_page() will call rb_erase() and it + * ksm_get_folio() will call rb_erase() and it * may rebalance the tree from under us. So * restart the search from scratch. Returning * NULL would be safe too, but we'd generate @@ -2127,8 +2133,8 @@ again: goto again; } - ret = memcmp_pages(kpage, tree_page); - put_page(tree_page); + ret = memcmp_pages(&kfolio->page, &tree_folio->page); + folio_put(tree_folio); parent = *new; if (ret < 0) @@ -2147,7 +2153,7 @@ again: INIT_HLIST_HEAD(&stable_node_dup->hlist); stable_node_dup->kpfn = kpfn; - set_page_stable_node(kpage, stable_node_dup); + folio_set_stable_node(kfolio, stable_node_dup); stable_node_dup->rmap_hlist_len = 0; DO_NUMA(stable_node_dup->nid = nid); if (!need_chain) { @@ -2425,7 +2431,7 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite * node in the stable tree and add both rmap_items. */ lock_page(kpage); - stable_node = stable_tree_insert(kpage); + stable_node = stable_tree_insert(page_folio(kpage)); if (stable_node) { stable_tree_append(tree_rmap_item, stable_node, false); @@ -2597,14 +2603,14 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) */ if (!ksm_merge_across_nodes) { struct ksm_stable_node *stable_node, *next; - struct page *page; + struct folio *folio; list_for_each_entry_safe(stable_node, next, &migrate_nodes, list) { - page = get_ksm_page(stable_node, - GET_KSM_PAGE_NOLOCK); - if (page) - put_page(page); + folio = ksm_get_folio(stable_node, + KSM_GET_FOLIO_NOLOCK); + if (folio) + folio_put(folio); cond_resched(); } } @@ -3172,12 +3178,11 @@ again: /* * Collect processes when the error hit an ksm page. */ -void collect_procs_ksm(struct page *page, struct list_head *to_kill, - int force_early) +void collect_procs_ksm(struct folio *folio, struct page *page, + struct list_head *to_kill, int force_early) { struct ksm_stable_node *stable_node; struct ksm_rmap_item *rmap_item; - struct folio *folio = page_folio(page); struct vm_area_struct *vma; struct task_struct *tsk; @@ -3229,11 +3234,11 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) /* * newfolio->mapping was set in advance; now we need smp_wmb() * to make sure that the new stable_node->kpfn is visible - * to get_ksm_page() before it can see that folio->mapping + * to ksm_get_folio() before it can see that folio->mapping * has gone stale (or that folio_test_swapcache has been cleared). */ smp_wmb(); - set_page_stable_node(&folio->page, NULL); + folio_set_stable_node(folio, NULL); } } #endif /* CONFIG_MIGRATION */ @@ -3256,7 +3261,7 @@ static bool stable_node_dup_remove_range(struct ksm_stable_node *stable_node, if (stable_node->kpfn >= start_pfn && stable_node->kpfn < end_pfn) { /* - * Don't get_ksm_page, page has already gone: + * Don't ksm_get_folio, page has already gone: * which is why we keep kpfn instead of page* */ remove_node_from_stable_tree(stable_node); @@ -3344,7 +3349,7 @@ static int ksm_memory_callback(struct notifier_block *self, * Most of the work is done by page migration; but there might * be a few stable_nodes left over, still pointing to struct * pages which have been offlined: prune those from the tree, - * otherwise get_ksm_page() might later try to access a + * otherwise ksm_get_folio() might later try to access a * non-existent struct page. */ ksm_check_stable_tree(mn->start_pfn, diff --git a/mm/madvise.c b/mm/madvise.c index 1a073fcc4c0c02..c49fef453491d0 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -321,6 +321,18 @@ static inline bool can_do_file_pageout(struct vm_area_struct *vma) file_permission(vma->vm_file, MAY_WRITE) == 0; } +static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end, + struct folio *folio, pte_t *ptep, + pte_t pte, bool *any_young, + bool *any_dirty) +{ + const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; + int max_nr = (end - addr) / PAGE_SIZE; + + return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL, + any_young, any_dirty); +} + static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -336,6 +348,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, LIST_HEAD(folio_list); bool pageout_anon_only_filter; unsigned int batch_count = 0; + int nr; if (fatal_signal_pending(current)) return -EINTR; @@ -363,10 +376,10 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, goto huge_unlock; } - folio = pfn_folio(pmd_pfn(orig_pmd)); + folio = pmd_folio(orig_pmd); /* Do not interfere with other mappings of this folio */ - if (folio_estimated_sharers(folio) != 1) + if (folio_likely_mapped_shared(folio)) goto huge_unlock; if (pageout_anon_only_filter && !folio_test_anon(folio)) @@ -423,7 +436,8 @@ restart: return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); - for (; addr < end; pte++, addr += PAGE_SIZE) { + for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) { + nr = 1; ptent = ptep_get(pte); if (++batch_count == SWAP_CLUSTER_MAX) { @@ -447,55 +461,64 @@ restart: continue; /* - * Creating a THP page is expensive so split it only if we - * are sure it's worth. Split it if we are only owner. + * If we encounter a large folio, only split it if it is not + * fully mapped within the range we are operating on. Otherwise + * leave it as is so that it can be swapped out whole. If we + * fail to split a folio, leave it in place and advance to the + * next pte in the range. */ if (folio_test_large(folio)) { - int err; - - if (folio_estimated_sharers(folio) > 1) - break; - if (pageout_anon_only_filter && !folio_test_anon(folio)) - break; - if (!folio_trylock(folio)) - break; - folio_get(folio); - arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(start_pte, ptl); - start_pte = NULL; - err = split_folio(folio); - folio_unlock(folio); - folio_put(folio); - if (err) - break; - start_pte = pte = - pte_offset_map_lock(mm, pmd, addr, &ptl); - if (!start_pte) - break; - arch_enter_lazy_mmu_mode(); - pte--; - addr -= PAGE_SIZE; - continue; + bool any_young; + + nr = madvise_folio_pte_batch(addr, end, folio, pte, + ptent, &any_young, NULL); + if (any_young) + ptent = pte_mkyoung(ptent); + + if (nr < folio_nr_pages(folio)) { + int err; + + if (folio_likely_mapped_shared(folio)) + continue; + if (pageout_anon_only_filter && !folio_test_anon(folio)) + continue; + if (!folio_trylock(folio)) + continue; + folio_get(folio); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(start_pte, ptl); + start_pte = NULL; + err = split_folio(folio); + folio_unlock(folio); + folio_put(folio); + start_pte = pte = + pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!start_pte) + break; + arch_enter_lazy_mmu_mode(); + if (!err) + nr = 0; + continue; + } } /* * Do not interfere with other mappings of this folio and - * non-LRU folio. + * non-LRU folio. If we have a large folio at this point, we + * know it is fully mapped so if its mapcount is the same as its + * number of pages, it must be exclusive. */ - if (!folio_test_lru(folio) || folio_mapcount(folio) != 1) + if (!folio_test_lru(folio) || + folio_mapcount(folio) != folio_nr_pages(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; - VM_BUG_ON_FOLIO(folio_test_large(folio), folio); - if (!pageout && pte_young(ptent)) { - ptent = ptep_get_and_clear_full(mm, addr, pte, - tlb->fullmm); - ptent = pte_mkold(ptent); - set_pte_at(mm, addr, pte, ptent); - tlb_remove_tlb_entry(tlb, pte, addr); + clear_young_dirty_ptes(vma, addr, pte, nr, + CYDP_CLEAR_YOUNG); + tlb_remove_tlb_entries(tlb, pte, nr, addr); } /* @@ -620,6 +643,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { + const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY; struct mmu_gather *tlb = walk->private; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; @@ -628,6 +652,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, struct folio *folio; int nr_swap = 0; unsigned long next; + int nr, max_nr; next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) @@ -640,7 +665,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); - for (; addr != end; pte++, addr += PAGE_SIZE) { + for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) { + nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) @@ -655,9 +681,11 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, entry = pte_to_swp_entry(ptent); if (!non_swap_entry(entry)) { - nr_swap--; - free_swap_and_cache(entry); - pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + max_nr = (end - addr) / PAGE_SIZE; + nr = swap_pte_batch(pte, max_nr, ptent); + nr_swap -= nr; + free_swap_and_cache_nr(entry, nr); + clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); @@ -670,44 +698,57 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, continue; /* - * If pmd isn't transhuge but the folio is large and - * is owned by only this process, split it and - * deactivate all pages. + * If we encounter a large folio, only split it if it is not + * fully mapped within the range we are operating on. Otherwise + * leave it as is so that it can be marked as lazyfree. If we + * fail to split a folio, leave it in place and advance to the + * next pte in the range. */ if (folio_test_large(folio)) { - int err; + bool any_young, any_dirty; - if (folio_estimated_sharers(folio) != 1) - break; - if (!folio_trylock(folio)) - break; - folio_get(folio); - arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(start_pte, ptl); - start_pte = NULL; - err = split_folio(folio); - folio_unlock(folio); - folio_put(folio); - if (err) - break; - start_pte = pte = - pte_offset_map_lock(mm, pmd, addr, &ptl); - if (!start_pte) - break; - arch_enter_lazy_mmu_mode(); - pte--; - addr -= PAGE_SIZE; - continue; + nr = madvise_folio_pte_batch(addr, end, folio, pte, + ptent, &any_young, &any_dirty); + + if (nr < folio_nr_pages(folio)) { + int err; + + if (folio_likely_mapped_shared(folio)) + continue; + if (!folio_trylock(folio)) + continue; + folio_get(folio); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(start_pte, ptl); + start_pte = NULL; + err = split_folio(folio); + folio_unlock(folio); + folio_put(folio); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + start_pte = pte; + if (!start_pte) + break; + arch_enter_lazy_mmu_mode(); + if (!err) + nr = 0; + continue; + } + + if (any_young) + ptent = pte_mkyoung(ptent); + if (any_dirty) + ptent = pte_mkdirty(ptent); } if (folio_test_swapcache(folio) || folio_test_dirty(folio)) { if (!folio_trylock(folio)) continue; /* - * If folio is shared with others, we mustn't clear - * the folio's dirty flag. + * If we have a large folio at this point, we know it is + * fully mapped so if its mapcount is the same as its + * number of pages, it must be exclusive. */ - if (folio_mapcount(folio) != 1) { + if (folio_mapcount(folio) != folio_nr_pages(folio)) { folio_unlock(folio); continue; } @@ -723,19 +764,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, } if (pte_young(ptent) || pte_dirty(ptent)) { - /* - * Some of architecture(ex, PPC) don't update TLB - * with set_pte_at and tlb_remove_tlb_entry so for - * the portability, remap the pte with old|clean - * after pte clearing. - */ - ptent = ptep_get_and_clear_full(mm, addr, pte, - tlb->fullmm); - - ptent = pte_mkold(ptent); - ptent = pte_mkclean(ptent); - set_pte_at(mm, addr, pte, ptent); - tlb_remove_tlb_entry(tlb, pte, addr); + clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags); + tlb_remove_tlb_entries(tlb, pte, nr, addr); } folio_mark_lazyfree(folio); } @@ -901,26 +931,19 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, return -EINVAL; } -static long madvise_populate(struct vm_area_struct *vma, - struct vm_area_struct **prev, - unsigned long start, unsigned long end, - int behavior) +static long madvise_populate(struct mm_struct *mm, unsigned long start, + unsigned long end, int behavior) { const bool write = behavior == MADV_POPULATE_WRITE; - struct mm_struct *mm = vma->vm_mm; int locked = 1; long pages; - *prev = vma; - while (start < end) { /* Populate (prefault) page tables readable/writable. */ pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; - *prev = NULL; - vma = NULL; } if (pages < 0) { switch (pages) { @@ -1021,9 +1044,6 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: return madvise_dontneed_free(vma, prev, start, end, behavior); - case MADV_POPULATE_READ: - case MADV_POPULATE_WRITE: - return madvise_populate(vma, prev, start, end, behavior); case MADV_NORMAL: new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ; break; @@ -1381,6 +1401,7 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, * -EIO - an I/O error occurred while paging in data. * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. + * -EPERM - memory is sealed. */ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { @@ -1424,10 +1445,29 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh start = untagged_addr_remote(mm, start); end = start + len; + /* + * Check if the address range is sealed for do_madvise(). + * can_modify_mm_madv assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm_madv(mm, start, end, behavior))) { + error = -EPERM; + goto out; + } + blk_start_plug(&plug); - error = madvise_walk_vmas(mm, start, end, behavior, - madvise_vma_behavior); + switch (behavior) { + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: + error = madvise_populate(mm, start, end, behavior); + break; + default: + error = madvise_walk_vmas(mm, start, end, behavior, + madvise_vma_behavior); + break; + } blk_finish_plug(&plug); + +out: if (write) mmap_write_unlock(mm); else diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fabce2b50c6955..602ad5faad4dd1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -53,6 +53,7 @@ #include <linux/sort.h> #include <linux/fs.h> #include <linux/seq_file.h> +#include <linux/parser.h> #include <linux/vmpressure.h> #include <linux/memremap.h> #include <linux/mm_inline.h> @@ -350,7 +351,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, /* * A lot of the calls to the cache allocation functions are expected to be - * inlined by the compiler. Since the calls to memcg_slab_pre_alloc_hook() are + * inlined by the compiler. Since the calls to memcg_slab_post_alloc_hook() are * conditional to this static branch, we'll have to allow modules that does * kmem_cache_alloc and the such to see this symbol as well */ @@ -715,6 +716,7 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) { struct memcg_vmstats_percpu *statc; int cpu = smp_processor_id(); + unsigned int stats_updates; if (!val) return; @@ -722,8 +724,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) cgroup_rstat_updated(memcg->css.cgroup, cpu); statc = this_cpu_ptr(memcg->vmstats_percpu); for (; statc; statc = statc->parent) { - statc->stats_updates += abs(val); - if (statc->stats_updates < MEMCG_CHARGE_BATCH) + stats_updates = READ_ONCE(statc->stats_updates) + abs(val); + WRITE_ONCE(statc->stats_updates, stats_updates); + if (stats_updates < MEMCG_CHARGE_BATCH) continue; /* @@ -731,9 +734,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) * redundant. Avoid the overhead of the atomic update. */ if (!memcg_vmstats_needs_flush(statc->vmstats)) - atomic64_add(statc->stats_updates, + atomic64_add(stats_updates, &statc->vmstats->stats_updates); - statc->stats_updates = 0; + WRITE_ONCE(statc->stats_updates, 0); } } @@ -836,8 +839,9 @@ static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) return x; } -void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, - int val) +static void __mod_memcg_lruvec_state(struct lruvec *lruvec, + enum node_stat_item idx, + int val) { struct mem_cgroup_per_node *pn; struct mem_cgroup *memcg; @@ -859,10 +863,13 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, case NR_ANON_THPS: case NR_SHMEM_PMDMAPPED: case NR_FILE_PMDMAPPED: - WARN_ON_ONCE(!in_task()); + if (WARN_ON_ONCE(!in_task())) + pr_warn("stat item index: %d\n", idx); break; default: VM_WARN_ON_IRQS_ENABLED(); + if (!irqs_disabled()) + pr_warn("stat item index: %d\n", idx); } } @@ -2369,8 +2376,7 @@ static void drain_local_stock(struct work_struct *dummy) clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); local_unlock_irqrestore(&memcg_stock.stock_lock, flags); - if (old) - obj_cgroup_put(old); + obj_cgroup_put(old); } /* @@ -2475,7 +2481,8 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg, psi_memstall_enter(&pflags); nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, - MEMCG_RECLAIM_MAY_SWAP); + MEMCG_RECLAIM_MAY_SWAP, + NULL); psi_memstall_leave(&pflags); } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); @@ -2781,7 +2788,7 @@ retry: psi_memstall_enter(&pflags); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, - gfp_mask, reclaim_options); + gfp_mask, reclaim_options, NULL); psi_memstall_leave(&pflags); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) @@ -2978,88 +2985,44 @@ void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg) } #ifdef CONFIG_MEMCG_KMEM -/* - * The allocated objcg pointers array is not accounted directly. - * Moreover, it should not come from DMA buffer and is not readily - * reclaimable. So those GFP bits should be masked off. - */ -#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \ - __GFP_ACCOUNT | __GFP_NOFAIL) -/* - * mod_objcg_mlstate() may be called with irq enabled, so - * mod_memcg_lruvec_state() should be used. - */ -static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, - struct pglist_data *pgdat, - enum node_stat_item idx, int nr) +static inline void __mod_objcg_mlstate(struct obj_cgroup *objcg, + struct pglist_data *pgdat, + enum node_stat_item idx, int nr) { struct mem_cgroup *memcg; struct lruvec *lruvec; + lockdep_assert_irqs_disabled(); + rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); lruvec = mem_cgroup_lruvec(memcg, pgdat); - mod_memcg_lruvec_state(lruvec, idx, nr); + __mod_memcg_lruvec_state(lruvec, idx, nr); rcu_read_unlock(); } -int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s, - gfp_t gfp, bool new_slab) -{ - unsigned int objects = objs_per_slab(s, slab); - unsigned long memcg_data; - void *vec; - - gfp &= ~OBJCGS_CLEAR_MASK; - vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp, - slab_nid(slab)); - if (!vec) - return -ENOMEM; - - memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS; - if (new_slab) { - /* - * If the slab is brand new and nobody can yet access its - * memcg_data, no synchronization is required and memcg_data can - * be simply assigned. - */ - slab->memcg_data = memcg_data; - } else if (cmpxchg(&slab->memcg_data, 0, memcg_data)) { - /* - * If the slab is already in use, somebody can allocate and - * assign obj_cgroups in parallel. In this case the existing - * objcg vector should be reused. - */ - kfree(vec); - return 0; - } - - kmemleak_not_leak(vec); - return 0; -} - static __always_inline struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p) { /* * Slab objects are accounted individually, not per-page. * Memcg membership data for each individual object is saved in - * slab->memcg_data. + * slab->obj_exts. */ if (folio_test_slab(folio)) { - struct obj_cgroup **objcgs; + struct slabobj_ext *obj_exts; struct slab *slab; unsigned int off; slab = folio_slab(folio); - objcgs = slab_objcgs(slab); - if (!objcgs) + obj_exts = slab_obj_exts(slab); + if (!obj_exts) return NULL; off = obj_to_index(slab->slab_cache, slab, p); - if (objcgs[off]) - return obj_cgroup_memcg(objcgs[off]); + if (obj_exts[off].objcg) + return obj_cgroup_memcg(obj_exts[off].objcg); return NULL; } @@ -3067,7 +3030,7 @@ struct mem_cgroup *mem_cgroup_from_obj_folio(struct folio *folio, void *p) /* * folio_memcg_check() is used here, because in theory we can encounter * a folio where the slab flag has been cleared already, but - * slab->memcg_data has not been freed yet + * slab->obj_exts has not been freed yet * folio_memcg_check() will guarantee that a proper memory * cgroup pointer or NULL will be returned. */ @@ -3145,8 +3108,7 @@ static struct obj_cgroup *current_objcg_update(void) if (old) { old = (struct obj_cgroup *) ((unsigned long)old & ~CURRENT_OBJCG_UPDATE_FLAG); - if (old) - obj_cgroup_put(old); + obj_cgroup_put(old); old = NULL; } @@ -3356,7 +3318,7 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) obj_cgroup_put(objcg); } -void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, +static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, enum node_stat_item idx, int nr) { struct memcg_stock_pcp *stock; @@ -3384,12 +3346,12 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, struct pglist_data *oldpg = stock->cached_pgdat; if (stock->nr_slab_reclaimable_b) { - mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B, + __mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B, stock->nr_slab_reclaimable_b); stock->nr_slab_reclaimable_b = 0; } if (stock->nr_slab_unreclaimable_b) { - mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B, + __mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B, stock->nr_slab_unreclaimable_b); stock->nr_slab_unreclaimable_b = 0; } @@ -3415,11 +3377,10 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, } } if (nr) - mod_objcg_mlstate(objcg, pgdat, idx, nr); + __mod_objcg_mlstate(objcg, pgdat, idx, nr); local_unlock_irqrestore(&memcg_stock.stock_lock, flags); - if (old) - obj_cgroup_put(old); + obj_cgroup_put(old); } static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) @@ -3482,13 +3443,13 @@ static struct obj_cgroup *drain_obj_stock(struct memcg_stock_pcp *stock) */ if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) { if (stock->nr_slab_reclaimable_b) { - mod_objcg_mlstate(old, stock->cached_pgdat, + __mod_objcg_mlstate(old, stock->cached_pgdat, NR_SLAB_RECLAIMABLE_B, stock->nr_slab_reclaimable_b); stock->nr_slab_reclaimable_b = 0; } if (stock->nr_slab_unreclaimable_b) { - mod_objcg_mlstate(old, stock->cached_pgdat, + __mod_objcg_mlstate(old, stock->cached_pgdat, NR_SLAB_UNRECLAIMABLE_B, stock->nr_slab_unreclaimable_b); stock->nr_slab_unreclaimable_b = 0; @@ -3546,8 +3507,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, } local_unlock_irqrestore(&memcg_stock.stock_lock, flags); - if (old) - obj_cgroup_put(old); + obj_cgroup_put(old); if (nr_pages) obj_cgroup_uncharge_pages(objcg, nr_pages); @@ -3602,6 +3562,96 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) refill_obj_stock(objcg, size, true); } +static inline size_t obj_full_size(struct kmem_cache *s) +{ + /* + * For each accounted object there is an extra space which is used + * to store obj_cgroup membership. Charge it too. + */ + return s->size + sizeof(struct obj_cgroup *); +} + +bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, + gfp_t flags, size_t size, void **p) +{ + struct obj_cgroup *objcg; + struct slab *slab; + unsigned long off; + size_t i; + + /* + * The obtained objcg pointer is safe to use within the current scope, + * defined by current task or set_active_memcg() pair. + * obj_cgroup_get() is used to get a permanent reference. + */ + objcg = current_obj_cgroup(); + if (!objcg) + return true; + + /* + * slab_alloc_node() avoids the NULL check, so we might be called with a + * single NULL object. kmem_cache_alloc_bulk() aborts if it can't fill + * the whole requested size. + * return success as there's nothing to free back + */ + if (unlikely(*p == NULL)) + return true; + + flags &= gfp_allowed_mask; + + if (lru) { + int ret; + struct mem_cgroup *memcg; + + memcg = get_mem_cgroup_from_objcg(objcg); + ret = memcg_list_lru_alloc(memcg, lru, flags); + css_put(&memcg->css); + + if (ret) + return false; + } + + if (obj_cgroup_charge(objcg, flags, size * obj_full_size(s))) + return false; + + for (i = 0; i < size; i++) { + slab = virt_to_slab(p[i]); + + if (!slab_obj_exts(slab) && + alloc_slab_obj_exts(slab, s, flags, false)) { + obj_cgroup_uncharge(objcg, obj_full_size(s)); + continue; + } + + off = obj_to_index(s, slab, p[i]); + obj_cgroup_get(objcg); + slab_obj_exts(slab)[off].objcg = objcg; + mod_objcg_state(objcg, slab_pgdat(slab), + cache_vmstat_idx(s), obj_full_size(s)); + } + + return true; +} + +void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, + void **p, int objects, struct slabobj_ext *obj_exts) +{ + for (int i = 0; i < objects; i++) { + struct obj_cgroup *objcg; + unsigned int off; + + off = obj_to_index(s, slab, p[i]); + objcg = obj_exts[off].objcg; + if (!objcg) + continue; + + obj_exts[off].objcg = NULL; + obj_cgroup_uncharge(objcg, obj_full_size(s)); + mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s), + -obj_full_size(s)); + obj_cgroup_put(objcg); + } +} #endif /* CONFIG_MEMCG_KMEM */ /* @@ -3709,7 +3759,7 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg, } if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) { + memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, NULL)) { ret = -EBUSY; break; } @@ -3823,7 +3873,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) return -EINTR; if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - MEMCG_RECLAIM_MAY_SWAP)) + MEMCG_RECLAIM_MAY_SWAP, NULL)) nr_retries--; } @@ -4386,7 +4436,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - if (val > 200) + if (val > MAX_SWAPPINESS) return -EINVAL; if (!mem_cgroup_is_root(memcg)) @@ -5468,8 +5518,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - if (memcg->orig_objcg) - obj_cgroup_put(memcg->orig_objcg); + obj_cgroup_put(memcg->orig_objcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); @@ -5845,7 +5894,7 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) } } } - statc->stats_updates = 0; + WRITE_ONCE(statc->stats_updates, 0); /* We are in a per-cpu loop here, only do the atomic write once */ if (atomic64_read(&memcg->vmstats->stats_updates)) atomic64_set(&memcg->vmstats->stats_updates, 0); @@ -6620,8 +6669,7 @@ static void mem_cgroup_exit(struct task_struct *task) objcg = (struct obj_cgroup *) ((unsigned long)objcg & ~CURRENT_OBJCG_UPDATE_FLAG); - if (objcg) - obj_cgroup_put(objcg); + obj_cgroup_put(objcg); /* * Some kernel allocations can happen after this point, @@ -6789,7 +6837,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, } reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP); + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL); if (!reclaimed && !nr_retries--) break; @@ -6838,7 +6886,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (nr_reclaims) { if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP)) + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, NULL)) nr_reclaims--; continue; } @@ -6968,19 +7016,50 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of, return nbytes; } +enum { + MEMORY_RECLAIM_SWAPPINESS = 0, + MEMORY_RECLAIM_NULL, +}; + +static const match_table_t tokens = { + { MEMORY_RECLAIM_SWAPPINESS, "swappiness=%d"}, + { MEMORY_RECLAIM_NULL, NULL }, +}; + static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); unsigned int nr_retries = MAX_RECLAIM_RETRIES; unsigned long nr_to_reclaim, nr_reclaimed = 0; + int swappiness = -1; unsigned int reclaim_options; - int err; + char *old_buf, *start; + substring_t args[MAX_OPT_ARGS]; buf = strstrip(buf); - err = page_counter_memparse(buf, "", &nr_to_reclaim); - if (err) - return err; + + old_buf = buf; + nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE; + if (buf == old_buf) + return -EINVAL; + + buf = strstrip(buf); + + while ((start = strsep(&buf, " ")) != NULL) { + if (!strlen(start)) + continue; + switch (match_token(start, tokens, args)) { + case MEMORY_RECLAIM_SWAPPINESS: + if (match_int(&args[0], &swappiness)) + return -EINVAL; + if (swappiness < MIN_SWAPPINESS || swappiness > MAX_SWAPPINESS) + return -EINVAL; + break; + default: + return -EINVAL; + } + } reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE; while (nr_reclaimed < nr_to_reclaim) { @@ -7000,7 +7079,9 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, lru_add_drain_all(); reclaimed = try_to_free_mem_cgroup_pages(memcg, - batch_size, GFP_KERNEL, reclaim_options); + batch_size, GFP_KERNEL, + reclaim_options, + swappiness == -1 ? NULL : &swappiness); if (!reclaimed && !nr_retries--) return -EAGAIN; @@ -7448,6 +7529,9 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) struct obj_cgroup *objcg; VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + VM_BUG_ON_FOLIO(folio_order(folio) > 1 && + !folio_test_hugetlb(folio) && + !list_empty(&folio->_deferred_list), folio); /* * Nobody should be changing or seriously looking at diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9e62a00b46ddee..16ada4fb02b799 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -141,7 +141,6 @@ static struct ctl_table memory_failure_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - { } }; /* @@ -156,7 +155,7 @@ static int __page_handle_poison(struct page *page) /* * zone_pcp_disable() can't be used here. It will - * hold pcp_batch_high_lock and dissolve_free_huge_page() might hold + * hold pcp_batch_high_lock and dissolve_free_hugetlb_folio() 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. @@ -166,7 +165,7 @@ static int __page_handle_poison(struct page *page) * 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); + ret = dissolve_free_hugetlb_folio(page_folio(page)); if (!ret) { drain_all_pages(page_zone(page)); ret = take_page_off_buddy(page); @@ -179,8 +178,8 @@ static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, boo { if (hugepage_or_freepage) { /* - * Doing this check for free pages is also fine since dissolve_free_huge_page - * returns 0 for non-hugetlb pages as well. + * Doing this check for free pages is also fine since + * dissolve_free_hugetlb_folio() returns 0 for non-hugetlb folios as well. */ if (__page_handle_poison(page) <= 0) /* @@ -217,6 +216,7 @@ EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value); static int hwpoison_filter_dev(struct page *p) { + struct folio *folio = page_folio(p); struct address_space *mapping; dev_t dev; @@ -224,7 +224,7 @@ static int hwpoison_filter_dev(struct page *p) hwpoison_filter_dev_minor == ~0U) return 0; - mapping = page_mapping(p); + mapping = folio_mapping(folio); if (mapping == NULL || mapping->host == NULL) return -EINVAL; @@ -370,20 +370,25 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) * Unknown page type encountered. Try to check whether it can turn PageLRU by * lru_add_drain_all. */ -void shake_page(struct page *p) +void shake_folio(struct folio *folio) { - if (PageHuge(p)) + if (folio_test_hugetlb(folio)) return; /* * TODO: Could shrink slab caches here if a lightweight range-based * shrinker will be available. */ - if (PageSlab(p)) + if (folio_test_slab(folio)) return; lru_add_drain_all(); } -EXPORT_SYMBOL_GPL(shake_page); +EXPORT_SYMBOL_GPL(shake_folio); + +static void shake_page(struct page *page) +{ + shake_folio(page_folio(page)); +} static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma, unsigned long address) @@ -428,21 +433,13 @@ static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma, * not much we can do. We just print a message and ignore otherwise. */ -#define FSDAX_INVALID_PGOFF ULONG_MAX - /* * Schedule a process for later kill. * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. - * - * Note: @fsdax_pgoff is used only when @p is a fsdax page and a - * filesystem with a memory failure handler has claimed the - * memory_failure event. In all other cases, page->index and - * page->mapping are sufficient for mapping the page back to its - * corresponding user virtual address. */ static void __add_to_kill(struct task_struct *tsk, struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, - unsigned long ksm_addr, pgoff_t fsdax_pgoff) + unsigned long addr) { struct to_kill *tk; @@ -452,12 +449,10 @@ static void __add_to_kill(struct task_struct *tsk, struct page *p, return; } - tk->addr = ksm_addr ? ksm_addr : page_address_in_vma(p, vma); - if (is_zone_device_page(p)) { - if (fsdax_pgoff != FSDAX_INVALID_PGOFF) - tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma); + tk->addr = addr; + if (is_zone_device_page(p)) tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr); - } else + else tk->size_shift = page_shift(compound_head(p)); /* @@ -484,10 +479,12 @@ static void __add_to_kill(struct task_struct *tsk, struct page *p, } static void add_to_kill_anon_file(struct task_struct *tsk, struct page *p, - struct vm_area_struct *vma, - struct list_head *to_kill) + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long addr) { - __add_to_kill(tsk, p, vma, to_kill, 0, FSDAX_INVALID_PGOFF); + if (addr == -EFAULT) + return; + __add_to_kill(tsk, p, vma, to_kill, addr); } #ifdef CONFIG_KSM @@ -503,12 +500,13 @@ static bool task_in_to_kill_list(struct list_head *to_kill, return false; } + void add_to_kill_ksm(struct task_struct *tsk, struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, - unsigned long ksm_addr) + unsigned long addr) { if (!task_in_to_kill_list(to_kill, tsk)) - __add_to_kill(tsk, p, vma, to_kill, ksm_addr, FSDAX_INVALID_PGOFF); + __add_to_kill(tsk, p, vma, to_kill, addr); } #endif /* @@ -610,7 +608,6 @@ struct task_struct *task_early_kill(struct task_struct *tsk, int force_early) static void collect_procs_anon(struct folio *folio, struct page *page, struct list_head *to_kill, int force_early) { - struct vm_area_struct *vma; struct task_struct *tsk; struct anon_vma *av; pgoff_t pgoff; @@ -622,8 +619,10 @@ static void collect_procs_anon(struct folio *folio, struct page *page, pgoff = page_to_pgoff(page); rcu_read_lock(); for_each_process(tsk) { + struct vm_area_struct *vma; struct anon_vma_chain *vmac; struct task_struct *t = task_early_kill(tsk, force_early); + unsigned long addr; if (!t) continue; @@ -632,9 +631,8 @@ static void collect_procs_anon(struct folio *folio, struct page *page, vma = vmac->vma; if (vma->vm_mm != t->mm) continue; - if (!page_mapped_in_vma(page, vma)) - continue; - add_to_kill_anon_file(t, page, vma, to_kill); + addr = page_mapped_in_vma(page, vma); + add_to_kill_anon_file(t, page, vma, to_kill, addr); } } rcu_read_unlock(); @@ -657,6 +655,7 @@ static void collect_procs_file(struct folio *folio, struct page *page, pgoff = page_to_pgoff(page); for_each_process(tsk) { struct task_struct *t = task_early_kill(tsk, force_early); + unsigned long addr; if (!t) continue; @@ -669,8 +668,10 @@ static void collect_procs_file(struct folio *folio, struct page *page, * Assume applications who requested early kill want * to be informed of all such data corruptions. */ - if (vma->vm_mm == t->mm) - add_to_kill_anon_file(t, page, vma, to_kill); + if (vma->vm_mm != t->mm) + continue; + addr = page_address_in_vma(page, vma); + add_to_kill_anon_file(t, page, vma, to_kill, addr); } } rcu_read_unlock(); @@ -682,7 +683,8 @@ static void add_to_kill_fsdax(struct task_struct *tsk, struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, pgoff_t pgoff) { - __add_to_kill(tsk, p, vma, to_kill, 0, pgoff); + unsigned long addr = vma_address(vma, pgoff, 1); + __add_to_kill(tsk, p, vma, to_kill, addr); } /* @@ -727,9 +729,9 @@ static void collect_procs(struct folio *folio, struct page *page, { if (!folio->mapping) return; - if (unlikely(PageKsm(page))) - collect_procs_ksm(page, tokill, force_early); - else if (PageAnon(page)) + if (unlikely(folio_test_ksm(folio))) + collect_procs_ksm(folio, page, tokill, force_early); + else if (folio_test_anon(folio)) collect_procs_anon(folio, page, tokill, force_early); else collect_procs_file(folio, page, tokill, force_early); @@ -1089,7 +1091,8 @@ out: */ static int me_pagecache_dirty(struct page_state *ps, struct page *p) { - struct address_space *mapping = page_mapping(p); + struct folio *folio = page_folio(p); + struct address_space *mapping = folio_mapping(folio); SetPageError(p); /* TBD: print more information about the file. */ @@ -1251,7 +1254,6 @@ static int me_huge_page(struct page_state *ps, struct page *p) #define mlock (1UL << PG_mlocked) #define lru (1UL << PG_lru) #define head (1UL << PG_head) -#define slab (1UL << PG_slab) #define reserved (1UL << PG_reserved) static struct page_state error_states[] = { @@ -1261,13 +1263,6 @@ static struct page_state error_states[] = { * PG_buddy pages only make a small fraction of all free pages. */ - /* - * Could in theory check if slab page is free or if we can drop - * currently unused objects without touching them. But just - * treat it as standard kernel for now. - */ - { slab, slab, MF_MSG_SLAB, me_kernel }, - { head, head, MF_MSG_HUGE, me_huge_page }, { sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty }, @@ -1294,7 +1289,6 @@ static struct page_state error_states[] = { #undef mlock #undef lru #undef head -#undef slab #undef reserved static void update_per_node_mf_stats(unsigned long pfn, @@ -1567,24 +1561,24 @@ static int get_hwpoison_page(struct page *p, unsigned long flags) * Do all that is necessary to remove user space mappings. Unmap * the pages and send SIGBUS to the processes if the data was dirty. */ -static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, - int flags, struct page *hpage) +static bool hwpoison_user_mappings(struct folio *folio, struct page *p, + unsigned long pfn, int flags) { - struct folio *folio = page_folio(hpage); enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; struct address_space *mapping; LIST_HEAD(tokill); bool unmap_success; int forcekill; - bool mlocked = PageMlocked(hpage); + bool mlocked = folio_test_mlocked(folio); /* * Here we are interested only in user-mapped pages, so skip any * other types of pages. */ - if (PageReserved(p) || PageSlab(p) || PageTable(p) || PageOffline(p)) + if (folio_test_reserved(folio) || folio_test_slab(folio) || + folio_test_pgtable(folio) || folio_test_offline(folio)) return true; - if (!(PageLRU(hpage) || PageHuge(p))) + if (!(folio_test_lru(folio) || folio_test_hugetlb(folio))) return true; /* @@ -1594,7 +1588,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (!page_mapped(p)) return true; - if (PageSwapCache(p)) { + if (folio_test_swapcache(folio)) { pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); ttu &= ~TTU_HWPOISON; } @@ -1605,11 +1599,11 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * XXX: the dirty test could be racy: set_page_dirty() may not always * be called inside page lock (it's recommended but not enforced). */ - mapping = page_mapping(hpage); - if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping && + mapping = folio_mapping(folio); + if (!(flags & MF_MUST_KILL) && !folio_test_dirty(folio) && mapping && mapping_can_writeback(mapping)) { - if (page_mkclean(hpage)) { - SetPageDirty(hpage); + if (folio_mkclean(folio)) { + folio_set_dirty(folio); } else { ttu &= ~TTU_HWPOISON; pr_info("%#lx: corrupted page was clean: dropped without side effects\n", @@ -1624,7 +1618,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, */ collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); - if (PageHuge(hpage) && !PageAnon(hpage)) { + if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { /* * For hugetlb pages in shared mappings, try_to_unmap * could potentially call huge_pmd_unshare. Because of @@ -1632,7 +1626,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * TTU_RMAP_LOCKED to indicate we have taken the lock * at this higher level. */ - mapping = hugetlb_page_mapping_lock_write(hpage); + mapping = hugetlb_folio_mapping_lock_write(folio); if (mapping) { try_to_unmap(folio, ttu|TTU_RMAP_LOCKED); i_mmap_unlock_write(mapping); @@ -1644,15 +1638,15 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, unmap_success = !page_mapped(p); if (!unmap_success) - pr_err("%#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(p)); + pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n", + pfn, folio_mapcount(page_folio(p))); /* * try_to_unmap() might put mlocked page in lru cache, so call * shake_page() again to ensure that it's flushed. */ if (mlocked) - shake_page(hpage); + shake_folio(folio); /* * Now that the dirty bit has been propagated to the @@ -1664,7 +1658,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - forcekill = PageDirty(hpage) || (flags & MF_MUST_KILL) || + forcekill = folio_test_dirty(folio) || (flags & MF_MUST_KILL) || !unmap_success; kill_procs(&tokill, forcekill, !unmap_success, pfn, flags); @@ -2108,7 +2102,7 @@ retry: page_flags = folio->flags; - if (!hwpoison_user_mappings(p, pfn, flags, &folio->page)) { + if (!hwpoison_user_mappings(folio, p, pfn, flags)) { folio_unlock(folio); return action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); } @@ -2197,7 +2191,7 @@ out: int memory_failure(unsigned long pfn, int flags) { struct page *p; - struct page *hpage; + struct folio *folio; struct dev_pagemap *pgmap; int res = 0; unsigned long page_flags; @@ -2285,8 +2279,8 @@ try_again: } } - hpage = compound_head(p); - if (PageTransHuge(hpage)) { + folio = page_folio(p); + if (folio_test_large(folio)) { /* * The flag must be set after the refcount is bumped * otherwise it may race with THP split. @@ -2300,12 +2294,13 @@ try_again: * or unhandlable page. The refcount is bumped iff the * page is a valid handlable page. */ - SetPageHasHWPoisoned(hpage); + folio_set_has_hwpoisoned(folio); if (try_to_split_thp_page(p) < 0) { res = action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED); goto unlock_mutex; } VM_BUG_ON_PAGE(!page_count(p), p); + folio = page_folio(p); } /* @@ -2316,9 +2311,9 @@ try_again: * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - shake_page(p); + shake_folio(folio); - lock_page(p); + folio_lock(folio); /* * We're only intended to deal with the non-Compound page here. @@ -2326,11 +2321,11 @@ try_again: * race window. If this happens, we could try again to hopefully * handle the page next round. */ - if (PageCompound(p)) { + if (folio_test_large(folio)) { if (retry) { ClearPageHWPoison(p); - unlock_page(p); - put_page(p); + folio_unlock(folio); + folio_put(folio); flags &= ~MF_COUNT_INCREASED; retry = false; goto try_again; @@ -2346,35 +2341,35 @@ try_again: * folio_remove_rmap_*() in try_to_unmap_one(). So to determine page * status correctly, we save a copy of the page flags at this time. */ - page_flags = p->flags; + page_flags = folio->flags; if (hwpoison_filter(p)) { ClearPageHWPoison(p); - unlock_page(p); - put_page(p); + folio_unlock(folio); + folio_put(folio); res = -EOPNOTSUPP; goto unlock_mutex; } /* - * __munlock_folio() may clear a writeback page's LRU flag without - * page_lock. We need wait writeback completion for this page or it - * may trigger vfs BUG while evict inode. + * __munlock_folio() may clear a writeback folio's LRU flag without + * the folio lock. We need to wait for writeback completion for this + * folio or it may trigger a vfs BUG while evicting inode. */ - if (!PageLRU(p) && !PageWriteback(p)) + if (!folio_test_lru(folio) && !folio_test_writeback(folio)) goto identify_page_state; /* * It's very difficult to mess with pages currently under IO * and in many cases impossible, so we just avoid it here. */ - wait_on_page_writeback(p); + folio_wait_writeback(folio); /* * Now take care of user space mappings. * Abort on fail: __filemap_remove_folio() assumes unmapped page. */ - if (!hwpoison_user_mappings(p, pfn, flags, p)) { + if (!hwpoison_user_mappings(folio, p, pfn, flags)) { res = action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED); goto unlock_page; } @@ -2382,7 +2377,8 @@ try_again: /* * Torn down by someone else? */ - if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) { + if (folio_test_lru(folio) && !folio_test_swapcache(folio) && + folio->mapping == NULL) { res = action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); goto unlock_page; } @@ -2392,7 +2388,7 @@ identify_page_state: mutex_unlock(&mf_mutex); return res; unlock_page: - unlock_page(p); + folio_unlock(folio); unlock_mutex: mutex_unlock(&mf_mutex); return res; @@ -2562,8 +2558,8 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } - if (folio_test_slab(folio) || PageTable(&folio->page) || - folio_test_reserved(folio) || PageOffline(&folio->page)) + if (folio_test_slab(folio) || folio_test_pgtable(folio) || + folio_test_reserved(folio) || folio_test_offline(folio)) goto unlock_mutex; /* @@ -2584,7 +2580,7 @@ int unpoison_memory(unsigned long pfn) ghp = get_hwpoison_page(p, MF_UNPOISON); if (!ghp) { - if (PageHuge(p)) { + if (folio_test_hugetlb(folio)) { huge = true; count = folio_free_raw_hwp(folio, false); if (count == 0) @@ -2600,7 +2596,7 @@ int unpoison_memory(unsigned long pfn) pfn, &unpoison_rs); } } else { - if (PageHuge(p)) { + if (folio_test_hugetlb(folio)) { huge = true; count = folio_free_raw_hwp(folio, false); if (count == 0) { @@ -2678,6 +2674,7 @@ static int soft_offline_in_use_page(struct page *page) struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + .reason = MR_MEMORY_FAILURE, }; if (!huge && folio_test_large(folio)) { diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index 0537664620e5f5..6632102bd5c99d 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -36,6 +36,11 @@ struct node_memory_type_map { static DEFINE_MUTEX(memory_tier_lock); static LIST_HEAD(memory_tiers); +/* + * The list is used to store all memory types that are not created + * by a device driver. + */ +static LIST_HEAD(default_memory_types); static struct node_memory_type_map node_memory_types[MAX_NUMNODES]; struct memory_dev_type *default_dram_type; @@ -108,6 +113,8 @@ static struct demotion_nodes *node_demotion __read_mostly; static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms); +/* The lock is used to protect `default_dram_perf*` info and nid. */ +static DEFINE_MUTEX(default_dram_perf_lock); static bool default_dram_perf_error; static struct access_coordinate default_dram_perf; static int default_dram_perf_ref_nid = NUMA_NO_NODE; @@ -505,7 +512,8 @@ static inline void __init_node_memory_type(int node, struct memory_dev_type *mem static struct memory_tier *set_node_memory_tier(int node) { struct memory_tier *memtier; - struct memory_dev_type *memtype; + struct memory_dev_type *memtype = default_dram_type; + int adist = MEMTIER_ADISTANCE_DRAM; pg_data_t *pgdat = NODE_DATA(node); @@ -514,7 +522,16 @@ static struct memory_tier *set_node_memory_tier(int node) if (!node_state(node, N_MEMORY)) return ERR_PTR(-EINVAL); - __init_node_memory_type(node, default_dram_type); + mt_calc_adistance(node, &adist); + if (!node_memory_types[node].memtype) { + memtype = mt_find_alloc_memory_type(adist, &default_memory_types); + if (IS_ERR(memtype)) { + memtype = default_dram_type; + pr_info("Failed to allocate a memory type. Fall back.\n"); + } + } + + __init_node_memory_type(node, memtype); memtype = node_memory_types[node].memtype; node_set(node, memtype->nodes); @@ -623,6 +640,64 @@ void clear_node_memory_type(int node, struct memory_dev_type *memtype) } EXPORT_SYMBOL_GPL(clear_node_memory_type); +struct memory_dev_type *mt_find_alloc_memory_type(int adist, struct list_head *memory_types) +{ + struct memory_dev_type *mtype; + + list_for_each_entry(mtype, memory_types, list) + if (mtype->adistance == adist) + return mtype; + + mtype = alloc_memory_type(adist); + if (IS_ERR(mtype)) + return mtype; + + list_add(&mtype->list, memory_types); + + return mtype; +} +EXPORT_SYMBOL_GPL(mt_find_alloc_memory_type); + +void mt_put_memory_types(struct list_head *memory_types) +{ + struct memory_dev_type *mtype, *mtn; + + list_for_each_entry_safe(mtype, mtn, memory_types, list) { + list_del(&mtype->list); + put_memory_type(mtype); + } +} +EXPORT_SYMBOL_GPL(mt_put_memory_types); + +/* + * This is invoked via `late_initcall()` to initialize memory tiers for + * CPU-less memory nodes after driver initialization, which is + * expected to provide `adistance` algorithms. + */ +static int __init memory_tier_late_init(void) +{ + int nid; + + guard(mutex)(&memory_tier_lock); + for_each_node_state(nid, N_MEMORY) { + /* + * Some device drivers may have initialized memory tiers + * between `memory_tier_init()` and `memory_tier_late_init()`, + * potentially bringing online memory nodes and + * configuring memory tiers. Exclude them here. + */ + if (node_memory_types[nid].memtype) + continue; + + set_node_memory_tier(nid); + } + + establish_demotion_targets(); + + return 0; +} +late_initcall(memory_tier_late_init); + static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix) { pr_info( @@ -634,25 +709,19 @@ static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix) int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source) { - int rc = 0; - - mutex_lock(&memory_tier_lock); - if (default_dram_perf_error) { - rc = -EIO; - goto out; - } + guard(mutex)(&default_dram_perf_lock); + if (default_dram_perf_error) + return -EIO; if (perf->read_latency + perf->write_latency == 0 || - perf->read_bandwidth + perf->write_bandwidth == 0) { - rc = -EINVAL; - goto out; - } + perf->read_bandwidth + perf->write_bandwidth == 0) + return -EINVAL; if (default_dram_perf_ref_nid == NUMA_NO_NODE) { default_dram_perf = *perf; default_dram_perf_ref_nid = nid; default_dram_perf_ref_source = kstrdup(source, GFP_KERNEL); - goto out; + return 0; } /* @@ -680,27 +749,25 @@ int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, pr_info( " disable default DRAM node performance based abstract distance algorithm.\n"); default_dram_perf_error = true; - rc = -EINVAL; + return -EINVAL; } -out: - mutex_unlock(&memory_tier_lock); - return rc; + return 0; } int mt_perf_to_adistance(struct access_coordinate *perf, int *adist) { + guard(mutex)(&default_dram_perf_lock); if (default_dram_perf_error) return -EIO; - if (default_dram_perf_ref_nid == NUMA_NO_NODE) - return -ENOENT; - if (perf->read_latency + perf->write_latency == 0 || perf->read_bandwidth + perf->write_bandwidth == 0) return -EINVAL; - mutex_lock(&memory_tier_lock); + if (default_dram_perf_ref_nid == NUMA_NO_NODE) + return -ENOENT; + /* * The abstract distance of a memory node is in direct proportion to * its memory latency (read + write) and inversely proportional to its @@ -713,7 +780,6 @@ int mt_perf_to_adistance(struct access_coordinate *perf, int *adist) (default_dram_perf.read_latency + default_dram_perf.write_latency) * (default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) / (perf->read_bandwidth + perf->write_bandwidth); - mutex_unlock(&memory_tier_lock); return 0; } @@ -826,7 +892,8 @@ static int __init memory_tier_init(void) * For now we can have 4 faster memory tiers with smaller adistance * than default DRAM tier. */ - default_dram_type = alloc_memory_type(MEMTIER_ADISTANCE_DRAM); + default_dram_type = mt_find_alloc_memory_type(MEMTIER_ADISTANCE_DRAM, + &default_memory_types); if (IS_ERR(default_dram_type)) panic("%s() failed to allocate default DRAM tier\n", __func__); @@ -836,6 +903,14 @@ static int __init memory_tier_init(void) * types assigned. */ for_each_node_state(node, N_MEMORY) { + if (!node_state(node, N_CPU)) + /* + * Defer memory tier initialization on + * CPUless numa nodes. These will be initialized + * after firmware and devices are initialized. + */ + continue; + memtier = set_node_memory_tier(node); if (IS_ERR(memtier)) /* diff --git a/mm/memory.c b/mm/memory.c index d2155ced45f8f8..eea6e4984eaefa 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -112,8 +112,10 @@ static bool vmf_pte_changed(struct vm_fault *vmf); * Return true if the original pte was a uffd-wp pte marker (so the pte was * wr-protected). */ -static bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) +static __always_inline bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) { + if (!userfaultfd_wp(vmf->vma)) + return false; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return false; @@ -989,7 +991,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma flags |= FPB_IGNORE_SOFT_DIRTY; nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags, - &any_writable); + &any_writable, NULL, NULL); folio_ref_add(folio, nr); if (folio_test_anon(folio)) { if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, @@ -1502,10 +1504,15 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, if (!delay_rmap) { folio_remove_rmap_ptes(folio, page, nr, vma); - /* Only sanity-check the first page in a batch. */ - if (unlikely(page_mapcount(page) < 0)) + if (unlikely(folio_mapcount(folio) < 0)) print_bad_pte(vma, addr, ptent, page); } + + if (want_init_mlocked_on_free() && folio_test_mlocked(folio) && + !delay_rmap && folio_test_anon(folio)) { + kernel_init_pages(page, folio_nr_pages(folio)); + } + if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) { *force_flush = true; *force_break = true; @@ -1553,7 +1560,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb, */ if (unlikely(folio_test_large(folio) && max_nr != 1)) { nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags, - NULL); + NULL, NULL, NULL); zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush, @@ -1631,12 +1638,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, folio_remove_rmap_pte(folio, page, vma); folio_put(folio); } else if (!non_swap_entry(entry)) { - /* Genuine swap entry, hence a private anon page */ + max_nr = (end - addr) / PAGE_SIZE; + nr = swap_pte_batch(pte, max_nr, ptent); + /* Genuine swap entries, hence a private anon pages */ if (!should_zap_cows(details)) continue; - rss[MM_SWAPENTS]--; - if (unlikely(!free_swap_and_cache(entry))) - print_bad_pte(vma, addr, ptent, NULL); + rss[MM_SWAPENTS] -= nr; + free_swap_and_cache_nr(entry, nr); } else if (is_migration_entry(entry)) { folio = pfn_swap_entry_folio(entry); if (!should_zap_folio(details, folio)) @@ -1659,8 +1667,8 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pr_alert("unrecognized swap entry 0x%lx\n", entry.val); WARN_ON_ONCE(1); } - pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); - zap_install_uffd_wp_if_needed(vma, addr, pte, 1, details, ptent); + clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); + zap_install_uffd_wp_if_needed(vma, addr, pte, nr, details, ptent); } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); add_mm_rss_vec(mm, rss); @@ -2765,7 +2773,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long next; int err = 0; - BUG_ON(pud_huge(*pud)); + BUG_ON(pud_leaf(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); @@ -3206,19 +3214,39 @@ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf) return VM_FAULT_RETRY; } +/** + * vmf_anon_prepare - Prepare to handle an anonymous fault. + * @vmf: The vm_fault descriptor passed from the fault handler. + * + * When preparing to insert an anonymous page into a VMA from a + * fault handler, call this function rather than anon_vma_prepare(). + * If this vma does not already have an associated anon_vma and we are + * only protected by the per-VMA lock, the caller must retry with the + * mmap_lock held. __anon_vma_prepare() will look at adjacent VMAs to + * determine if this VMA can share its anon_vma, and that's not safe to + * do with only the per-VMA lock held for this VMA. + * + * Return: 0 if fault handling can proceed. Any other value should be + * returned to the caller. + */ vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret = 0; if (likely(vma->anon_vma)) return 0; if (vmf->flags & FAULT_FLAG_VMA_LOCK) { - vma_end_read(vma); - return VM_FAULT_RETRY; + if (!mmap_read_trylock(vma->vm_mm)) { + vma_end_read(vma); + return VM_FAULT_RETRY; + } } if (__anon_vma_prepare(vma)) - return VM_FAULT_OOM; - return 0; + ret = VM_FAULT_OOM; + if (vmf->flags & FAULT_FLAG_VMA_LOCK) + mmap_read_unlock(vma->vm_mm); + return ret; } /* @@ -4190,7 +4218,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ - arch_swap_restore(entry, folio); + arch_swap_restore(folio_swap(entry, folio), folio); /* * Remove the swap entry and conditionally try to free up the swapcache. @@ -4326,8 +4354,8 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) * for this vma. Then filter out the orders that can't be allocated over * the faulting address and still be fully contained in the vma. */ - orders = thp_vma_allowable_orders(vma, vma->vm_flags, false, true, true, - BIT(PMD_ORDER) - 1); + orders = thp_vma_allowable_orders(vma, vma->vm_flags, + TVA_IN_PF | TVA_ENFORCE_SYSFS, BIT(PMD_ORDER) - 1); orders = thp_vma_suitable_orders(vma, vmf->address, orders); if (!orders) @@ -4352,6 +4380,9 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) pte_unmap(pte); + if (!orders) + goto fallback; + /* Try allocating the highest of the remaining orders. */ gfp = vma_thp_gfp_mask(vma); while (orders) { @@ -4359,6 +4390,7 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) folio = vma_alloc_folio(gfp, order, vma, addr, true); if (folio) { if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); folio_put(folio); goto next; } @@ -4367,6 +4399,7 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) return folio; } next: + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); order = next_order(&orders, order); } @@ -4382,7 +4415,6 @@ fallback: */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { - bool uffd_wp = vmf_orig_pte_uffd_wp(vmf); struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address; struct folio *folio; @@ -4427,8 +4459,9 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } /* Allocate our own private page. */ - if (unlikely(anon_vma_prepare(vma))) - goto oom; + ret = vmf_anon_prepare(vmf); + if (ret) + return ret; /* Returns NULL on OOM or ERR_PTR(-EAGAIN) if we must retry the fault */ folio = alloc_anon_folio(vmf); if (IS_ERR(folio)) @@ -4476,10 +4509,13 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) folio_ref_add(folio, nr_pages - 1); add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_FAULT_ALLOC); +#endif folio_add_new_anon_rmap(folio, vma, addr); folio_add_lru_vma(folio, vma); setpte: - if (uffd_wp) + if (vmf_orig_pte_uffd_wp(vmf)) entry = pte_mkuffd_wp(entry); set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr_pages); @@ -4654,7 +4690,6 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio, struct page *page, unsigned int nr, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; - bool uffd_wp = vmf_orig_pte_uffd_wp(vmf); bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE); pte_t entry; @@ -4669,16 +4704,14 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio, if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (unlikely(uffd_wp)) + if (unlikely(vmf_orig_pte_uffd_wp(vmf))) entry = pte_mkuffd_wp(entry); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { - add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr); VM_BUG_ON_FOLIO(nr != 1, folio); folio_add_new_anon_rmap(folio, vma, addr); folio_add_lru_vma(folio, vma); } else { - add_mm_counter(vma->vm_mm, mm_counter_file(folio), nr); folio_add_file_rmap_ptes(folio, page, nr, vma); } set_ptes(vma->vm_mm, addr, vmf->pte, entry, nr); @@ -4715,9 +4748,11 @@ vm_fault_t finish_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct page *page; vm_fault_t ret; + bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) && + !(vma->vm_flags & VM_SHARED); /* Did we COW the page? */ - if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) + if (is_cow) page = vmf->cow_page; else page = vmf->page; @@ -4753,8 +4788,10 @@ vm_fault_t finish_fault(struct vm_fault *vmf) /* Re-check under ptl */ if (likely(!vmf_pte_changed(vmf))) { struct folio *folio = page_folio(page); + int type = is_cow ? MM_ANONPAGES : mm_counter_file(folio); set_pte_range(vmf, folio, page, 1, vmf->address); + add_mm_counter(vma->vm_mm, type, 1); ret = 0; } else { update_mmu_tlb(vma, vmf->address, vmf->pte); @@ -5035,9 +5072,11 @@ static vm_fault_t do_fault(struct vm_fault *vmf) return ret; } -int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma, +int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int page_nid, int *flags) { + struct vm_area_struct *vma = vmf->vma; + folio_get(folio); /* Record the current PID acceesing VMA */ @@ -5049,7 +5088,55 @@ int numa_migrate_prep(struct folio *folio, struct vm_area_struct *vma, *flags |= TNF_FAULT_LOCAL; } - return mpol_misplaced(folio, vma, addr); + return mpol_misplaced(folio, vmf, addr); +} + +static void numa_rebuild_single_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, + unsigned long fault_addr, pte_t *fault_pte, + bool writable) +{ + pte_t pte, old_pte; + + old_pte = ptep_modify_prot_start(vma, fault_addr, fault_pte); + pte = pte_modify(old_pte, vma->vm_page_prot); + pte = pte_mkyoung(pte); + if (writable) + pte = pte_mkwrite(pte, vma); + ptep_modify_prot_commit(vma, fault_addr, fault_pte, old_pte, pte); + update_mmu_cache_range(vmf, vma, fault_addr, fault_pte, 1); +} + +static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_struct *vma, + struct folio *folio, pte_t fault_pte, + bool ignore_writable, bool pte_write_upgrade) +{ + int nr = pte_pfn(fault_pte) - folio_pfn(folio); + unsigned long start = max(vmf->address - nr * PAGE_SIZE, vma->vm_start); + unsigned long end = min(vmf->address + (folio_nr_pages(folio) - nr) * PAGE_SIZE, vma->vm_end); + pte_t *start_ptep = vmf->pte - (vmf->address - start) / PAGE_SIZE; + unsigned long addr; + + /* Restore all PTEs' mapping of the large folio */ + for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { + pte_t ptent = ptep_get(start_ptep); + bool writable = false; + + if (!pte_present(ptent) || !pte_protnone(ptent)) + continue; + + if (pfn_folio(pte_pfn(ptent)) != folio) + continue; + + if (!ignore_writable) { + ptent = pte_modify(ptent, vma->vm_page_prot); + writable = pte_write(ptent); + if (!writable && pte_write_upgrade && + can_change_pte_writable(vma, addr, ptent)) + writable = true; + } + + numa_rebuild_single_mapping(vmf, vma, addr, start_ptep, writable); + } } static vm_fault_t do_numa_page(struct vm_fault *vmf) @@ -5057,11 +5144,12 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct folio *folio = NULL; int nid = NUMA_NO_NODE; - bool writable = false; + bool writable = false, ignore_writable = false; + bool pte_write_upgrade = vma_wants_manual_pte_write_upgrade(vma); int last_cpupid; int target_nid; pte_t pte, old_pte; - int flags = 0; + int flags = 0, nr_pages; /* * The pte cannot be used safely until we verify, while holding the page @@ -5083,7 +5171,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) * is only valid while holding the PT lock. */ writable = pte_write(pte); - if (!writable && vma_wants_manual_pte_write_upgrade(vma) && + if (!writable && pte_write_upgrade && can_change_pte_writable(vma, vmf->address, pte)) writable = true; @@ -5091,10 +5179,6 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) if (!folio || folio_is_zone_device(folio)) goto out_map; - /* TODO: handle PTE-mapped THP */ - if (folio_test_large(folio)) - goto out_map; - /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses @@ -5110,10 +5194,11 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) * Flag if the folio is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ - if (folio_estimated_sharers(folio) > 1 && (vma->vm_flags & VM_SHARED)) + if (folio_likely_mapped_shared(folio) && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; nid = folio_nid(folio); + nr_pages = folio_nr_pages(folio); /* * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. @@ -5123,13 +5208,14 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) last_cpupid = (-1 & LAST_CPUPID_MASK); else last_cpupid = folio_last_cpupid(folio); - target_nid = numa_migrate_prep(folio, vma, vmf->address, nid, &flags); + target_nid = numa_migrate_prep(folio, vmf, vmf->address, nid, &flags); if (target_nid == NUMA_NO_NODE) { folio_put(folio); goto out_map; } pte_unmap_unlock(vmf->pte, vmf->ptl); writable = false; + ignore_writable = true; /* Migrate to the requested node */ if (migrate_misplaced_folio(folio, vma, target_nid)) { @@ -5150,20 +5236,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) out: if (nid != NUMA_NO_NODE) - task_numa_fault(last_cpupid, nid, 1, flags); + task_numa_fault(last_cpupid, nid, nr_pages, flags); return 0; out_map: /* * Make it present again, depending on how arch implements * non-accessible ptes, some can allow access by kernel mode. */ - old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); - pte = pte_modify(old_pte, vma->vm_page_prot); - pte = pte_mkyoung(pte); - if (writable) - pte = pte_mkwrite(pte, vma); - ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); - update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1); + if (folio && folio_test_large(folio)) + numa_rebuild_large_mapping(vmf, vma, folio, pte, ignore_writable, + pte_write_upgrade); + else + numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte, + writable); pte_unmap_unlock(vmf->pte, vmf->ptl); goto out; } @@ -5374,7 +5459,8 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && - thp_vma_allowable_order(vma, vm_flags, false, true, true, PUD_ORDER)) { + thp_vma_allowable_order(vma, vm_flags, + TVA_IN_PF | TVA_ENFORCE_SYSFS, PUD_ORDER)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -5408,7 +5494,8 @@ retry_pud: goto retry_pud; if (pmd_none(*vmf.pmd) && - thp_vma_allowable_order(vma, vm_flags, false, true, true, PMD_ORDER)) { + thp_vma_allowable_order(vma, vm_flags, + TVA_IN_PF | TVA_ENFORCE_SYSFS, PMD_ORDER)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -5762,15 +5849,6 @@ retry: if (!vma_start_read(vma)) goto inval; - /* - * find_mergeable_anon_vma uses adjacent vmas which are not locked. - * This check must happen after vma_start_read(); otherwise, a - * concurrent mremap() with MREMAP_DONTUNMAP could dissociate the VMA - * from its anon_vma. - */ - if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) - goto inval_end_read; - /* Check since vm_start/vm_end might change before we lock the VMA */ if (unlikely(address < vma->vm_start || address >= vma->vm_end)) goto inval_end_read; @@ -5868,34 +5946,48 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) /** * follow_pte - look up PTE at a user virtual address - * @mm: the mm_struct of the target address space + * @vma: the memory mapping * @address: user virtual address * @ptepp: location to store found PTE * @ptlp: location to store the lock for the PTE * * On a successful return, the pointer to the PTE is stored in @ptepp; * the corresponding lock is taken and its location is stored in @ptlp. - * The contents of the PTE are only stable until @ptlp is released; - * any further use, if any, must be protected against invalidation - * with MMU notifiers. + * + * The contents of the PTE are only stable until @ptlp is released using + * pte_unmap_unlock(). This function will fail if the PTE is non-present. + * Present PTEs may include PTEs that map refcounted pages, such as + * anonymous folios in COW mappings. + * + * Callers must be careful when relying on PTE content after + * pte_unmap_unlock(). Especially if the PTE maps a refcounted page, + * callers must protect against invalidation with MMU notifiers; otherwise + * access to the PFN at a later point in time can trigger use-after-free. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read. * - * KVM uses this function. While it is arguably less bad than ``follow_pfn``, - * it is not a good general-purpose API. + * This function must not be used to modify PTE content. * * Return: zero on success, -ve otherwise. */ -int follow_pte(struct mm_struct *mm, unsigned long address, +int follow_pte(struct vm_area_struct *vma, unsigned long address, pte_t **ptepp, spinlock_t **ptlp) { + struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; + mmap_assert_locked(mm); + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) + goto out; + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + goto out; + pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; @@ -5925,71 +6017,7 @@ out: } EXPORT_SYMBOL_GPL(follow_pte); -/** - * follow_pfn - look up PFN at a user virtual address - * @vma: memory mapping - * @address: user virtual address - * @pfn: location to store found PFN - * - * Only IO mappings and raw PFN mappings are allowed. - * - * This function does not allow the caller to read the permissions - * of the PTE. Do not use it. - * - * Return: zero and the pfn at @pfn on success, -ve otherwise. - */ -int follow_pfn(struct vm_area_struct *vma, unsigned long address, - unsigned long *pfn) -{ - int ret = -EINVAL; - spinlock_t *ptl; - pte_t *ptep; - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - return ret; - - ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); - if (ret) - return ret; - *pfn = pte_pfn(ptep_get(ptep)); - pte_unmap_unlock(ptep, ptl); - return 0; -} -EXPORT_SYMBOL(follow_pfn); - #ifdef CONFIG_HAVE_IOREMAP_PROT -int follow_phys(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned long *prot, resource_size_t *phys) -{ - int ret = -EINVAL; - pte_t *ptep, pte; - spinlock_t *ptl; - - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - goto out; - - if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) - goto out; - pte = ptep_get(ptep); - - /* Never return PFNs of anon folios in COW mappings. */ - if (vm_normal_folio(vma, address, pte)) - goto unlock; - - if ((flags & FOLL_WRITE) && !pte_write(pte)) - goto unlock; - - *prot = pgprot_val(pte_pgprot(pte)); - *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; - - ret = 0; -unlock: - pte_unmap_unlock(ptep, ptl); -out: - return ret; -} - /** * generic_access_phys - generic implementation for iomem mmap access * @vma: the vma to access @@ -6013,11 +6041,8 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, int offset = offset_in_page(addr); int ret = -EINVAL; - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - return -EINVAL; - retry: - if (follow_pte(vma->vm_mm, addr, &ptep, &ptl)) + if (follow_pte(vma, addr, &ptep, &ptl)) return -EINVAL; pte = ptep_get(ptep); pte_unmap_unlock(ptep, ptl); @@ -6032,7 +6057,7 @@ retry: if (!maddr) return -ENOMEM; - if (follow_pte(vma->vm_mm, addr, &ptep, &ptl)) + if (follow_pte(vma, addr, &ptep, &ptl)) goto out_unmap; if (!pte_same(pte, ptep_get(ptep))) { @@ -6440,3 +6465,15 @@ void ptlock_free(struct ptdesc *ptdesc) kmem_cache_free(page_ptl_cachep, ptdesc->ptl); } #endif + +void vma_pgtable_walk_begin(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_lock_read(vma); +} + +void vma_pgtable_walk_end(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_unlock_read(vma); +} diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a444e2d7dd2bff..431b1f6753c0b9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1841,6 +1841,7 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) struct migration_target_control mtc = { .nmask = &nmask, .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + .reason = MR_MEMORY_HOTPLUG, }; int ret; @@ -2050,11 +2051,11 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, } /* - * Dissolve free hugepages in the memory block before doing + * Dissolve free hugetlb folios in the memory block before doing * offlining actually in order to make hugetlbfs's object * counting consistent. */ - ret = dissolve_free_huge_pages(start_pfn, end_pfn); + ret = dissolve_free_hugetlb_folios(start_pfn, end_pfn); if (ret) { reason = "failure to dissolve huge pages"; goto failed_removal_isolated; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0fe77738d971de..aec756ae563779 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -509,8 +509,8 @@ static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) qp->nr_failed++; return; } - folio = pfn_folio(pmd_pfn(*pmd)); - if (is_huge_zero_page(&folio->page)) { + folio = pmd_folio(*pmd); + if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } @@ -642,12 +642,11 @@ static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * - * To check if the folio is shared, ideally we want to make sure - * every page is mapped to the same process. Doing that is very - * expensive, so check the estimated sharers of the folio instead. + * See folio_likely_mapped_shared() on possible imprecision when we + * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || - (folio_estimated_sharers(folio) == 1 && !hugetlb_pmd_shared(pte))) + (!folio_likely_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: @@ -1032,11 +1031,10 @@ static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * - * To check if the folio is shared, ideally we want to make sure - * every page is mapped to the same process. Doing that is very - * expensive, so check the estimated sharers of the folio instead. + * See folio_likely_mapped_shared() on possible imprecision when we + * cannot easily detect if a folio is shared. */ - if ((flags & MPOL_MF_MOVE_ALL) || folio_estimated_sharers(folio) == 1) { + if ((flags & MPOL_MF_MOVE_ALL) || !folio_likely_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, @@ -1070,6 +1068,7 @@ static long migrate_to_node(struct mm_struct *mm, int source, int dest, struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + .reason = MR_SYSCALL, }; nodes_clear(nmask); @@ -1227,7 +1226,8 @@ static struct folio *alloc_migration_target_by_mpol(struct folio *src, h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); - return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp); + return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, + htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) @@ -1504,9 +1504,10 @@ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { - if (*mode != MPOL_BIND) + if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) + *flags |= (MPOL_F_MOF | MPOL_F_MORON); + else return -EINVAL; - *flags |= (MPOL_F_MOF | MPOL_F_MORON); } return 0; } @@ -2200,9 +2201,9 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); - page = __alloc_pages(preferred_gfp, order, nid, nodemask); + page = __alloc_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) - page = __alloc_pages(gfp, order, nid, NULL); + page = __alloc_pages_noprof(gfp, order, nid, NULL); return page; } @@ -2217,7 +2218,7 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, * * Return: The page on success or NULL if allocation fails. */ -struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, +struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; @@ -2248,7 +2249,7 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ - page = __alloc_pages_node(nid, + page = __alloc_pages_node_noprof(nid, gfp | __GFP_THISNODE | __GFP_NORETRY, order); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; @@ -2261,7 +2262,7 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, } } - page = __alloc_pages(gfp, order, nid, nodemask); + page = __alloc_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ @@ -2292,7 +2293,7 @@ struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, * * Return: The folio on success or NULL if allocation fails. */ -struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, +struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage) { struct mempolicy *pol; @@ -2300,12 +2301,12 @@ struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, struct page *page; pol = get_vma_policy(vma, addr, order, &ilx); - page = alloc_pages_mpol(gfp | __GFP_COMP, order, - pol, ilx, numa_node_id()); + page = alloc_pages_mpol_noprof(gfp | __GFP_COMP, order, + pol, ilx, numa_node_id()); mpol_cond_put(pol); return page_rmappable_folio(page); } -EXPORT_SYMBOL(vma_alloc_folio); +EXPORT_SYMBOL(vma_alloc_folio_noprof); /** * alloc_pages - Allocate pages. @@ -2321,7 +2322,7 @@ EXPORT_SYMBOL(vma_alloc_folio); * flags are used. * Return: The page on success or NULL if allocation fails. */ -struct page *alloc_pages(gfp_t gfp, unsigned int order) +struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct mempolicy *pol = &default_policy; @@ -2332,16 +2333,16 @@ struct page *alloc_pages(gfp_t gfp, unsigned int order) if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); - return alloc_pages_mpol(gfp, order, - pol, NO_INTERLEAVE_INDEX, numa_node_id()); + return alloc_pages_mpol_noprof(gfp, order, pol, NO_INTERLEAVE_INDEX, + numa_node_id()); } -EXPORT_SYMBOL(alloc_pages); +EXPORT_SYMBOL(alloc_pages_noprof); -struct folio *folio_alloc(gfp_t gfp, unsigned int order) +struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { - return page_rmappable_folio(alloc_pages(gfp | __GFP_COMP, order)); + return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } -EXPORT_SYMBOL(folio_alloc); +EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, @@ -2360,13 +2361,13 @@ static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, for (i = 0; i < nodes; i++) { if (delta) { - nr_allocated = __alloc_pages_bulk(gfp, + nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, NULL, page_array); delta--; } else { - nr_allocated = __alloc_pages_bulk(gfp, + nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, NULL, page_array); } @@ -2503,11 +2504,11 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); - nr_allocated = __alloc_pages_bulk(preferred_gfp, nid, &pol->nodes, + nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, NULL, page_array); if (nr_allocated < nr_pages) - nr_allocated += __alloc_pages_bulk(gfp, numa_node_id(), NULL, + nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, NULL, page_array + nr_allocated); return nr_allocated; @@ -2519,7 +2520,7 @@ static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, * It can accelerate memory allocation especially interleaving * allocate memory. */ -unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, +unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; @@ -2543,8 +2544,8 @@ unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); - return __alloc_pages_bulk(gfp, nid, nodemask, - nr_pages, NULL, page_array); + return alloc_pages_bulk_noprof(gfp, nid, nodemask, + nr_pages, NULL, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) @@ -2718,7 +2719,7 @@ static void sp_free(struct sp_node *n) * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked - * @vma: vm area where folio mapped + * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's @@ -2728,18 +2729,24 @@ static void sp_free(struct sp_node *n) * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ -int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, +int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); + struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); - int thisnid = cpu_to_node(thiscpu); + int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; + /* + * Make sure ptl is held so that we don't preempt and we + * have a stable smp processor id + */ + lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; @@ -2764,15 +2771,26 @@ int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, break; case MPOL_BIND: - /* Optimize placement among multiple nodes via NUMA balancing */ + case MPOL_PREFERRED_MANY: + /* + * Even though MPOL_PREFERRED_MANY can allocate pages outside + * policy nodemask we don't allow numa migration to nodes + * outside policy nodemask for now. This is done so that if we + * want demotion to slow memory to happen, before allocating + * from some DRAM node say 'x', we will end up using a + * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario + * we should not promote to node 'x' from slow memory node. + */ if (pol->flags & MPOL_F_MORON) { + /* + * Optimize placement among multiple nodes + * via NUMA balancing + */ if (node_isset(thisnid, pol->nodes)) break; goto out; } - fallthrough; - case MPOL_PREFERRED_MANY: /* * use current page if in policy nodemask, * else select nearest allowed node, if any. @@ -2781,7 +2799,7 @@ int mpol_misplaced(struct folio *folio, struct vm_area_struct *vma, if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( - node_zonelist(numa_node_id(), GFP_HIGHUSER), + node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zone_to_nid(z->zone); diff --git a/mm/mempool.c b/mm/mempool.c index 076c736f5f1ff8..6ece63a00acf58 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -240,22 +240,24 @@ EXPORT_SYMBOL(mempool_init_node); * * Return: %0 on success, negative error code otherwise. */ -int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, - mempool_free_t *free_fn, void *pool_data) +int mempool_init_noprof(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data) { return mempool_init_node(pool, min_nr, alloc_fn, free_fn, pool_data, GFP_KERNEL, NUMA_NO_NODE); } -EXPORT_SYMBOL(mempool_init); +EXPORT_SYMBOL(mempool_init_noprof); /** - * mempool_create - create a memory pool + * mempool_create_node - create a memory pool * @min_nr: the minimum number of elements guaranteed to be * allocated for this pool. * @alloc_fn: user-defined element-allocation function. * @free_fn: user-defined element-freeing function. * @pool_data: optional private data available to the user-defined functions. + * @gfp_mask: memory allocation flags + * @node_id: numa node to allocate on * * this function creates and allocates a guaranteed size, preallocated * memory pool. The pool can be used from the mempool_alloc() and mempool_free() @@ -265,17 +267,9 @@ EXPORT_SYMBOL(mempool_init); * * Return: pointer to the created memory pool object or %NULL on error. */ -mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, - mempool_free_t *free_fn, void *pool_data) -{ - return mempool_create_node(min_nr, alloc_fn, free_fn, pool_data, - GFP_KERNEL, NUMA_NO_NODE); -} -EXPORT_SYMBOL(mempool_create); - -mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, - mempool_free_t *free_fn, void *pool_data, - gfp_t gfp_mask, int node_id) +mempool_t *mempool_create_node_noprof(int min_nr, mempool_alloc_t *alloc_fn, + mempool_free_t *free_fn, void *pool_data, + gfp_t gfp_mask, int node_id) { mempool_t *pool; @@ -291,7 +285,7 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, return pool; } -EXPORT_SYMBOL(mempool_create_node); +EXPORT_SYMBOL(mempool_create_node_noprof); /** * mempool_resize - resize an existing memory pool @@ -387,7 +381,7 @@ EXPORT_SYMBOL(mempool_resize); * * Return: pointer to the allocated element or %NULL on error. */ -void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) +void *mempool_alloc_noprof(mempool_t *pool, gfp_t gfp_mask) { void *element; unsigned long flags; @@ -454,7 +448,7 @@ repeat_alloc: finish_wait(&pool->wait, &wait); goto repeat_alloc; } -EXPORT_SYMBOL(mempool_alloc); +EXPORT_SYMBOL(mempool_alloc_noprof); /** * mempool_alloc_preallocated - allocate an element from preallocated elements @@ -562,7 +556,7 @@ void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data) { struct kmem_cache *mem = pool_data; VM_BUG_ON(mem->ctor); - return kmem_cache_alloc(mem, gfp_mask); + return kmem_cache_alloc_noprof(mem, gfp_mask); } EXPORT_SYMBOL(mempool_alloc_slab); @@ -580,7 +574,7 @@ EXPORT_SYMBOL(mempool_free_slab); void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data) { size_t size = (size_t)pool_data; - return kmalloc(size, gfp_mask); + return kmalloc_noprof(size, gfp_mask); } EXPORT_SYMBOL(mempool_kmalloc); @@ -610,7 +604,7 @@ EXPORT_SYMBOL(mempool_kvfree); void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data) { int order = (int)(long)pool_data; - return alloc_pages(gfp_mask, order); + return alloc_pages_noprof(gfp_mask, order); } EXPORT_SYMBOL(mempool_alloc_pages); diff --git a/mm/memremap.c b/mm/memremap.c index 9e9fb1972fff0a..40d4547ce5144e 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -456,21 +456,23 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, } EXPORT_SYMBOL_GPL(get_dev_pagemap); -void free_zone_device_page(struct page *page) +void free_zone_device_folio(struct folio *folio) { - if (WARN_ON_ONCE(!page->pgmap->ops || !page->pgmap->ops->page_free)) + if (WARN_ON_ONCE(!folio->page.pgmap->ops || + !folio->page.pgmap->ops->page_free)) return; - mem_cgroup_uncharge(page_folio(page)); + mem_cgroup_uncharge(folio); /* * Note: we don't expect anonymous compound pages yet. Once supported * and we could PTE-map them similar to THP, we'd have to clear * PG_anon_exclusive on all tail pages. */ - VM_BUG_ON_PAGE(PageAnon(page) && PageCompound(page), page); - if (PageAnon(page)) - __ClearPageAnonExclusive(page); + if (folio_test_anon(folio)) { + VM_BUG_ON_FOLIO(folio_test_large(folio), folio); + __ClearPageAnonExclusive(folio_page(folio, 0)); + } /* * When a device managed page is freed, the folio->mapping field @@ -481,20 +483,20 @@ void free_zone_device_page(struct page *page) * * For other types of ZONE_DEVICE pages, migration is either * handled differently or not done at all, so there is no need - * to clear page->mapping. + * to clear folio->mapping. */ - page->mapping = NULL; - page->pgmap->ops->page_free(page); + folio->mapping = NULL; + folio->page.pgmap->ops->page_free(folio_page(folio, 0)); - if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && - page->pgmap->type != MEMORY_DEVICE_COHERENT) + if (folio->page.pgmap->type != MEMORY_DEVICE_PRIVATE && + folio->page.pgmap->type != MEMORY_DEVICE_COHERENT) /* - * Reset the page count to 1 to prepare for handing out the page + * Reset the refcount to 1 to prepare for handing out the page * again. */ - set_page_count(page, 1); + folio_set_count(folio, 1); else - put_dev_pagemap(page->pgmap); + put_dev_pagemap(folio->page.pgmap); } void zone_device_page_init(struct page *page) @@ -510,9 +512,9 @@ void zone_device_page_init(struct page *page) EXPORT_SYMBOL_GPL(zone_device_page_init); #ifdef CONFIG_FS_DAX -bool __put_devmap_managed_page_refs(struct page *page, int refs) +bool __put_devmap_managed_folio_refs(struct folio *folio, int refs) { - if (page->pgmap->type != MEMORY_DEVICE_FS_DAX) + if (folio->page.pgmap->type != MEMORY_DEVICE_FS_DAX) return false; /* @@ -520,9 +522,9 @@ bool __put_devmap_managed_page_refs(struct page *page, int refs) * refcount is 1, then the page is free and the refcount is * stable because nobody holds a reference on the page. */ - if (page_ref_sub_return(page, refs) == 1) - wake_up_var(&page->_refcount); + if (folio_ref_sub_return(folio, refs) == 1) + wake_up_var(&folio->_refcount); return true; } -EXPORT_SYMBOL(__put_devmap_managed_page_refs); +EXPORT_SYMBOL(__put_devmap_managed_folio_refs); #endif /* CONFIG_FS_DAX */ diff --git a/mm/migrate.c b/mm/migrate.c index 73a052a382f13a..dd04f578c19c3e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -113,7 +113,7 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode) if (!mops->isolate_page(&folio->page, mode)) goto out_no_isolated; - /* Driver shouldn't use PG_isolated bit of page->flags */ + /* Driver shouldn't use the isolated flag */ WARN_ON_ONCE(folio_test_isolated(folio)); folio_set_isolated(folio); folio_unlock(folio); @@ -616,7 +616,7 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_migrate_ksm(newfolio, folio); /* * Please do not reorder this without considering how mm/ksm.c's - * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). + * ksm_get_folio() depends upon ksm_migrate_page() and PageSwapCache(). */ if (folio_test_swapcache(folio)) folio_clear_swapcache(folio); @@ -1425,7 +1425,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, * semaphore in write mode here and set TTU_RMAP_LOCKED * to let lower levels know we have taken the lock. */ - mapping = hugetlb_page_mapping_lock_write(&src->page); + mapping = hugetlb_folio_mapping_lock_write(src); if (unlikely(!mapping)) goto unlock_put_anon; @@ -1653,6 +1653,29 @@ static int migrate_pages_batch(struct list_head *from, cond_resched(); /* + * The rare folio on the deferred split list should + * be split now. It should not count as a failure. + * Only check it without removing it from the list. + * Since the folio can be on deferred_split_scan() + * local list and removing it can cause the local list + * corruption. Folio split process below can handle it + * with the help of folio_ref_freeze(). + * + * nr_pages > 2 is needed to avoid checking order-1 + * page cache folios. They exist, in contrast to + * non-existent order-1 anonymous folios, and do not + * use _deferred_list. + */ + if (nr_pages > 2 && + !list_empty(&folio->_deferred_list)) { + if (try_split_folio(folio, split_folios) == 0) { + stats->nr_thp_split += is_thp; + stats->nr_split++; + continue; + } + } + + /* * Large folio migration might be unsupported or * the allocation might be failed so we should retry * on the same folio with the large folio split @@ -2022,7 +2045,8 @@ struct folio *alloc_migration_target(struct folio *src, unsigned long private) gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); return alloc_hugetlb_folio_nodemask(h, nid, - mtc->nmask, gfp_mask); + mtc->nmask, gfp_mask, + htlb_allow_alloc_fallback(mtc->reason)); } if (folio_test_large(src)) { @@ -2060,6 +2084,7 @@ static int do_move_pages_to_node(struct list_head *pagelist, int node) struct migration_target_control mtc = { .nid = node, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, + .reason = MR_SYSCALL, }; err = migrate_pages(pagelist, alloc_migration_target, NULL, @@ -2115,7 +2140,7 @@ static int add_page_for_migration(struct mm_struct *mm, const void __user *p, goto out_putfolio; err = -EACCES; - if (page_mapcount(page) > 1 && !migrate_all) + if (folio_likely_mapped_shared(folio) && !migrate_all) goto out_putfolio; err = -EBUSY; @@ -2568,11 +2593,11 @@ int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, /* * Don't migrate file folios that are mapped in multiple processes * with execute permissions as they are probably shared libraries. - * To check if the folio is shared, ideally we want to make sure - * every page is mapped to the same process. Doing that is very - * expensive, so check the estimated mapcount of the folio instead. + * + * See folio_likely_mapped_shared() on possible imprecision when we + * cannot easily detect if a folio is shared. */ - if (folio_estimated_sharers(folio) != 1 && folio_is_file_lru(folio) && + if (folio_likely_mapped_shared(folio) && folio_is_file_lru(folio) && (vma->vm_flags & VM_EXEC)) goto out; diff --git a/mm/migrate_device.c b/mm/migrate_device.c index b6c27c76e1a0b2..7e0712493d1f48 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -71,7 +71,7 @@ again: return migrate_vma_collect_hole(start, end, -1, walk); if (pmd_trans_huge(*pmdp)) { - struct page *page; + struct folio *folio; ptl = pmd_lock(mm, pmdp); if (unlikely(!pmd_trans_huge(*pmdp))) { @@ -79,21 +79,21 @@ again: goto again; } - page = pmd_page(*pmdp); - if (is_huge_zero_page(page)) { + folio = pmd_folio(*pmdp); + if (is_huge_zero_folio(folio)) { spin_unlock(ptl); split_huge_pmd(vma, pmdp, addr); } else { int ret; - get_page(page); + folio_get(folio); spin_unlock(ptl); - if (unlikely(!trylock_page(page))) + if (unlikely(!folio_trylock(folio))) return migrate_vma_collect_skip(start, end, walk); - ret = split_huge_page(page); - unlock_page(page); - put_page(page); + ret = split_folio(folio); + folio_unlock(folio); + folio_put(folio); if (ret) return migrate_vma_collect_skip(start, end, walk); @@ -324,6 +324,8 @@ static void migrate_vma_collect(struct migrate_vma *migrate) */ static bool migrate_vma_check_page(struct page *page, struct page *fault_page) { + struct folio *folio = page_folio(page); + /* * One extra ref because caller holds an extra reference, either from * isolate_lru_page() for a regular page, or migrate_vma_collect() for @@ -336,18 +338,18 @@ static bool migrate_vma_check_page(struct page *page, struct page *fault_page) * check them than regular pages, because they can be mapped with a pmd * or with a pte (split pte mapping). */ - if (PageCompound(page)) + if (folio_test_large(folio)) return false; /* Page from ZONE_DEVICE have one extra reference */ - if (is_zone_device_page(page)) + if (folio_is_zone_device(folio)) extra++; /* For file back page */ - if (page_mapping(page)) - extra += 1 + page_has_private(page); + if (folio_mapping(folio)) + extra += 1 + folio_has_private(folio); - if ((page_count(page) - extra) > page_mapcount(page)) + if ((folio_ref_count(folio) - extra) > folio_mapcount(folio)) return false; return true; @@ -694,6 +696,7 @@ static void __migrate_device_pages(unsigned long *src_pfns, struct page *newpage = migrate_pfn_to_page(dst_pfns[i]); struct page *page = migrate_pfn_to_page(src_pfns[i]); struct address_space *mapping; + struct folio *folio; int r; if (!newpage) { @@ -728,15 +731,12 @@ static void __migrate_device_pages(unsigned long *src_pfns, continue; } - mapping = page_mapping(page); + folio = page_folio(page); + mapping = folio_mapping(folio); if (is_device_private_page(newpage) || is_device_coherent_page(newpage)) { if (mapping) { - struct folio *folio; - - folio = page_folio(page); - /* * For now only support anonymous memory migrating to * device private or coherent memory. @@ -759,11 +759,10 @@ static void __migrate_device_pages(unsigned long *src_pfns, if (migrate && migrate->fault_page == page) r = migrate_folio_extra(mapping, page_folio(newpage), - page_folio(page), - MIGRATE_SYNC_NO_COPY, 1); + folio, MIGRATE_SYNC_NO_COPY, 1); else r = migrate_folio(mapping, page_folio(newpage), - page_folio(page), MIGRATE_SYNC_NO_COPY); + folio, MIGRATE_SYNC_NO_COPY); if (r != MIGRATEPAGE_SUCCESS) src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; } diff --git a/mm/mlock.c b/mm/mlock.c index 1ed2f2ab37cd18..30b51cdea89dec 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -378,7 +378,7 @@ static int mlock_pte_range(pmd_t *pmd, unsigned long addr, goto out; if (is_huge_zero_pmd(*pmd)) goto out; - folio = page_folio(pmd_page(*pmd)); + folio = pmd_folio(*pmd); if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else diff --git a/mm/mm_init.c b/mm/mm_init.c index 549e76af8f82a8..2c8f3af4430f5c 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -24,6 +24,7 @@ #include <linux/page_ext.h> #include <linux/pti.h> #include <linux/pgtable.h> +#include <linux/stackdepot.h> #include <linux/swap.h> #include <linux/cma.h> #include <linux/crash_dump.h> @@ -226,7 +227,6 @@ static unsigned long required_movablecore_percent __initdata; static unsigned long nr_kernel_pages __initdata; static unsigned long nr_all_pages __initdata; -static unsigned long dma_reserve __initdata; static bool deferred_struct_pages __meminitdata; @@ -1144,7 +1144,7 @@ static void __init adjust_zone_range_for_zone_movable(int nid, * Return the number of holes in a range on a node. If nid is MAX_NUMNODES, * then all holes in the requested range will be accounted for. */ -unsigned long __init __absent_pages_in_range(int nid, +static unsigned long __init __absent_pages_in_range(int nid, unsigned long range_start_pfn, unsigned long range_end_pfn) { @@ -1265,6 +1265,30 @@ static void __init reset_memoryless_node_totalpages(struct pglist_data *pgdat) pr_debug("On node %d totalpages: 0\n", pgdat->node_id); } +static void __init calc_nr_kernel_pages(void) +{ + unsigned long start_pfn, end_pfn; + phys_addr_t start_addr, end_addr; + u64 u; +#ifdef CONFIG_HIGHMEM + unsigned long high_zone_low = arch_zone_lowest_possible_pfn[ZONE_HIGHMEM]; +#endif + + for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) { + start_pfn = PFN_UP(start_addr); + end_pfn = PFN_DOWN(end_addr); + + if (start_pfn < end_pfn) { + nr_all_pages += end_pfn - start_pfn; +#ifdef CONFIG_HIGHMEM + start_pfn = clamp(start_pfn, 0, high_zone_low); + end_pfn = clamp(end_pfn, 0, high_zone_low); +#endif + nr_kernel_pages += end_pfn - start_pfn; + } + } +} + static void __init calculate_node_totalpages(struct pglist_data *pgdat, unsigned long node_start_pfn, unsigned long node_end_pfn) @@ -1308,26 +1332,6 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat, pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); } -static unsigned long __init calc_memmap_size(unsigned long spanned_pages, - unsigned long present_pages) -{ - unsigned long pages = spanned_pages; - - /* - * Provide a more accurate estimation if there are holes within - * the zone and SPARSEMEM is in use. If there are holes within the - * zone, each populated memory region may cost us one or two extra - * memmap pages due to alignment because memmap pages for each - * populated regions may not be naturally aligned on page boundary. - * So the (present_pages >> 4) heuristic is a tradeoff for that. - */ - if (spanned_pages > present_pages + (present_pages >> 4) && - IS_ENABLED(CONFIG_SPARSEMEM)) - pages = present_pages; - - return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT; -} - #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void pgdat_init_split_queue(struct pglist_data *pgdat) { @@ -1542,15 +1546,6 @@ void __ref free_area_init_core_hotplug(struct pglist_data *pgdat) } #endif -/* - * Set up the zone data structures: - * - mark all pages reserved - * - mark all memory queues empty - * - clear the memory bitmaps - * - * NOTE: pgdat should get zeroed by caller. - * NOTE: this function is only called during early init. - */ static void __init free_area_init_core(struct pglist_data *pgdat) { enum zone_type j; @@ -1561,47 +1556,13 @@ static void __init free_area_init_core(struct pglist_data *pgdat) for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long size, freesize, memmap_pages; - - size = zone->spanned_pages; - freesize = zone->present_pages; - - /* - * Adjust freesize so that it accounts for how much memory - * is used by this zone for memmap. This affects the watermark - * and per-cpu initialisations - */ - memmap_pages = calc_memmap_size(size, freesize); - if (!is_highmem_idx(j)) { - if (freesize >= memmap_pages) { - freesize -= memmap_pages; - if (memmap_pages) - pr_debug(" %s zone: %lu pages used for memmap\n", - zone_names[j], memmap_pages); - } else - pr_warn(" %s zone: %lu memmap pages exceeds freesize %lu\n", - zone_names[j], memmap_pages, freesize); - } - - /* Account for reserved pages */ - if (j == 0 && freesize > dma_reserve) { - freesize -= dma_reserve; - pr_debug(" %s zone: %lu pages reserved\n", zone_names[0], dma_reserve); - } - - if (!is_highmem_idx(j)) - nr_kernel_pages += freesize; - /* Charge for highmem memmap if there are enough kernel pages */ - else if (nr_kernel_pages > memmap_pages * 2) - nr_kernel_pages -= memmap_pages; - nr_all_pages += freesize; + unsigned long size = zone->spanned_pages; /* - * Set an approximate value for lowmem here, it will be adjusted - * when the bootmem allocator frees pages into the buddy system. - * And all highmem pages will be managed by the buddy system. + * Initialize zone->managed_pages as 0 , it will be reset + * when memblock allocator frees pages into buddy system. */ - zone_init_internals(zone, j, nid, freesize); + zone_init_internals(zone, j, nid, zone->present_pages); if (!size) continue; @@ -1874,30 +1835,26 @@ void __init free_area_init(unsigned long *max_zone_pfn) panic("Cannot allocate %zuB for node %d.\n", sizeof(*pgdat), nid); arch_refresh_nodedata(nid, pgdat); - free_area_init_node(nid); - - /* - * We do not want to confuse userspace by sysfs - * files/directories for node without any memory - * attached to it, so this node is not marked as - * N_MEMORY and not marked online so that no sysfs - * hierarchy will be created via register_one_node for - * it. The pgdat will get fully initialized by - * hotadd_init_pgdat() when memory is hotplugged into - * this node. - */ - continue; } pgdat = NODE_DATA(nid); free_area_init_node(nid); - /* Any memory on that node */ - if (pgdat->node_present_pages) + /* + * No sysfs hierarcy will be created via register_one_node() + *for memory-less node because here it's not marked as N_MEMORY + *and won't be set online later. The benefit is userspace + *program won't be confused by sysfs files/directories of + *memory-less node. The pgdat will get fully initialized by + *hotadd_init_pgdat() when memory is hotplugged into this node. + */ + if (pgdat->node_present_pages) { node_set_state(nid, N_MEMORY); - check_for_memory(pgdat); + check_for_memory(pgdat); + } } + calc_nr_kernel_pages(); memmap_init(); /* disable hash distribution for systems with a single node */ @@ -2057,7 +2014,7 @@ static unsigned long __init deferred_init_pages(struct zone *zone, __init_single_page(page, pfn, zid, nid); nr_pages++; } - return (nr_pages); + return nr_pages; } /* @@ -2259,10 +2216,6 @@ zone_empty: * Return true when zone was grown, otherwise return false. We return true even * when we grow less than requested, to let the caller decide if there are * enough pages to satisfy the allocation. - * - * Note: We use noinline because this function is needed only during boot, and - * it is called from a __ref function _deferred_grow_zone. This way we are - * making sure that it is not inlined into permanent text section. */ bool __init deferred_grow_zone(struct zone *zone, unsigned int order) { @@ -2412,17 +2365,6 @@ void __init page_alloc_init_late(void) page_alloc_sysctl_init(); } -#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES -/* - * Returns the number of pages that arch has reserved but - * is not known to alloc_large_system_hash(). - */ -static unsigned long __init arch_reserved_kernel_pages(void) -{ - return 0; -} -#endif - /* * Adaptive scale is meant to reduce sizes of hash tables on large memory * machines. As memory size is increased the scale is also increased but at @@ -2465,7 +2407,6 @@ void *__init alloc_large_system_hash(const char *tablename, if (!numentries) { /* round applicable memory size up to nearest megabyte */ numentries = nr_kernel_pages; - numentries -= arch_reserved_kernel_pages(); /* It isn't necessary when PAGE_SIZE >= 1MB */ if (PAGE_SIZE < SZ_1M) @@ -2547,26 +2488,9 @@ void *__init alloc_large_system_hash(const char *tablename, return table; } -/** - * set_dma_reserve - set the specified number of pages reserved in the first zone - * @new_dma_reserve: The number of pages to mark reserved - * - * The per-cpu batchsize and zone watermarks are determined by managed_pages. - * In the DMA zone, a significant percentage may be consumed by kernel image - * and other unfreeable allocations which can skew the watermarks badly. This - * function may optionally be used to account for unfreeable pages in the - * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and - * smaller per-cpu batchsize. - */ -void __init set_dma_reserve(unsigned long new_dma_reserve) -{ - dma_reserve = new_dma_reserve; -} - void __init memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order) { - if (IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT)) { int nid = early_pfn_to_nid(pfn); @@ -2578,6 +2502,17 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, /* KMSAN will take care of these pages. */ return; } + + /* pages were reserved and not allocated */ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } + __free_pages_core(page, order); } @@ -2587,6 +2522,9 @@ EXPORT_SYMBOL(init_on_alloc); DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); EXPORT_SYMBOL(init_on_free); +DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); +EXPORT_SYMBOL(init_mlocked_on_free); + static bool _init_on_alloc_enabled_early __read_mostly = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); static int __init early_init_on_alloc(char *buf) @@ -2604,6 +2542,14 @@ static int __init early_init_on_free(char *buf) } early_param("init_on_free", early_init_on_free); +static bool _init_mlocked_on_free_enabled_early __read_mostly + = IS_ENABLED(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON); +static int __init early_init_mlocked_on_free(char *buf) +{ + return kstrtobool(buf, &_init_mlocked_on_free_enabled_early); +} +early_param("init_mlocked_on_free", early_init_mlocked_on_free); + DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); /* @@ -2631,12 +2577,21 @@ static void __init mem_debugging_and_hardening_init(void) } #endif - if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && + if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early || + _init_mlocked_on_free_enabled_early) && page_poisoning_requested) { pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_alloc and init_on_free\n"); + "will take precedence over init_on_alloc, init_on_free " + "and init_mlocked_on_free\n"); _init_on_alloc_enabled_early = false; _init_on_free_enabled_early = false; + _init_mlocked_on_free_enabled_early = false; + } + + if (_init_mlocked_on_free_enabled_early && _init_on_free_enabled_early) { + pr_info("mem auto-init: init_on_free is on, " + "will take precedence over init_mlocked_on_free\n"); + _init_mlocked_on_free_enabled_early = false; } if (_init_on_alloc_enabled_early) { @@ -2653,9 +2608,17 @@ static void __init mem_debugging_and_hardening_init(void) static_branch_disable(&init_on_free); } - if (IS_ENABLED(CONFIG_KMSAN) && - (_init_on_alloc_enabled_early || _init_on_free_enabled_early)) - pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n"); + if (_init_mlocked_on_free_enabled_early) { + want_check_pages = true; + static_branch_enable(&init_mlocked_on_free); + } else { + static_branch_disable(&init_mlocked_on_free); + } + + if (IS_ENABLED(CONFIG_KMSAN) && (_init_on_alloc_enabled_early || + _init_on_free_enabled_early || _init_mlocked_on_free_enabled_early)) + pr_info("mem auto-init: please make sure init_on_alloc, init_on_free and " + "init_mlocked_on_free are disabled when running KMSAN\n"); #ifdef CONFIG_DEBUG_PAGEALLOC if (debug_pagealloc_enabled()) { @@ -2694,9 +2657,10 @@ static void __init report_meminit(void) else stack = "off"; - pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n", + pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s, mlocked free:%s\n", stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off", - want_init_on_free() ? "on" : "off"); + want_init_on_free() ? "on" : "off", + want_init_mlocked_on_free() ? "on" : "off"); if (want_init_on_free()) pr_info("mem auto-init: clearing system memory may take some time...\n"); } diff --git a/mm/mmap.c b/mm/mmap.c index 6dbda99a47da1c..057270dbe3aa12 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1114,21 +1114,21 @@ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_ */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { - MA_STATE(mas, &vma->vm_mm->mm_mt, vma->vm_end, vma->vm_end); struct anon_vma *anon_vma = NULL; struct vm_area_struct *prev, *next; + VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end); /* Try next first. */ - next = mas_walk(&mas); + next = vma_iter_load(&vmi); if (next) { anon_vma = reusable_anon_vma(next, vma, next); if (anon_vma) return anon_vma; } - prev = mas_prev(&mas, 0); + prev = vma_prev(&vmi); VM_BUG_ON_VMA(prev != vma, vma); - prev = mas_prev(&mas, 0); + prev = vma_prev(&vmi); /* Try prev next. */ if (prev) anon_vma = reusable_anon_vma(prev, prev, vma); @@ -1255,17 +1255,15 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (mm->map_count > sysctl_max_map_count) return -ENOMEM; - /* Obtain the address to map to. we verify (or select) it and ensure - * that it represents a valid section of the address space. + /* + * addr is returned from get_unmapped_area, + * There are two cases: + * 1> MAP_FIXED == false + * unallocated memory, no need to check sealing. + * 1> MAP_FIXED == true + * sealing is checked inside mmap_region when + * do_vmi_munmap is called. */ - addr = get_unmapped_area(file, addr, len, pgoff, flags); - if (IS_ERR_VALUE(addr)) - return addr; - - if (flags & MAP_FIXED_NOREPLACE) { - if (find_vma_intersection(mm, addr, addr + len)) - return -EEXIST; - } if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); @@ -1280,6 +1278,18 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags |= calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; + /* Obtain the address to map to. we verify (or select) it and ensure + * that it represents a valid section of the address space. + */ + addr = __get_unmapped_area(file, addr, len, pgoff, flags, vm_flags); + if (IS_ERR_VALUE(addr)) + return addr; + + if (flags & MAP_FIXED_NOREPLACE) { + if (find_vma_intersection(mm, addr, addr + len)) + return -EEXIST; + } + if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; @@ -1514,32 +1524,32 @@ bool vma_needs_dirty_tracking(struct vm_area_struct *vma) * to the private version (using protection_map[] without the * VM_SHARED bit). */ -int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) +bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { /* If it was private or non-writable, the write bit is already clear */ if (!vma_is_shared_writable(vma)) - return 0; + return false; /* The backer wishes to know when pages are first written to? */ if (vm_ops_needs_writenotify(vma->vm_ops)) - return 1; + return true; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags))) - return 0; + return false; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) - return 1; + return true; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_wp(vma)) - return 1; + return true; /* Can the mapping track the dirty pages? */ return vma_fs_can_writeback(vma); @@ -1549,14 +1559,14 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ -static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) +static inline bool accountable_mapping(struct file *file, vm_flags_t vm_flags) { /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) - return 0; + return false; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } @@ -1576,11 +1586,10 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) unsigned long length, gap; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; - - MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); + VMA_ITERATOR(vmi, current->mm, 0); /* Adjust search length to account for worst case alignment overhead */ - length = info->length + info->align_mask; + length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; @@ -1589,23 +1598,29 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: - if (mas_empty_area(&mas, low_limit, high_limit - 1, length)) + if (vma_iter_area_lowest(&vmi, low_limit, high_limit, length)) return -ENOMEM; - gap = mas.index; + /* + * Adjust for the gap first so it doesn't interfere with the + * later alignment. The first step is the minimum needed to + * fulill the start gap, the next steps is the minimum to align + * that. It is the minimum needed to fulill both. + */ + gap = vma_iter_addr(&vmi) + info->start_gap; gap += (info->align_offset - gap) & info->align_mask; - tmp = mas_next(&mas, ULONG_MAX); + tmp = vma_next(&vmi); if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) < gap + length - 1) { low_limit = tmp->vm_end; - mas_reset(&mas); + vma_iter_reset(&vmi); goto retry; } } else { - tmp = mas_prev(&mas, 0); + tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { low_limit = vm_end_gap(tmp); - mas_reset(&mas); + vma_iter_reset(&vmi); goto retry; } } @@ -1628,10 +1643,10 @@ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) unsigned long length, gap, gap_end; unsigned long low_limit, high_limit; struct vm_area_struct *tmp; + VMA_ITERATOR(vmi, current->mm, 0); - MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); /* Adjust search length to account for worst case alignment overhead */ - length = info->length + info->align_mask; + length = info->length + info->align_mask + info->start_gap; if (length < info->length) return -ENOMEM; @@ -1640,24 +1655,24 @@ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) low_limit = mmap_min_addr; high_limit = info->high_limit; retry: - if (mas_empty_area_rev(&mas, low_limit, high_limit - 1, length)) + if (vma_iter_area_highest(&vmi, low_limit, high_limit, length)) return -ENOMEM; - gap = mas.last + 1 - info->length; + gap = vma_iter_end(&vmi) - info->length; gap -= (gap - info->align_offset) & info->align_mask; - gap_end = mas.last; - tmp = mas_next(&mas, ULONG_MAX); + gap_end = vma_iter_end(&vmi); + tmp = vma_next(&vmi); if (tmp && (tmp->vm_flags & VM_STARTGAP_FLAGS)) { /* Avoid prev check if possible */ - if (vm_start_gap(tmp) <= gap_end) { + if (vm_start_gap(tmp) < gap_end) { high_limit = vm_start_gap(tmp); - mas_reset(&mas); + vma_iter_reset(&vmi); goto retry; } } else { - tmp = mas_prev(&mas, 0); + tmp = vma_prev(&vmi); if (tmp && vm_end_gap(tmp) > gap) { high_limit = tmp->vm_start; - mas_reset(&mas); + vma_iter_reset(&vmi); goto retry; } } @@ -1705,7 +1720,7 @@ generic_get_unmapped_area(struct file *filp, unsigned long addr, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len > mmap_end - mmap_min_addr) @@ -1723,12 +1738,9 @@ generic_get_unmapped_area(struct file *filp, unsigned long addr, return addr; } - info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = mmap_end; - info.align_mask = 0; - info.align_offset = 0; return vm_unmapped_area(&info); } @@ -1753,7 +1765,7 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; - struct vm_unmapped_area_info info; + struct vm_unmapped_area_info info = {}; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); /* requested length too big for entire address space */ @@ -1777,8 +1789,6 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); - info.align_mask = 0; - info.align_offset = 0; addr = vm_unmapped_area(&info); /* @@ -1808,12 +1818,41 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, } #endif +#ifndef HAVE_ARCH_UNMAPPED_AREA_VMFLAGS +unsigned long +arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) +{ + return arch_get_unmapped_area(filp, addr, len, pgoff, flags); +} + unsigned long -get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags) +arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) +{ + return arch_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); +} +#endif + +unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, struct file *filp, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags) +{ + if (test_bit(MMF_TOPDOWN, &mm->flags)) + return arch_get_unmapped_area_topdown_vmflags(filp, addr, len, pgoff, + flags, vm_flags); + return arch_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, vm_flags); +} + +unsigned long +__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { unsigned long (*get_area)(struct file *, unsigned long, - unsigned long, unsigned long, unsigned long); + unsigned long, unsigned long, unsigned long) + = NULL; unsigned long error = arch_mmap_check(addr, len, flags); if (error) @@ -1823,7 +1862,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (len > TASK_SIZE) return -ENOMEM; - get_area = current->mm->get_unmapped_area; if (file) { if (file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; @@ -1833,16 +1871,22 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, * so use shmem's get_unmapped_area in case it can be huge. */ get_area = shmem_get_unmapped_area; - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - /* Ensures that larger anonymous mappings are THP aligned. */ - get_area = thp_get_unmapped_area; } /* Always treat pgoff as zero for anonymous memory. */ if (!file) pgoff = 0; - addr = get_area(file, addr, len, pgoff, flags); + if (get_area) { + addr = get_area(file, addr, len, pgoff, flags); + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + /* Ensures that larger anonymous mappings are THP aligned. */ + addr = thp_get_unmapped_area_vmflags(file, addr, len, + pgoff, flags, vm_flags); + } else { + addr = mm_get_unmapped_area_vmflags(current->mm, file, addr, len, + pgoff, flags, vm_flags); + } if (IS_ERR_VALUE(addr)) return addr; @@ -1855,7 +1899,16 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, return error ? error : addr; } -EXPORT_SYMBOL(get_unmapped_area); +unsigned long +mm_get_unmapped_area(struct mm_struct *mm, struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + if (test_bit(MMF_TOPDOWN, &mm->flags)) + return arch_get_unmapped_area_topdown(file, addr, len, pgoff, flags); + return arch_get_unmapped_area(file, addr, len, pgoff, flags); +} +EXPORT_SYMBOL(mm_get_unmapped_area); /** * find_vma_intersection() - Look up the first VMA which intersects the interval @@ -1912,12 +1965,12 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma; - MA_STATE(mas, &mm->mm_mt, addr, addr); + VMA_ITERATOR(vmi, mm, addr); - vma = mas_walk(&mas); - *pprev = mas_prev(&mas, 0); + vma = vma_iter_load(&vmi); + *pprev = vma_prev(&vmi); if (!vma) - vma = mas_next(&mas, ULONG_MAX); + vma = vma_next(&vmi); return vma; } @@ -1971,7 +2024,7 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) struct vm_area_struct *next; unsigned long gap_addr; int error = 0; - MA_STATE(mas, &mm->mm_mt, vma->vm_start, address); + VMA_ITERATOR(vmi, mm, vma->vm_start); if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; @@ -1997,15 +2050,15 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) } if (next) - mas_prev_range(&mas, address); + vma_iter_prev_range_limit(&vmi, address); - __mas_set_range(&mas, vma->vm_start, address - 1); - if (mas_preallocate(&mas, vma, GFP_KERNEL)) + vma_iter_config(&vmi, vma->vm_start, address); + if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { - mas_destroy(&mas); + vma_iter_free(&vmi); return -ENOMEM; } @@ -2045,7 +2098,7 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; /* Overwrite old entry in mtree. */ - mas_store_prealloc(&mas, vma); + vma_iter_store(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); @@ -2054,7 +2107,7 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) } } anon_vma_unlock_write(vma->anon_vma); - mas_destroy(&mas); + vma_iter_free(&vmi); validate_mm(mm); return error; } @@ -2067,9 +2120,9 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; - MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_start); struct vm_area_struct *prev; int error = 0; + VMA_ITERATOR(vmi, mm, vma->vm_start); if (!(vma->vm_flags & VM_GROWSDOWN)) return -EFAULT; @@ -2079,7 +2132,7 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) return -EPERM; /* Enforce stack_guard_gap */ - prev = mas_prev(&mas, 0); + prev = vma_prev(&vmi); /* Check that both stack segments have the same anon_vma? */ if (prev) { if (!(prev->vm_flags & VM_GROWSDOWN) && @@ -2089,15 +2142,15 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) } if (prev) - mas_next_range(&mas, vma->vm_start); + vma_iter_next_range_limit(&vmi, vma->vm_start); - __mas_set_range(&mas, address, vma->vm_end - 1); - if (mas_preallocate(&mas, vma, GFP_KERNEL)) + vma_iter_config(&vmi, address, vma->vm_end); + if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { - mas_destroy(&mas); + vma_iter_free(&vmi); return -ENOMEM; } @@ -2138,7 +2191,7 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) vma->vm_start = address; vma->vm_pgoff -= grow; /* Overwrite old entry in mtree. */ - mas_store_prealloc(&mas, vma); + vma_iter_store(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); @@ -2147,7 +2200,7 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) } } anon_vma_unlock_write(vma->anon_vma); - mas_destroy(&mas); + vma_iter_free(&vmi); validate_mm(mm); return error; } @@ -2682,6 +2735,14 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, if (end == start) return -EINVAL; + /* + * Check if memory is sealed before arch_unmap. + * Prevent unmapping a sealed VMA. + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(mm, start, end))) + return -EPERM; + /* arch_unmap() might do unmaps itself. */ arch_unmap(mm, start, end); @@ -2744,7 +2805,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } /* Unmap any existing mapping in the area */ - if (do_vmi_munmap(&vmi, mm, addr, len, uf, false)) + error = do_vmi_munmap(&vmi, mm, addr, len, uf, false); + if (error == -EPERM) + return error; + else if (error) return -ENOMEM; /* @@ -3094,6 +3158,14 @@ int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; + /* + * Check if memory is sealed before arch_unmap. + * Prevent unmapping a sealed VMA. + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(mm, start, end))) + return -EPERM; + arch_unmap(mm, start, end); return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); } @@ -3242,7 +3314,7 @@ void exit_mmap(struct mm_struct *mm) struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; - MA_STATE(mas, &mm->mm_mt, 0, 0); + VMA_ITERATOR(vmi, mm, 0); int count = 0; /* mm's last user has gone, and its about to be pulled down */ @@ -3251,7 +3323,7 @@ void exit_mmap(struct mm_struct *mm) mmap_read_lock(mm); arch_exit_mmap(mm); - vma = mas_find(&mas, ULONG_MAX); + vma = vma_next(&vmi); if (!vma || unlikely(xa_is_zero(vma))) { /* Can happen if dup_mmap() received an OOM */ mmap_read_unlock(mm); @@ -3264,7 +3336,7 @@ void exit_mmap(struct mm_struct *mm) tlb_gather_mmu_fullmm(&tlb, mm); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */ - unmap_vmas(&tlb, &mas, vma, 0, ULONG_MAX, ULONG_MAX, false); + unmap_vmas(&tlb, &vmi.mas, vma, 0, ULONG_MAX, ULONG_MAX, false); mmap_read_unlock(mm); /* @@ -3274,8 +3346,8 @@ void exit_mmap(struct mm_struct *mm) set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); mt_clear_in_rcu(&mm->mm_mt); - mas_set(&mas, vma->vm_end); - free_pgtables(&tlb, &mas, vma, FIRST_USER_ADDRESS, + vma_iter_set(&vmi, vma->vm_end); + free_pgtables(&tlb, &vmi.mas, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING, true); tlb_finish_mmu(&tlb); @@ -3284,14 +3356,14 @@ void exit_mmap(struct mm_struct *mm) * enabled, without holding any MM locks besides the unreachable * mmap_write_lock. */ - mas_set(&mas, vma->vm_end); + vma_iter_set(&vmi, vma->vm_end); do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); remove_vma(vma, true); count++; cond_resched(); - vma = mas_find(&mas, ULONG_MAX); + vma = vma_next(&vmi); } while (vma && likely(!xa_is_zero(vma))); BUG_ON(count != mm->map_count); @@ -3713,7 +3785,7 @@ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; - MA_STATE(mas, &mm->mm_mt, 0, 0); + VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); @@ -3725,14 +3797,14 @@ int mm_take_all_locks(struct mm_struct *mm) * being written to until mmap_write_unlock() or mmap_write_downgrade() * is reached. */ - mas_for_each(&mas, vma, ULONG_MAX) { + for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; vma_start_write(vma); } - mas_set(&mas, 0); - mas_for_each(&mas, vma, ULONG_MAX) { + vma_iter_init(&vmi, mm, 0); + for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && @@ -3740,8 +3812,8 @@ int mm_take_all_locks(struct mm_struct *mm) vm_lock_mapping(mm, vma->vm_file->f_mapping); } - mas_set(&mas, 0); - mas_for_each(&mas, vma, ULONG_MAX) { + vma_iter_init(&vmi, mm, 0); + for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && @@ -3749,8 +3821,8 @@ int mm_take_all_locks(struct mm_struct *mm) vm_lock_mapping(mm, vma->vm_file->f_mapping); } - mas_set(&mas, 0); - mas_for_each(&mas, vma, ULONG_MAX) { + vma_iter_init(&vmi, mm, 0); + for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) @@ -3809,12 +3881,12 @@ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; - MA_STATE(mas, &mm->mm_mt, 0, 0); + VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); - mas_for_each(&mas, vma, ULONG_MAX) { + for_each_vma(vmi, vma) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); diff --git a/mm/mprotect.c b/mm/mprotect.c index f8a4544b4601db..8c6cd88252738d 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -32,6 +32,7 @@ #include <linux/sched/sysctl.h> #include <linux/userfaultfd_k.h> #include <linux/memory-tiers.h> +#include <uapi/linux/mman.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> @@ -129,7 +130,8 @@ static long change_pte_range(struct mmu_gather *tlb, /* Also skip shared copy-on-write pages */ if (is_cow_mapping(vma->vm_flags) && - folio_ref_count(folio) != 1) + (folio_maybe_dma_pinned(folio) || + folio_likely_mapped_shared(folio))) continue; /* @@ -743,6 +745,15 @@ static int do_mprotect_pkey(unsigned long start, size_t len, } } + /* + * checking if memory is sealed. + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(current->mm, start, end))) { + error = -EPERM; + goto out; + } + prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; diff --git a/mm/mremap.c b/mm/mremap.c index 38d98465f3d825..5f96bc5ee91827 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -205,7 +205,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, */ if (pte_present(pte)) force_flush = true; - pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); + pte = move_pte(pte, old_addr, new_addr); pte = move_soft_dirty_pte(pte); set_pte_at(mm, new_addr, new_pte, pte); } @@ -902,7 +902,25 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, if ((mm->map_count + 2) >= sysctl_max_map_count - 3) return -ENOMEM; + /* + * In mremap_to(). + * Move a VMA to another location, check if src addr is sealed. + * + * Place can_modify_mm here because mremap_to() + * does its own checking for address range, and we only + * check the sealing after passing those checks. + * + * can_modify_mm assumes we have acquired the lock on MM. + */ + if (unlikely(!can_modify_mm(mm, addr, addr + old_len))) + return -EPERM; + if (flags & MREMAP_FIXED) { + /* + * In mremap_to(). + * VMA is moved to dst address, and munmap dst first. + * do_munmap will check if dst is sealed. + */ ret = do_munmap(mm, new_addr, new_len, uf_unmap_early); if (ret) goto out; @@ -1062,6 +1080,19 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, } /* + * Below is shrink/expand case (not mremap_to()) + * Check if src address is sealed, if so, reject. + * In other words, prevent shrinking or expanding a sealed VMA. + * + * Place can_modify_mm here so we can keep the logic related to + * shrink/expand together. + */ + if (unlikely(!can_modify_mm(mm, addr, addr + old_len))) { + ret = -EPERM; + goto out; + } + + /* * Always allow a shrinking remap: that just unmaps * the unnecessary pages.. * do_vmi_munmap does all the needed commit accounting, and diff --git a/mm/mseal.c b/mm/mseal.c new file mode 100644 index 00000000000000..bf783bba8ed0b9 --- /dev/null +++ b/mm/mseal.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Implement mseal() syscall. + * + * Copyright (c) 2023,2024 Google, Inc. + * + * Author: Jeff Xu <jeffxu@chromium.org> + */ + +#include <linux/mempolicy.h> +#include <linux/mman.h> +#include <linux/mm.h> +#include <linux/mm_inline.h> +#include <linux/mmu_context.h> +#include <linux/syscalls.h> +#include <linux/sched.h> +#include "internal.h" + +static inline bool vma_is_sealed(struct vm_area_struct *vma) +{ + return (vma->vm_flags & VM_SEALED); +} + +static inline void set_vma_sealed(struct vm_area_struct *vma) +{ + vm_flags_set(vma, VM_SEALED); +} + +/* + * check if a vma is sealed for modification. + * return true, if modification is allowed. + */ +static bool can_modify_vma(struct vm_area_struct *vma) +{ + if (unlikely(vma_is_sealed(vma))) + return false; + + return true; +} + +static bool is_madv_discard(int behavior) +{ + return behavior & + (MADV_FREE | MADV_DONTNEED | MADV_DONTNEED_LOCKED | + MADV_REMOVE | MADV_DONTFORK | MADV_WIPEONFORK); +} + +static bool is_ro_anon(struct vm_area_struct *vma) +{ + /* check anonymous mapping. */ + if (vma->vm_file || vma->vm_flags & VM_SHARED) + return false; + + /* + * check for non-writable: + * PROT=RO or PKRU is not writeable. + */ + if (!(vma->vm_flags & VM_WRITE) || + !arch_vma_access_permitted(vma, true, false, false)) + return true; + + return false; +} + +/* + * Check if the vmas of a memory range are allowed to be modified. + * the memory ranger can have a gap (unallocated memory). + * return true, if it is allowed. + */ +bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end) +{ + struct vm_area_struct *vma; + + VMA_ITERATOR(vmi, mm, start); + + /* going through each vma to check. */ + for_each_vma_range(vmi, vma, end) { + if (unlikely(!can_modify_vma(vma))) + return false; + } + + /* Allow by default. */ + return true; +} + +/* + * Check if the vmas of a memory range are allowed to be modified by madvise. + * the memory ranger can have a gap (unallocated memory). + * return true, if it is allowed. + */ +bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long end, + int behavior) +{ + struct vm_area_struct *vma; + + VMA_ITERATOR(vmi, mm, start); + + if (!is_madv_discard(behavior)) + return true; + + /* going through each vma to check. */ + for_each_vma_range(vmi, vma, end) + if (unlikely(is_ro_anon(vma) && !can_modify_vma(vma))) + return false; + + /* Allow by default. */ + return true; +} + +static int mseal_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, + struct vm_area_struct **prev, unsigned long start, + unsigned long end, vm_flags_t newflags) +{ + int ret = 0; + vm_flags_t oldflags = vma->vm_flags; + + if (newflags == oldflags) + goto out; + + vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto out; + } + + set_vma_sealed(vma); +out: + *prev = vma; + return ret; +} + +/* + * Check for do_mseal: + * 1> start is part of a valid vma. + * 2> end is part of a valid vma. + * 3> No gap (unallocated address) between start and end. + * 4> map is sealable. + */ +static int check_mm_seal(unsigned long start, unsigned long end) +{ + struct vm_area_struct *vma; + unsigned long nstart = start; + + VMA_ITERATOR(vmi, current->mm, start); + + /* going through each vma to check. */ + for_each_vma_range(vmi, vma, end) { + if (vma->vm_start > nstart) + /* unallocated memory found. */ + return -ENOMEM; + + if (vma->vm_end >= end) + return 0; + + nstart = vma->vm_end; + } + + return -ENOMEM; +} + +/* + * Apply sealing. + */ +static int apply_mm_seal(unsigned long start, unsigned long end) +{ + unsigned long nstart; + struct vm_area_struct *vma, *prev; + + VMA_ITERATOR(vmi, current->mm, start); + + vma = vma_iter_load(&vmi); + /* + * Note: check_mm_seal should already checked ENOMEM case. + * so vma should not be null, same for the other ENOMEM cases. + */ + prev = vma_prev(&vmi); + if (start > vma->vm_start) + prev = vma; + + nstart = start; + for_each_vma_range(vmi, vma, end) { + int error; + unsigned long tmp; + vm_flags_t newflags; + + newflags = vma->vm_flags | VM_SEALED; + tmp = vma->vm_end; + if (tmp > end) + tmp = end; + error = mseal_fixup(&vmi, vma, &prev, nstart, tmp, newflags); + if (error) + return error; + nstart = vma_iter_end(&vmi); + } + + return 0; +} + +/* + * mseal(2) seals the VM's meta data from + * selected syscalls. + * + * addr/len: VM address range. + * + * The address range by addr/len must meet: + * start (addr) must be in a valid VMA. + * end (addr + len) must be in a valid VMA. + * no gap (unallocated memory) between start and end. + * start (addr) must be page aligned. + * + * len: len will be page aligned implicitly. + * + * Below VMA operations are blocked after sealing. + * 1> Unmapping, moving to another location, and shrinking + * the size, via munmap() and mremap(), can leave an empty + * space, therefore can be replaced with a VMA with a new + * set of attributes. + * 2> Moving or expanding a different vma into the current location, + * via mremap(). + * 3> Modifying a VMA via mmap(MAP_FIXED). + * 4> Size expansion, via mremap(), does not appear to pose any + * specific risks to sealed VMAs. It is included anyway because + * the use case is unclear. In any case, users can rely on + * merging to expand a sealed VMA. + * 5> mprotect and pkey_mprotect. + * 6> Some destructive madvice() behavior (e.g. MADV_DONTNEED) + * for anonymous memory, when users don't have write permission to the + * memory. Those behaviors can alter region contents by discarding pages, + * effectively a memset(0) for anonymous memory. + * + * flags: reserved. + * + * return values: + * zero: success. + * -EINVAL: + * invalid input flags. + * start address is not page aligned. + * Address arange (start + len) overflow. + * -ENOMEM: + * addr is not a valid address (not allocated). + * end (start + len) is not a valid address. + * a gap (unallocated memory) between start and end. + * -EPERM: + * - In 32 bit architecture, sealing is not supported. + * Note: + * user can call mseal(2) multiple times, adding a seal on an + * already sealed memory is a no-action (no error). + * + * unseal() is not supported. + */ +static int do_mseal(unsigned long start, size_t len_in, unsigned long flags) +{ + size_t len; + int ret = 0; + unsigned long end; + struct mm_struct *mm = current->mm; + + ret = can_do_mseal(flags); + if (ret) + return ret; + + start = untagged_addr(start); + if (!PAGE_ALIGNED(start)) + return -EINVAL; + + len = PAGE_ALIGN(len_in); + /* Check to see whether len was rounded up from small -ve to zero. */ + if (len_in && !len) + return -EINVAL; + + end = start + len; + if (end < start) + return -EINVAL; + + if (end == start) + return 0; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + /* + * First pass, this helps to avoid + * partial sealing in case of error in input address range, + * e.g. ENOMEM error. + */ + ret = check_mm_seal(start, end); + if (ret) + goto out; + + /* + * Second pass, this should success, unless there are errors + * from vma_modify_flags, e.g. merge/split error, or process + * reaching the max supported VMAs, however, those cases shall + * be rare. + */ + ret = apply_mm_seal(start, end); + +out: + mmap_write_unlock(current->mm); + return ret; +} + +SYSCALL_DEFINE3(mseal, unsigned long, start, size_t, len, unsigned long, + flags) +{ + return do_mseal(start, len, flags); +} diff --git a/mm/nommu.c b/mm/nommu.c index 5ec8f44e7ce976..331d2f778695c9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -110,55 +110,34 @@ unsigned int kobjsize(const void *objp) return page_size(page); } -/** - * follow_pfn - look up PFN at a user virtual address - * @vma: memory mapping - * @address: user virtual address - * @pfn: location to store found PFN - * - * Only IO mappings and raw PFN mappings are allowed. - * - * Returns zero and the pfn at @pfn on success, -ve otherwise. - */ -int follow_pfn(struct vm_area_struct *vma, unsigned long address, - unsigned long *pfn) -{ - if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) - return -EINVAL; - - *pfn = address >> PAGE_SHIFT; - return 0; -} -EXPORT_SYMBOL(follow_pfn); - void vfree(const void *addr) { kfree(addr); } EXPORT_SYMBOL(vfree); -void *__vmalloc(unsigned long size, gfp_t gfp_mask) +void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) { /* * You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc() * returns only a logical address. */ - return kmalloc(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM); + return kmalloc_noprof(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM); } -EXPORT_SYMBOL(__vmalloc); +EXPORT_SYMBOL(__vmalloc_noprof); -void *__vmalloc_node_range(unsigned long size, unsigned long align, +void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) { - return __vmalloc(size, gfp_mask); + return __vmalloc_noprof(size, gfp_mask); } -void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, +void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { - return __vmalloc(size, gfp_mask); + return __vmalloc_noprof(size, gfp_mask); } static void *__vmalloc_user_flags(unsigned long size, gfp_t flags) @@ -179,11 +158,11 @@ static void *__vmalloc_user_flags(unsigned long size, gfp_t flags) return ret; } -void *vmalloc_user(unsigned long size) +void *vmalloc_user_noprof(unsigned long size) { return __vmalloc_user_flags(size, GFP_KERNEL | __GFP_ZERO); } -EXPORT_SYMBOL(vmalloc_user); +EXPORT_SYMBOL(vmalloc_user_noprof); struct page *vmalloc_to_page(const void *addr) { @@ -217,13 +196,13 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count) * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ -void *vmalloc(unsigned long size) +void *vmalloc_noprof(unsigned long size) { - return __vmalloc(size, GFP_KERNEL); + return __vmalloc_noprof(size, GFP_KERNEL); } -EXPORT_SYMBOL(vmalloc); +EXPORT_SYMBOL(vmalloc_noprof); -void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __weak __alias(__vmalloc); +void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) __weak __alias(__vmalloc_noprof); /* * vzalloc - allocate virtually contiguous memory with zero fill @@ -237,11 +216,11 @@ void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __weak __alias(__vmalloc) * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ -void *vzalloc(unsigned long size) +void *vzalloc_noprof(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_ZERO); + return __vmalloc_noprof(size, GFP_KERNEL | __GFP_ZERO); } -EXPORT_SYMBOL(vzalloc); +EXPORT_SYMBOL(vzalloc_noprof); /** * vmalloc_node - allocate memory on a specific node @@ -254,11 +233,11 @@ EXPORT_SYMBOL(vzalloc); * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ -void *vmalloc_node(unsigned long size, int node) +void *vmalloc_node_noprof(unsigned long size, int node) { - return vmalloc(size); + return vmalloc_noprof(size); } -EXPORT_SYMBOL(vmalloc_node); +EXPORT_SYMBOL(vmalloc_node_noprof); /** * vzalloc_node - allocate memory on a specific node with zero fill @@ -272,11 +251,11 @@ EXPORT_SYMBOL(vmalloc_node); * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ -void *vzalloc_node(unsigned long size, int node) +void *vzalloc_node_noprof(unsigned long size, int node) { - return vzalloc(size); + return vzalloc_noprof(size); } -EXPORT_SYMBOL(vzalloc_node); +EXPORT_SYMBOL(vzalloc_node_noprof); /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) @@ -285,11 +264,11 @@ EXPORT_SYMBOL(vzalloc_node); * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. */ -void *vmalloc_32(unsigned long size) +void *vmalloc_32_noprof(unsigned long size) { - return __vmalloc(size, GFP_KERNEL); + return __vmalloc_noprof(size, GFP_KERNEL); } -EXPORT_SYMBOL(vmalloc_32); +EXPORT_SYMBOL(vmalloc_32_noprof); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory @@ -301,15 +280,15 @@ EXPORT_SYMBOL(vmalloc_32); * VM_USERMAP is set on the corresponding VMA so that subsequent calls to * remap_vmalloc_range() are permissible. */ -void *vmalloc_32_user(unsigned long size) +void *vmalloc_32_user_noprof(unsigned long size) { /* * We'll have to sort out the ZONE_DMA bits for 64-bit, * but for now this can simply use vmalloc_user() directly. */ - return vmalloc_user(size); + return vmalloc_user_noprof(size); } -EXPORT_SYMBOL(vmalloc_32_user); +EXPORT_SYMBOL(vmalloc_32_user_noprof); void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 8d6a207c3c5905..4d7a0004df2cac 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -724,7 +724,6 @@ static struct ctl_table vm_oom_kill_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - {} }; #endif diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3e19b87049db17..692c0da04cbd03 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -838,13 +838,15 @@ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, } /** - * __wb_calc_thresh - @wb's share of dirty throttling threshold + * __wb_calc_thresh - @wb's share of dirty threshold * @dtc: dirty_throttle_context of interest + * @thresh: dirty throttling or dirty background threshold of wb_domain in @dtc * - * Note that balance_dirty_pages() will only seriously take it as a hard limit - * when sleeping max_pause per page is not enough to keep the dirty pages under - * control. For example, when the device is completely stalled due to some error - * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. + * Note that balance_dirty_pages() will only seriously take dirty throttling + * threshold as a hard limit when sleeping max_pause per page is not enough + * to keep the dirty pages under control. For example, when the device is + * completely stalled due to some error conditions, or when there are 1000 + * dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * @@ -855,19 +857,20 @@ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * - * Return: @wb's dirty limit in pages. The term "dirty" in the context of - * dirty balancing includes all PG_dirty and PG_writeback pages. + * Return: @wb's dirty limit in pages. For dirty throttling limit, the term + * "dirty" in the context of dirty balancing includes all PG_dirty and + * PG_writeback pages. */ -static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) +static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, + unsigned long thresh) { struct wb_domain *dom = dtc_dom(dtc); - unsigned long thresh = dtc->thresh; u64 wb_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* - * Calculate this BDI's share of the thresh ratio. + * Calculate this wb's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); @@ -887,9 +890,28 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { - struct dirty_throttle_control gdtc = { GDTC_INIT(wb), - .thresh = thresh }; - return __wb_calc_thresh(&gdtc); + struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; + + return __wb_calc_thresh(&gdtc, thresh); +} + +unsigned long cgwb_calc_thresh(struct bdi_writeback *wb) +{ + struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; + struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; + unsigned long filepages = 0, headroom = 0, writeback = 0; + + gdtc.avail = global_dirtyable_memory(); + gdtc.dirty = global_node_page_state(NR_FILE_DIRTY) + + global_node_page_state(NR_WRITEBACK); + + mem_cgroup_wb_stats(wb, &filepages, &headroom, + &mdtc.dirty, &writeback); + mdtc.dirty += writeback; + mdtc_calc_avail(&mdtc, filepages, headroom); + domain_dirty_limits(&mdtc); + + return __wb_calc_thresh(&mdtc, mdtc.thresh); } /* @@ -1636,7 +1658,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ - dtc->wb_thresh = __wb_calc_thresh(dtc); + dtc->wb_thresh = __wb_calc_thresh(dtc, dtc->thresh); dtc->wb_bg_thresh = dtc->thresh ? div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; @@ -1675,7 +1697,7 @@ static int balance_dirty_pages(struct bdi_writeback *wb, struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; - unsigned long nr_reclaimable; /* = file_dirty */ + unsigned long nr_dirty; long period; long pause; long max_pause; @@ -1696,9 +1718,9 @@ static int balance_dirty_pages(struct bdi_writeback *wb, unsigned long m_thresh = 0; unsigned long m_bg_thresh = 0; - nr_reclaimable = global_node_page_state(NR_FILE_DIRTY); + nr_dirty = global_node_page_state(NR_FILE_DIRTY); gdtc->avail = global_dirtyable_memory(); - gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); + gdtc->dirty = nr_dirty + global_node_page_state(NR_WRITEBACK); domain_dirty_limits(gdtc); @@ -1749,7 +1771,7 @@ static int balance_dirty_pages(struct bdi_writeback *wb, * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ - if (!laptop_mode && nr_reclaimable > gdtc->bg_thresh && + if (!laptop_mode && nr_dirty > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb); @@ -2095,7 +2117,7 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (gdtc->dirty > gdtc->bg_thresh) return true; - thresh = wb_calc_thresh(gdtc->wb, gdtc->bg_thresh); + thresh = __wb_calc_thresh(gdtc, gdtc->bg_thresh); if (thresh < 2 * wb_stat_error()) reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); else @@ -2115,7 +2137,7 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (mdtc->dirty > mdtc->bg_thresh) return true; - thresh = wb_calc_thresh(mdtc->wb, mdtc->bg_thresh); + thresh = __wb_calc_thresh(mdtc, mdtc->bg_thresh); if (thresh < 2 * wb_stat_error()) reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); else @@ -2291,7 +2313,6 @@ static struct ctl_table vm_page_writeback_sysctls[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - {} }; #endif @@ -2700,17 +2721,20 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) } /* - * Mark the folio dirty, and set it dirty in the page cache, and mark - * the inode dirty. + * Mark the folio dirty, and set it dirty in the page cache. * * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * - * The caller must hold folio_memcg_lock(). Most callers have the folio - * locked. A few have the folio blocked from truncation through other - * means (eg zap_vma_pages() has it mapped and is holding the page table - * lock). This can also be called from mark_buffer_dirty(), which I - * cannot prove is always protected against truncate. + * The caller must hold folio_memcg_lock(). It is the caller's + * responsibility to prevent the folio from being truncated while + * this function is in progress, although it may have been truncated + * before this function is called. Most callers have the folio locked. + * A few have the folio blocked from truncation through other means (e.g. + * zap_vma_pages() has it mapped and is holding the page table lock). + * When called from mark_buffer_dirty(), the filesystem should hold a + * reference to the buffer_head that is being marked dirty, which causes + * try_to_free_buffers() to fail. */ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 14d39f34d3367f..cd584aace6bfde 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -54,6 +54,7 @@ #include <linux/khugepaged.h> #include <linux/delayacct.h> #include <linux/cacheinfo.h> +#include <linux/pgalloc_tag.h> #include <asm/div64.h> #include "internal.h" #include "shuffle.h" @@ -206,24 +207,6 @@ EXPORT_SYMBOL(node_states); gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; -/* - * A cached value of the page's pageblock's migratetype, used when the page is - * put on a pcplist. Used to avoid the pageblock migratetype lookup when - * freeing from pcplists in most cases, at the cost of possibly becoming stale. - * Also the migratetype set in the page does not necessarily match the pcplist - * index, e.g. page might have MIGRATE_CMA set but be on a pcplist with any - * other index - this ensures that it will be put on the correct CMA freelist. - */ -static inline int get_pcppage_migratetype(struct page *page) -{ - return page->index; -} - -static inline void set_pcppage_migratetype(struct page *page, int migratetype) -{ - page->index = migratetype; -} - #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE unsigned int pageblock_order __read_mostly; #endif @@ -332,7 +315,7 @@ static inline bool deferred_pages_enabled(void) static bool __ref _deferred_grow_zone(struct zone *zone, unsigned int order) { - return deferred_grow_zone(zone, order); + return deferred_grow_zone(zone, order); } #else static inline bool deferred_pages_enabled(void) @@ -523,7 +506,7 @@ static inline unsigned int order_to_pindex(int migratetype, int order) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (order > PAGE_ALLOC_COSTLY_ORDER) { - VM_BUG_ON(order != pageblock_order); + VM_BUG_ON(order != HPAGE_PMD_ORDER); return NR_LOWORDER_PCP_LISTS; } #else @@ -539,7 +522,7 @@ static inline int pindex_to_order(unsigned int pindex) #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pindex == NR_LOWORDER_PCP_LISTS) - order = pageblock_order; + order = HPAGE_PMD_ORDER; #else VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); #endif @@ -552,20 +535,12 @@ static inline bool pcp_allowed_order(unsigned int order) if (order <= PAGE_ALLOC_COSTLY_ORDER) return true; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (order == pageblock_order) + if (order == HPAGE_PMD_ORDER) return true; #endif return false; } -static inline void free_the_page(struct page *page, unsigned int order) -{ - if (pcp_allowed_order(order)) /* Via pcp? */ - free_unref_page(page, order); - else - __free_pages_ok(page, order, FPI_NONE); -} - /* * Higher-order pages are called "compound pages". They are structured thusly: * @@ -590,20 +565,6 @@ void prep_compound_page(struct page *page, unsigned int order) prep_compound_head(page, order); } -void destroy_large_folio(struct folio *folio) -{ - if (folio_test_hugetlb(folio)) { - free_huge_folio(folio); - return; - } - - if (folio_test_large_rmappable(folio)) - folio_undo_large_rmappable(folio); - - mem_cgroup_uncharge(folio); - free_the_page(&folio->page, folio_order(folio)); -} - static inline void set_buddy_order(struct page *page, unsigned int order) { set_page_private(page, order); @@ -634,12 +595,14 @@ compaction_capture(struct capture_control *capc, struct page *page, return false; /* - * Do not let lower order allocations pollute a movable pageblock. + * Do not let lower order allocations pollute a movable pageblock + * unless compaction is also requesting movable pages. * This might let an unmovable request use a reclaimable pageblock * and vice-versa but no more than normal fallback logic which can * have trouble finding a high-order free page. */ - if (order < pageblock_order && migratetype == MIGRATE_MOVABLE) + if (order < pageblock_order && migratetype == MIGRATE_MOVABLE && + capc->cc->migratetype != MIGRATE_MOVABLE) return false; capc->page = page; @@ -660,23 +623,33 @@ compaction_capture(struct capture_control *capc, struct page *page, } #endif /* CONFIG_COMPACTION */ -/* Used for pages not on another list */ -static inline void add_to_free_list(struct page *page, struct zone *zone, - unsigned int order, int migratetype) +static inline void account_freepages(struct zone *zone, int nr_pages, + int migratetype) { - struct free_area *area = &zone->free_area[order]; + if (is_migrate_isolate(migratetype)) + return; - list_add(&page->buddy_list, &area->free_list[migratetype]); - area->nr_free++; + __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); + + if (is_migrate_cma(migratetype)) + __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); } /* Used for pages not on another list */ -static inline void add_to_free_list_tail(struct page *page, struct zone *zone, - unsigned int order, int migratetype) +static inline void __add_to_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype, + bool tail) { struct free_area *area = &zone->free_area[order]; - list_add_tail(&page->buddy_list, &area->free_list[migratetype]); + VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype, + "page type is %lu, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), migratetype, 1 << order); + + if (tail) + list_add_tail(&page->buddy_list, &area->free_list[migratetype]); + else + list_add(&page->buddy_list, &area->free_list[migratetype]); area->nr_free++; } @@ -686,16 +659,28 @@ static inline void add_to_free_list_tail(struct page *page, struct zone *zone, * allocation again (e.g., optimization for memory onlining). */ static inline void move_to_free_list(struct page *page, struct zone *zone, - unsigned int order, int migratetype) + unsigned int order, int old_mt, int new_mt) { struct free_area *area = &zone->free_area[order]; - list_move_tail(&page->buddy_list, &area->free_list[migratetype]); + /* Free page moving can fail, so it happens before the type update */ + VM_WARN_ONCE(get_pageblock_migratetype(page) != old_mt, + "page type is %lu, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), old_mt, 1 << order); + + list_move_tail(&page->buddy_list, &area->free_list[new_mt]); + + account_freepages(zone, -(1 << order), old_mt); + account_freepages(zone, 1 << order, new_mt); } -static inline void del_page_from_free_list(struct page *page, struct zone *zone, - unsigned int order) +static inline void __del_page_from_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype) { + VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype, + "page type is %lu, passed migratetype is %d (nr=%d)\n", + get_pageblock_migratetype(page), migratetype, 1 << order); + /* clear reported state and update reported page count */ if (page_reported(page)) __ClearPageReported(page); @@ -706,6 +691,13 @@ static inline void del_page_from_free_list(struct page *page, struct zone *zone, zone->free_area[order].nr_free--; } +static inline void del_page_from_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype) +{ + __del_page_from_free_list(page, zone, order, migratetype); + account_freepages(zone, -(1 << order), migratetype); +} + static inline struct page *get_page_from_free_area(struct free_area *area, int migratetype) { @@ -777,16 +769,16 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); VM_BUG_ON(migratetype == -1); - if (likely(!is_migrate_isolate(migratetype))) - __mod_zone_freepage_state(zone, 1 << order, migratetype); - VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); + account_freepages(zone, 1 << order, migratetype); + while (order < MAX_PAGE_ORDER) { + int buddy_mt = migratetype; + if (compaction_capture(capc, page, order, migratetype)) { - __mod_zone_freepage_state(zone, -(1 << order), - migratetype); + account_freepages(zone, -(1 << order), migratetype); return; } @@ -801,11 +793,11 @@ static inline void __free_one_page(struct page *page, * pageblock isolation could cause incorrect freepage or CMA * accounting or HIGHATOMIC accounting. */ - int buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn); + buddy_mt = get_pfnblock_migratetype(buddy, buddy_pfn); - if (migratetype != buddy_mt - && (!migratetype_is_mergeable(migratetype) || - !migratetype_is_mergeable(buddy_mt))) + if (migratetype != buddy_mt && + (!migratetype_is_mergeable(migratetype) || + !migratetype_is_mergeable(buddy_mt))) goto done_merging; } @@ -814,9 +806,19 @@ static inline void __free_one_page(struct page *page, * merge with it and move up one order. */ if (page_is_guard(buddy)) - clear_page_guard(zone, buddy, order, migratetype); + clear_page_guard(zone, buddy, order); else - del_page_from_free_list(buddy, zone, order); + __del_page_from_free_list(buddy, zone, order, buddy_mt); + + if (unlikely(buddy_mt != migratetype)) { + /* + * Match buddy type. This ensures that an + * expand() down the line puts the sub-blocks + * on the right freelists. + */ + set_pageblock_migratetype(buddy, migratetype); + } + combined_pfn = buddy_pfn & pfn; page = page + (combined_pfn - pfn); pfn = combined_pfn; @@ -833,74 +835,13 @@ done_merging: else to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order); - if (to_tail) - add_to_free_list_tail(page, zone, order, migratetype); - else - add_to_free_list(page, zone, order, migratetype); + __add_to_free_list(page, zone, order, migratetype, to_tail); /* Notify page reporting subsystem of freed page */ if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY)) page_reporting_notify_free(order); } -/** - * split_free_page() -- split a free page at split_pfn_offset - * @free_page: the original free page - * @order: the order of the page - * @split_pfn_offset: split offset within the page - * - * Return -ENOENT if the free page is changed, otherwise 0 - * - * It is used when the free page crosses two pageblocks with different migratetypes - * at split_pfn_offset within the page. The split free page will be put into - * separate migratetype lists afterwards. Otherwise, the function achieves - * nothing. - */ -int split_free_page(struct page *free_page, - unsigned int order, unsigned long split_pfn_offset) -{ - struct zone *zone = page_zone(free_page); - unsigned long free_page_pfn = page_to_pfn(free_page); - unsigned long pfn; - unsigned long flags; - int free_page_order; - int mt; - int ret = 0; - - if (split_pfn_offset == 0) - return ret; - - spin_lock_irqsave(&zone->lock, flags); - - if (!PageBuddy(free_page) || buddy_order(free_page) != order) { - ret = -ENOENT; - goto out; - } - - mt = get_pfnblock_migratetype(free_page, free_page_pfn); - if (likely(!is_migrate_isolate(mt))) - __mod_zone_freepage_state(zone, -(1UL << order), mt); - - del_page_from_free_list(free_page, zone, order); - for (pfn = free_page_pfn; - pfn < free_page_pfn + (1UL << order);) { - int mt = get_pfnblock_migratetype(pfn_to_page(pfn), pfn); - - free_page_order = min_t(unsigned int, - pfn ? __ffs(pfn) : order, - __fls(split_pfn_offset)); - __free_one_page(pfn_to_page(pfn), pfn, zone, free_page_order, - mt, FPI_NONE); - pfn += 1UL << free_page_order; - split_pfn_offset -= (1UL << free_page_order); - /* we have done the first part, now switch to second part */ - if (split_pfn_offset == 0) - split_pfn_offset = (1UL << order) - (pfn - free_page_pfn); - } -out: - spin_unlock_irqrestore(&zone->lock, flags); - return ret; -} /* * A bad page could be due to a number of fields. Instead of multiple branches, * try and check multiple fields with one check. The caller must do a detailed @@ -996,6 +937,10 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) bad_page(page, "nonzero entire_mapcount"); goto out; } + if (unlikely(folio_large_mapcount(folio))) { + bad_page(page, "nonzero large_mapcount"); + goto out; + } if (unlikely(atomic_read(&folio->_nr_pages_mapped))) { bad_page(page, "nonzero nr_pages_mapped"); goto out; @@ -1006,10 +951,11 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) } break; case 2: - /* - * the second tail page: ->mapping is - * deferred_list.next -- ignore value. - */ + /* the second tail page: deferred_list overlaps ->mapping */ + if (unlikely(!list_empty(&folio->_deferred_list))) { + bad_page(page, "on deferred list"); + goto out; + } break; default: if (page->mapping != TAIL_MAPPING) { @@ -1070,7 +1016,7 @@ static inline bool should_skip_kasan_poison(struct page *page) return page_kasan_tag(page) == KASAN_TAG_KERNEL; } -static void kernel_init_pages(struct page *page, int numpages) +void kernel_init_pages(struct page *page, int numpages) { int i; @@ -1101,6 +1047,7 @@ __always_inline bool free_pages_prepare(struct page *page, /* Do not let hwpoison pages hit pcplists/buddy */ reset_page_owner(page, order); page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); return false; } @@ -1140,6 +1087,7 @@ __always_inline bool free_pages_prepare(struct page *page, page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; reset_page_owner(page, order); page_table_check_free(page, order); + pgalloc_tag_sub(page, 1 << order); if (!PageHighMem(page)) { debug_check_no_locks_freed(page_address(page), @@ -1191,7 +1139,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, { unsigned long flags; unsigned int order; - bool isolated_pageblocks; struct page *page; /* @@ -1204,7 +1151,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, pindex = pindex - 1; spin_lock_irqsave(&zone->lock, flags); - isolated_pageblocks = has_isolate_pageblock(zone); while (count > 0) { struct list_head *list; @@ -1220,23 +1166,19 @@ static void free_pcppages_bulk(struct zone *zone, int count, order = pindex_to_order(pindex); nr_pages = 1 << order; do { + unsigned long pfn; int mt; page = list_last_entry(list, struct page, pcp_list); - mt = get_pcppage_migratetype(page); + pfn = page_to_pfn(page); + mt = get_pfnblock_migratetype(page, pfn); /* must delete to avoid corrupting pcp list */ list_del(&page->pcp_list); count -= nr_pages; pcp->count -= nr_pages; - /* MIGRATE_ISOLATE page should not go to pcplists */ - VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); - /* Pageblock could have been isolated meanwhile */ - if (unlikely(isolated_pageblocks)) - mt = get_pageblock_migratetype(page); - - __free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE); + __free_one_page(page, pfn, zone, order, mt, FPI_NONE); trace_mm_page_pcpu_drain(page, order, mt); } while (count > 0 && !list_empty(list)); } @@ -1244,18 +1186,15 @@ static void free_pcppages_bulk(struct zone *zone, int count, spin_unlock_irqrestore(&zone->lock, flags); } -static void free_one_page(struct zone *zone, - struct page *page, unsigned long pfn, - unsigned int order, - int migratetype, fpi_t fpi_flags) +static void free_one_page(struct zone *zone, struct page *page, + unsigned long pfn, unsigned int order, + fpi_t fpi_flags) { unsigned long flags; + int migratetype; spin_lock_irqsave(&zone->lock, flags); - if (unlikely(has_isolate_pageblock(zone) || - is_migrate_isolate(migratetype))) { - migratetype = get_pfnblock_migratetype(page, pfn); - } + migratetype = get_pfnblock_migratetype(page, pfn); __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); spin_unlock_irqrestore(&zone->lock, flags); } @@ -1263,21 +1202,13 @@ static void free_one_page(struct zone *zone, static void __free_pages_ok(struct page *page, unsigned int order, fpi_t fpi_flags) { - int migratetype; unsigned long pfn = page_to_pfn(page); struct zone *zone = page_zone(page); if (!free_pages_prepare(page, order)) return; - /* - * Calling get_pfnblock_migratetype() without spin_lock_irqsave() here - * is used to avoid calling get_pfnblock_migratetype() under the lock. - * This will reduce the lock holding time. - */ - migratetype = get_pfnblock_migratetype(page, pfn); - - free_one_page(zone, page, pfn, order, migratetype, fpi_flags); + free_one_page(zone, page, pfn, order, fpi_flags); __count_vm_events(PGFREE, 1 << order); } @@ -1388,6 +1319,7 @@ static inline void expand(struct zone *zone, struct page *page, int low, int high, int migratetype) { unsigned long size = 1 << high; + unsigned long nr_added = 0; while (high > low) { high--; @@ -1400,12 +1332,14 @@ static inline void expand(struct zone *zone, struct page *page, * Corresponding page table entries will not be touched, * pages will stay not present in virtual address space */ - if (set_page_guard(zone, &page[size], high, migratetype)) + if (set_page_guard(zone, &page[size], high)) continue; - add_to_free_list(&page[size], zone, high, migratetype); + __add_to_free_list(&page[size], zone, high, migratetype, false); set_buddy_order(&page[size], high); + nr_added += size; } + account_freepages(zone, nr_added, migratetype); } static void check_new_page_bad(struct page *page) @@ -1533,6 +1467,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, set_page_owner(page, order, gfp_flags); page_table_check_alloc(page, order); + pgalloc_tag_add(page, current, 1 << order); } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, @@ -1573,9 +1508,8 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, page = get_page_from_free_area(area, migratetype); if (!page) continue; - del_page_from_free_list(page, zone, current_order); + del_page_from_free_list(page, zone, current_order, migratetype); expand(zone, page, order, current_order, migratetype); - set_pcppage_migratetype(page, migratetype); trace_mm_page_alloc_zone_locked(page, order, migratetype, pcp_allowed_order(order) && migratetype < MIGRATE_PCPTYPES); @@ -1592,7 +1526,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, * * The other migratetypes do not have fallbacks. */ -static int fallbacks[MIGRATE_TYPES][MIGRATE_PCPTYPES - 1] = { +static int fallbacks[MIGRATE_PCPTYPES][MIGRATE_PCPTYPES - 1] = { [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE }, [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE }, [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE }, @@ -1610,30 +1544,23 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone, #endif /* - * Move the free pages in a range to the freelist tail of the requested type. - * Note that start_page and end_pages are not aligned on a pageblock - * boundary. If alignment is required, use move_freepages_block() + * Change the type of a block and move all its free pages to that + * type's freelist. */ -static int move_freepages(struct zone *zone, - unsigned long start_pfn, unsigned long end_pfn, - int migratetype, int *num_movable) +static int __move_freepages_block(struct zone *zone, unsigned long start_pfn, + int old_mt, int new_mt) { struct page *page; - unsigned long pfn; + unsigned long pfn, end_pfn; unsigned int order; int pages_moved = 0; - for (pfn = start_pfn; pfn <= end_pfn;) { + VM_WARN_ON(start_pfn & (pageblock_nr_pages - 1)); + end_pfn = pageblock_end_pfn(start_pfn); + + for (pfn = start_pfn; pfn < end_pfn;) { page = pfn_to_page(pfn); if (!PageBuddy(page)) { - /* - * We assume that pages that could be isolated for - * migration are movable. But we don't actually try - * isolating, as that would be expensive. - */ - if (num_movable && - (PageLRU(page) || __PageMovable(page))) - (*num_movable)++; pfn++; continue; } @@ -1643,35 +1570,186 @@ static int move_freepages(struct zone *zone, VM_BUG_ON_PAGE(page_zone(page) != zone, page); order = buddy_order(page); - move_to_free_list(page, zone, order, migratetype); + + move_to_free_list(page, zone, order, old_mt, new_mt); + pfn += 1 << order; pages_moved += 1 << order; } + set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt); + return pages_moved; } -int move_freepages_block(struct zone *zone, struct page *page, - int migratetype, int *num_movable) +static bool prep_move_freepages_block(struct zone *zone, struct page *page, + unsigned long *start_pfn, + int *num_free, int *num_movable) { - unsigned long start_pfn, end_pfn, pfn; + unsigned long pfn, start, end; - if (num_movable) + pfn = page_to_pfn(page); + start = pageblock_start_pfn(pfn); + end = pageblock_end_pfn(pfn); + + /* + * The caller only has the lock for @zone, don't touch ranges + * that straddle into other zones. While we could move part of + * the range that's inside the zone, this call is usually + * accompanied by other operations such as migratetype updates + * which also should be locked. + */ + if (!zone_spans_pfn(zone, start)) + return false; + if (!zone_spans_pfn(zone, end - 1)) + return false; + + *start_pfn = start; + + if (num_free) { + *num_free = 0; *num_movable = 0; + for (pfn = start; pfn < end;) { + page = pfn_to_page(pfn); + if (PageBuddy(page)) { + int nr = 1 << buddy_order(page); - pfn = page_to_pfn(page); - start_pfn = pageblock_start_pfn(pfn); - end_pfn = pageblock_end_pfn(pfn) - 1; + *num_free += nr; + pfn += nr; + continue; + } + /* + * We assume that pages that could be isolated for + * migration are movable. But we don't actually try + * isolating, as that would be expensive. + */ + if (PageLRU(page) || __PageMovable(page)) + (*num_movable)++; + pfn++; + } + } - /* Do not cross zone boundaries */ - if (!zone_spans_pfn(zone, start_pfn)) - start_pfn = pfn; - if (!zone_spans_pfn(zone, end_pfn)) - return 0; + return true; +} + +static int move_freepages_block(struct zone *zone, struct page *page, + int old_mt, int new_mt) +{ + unsigned long start_pfn; + + if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL)) + return -1; + + return __move_freepages_block(zone, start_pfn, old_mt, new_mt); +} + +#ifdef CONFIG_MEMORY_ISOLATION +/* Look for a buddy that straddles start_pfn */ +static unsigned long find_large_buddy(unsigned long start_pfn) +{ + int order = 0; + struct page *page; + unsigned long pfn = start_pfn; + + while (!PageBuddy(page = pfn_to_page(pfn))) { + /* Nothing found */ + if (++order > MAX_PAGE_ORDER) + return start_pfn; + pfn &= ~0UL << order; + } + + /* + * Found a preceding buddy, but does it straddle? + */ + if (pfn + (1 << buddy_order(page)) > start_pfn) + return pfn; + + /* Nothing found */ + return start_pfn; +} + +/* Split a multi-block free page into its individual pageblocks */ +static void split_large_buddy(struct zone *zone, struct page *page, + unsigned long pfn, int order) +{ + unsigned long end_pfn = pfn + (1 << order); + + VM_WARN_ON_ONCE(order <= pageblock_order); + VM_WARN_ON_ONCE(pfn & (pageblock_nr_pages - 1)); + + /* Caller removed page from freelist, buddy info cleared! */ + VM_WARN_ON_ONCE(PageBuddy(page)); + + while (pfn != end_pfn) { + int mt = get_pfnblock_migratetype(page, pfn); + + __free_one_page(page, pfn, zone, pageblock_order, mt, FPI_NONE); + pfn += pageblock_nr_pages; + page = pfn_to_page(pfn); + } +} + +/** + * move_freepages_block_isolate - move free pages in block for page isolation + * @zone: the zone + * @page: the pageblock page + * @migratetype: migratetype to set on the pageblock + * + * This is similar to move_freepages_block(), but handles the special + * case encountered in page isolation, where the block of interest + * might be part of a larger buddy spanning multiple pageblocks. + * + * Unlike the regular page allocator path, which moves pages while + * stealing buddies off the freelist, page isolation is interested in + * arbitrary pfn ranges that may have overlapping buddies on both ends. + * + * This function handles that. Straddling buddies are split into + * individual pageblocks. Only the block of interest is moved. + * + * Returns %true if pages could be moved, %false otherwise. + */ +bool move_freepages_block_isolate(struct zone *zone, struct page *page, + int migratetype) +{ + unsigned long start_pfn, pfn; + + if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL)) + return false; + + /* No splits needed if buddies can't span multiple blocks */ + if (pageblock_order == MAX_PAGE_ORDER) + goto move; + + /* We're a tail block in a larger buddy */ + pfn = find_large_buddy(start_pfn); + if (pfn != start_pfn) { + struct page *buddy = pfn_to_page(pfn); + int order = buddy_order(buddy); - return move_freepages(zone, start_pfn, end_pfn, migratetype, - num_movable); + del_page_from_free_list(buddy, zone, order, + get_pfnblock_migratetype(buddy, pfn)); + set_pageblock_migratetype(page, migratetype); + split_large_buddy(zone, buddy, pfn, order); + return true; + } + + /* We're the starting block of a larger buddy */ + if (PageBuddy(page) && buddy_order(page) > pageblock_order) { + int order = buddy_order(page); + + del_page_from_free_list(page, zone, order, + get_pfnblock_migratetype(page, pfn)); + set_pageblock_migratetype(page, migratetype); + split_large_buddy(zone, page, pfn, order); + return true; + } +move: + __move_freepages_block(zone, start_pfn, + get_pfnblock_migratetype(page, start_pfn), + migratetype); + return true; } +#endif /* CONFIG_MEMORY_ISOLATION */ static void change_pageblock_range(struct page *pageblock_page, int start_order, int migratetype) @@ -1755,33 +1833,37 @@ static inline bool boost_watermark(struct zone *zone) } /* - * This function implements actual steal behaviour. If order is large enough, - * we can steal whole pageblock. If not, we first move freepages in this - * pageblock to our migratetype and determine how many already-allocated pages - * are there in the pageblock with a compatible migratetype. If at least half - * of pages are free or compatible, we can change migratetype of the pageblock - * itself, so pages freed in the future will be put on the correct free list. + * This function implements actual steal behaviour. If order is large enough, we + * can claim the whole pageblock for the requested migratetype. If not, we check + * the pageblock for constituent pages; if at least half of the pages are free + * or compatible, we can still claim the whole block, so pages freed in the + * future will be put on the correct free list. Otherwise, we isolate exactly + * the order we need from the fallback block and leave its migratetype alone. */ -static void steal_suitable_fallback(struct zone *zone, struct page *page, - unsigned int alloc_flags, int start_type, bool whole_block) +static struct page * +steal_suitable_fallback(struct zone *zone, struct page *page, + int current_order, int order, int start_type, + unsigned int alloc_flags, bool whole_block) { - unsigned int current_order = buddy_order(page); int free_pages, movable_pages, alike_pages; - int old_block_type; + unsigned long start_pfn; + int block_type; - old_block_type = get_pageblock_migratetype(page); + block_type = get_pageblock_migratetype(page); /* * This can happen due to races and we want to prevent broken * highatomic accounting. */ - if (is_migrate_highatomic(old_block_type)) + if (is_migrate_highatomic(block_type)) goto single_page; /* Take ownership for orders >= pageblock_order */ if (current_order >= pageblock_order) { + del_page_from_free_list(page, zone, current_order, block_type); change_pageblock_range(page, current_order, start_type); - goto single_page; + expand(zone, page, order, current_order, start_type); + return page; } /* @@ -1796,10 +1878,9 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, if (!whole_block) goto single_page; - free_pages = move_freepages_block(zone, page, start_type, - &movable_pages); /* moving whole block can fail due to zone boundary conditions */ - if (!free_pages) + if (!prep_move_freepages_block(zone, page, &start_pfn, &free_pages, + &movable_pages)) goto single_page; /* @@ -1817,7 +1898,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, * vice versa, be conservative since we can't distinguish the * exact migratetype of non-movable pages. */ - if (old_block_type == MIGRATE_MOVABLE) + if (block_type == MIGRATE_MOVABLE) alike_pages = pageblock_nr_pages - (free_pages + movable_pages); else @@ -1828,13 +1909,15 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, * compatible migratability as our allocation, claim the whole block. */ if (free_pages + alike_pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) - set_pageblock_migratetype(page, start_type); - - return; + page_group_by_mobility_disabled) { + __move_freepages_block(zone, start_pfn, block_type, start_type); + return __rmqueue_smallest(zone, order, start_type); + } single_page: - move_to_free_list(page, zone, current_order, start_type); + del_page_from_free_list(page, zone, current_order, block_type); + expand(zone, page, order, current_order, block_type); + return page; } /* @@ -1901,11 +1984,10 @@ static void reserve_highatomic_pageblock(struct page *page, struct zone *zone) /* Yoink! */ mt = get_pageblock_migratetype(page); /* Only reserve normal pageblocks (i.e., they can merge with others) */ - if (migratetype_is_mergeable(mt)) { - zone->nr_reserved_highatomic += pageblock_nr_pages; - set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC); - move_freepages_block(zone, page, MIGRATE_HIGHATOMIC, NULL); - } + if (migratetype_is_mergeable(mt)) + if (move_freepages_block(zone, page, mt, + MIGRATE_HIGHATOMIC) != -1) + zone->nr_reserved_highatomic += pageblock_nr_pages; out_unlock: spin_unlock_irqrestore(&zone->lock, flags); @@ -1929,7 +2011,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, struct zone *zone; struct page *page; int order; - bool ret; + int ret; for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx, ac->nodemask) { @@ -1944,11 +2026,13 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < NR_PAGE_ORDERS; order++) { struct free_area *area = &(zone->free_area[order]); + int mt; page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC); if (!page) continue; + mt = get_pageblock_migratetype(page); /* * In page freeing path, migratetype change is racy so * we can counter several free pages in a pageblock @@ -1956,7 +2040,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, * from highatomic to ac->migratetype. So we should * adjust the count once. */ - if (is_migrate_highatomic_page(page)) { + if (is_migrate_highatomic(mt)) { /* * It should never happen but changes to * locking could inadvertently allow a per-cpu @@ -1978,10 +2062,14 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, * of pageblocks that cannot be completely freed * may increase. */ - set_pageblock_migratetype(page, ac->migratetype); - ret = move_freepages_block(zone, page, ac->migratetype, - NULL); - if (ret) { + ret = move_freepages_block(zone, page, mt, + ac->migratetype); + /* + * Reserving this block already succeeded, so this should + * not fail on zone boundaries. + */ + WARN_ON_ONCE(ret == -1); + if (ret > 0) { spin_unlock_irqrestore(&zone->lock, flags); return ret; } @@ -2002,7 +2090,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, * deviation from the rest of this file, to make the for loop * condition simpler. */ -static __always_inline bool +static __always_inline struct page * __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, unsigned int alloc_flags) { @@ -2049,7 +2137,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, goto do_steal; } - return false; + return NULL; find_smallest: for (current_order = order; current_order < NR_PAGE_ORDERS; current_order++) { @@ -2069,16 +2157,53 @@ find_smallest: do_steal: page = get_page_from_free_area(area, fallback_mt); - steal_suitable_fallback(zone, page, alloc_flags, start_migratetype, - can_steal); + /* take off list, maybe claim block, expand remainder */ + page = steal_suitable_fallback(zone, page, current_order, order, + start_migratetype, alloc_flags, can_steal); trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, fallback_mt); - return true; - + return page; } +#ifdef CONFIG_CMA +/* + * GFP_MOVABLE allocation could drain UNMOVABLE & RECLAIMABLE page blocks via + * the help of CMA which makes GFP_KERNEL failed. Checking if zone_watermark_ok + * again without ALLOC_CMA to see if to use CMA first. + */ +static bool use_cma_first(struct zone *zone, unsigned int order, unsigned int alloc_flags) +{ + unsigned long watermark; + bool cma_first = false; + + watermark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); + /* check if GFP_MOVABLE pass previous zone_watermark_ok via the help of CMA */ + if (zone_watermark_ok(zone, order, watermark, 0, alloc_flags & (~ALLOC_CMA))) { + /* + * Balance movable allocations between regular and CMA areas by + * allocating from CMA when over half of the zone's free memory + * is in the CMA area. + */ + cma_first = (zone_page_state(zone, NR_FREE_CMA_PAGES) > + zone_page_state(zone, NR_FREE_PAGES) / 2); + } else { + /* + * watermark failed means UNMOVABLE & RECLAIMBLE is not enough + * now, we should use cma first to keep them stay around the + * corresponding watermark + */ + cma_first = true; + } + return cma_first; +} +#else +static bool use_cma_first(struct zone *zone, unsigned int order, unsigned int alloc_flags) +{ + return false; +} +#endif /* * Do the hard work of removing an element from the buddy allocator. * Call me with the zone->lock already held. @@ -2092,26 +2217,25 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, if (IS_ENABLED(CONFIG_CMA)) { /* * Balance movable allocations between regular and CMA areas by - * allocating from CMA when over half of the zone's free memory - * is in the CMA area. + * allocating from CMA base on judging zone_watermark_ok again + * to see if the latest check got pass via the help of CMA */ if (alloc_flags & ALLOC_CMA && - zone_page_state(zone, NR_FREE_CMA_PAGES) > - zone_page_state(zone, NR_FREE_PAGES) / 2) { + use_cma_first(zone, order, alloc_flags)) { page = __rmqueue_cma_fallback(zone, order); if (page) return page; } } -retry: + page = __rmqueue_smallest(zone, order, migratetype); if (unlikely(!page)) { if (alloc_flags & ALLOC_CMA) page = __rmqueue_cma_fallback(zone, order); - if (!page && __rmqueue_fallback(zone, order, migratetype, - alloc_flags)) - goto retry; + if (!page) + page = __rmqueue_fallback(zone, order, migratetype, + alloc_flags); } return page; } @@ -2146,12 +2270,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * pages are ordered properly. */ list_add_tail(&page->pcp_list, list); - if (is_migrate_cma(get_pcppage_migratetype(page))) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, - -(1 << order)); } - - __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock_irqrestore(&zone->lock, flags); return i; @@ -2216,12 +2335,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) */ static void drain_pages_zone(unsigned int cpu, struct zone *zone) { - struct per_cpu_pages *pcp; + struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + int count = READ_ONCE(pcp->count); + + while (count) { + int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX); + count -= to_drain; - pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - if (pcp->count) { spin_lock(&pcp->lock); - free_pcppages_bulk(zone, pcp->count, pcp, 0); + free_pcppages_bulk(zone, to_drain, pcp, 0); spin_unlock(&pcp->lock); } } @@ -2339,19 +2461,6 @@ void drain_all_pages(struct zone *zone) __drain_all_pages(zone, false); } -static bool free_unref_page_prepare(struct page *page, unsigned long pfn, - unsigned int order) -{ - int migratetype; - - if (!free_pages_prepare(page, order)) - return false; - - migratetype = get_pfnblock_migratetype(page, pfn); - set_pcppage_migratetype(page, migratetype); - return true; -} - static int nr_pcp_free(struct per_cpu_pages *pcp, int batch, int high, bool free_high) { int min_nr_free, max_nr_free; @@ -2482,9 +2591,14 @@ void free_unref_page(struct page *page, unsigned int order) struct per_cpu_pages *pcp; struct zone *zone; unsigned long pfn = page_to_pfn(page); - int migratetype, pcpmigratetype; + int migratetype; - if (!free_unref_page_prepare(page, pfn, order)) + if (!pcp_allowed_order(order)) { + __free_pages_ok(page, order, FPI_NONE); + return; + } + + if (!free_pages_prepare(page, order)) return; /* @@ -2494,23 +2608,23 @@ void free_unref_page(struct page *page, unsigned int order) * get those areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ - migratetype = pcpmigratetype = get_pcppage_migratetype(page); + migratetype = get_pfnblock_migratetype(page, pfn); if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE); + free_one_page(page_zone(page), page, pfn, order, FPI_NONE); return; } - pcpmigratetype = MIGRATE_MOVABLE; + migratetype = MIGRATE_MOVABLE; } zone = page_zone(page); pcp_trylock_prepare(UP_flags); pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (pcp) { - free_unref_page_commit(zone, pcp, page, pcpmigratetype, order); + free_unref_page_commit(zone, pcp, page, migratetype, order); pcp_spin_unlock(pcp); } else { - free_one_page(zone, page, pfn, order, migratetype, FPI_NONE); + free_one_page(zone, page, pfn, order, FPI_NONE); } pcp_trylock_finish(UP_flags); } @@ -2523,7 +2637,7 @@ void free_unref_folios(struct folio_batch *folios) unsigned long __maybe_unused UP_flags; struct per_cpu_pages *pcp = NULL; struct zone *locked_zone = NULL; - int i, j, migratetype; + int i, j; /* Prepare folios for freeing */ for (i = 0, j = 0; i < folios->nr; i++) { @@ -2533,18 +2647,15 @@ void free_unref_folios(struct folio_batch *folios) if (order > 0 && folio_test_large_rmappable(folio)) folio_undo_large_rmappable(folio); - if (!free_unref_page_prepare(&folio->page, pfn, order)) + if (!free_pages_prepare(&folio->page, order)) continue; - /* - * Free isolated folios and orders not handled on the PCP - * directly to the allocator, see comment in free_unref_page. + * Free orders not handled on the PCP directly to the + * allocator. */ - migratetype = get_pcppage_migratetype(&folio->page); - if (!pcp_allowed_order(order) || - is_migrate_isolate(migratetype)) { - free_one_page(folio_zone(folio), &folio->page, pfn, - order, migratetype, FPI_NONE); + if (!pcp_allowed_order(order)) { + free_one_page(folio_zone(folio), &folio->page, + pfn, order, FPI_NONE); continue; } folio->private = (void *)(unsigned long)order; @@ -2557,16 +2668,31 @@ void free_unref_folios(struct folio_batch *folios) for (i = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; struct zone *zone = folio_zone(folio); + unsigned long pfn = folio_pfn(folio); unsigned int order = (unsigned long)folio->private; + int migratetype; folio->private = NULL; - migratetype = get_pcppage_migratetype(&folio->page); + migratetype = get_pfnblock_migratetype(&folio->page, pfn); /* Different zone requires a different pcp lock */ - if (zone != locked_zone) { + if (zone != locked_zone || + is_migrate_isolate(migratetype)) { if (pcp) { pcp_spin_unlock(pcp); pcp_trylock_finish(UP_flags); + locked_zone = NULL; + pcp = NULL; + } + + /* + * Free isolated pages directly to the + * allocator, see comment in free_unref_page. + */ + if (is_migrate_isolate(migratetype)) { + free_one_page(zone, &folio->page, pfn, + order, FPI_NONE); + continue; } /* @@ -2577,10 +2703,8 @@ void free_unref_folios(struct folio_batch *folios) pcp = pcp_spin_trylock(zone->per_cpu_pageset); if (unlikely(!pcp)) { pcp_trylock_finish(UP_flags); - free_one_page(zone, &folio->page, - folio_pfn(folio), order, - migratetype, FPI_NONE); - locked_zone = NULL; + free_one_page(zone, &folio->page, pfn, + order, FPI_NONE); continue; } locked_zone = zone; @@ -2623,6 +2747,7 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); split_page_owner(page, order, 0); + pgalloc_tag_split(page, 1 << order); split_page_memcg(page, order, 0); } EXPORT_SYMBOL_GPL(split_page); @@ -2643,11 +2768,9 @@ int __isolate_free_page(struct page *page, unsigned int order) watermark = zone->_watermark[WMARK_MIN] + (1UL << order); if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA)) return 0; - - __mod_zone_freepage_state(zone, -(1UL << order), mt); } - del_page_from_free_list(page, zone, order); + del_page_from_free_list(page, zone, order, mt); /* * Set the pageblock if the isolated page is at least half of a @@ -2662,8 +2785,8 @@ int __isolate_free_page(struct page *page, unsigned int order) * with others) */ if (migratetype_is_mergeable(mt)) - set_pageblock_migratetype(page, - MIGRATE_MOVABLE); + move_freepages_block(zone, page, mt, + MIGRATE_MOVABLE); } } @@ -2747,8 +2870,6 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, return NULL; } } - __mod_zone_freepage_state(zone, -(1 << order), - get_pcppage_migratetype(page)); spin_unlock_irqrestore(&zone->lock, flags); } while (check_new_pages(page, order)); @@ -4384,7 +4505,7 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order, * * Returns the number of pages on the list or array. */ -unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, +unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, struct list_head *page_list, struct page **page_array) @@ -4520,7 +4641,7 @@ failed_irq: pcp_trylock_finish(UP_flags); failed: - page = __alloc_pages(gfp, 0, preferred_nid, nodemask); + page = __alloc_pages_noprof(gfp, 0, preferred_nid, nodemask); if (page) { if (page_list) list_add(&page->lru, page_list); @@ -4531,13 +4652,13 @@ failed: goto out; } -EXPORT_SYMBOL_GPL(__alloc_pages_bulk); +EXPORT_SYMBOL_GPL(alloc_pages_bulk_noprof); /* * This is the 'heart' of the zoned buddy allocator. */ -struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, - nodemask_t *nodemask) +struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, + int preferred_nid, nodemask_t *nodemask) { struct page *page; unsigned int alloc_flags = ALLOC_WMARK_LOW; @@ -4599,38 +4720,38 @@ out: return page; } -EXPORT_SYMBOL(__alloc_pages); +EXPORT_SYMBOL(__alloc_pages_noprof); -struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, +struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask) { - struct page *page = __alloc_pages(gfp | __GFP_COMP, order, + struct page *page = __alloc_pages_noprof(gfp | __GFP_COMP, order, preferred_nid, nodemask); return page_rmappable_folio(page); } -EXPORT_SYMBOL(__folio_alloc); +EXPORT_SYMBOL(__folio_alloc_noprof); /* * Common helper functions. Never use with __GFP_HIGHMEM because the returned * address cannot represent highmem pages. Use alloc_pages and then kmap if * you need to access high mem. */ -unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order) +unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order) { struct page *page; - page = alloc_pages(gfp_mask & ~__GFP_HIGHMEM, order); + page = alloc_pages_noprof(gfp_mask & ~__GFP_HIGHMEM, order); if (!page) return 0; return (unsigned long) page_address(page); } -EXPORT_SYMBOL(__get_free_pages); +EXPORT_SYMBOL(get_free_pages_noprof); -unsigned long get_zeroed_page(gfp_t gfp_mask) +unsigned long get_zeroed_page_noprof(gfp_t gfp_mask) { - return __get_free_page(gfp_mask | __GFP_ZERO); + return get_free_pages_noprof(gfp_mask | __GFP_ZERO, 0); } -EXPORT_SYMBOL(get_zeroed_page); +EXPORT_SYMBOL(get_zeroed_page_noprof); /** * __free_pages - Free pages allocated with alloc_pages(). @@ -4656,12 +4777,15 @@ void __free_pages(struct page *page, unsigned int order) { /* get PageHead before we drop reference */ int head = PageHead(page); + struct alloc_tag *tag = pgalloc_tag_get(page); if (put_page_testzero(page)) - free_the_page(page, order); - else if (!head) + free_unref_page(page, order); + else if (!head) { + pgalloc_tag_sub_pages(tag, (1 << order) - 1); while (order-- > 0) - free_the_page(page + (1 << order), order); + free_unref_page(page + (1 << order), order); + } } EXPORT_SYMBOL(__free_pages); @@ -4722,7 +4846,7 @@ void __page_frag_cache_drain(struct page *page, unsigned int count) VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); if (page_ref_sub_and_test(page, count)) - free_the_page(page, compound_order(page)); + free_unref_page(page, compound_order(page)); } EXPORT_SYMBOL(__page_frag_cache_drain); @@ -4763,7 +4887,7 @@ refill: goto refill; if (unlikely(nc->pfmemalloc)) { - free_the_page(page, compound_order(page)); + free_unref_page(page, compound_order(page)); goto refill; } @@ -4807,7 +4931,7 @@ void page_frag_free(void *addr) struct page *page = virt_to_head_page(addr); if (unlikely(put_page_testzero(page))) - free_the_page(page, compound_order(page)); + free_unref_page(page, compound_order(page)); } EXPORT_SYMBOL(page_frag_free); @@ -4820,6 +4944,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order, struct page *last = page + nr; split_page_owner(page, order, 0); + pgalloc_tag_split(page, 1 << order); split_page_memcg(page, order, 0); while (page < --last) set_page_refcounted(last); @@ -4846,7 +4971,7 @@ static void *make_alloc_exact(unsigned long addr, unsigned int order, * * Return: pointer to the allocated area or %NULL in case of error. */ -void *alloc_pages_exact(size_t size, gfp_t gfp_mask) +void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) { unsigned int order = get_order(size); unsigned long addr; @@ -4854,10 +4979,10 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); - addr = __get_free_pages(gfp_mask, order); + addr = get_free_pages_noprof(gfp_mask, order); return make_alloc_exact(addr, order, size); } -EXPORT_SYMBOL(alloc_pages_exact); +EXPORT_SYMBOL(alloc_pages_exact_noprof); /** * alloc_pages_exact_nid - allocate an exact number of physically-contiguous @@ -4871,7 +4996,7 @@ EXPORT_SYMBOL(alloc_pages_exact); * * Return: pointer to the allocated area or %NULL in case of error. */ -void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) +void * __meminit alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) { unsigned int order = get_order(size); struct page *p; @@ -4879,7 +5004,7 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM))) gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM); - p = alloc_pages_node(nid, gfp_mask, order); + p = alloc_pages_node_noprof(nid, gfp_mask, order); if (!p) return NULL; return make_alloc_exact((unsigned long)page_address(p), order, size); @@ -5180,37 +5305,13 @@ static void setup_min_slab_ratio(void); static void build_zonelists(pg_data_t *pgdat) { - int node, local_node; struct zoneref *zonerefs; int nr_zones; - local_node = pgdat->node_id; - zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs; nr_zones = build_zonerefs_node(pgdat, zonerefs); zonerefs += nr_zones; - /* - * Now we build the zonelist so that it contains the zones - * of all the other nodes. - * We don't want to pressure a particular node, so when - * building the zones for node N, we make sure that the - * zones coming right after the local ones are those from - * node N+1 (modulo N) - */ - for (node = local_node + 1; node < MAX_NUMNODES; node++) { - if (!node_online(node)) - continue; - nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs); - zonerefs += nr_zones; - } - for (node = 0; node < local_node; node++) { - if (!node_online(node)) - continue; - nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs); - zonerefs += nr_zones; - } - zonerefs->zone = NULL; zonerefs->zone_idx = 0; } @@ -5827,10 +5928,11 @@ static void setup_per_zone_lowmem_reserve(void) for (j = i + 1; j < MAX_NR_ZONES; j++) { struct zone *upper_zone = &pgdat->node_zones[j]; + bool empty = !zone_managed_pages(upper_zone); managed_pages += zone_managed_pages(upper_zone); - if (clear) + if (clear || empty) zone->lowmem_reserve[j] = 0; else zone->lowmem_reserve[j] = managed_pages / ratio; @@ -6211,7 +6313,6 @@ static struct ctl_table page_alloc_sysctl_table[] = { .extra2 = SYSCTL_ONE_HUNDRED, }, #endif - {} }; void __init page_alloc_sysctl_init(void) @@ -6251,6 +6352,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc, struct migration_target_control mtc = { .nid = zone_to_nid(cc->zone), .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + .reason = MR_CONTIG_RANGE, }; struct page *page; unsigned long total_mapped = 0; @@ -6283,8 +6385,12 @@ int __alloc_contig_migrate_range(struct compact_control *cc, if (trace_mm_alloc_contig_migrate_range_info_enabled()) { total_reclaimed += nr_reclaimed; - list_for_each_entry(page, &cc->migratepages, lru) - total_mapped += page_mapcount(page); + list_for_each_entry(page, &cc->migratepages, lru) { + struct folio *folio = page_folio(page); + + total_mapped += folio_mapped(folio) * + folio_nr_pages(folio); + } } ret = migrate_pages(&cc->migratepages, alloc_migration_target, @@ -6336,11 +6442,10 @@ int __alloc_contig_migrate_range(struct compact_control *cc, * pages which PFN is in [start, end) are allocated for the caller and * need to be freed with free_contig_range(). */ -int alloc_contig_range(unsigned long start, unsigned long end, +int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask) { unsigned long outer_start, outer_end; - int order; int ret = 0; struct compact_control cc = { @@ -6413,29 +6518,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, * We don't have to hold zone->lock here because the pages are * isolated thus they won't get removed from buddy. */ - - order = 0; - outer_start = start; - while (!PageBuddy(pfn_to_page(outer_start))) { - if (++order > MAX_PAGE_ORDER) { - outer_start = start; - break; - } - outer_start &= ~0UL << order; - } - - if (outer_start != start) { - order = buddy_order(pfn_to_page(outer_start)); - - /* - * outer_start page could be small order buddy page and - * it doesn't include start page. Adjust outer_start - * in this case to report failed page properly - * on tracepoint in test_pages_isolated() - */ - if (outer_start + (1UL << order) <= start) - outer_start = start; - } + outer_start = find_large_buddy(start); /* Make sure the range is really isolated. */ if (test_pages_isolated(outer_start, end, 0)) { @@ -6460,15 +6543,15 @@ done: undo_isolate_page_range(start, end, migratetype); return ret; } -EXPORT_SYMBOL(alloc_contig_range); +EXPORT_SYMBOL(alloc_contig_range_noprof); static int __alloc_contig_pages(unsigned long start_pfn, unsigned long nr_pages, gfp_t gfp_mask) { unsigned long end_pfn = start_pfn + nr_pages; - return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - gfp_mask); + return alloc_contig_range_noprof(start_pfn, end_pfn, MIGRATE_MOVABLE, + gfp_mask); } static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, @@ -6523,8 +6606,8 @@ static bool zone_spans_last_pfn(const struct zone *zone, * * Return: pointer to contiguous pages on success, or NULL if not successful. */ -struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, - int nid, nodemask_t *nodemask) +struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) { unsigned long ret, pfn, flags; struct zonelist *zonelist; @@ -6655,8 +6738,9 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) BUG_ON(page_count(page)); BUG_ON(!PageBuddy(page)); + VM_WARN_ON(get_pageblock_migratetype(page) != MIGRATE_ISOLATE); order = buddy_order(page); - del_page_from_free_list(page, zone, order); + del_page_from_free_list(page, zone, order, MIGRATE_ISOLATE); pfn += (1 << order); } spin_unlock_irqrestore(&zone->lock, flags); @@ -6666,16 +6750,16 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) /* * This function returns a stable result only if called under zone lock. */ -bool is_free_buddy_page(struct page *page) +bool is_free_buddy_page(const struct page *page) { unsigned long pfn = page_to_pfn(page); unsigned int order; for (order = 0; order < NR_PAGE_ORDERS; order++) { - struct page *page_head = page - (pfn & ((1 << order) - 1)); + const struct page *head = page - (pfn & ((1 << order) - 1)); - if (PageBuddy(page_head) && - buddy_order_unsafe(page_head) >= order) + if (PageBuddy(head) && + buddy_order_unsafe(head) >= order) break; } @@ -6684,6 +6768,14 @@ bool is_free_buddy_page(struct page *page) EXPORT_SYMBOL(is_free_buddy_page); #ifdef CONFIG_MEMORY_FAILURE +static inline void add_to_free_list(struct page *page, struct zone *zone, + unsigned int order, int migratetype, + bool tail) +{ + __add_to_free_list(page, zone, order, migratetype, tail); + account_freepages(zone, 1 << order, migratetype); +} + /* * Break down a higher-order page in sub-pages, and keep our target out of * buddy allocator. @@ -6706,10 +6798,10 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page, current_buddy = page + size; } - if (set_page_guard(zone, current_buddy, high, migratetype)) + if (set_page_guard(zone, current_buddy, high)) continue; - add_to_free_list(current_buddy, zone, high, migratetype); + add_to_free_list(current_buddy, zone, high, migratetype, false); set_buddy_order(current_buddy, high); } } @@ -6735,12 +6827,11 @@ bool take_page_off_buddy(struct page *page) int migratetype = get_pfnblock_migratetype(page_head, pfn_head); - del_page_from_free_list(page_head, zone, page_order); + del_page_from_free_list(page_head, zone, page_order, + migratetype); break_down_buddy_pages(zone, page_head, page, 0, page_order, migratetype); SetPageHWPoisonTakenOff(page); - if (!is_migrate_isolate(migratetype)) - __mod_zone_freepage_state(zone, -1, migratetype); ret = true; break; } @@ -6757,13 +6848,14 @@ bool take_page_off_buddy(struct page *page) bool put_page_back_buddy(struct page *page) { struct zone *zone = page_zone(page); - unsigned long pfn = page_to_pfn(page); unsigned long flags; - int migratetype = get_pfnblock_migratetype(page, pfn); bool ret = false; spin_lock_irqsave(&zone->lock, flags); if (put_page_testzero(page)) { + unsigned long pfn = page_to_pfn(page); + int migratetype = get_pfnblock_migratetype(page, pfn); + ClearPageHWPoisonTakenOff(page); __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE); if (TestClearPageHWPoison(page)) { @@ -6847,7 +6939,7 @@ static bool try_to_accept_memory_one(struct zone *zone) list_del(&page->lru); last = list_empty(&zone->unaccepted_pages); - __mod_zone_freepage_state(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); + account_freepages(zone, -MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, -MAX_ORDER_NR_PAGES); spin_unlock_irqrestore(&zone->lock, flags); @@ -6899,7 +6991,7 @@ static bool __free_unaccepted(struct page *page) spin_lock_irqsave(&zone->lock, flags); first = list_empty(&zone->unaccepted_pages); list_add_tail(&page->lru, &zone->unaccepted_pages); - __mod_zone_freepage_state(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); + account_freepages(zone, MAX_ORDER_NR_PAGES, MIGRATE_MOVABLE); __mod_zone_page_state(zone, NR_UNACCEPTED, MAX_ORDER_NR_PAGES); spin_unlock_irqrestore(&zone->lock, flags); diff --git a/mm/page_ext.c b/mm/page_ext.c index 4548fcc66d74d0..95dd8ffeaf811a 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -10,6 +10,7 @@ #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate.h> +#include <linux/pgalloc_tag.h> /* * struct page extension @@ -82,6 +83,9 @@ static struct page_ext_operations *page_ext_ops[] __initdata = { #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + &page_alloc_tagging_ops, +#endif #ifdef CONFIG_PAGE_TABLE_CHECK &page_table_check_ops, #endif @@ -91,7 +95,16 @@ unsigned long page_ext_size; static unsigned long total_usage; +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG +/* + * To ensure correct allocation tagging for pages, page_ext should be available + * before the first page allocation. Otherwise early task stacks will be + * allocated before page_ext initialization and missing tags will be flagged. + */ +bool early_page_ext __meminitdata = true; +#else bool early_page_ext __meminitdata; +#endif static int __init setup_early_page_ext(char *str) { early_page_ext = true; @@ -501,7 +514,7 @@ void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) * Context: Any context. Caller may not sleep until they have called * page_ext_put(). */ -struct page_ext *page_ext_get(struct page *page) +struct page_ext *page_ext_get(const struct page *page) { struct page_ext *page_ext; diff --git a/mm/page_io.c b/mm/page_io.c index ae2b49055e4357..46c603dddf043d 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -189,7 +189,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) * Arch code may have to preserve more data than just the page * contents, e.g. memory tags. */ - ret = arch_prepare_to_swap(&folio->page); + ret = arch_prepare_to_swap(folio); if (ret) { folio_mark_dirty(folio); folio_unlock(folio); @@ -217,6 +217,7 @@ static inline void count_swpout_vm_event(struct folio *folio) count_memcg_folio_events(folio, THP_SWPOUT, 1); count_vm_event(THP_SWPOUT); } + count_mthp_stat(folio_order(folio), MTHP_STAT_ANON_SWPOUT); #endif count_vm_events(PSWPOUT, folio_nr_pages(folio)); } diff --git a/mm/page_isolation.c b/mm/page_isolation.c index a5c8fa4c2a75c3..042937d5abe4b8 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -178,15 +178,11 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end, migratetype, isol_flags); if (!unmovable) { - unsigned long nr_pages; - int mt = get_pageblock_migratetype(page); - - set_pageblock_migratetype(page, MIGRATE_ISOLATE); + if (!move_freepages_block_isolate(zone, page, MIGRATE_ISOLATE)) { + spin_unlock_irqrestore(&zone->lock, flags); + return -EBUSY; + } zone->nr_isolate_pageblock++; - nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE, - NULL); - - __mod_zone_freepage_state(zone, -nr_pages, mt); spin_unlock_irqrestore(&zone->lock, flags); return 0; } @@ -206,7 +202,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ static void unset_migratetype_isolate(struct page *page, int migratetype) { struct zone *zone; - unsigned long flags, nr_pages; + unsigned long flags; bool isolated_page = false; unsigned int order; struct page *buddy; @@ -252,12 +248,15 @@ static void unset_migratetype_isolate(struct page *page, int migratetype) * allocation. */ if (!isolated_page) { - nr_pages = move_freepages_block(zone, page, migratetype, NULL); - __mod_zone_freepage_state(zone, nr_pages, migratetype); - } - set_pageblock_migratetype(page, migratetype); - if (isolated_page) + /* + * Isolating this block already succeeded, so this + * should not fail on zone boundaries. + */ + WARN_ON_ONCE(!move_freepages_block_isolate(zone, page, migratetype)); + } else { + set_pageblock_migratetype(page, migratetype); __putback_isolated_page(page, order, migratetype); + } zone->nr_isolate_pageblock--; out: spin_unlock_irqrestore(&zone->lock, flags); @@ -367,26 +366,29 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, VM_BUG_ON(!page); pfn = page_to_pfn(page); - /* - * start_pfn is MAX_ORDER_NR_PAGES aligned, if there is any - * free pages in [start_pfn, boundary_pfn), its head page will - * always be in the range. - */ + if (PageBuddy(page)) { int order = buddy_order(page); - if (pfn + (1UL << order) > boundary_pfn) { - /* free page changed before split, check it again */ - if (split_free_page(page, order, boundary_pfn - pfn)) - continue; - } + /* move_freepages_block_isolate() handled this */ + VM_WARN_ON_ONCE(pfn + (1 << order) > boundary_pfn); pfn += 1UL << order; continue; } + /* - * migrate compound pages then let the free page handling code - * above do the rest. If migration is not possible, just fail. + * If a compound page is straddling our block, attempt + * to migrate it out of the way. + * + * We don't have to worry about this creating a large + * free page that straddles into our block: gigantic + * pages are freed as order-0 chunks, and LRU pages + * (currently) do not exceed pageblock_order. + * + * The block of interest has already been marked + * MIGRATE_ISOLATE above, so when migration is done it + * will free its pages onto the correct freelists. */ if (PageCompound(page)) { struct page *head = compound_head(page); @@ -397,16 +399,10 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, pfn = head_pfn + nr_pages; continue; } + #if defined CONFIG_COMPACTION || defined CONFIG_CMA - /* - * hugetlb, lru compound (THP), and movable compound pages - * can be migrated. Otherwise, fail the isolation. - */ - if (PageHuge(page) || PageLRU(page) || __PageMovable(page)) { - int order; - unsigned long outer_pfn; + if (PageHuge(page)) { int page_mt = get_pageblock_migratetype(page); - bool isolate_page = !is_migrate_isolate_page(page); struct compact_control cc = { .nr_migratepages = 0, .order = -1, @@ -419,56 +415,25 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, }; INIT_LIST_HEAD(&cc.migratepages); - /* - * XXX: mark the page as MIGRATE_ISOLATE so that - * no one else can grab the freed page after migration. - * Ideally, the page should be freed as two separate - * pages to be added into separate migratetype free - * lists. - */ - if (isolate_page) { - ret = set_migratetype_isolate(page, page_mt, - flags, head_pfn, head_pfn + nr_pages); - if (ret) - goto failed; - } - ret = __alloc_contig_migrate_range(&cc, head_pfn, head_pfn + nr_pages, page_mt); - - /* - * restore the page's migratetype so that it can - * be split into separate migratetype free lists - * later. - */ - if (isolate_page) - unset_migratetype_isolate(page, page_mt); - if (ret) goto failed; - /* - * reset pfn to the head of the free page, so - * that the free page handling code above can split - * the free page to the right migratetype list. - * - * head_pfn is not used here as a hugetlb page order - * can be bigger than MAX_PAGE_ORDER, but after it is - * freed, the free page order is not. Use pfn within - * the range to find the head of the free page. - */ - order = 0; - outer_pfn = pfn; - while (!PageBuddy(pfn_to_page(outer_pfn))) { - /* stop if we cannot find the free page */ - if (++order > MAX_PAGE_ORDER) - goto failed; - outer_pfn &= ~0UL << order; - } - pfn = outer_pfn; + pfn = head_pfn + nr_pages; continue; - } else + } + + /* + * These pages are movable too, but they're + * not expected to exceed pageblock_order. + * + * Let us know when they do, so we can add + * proper free and split handling for them. + */ + VM_WARN_ON_ONCE_PAGE(PageLRU(page), page); + VM_WARN_ON_ONCE_PAGE(__PageMovable(page), page); #endif - goto failed; + goto failed; } pfn++; diff --git a/mm/page_owner.c b/mm/page_owner.c index 742f432e5bf06f..6e65dc88c1b811 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -328,7 +328,7 @@ noinline void __set_page_owner(struct page *page, unsigned short order, if (unlikely(!page_ext)) return; __update_page_owner_handle(page_ext, handle, order, gfp_mask, -1, - current->pid, current->tgid, ts_nsec, + ts_nsec, current->pid, current->tgid, current->comm); page_ext_put(page_ext); inc_stack_record_count(handle, gfp_mask, 1 << order); @@ -515,7 +515,7 @@ static inline int print_page_owner_memcg(char *kbuf, size_t count, int ret, if (!memcg_data) goto out_unlock; - if (memcg_data & MEMCG_DATA_OBJCGS) + if (memcg_data & MEMCG_DATA_OBJEXTS) ret += scnprintf(kbuf + ret, count - ret, "Slab cache page\n"); diff --git a/mm/page_table_check.c b/mm/page_table_check.c index af69c3c8f7c2d5..4169576bed7298 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -7,6 +7,8 @@ #include <linux/kstrtox.h> #include <linux/mm.h> #include <linux/page_table_check.h> +#include <linux/swap.h> +#include <linux/swapops.h> #undef pr_fmt #define pr_fmt(fmt) "page_table_check: " fmt @@ -182,6 +184,22 @@ void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) } EXPORT_SYMBOL(__page_table_check_pud_clear); +/* Whether the swap entry cached writable information */ +static inline bool swap_cached_writable(swp_entry_t entry) +{ + return is_writable_device_exclusive_entry(entry) || + is_writable_device_private_entry(entry) || + is_writable_migration_entry(entry); +} + +static inline void page_table_check_pte_flags(pte_t pte) +{ + if (pte_present(pte) && pte_uffd_wp(pte)) + WARN_ON_ONCE(pte_write(pte)); + else if (is_swap_pte(pte) && pte_swp_uffd_wp(pte)) + WARN_ON_ONCE(swap_cached_writable(pte_to_swp_entry(pte))); +} + void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { @@ -190,6 +208,8 @@ void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, if (&init_mm == mm) return; + page_table_check_pte_flags(pte); + for (i = 0; i < nr; i++) __page_table_check_pte_clear(mm, ptep_get(ptep + i)); if (pte_user_accessible_page(pte)) @@ -197,11 +217,21 @@ void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, } EXPORT_SYMBOL(__page_table_check_ptes_set); +static inline void page_table_check_pmd_flags(pmd_t pmd) +{ + if (pmd_present(pmd) && pmd_uffd_wp(pmd)) + WARN_ON_ONCE(pmd_write(pmd)); + else if (is_swap_pmd(pmd) && pmd_swp_uffd_wp(pmd)) + WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd))); +} + void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { if (&init_mm == mm) return; + page_table_check_pmd_flags(pmd); + __page_table_check_pmd_clear(mm, *pmdp); if (pmd_user_accessible_page(pmd)) { page_table_check_set(pmd_pfn(pmd), PMD_SIZE >> PAGE_SHIFT, diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 74d2de15fb5e09..ae5cc42aa2087a 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -314,17 +314,21 @@ next_pte: return false; } +#ifdef CONFIG_MEMORY_FAILURE /** * page_mapped_in_vma - check whether a page is really mapped in a VMA * @page: the page to test * @vma: the VMA to test * - * Returns 1 if the page is mapped into the page tables of the VMA, 0 - * if the page is not mapped into the page tables of this VMA. Only - * valid for normal file or anonymous VMAs. + * Return: The address the page is mapped at if the page is in the range + * covered by the VMA and present in the page table. If the page is + * outside the VMA or not present, returns -EFAULT. + * Only valid for normal file or anonymous VMAs. */ -int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) +unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) { + struct folio *folio = page_folio(page); + pgoff_t pgoff = folio->index + folio_page_idx(folio, page); struct page_vma_mapped_walk pvmw = { .pfn = page_to_pfn(page), .nr_pages = 1, @@ -332,11 +336,13 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) .flags = PVMW_SYNC, }; - pvmw.address = vma_address(page, vma); + pvmw.address = vma_address(vma, pgoff, 1); if (pvmw.address == -EFAULT) - return 0; + goto out; if (!page_vma_mapped_walk(&pvmw)) - return 0; + return -EFAULT; page_vma_mapped_walk_done(&pvmw); - return 1; +out: + return pvmw.address; } +#endif diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h index cdd0aa597a8196..7e42f0ca3b7bb3 100644 --- a/mm/percpu-internal.h +++ b/mm/percpu-internal.h @@ -32,6 +32,19 @@ struct pcpu_block_md { int nr_bits; /* total bits responsible for */ }; +struct pcpuobj_ext { +#ifdef CONFIG_MEMCG_KMEM + struct obj_cgroup *cgroup; +#endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + union codetag_ref tag; +#endif +}; + +#if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MEM_ALLOC_PROFILING) +#define NEED_PCPUOBJ_EXT +#endif + struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ @@ -64,8 +77,8 @@ struct pcpu_chunk { int end_offset; /* additional area required to have the region end page aligned */ -#ifdef CONFIG_MEMCG_KMEM - struct obj_cgroup **obj_cgroups; /* vector of object cgroups */ +#ifdef NEED_PCPUOBJ_EXT + struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ @@ -74,6 +87,15 @@ struct pcpu_chunk { unsigned long populated[]; /* populated bitmap */ }; +static inline bool need_pcpuobj_ext(void) +{ + if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) + return true; + if (!mem_cgroup_kmem_disabled()) + return true; + return false; +} + extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 2054c9213c4339..cd69caf6aa8d8e 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -231,10 +231,10 @@ static int pcpu_map_pages(struct pcpu_chunk *chunk, return 0; err: for_each_possible_cpu(tcpu) { - if (tcpu == cpu) - break; __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); + if (tcpu == cpu) + break; } pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; diff --git a/mm/percpu.c b/mm/percpu.c index 4e11fc1e6deff0..474e3683b74d17 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1392,9 +1392,9 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); -#ifdef CONFIG_MEMCG_KMEM +#ifdef NEED_PCPUOBJ_EXT /* first chunk is free to use */ - chunk->obj_cgroups = NULL; + chunk->obj_exts = NULL; #endif pcpu_init_md_blocks(chunk); @@ -1463,12 +1463,12 @@ static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) if (!chunk->md_blocks) goto md_blocks_fail; -#ifdef CONFIG_MEMCG_KMEM - if (!mem_cgroup_kmem_disabled()) { - chunk->obj_cgroups = +#ifdef NEED_PCPUOBJ_EXT + if (need_pcpuobj_ext()) { + chunk->obj_exts = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * - sizeof(struct obj_cgroup *), gfp); - if (!chunk->obj_cgroups) + sizeof(struct pcpuobj_ext), gfp); + if (!chunk->obj_exts) goto objcg_fail; } #endif @@ -1480,7 +1480,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) return chunk; -#ifdef CONFIG_MEMCG_KMEM +#ifdef NEED_PCPUOBJ_EXT objcg_fail: pcpu_mem_free(chunk->md_blocks); #endif @@ -1498,8 +1498,8 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; -#ifdef CONFIG_MEMCG_KMEM - pcpu_mem_free(chunk->obj_cgroups); +#ifdef NEED_PCPUOBJ_EXT + pcpu_mem_free(chunk->obj_exts); #endif pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); @@ -1646,9 +1646,9 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, if (!objcg) return; - if (likely(chunk && chunk->obj_cgroups)) { + if (likely(chunk && chunk->obj_exts)) { obj_cgroup_get(objcg); - chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = objcg; + chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = objcg; rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, @@ -1663,13 +1663,13 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; - if (unlikely(!chunk->obj_cgroups)) + if (unlikely(!chunk->obj_exts)) return; - objcg = chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT]; + objcg = chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup; if (!objcg) return; - chunk->obj_cgroups[off >> PCPU_MIN_ALLOC_SHIFT] = NULL; + chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = NULL; obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); @@ -1699,6 +1699,32 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) } #endif /* CONFIG_MEMCG_KMEM */ +#ifdef CONFIG_MEM_ALLOC_PROFILING +static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, + size_t size) +{ + if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) { + alloc_tag_add(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, + current->alloc_tag, size); + } +} + +static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) +{ + if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) + alloc_tag_sub(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, size); +} +#else +static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, + size_t size) +{ +} + +static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) +{ +} +#endif + /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes @@ -1714,7 +1740,7 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ -static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, +void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, gfp_t gfp) { gfp_t pcpu_gfp; @@ -1881,6 +1907,8 @@ area_found: pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); + pcpu_alloc_tag_alloc_hook(chunk, off, size); + return ptr; fail_unlock: @@ -1909,61 +1937,7 @@ fail: return NULL; } - -/** - * __alloc_percpu_gfp - allocate dynamic percpu area - * @size: size of area to allocate in bytes - * @align: alignment of area (max PAGE_SIZE) - * @gfp: allocation flags - * - * Allocate zero-filled percpu area of @size bytes aligned at @align. If - * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can - * be called from any context but is a lot more likely to fail. If @gfp - * has __GFP_NOWARN then no warning will be triggered on invalid or failed - * allocation requests. - * - * RETURNS: - * Percpu pointer to the allocated area on success, NULL on failure. - */ -void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) -{ - return pcpu_alloc(size, align, false, gfp); -} -EXPORT_SYMBOL_GPL(__alloc_percpu_gfp); - -/** - * __alloc_percpu - allocate dynamic percpu area - * @size: size of area to allocate in bytes - * @align: alignment of area (max PAGE_SIZE) - * - * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL). - */ -void __percpu *__alloc_percpu(size_t size, size_t align) -{ - return pcpu_alloc(size, align, false, GFP_KERNEL); -} -EXPORT_SYMBOL_GPL(__alloc_percpu); - -/** - * __alloc_reserved_percpu - allocate reserved percpu area - * @size: size of area to allocate in bytes - * @align: alignment of area (max PAGE_SIZE) - * - * Allocate zero-filled percpu area of @size bytes aligned at @align - * from reserved percpu area if arch has set it up; otherwise, - * allocation is served from the same dynamic area. Might sleep. - * Might trigger writeouts. - * - * CONTEXT: - * Does GFP_KERNEL allocation. - * - * RETURNS: - * Percpu pointer to the allocated area on success, NULL on failure. - */ -void __percpu *__alloc_reserved_percpu(size_t size, size_t align) -{ - return pcpu_alloc(size, align, true, GFP_KERNEL); -} +EXPORT_SYMBOL_GPL(pcpu_alloc_noprof); /** * pcpu_balance_free - manage the amount of free chunks @@ -2302,6 +2276,8 @@ void free_percpu(void __percpu *ptr) spin_lock_irqsave(&pcpu_lock, flags); size = pcpu_free_area(chunk, off); + pcpu_alloc_tag_free_hook(chunk, off, size); + pcpu_memcg_free_hook(chunk, off, size); /* diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4fcd959dcc4d02..74e34ea90656a5 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -198,6 +198,7 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON(!pmd_present(*pmdp)); pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return old; @@ -208,6 +209,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON(!pmd_present(*pmdp)); return pmdp_invalidate(vma, address, pmdp); } #endif diff --git a/mm/readahead.c b/mm/readahead.c index 130c0e7df99f58..c1b23989d9caf3 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -228,6 +228,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, */ for (i = 0; i < nr_to_read; i++) { struct folio *folio = xa_load(&mapping->i_pages, index + i); + int ret; if (folio && !xa_is_value(folio)) { /* @@ -247,9 +248,12 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, folio = filemap_alloc_folio(gfp_mask, 0); if (!folio) break; - if (filemap_add_folio(mapping, folio, index + i, - gfp_mask) < 0) { + + ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); + if (ret < 0) { folio_put(folio); + if (ret == -ENOMEM) + break; read_pages(ractl); ractl->_index++; i = ractl->_index + ractl->_nr_pages - index - 1; @@ -490,6 +494,7 @@ void page_cache_ra_order(struct readahead_control *ractl, pgoff_t index = readahead_index(ractl); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; + unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); @@ -504,6 +509,8 @@ void page_cache_ra_order(struct readahead_control *ractl, new_order = min_t(unsigned int, new_order, ilog2(ra->size)); } + /* See comment in page_cache_ra_unbounded() */ + nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); while (index <= limit) { unsigned int order = new_order; @@ -527,6 +534,7 @@ void page_cache_ra_order(struct readahead_control *ractl, read_pages(ractl); filemap_invalidate_unlock_shared(mapping); + memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have diff --git a/mm/rmap.c b/mm/rmap.c index 3746a553101832..7faa60bc3e4db6 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -23,7 +23,7 @@ * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) - * page->flags PG_locked (lock_page) + * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem @@ -50,7 +50,7 @@ * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) - * page->flags PG_locked (lock_page) + * folio_lock */ #include <linux/mm.h> @@ -182,8 +182,6 @@ static void anon_vma_chain_link(struct vm_area_struct *vma, * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. - * - * This must be called with the mmap_lock held for reading. */ int __anon_vma_prepare(struct vm_area_struct *vma) { @@ -191,6 +189,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; + mmap_assert_locked(mm); might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); @@ -775,6 +774,8 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { struct folio *folio = page_folio(page); + pgoff_t pgoff; + if (folio_test_anon(folio)) { struct anon_vma *page__anon_vma = folio_anon_vma(folio); /* @@ -790,7 +791,9 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) return -EFAULT; } - return vma_address(page, vma); + /* The !page__anon_vma above handles KSM folios */ + pgoff = folio->index + folio_page_idx(folio, page); + return vma_address(vma, pgoff, 1); } /* @@ -1128,56 +1131,38 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, if (invalid_mkclean_vma(vma, NULL)) return 0; - pvmw.address = vma_pgoff_address(pgoff, nr_pages, vma); + pvmw.address = vma_address(vma, pgoff, nr_pages); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } -int folio_total_mapcount(struct folio *folio) -{ - int mapcount = folio_entire_mapcount(folio); - int nr_pages; - int i; - - /* In the common case, avoid the loop when no pages mapped by PTE */ - if (folio_nr_pages_mapped(folio) == 0) - return mapcount; - /* - * Add all the PTE mappings of those pages mapped by PTE. - * Limit the loop to folio_nr_pages_mapped()? - * Perhaps: given all the raciness, that may be a good or a bad idea. - */ - nr_pages = folio_nr_pages(folio); - for (i = 0; i < nr_pages; i++) - mapcount += atomic_read(&folio_page(folio, i)->_mapcount); - - /* But each of those _mapcounts was based on -1 */ - mapcount += nr_pages; - return mapcount; -} - static __always_inline unsigned int __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level, int *nr_pmdmapped) { atomic_t *mapped = &folio->_nr_pages_mapped; + const int orig_nr_pages = nr_pages; int first, nr = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: + if (!folio_test_large(folio)) { + nr = atomic_inc_and_test(&page->_mapcount); + break; + } + do { first = atomic_inc_and_test(&page->_mapcount); - if (first && folio_test_large(folio)) { + if (first) { first = atomic_inc_return_relaxed(mapped); - first = (first < ENTIRELY_MAPPED); + if (first < ENTIRELY_MAPPED) + nr++; } - - if (first) - nr++; } while (page++, --nr_pages > 0); + atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: first = atomic_inc_and_test(&folio->_entire_mapcount); @@ -1194,6 +1179,7 @@ static __always_inline unsigned int __folio_add_rmap(struct folio *folio, nr = 0; } } + atomic_inc(&folio->_large_mapcount); break; } return nr; @@ -1429,10 +1415,14 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, SetPageAnonExclusive(page); } + /* increment count (starts at -1) */ + atomic_set(&folio->_large_mapcount, nr - 1); atomic_set(&folio->_nr_pages_mapped, nr); } else { /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); + /* increment count (starts at -1) */ + atomic_set(&folio->_large_mapcount, 0); atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); SetPageAnonExclusive(&folio->page); __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr); @@ -1504,24 +1494,32 @@ static __always_inline void __folio_remove_rmap(struct folio *folio, { atomic_t *mapped = &folio->_nr_pages_mapped; int last, nr = 0, nr_pmdmapped = 0; + bool partially_mapped = false; enum node_stat_item idx; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: + if (!folio_test_large(folio)) { + nr = atomic_add_negative(-1, &page->_mapcount); + break; + } + + atomic_sub(nr_pages, &folio->_large_mapcount); do { last = atomic_add_negative(-1, &page->_mapcount); - if (last && folio_test_large(folio)) { + if (last) { last = atomic_dec_return_relaxed(mapped); - last = (last < ENTIRELY_MAPPED); + if (last < ENTIRELY_MAPPED) + nr++; } - - if (last) - nr++; } while (page++, --nr_pages > 0); + + partially_mapped = nr && atomic_read(mapped); break; case RMAP_LEVEL_PMD: + atomic_dec(&folio->_large_mapcount); last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); @@ -1536,6 +1534,8 @@ static __always_inline void __folio_remove_rmap(struct folio *folio, nr = 0; } } + + partially_mapped = nr < nr_pmdmapped; break; } @@ -1557,9 +1557,10 @@ static __always_inline void __folio_remove_rmap(struct folio *folio, * page of the folio is unmapped and at least one page * is still mapped. */ - if (folio_test_large(folio) && folio_test_anon(folio)) - if (level == RMAP_LEVEL_PTE || nr < nr_pmdmapped) - deferred_split_folio(folio); + if (folio_test_anon(folio) && + list_empty(&folio->_deferred_list) && + partially_mapped) + deferred_split_folio(folio); } /* @@ -2588,7 +2589,8 @@ static void rmap_walk_anon(struct folio *folio, anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; - unsigned long address = vma_address(&folio->page, vma); + unsigned long address = vma_address(vma, pgoff_start, + folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); @@ -2649,7 +2651,8 @@ static void rmap_walk_file(struct folio *folio, lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { - unsigned long address = vma_address(&folio->page, vma); + unsigned long address = vma_address(vma, pgoff_start, + folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); @@ -2702,6 +2705,7 @@ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && @@ -2716,6 +2720,7 @@ void hugetlb_add_new_anon_rmap(struct folio *folio, BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); + atomic_set(&folio->_large_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); diff --git a/mm/shmem.c b/mm/shmem.c index 94ab99b6b574a4..fa2a0ed97507d1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1907,7 +1907,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, * Some architectures may have to restore extra metadata to the * folio after reading from swap. */ - arch_swap_restore(swap, folio); + arch_swap_restore(folio_swap(swap, folio), folio); if (shmem_should_replace_folio(folio, gfp)) { error = shmem_replace_folio(&folio, gfp, info, index); @@ -2267,8 +2267,6 @@ unsigned long shmem_get_unmapped_area(struct file *file, unsigned long uaddr, unsigned long len, unsigned long pgoff, unsigned long flags) { - unsigned long (*get_area)(struct file *, - unsigned long, unsigned long, unsigned long, unsigned long); unsigned long addr; unsigned long offset; unsigned long inflated_len; @@ -2278,8 +2276,8 @@ unsigned long shmem_get_unmapped_area(struct file *file, if (len > TASK_SIZE) return -ENOMEM; - get_area = current->mm->get_unmapped_area; - addr = get_area(file, uaddr, len, pgoff, flags); + addr = mm_get_unmapped_area(current->mm, file, uaddr, len, pgoff, + flags); if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return addr; @@ -2336,7 +2334,8 @@ unsigned long shmem_get_unmapped_area(struct file *file, if (inflated_len < len) return addr; - inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags); + inflated_addr = mm_get_unmapped_area(current->mm, NULL, uaddr, + inflated_len, 0, flags); if (IS_ERR_VALUE(inflated_addr)) return addr; if (inflated_addr & ~PAGE_MASK) @@ -4801,7 +4800,7 @@ unsigned long shmem_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { - return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); + return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags); } #endif diff --git a/mm/show_mem.c b/mm/show_mem.c index 8dcfafbd283c12..bdb439551eefcb 100644 --- a/mm/show_mem.c +++ b/mm/show_mem.c @@ -423,4 +423,30 @@ void __show_mem(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) #ifdef CONFIG_MEMORY_FAILURE printk("%lu pages hwpoisoned\n", atomic_long_read(&num_poisoned_pages)); #endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + { + struct codetag_bytes tags[10]; + size_t i, nr; + + nr = alloc_tag_top_users(tags, ARRAY_SIZE(tags), false); + if (nr) { + pr_notice("Memory allocations:\n"); + for (i = 0; i < nr; i++) { + struct codetag *ct = tags[i].ct; + struct alloc_tag *tag = ct_to_alloc_tag(ct); + struct alloc_tag_counters counter = alloc_tag_read(tag); + + /* Same as alloc_tag_to_text() but w/o intermediate buffer */ + if (ct->modname) + pr_notice("%12lli %8llu %s:%u [%s] func:%s\n", + counter.bytes, counter.calls, ct->filename, + ct->lineno, ct->modname, ct->function); + else + pr_notice("%12lli %8llu %s:%u func:%s\n", + counter.bytes, counter.calls, ct->filename, + ct->lineno, ct->function); + } + } + } +#endif } diff --git a/mm/slab.h b/mm/slab.h index d2bc9b19122292..d12fb4392e3539 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -84,11 +84,11 @@ struct slab { }; struct rcu_head rcu_head; }; - unsigned int __unused; + unsigned int __page_type; atomic_t __page_refcount; -#ifdef CONFIG_MEMCG - unsigned long memcg_data; +#ifdef CONFIG_SLAB_OBJ_EXT + unsigned long obj_exts; #endif }; @@ -97,8 +97,8 @@ struct slab { SLAB_MATCH(flags, __page_flags); SLAB_MATCH(compound_head, slab_cache); /* Ensure bit 0 is clear */ SLAB_MATCH(_refcount, __page_refcount); -#ifdef CONFIG_MEMCG -SLAB_MATCH(memcg_data, memcg_data); +#ifdef CONFIG_SLAB_OBJ_EXT +SLAB_MATCH(memcg_data, obj_exts); #endif #undef SLAB_MATCH static_assert(sizeof(struct slab) <= sizeof(struct page)); @@ -536,42 +536,52 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla return false; } -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_SLAB_OBJ_EXT + /* - * slab_objcgs - get the object cgroups vector associated with a slab + * slab_obj_exts - get the pointer to the slab object extension vector + * associated with a slab. * @slab: a pointer to the slab struct * - * Returns a pointer to the object cgroups vector associated with the slab, + * Returns a pointer to the object extension vector associated with the slab, * or NULL if no such vector has been associated yet. */ -static inline struct obj_cgroup **slab_objcgs(struct slab *slab) +static inline struct slabobj_ext *slab_obj_exts(struct slab *slab) { - unsigned long memcg_data = READ_ONCE(slab->memcg_data); + unsigned long obj_exts = READ_ONCE(slab->obj_exts); - VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), +#ifdef CONFIG_MEMCG + VM_BUG_ON_PAGE(obj_exts && !(obj_exts & MEMCG_DATA_OBJEXTS), slab_page(slab)); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, slab_page(slab)); - - return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + VM_BUG_ON_PAGE(obj_exts & MEMCG_DATA_KMEM, slab_page(slab)); +#endif + return (struct slabobj_ext *)(obj_exts & ~OBJEXTS_FLAGS_MASK); } -int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s, - gfp_t gfp, bool new_slab); -void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, - enum node_stat_item idx, int nr); -#else /* CONFIG_MEMCG_KMEM */ -static inline struct obj_cgroup **slab_objcgs(struct slab *slab) +int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, + gfp_t gfp, bool new_slab); + +#else /* CONFIG_SLAB_OBJ_EXT */ + +static inline struct slabobj_ext *slab_obj_exts(struct slab *slab) { return NULL; } -static inline int memcg_alloc_slab_cgroups(struct slab *slab, - struct kmem_cache *s, gfp_t gfp, - bool new_slab) +#endif /* CONFIG_SLAB_OBJ_EXT */ + +static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s) { - return 0; + return (s->flags & SLAB_RECLAIM_ACCOUNT) ? + NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B; } -#endif /* CONFIG_MEMCG_KMEM */ + +#ifdef CONFIG_MEMCG_KMEM +bool __memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, + gfp_t flags, size_t size, void **p); +void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, + void **p, int objects, struct slabobj_ext *obj_exts); +#endif size_t __ksize(const void *objp); diff --git a/mm/slab_common.c b/mm/slab_common.c index f5234672f03cea..3179a6aeffc56e 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1189,7 +1189,7 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags) return (void *)p; } - ret = kmalloc_track_caller(new_size, flags); + ret = kmalloc_node_track_caller_noprof(new_size, flags, NUMA_NO_NODE, _RET_IP_); if (ret && p) { /* Disable KASAN checks as the object's redzone is accessed. */ kasan_disable_current(); @@ -1213,7 +1213,7 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags) * * Return: pointer to the allocated memory or %NULL in case of error */ -void *krealloc(const void *p, size_t new_size, gfp_t flags) +void *krealloc_noprof(const void *p, size_t new_size, gfp_t flags) { void *ret; @@ -1228,7 +1228,7 @@ void *krealloc(const void *p, size_t new_size, gfp_t flags) return ret; } -EXPORT_SYMBOL(krealloc); +EXPORT_SYMBOL(krealloc_noprof); /** * kfree_sensitive - Clear sensitive information in memory before freeing diff --git a/mm/slub.c b/mm/slub.c index 1bb2a93cf7b6a4..3e33ff900d35ea 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -616,18 +616,12 @@ slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) */ static __always_inline void slab_lock(struct slab *slab) { - struct page *page = slab_page(slab); - - VM_BUG_ON_PAGE(PageTail(page), page); - bit_spin_lock(PG_locked, &page->flags); + bit_spin_lock(PG_locked, &slab->__page_flags); } static __always_inline void slab_unlock(struct slab *slab) { - struct page *page = slab_page(slab); - - VM_BUG_ON_PAGE(PageTail(page), page); - bit_spin_unlock(PG_locked, &page->flags); + bit_spin_unlock(PG_locked, &slab->__page_flags); } static inline bool @@ -1865,198 +1859,278 @@ static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab, #endif #endif /* CONFIG_SLUB_DEBUG */ -static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s) +#ifdef CONFIG_SLAB_OBJ_EXT + +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + +static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) { - return (s->flags & SLAB_RECLAIM_ACCOUNT) ? - NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B; + struct slabobj_ext *slab_exts; + struct slab *obj_exts_slab; + + obj_exts_slab = virt_to_slab(obj_exts); + slab_exts = slab_obj_exts(obj_exts_slab); + if (slab_exts) { + unsigned int offs = obj_to_index(obj_exts_slab->slab_cache, + obj_exts_slab, obj_exts); + /* codetag should be NULL */ + WARN_ON(slab_exts[offs].ref.ct); + set_codetag_empty(&slab_exts[offs].ref); + } } -#ifdef CONFIG_MEMCG_KMEM -static inline void memcg_free_slab_cgroups(struct slab *slab) +static inline void mark_failed_objexts_alloc(struct slab *slab) { - kfree(slab_objcgs(slab)); - slab->memcg_data = 0; + slab->obj_exts = OBJEXTS_ALLOC_FAIL; } -static inline size_t obj_full_size(struct kmem_cache *s) +static inline void handle_failed_objexts_alloc(unsigned long obj_exts, + struct slabobj_ext *vec, unsigned int objects) { /* - * For each accounted object there is an extra space which is used - * to store obj_cgroup membership. Charge it too. + * If vector previously failed to allocate then we have live + * objects with no tag reference. Mark all references in this + * vector as empty to avoid warnings later on. */ - return s->size + sizeof(struct obj_cgroup *); + if (obj_exts & OBJEXTS_ALLOC_FAIL) { + unsigned int i; + + for (i = 0; i < objects; i++) + set_codetag_empty(&vec[i].ref); + } } +#else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + +static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) {} +static inline void mark_failed_objexts_alloc(struct slab *slab) {} +static inline void handle_failed_objexts_alloc(unsigned long obj_exts, + struct slabobj_ext *vec, unsigned int objects) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + /* - * Returns false if the allocation should fail. + * The allocated objcg pointers array is not accounted directly. + * Moreover, it should not come from DMA buffer and is not readily + * reclaimable. So those GFP bits should be masked off. */ -static bool __memcg_slab_pre_alloc_hook(struct kmem_cache *s, - struct list_lru *lru, - struct obj_cgroup **objcgp, - size_t objects, gfp_t flags) +#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \ + __GFP_ACCOUNT | __GFP_NOFAIL) + +int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, + gfp_t gfp, bool new_slab) +{ + unsigned int objects = objs_per_slab(s, slab); + unsigned long new_exts; + unsigned long old_exts; + struct slabobj_ext *vec; + + gfp &= ~OBJCGS_CLEAR_MASK; + /* Prevent recursive extension vector allocation */ + gfp |= __GFP_NO_OBJ_EXT; + vec = kcalloc_node(objects, sizeof(struct slabobj_ext), gfp, + slab_nid(slab)); + if (!vec) { + /* Mark vectors which failed to allocate */ + if (new_slab) + mark_failed_objexts_alloc(slab); + + return -ENOMEM; + } + + new_exts = (unsigned long)vec; +#ifdef CONFIG_MEMCG + new_exts |= MEMCG_DATA_OBJEXTS; +#endif + old_exts = slab->obj_exts; + handle_failed_objexts_alloc(old_exts, vec, objects); + if (new_slab) { + /* + * If the slab is brand new and nobody can yet access its + * obj_exts, no synchronization is required and obj_exts can + * be simply assigned. + */ + slab->obj_exts = new_exts; + } else if (cmpxchg(&slab->obj_exts, old_exts, new_exts) != old_exts) { + /* + * If the slab is already in use, somebody can allocate and + * assign slabobj_exts in parallel. In this case the existing + * objcg vector should be reused. + */ + mark_objexts_empty(vec); + kfree(vec); + return 0; + } + + kmemleak_not_leak(vec); + return 0; +} + +static inline void free_slab_obj_exts(struct slab *slab) { + struct slabobj_ext *obj_exts; + + obj_exts = slab_obj_exts(slab); + if (!obj_exts) + return; + /* - * The obtained objcg pointer is safe to use within the current scope, - * defined by current task or set_active_memcg() pair. - * obj_cgroup_get() is used to get a permanent reference. + * obj_exts was created with __GFP_NO_OBJ_EXT flag, therefore its + * corresponding extension will be NULL. alloc_tag_sub() will throw a + * warning if slab has extensions but the extension of an object is + * NULL, therefore replace NULL with CODETAG_EMPTY to indicate that + * the extension for obj_exts is expected to be NULL. */ - struct obj_cgroup *objcg = current_obj_cgroup(); - if (!objcg) + mark_objexts_empty(obj_exts); + kfree(obj_exts); + slab->obj_exts = 0; +} + +static inline bool need_slab_obj_ext(void) +{ + if (mem_alloc_profiling_enabled()) return true; - if (lru) { - int ret; - struct mem_cgroup *memcg; + /* + * CONFIG_MEMCG_KMEM creates vector of obj_cgroup objects conditionally + * inside memcg_slab_post_alloc_hook. No other users for now. + */ + return false; +} - memcg = get_mem_cgroup_from_objcg(objcg); - ret = memcg_list_lru_alloc(memcg, lru, flags); - css_put(&memcg->css); +static inline struct slabobj_ext * +prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p) +{ + struct slab *slab; - if (ret) - return false; - } + if (!p) + return NULL; - if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) - return false; + if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE)) + return NULL; - *objcgp = objcg; - return true; + if (flags & __GFP_NO_OBJ_EXT) + return NULL; + + slab = virt_to_slab(p); + if (!slab_obj_exts(slab) && + WARN(alloc_slab_obj_exts(slab, s, flags, false), + "%s, %s: Failed to create slab extension vector!\n", + __func__, s->name)) + return NULL; + + return slab_obj_exts(slab) + obj_to_index(s, slab, p); } -/* - * Returns false if the allocation should fail. - */ -static __fastpath_inline -bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, struct list_lru *lru, - struct obj_cgroup **objcgp, size_t objects, - gfp_t flags) +static inline void +alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p, + int objects) { - if (!memcg_kmem_online()) - return true; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct slabobj_ext *obj_exts; + int i; - if (likely(!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))) - return true; + if (!mem_alloc_profiling_enabled()) + return; - return likely(__memcg_slab_pre_alloc_hook(s, lru, objcgp, objects, - flags)); + obj_exts = slab_obj_exts(slab); + if (!obj_exts) + return; + + for (i = 0; i < objects; i++) { + unsigned int off = obj_to_index(s, slab, p[i]); + + alloc_tag_sub(&obj_exts[off].ref, s->size); + } +#endif } -static void __memcg_slab_post_alloc_hook(struct kmem_cache *s, - struct obj_cgroup *objcg, - gfp_t flags, size_t size, - void **p) +#else /* CONFIG_SLAB_OBJ_EXT */ + +static int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, + gfp_t gfp, bool new_slab) { - struct slab *slab; - unsigned long off; - size_t i; + return 0; +} - flags &= gfp_allowed_mask; +static inline void free_slab_obj_exts(struct slab *slab) +{ +} - for (i = 0; i < size; i++) { - if (likely(p[i])) { - slab = virt_to_slab(p[i]); +static inline bool need_slab_obj_ext(void) +{ + return false; +} - if (!slab_objcgs(slab) && - memcg_alloc_slab_cgroups(slab, s, flags, false)) { - obj_cgroup_uncharge(objcg, obj_full_size(s)); - continue; - } +static inline struct slabobj_ext * +prepare_slab_obj_exts_hook(struct kmem_cache *s, gfp_t flags, void *p) +{ + return NULL; +} - off = obj_to_index(s, slab, p[i]); - obj_cgroup_get(objcg); - slab_objcgs(slab)[off] = objcg; - mod_objcg_state(objcg, slab_pgdat(slab), - cache_vmstat_idx(s), obj_full_size(s)); - } else { - obj_cgroup_uncharge(objcg, obj_full_size(s)); - } - } +static inline void +alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p, + int objects) +{ } +#endif /* CONFIG_SLAB_OBJ_EXT */ + +#ifdef CONFIG_MEMCG_KMEM + +static void memcg_alloc_abort_single(struct kmem_cache *s, void *object); + static __fastpath_inline -void memcg_slab_post_alloc_hook(struct kmem_cache *s, struct obj_cgroup *objcg, +bool memcg_slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, gfp_t flags, size_t size, void **p) { - if (likely(!memcg_kmem_online() || !objcg)) - return; - - return __memcg_slab_post_alloc_hook(s, objcg, flags, size, p); -} + if (likely(!memcg_kmem_online())) + return true; -static void __memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, - void **p, int objects, - struct obj_cgroup **objcgs) -{ - for (int i = 0; i < objects; i++) { - struct obj_cgroup *objcg; - unsigned int off; + if (likely(!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))) + return true; - off = obj_to_index(s, slab, p[i]); - objcg = objcgs[off]; - if (!objcg) - continue; + if (likely(__memcg_slab_post_alloc_hook(s, lru, flags, size, p))) + return true; - objcgs[off] = NULL; - obj_cgroup_uncharge(objcg, obj_full_size(s)); - mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s), - -obj_full_size(s)); - obj_cgroup_put(objcg); + if (likely(size == 1)) { + memcg_alloc_abort_single(s, *p); + *p = NULL; + } else { + kmem_cache_free_bulk(s, size, p); } + + return false; } static __fastpath_inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p, int objects) { - struct obj_cgroup **objcgs; + struct slabobj_ext *obj_exts; if (!memcg_kmem_online()) return; - objcgs = slab_objcgs(slab); - if (likely(!objcgs)) + obj_exts = slab_obj_exts(slab); + if (likely(!obj_exts)) return; - __memcg_slab_free_hook(s, slab, p, objects, objcgs); -} - -static inline -void memcg_slab_alloc_error_hook(struct kmem_cache *s, int objects, - struct obj_cgroup *objcg) -{ - if (objcg) - obj_cgroup_uncharge(objcg, objects * obj_full_size(s)); + __memcg_slab_free_hook(s, slab, p, objects, obj_exts); } #else /* CONFIG_MEMCG_KMEM */ -static inline void memcg_free_slab_cgroups(struct slab *slab) -{ -} - -static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, - struct list_lru *lru, - struct obj_cgroup **objcgp, - size_t objects, gfp_t flags) -{ - return true; -} - -static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, - struct obj_cgroup *objcg, +static inline bool memcg_slab_post_alloc_hook(struct kmem_cache *s, + struct list_lru *lru, gfp_t flags, size_t size, void **p) { + return true; } static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p, int objects) { } - -static inline -void memcg_slab_alloc_error_hook(struct kmem_cache *s, int objects, - struct obj_cgroup *objcg) -{ -} #endif /* CONFIG_MEMCG_KMEM */ /* @@ -2106,9 +2180,9 @@ bool slab_free_hook(struct kmem_cache *s, void *x, bool init) return !kasan_slab_free(s, x, init); } -static inline bool slab_free_freelist_hook(struct kmem_cache *s, - void **head, void **tail, - int *cnt) +static __fastpath_inline +bool slab_free_freelist_hook(struct kmem_cache *s, void **head, void **tail, + int *cnt) { void *object; @@ -2298,7 +2372,7 @@ static __always_inline void account_slab(struct slab *slab, int order, struct kmem_cache *s, gfp_t gfp) { if (memcg_kmem_online() && (s->flags & SLAB_ACCOUNT)) - memcg_alloc_slab_cgroups(slab, s, gfp, true); + alloc_slab_obj_exts(slab, s, gfp, true); mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s), PAGE_SIZE << order); @@ -2307,8 +2381,8 @@ static __always_inline void account_slab(struct slab *slab, int order, static __always_inline void unaccount_slab(struct slab *slab, int order, struct kmem_cache *s) { - if (memcg_kmem_online()) - memcg_free_slab_cgroups(slab); + if (memcg_kmem_online() || need_slab_obj_ext()) + free_slab_obj_exts(slab); mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s), -(PAGE_SIZE << order)); @@ -3736,10 +3810,7 @@ noinline int should_failslab(struct kmem_cache *s, gfp_t gfpflags) ALLOW_ERROR_INJECTION(should_failslab, ERRNO); static __fastpath_inline -struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, - struct list_lru *lru, - struct obj_cgroup **objcgp, - size_t size, gfp_t flags) +struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags) { flags &= gfp_allowed_mask; @@ -3748,18 +3819,16 @@ struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, if (unlikely(should_failslab(s, flags))) return NULL; - if (unlikely(!memcg_slab_pre_alloc_hook(s, lru, objcgp, size, flags))) - return NULL; - return s; } static __fastpath_inline -void slab_post_alloc_hook(struct kmem_cache *s, struct obj_cgroup *objcg, +bool slab_post_alloc_hook(struct kmem_cache *s, struct list_lru *lru, gfp_t flags, size_t size, void **p, bool init, unsigned int orig_size) { unsigned int zero_size = s->object_size; + struct slabobj_ext *obj_exts; bool kasan_init = init; size_t i; gfp_t init_flags = flags & gfp_allowed_mask; @@ -3802,9 +3871,21 @@ void slab_post_alloc_hook(struct kmem_cache *s, struct obj_cgroup *objcg, kmemleak_alloc_recursive(p[i], s->object_size, 1, s->flags, init_flags); kmsan_slab_alloc(s, p[i], init_flags); + if (need_slab_obj_ext()) { + obj_exts = prepare_slab_obj_exts_hook(s, flags, p[i]); +#ifdef CONFIG_MEM_ALLOC_PROFILING + /* + * Currently obj_exts is used only for allocation profiling. + * If other users appear then mem_alloc_profiling_enabled() + * check should be added before alloc_tag_add(). + */ + if (likely(obj_exts)) + alloc_tag_add(&obj_exts->ref, current->alloc_tag, s->size); +#endif + } } - memcg_slab_post_alloc_hook(s, objcg, flags, size, p); + return memcg_slab_post_alloc_hook(s, lru, flags, size, p); } /* @@ -3821,10 +3902,9 @@ static __fastpath_inline void *slab_alloc_node(struct kmem_cache *s, struct list gfp_t gfpflags, int node, unsigned long addr, size_t orig_size) { void *object; - struct obj_cgroup *objcg = NULL; bool init = false; - s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags); + s = slab_pre_alloc_hook(s, gfpflags); if (unlikely(!s)) return NULL; @@ -3841,13 +3921,15 @@ out: /* * When init equals 'true', like for kzalloc() family, only * @orig_size bytes might be zeroed instead of s->object_size + * In case this fails due to memcg_slab_post_alloc_hook(), + * object is set to NULL */ - slab_post_alloc_hook(s, objcg, gfpflags, 1, &object, init, orig_size); + slab_post_alloc_hook(s, lru, gfpflags, 1, &object, init, orig_size); return object; } -void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) +void *kmem_cache_alloc_noprof(struct kmem_cache *s, gfp_t gfpflags) { void *ret = slab_alloc_node(s, NULL, gfpflags, NUMA_NO_NODE, _RET_IP_, s->object_size); @@ -3856,9 +3938,9 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) return ret; } -EXPORT_SYMBOL(kmem_cache_alloc); +EXPORT_SYMBOL(kmem_cache_alloc_noprof); -void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, +void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags) { void *ret = slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, _RET_IP_, @@ -3868,7 +3950,7 @@ void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, return ret; } -EXPORT_SYMBOL(kmem_cache_alloc_lru); +EXPORT_SYMBOL(kmem_cache_alloc_lru_noprof); /** * kmem_cache_alloc_node - Allocate an object on the specified node @@ -3883,7 +3965,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_lru); * * Return: pointer to the new object or %NULL in case of error */ -void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) +void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t gfpflags, int node) { void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, s->object_size); @@ -3891,7 +3973,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) return ret; } -EXPORT_SYMBOL(kmem_cache_alloc_node); +EXPORT_SYMBOL(kmem_cache_alloc_node_noprof); /* * To avoid unnecessary overhead, we pass through large allocation requests @@ -3908,7 +3990,7 @@ static void *__kmalloc_large_node(size_t size, gfp_t flags, int node) flags = kmalloc_fix_flags(flags); flags |= __GFP_COMP; - folio = (struct folio *)alloc_pages_node(node, flags, order); + folio = (struct folio *)alloc_pages_node_noprof(node, flags, order); if (folio) { ptr = folio_address(folio); lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, @@ -3923,7 +4005,7 @@ static void *__kmalloc_large_node(size_t size, gfp_t flags, int node) return ptr; } -void *kmalloc_large(size_t size, gfp_t flags) +void *kmalloc_large_noprof(size_t size, gfp_t flags) { void *ret = __kmalloc_large_node(size, flags, NUMA_NO_NODE); @@ -3931,9 +4013,9 @@ void *kmalloc_large(size_t size, gfp_t flags) flags, NUMA_NO_NODE); return ret; } -EXPORT_SYMBOL(kmalloc_large); +EXPORT_SYMBOL(kmalloc_large_noprof); -void *kmalloc_large_node(size_t size, gfp_t flags, int node) +void *kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) { void *ret = __kmalloc_large_node(size, flags, node); @@ -3941,7 +4023,7 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) flags, node); return ret; } -EXPORT_SYMBOL(kmalloc_large_node); +EXPORT_SYMBOL(kmalloc_large_node_noprof); static __always_inline void *__do_kmalloc_node(size_t size, gfp_t flags, int node, @@ -3968,26 +4050,26 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, return ret; } -void *__kmalloc_node(size_t size, gfp_t flags, int node) +void *__kmalloc_node_noprof(size_t size, gfp_t flags, int node) { return __do_kmalloc_node(size, flags, node, _RET_IP_); } -EXPORT_SYMBOL(__kmalloc_node); +EXPORT_SYMBOL(__kmalloc_node_noprof); -void *__kmalloc(size_t size, gfp_t flags) +void *__kmalloc_noprof(size_t size, gfp_t flags) { return __do_kmalloc_node(size, flags, NUMA_NO_NODE, _RET_IP_); } -EXPORT_SYMBOL(__kmalloc); +EXPORT_SYMBOL(__kmalloc_noprof); -void *__kmalloc_node_track_caller(size_t size, gfp_t flags, - int node, unsigned long caller) +void *kmalloc_node_track_caller_noprof(size_t size, gfp_t flags, + int node, unsigned long caller) { return __do_kmalloc_node(size, flags, node, caller); } -EXPORT_SYMBOL(__kmalloc_node_track_caller); +EXPORT_SYMBOL(kmalloc_node_track_caller_noprof); -void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) +void *kmalloc_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, size_t size) { void *ret = slab_alloc_node(s, NULL, gfpflags, NUMA_NO_NODE, _RET_IP_, size); @@ -3997,9 +4079,9 @@ void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } -EXPORT_SYMBOL(kmalloc_trace); +EXPORT_SYMBOL(kmalloc_trace_noprof); -void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, +void *kmalloc_node_trace_noprof(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, size); @@ -4009,7 +4091,7 @@ void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } -EXPORT_SYMBOL(kmalloc_node_trace); +EXPORT_SYMBOL(kmalloc_node_trace_noprof); static noinline void free_to_partial_list( struct kmem_cache *s, struct slab *slab, @@ -4276,16 +4358,28 @@ void slab_free(struct kmem_cache *s, struct slab *slab, void *object, unsigned long addr) { memcg_slab_free_hook(s, slab, &object, 1); + alloc_tagging_slab_free_hook(s, slab, &object, 1); if (likely(slab_free_hook(s, object, slab_want_init_on_free(s)))) do_slab_free(s, slab, object, object, 1, addr); } +#ifdef CONFIG_MEMCG_KMEM +/* Do not inline the rare memcg charging failed path into the allocation path */ +static noinline +void memcg_alloc_abort_single(struct kmem_cache *s, void *object) +{ + if (likely(slab_free_hook(s, object, slab_want_init_on_free(s)))) + do_slab_free(s, virt_to_slab(object), object, object, 1, _RET_IP_); +} +#endif + static __fastpath_inline void slab_free_bulk(struct kmem_cache *s, struct slab *slab, void *head, void *tail, void **p, int cnt, unsigned long addr) { memcg_slab_free_hook(s, slab, p, cnt); + alloc_tagging_slab_free_hook(s, slab, p, cnt); /* * With KASAN enabled slab_free_freelist_hook modifies the freelist * to remove objects, whose reuse must be delayed. @@ -4612,36 +4706,33 @@ error: #endif /* CONFIG_SLUB_TINY */ /* Note that interrupts must be enabled when calling this function. */ -int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, - void **p) +int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, + void **p) { int i; - struct obj_cgroup *objcg = NULL; if (!size) return 0; - /* memcg and kmem_cache debug support */ - s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags); + s = slab_pre_alloc_hook(s, flags); if (unlikely(!s)) return 0; i = __kmem_cache_alloc_bulk(s, flags, size, p); + if (unlikely(i == 0)) + return 0; /* * memcg and kmem_cache debug support and memory initialization. * Done outside of the IRQ disabled fastpath loop. */ - if (likely(i != 0)) { - slab_post_alloc_hook(s, objcg, flags, size, p, - slab_want_init_on_alloc(flags, s), s->object_size); - } else { - memcg_slab_alloc_error_hook(s, size, objcg); + if (unlikely(!slab_post_alloc_hook(s, NULL, flags, size, p, + slab_want_init_on_alloc(flags, s), s->object_size))) { + return 0; } - return i; } -EXPORT_SYMBOL(kmem_cache_alloc_bulk); +EXPORT_SYMBOL(kmem_cache_alloc_bulk_noprof); /* @@ -5630,7 +5721,8 @@ void __init kmem_cache_init(void) node_set(node, slab_nodes); create_boot_cache(kmem_cache_node, "kmem_cache_node", - sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN, 0, 0); + sizeof(struct kmem_cache_node), + SLAB_HWCACHE_ALIGN | SLAB_NO_OBJ_EXT, 0, 0); hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI); @@ -5640,7 +5732,7 @@ void __init kmem_cache_init(void) create_boot_cache(kmem_cache, "kmem_cache", offsetof(struct kmem_cache, node) + nr_node_ids * sizeof(struct kmem_cache_node *), - SLAB_HWCACHE_ALIGN, 0, 0); + SLAB_HWCACHE_ALIGN | SLAB_NO_OBJ_EXT, 0, 0); kmem_cache = bootstrap(&boot_kmem_cache); kmem_cache_node = bootstrap(&boot_kmem_cache_node); diff --git a/mm/sparse.c b/mm/sparse.c index aed0951b87fa04..de40b2c7340673 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -226,19 +226,6 @@ static void __init memory_present(int nid, unsigned long start, unsigned long en { unsigned long pfn; -#ifdef CONFIG_SPARSEMEM_EXTREME - if (unlikely(!mem_section)) { - unsigned long size, align; - - size = sizeof(struct mem_section *) * NR_SECTION_ROOTS; - align = 1 << (INTERNODE_CACHE_SHIFT); - mem_section = memblock_alloc(size, align); - if (!mem_section) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, size, align); - } -#endif - start &= PAGE_SECTION_MASK; mminit_validate_memmodel_limits(&start, &end); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) { @@ -267,6 +254,19 @@ static void __init memblocks_present(void) unsigned long start, end; int i, nid; +#ifdef CONFIG_SPARSEMEM_EXTREME + if (unlikely(!mem_section)) { + unsigned long size, align; + + size = sizeof(struct mem_section *) * NR_SECTION_ROOTS; + align = 1 << (INTERNODE_CACHE_SHIFT); + mem_section = memblock_alloc(size, align); + if (!mem_section) + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, size, align); + } +#endif + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) memory_present(nid, start, end); } @@ -560,6 +560,8 @@ void __init sparse_init(void) unsigned long pnum_end, pnum_begin, map_count = 1; int nid_begin; + /* see include/linux/mmzone.h 'struct mem_section' definition */ + BUILD_BUG_ON(!is_power_of_2(sizeof(struct mem_section))); memblocks_present(); pnum_begin = first_present_section_nr(); diff --git a/mm/swap.c b/mm/swap.c index 500a09a48dfd3a..67786cb771305c 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -112,34 +112,21 @@ static void page_cache_release(struct folio *folio) unlock_page_lruvec_irqrestore(lruvec, flags); } -static void __folio_put_small(struct folio *folio) +void __folio_put(struct folio *folio) { + if (unlikely(folio_is_zone_device(folio))) { + free_zone_device_folio(folio); + return; + } else if (folio_test_hugetlb(folio)) { + free_huge_folio(folio); + return; + } + page_cache_release(folio); + if (folio_test_large(folio) && folio_test_large_rmappable(folio)) + folio_undo_large_rmappable(folio); mem_cgroup_uncharge(folio); - free_unref_page(&folio->page, 0); -} - -static void __folio_put_large(struct folio *folio) -{ - /* - * __page_cache_release() is supposed to be called for thp, not for - * hugetlb. This is because hugetlb page does never have PageLRU set - * (it's never listed to any LRU lists) and no memcg routines should - * be called for hugetlb (it has a separate hugetlb_cgroup.) - */ - if (!folio_test_hugetlb(folio)) - page_cache_release(folio); - destroy_large_folio(folio); -} - -void __folio_put(struct folio *folio) -{ - if (unlikely(folio_is_zone_device(folio))) - free_zone_device_page(&folio->page); - else if (unlikely(folio_test_large(folio))) - __folio_put_large(folio); - else - __folio_put_small(folio); + free_unref_page(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); @@ -158,8 +145,8 @@ void put_pages_list(struct list_head *pages) list_for_each_entry_safe(folio, next, pages, lru) { if (!folio_put_testzero(folio)) continue; - if (folio_test_large(folio)) { - __folio_put_large(folio); + if (folio_test_hugetlb(folio)) { + free_huge_folio(folio); continue; } /* LRU flag must be clear because it's passed using the lru */ @@ -460,15 +447,18 @@ static void folio_inc_refs(struct folio *folio) } #endif /* CONFIG_LRU_GEN */ -/* - * Mark a page as having seen activity. +/** + * folio_mark_accessed - Mark a folio as having seen activity. + * @folio: The folio to mark. + * + * This function will perform one of the following transitions: * - * inactive,unreferenced -> inactive,referenced - * inactive,referenced -> active,unreferenced - * active,unreferenced -> active,referenced + * * inactive,unreferenced -> inactive,referenced + * * inactive,referenced -> active,unreferenced + * * active,unreferenced -> active,referenced * - * When a newly allocated page is not yet visible, so safe for non-atomic ops, - * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). + * When a newly allocated folio is not yet visible, so safe for non-atomic ops, + * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ void folio_mark_accessed(struct folio *folio) { @@ -985,7 +975,7 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) struct folio *folio = folios->folios[i]; unsigned int nr_refs = refs ? refs[i] : 1; - if (is_huge_zero_page(&folio->page)) + if (is_huge_zero_folio(folio)) continue; if (folio_is_zone_device(folio)) { @@ -993,10 +983,10 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } - if (put_devmap_managed_page_refs(&folio->page, nr_refs)) + if (put_devmap_managed_folio_refs(folio, nr_refs)) continue; if (folio_ref_sub_and_test(folio, nr_refs)) - free_zone_device_page(&folio->page); + free_zone_device_folio(folio); continue; } diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 90973ce7881db2..13ab3b771409c3 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -264,7 +264,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache) cache->cur = 0; if (swap_slot_cache_active) cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE, - cache->slots, 1); + cache->slots, 0); return cache->nr; } @@ -310,8 +310,8 @@ swp_entry_t folio_alloc_swap(struct folio *folio) entry.val = 0; if (folio_test_large(folio)) { - if (IS_ENABLED(CONFIG_THP_SWAP) && arch_thp_swp_supported()) - get_swap_pages(1, &entry, folio_nr_pages(folio)); + if (IS_ENABLED(CONFIG_THP_SWAP)) + get_swap_pages(1, &entry, folio_order(folio)); goto out; } @@ -343,7 +343,7 @@ repeat: goto out; } - get_swap_pages(1, &entry, 1); + get_swap_pages(1, &entry, 0); out: if (mem_cgroup_try_charge_swap(folio, entry)) { put_swap_folio(folio, entry); diff --git a/mm/swap_state.c b/mm/swap_state.c index bfc7e8c58a6d34..642c30d8376c60 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -73,11 +73,11 @@ void *get_shadow_from_swap_cache(swp_entry_t entry) { struct address_space *address_space = swap_address_space(entry); pgoff_t idx = swp_offset(entry); - struct page *page; + void *shadow; - page = xa_load(&address_space->i_pages, idx); - if (xa_is_value(page)) - return page; + shadow = xa_load(&address_space->i_pages, idx); + if (xa_is_value(shadow)) + return shadow; return NULL; } @@ -301,7 +301,7 @@ void free_page_and_swap_cache(struct page *page) struct folio *folio = page_folio(page); free_swap_cache(folio); - if (!is_huge_zero_page(page)) + if (!is_huge_zero_folio(folio)) folio_put(folio); } diff --git a/mm/swapfile.c b/mm/swapfile.c index 4919423cce76a3..96606580ee091d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -130,7 +130,11 @@ static inline unsigned char swap_count(unsigned char ent) /* Reclaim the swap entry if swap is getting full*/ #define TTRS_FULL 0x4 -/* returns 1 if swap entry is freed */ +/* + * returns number of pages in the folio that backs the swap entry. If positive, + * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no + * folio was associated with the swap entry. + */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { @@ -155,6 +159,7 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, ret = folio_free_swap(folio); folio_unlock(folio); } + ret = ret ? folio_nr_pages(folio) : -folio_nr_pages(folio); folio_put(folio); return ret; } @@ -273,15 +278,15 @@ static void discard_swap_cluster(struct swap_info_struct *si, #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR -#define swap_entry_size(size) (size) +#define swap_entry_order(order) (order) #else #define SWAPFILE_CLUSTER 256 /* - * Define swap_entry_size() as constant to let compiler to optimize + * Define swap_entry_order() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ -#define swap_entry_size(size) 1 +#define swap_entry_order(order) 0 #endif #define LATENCY_LIMIT 256 @@ -343,18 +348,6 @@ static inline void cluster_set_null(struct swap_cluster_info *info) info->data = 0; } -static inline bool cluster_is_huge(struct swap_cluster_info *info) -{ - if (IS_ENABLED(CONFIG_THP_SWAP)) - return info->flags & CLUSTER_FLAG_HUGE; - return false; -} - -static inline void cluster_clear_huge(struct swap_cluster_info *info) -{ - info->flags &= ~CLUSTER_FLAG_HUGE; -} - static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { @@ -558,10 +551,12 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx) /* * The cluster corresponding to page_nr will be used. The cluster will be - * removed from free cluster list and its usage counter will be increased. + * removed from free cluster list and its usage counter will be increased by + * count. */ -static void inc_cluster_info_page(struct swap_info_struct *p, - struct swap_cluster_info *cluster_info, unsigned long page_nr) +static void add_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr, + unsigned long count) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; @@ -570,9 +565,19 @@ static void inc_cluster_info_page(struct swap_info_struct *p, if (cluster_is_free(&cluster_info[idx])) alloc_cluster(p, idx); - VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); + VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER); cluster_set_count(&cluster_info[idx], - cluster_count(&cluster_info[idx]) + 1); + cluster_count(&cluster_info[idx]) + count); +} + +/* + * The cluster corresponding to page_nr will be used. The cluster will be + * removed from free cluster list and its usage counter will be increased by 1. + */ +static void inc_cluster_info_page(struct swap_info_struct *p, + struct swap_cluster_info *cluster_info, unsigned long page_nr) +{ + add_cluster_info_page(p, cluster_info, page_nr, 1); } /* @@ -602,7 +607,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p, */ static bool scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, - unsigned long offset) + unsigned long offset, int order) { struct percpu_cluster *percpu_cluster; bool conflict; @@ -616,27 +621,42 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); - cluster_set_null(&percpu_cluster->index); + percpu_cluster->next[order] = SWAP_NEXT_INVALID; + return true; +} + +static inline bool swap_range_empty(char *swap_map, unsigned int start, + unsigned int nr_pages) +{ + unsigned int i; + + for (i = 0; i < nr_pages; i++) { + if (swap_map[start + i]) + return false; + } + return true; } /* - * Try to get a swap entry from current cpu's swap entry pool (a cluster). This - * might involve allocating a new cluster for current CPU too. + * Try to get swap entries with specified order from current cpu's swap entry + * pool (a cluster). This might involve allocating a new cluster for current CPU + * too. */ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, - unsigned long *offset, unsigned long *scan_base) + unsigned long *offset, unsigned long *scan_base, int order) { + unsigned int nr_pages = 1 << order; struct percpu_cluster *cluster; struct swap_cluster_info *ci; - unsigned long tmp, max; + unsigned int tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); - if (cluster_is_null(&cluster->index)) { + tmp = cluster->next[order]; + if (tmp == SWAP_NEXT_INVALID) { if (!cluster_list_empty(&si->free_clusters)) { - cluster->index = si->free_clusters.head; - cluster->next = cluster_next(&cluster->index) * + tmp = cluster_next(&si->free_clusters.head) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* @@ -654,27 +674,27 @@ new_cluster: /* * Other CPUs can use our cluster if they can't find a free cluster, - * check if there is still free entry in the cluster + * check if there is still free entry in the cluster, maintaining + * natural alignment. */ - tmp = cluster->next; - max = min_t(unsigned long, si->max, - (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); + max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER)); if (tmp < max) { ci = lock_cluster(si, tmp); while (tmp < max) { - if (!si->swap_map[tmp]) + if (swap_range_empty(si->swap_map, tmp, nr_pages)) break; - tmp++; + tmp += nr_pages; } unlock_cluster(ci); } if (tmp >= max) { - cluster_set_null(&cluster->index); + cluster->next[order] = SWAP_NEXT_INVALID; goto new_cluster; } - cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; + tmp += nr_pages; + cluster->next[order] = tmp < max ? tmp : SWAP_NEXT_INVALID; return true; } @@ -804,13 +824,14 @@ static bool swap_offset_available_and_locked(struct swap_info_struct *si, static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, - swp_entry_t slots[]) + swp_entry_t slots[], int order) { struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; + unsigned int nr_pages = 1 << order; int n_ret = 0; bool scanned_many = false; @@ -825,6 +846,25 @@ static int scan_swap_map_slots(struct swap_info_struct *si, * And we let swap pages go all over an SSD partition. Hugh */ + if (order > 0) { + /* + * Should not even be attempting large allocations when huge + * page swap is disabled. Warn and fail the allocation. + */ + if (!IS_ENABLED(CONFIG_THP_SWAP) || + nr_pages > SWAPFILE_CLUSTER) { + VM_WARN_ON_ONCE(1); + return 0; + } + + /* + * Swapfile is not block device or not using clusters so unable + * to allocate large entries. + */ + if (!(si->flags & SWP_BLKDEV) || !si->cluster_info) + return 0; + } + si->flags += SWP_SCANNING; /* * Use percpu scan base for SSD to reduce lock contention on @@ -839,8 +879,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si, /* SSD algorithm */ if (si->cluster_info) { - if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) + if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) { + if (order > 0) + goto no_page; goto scan; + } } else if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; @@ -882,13 +925,16 @@ static int scan_swap_map_slots(struct swap_info_struct *si, checks: if (si->cluster_info) { - while (scan_swap_map_ssd_cluster_conflict(si, offset)) { + while (scan_swap_map_ssd_cluster_conflict(si, offset, order)) { /* take a break if we already got some slots */ if (n_ret) goto done; if (!scan_swap_map_try_ssd_cluster(si, &offset, - &scan_base)) + &scan_base, order)) { + if (order > 0) + goto no_page; goto scan; + } } } if (!(si->flags & SWP_WRITEOK)) @@ -907,7 +953,7 @@ checks: swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ - if (swap_was_freed) + if (swap_was_freed > 0) goto checks; goto scan; /* check next one */ } @@ -919,11 +965,11 @@ checks: else goto done; } - WRITE_ONCE(si->swap_map[offset], usage); - inc_cluster_info_page(si, si->cluster_info, offset); + memset(si->swap_map + offset, usage, nr_pages); + add_cluster_info_page(si, si->cluster_info, offset, nr_pages); unlock_cluster(ci); - swap_range_alloc(si, offset, 1); + swap_range_alloc(si, offset, nr_pages); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ @@ -944,8 +990,10 @@ checks: /* try to get more slots in cluster */ if (si->cluster_info) { - if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) + if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) goto checks; + if (order > 0) + goto done; } else if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; @@ -972,11 +1020,13 @@ checks: } done: - set_cluster_next(si, offset + 1); + if (order == 0) + set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: + VM_WARN_ON(order > 0); spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (unlikely(--latency_ration < 0)) { @@ -1005,38 +1055,6 @@ no_page: return n_ret; } -static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) -{ - unsigned long idx; - struct swap_cluster_info *ci; - unsigned long offset; - - /* - * Should not even be attempting cluster allocations when huge - * page swap is disabled. Warn and fail the allocation. - */ - if (!IS_ENABLED(CONFIG_THP_SWAP)) { - VM_WARN_ON_ONCE(1); - return 0; - } - - if (cluster_list_empty(&si->free_clusters)) - return 0; - - idx = cluster_list_first(&si->free_clusters); - offset = idx * SWAPFILE_CLUSTER; - ci = lock_cluster(si, offset); - alloc_cluster(si, idx); - cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); - - memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER); - unlock_cluster(ci); - swap_range_alloc(si, offset, SWAPFILE_CLUSTER); - *slot = swp_entry(si->type, offset); - - return 1; -} - static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) { unsigned long offset = idx * SWAPFILE_CLUSTER; @@ -1050,17 +1068,15 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) swap_range_free(si, offset, SWAPFILE_CLUSTER); } -int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) +int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order) { - unsigned long size = swap_entry_size(entry_size); + int order = swap_entry_order(entry_order); + unsigned long size = 1 << order; struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; - /* Only single cluster request supported */ - WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER); - spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; @@ -1096,14 +1112,10 @@ start_over: spin_unlock(&si->lock); goto nextsi; } - if (size == SWAPFILE_CLUSTER) { - if (si->flags & SWP_BLKDEV) - n_ret = swap_alloc_cluster(si, swp_entries); - } else - n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, - n_goal, swp_entries); + n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, + n_goal, swp_entries, order); spin_unlock(&si->lock); - if (n_ret || size == SWAPFILE_CLUSTER) + if (n_ret || size > 1) goto check_out; cond_resched(); @@ -1226,16 +1238,15 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, /* * When we get a swap entry, if there aren't some other ways to - * prevent swapoff, such as the folio in swap cache is locked, page - * table lock is held, etc., the swap entry may become invalid because - * of swapoff. Then, we need to enclose all swap related functions - * with get_swap_device() and put_swap_device(), unless the swap - * functions call get/put_swap_device() by themselves. + * prevent swapoff, such as the folio in swap cache is locked, RCU + * reader side is locked, etc., the swap entry may become invalid + * because of swapoff. Then, we need to enclose all swap related + * functions with get_swap_device() and put_swap_device(), unless the + * swap functions call get/put_swap_device() by themselves. * - * Note that when only holding the PTL, swapoff might succeed immediately - * after freeing a swap entry. Therefore, immediately after - * __swap_entry_free(), the swap info might become stale and should not - * be touched without a prior get_swap_device(). + * RCU reader side lock (including any spinlock) is sufficient to + * prevent swapoff, because synchronize_rcu() is called in swapoff() + * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid @@ -1357,7 +1368,7 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry) unsigned char *map; unsigned int i, free_entries = 0; unsigned char val; - int size = swap_entry_size(folio_nr_pages(folio)); + int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) @@ -1365,7 +1376,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry) ci = lock_cluster_or_swap_info(si, offset); if (size == SWAPFILE_CLUSTER) { - VM_BUG_ON(!cluster_is_huge(ci)); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) { val = map[i]; @@ -1373,7 +1383,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry) if (val == SWAP_HAS_CACHE) free_entries++; } - cluster_clear_huge(ci); if (free_entries == SWAPFILE_CLUSTER) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); @@ -1395,23 +1404,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry) unlock_cluster_or_swap_info(si, ci); } -#ifdef CONFIG_THP_SWAP -int split_swap_cluster(swp_entry_t entry) -{ - struct swap_info_struct *si; - struct swap_cluster_info *ci; - unsigned long offset = swp_offset(entry); - - si = _swap_info_get(entry); - if (!si) - return -EBUSY; - ci = lock_cluster(si, offset); - cluster_clear_huge(ci); - unlock_cluster(ci); - return 0; -} -#endif - static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; @@ -1519,22 +1511,23 @@ out: } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, - swp_entry_t entry) + swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; + unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); - unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER); + unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); - if (!ci || !cluster_is_huge(ci)) { + if (!ci || nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } - for (i = 0; i < SWAPFILE_CLUSTER; i++) { + for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; @@ -1556,7 +1549,7 @@ static bool folio_swapped(struct folio *folio) if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_swapcount(si, entry) != 0; - return swap_page_trans_huge_swapped(si, entry); + return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } /** @@ -1602,33 +1595,88 @@ bool folio_free_swap(struct folio *folio) return true; } -/* - * Free the swap entry like above, but also try to - * free the page cache entry if it is the last user. +/** + * free_swap_and_cache_nr() - Release reference on range of swap entries and + * reclaim their cache if no more references remain. + * @entry: First entry of range. + * @nr: Number of entries in range. + * + * For each swap entry in the contiguous range, release a reference. If any swap + * entries become free, try to reclaim their underlying folios, if present. The + * offset range is defined by [entry.offset, entry.offset + nr). */ -int free_swap_and_cache(swp_entry_t entry) +void free_swap_and_cache_nr(swp_entry_t entry, int nr) { - struct swap_info_struct *p; + const unsigned long start_offset = swp_offset(entry); + const unsigned long end_offset = start_offset + nr; + unsigned int type = swp_type(entry); + struct swap_info_struct *si; + bool any_only_cache = false; + unsigned long offset; unsigned char count; if (non_swap_entry(entry)) - return 1; + return; - p = get_swap_device(entry); - if (p) { - if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { - put_swap_device(p); - return 0; + si = get_swap_device(entry); + if (!si) + return; + + if (WARN_ON(end_offset > si->max)) + goto out; + + /* + * First free all entries in the range. + */ + for (offset = start_offset; offset < end_offset; offset++) { + if (data_race(si->swap_map[offset])) { + count = __swap_entry_free(si, swp_entry(type, offset)); + if (count == SWAP_HAS_CACHE) + any_only_cache = true; + } else { + WARN_ON_ONCE(1); } + } - count = __swap_entry_free(p, entry); - if (count == SWAP_HAS_CACHE && - !swap_page_trans_huge_swapped(p, entry)) - __try_to_reclaim_swap(p, swp_offset(entry), + /* + * Short-circuit the below loop if none of the entries had their + * reference drop to zero. + */ + if (!any_only_cache) + goto out; + + /* + * Now go back over the range trying to reclaim the swap cache. This is + * more efficient for large folios because we will only try to reclaim + * the swap once per folio in the common case. If we do + * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the + * latter will get a reference and lock the folio for every individual + * page but will only succeed once the swap slot for every subpage is + * zero. + */ + for (offset = start_offset; offset < end_offset; offset += nr) { + nr = 1; + if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { + /* + * Folios are always naturally aligned in swap so + * advance forward to the next boundary. Zero means no + * folio was found for the swap entry, so advance by 1 + * in this case. Negative value means folio was found + * but could not be reclaimed. Here we can still advance + * to the next boundary. + */ + nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); - put_swap_device(p); + if (nr == 0) + nr = 1; + else if (nr < 0) + nr = -nr; + nr = ALIGN(offset + 1, nr) - offset; + } } - return p != NULL; + +out: + put_swap_device(si); } #ifdef CONFIG_HIBERNATION @@ -1643,7 +1691,7 @@ swp_entry_t get_swap_page_of_type(int type) /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); - if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry)) + if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: @@ -1806,7 +1854,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ - arch_swap_restore(entry, folio); + arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); @@ -2396,13 +2444,17 @@ static void reinsert_swap_info(struct swap_info_struct *p) spin_unlock(&swap_lock); } +static bool __has_usable_swap(void) +{ + return !plist_head_empty(&swap_active_head); +} + bool has_usable_swap(void) { - bool ret = true; + bool ret; spin_lock(&swap_lock); - if (plist_head_empty(&swap_active_head)) - ret = false; + ret = __has_usable_swap(); spin_unlock(&swap_lock); return ret; } @@ -2495,10 +2547,11 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) /* * Wait for swap operations protected by get/put_swap_device() - * to complete. - * - * We need synchronize_rcu() here to protect the accessing to - * the swap cache data structure. + * to complete. Because of synchronize_rcu() here, all swap + * operations protected by RCU reader side lock (including any + * spinlock) will be waited too. This makes it easy to + * prevent folio_test_swapcache() and the following swap cache + * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); @@ -3097,7 +3150,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && bdev_nonrot(p->bdev)) { - int cpu; + int cpu, i; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; @@ -3133,8 +3186,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; + cluster = per_cpu_ptr(p->percpu_cluster, cpu); - cluster_set_null(&cluster->index); + for (i = 0; i < SWAP_NR_ORDERS; i++) + cluster->next[i] = SWAP_NEXT_INVALID; } } else { atomic_inc(&nr_rotate_swap); @@ -3659,6 +3714,9 @@ void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) if (!(gfp & __GFP_IO)) return; + if (!__has_usable_swap()) + return; + if (!blk_cgroup_congested()) return; diff --git a/mm/truncate.c b/mm/truncate.c index 725b150e47ac4c..e99085bf3d34d9 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -764,15 +764,15 @@ EXPORT_SYMBOL(truncate_setsize); * @from: original inode size * @to: new inode size * - * Handle extension of inode size either caused by extending truncate or by - * write starting after current i_size. We mark the page straddling current - * i_size RO so that page_mkwrite() is called on the nearest write access to - * the page. This way filesystem can be sure that page_mkwrite() is called on - * the page before user writes to the page via mmap after the i_size has been - * changed. + * Handle extension of inode size either caused by extending truncate or + * by write starting after current i_size. We mark the page straddling + * current i_size RO so that page_mkwrite() is called on the first + * write access to the page. The filesystem will update its per-block + * information before user writes to the page via mmap after the i_size + * has been changed. * * The function must be called after i_size is updated so that page fault - * coming after we unlock the page will already see the new i_size. + * coming after we unlock the folio will already see the new i_size. * The function must be called while we still hold i_rwsem - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. @@ -781,31 +781,29 @@ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { int bsize = i_blocksize(inode); loff_t rounded_from; - struct page *page; - pgoff_t index; + struct folio *folio; WARN_ON(to > inode->i_size); - if (from >= to || bsize == PAGE_SIZE) + if (from >= to || bsize >= PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; - index = from >> PAGE_SHIFT; - page = find_lock_page(inode->i_mapping, index); - /* Page not cached? Nothing to do */ - if (!page) + folio = filemap_lock_folio(inode->i_mapping, from / PAGE_SIZE); + /* Folio not cached? Nothing to do */ + if (IS_ERR(folio)) return; /* - * See clear_page_dirty_for_io() for details why set_page_dirty() + * See folio_clear_dirty_for_io() for details why folio_mark_dirty() * is needed. */ - if (page_mkclean(page)) - set_page_dirty(page); - unlock_page(page); - put_page(page); + if (folio_mkclean(folio)) + folio_mark_dirty(folio); + folio_unlock(folio); + folio_put(folio); } EXPORT_SYMBOL(pagecache_isize_extended); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 3c3539c573e7fe..d9e82ae68244e6 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -56,17 +56,16 @@ struct vm_area_struct *find_vma_and_prepare_anon(struct mm_struct *mm, #ifdef CONFIG_PER_VMA_LOCK /* - * lock_vma() - Lookup and lock vma corresponding to @address. + * uffd_lock_vma() - Lookup and lock vma corresponding to @address. * @mm: mm to search vma in. * @address: address that the vma should contain. * - * Should be called without holding mmap_lock. vma should be unlocked after use - * with unlock_vma(). + * Should be called without holding mmap_lock. * * Return: A locked vma containing @address, -ENOENT if no vma is found, or * -ENOMEM if anon_vma couldn't be allocated. */ -static struct vm_area_struct *lock_vma(struct mm_struct *mm, +static struct vm_area_struct *uffd_lock_vma(struct mm_struct *mm, unsigned long address) { struct vm_area_struct *vma; @@ -74,9 +73,8 @@ static struct vm_area_struct *lock_vma(struct mm_struct *mm, vma = lock_vma_under_rcu(mm, address); if (vma) { /* - * lock_vma_under_rcu() only checks anon_vma for private - * anonymous mappings. But we need to ensure it is assigned in - * private file-backed vmas as well. + * We know we're going to need to use anon_vma, so check + * that early. */ if (!(vma->vm_flags & VM_SHARED) && unlikely(!vma->anon_vma)) vma_end_read(vma); @@ -107,7 +105,7 @@ static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm, { struct vm_area_struct *dst_vma; - dst_vma = lock_vma(dst_mm, dst_start); + dst_vma = uffd_lock_vma(dst_mm, dst_start); if (IS_ERR(dst_vma) || validate_dst_vma(dst_vma, dst_start + len)) return dst_vma; @@ -180,9 +178,9 @@ int mfill_atomic_install_pte(pmd_t *dst_pmd, pte_t _dst_pte, *dst_pte; bool writable = dst_vma->vm_flags & VM_WRITE; bool vm_shared = dst_vma->vm_flags & VM_SHARED; - bool page_in_cache = page_mapping(page); spinlock_t *ptl; - struct folio *folio; + struct folio *folio = page_folio(page); + bool page_in_cache = folio_mapping(folio); _dst_pte = mk_pte(page, dst_vma->vm_page_prot); _dst_pte = pte_mkdirty(_dst_pte); @@ -212,7 +210,6 @@ int mfill_atomic_install_pte(pmd_t *dst_pmd, if (!pte_none_mostly(ptep_get(dst_pte))) goto out_unlock; - folio = page_folio(page); if (page_in_cache) { /* Usually, cache pages are already added to LRU */ if (newly_allocated) @@ -1026,7 +1023,7 @@ static int move_present_pte(struct mm_struct *mm, } folio_move_anon_rmap(src_folio, dst_vma); - WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + src_folio->index = linear_page_index(dst_vma, dst_addr); orig_dst_pte = mk_pte(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ @@ -1402,7 +1399,7 @@ static int uffd_move_lock(struct mm_struct *mm, struct vm_area_struct *vma; int err; - vma = lock_vma(mm, dst_start); + vma = uffd_lock_vma(mm, dst_start); if (IS_ERR(vma)) return PTR_ERR(vma); @@ -1417,7 +1414,7 @@ static int uffd_move_lock(struct mm_struct *mm, } /* - * Using lock_vma() to get src_vma can lead to following deadlock: + * Using uffd_lock_vma() to get src_vma can lead to following deadlock: * * Thread1 Thread2 * ------- ------- @@ -1439,7 +1436,7 @@ static int uffd_move_lock(struct mm_struct *mm, err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap); if (!err) { /* - * See comment in lock_vma() as to why not using + * See comment in uffd_lock_vma() as to why not using * vma_start_read() here. */ down_read(&(*dst_vmap)->vm_lock->lock); @@ -1662,9 +1659,9 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, /* Check if we can move the pmd without splitting it. */ if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || !pmd_none(dst_pmdval)) { - struct folio *folio = pfn_folio(pmd_pfn(*src_pmd)); + struct folio *folio = pmd_folio(*src_pmd); - if (!folio || (!is_huge_zero_page(&folio->page) && + if (!folio || (!is_huge_zero_folio(folio) && !PageAnonExclusive(&folio->page))) { spin_unlock(ptl); err = -EBUSY; diff --git a/mm/util.c b/mm/util.c index 669397235787b9..c9e519e6811f55 100644 --- a/mm/util.c +++ b/mm/util.c @@ -124,16 +124,16 @@ EXPORT_SYMBOL(kstrndup); * Return: newly allocated copy of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ -void *kmemdup(const void *src, size_t len, gfp_t gfp) +void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) { void *p; - p = kmalloc_track_caller(len, gfp); + p = kmalloc_node_track_caller_noprof(len, gfp, NUMA_NO_NODE, _RET_IP_); if (p) memcpy(p, src, len); return p; } -EXPORT_SYMBOL(kmemdup); +EXPORT_SYMBOL(kmemdup_noprof); /** * kmemdup_array - duplicate a given array. @@ -469,17 +469,17 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); - mm->get_unmapped_area = arch_get_unmapped_area_topdown; + set_bit(MMF_TOPDOWN, &mm->flags); } } #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; - mm->get_unmapped_area = arch_get_unmapped_area; + clear_bit(MMF_TOPDOWN, &mm->flags); } #endif @@ -609,7 +609,7 @@ EXPORT_SYMBOL(vm_mmap); * * Return: pointer to the allocated memory of %NULL in case of failure */ -void *kvmalloc_node(size_t size, gfp_t flags, int node) +void *kvmalloc_node_noprof(size_t size, gfp_t flags, int node) { gfp_t kmalloc_flags = flags; void *ret; @@ -631,7 +631,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) kmalloc_flags &= ~__GFP_NOFAIL; } - ret = kmalloc_node(size, kmalloc_flags, node); + ret = kmalloc_node_noprof(size, kmalloc_flags, node); /* * It doesn't really make sense to fallback to vmalloc for sub page @@ -656,11 +656,11 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) * about the resulting pointer, and cannot play * protection games. */ - return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, node, __builtin_return_address(0)); } -EXPORT_SYMBOL(kvmalloc_node); +EXPORT_SYMBOL(kvmalloc_node_noprof); /** * kvfree() - Free memory. @@ -699,7 +699,7 @@ void kvfree_sensitive(const void *addr, size_t len) } EXPORT_SYMBOL(kvfree_sensitive); -void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) +void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags) { void *newp; @@ -712,7 +712,7 @@ void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) kvfree(p); return newp; } -EXPORT_SYMBOL(kvrealloc); +EXPORT_SYMBOL(kvrealloc_noprof); /** * __vmalloc_array - allocate memory for a virtually contiguous array. @@ -720,7 +720,7 @@ EXPORT_SYMBOL(kvrealloc); * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -void *__vmalloc_array(size_t n, size_t size, gfp_t flags) +void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; @@ -728,18 +728,18 @@ void *__vmalloc_array(size_t n, size_t size, gfp_t flags) return NULL; return __vmalloc(bytes, flags); } -EXPORT_SYMBOL(__vmalloc_array); +EXPORT_SYMBOL(__vmalloc_array_noprof); /** * vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ -void *vmalloc_array(size_t n, size_t size) +void *vmalloc_array_noprof(size_t n, size_t size) { return __vmalloc_array(n, size, GFP_KERNEL); } -EXPORT_SYMBOL(vmalloc_array); +EXPORT_SYMBOL(vmalloc_array_noprof); /** * __vcalloc - allocate and zero memory for a virtually contiguous array. @@ -747,22 +747,22 @@ EXPORT_SYMBOL(vmalloc_array); * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -void *__vcalloc(size_t n, size_t size, gfp_t flags) +void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) { return __vmalloc_array(n, size, flags | __GFP_ZERO); } -EXPORT_SYMBOL(__vcalloc); +EXPORT_SYMBOL(__vcalloc_noprof); /** * vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ -void *vcalloc(size_t n, size_t size) +void *vcalloc_noprof(size_t n, size_t size) { return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO); } -EXPORT_SYMBOL(vcalloc); +EXPORT_SYMBOL(vcalloc_noprof); struct anon_vma *folio_anon_vma(struct folio *folio) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 68fa001648cc1c..6641be0ca80b4d 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -42,6 +42,7 @@ #include <linux/sched/mm.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> +#include <linux/page_owner.h> #define CREATE_TRACE_POINTS #include <trace/events/vmalloc.h> @@ -96,6 +97,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, { pte_t *pte; u64 pfn; + struct page *page; unsigned long size = PAGE_SIZE; pfn = phys_addr >> PAGE_SHIFT; @@ -103,7 +105,13 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (!pte) return -ENOMEM; do { - BUG_ON(!pte_none(ptep_get(pte))); + if (!pte_none(ptep_get(pte))) { + if (pfn_valid(pfn)) { + page = pfn_to_page(pfn); + dump_page(page, "remapping already mapped page"); + } + BUG(); + } #ifdef CONFIG_HUGETLB_PAGE size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift); @@ -1926,15 +1934,25 @@ node_alloc(unsigned long size, unsigned long align, return va; } +static inline void setup_vmalloc_vm(struct vm_struct *vm, + struct vmap_area *va, unsigned long flags, const void *caller) +{ + vm->flags = flags; + vm->addr = (void *)va->va_start; + vm->size = va->va_end - va->va_start; + vm->caller = caller; + va->vm = vm; +} + /* * Allocate a region of KVA of the specified size and alignment, within the - * vstart and vend. + * vstart and vend. If vm is passed in, the two will also be bound. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask, - unsigned long va_flags) + unsigned long va_flags, struct vm_struct *vm) { struct vmap_node *vn; struct vmap_area *va; @@ -1997,6 +2015,12 @@ retry: va->vm = NULL; va->flags = (va_flags | vn_id); + if (vm) { + vm->addr = (void *)va->va_start; + vm->size = va->va_end - va->va_start; + va->vm = vm; + } + vn = addr_to_node(va->va_start); spin_lock(&vn->busy.lock); @@ -2574,7 +2598,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask, - VMAP_RAM|VMAP_BLOCK); + VMAP_RAM|VMAP_BLOCK, NULL); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); @@ -2710,7 +2734,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) * get_order(0) returns funny result. Just warn and terminate * early. */ - return NULL; + return ERR_PTR(-EINVAL); } order = get_order(size); @@ -2931,7 +2955,8 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, - node, GFP_KERNEL, VMAP_RAM); + node, GFP_KERNEL, VMAP_RAM, + NULL); if (IS_ERR(va)) return NULL; @@ -3034,26 +3059,6 @@ void __init vm_area_register_early(struct vm_struct *vm, size_t align) kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } -static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, - struct vmap_area *va, unsigned long flags, const void *caller) -{ - vm->flags = flags; - vm->addr = (void *)va->va_start; - vm->size = va->va_end - va->va_start; - vm->caller = caller; - va->vm = vm; -} - -static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, const void *caller) -{ - struct vmap_node *vn = addr_to_node(va->va_start); - - spin_lock(&vn->busy.lock); - setup_vmalloc_vm_locked(vm, va, flags, caller); - spin_unlock(&vn->busy.lock); -} - static void clear_vm_uninitialized_flag(struct vm_struct *vm) { /* @@ -3090,14 +3095,15 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE; - va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0); + area->flags = flags; + area->caller = caller; + + va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { kfree(area); return NULL; } - setup_vmalloc_vm(area, va, flags, caller); - /* * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a * best-effort approach, as they can be mapped outside of vmalloc code. @@ -3523,12 +3529,12 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * but mempolicy wants to alloc memory by interleaving. */ if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) - nr = alloc_pages_bulk_array_mempolicy(bulk_gfp, + nr = alloc_pages_bulk_array_mempolicy_noprof(bulk_gfp, nr_pages_request, pages + nr_allocated); else - nr = alloc_pages_bulk_array_node(bulk_gfp, nid, + nr = alloc_pages_bulk_array_node_noprof(bulk_gfp, nid, nr_pages_request, pages + nr_allocated); @@ -3558,9 +3564,9 @@ vm_area_alloc_pages(gfp_t gfp, int nid, break; if (nid == NUMA_NO_NODE) - page = alloc_pages(alloc_gfp, order); + page = alloc_pages_noprof(alloc_gfp, order); else - page = alloc_pages_node(nid, alloc_gfp, order); + page = alloc_pages_node_noprof(nid, alloc_gfp, order); if (unlikely(!page)) { if (!nofail) break; @@ -3617,10 +3623,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { - area->pages = __vmalloc_node(array_size, 1, nested_gfp, node, + area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node, area->caller); } else { - area->pages = kmalloc_node(array_size, nested_gfp, node); + area->pages = kmalloc_node_noprof(array_size, nested_gfp, node); } if (!area->pages) { @@ -3730,7 +3736,7 @@ fail: * * Return: the address of the area or %NULL on failure */ -void *__vmalloc_node_range(unsigned long size, unsigned long align, +void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) @@ -3877,10 +3883,10 @@ fail: * * Return: pointer to the allocated memory or %NULL on error */ -void *__vmalloc_node(unsigned long size, unsigned long align, +void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { - return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, + return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, 0, node, caller); } /* @@ -3889,15 +3895,15 @@ void *__vmalloc_node(unsigned long size, unsigned long align, * than that. */ #ifdef CONFIG_TEST_VMALLOC_MODULE -EXPORT_SYMBOL_GPL(__vmalloc_node); +EXPORT_SYMBOL_GPL(__vmalloc_node_noprof); #endif -void *__vmalloc(unsigned long size, gfp_t gfp_mask) +void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) { - return __vmalloc_node(size, 1, gfp_mask, NUMA_NO_NODE, + return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(__vmalloc); +EXPORT_SYMBOL(__vmalloc_noprof); /** * vmalloc - allocate virtually contiguous memory @@ -3911,12 +3917,12 @@ EXPORT_SYMBOL(__vmalloc); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc(unsigned long size) +void *vmalloc_noprof(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL, NUMA_NO_NODE, + return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc); +EXPORT_SYMBOL(vmalloc_noprof); /** * vmalloc_huge - allocate virtually contiguous memory, allow huge pages @@ -3930,13 +3936,13 @@ EXPORT_SYMBOL(vmalloc); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) +void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) { - return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL_GPL(vmalloc_huge); +EXPORT_SYMBOL_GPL(vmalloc_huge_noprof); /** * vzalloc - allocate virtually contiguous memory with zero fill @@ -3951,12 +3957,12 @@ EXPORT_SYMBOL_GPL(vmalloc_huge); * * Return: pointer to the allocated memory or %NULL on error */ -void *vzalloc(unsigned long size) +void *vzalloc_noprof(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, + return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vzalloc); +EXPORT_SYMBOL(vzalloc_noprof); /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace @@ -3967,14 +3973,14 @@ EXPORT_SYMBOL(vzalloc); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_user(unsigned long size) +void *vmalloc_user_noprof(unsigned long size) { - return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, + return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_user); +EXPORT_SYMBOL(vmalloc_user_noprof); /** * vmalloc_node - allocate memory on a specific node @@ -3989,12 +3995,12 @@ EXPORT_SYMBOL(vmalloc_user); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_node(unsigned long size, int node) +void *vmalloc_node_noprof(unsigned long size, int node) { - return __vmalloc_node(size, 1, GFP_KERNEL, node, + return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_node); +EXPORT_SYMBOL(vmalloc_node_noprof); /** * vzalloc_node - allocate memory on a specific node with zero fill @@ -4007,12 +4013,12 @@ EXPORT_SYMBOL(vmalloc_node); * * Return: pointer to the allocated memory or %NULL on error */ -void *vzalloc_node(unsigned long size, int node) +void *vzalloc_node_noprof(unsigned long size, int node) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, node, + return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node, __builtin_return_address(0)); } -EXPORT_SYMBOL(vzalloc_node); +EXPORT_SYMBOL(vzalloc_node_noprof); #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) @@ -4035,12 +4041,12 @@ EXPORT_SYMBOL(vzalloc_node); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_32(unsigned long size) +void *vmalloc_32_noprof(unsigned long size) { - return __vmalloc_node(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, + return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_32); +EXPORT_SYMBOL(vmalloc_32_noprof); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory @@ -4051,14 +4057,14 @@ EXPORT_SYMBOL(vmalloc_32); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_32_user(unsigned long size) +void *vmalloc_32_user_noprof(unsigned long size) { - return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, + return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_32_user); +EXPORT_SYMBOL(vmalloc_32_user_noprof); /* * Atomically zero bytes in the iterator. @@ -4672,7 +4678,7 @@ retry: spin_lock(&vn->busy.lock); insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head); - setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, + setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); spin_unlock(&vn->busy.lock); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 3ef654addd44c2..49bd944239613d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -92,6 +92,11 @@ struct scan_control { unsigned long anon_cost; unsigned long file_cost; +#ifdef CONFIG_MEMCG + /* Swappiness value for proactive reclaim. Always use sc_swappiness()! */ + int *proactive_swappiness; +#endif + /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 @@ -189,7 +194,7 @@ struct scan_control { #endif /* - * From 0 .. 200. Higher means more swappy. + * From 0 .. MAX_SWAPPINESS. Higher means more swappy. */ int vm_swappiness = 60; @@ -233,6 +238,13 @@ static bool writeback_throttling_sane(struct scan_control *sc) #endif return false; } + +static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) +{ + if (sc->proactive && sc->proactive_swappiness) + return *sc->proactive_swappiness; + return mem_cgroup_swappiness(memcg); +} #else static bool cgroup_reclaim(struct scan_control *sc) { @@ -248,6 +260,11 @@ static bool writeback_throttling_sane(struct scan_control *sc) { return true; } + +static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg) +{ + return READ_ONCE(vm_swappiness); +} #endif static void set_task_reclaim_state(struct task_struct *task, @@ -967,7 +984,8 @@ static unsigned int demote_folio_list(struct list_head *demote_folios, .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT, .nid = target_nid, - .nmask = &allowed_mask + .nmask = &allowed_mask, + .reason = MR_DEMOTION, }; if (list_empty(demote_folios)) @@ -1205,25 +1223,28 @@ retry: if (!can_split_folio(folio, NULL)) goto activate_locked; /* - * Split folios without a PMD map right - * away. Chances are some or all of the - * tail pages can be freed without IO. + * Split partially mapped folios right away. + * We can free the unmapped pages without IO. */ - if (!folio_entire_mapcount(folio) && - split_folio_to_list(folio, - folio_list)) + if (data_race(!list_empty(&folio->_deferred_list)) && + split_folio_to_list(folio, folio_list)) goto activate_locked; } if (!add_to_swap(folio)) { + int __maybe_unused order = folio_order(folio); + if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ - if (split_folio_to_list(folio, - folio_list)) + if (split_folio_to_list(folio, folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); - count_vm_event(THP_SWPOUT_FALLBACK); + if (nr_pages >= HPAGE_PMD_NR) { + count_memcg_folio_events(folio, + THP_SWPOUT_FALLBACK, 1); + count_vm_event(THP_SWPOUT_FALLBACK); + } + count_mthp_stat(order, MTHP_STAT_ANON_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) goto activate_locked_split; @@ -1256,6 +1277,20 @@ retry: if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; + /* + * Without TTU_SYNC, try_to_unmap will only begin to + * hold PTL from the first present PTE within a large + * folio. Some initial PTEs might be skipped due to + * races with parallel PTE writes in which PTEs can be + * cleared temporarily before being written new present + * values. This will lead to a large folio is still + * mapped while some subpages have been partially + * unmapped after try_to_unmap; TTU_SYNC helps + * try_to_unmap acquire PTL from the first PTE, + * eliminating the influence of temporary PTE values. + */ + if (folio_test_large(folio) && list_empty(&folio->_deferred_list)) + flags |= TTU_SYNC; try_to_unmap(folio, flags); if (folio_mapped(folio)) { @@ -2337,7 +2372,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; - int swappiness = mem_cgroup_swappiness(memcg); + int swappiness = sc_swappiness(sc, memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; @@ -2413,7 +2448,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; - fp = (200 - swappiness) * (total_cost + 1); + fp = (MAX_SWAPPINESS - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[0] = ap; @@ -2618,7 +2653,7 @@ static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; - return mem_cgroup_swappiness(memcg); + return sc_swappiness(sc, memcg); } static int get_nr_gens(struct lruvec *lruvec, int type) @@ -4433,7 +4468,7 @@ static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx { int type, tier; struct ctrl_pos sp, pv; - int gain[ANON_AND_FILE] = { swappiness, 200 - swappiness }; + int gain[ANON_AND_FILE] = { swappiness, MAX_SWAPPINESS - swappiness }; /* * Compare the first tier of anon with that of file to determine which @@ -4480,7 +4515,7 @@ static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int sw type = LRU_GEN_ANON; else if (swappiness == 1) type = LRU_GEN_FILE; - else if (swappiness == 200) + else if (swappiness == MAX_SWAPPINESS) type = LRU_GEN_ANON; else if (!(sc->gfp_mask & __GFP_IO)) type = LRU_GEN_FILE; @@ -5414,9 +5449,9 @@ static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, lruvec = get_lruvec(memcg, nid); - if (swappiness < 0) + if (swappiness < MIN_SWAPPINESS) swappiness = get_swappiness(lruvec, sc); - else if (swappiness > 200) + else if (swappiness > MAX_SWAPPINESS) goto done; switch (cmd) { @@ -6499,12 +6534,14 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options) + unsigned int reclaim_options, + int *swappiness) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), + .proactive_swappiness = swappiness, .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, diff --git a/mm/z3fold.c b/mm/z3fold.c index 7ab05621052dc5..2ebfed32871bf3 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -1237,12 +1237,12 @@ static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle) } /** - * z3fold_get_pool_size() - gets the z3fold pool size in pages + * z3fold_get_pool_pages() - gets the z3fold pool size in pages * @pool: pool whose size is being queried * * Returns: size in pages of the given pool. */ -static u64 z3fold_get_pool_size(struct z3fold_pool *pool) +static u64 z3fold_get_pool_pages(struct z3fold_pool *pool) { return atomic64_read(&pool->pages_nr); } @@ -1402,9 +1402,9 @@ static void z3fold_zpool_unmap(void *pool, unsigned long handle) z3fold_unmap(pool, handle); } -static u64 z3fold_zpool_total_size(void *pool) +static u64 z3fold_zpool_total_pages(void *pool) { - return z3fold_get_pool_size(pool) * PAGE_SIZE; + return z3fold_get_pool_pages(pool); } static struct zpool_driver z3fold_zpool_driver = { @@ -1417,7 +1417,7 @@ static struct zpool_driver z3fold_zpool_driver = { .free = z3fold_zpool_free, .map = z3fold_zpool_map, .unmap = z3fold_zpool_unmap, - .total_size = z3fold_zpool_total_size, + .total_pages = z3fold_zpool_total_pages, }; MODULE_ALIAS("zpool-z3fold"); diff --git a/mm/zbud.c b/mm/zbud.c index 2190cc1f37b3dc..e9836fff943811 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -365,13 +365,13 @@ static void zbud_unmap(struct zbud_pool *pool, unsigned long handle) } /** - * zbud_get_pool_size() - gets the zbud pool size in pages + * zbud_get_pool_pages() - gets the zbud pool size in pages * @pool: pool whose size is being queried * * Returns: size in pages of the given pool. The pool lock need not be * taken to access pages_nr. */ -static u64 zbud_get_pool_size(struct zbud_pool *pool) +static u64 zbud_get_pool_pages(struct zbud_pool *pool) { return pool->pages_nr; } @@ -410,9 +410,9 @@ static void zbud_zpool_unmap(void *pool, unsigned long handle) zbud_unmap(pool, handle); } -static u64 zbud_zpool_total_size(void *pool) +static u64 zbud_zpool_total_pages(void *pool) { - return zbud_get_pool_size(pool) * PAGE_SIZE; + return zbud_get_pool_pages(pool); } static struct zpool_driver zbud_zpool_driver = { @@ -425,7 +425,7 @@ static struct zpool_driver zbud_zpool_driver = { .free = zbud_zpool_free, .map = zbud_zpool_map, .unmap = zbud_zpool_unmap, - .total_size = zbud_zpool_total_size, + .total_pages = zbud_zpool_total_pages, }; MODULE_ALIAS("zpool-zbud"); diff --git a/mm/zpool.c b/mm/zpool.c index 846410479c2f41..b9fda1fa857da7 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -321,16 +321,16 @@ void zpool_unmap_handle(struct zpool *zpool, unsigned long handle) } /** - * zpool_get_total_size() - The total size of the pool + * zpool_get_total_pages() - The total size of the pool * @zpool: The zpool to check * - * This returns the total size in bytes of the pool. + * This returns the total size in pages of the pool. * - * Returns: Total size of the zpool in bytes. + * Returns: Total size of the zpool in pages. */ -u64 zpool_get_total_size(struct zpool *zpool) +u64 zpool_get_total_pages(struct zpool *zpool) { - return zpool->driver->total_size(zpool->pool); + return zpool->driver->total_pages(zpool->pool); } /** diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 7d7cb3eaabe029..b42d3545ca856f 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -399,9 +399,9 @@ static void zs_zpool_unmap(void *pool, unsigned long handle) zs_unmap_object(pool, handle); } -static u64 zs_zpool_total_size(void *pool) +static u64 zs_zpool_total_pages(void *pool) { - return zs_get_total_pages(pool) << PAGE_SHIFT; + return zs_get_total_pages(pool); } static struct zpool_driver zs_zpool_driver = { @@ -414,7 +414,7 @@ static struct zpool_driver zs_zpool_driver = { .free = zs_zpool_free, .map = zs_zpool_map, .unmap = zs_zpool_unmap, - .total_size = zs_zpool_total_size, + .total_pages = zs_zpool_total_pages, }; MODULE_ALIAS("zpool-zsmalloc"); diff --git a/mm/zswap.c b/mm/zswap.c index caed028945b046..a50e2986cd2fab 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -20,7 +20,6 @@ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> -#include <linux/rbtree.h> #include <linux/swap.h> #include <linux/crypto.h> #include <linux/scatterlist.h> @@ -43,8 +42,6 @@ /********************************* * statistics **********************************/ -/* Total bytes used by the compressed storage */ -u64 zswap_pool_total_size; /* The number of compressed pages currently stored in zswap */ atomic_t zswap_stored_pages = ATOMIC_INIT(0); /* The number of same-value filled pages currently stored in zswap */ @@ -126,19 +123,6 @@ static unsigned int zswap_accept_thr_percent = 90; /* of max pool size */ module_param_named(accept_threshold_percent, zswap_accept_thr_percent, uint, 0644); -/* - * Enable/disable handling same-value filled pages (enabled by default). - * If disabled every page is considered non-same-value filled. - */ -static bool zswap_same_filled_pages_enabled = true; -module_param_named(same_filled_pages_enabled, zswap_same_filled_pages_enabled, - bool, 0644); - -/* Enable/disable handling non-same-value filled pages (enabled by default) */ -static bool zswap_non_same_filled_pages_enabled = true; -module_param_named(non_same_filled_pages_enabled, zswap_non_same_filled_pages_enabled, - bool, 0644); - /* Number of zpools in zswap_pool (empirically determined for scalability) */ #define ZSWAP_NR_ZPOOLS 32 @@ -183,8 +167,6 @@ struct zswap_pool { /* Global LRU lists shared by all zswap pools. */ static struct list_lru zswap_list_lru; -/* counter of pages stored in all zswap pools. */ -static atomic_t zswap_nr_stored = ATOMIC_INIT(0); /* The lock protects zswap_next_shrink updates. */ static DEFINE_SPINLOCK(zswap_shrink_lock); @@ -198,7 +180,6 @@ static struct shrinker *zswap_shrinker; * This structure contains the metadata for tracking a single compressed * page within zswap. * - * rbnode - links the entry into red-black tree for the appropriate swap type * swpentry - associated swap entry, the offset indexes into the red-black tree * length - the length in bytes of the compressed page data. Needed during * decompression. For a same value filled page length is 0, and both @@ -210,7 +191,6 @@ static struct shrinker *zswap_shrinker; * lru - handle to the pool's lru used to evict pages. */ struct zswap_entry { - struct rb_node rbnode; swp_entry_t swpentry; unsigned int length; struct zswap_pool *pool; @@ -222,12 +202,7 @@ struct zswap_entry { struct list_head lru; }; -struct zswap_tree { - struct rb_root rbroot; - spinlock_t lock; -}; - -static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; +static struct xarray *zswap_trees[MAX_SWAPFILES]; static unsigned int nr_zswap_trees[MAX_SWAPFILES]; /* RCU-protected iteration */ @@ -255,7 +230,7 @@ static bool zswap_has_pool; * helpers and fwd declarations **********************************/ -static inline struct zswap_tree *swap_zswap_tree(swp_entry_t swp) +static inline struct xarray *swap_zswap_tree(swp_entry_t swp) { return &zswap_trees[swp_type(swp)][swp_offset(swp) >> SWAP_ADDRESS_SPACE_SHIFT]; @@ -265,45 +240,6 @@ static inline struct zswap_tree *swap_zswap_tree(swp_entry_t swp) pr_debug("%s pool %s/%s\n", msg, (p)->tfm_name, \ zpool_get_type((p)->zpools[0])) -static bool zswap_is_full(void) -{ - return totalram_pages() * zswap_max_pool_percent / 100 < - DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE); -} - -static bool zswap_can_accept(void) -{ - return totalram_pages() * zswap_accept_thr_percent / 100 * - zswap_max_pool_percent / 100 > - DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE); -} - -static u64 get_zswap_pool_size(struct zswap_pool *pool) -{ - u64 pool_size = 0; - int i; - - for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) - pool_size += zpool_get_total_size(pool->zpools[i]); - - return pool_size; -} - -static void zswap_update_total_size(void) -{ - struct zswap_pool *pool; - u64 total = 0; - - rcu_read_lock(); - - list_for_each_entry_rcu(pool, &zswap_pools, list) - total += get_zswap_pool_size(pool); - - rcu_read_unlock(); - - zswap_pool_total_size = total; -} - /********************************* * pool functions **********************************/ @@ -541,6 +477,48 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) return NULL; } +static unsigned long zswap_max_pages(void) +{ + return totalram_pages() * zswap_max_pool_percent / 100; +} + +static unsigned long zswap_accept_thr_pages(void) +{ + return zswap_max_pages() * zswap_accept_thr_percent / 100; +} + +unsigned long zswap_total_pages(void) +{ + struct zswap_pool *pool; + unsigned long total = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(pool, &zswap_pools, list) { + int i; + + for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) + total += zpool_get_total_pages(pool->zpools[i]); + } + rcu_read_unlock(); + + return total; +} + +static bool zswap_check_limits(void) +{ + unsigned long cur_pages = zswap_total_pages(); + unsigned long max_pages = zswap_max_pages(); + + if (cur_pages >= max_pages) { + zswap_pool_limit_hit++; + zswap_pool_reached_full = true; + } else if (zswap_pool_reached_full && + cur_pages <= zswap_accept_thr_pages()) { + zswap_pool_reached_full = false; + } + return zswap_pool_reached_full; +} + /********************************* * param callbacks **********************************/ @@ -807,63 +785,6 @@ void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) } /********************************* -* rbtree functions -**********************************/ -static struct zswap_entry *zswap_rb_search(struct rb_root *root, pgoff_t offset) -{ - struct rb_node *node = root->rb_node; - struct zswap_entry *entry; - pgoff_t entry_offset; - - while (node) { - entry = rb_entry(node, struct zswap_entry, rbnode); - entry_offset = swp_offset(entry->swpentry); - if (entry_offset > offset) - node = node->rb_left; - else if (entry_offset < offset) - node = node->rb_right; - else - return entry; - } - return NULL; -} - -/* - * In the case that a entry with the same offset is found, a pointer to - * the existing entry is stored in dupentry and the function returns -EEXIST - */ -static int zswap_rb_insert(struct rb_root *root, struct zswap_entry *entry, - struct zswap_entry **dupentry) -{ - struct rb_node **link = &root->rb_node, *parent = NULL; - struct zswap_entry *myentry; - pgoff_t myentry_offset, entry_offset = swp_offset(entry->swpentry); - - while (*link) { - parent = *link; - myentry = rb_entry(parent, struct zswap_entry, rbnode); - myentry_offset = swp_offset(myentry->swpentry); - if (myentry_offset > entry_offset) - link = &(*link)->rb_left; - else if (myentry_offset < entry_offset) - link = &(*link)->rb_right; - else { - *dupentry = myentry; - return -EEXIST; - } - } - rb_link_node(&entry->rbnode, parent, link); - rb_insert_color(&entry->rbnode, root); - return 0; -} - -static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry) -{ - rb_erase(&entry->rbnode, root); - RB_CLEAR_NODE(&entry->rbnode); -} - -/********************************* * zswap entry functions **********************************/ static struct kmem_cache *zswap_entry_cache; @@ -874,7 +795,6 @@ static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp, int nid) entry = kmem_cache_alloc_node(zswap_entry_cache, gfp, nid); if (!entry) return NULL; - RB_CLEAR_NODE(&entry->rbnode); return entry; } @@ -885,12 +805,7 @@ static void zswap_entry_cache_free(struct zswap_entry *entry) static struct zpool *zswap_find_zpool(struct zswap_entry *entry) { - int i = 0; - - if (ZSWAP_NR_ZPOOLS > 1) - i = hash_ptr(entry, ilog2(ZSWAP_NR_ZPOOLS)); - - return entry->pool->zpools[i]; + return entry->pool->zpools[hash_ptr(entry, ilog2(ZSWAP_NR_ZPOOLS))]; } /* @@ -904,7 +819,6 @@ static void zswap_entry_free(struct zswap_entry *entry) else { zswap_lru_del(&zswap_list_lru, entry); zpool_free(zswap_find_zpool(entry), entry->handle); - atomic_dec(&zswap_nr_stored); zswap_pool_put(entry->pool); } if (entry->objcg) { @@ -913,18 +827,6 @@ static void zswap_entry_free(struct zswap_entry *entry) } zswap_entry_cache_free(entry); atomic_dec(&zswap_stored_pages); - zswap_update_total_size(); -} - -/* - * The caller hold the tree lock and search the entry from the tree, - * so it must be on the tree, remove it from the tree and free it. - */ -static void zswap_invalidate_entry(struct zswap_tree *tree, - struct zswap_entry *entry) -{ - zswap_rb_erase(&tree->rbroot, entry); - zswap_entry_free(entry); } /********************************* @@ -1126,7 +1028,8 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page) static int zswap_writeback_entry(struct zswap_entry *entry, swp_entry_t swpentry) { - struct zswap_tree *tree; + struct xarray *tree; + pgoff_t offset = swp_offset(swpentry); struct folio *folio; struct mempolicy *mpol; bool folio_was_allocated; @@ -1163,19 +1066,13 @@ static int zswap_writeback_entry(struct zswap_entry *entry, * be dereferenced. */ tree = swap_zswap_tree(swpentry); - spin_lock(&tree->lock); - if (zswap_rb_search(&tree->rbroot, swp_offset(swpentry)) != entry) { - spin_unlock(&tree->lock); + if (entry != xa_cmpxchg(tree, offset, entry, NULL, GFP_KERNEL)) { delete_from_swap_cache(folio); folio_unlock(folio); folio_put(folio); return -ENOMEM; } - /* Safe to deref entry after the entry is verified above. */ - zswap_rb_erase(&tree->rbroot, entry); - spin_unlock(&tree->lock); - zswap_decompress(entry, &folio->page); count_vm_event(ZSWPWB); @@ -1331,15 +1228,22 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, if (!gfp_has_io_fs(sc->gfp_mask)) return 0; -#ifdef CONFIG_MEMCG_KMEM - mem_cgroup_flush_stats(memcg); - nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; - nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); -#else - /* use pool stats instead of memcg stats */ - nr_backing = zswap_pool_total_size >> PAGE_SHIFT; - nr_stored = atomic_read(&zswap_nr_stored); -#endif + /* + * For memcg, use the cgroup-wide ZSWAP stats since we don't + * have them per-node and thus per-lruvec. Careful if memcg is + * runtime-disabled: we can get sc->memcg == NULL, which is ok + * for the lruvec, but not for memcg_page_state(). + * + * Without memcg, use the zswap pool-wide metrics. + */ + if (!mem_cgroup_disabled()) { + mem_cgroup_flush_stats(memcg); + nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT; + nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); + } else { + nr_backing = zswap_total_pages(); + nr_stored = atomic_read(&zswap_stored_pages); + } if (!nr_stored) return 0; @@ -1358,6 +1262,11 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, * This ensures that the better zswap compresses memory, the fewer * pages we will evict to swap (as it will otherwise incur IO for * relatively small memory saving). + * + * The memory saving factor calculated here takes same-filled pages into + * account, but those are not freeable since they almost occupy no + * space. Hence, we may scale nr_freeable down a little bit more than we + * should if we have a lot of same-filled pages. */ return mult_frac(nr_freeable, nr_backing, nr_stored); } @@ -1405,6 +1314,10 @@ static void shrink_worker(struct work_struct *w) { struct mem_cgroup *memcg; int ret, failures = 0; + unsigned long thr; + + /* Reclaim down to the accept threshold */ + thr = zswap_accept_thr_pages(); /* global reclaim will select cgroup in a round-robin fashion. */ do { @@ -1452,32 +1365,37 @@ static void shrink_worker(struct work_struct *w) break; if (ret && ++failures == MAX_RECLAIM_RETRIES) break; - resched: cond_resched(); - } while (!zswap_can_accept()); + } while (zswap_total_pages() > thr); } -static int zswap_is_page_same_filled(void *ptr, unsigned long *value) +/********************************* +* same-filled functions +**********************************/ +static bool zswap_is_folio_same_filled(struct folio *folio, unsigned long *value) { unsigned long *page; unsigned long val; unsigned int pos, last_pos = PAGE_SIZE / sizeof(*page) - 1; + bool ret = false; - page = (unsigned long *)ptr; + page = kmap_local_folio(folio, 0); val = page[0]; if (val != page[last_pos]) - return 0; + goto out; for (pos = 1; pos < last_pos; pos++) { if (val != page[pos]) - return 0; + goto out; } *value = val; - - return 1; + ret = true; +out: + kunmap_local(page); + return ret; } static void zswap_fill_page(void *ptr, unsigned long value) @@ -1488,14 +1406,18 @@ static void zswap_fill_page(void *ptr, unsigned long value) memset_l(page, value, PAGE_SIZE / sizeof(unsigned long)); } +/********************************* +* main API +**********************************/ bool zswap_store(struct folio *folio) { swp_entry_t swp = folio->swap; pgoff_t offset = swp_offset(swp); - struct zswap_tree *tree = swap_zswap_tree(swp); - struct zswap_entry *entry, *dupentry; + struct xarray *tree = swap_zswap_tree(swp); + struct zswap_entry *entry, *old; struct obj_cgroup *objcg = NULL; struct mem_cgroup *memcg = NULL; + unsigned long value; VM_WARN_ON_ONCE(!folio_test_locked(folio)); VM_WARN_ON_ONCE(!folio_test_swapcache(folio)); @@ -1507,6 +1429,7 @@ bool zswap_store(struct folio *folio) if (!zswap_enabled) goto check_old; + /* Check cgroup limits */ objcg = get_obj_cgroup_from_folio(folio); if (objcg && !obj_cgroup_may_zswap(objcg)) { memcg = get_mem_cgroup_from_objcg(objcg); @@ -1517,19 +1440,8 @@ bool zswap_store(struct folio *folio) mem_cgroup_put(memcg); } - /* reclaim space if needed */ - if (zswap_is_full()) { - zswap_pool_limit_hit++; - zswap_pool_reached_full = true; - goto shrink; - } - - if (zswap_pool_reached_full) { - if (!zswap_can_accept()) - goto shrink; - else - zswap_pool_reached_full = false; - } + if (zswap_check_limits()) + goto reject; /* allocate entry */ entry = zswap_entry_cache_alloc(GFP_KERNEL, folio_nid(folio)); @@ -1538,24 +1450,13 @@ bool zswap_store(struct folio *folio) goto reject; } - if (zswap_same_filled_pages_enabled) { - unsigned long value; - u8 *src; - - src = kmap_local_folio(folio, 0); - if (zswap_is_page_same_filled(src, &value)) { - kunmap_local(src); - entry->length = 0; - entry->value = value; - atomic_inc(&zswap_same_filled_pages); - goto insert_entry; - } - kunmap_local(src); + if (zswap_is_folio_same_filled(folio, &value)) { + entry->length = 0; + entry->value = value; + atomic_inc(&zswap_same_filled_pages); + goto store_entry; } - if (!zswap_non_same_filled_pages_enabled) - goto freepage; - /* if entry is successfully added, it keeps the reference */ entry->pool = zswap_pool_current_get(); if (!entry->pool) @@ -1573,62 +1474,77 @@ bool zswap_store(struct folio *folio) if (!zswap_compress(folio, entry)) goto put_pool; -insert_entry: +store_entry: entry->swpentry = swp; entry->objcg = objcg; + + old = xa_store(tree, offset, entry, GFP_KERNEL); + if (xa_is_err(old)) { + int err = xa_err(old); + + WARN_ONCE(err != -ENOMEM, "unexpected xarray error: %d\n", err); + zswap_reject_alloc_fail++; + goto store_failed; + } + + /* + * We may have had an existing entry that became stale when + * the folio was redirtied and now the new version is being + * swapped out. Get rid of the old. + */ + if (old) + zswap_entry_free(old); + if (objcg) { obj_cgroup_charge_zswap(objcg, entry->length); - /* Account before objcg ref is moved to tree */ count_objcg_event(objcg, ZSWPOUT); } - /* map */ - spin_lock(&tree->lock); /* - * The folio may have been dirtied again, invalidate the - * possibly stale entry before inserting the new entry. + * We finish initializing the entry while it's already in xarray. + * This is safe because: + * + * 1. Concurrent stores and invalidations are excluded by folio lock. + * + * 2. Writeback is excluded by the entry not being on the LRU yet. + * The publishing order matters to prevent writeback from seeing + * an incoherent entry. */ - if (zswap_rb_insert(&tree->rbroot, entry, &dupentry) == -EEXIST) { - zswap_invalidate_entry(tree, dupentry); - WARN_ON(zswap_rb_insert(&tree->rbroot, entry, &dupentry)); - } if (entry->length) { INIT_LIST_HEAD(&entry->lru); zswap_lru_add(&zswap_list_lru, entry); - atomic_inc(&zswap_nr_stored); } - spin_unlock(&tree->lock); /* update stats */ atomic_inc(&zswap_stored_pages); - zswap_update_total_size(); count_vm_event(ZSWPOUT); return true; +store_failed: + if (!entry->length) + atomic_dec(&zswap_same_filled_pages); + else { + zpool_free(zswap_find_zpool(entry), entry->handle); put_pool: - zswap_pool_put(entry->pool); + zswap_pool_put(entry->pool); + } freepage: zswap_entry_cache_free(entry); reject: - if (objcg) - obj_cgroup_put(objcg); + obj_cgroup_put(objcg); + if (zswap_pool_reached_full) + queue_work(shrink_wq, &zswap_shrink_work); check_old: /* * If the zswap store fails or zswap is disabled, we must invalidate the * possibly stale entry which was previously stored at this offset. * Otherwise, writeback could overwrite the new data in the swapfile. */ - spin_lock(&tree->lock); - entry = zswap_rb_search(&tree->rbroot, offset); + entry = xa_erase(tree, offset); if (entry) - zswap_invalidate_entry(tree, entry); - spin_unlock(&tree->lock); + zswap_entry_free(entry); return false; - -shrink: - queue_work(shrink_wq, &zswap_shrink_work); - goto reject; } bool zswap_load(struct folio *folio) @@ -1637,18 +1553,12 @@ bool zswap_load(struct folio *folio) pgoff_t offset = swp_offset(swp); struct page *page = &folio->page; bool swapcache = folio_test_swapcache(folio); - struct zswap_tree *tree = swap_zswap_tree(swp); + struct xarray *tree = swap_zswap_tree(swp); struct zswap_entry *entry; u8 *dst; VM_WARN_ON_ONCE(!folio_test_locked(folio)); - spin_lock(&tree->lock); - entry = zswap_rb_search(&tree->rbroot, offset); - if (!entry) { - spin_unlock(&tree->lock); - return false; - } /* * When reading into the swapcache, invalidate our entry. The * swapcache can be the authoritative owner of the page and @@ -1662,8 +1572,12 @@ bool zswap_load(struct folio *folio) * the fault fails. We remain the primary owner of the entry.) */ if (swapcache) - zswap_rb_erase(&tree->rbroot, entry); - spin_unlock(&tree->lock); + entry = xa_erase(tree, offset); + else + entry = xa_load(tree, offset); + + if (!entry) + return false; if (entry->length) zswap_decompress(entry, page); @@ -1688,19 +1602,17 @@ bool zswap_load(struct folio *folio) void zswap_invalidate(swp_entry_t swp) { pgoff_t offset = swp_offset(swp); - struct zswap_tree *tree = swap_zswap_tree(swp); + struct xarray *tree = swap_zswap_tree(swp); struct zswap_entry *entry; - spin_lock(&tree->lock); - entry = zswap_rb_search(&tree->rbroot, offset); + entry = xa_erase(tree, offset); if (entry) - zswap_invalidate_entry(tree, entry); - spin_unlock(&tree->lock); + zswap_entry_free(entry); } int zswap_swapon(int type, unsigned long nr_pages) { - struct zswap_tree *trees, *tree; + struct xarray *trees, *tree; unsigned int nr, i; nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); @@ -1710,11 +1622,8 @@ int zswap_swapon(int type, unsigned long nr_pages) return -ENOMEM; } - for (i = 0; i < nr; i++) { - tree = trees + i; - tree->rbroot = RB_ROOT; - spin_lock_init(&tree->lock); - } + for (i = 0; i < nr; i++) + xa_init(trees + i); nr_zswap_trees[type] = nr; zswap_trees[type] = trees; @@ -1723,7 +1632,7 @@ int zswap_swapon(int type, unsigned long nr_pages) void zswap_swapoff(int type) { - struct zswap_tree *trees = zswap_trees[type]; + struct xarray *trees = zswap_trees[type]; unsigned int i; if (!trees) @@ -1731,7 +1640,7 @@ void zswap_swapoff(int type) /* try_to_unuse() invalidated all the entries already */ for (i = 0; i < nr_zswap_trees[type]; i++) - WARN_ON_ONCE(!RB_EMPTY_ROOT(&trees[i].rbroot)); + WARN_ON_ONCE(!xa_empty(trees + i)); kvfree(trees); nr_zswap_trees[type] = 0; @@ -1746,6 +1655,13 @@ void zswap_swapoff(int type) static struct dentry *zswap_debugfs_root; +static int debugfs_get_total_size(void *data, u64 *val) +{ + *val = zswap_total_pages() * PAGE_SIZE; + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(total_size_fops, debugfs_get_total_size, NULL, "%llu\n"); + static int zswap_debugfs_init(void) { if (!debugfs_initialized()) @@ -1767,8 +1683,8 @@ static int zswap_debugfs_init(void) zswap_debugfs_root, &zswap_reject_compress_poor); debugfs_create_u64("written_back_pages", 0444, zswap_debugfs_root, &zswap_written_back_pages); - debugfs_create_u64("pool_total_size", 0444, - zswap_debugfs_root, &zswap_pool_total_size); + debugfs_create_file("pool_total_size", 0444, + zswap_debugfs_root, NULL, &total_size_fops); debugfs_create_atomic_t("stored_pages", 0444, zswap_debugfs_root, &zswap_stored_pages); debugfs_create_atomic_t("same_filled_pages", 0444, diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 558e158c98d010..9169efb2f43aa9 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/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3ad74f76983b24..05346250f7195b 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 a8b8cfebe0180c..4a27e4a17a6744 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3218,7 +3218,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, if (key) { set_bit(HCI_CONN_ENCRYPT, &conn->flags); - if (!(hdev->commands[20] & 0x10)) { + if (!read_key_size_capable(hdev)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; } else { cp.handle = cpu_to_le16(conn->handle); @@ -3666,8 +3666,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, * controller really supports it. If it doesn't, assume * the default size (16). */ - if (!(hdev->commands[20] & 0x10) || - test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) { + if (!read_key_size_capable(hdev)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; goto notify; } @@ -6038,7 +6037,7 @@ static void hci_le_conn_update_complete_evt(struct hci_dev *hdev, void *data, static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, bool addr_resolved, - u8 adv_type) + u8 adv_type, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct hci_conn_params *params; @@ -6093,7 +6092,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, conn = hci_connect_le(hdev, addr, addr_type, addr_resolved, BT_SECURITY_LOW, hdev->def_le_autoconnect_timeout, - HCI_ROLE_MASTER); + HCI_ROLE_MASTER, phy, sec_phy); if (!IS_ERR(conn)) { /* If HCI_AUTO_CONN_EXPLICIT is set, conn is already owned * by higher layer that tried to connect, if no then @@ -6128,8 +6127,9 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len, - bool ext_adv, bool ctl_time, u64 instant) + u8 direct_addr_type, u8 phy, u8 sec_phy, s8 rssi, + u8 *data, u8 len, bool ext_adv, bool ctl_time, + u64 instant) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -6217,7 +6217,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * for advertising reports) and is already verified to be RPA above. */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, bdaddr_resolved, - type); + type, phy, sec_phy); if (!ext_adv && conn && type == LE_ADV_IND && len <= max_adv_len(hdev)) { /* Store report for later inclusion by @@ -6363,7 +6363,8 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, void *data, if (info->length <= max_adv_len(hdev)) { rssi = info->data[info->length]; process_adv_report(hdev, info->type, &info->bdaddr, - info->bdaddr_type, NULL, 0, rssi, + info->bdaddr_type, NULL, 0, + HCI_ADV_PHY_1M, 0, rssi, info->data, info->length, false, false, instant); } else { @@ -6448,6 +6449,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &info->bdaddr, info->bdaddr_type, NULL, 0, + info->primary_phy, + info->secondary_phy, info->rssi, info->data, info->length, !(evt_type & LE_EXT_ADV_LEGACY_PDU), false, instant); @@ -6730,8 +6733,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, void *data, process_adv_report(hdev, info->type, &info->bdaddr, info->bdaddr_type, &info->direct_addr, - info->direct_addr_type, info->rssi, NULL, 0, - false, false, instant); + info->direct_addr_type, HCI_ADV_PHY_1M, 0, + info->rssi, NULL, 0, false, false, instant); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c5d8799046ccff..4c707eb64e6f63 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6346,7 +6346,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen = sizeof(*cp); - if (scan_1m(hdev)) { + if (scan_1m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_1M || + conn->le_adv_sec_phy == HCI_ADV_PHY_1M)) { cp->phys |= LE_SCAN_PHY_1M; set_ext_conn_params(conn, p); @@ -6354,7 +6355,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen += sizeof(*p); } - if (scan_2m(hdev)) { + if (scan_2m(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_2M || + conn->le_adv_sec_phy == HCI_ADV_PHY_2M)) { cp->phys |= LE_SCAN_PHY_2M; set_ext_conn_params(conn, p); @@ -6362,7 +6364,8 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, plen += sizeof(*p); } - if (scan_coded(hdev)) { + if (scan_coded(hdev) && (conn->le_adv_phy == HCI_ADV_PHY_CODED || + conn->le_adv_sec_phy == HCI_ADV_PHY_CODED)) { cp->phys |= LE_SCAN_PHY_CODED; set_ext_conn_params(conn, p); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index dc089740879363..84fc70862d78ae 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7018,7 +7018,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) hcon = hci_connect_le(hdev, dst, dst_type, false, chan->sec_level, timeout, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, 0, 0); else hcon = hci_connect_le_scan(hdev, dst, dst_type, chan->sec_level, timeout, diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index e7d810b23082f5..5cc83f906c123f 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -439,7 +439,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; struct l2cap_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -486,7 +487,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mode 0x%2.2x", chan->mode); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *) &opts, len)) err = -EFAULT; @@ -536,7 +537,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = chan->conn->hcon->handle; memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *) &cinfo, len)) err = -EFAULT; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 32ed6e9245a307..965f621ef865ad 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/sco.c b/net/bluetooth/sco.c index 368e026f4d15ca..5d03c5440b06f8 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -964,7 +964,8 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; BT_DBG("sk %p", sk); @@ -986,7 +987,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mtu %u", opts.mtu); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; @@ -1004,7 +1005,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 2cf4fc75626399..f17dbac7d82843 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -667,7 +667,7 @@ void br_ifinfo_notify(int event, const struct net_bridge *br, { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; - return br_info_notify(event, br, port, filter); + br_info_notify(event, br, port, filter); } /* diff --git a/net/core/filter.c b/net/core/filter.c index 8adf95765cdd96..ae5254f712c94b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4360,10 +4360,12 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { @@ -4375,11 +4377,20 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } @@ -4442,9 +4453,9 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, - void *fwd, - enum bpf_map_type map_type, u32 map_id) + struct bpf_prog *xdp_prog, void *fwd, + enum bpf_map_type map_type, u32 map_id, + u32 flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map; @@ -4454,11 +4465,20 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } @@ -4495,9 +4515,11 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { @@ -4517,7 +4539,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, return 0; } - return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id); + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 4d75ef9d24bfa7..fd20aae30be23c 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1226,11 +1226,8 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); - if (psock) { - read_lock_bh(&sk->sk_callback_lock); + if (psock) sk_psock_data_ready(sk, psock); - read_unlock_bh(&sk->sk_callback_lock); - } rcu_read_unlock(); } } diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 2edc8b796a4e73..049c3adeb85044 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/icmp.c b/net/ipv4/icmp.c index e63a3bf9961762..437e782b9663bb 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/route.c b/net/ipv4/route.c index d36ace160d426f..b814fdab19f710 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2166,6 +2166,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, int err = -EINVAL; u32 tag = 0; + if (!in_dev) + return -EINVAL; + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 3afeeb68e8a7e2..781b67a525719a 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 c02bf011d4a6f4..420905be5f30c9 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/udp.c b/net/ipv6/udp.c index 8b1dd7f512491d..1a4cccdd40c9ca 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/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 39e487ccc46881..8ba00ad433c21b 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -127,6 +127,9 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, /* checksums verified by L2TP */ skb->ip_summed = CHECKSUM_NONE; + /* drop outer flow-hash */ + skb_clear_hash(skb); + skb_dst_drop(skb); nf_reset_ct(skb); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 80e4b9784131d1..ccacaed32817ae 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 32475da98d739c..cbc9b5e40cb35e 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 d913ce7ba72ef8..3f9664e4e00c6c 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 91b55d6a68b973..a6b62169f08483 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 96b70006b7fc0b..3bbb216a0fc8ce 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 23404b275457a7..4dc1def6954865 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 c1f8501384056d..6e24864f9a40ba 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 0429e59ba387c9..73850312580f70 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 6bf223e6cd1a54..cfd0a62d0152bd 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 a0921adc31a9ff..1e689c71412716 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,8 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -174,7 +175,8 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 274b6f7e6bb57e..d170758a1eb5d0 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -338,7 +338,9 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, return; if (n > 1) { - nf_unregister_net_hook(ctx->net, &found->ops); + if (!(ctx->chain->table->flags & NFT_TABLE_F_DORMANT)) + nf_unregister_net_hook(ctx->net, &found->ops); + list_del_rcu(&found->list); kfree_rcu(found, rcu); return; diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index f4a38bd6a7e04f..bfb7758063f315 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,15 @@ EXPORT_SYMBOL_GPL(nsh_pop); static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { + unsigned int outer_hlen, mac_len, nsh_len; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; - unsigned int nsh_len, mac_len; - __be16 proto; + __be16 outer_proto, proto; skb_reset_network_header(skb); + outer_proto = skb->protocol; + outer_hlen = skb_mac_header_len(skb); mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -113,10 +115,10 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, } for (skb = segs; skb; skb = skb->next) { - skb->protocol = htons(ETH_P_NSH); - __skb_push(skb, nsh_len); - skb->mac_header = mac_offset; - skb->network_header = skb->mac_header + mac_len; + skb->protocol = outer_proto; + __skb_push(skb, nsh_len + outer_hlen); + skb_reset_mac_header(skb); + skb_set_network_header(skb, outer_hlen); skb->mac_len = mac_len; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 74b63cdb59923a..2928c142a2ddb3 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1593,9 +1593,9 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; + struct hlist_node *next; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node, - lockdep_ovsl_is_held()) + hlist_for_each_entry_safe(ct_limit, next, head, hlist_node) kfree_rcu(ct_limit, rcu); } kfree(info->limits); diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h index c53b329092d405..4ebc1b7043d917 100644 --- a/net/sunrpc/auth_gss/auth_gss_internal.h +++ b/net/sunrpc/auth_gss/auth_gss_internal.h @@ -23,7 +23,7 @@ simple_get_bytes(const void *p, const void *end, void *res, size_t len) } static inline const void * -simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) +simple_get_netobj_noprof(const void *p, const void *end, struct xdr_netobj *dest) { const void *q; unsigned int len; @@ -35,7 +35,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) if (unlikely(q > end || q < p)) return ERR_PTR(-EFAULT); if (len) { - dest->data = kmemdup(p, len, GFP_KERNEL); + dest->data = kmemdup_noprof(p, len, GFP_KERNEL); if (unlikely(dest->data == NULL)) return ERR_PTR(-ENOMEM); } else @@ -43,3 +43,5 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) dest->len = len; return q; } + +#define simple_get_netobj(...) alloc_hooks(simple_get_netobj_noprof(__VA_ARGS__)) diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index f2a100c4c81f12..40797114d50a49 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 dfca39abd16c88..bb5436b719e051 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 762f424ff2d59c..e5e47452308ab7 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 ca1e0e198ceb45..5df08d848b5c9c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -360,7 +360,7 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0; - strp->msg_ready = 1; + WRITE_ONCE(strp->msg_ready, 1); tls_rx_msg_ready(strp); } @@ -528,7 +528,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); - strp->msg_ready = 1; + WRITE_ONCE(strp->msg_ready, 1); tls_rx_msg_ready(strp); return 0; @@ -580,7 +580,7 @@ void tls_strp_msg_done(struct tls_strparser *strp) else tls_strp_flush_anchor_copy(strp); - strp->msg_ready = 0; + WRITE_ONCE(strp->msg_ready, 0); memset(&strp->stm, 0, sizeof(strp->stm)); tls_strp_check_rcv(strp); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 6433a414acf862..0104be9d470456 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -299,7 +299,7 @@ static void __unix_gc(struct work_struct *work) __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); if (sk->sk_state == TCP_LISTEN) { - unix_state_lock(sk); + unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); unix_state_unlock(sk); } } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b4edba6b0b7ba0..30ff9a47081348 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 cbbf347c6b2e09..df013c98b80dfb 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/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 6affe5cd85d8f1..53d8fabfa68580 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3593,6 +3593,8 @@ xfrm_policy *xfrm_in_fwd_icmp(struct sk_buff *skb, return pol; pol = xfrm_policy_lookup(net, &fl1, family, XFRM_POLICY_FWD, if_id); + if (IS_ERR(pol)) + pol = NULL; } return pol; diff --git a/rust/Makefile b/rust/Makefile index 846e6ab9d5a9b6..86a125c4243cb2 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -175,7 +175,6 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $< mkdir -p $(objtree)/$(obj)/test/doctests/kernel; \ OBJTREE=$(abspath $(objtree)) \ $(RUSTDOC) --test $(rust_flags) \ - @$(objtree)/include/generated/rustc_cfg \ -L$(objtree)/$(obj) --extern alloc --extern kernel \ --extern build_error --extern macros \ --extern bindings --extern uapi \ diff --git a/rust/helpers.c b/rust/helpers.c index 70e59efd92bc43..858d802abd115e 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -28,6 +28,7 @@ #include <linux/mutex.h> #include <linux/refcount.h> #include <linux/sched/signal.h> +#include <linux/slab.h> #include <linux/spinlock.h> #include <linux/wait.h> #include <linux/workqueue.h> @@ -157,6 +158,13 @@ void rust_helper_init_work_with_key(struct work_struct *work, work_func_t func, } EXPORT_SYMBOL_GPL(rust_helper_init_work_with_key); +void * __must_check __realloc_size(2) +rust_helper_krealloc(const void *objp, size_t new_size, gfp_t flags) +{ + return krealloc(objp, new_size, flags); +} +EXPORT_SYMBOL_GPL(rust_helper_krealloc); + /* * `bindgen` binds the C `size_t` type as the Rust `usize` type, so we can * use it in contexts where Rust expects a `usize` like slice (array) indices. diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 424257284d167b..09004b56fb65c7 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -1292,8 +1292,15 @@ impl_zeroable! { i8, i16, i32, i64, i128, isize, f32, f64, - // SAFETY: These are ZSTs, there is nothing to zero. - {<T: ?Sized>} PhantomData<T>, core::marker::PhantomPinned, Infallible, (), + // Note: do not add uninhabited types (such as `!` or `core::convert::Infallible`) to this list; + // creating an instance of an uninhabited type is immediate undefined behavior. For more on + // uninhabited/empty types, consult The Rustonomicon: + // <https://doc.rust-lang.org/stable/nomicon/exotic-sizes.html#empty-types>. The Rust Reference + // also has information on undefined behavior: + // <https://doc.rust-lang.org/stable/reference/behavior-considered-undefined.html>. + // + // SAFETY: These are inhabited ZSTs; there is nothing to zero and a valid value exists. + {<T: ?Sized>} PhantomData<T>, core::marker::PhantomPinned, (), // SAFETY: Type is allowed to take any value, including all zeros. {<T>} MaybeUninit<T>, diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index be68d5e567b1a1..6858e2f8a3ed97 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -65,7 +65,7 @@ const __LOG_PREFIX: &[u8] = b"rust_kernel\0"; /// The top level entrypoint to implementing a kernel module. /// /// For any teardown or cleanup operations, your type may implement [`Drop`]. -pub trait Module: Sized + Sync { +pub trait Module: Sized + Sync + Send { /// Called at module initialization time. /// /// Use this method to perform whatever setup or registration your module diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index 96e09c6e8530b4..265d0e1c13710a 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -640,6 +640,10 @@ pub struct Registration { drivers: Pin<&'static mut [DriverVTable]>, } +// SAFETY: The only action allowed in a `Registration` instance is dropping it, which is safe to do +// from any thread because `phy_drivers_unregister` can be called from any thread context. +unsafe impl Send for Registration {} + impl Registration { /// Registers a PHY driver. pub fn register( diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index f489f315738323..520eae5fd79281 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -35,18 +35,6 @@ use proc_macro::TokenStream; /// author: "Rust for Linux Contributors", /// description: "My very own kernel module!", /// license: "GPL", -/// params: { -/// my_i32: i32 { -/// default: 42, -/// permissions: 0o000, -/// description: "Example of i32", -/// }, -/// writeable_i32: i32 { -/// default: 42, -/// permissions: 0o644, -/// description: "Example of i32", -/// }, -/// }, /// } /// /// struct MyModule; diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 27979e582e4b94..acd0393b509574 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -199,17 +199,6 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { /// Used by the printing macros, e.g. [`info!`]. const __LOG_PREFIX: &[u8] = b\"{name}\\0\"; - /// The \"Rust loadable module\" mark. - // - // This may be best done another way later on, e.g. as a new modinfo - // key or a new section. For the moment, keep it simple. - #[cfg(MODULE)] - #[doc(hidden)] - #[used] - static __IS_RUST_MODULE: () = (); - - static mut __MOD: Option<{type_}> = None; - // SAFETY: `__this_module` is constructed by the kernel at load time and will not be // freed until the module is unloaded. #[cfg(MODULE)] @@ -221,81 +210,132 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { kernel::ThisModule::from_ptr(core::ptr::null_mut()) }}; - // Loadable modules need to export the `{{init,cleanup}}_module` identifiers. - /// # Safety - /// - /// This function must not be called after module initialization, because it may be - /// freed after that completes. - #[cfg(MODULE)] - #[doc(hidden)] - #[no_mangle] - #[link_section = \".init.text\"] - pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{ - __init() - }} - - #[cfg(MODULE)] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn cleanup_module() {{ - __exit() - }} + // Double nested modules, since then nobody can access the public items inside. + mod __module_init {{ + mod __module_init {{ + use super::super::{type_}; + + /// The \"Rust loadable module\" mark. + // + // This may be best done another way later on, e.g. as a new modinfo + // key or a new section. For the moment, keep it simple. + #[cfg(MODULE)] + #[doc(hidden)] + #[used] + static __IS_RUST_MODULE: () = (); + + static mut __MOD: Option<{type_}> = None; + + // Loadable modules need to export the `{{init,cleanup}}_module` identifiers. + /// # Safety + /// + /// This function must not be called after module initialization, because it may be + /// freed after that completes. + #[cfg(MODULE)] + #[doc(hidden)] + #[no_mangle] + #[link_section = \".init.text\"] + pub unsafe extern \"C\" fn init_module() -> core::ffi::c_int {{ + // SAFETY: This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name. + unsafe {{ __init() }} + }} - // Built-in modules are initialized through an initcall pointer - // and the identifiers need to be unique. - #[cfg(not(MODULE))] - #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] - #[doc(hidden)] - #[link_section = \"{initcall_section}\"] - #[used] - pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init; + #[cfg(MODULE)] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn cleanup_module() {{ + // SAFETY: + // - This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name, + // - furthermore it is only called after `init_module` has returned `0` + // (which delegates to `__init`). + unsafe {{ __exit() }} + }} - #[cfg(not(MODULE))] - #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)] - core::arch::global_asm!( - r#\".section \"{initcall_section}\", \"a\" - __{name}_initcall: - .long __{name}_init - . - .previous - \"# - ); + // Built-in modules are initialized through an initcall pointer + // and the identifiers need to be unique. + #[cfg(not(MODULE))] + #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] + #[doc(hidden)] + #[link_section = \"{initcall_section}\"] + #[used] + pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init; + + #[cfg(not(MODULE))] + #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)] + core::arch::global_asm!( + r#\".section \"{initcall_section}\", \"a\" + __{name}_initcall: + .long __{name}_init - . + .previous + \"# + ); + + #[cfg(not(MODULE))] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{ + // SAFETY: This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // placement above in the initcall section. + unsafe {{ __init() }} + }} - #[cfg(not(MODULE))] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{ - __init() - }} + #[cfg(not(MODULE))] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn __{name}_exit() {{ + // SAFETY: + // - This function is inaccessible to the outside due to the double + // module wrapping it. It is called exactly once by the C side via its + // unique name, + // - furthermore it is only called after `__{name}_init` has returned `0` + // (which delegates to `__init`). + unsafe {{ __exit() }} + }} - #[cfg(not(MODULE))] - #[doc(hidden)] - #[no_mangle] - pub extern \"C\" fn __{name}_exit() {{ - __exit() - }} + /// # Safety + /// + /// This function must only be called once. + unsafe fn __init() -> core::ffi::c_int {{ + match <{type_} as kernel::Module>::init(&super::super::THIS_MODULE) {{ + Ok(m) => {{ + // SAFETY: No data race, since `__MOD` can only be accessed by this + // module and there only `__init` and `__exit` access it. These + // functions are only called once and `__exit` cannot be called + // before or during `__init`. + unsafe {{ + __MOD = Some(m); + }} + return 0; + }} + Err(e) => {{ + return e.to_errno(); + }} + }} + }} - fn __init() -> core::ffi::c_int {{ - match <{type_} as kernel::Module>::init(&THIS_MODULE) {{ - Ok(m) => {{ + /// # Safety + /// + /// This function must + /// - only be called once, + /// - be called after `__init` has been called and returned `0`. + unsafe fn __exit() {{ + // SAFETY: No data race, since `__MOD` can only be accessed by this module + // and there only `__init` and `__exit` access it. These functions are only + // called once and `__init` was already called. unsafe {{ - __MOD = Some(m); + // Invokes `drop()` on `__MOD`, which should be used for cleanup. + __MOD = None; }} - return 0; - }} - Err(e) => {{ - return e.to_errno(); }} - }} - }} - fn __exit() {{ - unsafe {{ - // Invokes `drop()` on `__MOD`, which should be used for cleanup. - __MOD = None; + {modinfo} }} }} - - {modinfo} ", type_ = info.type_, name = info.name, diff --git a/samples/kfifo/dma-example.c b/samples/kfifo/dma-example.c index 0cf27483cb3613..74fe915b7ffe8c 100644 --- a/samples/kfifo/dma-example.c +++ b/samples/kfifo/dma-example.c @@ -6,8 +6,9 @@ */ #include <linux/init.h> -#include <linux/module.h> #include <linux/kfifo.h> +#include <linux/module.h> +#include <linux/scatterlist.h> /* * This module shows how to handle fifo dma operations. diff --git a/scripts/Makefile.build b/scripts/Makefile.build index baf86c0880b6d7..533a7799fdfe6d 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -273,7 +273,7 @@ rust_common_cmd = \ -Zallow-features=$(rust_allowed_features) \ -Zcrate-attr=no_std \ -Zcrate-attr='feature($(rust_allowed_features))' \ - --extern alloc --extern kernel \ + -Zunstable-options --extern force:alloc --extern kernel \ --crate-type rlib -L $(objtree)/rust/ \ --crate-name $(basename $(notdir $@)) \ --sysroot=/dev/null \ diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index c5af566e911ae7..1d13cecc7cc780 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -37,11 +37,6 @@ else KBUILD_CFLAGS += -Wno-main endif -# These warnings generated too much noise in a regular build. -# Use make W=1 to enable them (see scripts/Makefile.extrawarn) -KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) -KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) - # These result in bogus false positives KBUILD_CFLAGS += $(call cc-disable-warning, dangling-pointer) @@ -82,22 +77,17 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init) # Warn if there is an enum types mismatch KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion) +KBUILD_CFLAGS += -Wextra +KBUILD_CFLAGS += -Wunused + # # W=1 - warnings which may be relevant and do not occur too often # ifneq ($(findstring 1, $(KBUILD_EXTRA_WARN)),) -KBUILD_CFLAGS += -Wextra -Wunused -Wno-unused-parameter -KBUILD_CFLAGS += $(call cc-option, -Wrestrict) KBUILD_CFLAGS += -Wmissing-format-attribute -KBUILD_CFLAGS += -Wold-style-definition KBUILD_CFLAGS += -Wmissing-include-dirs -KBUILD_CFLAGS += $(call cc-option, -Wunused-but-set-variable) KBUILD_CFLAGS += $(call cc-option, -Wunused-const-variable) -KBUILD_CFLAGS += $(call cc-option, -Wpacked-not-aligned) -KBUILD_CFLAGS += $(call cc-option, -Wformat-overflow) -KBUILD_CFLAGS += $(call cc-option, -Wformat-truncation) -KBUILD_CFLAGS += $(call cc-option, -Wstringop-truncation) KBUILD_CPPFLAGS += -Wundef KBUILD_CPPFLAGS += -DKBUILD_EXTRA_WARN1 @@ -108,10 +98,16 @@ else # Suppress them by using -Wno... except for W=1. KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) -KBUILD_CFLAGS += $(call cc-disable-warning, restrict) KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned) KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) +ifdef CONFIG_CC_IS_GCC KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) +else +# Clang checks for overflow/truncation with '%p', while GCC does not: +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219 +KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf) +KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf) +endif KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) KBUILD_CFLAGS += -Wno-override-init # alias for -Wno-initializer-overrides in clang @@ -133,7 +129,6 @@ endif KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) -KBUILD_CFLAGS += $(call cc-disable-warning, cast-function-type-strict) KBUILD_CFLAGS += -Wno-enum-compare-conditional KBUILD_CFLAGS += -Wno-enum-enum-conversion endif @@ -148,9 +143,6 @@ ifneq ($(findstring 2, $(KBUILD_EXTRA_WARN)),) KBUILD_CFLAGS += -Wdisabled-optimization KBUILD_CFLAGS += -Wshadow KBUILD_CFLAGS += $(call cc-option, -Wlogical-op) -KBUILD_CFLAGS += -Wmissing-field-initializers -KBUILD_CFLAGS += -Wtype-limits -KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized) KBUILD_CFLAGS += $(call cc-option, -Wunused-macros) KBUILD_CPPFLAGS += -DKBUILD_EXTRA_WARN2 @@ -190,6 +182,7 @@ else # The following turn off the warnings enabled by -Wextra KBUILD_CFLAGS += -Wno-sign-compare +KBUILD_CFLAGS += -Wno-unused-parameter endif diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index cba589e5b57d61..2f11c4f9c345a0 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -26,11 +26,7 @@ def get_current_cpu(): if utils.get_gdbserver_type() == utils.GDBSERVER_QEMU: return gdb.selected_thread().num - 1 elif utils.get_gdbserver_type() == utils.GDBSERVER_KGDB: - tid = gdb.selected_thread().ptid[2] - if tid > (0x100000000 - MAX_CPUS - 2): - return 0x100000000 - tid - 2 - else: - return tasks.get_thread_info(tasks.get_task_by_pid(tid))['cpu'] + return gdb.parse_and_eval("kgdb_active.counter") else: raise gdb.GdbError("Sorry, obtaining the current CPU is not yet " "supported with this gdb server.") @@ -152,9 +148,8 @@ Note that VAR has to be quoted as string.""" def __init__(self): super(PerCpu, self).__init__("lx_per_cpu") - def invoke(self, var_name, cpu=-1): - var_ptr = gdb.parse_and_eval("&" + var_name.string()) - return per_cpu(var_ptr, cpu) + def invoke(self, var, cpu=-1): + return per_cpu(var.address, cpu) PerCpu() diff --git a/scripts/gdb/linux/tasks.py b/scripts/gdb/linux/tasks.py index 6793d6e86e777b..62348397c1f5c8 100644 --- a/scripts/gdb/linux/tasks.py +++ b/scripts/gdb/linux/tasks.py @@ -85,7 +85,7 @@ thread_info_type = utils.CachedType("struct thread_info") def get_thread_info(task): thread_info_ptr_type = thread_info_type.get_type().pointer() - if task.type.fields()[0].type == thread_info_type.get_type(): + if task_type.get_type().fields()[0].type == thread_info_type.get_type(): return task['thread_info'] thread_info = task['stack'].cast(thread_info_ptr_type) return thread_info.dereference() diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index 7d5278d815fa15..245ab297ea84a0 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -196,7 +196,7 @@ def get_gdbserver_type(): def probe_kgdb(): try: thread_info = gdb.execute("info thread 2", to_string=True) - return "shadowCPU0" in thread_info + return "shadowCPU" in thread_info except gdb.error: return False diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 653b92f6d4c8f4..47978efe4797c2 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -204,6 +204,11 @@ static int symbol_in_range(const struct sym_entry *s, return 0; } +static bool string_starts_with(const char *s, const char *prefix) +{ + return strncmp(s, prefix, strlen(prefix)) == 0; +} + static int symbol_valid(const struct sym_entry *s) { const char *name = sym_name(s); @@ -211,6 +216,14 @@ static int symbol_valid(const struct sym_entry *s) /* if --all-symbols is not specified, then symbols outside the text * and inittext sections are discarded */ if (!all_symbols) { + /* + * Symbols starting with __start and __stop are used to denote + * section boundaries, and should always be included: + */ + if (string_starts_with(name, "__start_") || + string_starts_with(name, "__stop_")) + return 1; + if (symbol_in_range(s, text_ranges, ARRAY_SIZE(text_ranges)) == 0) return 0; diff --git a/scripts/kernel-doc b/scripts/kernel-doc index cb1be22afc65ff..b463acecad401b 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1723,6 +1723,7 @@ sub dump_function($$) { $prototype =~ s/__must_check +//; $prototype =~ s/__weak +//; $prototype =~ s/__sched +//; + $prototype =~ s/_noprof//; $prototype =~ s/__printf\s*\(\s*\d*\s*,\s*\d*\s*\) +//; $prototype =~ s/__(?:re)?alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\) +//; $prototype =~ s/__diagnose_as\s*\(\s*\S+\s*(?:,\s*\d+\s*)*\) +//; diff --git a/scripts/module.lds.S b/scripts/module.lds.S index bf5bcf2836d815..45c67a0994f3e3 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -9,6 +9,8 @@ #define DISCARD_EH_FRAME *(.eh_frame) #endif +#include <asm-generic/codetag.lds.h> + SECTIONS { /DISCARD/ : { *(.discard) @@ -47,12 +49,17 @@ SECTIONS { .data : { *(.data .data.[0-9a-zA-Z_]*) *(.data..L*) + CODETAG_SECTIONS() } .rodata : { *(.rodata .rodata.[0-9a-zA-Z_]*) *(.rodata..L*) } +#else + .data : { + CODETAG_SECTIONS() + } #endif } diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index 2cff851ebfd7e1..effbf5982be10f 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -255,6 +255,21 @@ config INIT_ON_FREE_DEFAULT_ON touching "cold" memory areas. Most cases see 3-5% impact. Some synthetic workloads have measured as high as 8%. +config INIT_MLOCKED_ON_FREE_DEFAULT_ON + bool "Enable mlocked memory zeroing on free" + depends on !KMSAN + help + This config has the effect of setting "init_mlocked_on_free=1" + on the kernel command line. If it is enabled, all mlocked process + memory is zeroed when freed. This restriction to mlocked memory + improves performance over "init_on_free" but can still be used to + protect confidential data like key material from content exposures + to other processes, as well as live forensics and cold boot attacks. + Any non-mlocked memory is not cleared before it is reassigned. This + configuration can be overwritten by setting "init_mlocked_on_free=0" + on the command line. The "init_on_free" boot option takes + precedence over "init_mlocked_on_free". + config CC_HAS_ZERO_CALL_USED_REGS def_bool $(cc-option,-fzero-call-used-regs=used-gpr) # https://github.com/ClangBuiltLinux/linux/issues/1766 diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c index fe72e7d7724127..dadeda7758ceeb 100644 --- a/sound/pci/emu10k1/emu10k1.c +++ b/sound/pci/emu10k1/emu10k1.c @@ -189,8 +189,7 @@ static int snd_emu10k1_suspend(struct device *dev) emu->suspend = 1; - cancel_work_sync(&emu->emu1010.firmware_work); - cancel_work_sync(&emu->emu1010.clock_work); + cancel_work_sync(&emu->emu1010.work); snd_ac97_suspend(emu->ac97); diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index de5c41e578e1f4..8ccc0178360ce8 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -732,69 +732,67 @@ static int snd_emu1010_load_firmware(struct snd_emu10k1 *emu, int dock, return snd_emu1010_load_firmware_entry(emu, *fw); } -static void emu1010_firmware_work(struct work_struct *work) +static void snd_emu1010_load_dock_firmware(struct snd_emu10k1 *emu) { - struct snd_emu10k1 *emu; - u32 tmp, tmp2, reg; + u32 tmp, tmp2; int err; - emu = container_of(work, struct snd_emu10k1, - emu1010.firmware_work); - if (emu->card->shutdown) + // The docking events clearly arrive prematurely - while the + // Dock's FPGA seems to be successfully programmed, the Dock + // fails to initialize subsequently if we don't give it some + // time to "warm up" here. + msleep(200); + + dev_info(emu->card->dev, "emu1010: Loading Audio Dock Firmware\n"); + /* Return to Audio Dock programming mode */ + snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, + EMU_HANA_FPGA_CONFIG_AUDIODOCK); + err = snd_emu1010_load_firmware(emu, 1, &emu->dock_fw); + if (err < 0) return; -#ifdef CONFIG_PM_SLEEP - if (emu->suspend) + snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, 0); + + snd_emu1010_fpga_read(emu, EMU_HANA_ID, &tmp); + dev_dbg(emu->card->dev, "emu1010: EMU_HANA+DOCK_ID = 0x%x\n", tmp); + if ((tmp & 0x1f) != 0x15) { + /* FPGA failed to be programmed */ + dev_err(emu->card->dev, + "emu1010: Loading Audio Dock Firmware failed, reg = 0x%x\n", + tmp); return; -#endif + } + dev_info(emu->card->dev, "emu1010: Audio Dock Firmware loaded\n"); + + snd_emu1010_fpga_read(emu, EMU_DOCK_MAJOR_REV, &tmp); + snd_emu1010_fpga_read(emu, EMU_DOCK_MINOR_REV, &tmp2); + dev_info(emu->card->dev, "Audio Dock ver: %u.%u\n", tmp, tmp2); + + /* Allow DLL to settle, to sync clocking between 1010 and Dock */ + msleep(10); +} + +static void emu1010_dock_event(struct snd_emu10k1 *emu) +{ + u32 reg; + snd_emu1010_fpga_read(emu, EMU_HANA_OPTION_CARDS, ®); /* OPTIONS: Which cards are attached to the EMU */ if (reg & EMU_HANA_OPTION_DOCK_OFFLINE) { /* Audio Dock attached */ - /* Return to Audio Dock programming mode */ - dev_info(emu->card->dev, - "emu1010: Loading Audio Dock Firmware\n"); - snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, - EMU_HANA_FPGA_CONFIG_AUDIODOCK); - err = snd_emu1010_load_firmware(emu, 1, &emu->dock_fw); - if (err < 0) - return; - snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, 0); - snd_emu1010_fpga_read(emu, EMU_HANA_ID, &tmp); - dev_info(emu->card->dev, - "emu1010: EMU_HANA+DOCK_ID = 0x%x\n", tmp); - if ((tmp & 0x1f) != 0x15) { - /* FPGA failed to be programmed */ - dev_info(emu->card->dev, - "emu1010: Loading Audio Dock Firmware file failed, reg = 0x%x\n", - tmp); - return; - } - dev_info(emu->card->dev, - "emu1010: Audio Dock Firmware loaded\n"); - snd_emu1010_fpga_read(emu, EMU_DOCK_MAJOR_REV, &tmp); - snd_emu1010_fpga_read(emu, EMU_DOCK_MINOR_REV, &tmp2); - dev_info(emu->card->dev, "Audio Dock ver: %u.%u\n", tmp, tmp2); - /* Sync clocking between 1010 and Dock */ - /* Allow DLL to settle */ - msleep(10); + snd_emu1010_load_dock_firmware(emu); /* Unmute all. Default is muted after a firmware load */ snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE); + } else if (!(reg & EMU_HANA_OPTION_DOCK_ONLINE)) { + /* Audio Dock removed */ + dev_info(emu->card->dev, "emu1010: Audio Dock detached\n"); + /* The hardware auto-mutes all, so we unmute again */ + snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE); } } -static void emu1010_clock_work(struct work_struct *work) +static void emu1010_clock_event(struct snd_emu10k1 *emu) { - struct snd_emu10k1 *emu; struct snd_ctl_elem_id id; - emu = container_of(work, struct snd_emu10k1, - emu1010.clock_work); - if (emu->card->shutdown) - return; -#ifdef CONFIG_PM_SLEEP - if (emu->suspend) - return; -#endif - spin_lock_irq(&emu->reg_lock); // This is the only thing that can actually happen. emu->emu1010.clock_source = emu->emu1010.clock_fallback; @@ -805,21 +803,44 @@ static void emu1010_clock_work(struct work_struct *work) snd_ctl_notify(emu->card, SNDRV_CTL_EVENT_MASK_VALUE, &id); } -static void emu1010_interrupt(struct snd_emu10k1 *emu) +static void emu1010_work(struct work_struct *work) { + struct snd_emu10k1 *emu; u32 sts; + emu = container_of(work, struct snd_emu10k1, emu1010.work); + if (emu->card->shutdown) + return; +#ifdef CONFIG_PM_SLEEP + if (emu->suspend) + return; +#endif + + snd_emu1010_fpga_lock(emu); + snd_emu1010_fpga_read(emu, EMU_HANA_IRQ_STATUS, &sts); - if (sts & EMU_HANA_IRQ_DOCK_LOST) { - /* Audio Dock removed */ - dev_info(emu->card->dev, "emu1010: Audio Dock detached\n"); - /* The hardware auto-mutes all, so we unmute again */ - snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE); - } else if (sts & EMU_HANA_IRQ_DOCK) { - schedule_work(&emu->emu1010.firmware_work); - } + + // The distinction of the IRQ status bits is unreliable, + // so we dispatch later based on option card status. + if (sts & (EMU_HANA_IRQ_DOCK | EMU_HANA_IRQ_DOCK_LOST)) + emu1010_dock_event(emu); + if (sts & EMU_HANA_IRQ_WCLK_CHANGED) - schedule_work(&emu->emu1010.clock_work); + emu1010_clock_event(emu); + + snd_emu1010_fpga_unlock(emu); +} + +static void emu1010_interrupt(struct snd_emu10k1 *emu) +{ + // We get an interrupt on each GPIO input pin change, but we + // care only about the ones triggered by the dedicated pin. + u16 sts = inw(emu->port + A_GPIO); + u16 bit = emu->card_capabilities->ca0108_chip ? 0x2000 : 0x8000; + if (!(sts & bit)) + return; + + schedule_work(&emu->emu1010.work); } /* @@ -841,6 +862,8 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) * Proper init follows in snd_emu10k1_init(). */ outl(HCFG_LOCKSOUNDCACHE | HCFG_LOCKTANKCACHE_MASK, emu->port + HCFG); + snd_emu1010_fpga_lock(emu); + /* Disable 48Volt power to Audio Dock */ snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_PWR, 0); @@ -866,7 +889,7 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) err = snd_emu1010_load_firmware(emu, 0, &emu->firmware); if (err < 0) { dev_info(emu->card->dev, "emu1010: Loading Firmware failed\n"); - return err; + goto fail; } /* ID, should read & 0x7f = 0x55 when FPGA programmed. */ @@ -876,7 +899,8 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) dev_info(emu->card->dev, "emu1010: Loading Hana Firmware file failed, reg = 0x%x\n", reg); - return -ENODEV; + err = -ENODEV; + goto fail; } dev_info(emu->card->dev, "emu1010: Hana Firmware loaded\n"); @@ -889,7 +913,7 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) snd_emu1010_fpga_read(emu, EMU_HANA_OPTION_CARDS, ®); dev_info(emu->card->dev, "emu1010: Card options = 0x%x\n", reg); if (reg & EMU_HANA_OPTION_DOCK_OFFLINE) - schedule_work(&emu->emu1010.firmware_work); + snd_emu1010_load_dock_firmware(emu); if (emu->card_capabilities->no_adat) { emu->emu1010.optical_in = 0; /* IN_SPDIF */ emu->emu1010.optical_out = 0; /* OUT_SPDIF */ @@ -936,7 +960,9 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) // so it is safe to simply enable the outputs. snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE); - return 0; +fail: + snd_emu1010_fpga_unlock(emu); + return err; } /* * Create the EMU10K1 instance @@ -958,10 +984,10 @@ static void snd_emu10k1_free(struct snd_card *card) } if (emu->card_capabilities->emu_model == EMU_MODEL_EMU1010) { /* Disable 48Volt power to Audio Dock */ - snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_PWR, 0); + snd_emu1010_fpga_write_lock(emu, EMU_HANA_DOCK_PWR, 0); } - cancel_work_sync(&emu->emu1010.firmware_work); - cancel_work_sync(&emu->emu1010.clock_work); + cancel_work_sync(&emu->emu1010.work); + mutex_destroy(&emu->emu1010.lock); release_firmware(emu->firmware); release_firmware(emu->dock_fw); snd_util_memhdr_free(emu->memhdr); @@ -1540,8 +1566,8 @@ int snd_emu10k1_create(struct snd_card *card, emu->irq = -1; emu->synth = NULL; emu->get_synth_voice = NULL; - INIT_WORK(&emu->emu1010.firmware_work, emu1010_firmware_work); - INIT_WORK(&emu->emu1010.clock_work, emu1010_clock_work); + INIT_WORK(&emu->emu1010.work, emu1010_work); + mutex_init(&emu->emu1010.lock); /* read revision & serial */ emu->revision = pci->revision; pci_read_config_dword(pci, PCI_SUBSYSTEM_VENDOR_ID, &emu->serial); diff --git a/sound/pci/emu10k1/emumixer.c b/sound/pci/emu10k1/emumixer.c index 0a32ea53d8c648..05b98d9b547b2a 100644 --- a/sound/pci/emu10k1/emumixer.c +++ b/sound/pci/emu10k1/emumixer.c @@ -661,7 +661,9 @@ static int snd_emu1010_output_source_put(struct snd_kcontrol *kcontrol, change = (emu->emu1010.output_source[channel] != val); if (change) { emu->emu1010.output_source[channel] = val; + snd_emu1010_fpga_lock(emu); snd_emu1010_output_source_apply(emu, channel, val); + snd_emu1010_fpga_unlock(emu); } return change; } @@ -705,7 +707,9 @@ static int snd_emu1010_input_source_put(struct snd_kcontrol *kcontrol, change = (emu->emu1010.input_source[channel] != val); if (change) { emu->emu1010.input_source[channel] = val; + snd_emu1010_fpga_lock(emu); snd_emu1010_input_source_apply(emu, channel, val); + snd_emu1010_fpga_unlock(emu); } return change; } @@ -774,7 +778,7 @@ static int snd_emu1010_adc_pads_put(struct snd_kcontrol *kcontrol, struct snd_ct cache = cache & ~mask; change = (cache != emu->emu1010.adc_pads); if (change) { - snd_emu1010_fpga_write(emu, EMU_HANA_ADC_PADS, cache ); + snd_emu1010_fpga_write_lock(emu, EMU_HANA_ADC_PADS, cache ); emu->emu1010.adc_pads = cache; } @@ -832,7 +836,7 @@ static int snd_emu1010_dac_pads_put(struct snd_kcontrol *kcontrol, struct snd_ct cache = cache & ~mask; change = (cache != emu->emu1010.dac_pads); if (change) { - snd_emu1010_fpga_write(emu, EMU_HANA_DAC_PADS, cache ); + snd_emu1010_fpga_write_lock(emu, EMU_HANA_DAC_PADS, cache ); emu->emu1010.dac_pads = cache; } @@ -980,6 +984,7 @@ static int snd_emu1010_clock_source_put(struct snd_kcontrol *kcontrol, val = ucontrol->value.enumerated.item[0] ; if (val >= emu_ci->num) return -EINVAL; + snd_emu1010_fpga_lock(emu); spin_lock_irq(&emu->reg_lock); change = (emu->emu1010.clock_source != val); if (change) { @@ -996,6 +1001,7 @@ static int snd_emu1010_clock_source_put(struct snd_kcontrol *kcontrol, } else { spin_unlock_irq(&emu->reg_lock); } + snd_emu1010_fpga_unlock(emu); return change; } @@ -1041,7 +1047,7 @@ static int snd_emu1010_clock_fallback_put(struct snd_kcontrol *kcontrol, change = (emu->emu1010.clock_fallback != val); if (change) { emu->emu1010.clock_fallback = val; - snd_emu1010_fpga_write(emu, EMU_HANA_DEFCLOCK, 1 - val); + snd_emu1010_fpga_write_lock(emu, EMU_HANA_DEFCLOCK, 1 - val); } return change; } @@ -1093,7 +1099,7 @@ static int snd_emu1010_optical_out_put(struct snd_kcontrol *kcontrol, emu->emu1010.optical_out = val; tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : EMU_HANA_OPTICAL_IN_SPDIF) | (emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : EMU_HANA_OPTICAL_OUT_SPDIF); - snd_emu1010_fpga_write(emu, EMU_HANA_OPTICAL_TYPE, tmp); + snd_emu1010_fpga_write_lock(emu, EMU_HANA_OPTICAL_TYPE, tmp); } return change; } @@ -1144,7 +1150,7 @@ static int snd_emu1010_optical_in_put(struct snd_kcontrol *kcontrol, emu->emu1010.optical_in = val; tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : EMU_HANA_OPTICAL_IN_SPDIF) | (emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : EMU_HANA_OPTICAL_OUT_SPDIF); - snd_emu1010_fpga_write(emu, EMU_HANA_OPTICAL_TYPE, tmp); + snd_emu1010_fpga_write_lock(emu, EMU_HANA_OPTICAL_TYPE, tmp); } return change; } @@ -2323,7 +2329,9 @@ int snd_emu10k1_mixer(struct snd_emu10k1 *emu, for (i = 0; i < emu_ri->n_outs; i++) emu->emu1010.output_source[i] = emu1010_map_source(emu_ri, emu_ri->out_dflts[i]); + snd_emu1010_fpga_lock(emu); snd_emu1010_apply_sources(emu); + snd_emu1010_fpga_unlock(emu); kctl = emu->ctl_clock_source = snd_ctl_new1(&snd_emu1010_clock_source, emu); err = snd_ctl_add(card, kctl); diff --git a/sound/pci/emu10k1/emuproc.c b/sound/pci/emu10k1/emuproc.c index 2f80fd91017c39..737c28d31b41a3 100644 --- a/sound/pci/emu10k1/emuproc.c +++ b/sound/pci/emu10k1/emuproc.c @@ -165,6 +165,8 @@ static void snd_emu10k1_proc_spdif_read(struct snd_info_entry *entry, u32 value2; if (emu->card_capabilities->emu_model) { + snd_emu1010_fpga_lock(emu); + // This represents the S/PDIF lock status on 0404b, which is // kinda weird and unhelpful, because monitoring it via IRQ is // impractical (one gets an IRQ flood as long as it is desynced). @@ -197,6 +199,8 @@ static void snd_emu10k1_proc_spdif_read(struct snd_info_entry *entry, snd_iprintf(buffer, "\nS/PDIF mode: %s%s\n", value & EMU_HANA_SPDIF_MODE_RX_PRO ? "professional" : "consumer", value & EMU_HANA_SPDIF_MODE_RX_NOCOPY ? ", no copy" : ""); + + snd_emu1010_fpga_unlock(emu); } else { snd_emu10k1_proc_spdif_status(emu, buffer, "CD-ROM S/PDIF In", CDCS, CDSRCS); snd_emu10k1_proc_spdif_status(emu, buffer, "Optical or Coax S/PDIF In", GPSCS, GPSRCS); @@ -458,6 +462,9 @@ static void snd_emu_proc_emu1010_reg_read(struct snd_info_entry *entry, struct snd_emu10k1 *emu = entry->private_data; u32 value; int i; + + snd_emu1010_fpga_lock(emu); + snd_iprintf(buffer, "EMU1010 Registers:\n\n"); for(i = 0; i < 0x40; i+=1) { @@ -496,6 +503,8 @@ static void snd_emu_proc_emu1010_reg_read(struct snd_info_entry *entry, snd_emu_proc_emu1010_link_read(emu, buffer, 0x701); } } + + snd_emu1010_fpga_unlock(emu); } static void snd_emu_proc_io_reg_read(struct snd_info_entry *entry, diff --git a/sound/pci/emu10k1/io.c b/sound/pci/emu10k1/io.c index 74df2330015f66..f4a1c2d4b07875 100644 --- a/sound/pci/emu10k1/io.c +++ b/sound/pci/emu10k1/io.c @@ -285,24 +285,33 @@ static void snd_emu1010_fpga_write_locked(struct snd_emu10k1 *emu, u32 reg, u32 outw(value, emu->port + A_GPIO); udelay(10); outw(value | 0x80 , emu->port + A_GPIO); /* High bit clocks the value into the fpga. */ + udelay(10); } void snd_emu1010_fpga_write(struct snd_emu10k1 *emu, u32 reg, u32 value) { - unsigned long flags; + if (snd_BUG_ON(!mutex_is_locked(&emu->emu1010.lock))) + return; + snd_emu1010_fpga_write_locked(emu, reg, value); +} - spin_lock_irqsave(&emu->emu_lock, flags); +void snd_emu1010_fpga_write_lock(struct snd_emu10k1 *emu, u32 reg, u32 value) +{ + snd_emu1010_fpga_lock(emu); snd_emu1010_fpga_write_locked(emu, reg, value); - spin_unlock_irqrestore(&emu->emu_lock, flags); + snd_emu1010_fpga_unlock(emu); } -static void snd_emu1010_fpga_read_locked(struct snd_emu10k1 *emu, u32 reg, u32 *value) +void snd_emu1010_fpga_read(struct snd_emu10k1 *emu, u32 reg, u32 *value) { // The higest input pin is used as the designated interrupt trigger, // so it needs to be masked out. // But note that any other input pin change will also cause an IRQ, // so using this function often causes an IRQ as a side effect. u32 mask = emu->card_capabilities->ca0108_chip ? 0x1f : 0x7f; + + if (snd_BUG_ON(!mutex_is_locked(&emu->emu1010.lock))) + return; if (snd_BUG_ON(reg > 0x3f)) return; reg += 0x40; /* 0x40 upwards are registers. */ @@ -313,47 +322,31 @@ static void snd_emu1010_fpga_read_locked(struct snd_emu10k1 *emu, u32 reg, u32 * *value = ((inw(emu->port + A_GPIO) >> 8) & mask); } -void snd_emu1010_fpga_read(struct snd_emu10k1 *emu, u32 reg, u32 *value) -{ - unsigned long flags; - - spin_lock_irqsave(&emu->emu_lock, flags); - snd_emu1010_fpga_read_locked(emu, reg, value); - spin_unlock_irqrestore(&emu->emu_lock, flags); -} - /* Each Destination has one and only one Source, * but one Source can feed any number of Destinations simultaneously. */ void snd_emu1010_fpga_link_dst_src_write(struct snd_emu10k1 *emu, u32 dst, u32 src) { - unsigned long flags; - if (snd_BUG_ON(dst & ~0x71f)) return; if (snd_BUG_ON(src & ~0x71f)) return; - spin_lock_irqsave(&emu->emu_lock, flags); - snd_emu1010_fpga_write_locked(emu, EMU_HANA_DESTHI, dst >> 8); - snd_emu1010_fpga_write_locked(emu, EMU_HANA_DESTLO, dst & 0x1f); - snd_emu1010_fpga_write_locked(emu, EMU_HANA_SRCHI, src >> 8); - snd_emu1010_fpga_write_locked(emu, EMU_HANA_SRCLO, src & 0x1f); - spin_unlock_irqrestore(&emu->emu_lock, flags); + snd_emu1010_fpga_write(emu, EMU_HANA_DESTHI, dst >> 8); + snd_emu1010_fpga_write(emu, EMU_HANA_DESTLO, dst & 0x1f); + snd_emu1010_fpga_write(emu, EMU_HANA_SRCHI, src >> 8); + snd_emu1010_fpga_write(emu, EMU_HANA_SRCLO, src & 0x1f); } u32 snd_emu1010_fpga_link_dst_src_read(struct snd_emu10k1 *emu, u32 dst) { - unsigned long flags; u32 hi, lo; if (snd_BUG_ON(dst & ~0x71f)) return 0; - spin_lock_irqsave(&emu->emu_lock, flags); - snd_emu1010_fpga_write_locked(emu, EMU_HANA_DESTHI, dst >> 8); - snd_emu1010_fpga_write_locked(emu, EMU_HANA_DESTLO, dst & 0x1f); - snd_emu1010_fpga_read_locked(emu, EMU_HANA_SRCHI, &hi); - snd_emu1010_fpga_read_locked(emu, EMU_HANA_SRCLO, &lo); - spin_unlock_irqrestore(&emu->emu_lock, flags); + snd_emu1010_fpga_write(emu, EMU_HANA_DESTHI, dst >> 8); + snd_emu1010_fpga_write(emu, EMU_HANA_DESTLO, dst & 0x1f); + snd_emu1010_fpga_read(emu, EMU_HANA_SRCHI, &hi); + snd_emu1010_fpga_read(emu, EMU_HANA_SRCLO, &lo); return (hi << 8) | lo; } diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index d3fa6e136744de..990b5bd717a1cb 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -13,6 +13,7 @@ #include <sound/soc.h> #include <linux/pm_runtime.h> #include <linux/spi/spi.h> +#include <linux/vmalloc.h> #include "hda_local.h" #include "hda_auto_parser.h" #include "hda_jack.h" diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 1a3f84599cb584..558c1f38fe9718 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -644,6 +644,8 @@ static int cs35l56_hda_fw_load(struct cs35l56_hda *cs35l56) ret = cs35l56_wait_for_firmware_boot(&cs35l56->base); if (ret) goto err_powered_up; + + regcache_cache_only(cs35l56->base.regmap, false); } /* Disable auto-hibernate so that runtime_pm has control */ @@ -1002,6 +1004,8 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id) if (ret) goto err; + regcache_cache_only(cs35l56->base.regmap, false); + ret = cs35l56_set_patch(&cs35l56->base); if (ret) goto err; diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 69c68d8e7a6b54..1760b5d42460af 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -433,6 +433,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "MDC"), + DMI_MATCH(DMI_BOARD_NAME, "Herbag_MDU"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "System76"), DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"), } diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index dfb4ce53491bba..f8e57a2fc3e324 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -1094,6 +1094,7 @@ static int cs35l41_handle_pdata(struct device *dev, struct cs35l41_hw_cfg *hw_cf static int cs35l41_dsp_init(struct cs35l41_private *cs35l41) { struct wm_adsp *dsp; + uint32_t dsp1rx5_src; int ret; dsp = &cs35l41->dsp; @@ -1113,16 +1114,29 @@ static int cs35l41_dsp_init(struct cs35l41_private *cs35l41) return ret; } - ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC, - CS35L41_INPUT_SRC_VPMON); + switch (cs35l41->hw_cfg.bst_type) { + case CS35L41_INT_BOOST: + case CS35L41_SHD_BOOST_ACTV: + dsp1rx5_src = CS35L41_INPUT_SRC_VPMON; + break; + case CS35L41_EXT_BOOST: + case CS35L41_SHD_BOOST_PASS: + dsp1rx5_src = CS35L41_INPUT_SRC_VBSTMON; + break; + default: + dev_err(cs35l41->dev, "wm_halo_init failed - Invalid Boost Type: %d\n", + cs35l41->hw_cfg.bst_type); + goto err_dsp; + } + + ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX5_SRC, dsp1rx5_src); if (ret < 0) { - dev_err(cs35l41->dev, "Write INPUT_SRC_VPMON failed: %d\n", ret); + dev_err(cs35l41->dev, "Write DSP1RX5_SRC: %d failed: %d\n", dsp1rx5_src, ret); goto err_dsp; } - ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC, - CS35L41_INPUT_SRC_CLASSH); + ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX6_SRC, CS35L41_INPUT_SRC_VBSTMON); if (ret < 0) { - dev_err(cs35l41->dev, "Write INPUT_SRC_CLASSH failed: %d\n", ret); + dev_err(cs35l41->dev, "Write CS35L41_INPUT_SRC_VBSTMON failed: %d\n", ret); goto err_dsp; } ret = regmap_write(cs35l41->regmap, CS35L41_DSP1_RX7_SRC, diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c index 14a5f86019aad4..70ff55c1517fe0 100644 --- a/sound/soc/codecs/cs35l56-sdw.c +++ b/sound/soc/codecs/cs35l56-sdw.c @@ -188,8 +188,6 @@ static void cs35l56_sdw_init(struct sdw_slave *peripheral) goto out; } - regcache_cache_only(cs35l56->base.regmap, false); - ret = cs35l56_init(cs35l56); if (ret < 0) { regcache_cache_only(cs35l56->base.regmap, true); diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index 08cac58e3ab222..fd02b621da52c0 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -40,16 +40,11 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_set_patch, SND_SOC_CS35L56_SHARED); static const struct reg_default cs35l56_reg_defaults[] = { /* no defaults for OTP_MEM - first read populates cache */ - { CS35L56_ASP1_ENABLES1, 0x00000000 }, - { CS35L56_ASP1_CONTROL1, 0x00000028 }, - { CS35L56_ASP1_CONTROL2, 0x18180200 }, - { CS35L56_ASP1_CONTROL3, 0x00000002 }, - { CS35L56_ASP1_FRAME_CONTROL1, 0x03020100 }, - { CS35L56_ASP1_FRAME_CONTROL5, 0x00020100 }, - { CS35L56_ASP1_DATA_CONTROL1, 0x00000018 }, - { CS35L56_ASP1_DATA_CONTROL5, 0x00000018 }, - - /* no defaults for ASP1TX mixer */ + /* + * No defaults for ASP1 control or ASP1TX mixer. See + * cs35l56_populate_asp1_register_defaults() and + * cs35l56_sync_asp1_mixer_widgets_with_firmware(). + */ { CS35L56_SWIRE_DP3_CH1_INPUT, 0x00000018 }, { CS35L56_SWIRE_DP3_CH2_INPUT, 0x00000019 }, @@ -210,6 +205,36 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg) } } +static const struct reg_sequence cs35l56_asp1_defaults[] = { + REG_SEQ0(CS35L56_ASP1_ENABLES1, 0x00000000), + REG_SEQ0(CS35L56_ASP1_CONTROL1, 0x00000028), + REG_SEQ0(CS35L56_ASP1_CONTROL2, 0x18180200), + REG_SEQ0(CS35L56_ASP1_CONTROL3, 0x00000002), + REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL1, 0x03020100), + REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL5, 0x00020100), + REG_SEQ0(CS35L56_ASP1_DATA_CONTROL1, 0x00000018), + REG_SEQ0(CS35L56_ASP1_DATA_CONTROL5, 0x00000018), +}; + +/* + * The firmware can have control of the ASP so we don't provide regmap + * with defaults for these registers, to prevent a regcache_sync() from + * overwriting the firmware settings. But if the machine driver hooks up + * the ASP it means the driver is taking control of the ASP, so then the + * registers are populated with the defaults. + */ +int cs35l56_init_asp1_regs_for_driver_control(struct cs35l56_base *cs35l56_base) +{ + if (!cs35l56_base->fw_owns_asp1) + return 0; + + cs35l56_base->fw_owns_asp1 = false; + + return regmap_multi_reg_write(cs35l56_base->regmap, cs35l56_asp1_defaults, + ARRAY_SIZE(cs35l56_asp1_defaults)); +} +EXPORT_SYMBOL_NS_GPL(cs35l56_init_asp1_regs_for_driver_control, SND_SOC_CS35L56_SHARED); + /* * The firmware boot sequence can overwrite the ASP1 config registers so that * they don't match regmap's view of their values. Rewrite the values from the @@ -217,19 +242,15 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg) */ int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base) { - struct reg_sequence asp1_regs[] = { - { .reg = CS35L56_ASP1_ENABLES1 }, - { .reg = CS35L56_ASP1_CONTROL1 }, - { .reg = CS35L56_ASP1_CONTROL2 }, - { .reg = CS35L56_ASP1_CONTROL3 }, - { .reg = CS35L56_ASP1_FRAME_CONTROL1 }, - { .reg = CS35L56_ASP1_FRAME_CONTROL5 }, - { .reg = CS35L56_ASP1_DATA_CONTROL1 }, - { .reg = CS35L56_ASP1_DATA_CONTROL5 }, - }; + struct reg_sequence asp1_regs[ARRAY_SIZE(cs35l56_asp1_defaults)]; int i, ret; - /* Read values from regmap cache into a write sequence */ + if (cs35l56_base->fw_owns_asp1) + return 0; + + memcpy(asp1_regs, cs35l56_asp1_defaults, sizeof(asp1_regs)); + + /* Read current values from regmap cache into the write sequence */ for (i = 0; i < ARRAY_SIZE(asp1_regs); ++i) { ret = regmap_read(cs35l56_base->regmap, asp1_regs[i].reg, &asp1_regs[i].def); if (ret) @@ -307,10 +328,10 @@ int cs35l56_wait_for_firmware_boot(struct cs35l56_base *cs35l56_base) reg = CS35L56_DSP1_HALO_STATE; /* - * This can't be a regmap_read_poll_timeout() because cs35l56 will NAK - * I2C until it has booted which would terminate the poll + * The regmap must remain in cache-only until the chip has + * booted, so use a bypassed read of the status register. */ - poll_ret = read_poll_timeout(regmap_read, read_ret, + poll_ret = read_poll_timeout(regmap_read_bypassed, read_ret, (val < 0xFFFF) && (val >= CS35L56_HALO_STATE_BOOT_DONE), CS35L56_HALO_STATE_POLL_US, CS35L56_HALO_STATE_TIMEOUT_US, @@ -362,7 +383,8 @@ void cs35l56_system_reset(struct cs35l56_base *cs35l56_base, bool is_soundwire) return; cs35l56_wait_control_port_ready(); - regcache_cache_only(cs35l56_base->regmap, false); + + /* Leave in cache-only. This will be revoked when the chip has rebooted. */ } EXPORT_SYMBOL_NS_GPL(cs35l56_system_reset, SND_SOC_CS35L56_SHARED); @@ -577,14 +599,14 @@ int cs35l56_runtime_resume_common(struct cs35l56_base *cs35l56_base, bool is_sou cs35l56_issue_wake_event(cs35l56_base); out_sync: - regcache_cache_only(cs35l56_base->regmap, false); - ret = cs35l56_wait_for_firmware_boot(cs35l56_base); if (ret) { dev_err(cs35l56_base->dev, "Hibernate wake failed: %d\n", ret); goto err; } + regcache_cache_only(cs35l56_base->regmap, false); + ret = cs35l56_mbox_send(cs35l56_base, CS35L56_MBOX_CMD_PREVENT_AUTO_HIBERNATE); if (ret) goto err; @@ -684,7 +706,7 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_calibration_controls, SND_SOC_CS35L56_SHARED); int cs35l56_get_calibration(struct cs35l56_base *cs35l56_base) { - u64 silicon_uid; + u64 silicon_uid = 0; int ret; /* Driver can't apply calibration to a secured part, so skip */ @@ -757,7 +779,7 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) * devices so the REVID needs to be determined before waiting for the * firmware to boot. */ - ret = regmap_read(cs35l56_base->regmap, CS35L56_REVID, &revid); + ret = regmap_read_bypassed(cs35l56_base->regmap, CS35L56_REVID, &revid); if (ret < 0) { dev_err(cs35l56_base->dev, "Get Revision ID failed\n"); return ret; @@ -768,7 +790,7 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) if (ret) return ret; - ret = regmap_read(cs35l56_base->regmap, CS35L56_DEVID, &devid); + ret = regmap_read_bypassed(cs35l56_base->regmap, CS35L56_DEVID, &devid); if (ret < 0) { dev_err(cs35l56_base->dev, "Get Device ID failed\n"); return ret; @@ -787,6 +809,9 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base) cs35l56_base->type = devid & 0xFF; + /* Silicon is now identified and booted so exit cache-only */ + regcache_cache_only(cs35l56_base->regmap, false); + ret = regmap_read(cs35l56_base->regmap, CS35L56_DSP_RESTRICT_STS1, &secured); if (ret) { dev_err(cs35l56_base->dev, "Get Secure status failed\n"); diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 8d2f021fb36281..6331b8c6136eaf 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -454,9 +454,14 @@ static int cs35l56_asp_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int f { struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component); unsigned int val; + int ret; dev_dbg(cs35l56->base.dev, "%s: %#x\n", __func__, fmt); + ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base); + if (ret) + return ret; + switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) { case SND_SOC_DAIFMT_CBC_CFC: break; @@ -530,6 +535,11 @@ static int cs35l56_asp_dai_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx unsigned int rx_mask, int slots, int slot_width) { struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component); + int ret; + + ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base); + if (ret) + return ret; if ((slots == 0) || (slot_width == 0)) { dev_dbg(cs35l56->base.dev, "tdm config cleared\n"); @@ -578,6 +588,11 @@ static int cs35l56_asp_dai_hw_params(struct snd_pcm_substream *substream, struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component); unsigned int rate = params_rate(params); u8 asp_width, asp_wl; + int ret; + + ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base); + if (ret) + return ret; asp_wl = params_width(params); if (cs35l56->asp_slot_width) @@ -634,7 +649,11 @@ static int cs35l56_asp_dai_set_sysclk(struct snd_soc_dai *dai, int clk_id, unsigned int freq, int dir) { struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component); - int freq_id; + int freq_id, ret; + + ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base); + if (ret) + return ret; if (freq == 0) { cs35l56->sysclk_set = false; @@ -1403,6 +1422,9 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56) cs35l56->base.cal_index = -1; cs35l56->speaker_id = -ENOENT; + /* Assume that the firmware owns ASP1 until we know different */ + cs35l56->base.fw_owns_asp1 = true; + dev_set_drvdata(cs35l56->base.dev, cs35l56); cs35l56_fill_supply_names(cs35l56->supplies); @@ -1531,6 +1553,8 @@ post_soft_reset: return ret; dev_dbg(cs35l56->base.dev, "Firmware rebooted after soft reset\n"); + + regcache_cache_only(cs35l56->base.regmap, false); } /* Disable auto-hibernate so that runtime_pm has control */ diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index e3ba04484813a2..d0d24a53df7462 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -444,6 +444,7 @@ struct rt5645_priv { struct regmap *regmap; struct i2c_client *i2c; struct gpio_desc *gpiod_hp_det; + struct gpio_desc *gpiod_cbj_sleeve; struct snd_soc_jack *hp_jack; struct snd_soc_jack *mic_jack; struct snd_soc_jack *btn_jack; @@ -3186,6 +3187,9 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse regmap_update_bits(rt5645->regmap, RT5645_IN1_CTRL2, RT5645_CBJ_MN_JD, 0); + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 1); + msleep(600); regmap_read(rt5645->regmap, RT5645_IN1_CTRL3, &val); val &= 0x7; @@ -3202,6 +3206,8 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse snd_soc_dapm_disable_pin(dapm, "Mic Det Power"); snd_soc_dapm_sync(dapm); rt5645->jack_type = SND_JACK_HEADPHONE; + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } if (rt5645->pdata.level_trigger_irq) regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2, @@ -3229,6 +3235,9 @@ static int rt5645_jack_detect(struct snd_soc_component *component, int jack_inse if (rt5645->pdata.level_trigger_irq) regmap_update_bits(rt5645->regmap, RT5645_IRQ_CTRL2, RT5645_JD_1_1_MASK, RT5645_JD_1_1_INV); + + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } return rt5645->jack_type; @@ -4012,6 +4021,16 @@ static int rt5645_i2c_probe(struct i2c_client *i2c) return ret; } + rt5645->gpiod_cbj_sleeve = devm_gpiod_get_optional(&i2c->dev, "cbj-sleeve", + GPIOD_OUT_LOW); + + if (IS_ERR(rt5645->gpiod_cbj_sleeve)) { + ret = PTR_ERR(rt5645->gpiod_cbj_sleeve); + dev_info(&i2c->dev, "failed to initialize gpiod, ret=%d\n", ret); + if (ret != -ENOENT) + return ret; + } + for (i = 0; i < ARRAY_SIZE(rt5645->supplies); i++) rt5645->supplies[i].supply = rt5645_supply_names[i]; @@ -4259,6 +4278,9 @@ static void rt5645_i2c_remove(struct i2c_client *i2c) cancel_delayed_work_sync(&rt5645->jack_detect_work); cancel_delayed_work_sync(&rt5645->rcclock_work); + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); + regulator_bulk_disable(ARRAY_SIZE(rt5645->supplies), rt5645->supplies); } @@ -4274,6 +4296,9 @@ static void rt5645_i2c_shutdown(struct i2c_client *i2c) 0); msleep(20); regmap_write(rt5645->regmap, RT5645_RESET, 0); + + if (rt5645->gpiod_cbj_sleeve) + gpiod_set_value(rt5645->gpiod_cbj_sleeve, 0); } static int __maybe_unused rt5645_sys_suspend(struct device *dev) diff --git a/sound/soc/codecs/rt715-sdca.c b/sound/soc/codecs/rt715-sdca.c index 3fb7b9adb61de6..bc3579203c7a47 100644 --- a/sound/soc/codecs/rt715-sdca.c +++ b/sound/soc/codecs/rt715-sdca.c @@ -316,7 +316,7 @@ static int rt715_sdca_set_amp_gain_8ch_get(struct snd_kcontrol *kcontrol, return 0; } -static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -17625, 375, 0); +static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -1725, 75, 0); static const DECLARE_TLV_DB_SCALE(mic_vol_tlv, 0, 1000, 0); static int rt715_sdca_get_volsw(struct snd_kcontrol *kcontrol, @@ -477,7 +477,7 @@ static const struct snd_kcontrol_new rt715_sdca_snd_controls[] = { RT715_SDCA_FU_VOL_CTRL, CH_01), SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_ADC7_27_VOL, RT715_SDCA_FU_VOL_CTRL, CH_02), - 0x2f, 0x7f, 0, + 0x2f, 0x3f, 0, rt715_sdca_set_amp_gain_get, rt715_sdca_set_amp_gain_put, in_vol_tlv), RT715_SDCA_EXT_TLV("FU02 Capture Volume", @@ -485,13 +485,13 @@ static const struct snd_kcontrol_new rt715_sdca_snd_controls[] = { RT715_SDCA_FU_VOL_CTRL, CH_01), rt715_sdca_set_amp_gain_4ch_get, rt715_sdca_set_amp_gain_4ch_put, - in_vol_tlv, 4, 0x7f), + in_vol_tlv, 4, 0x3f), RT715_SDCA_EXT_TLV("FU06 Capture Volume", SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_ADC10_11_VOL, RT715_SDCA_FU_VOL_CTRL, CH_01), rt715_sdca_set_amp_gain_4ch_get, rt715_sdca_set_amp_gain_4ch_put, - in_vol_tlv, 4, 0x7f), + in_vol_tlv, 4, 0x3f), /* MIC Boost Control */ RT715_SDCA_BOOST_EXT_TLV("FU0E Boost", SDW_SDCA_CTL(FUN_MIC_ARRAY, RT715_SDCA_FU_DMIC_GAIN_EN, diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c index 7e13868ff99f03..f012fe0ded6d28 100644 --- a/sound/soc/codecs/rt715-sdw.c +++ b/sound/soc/codecs/rt715-sdw.c @@ -111,6 +111,7 @@ static bool rt715_readable_register(struct device *dev, unsigned int reg) case 0x839d: case 0x83a7: case 0x83a9: + case 0x752001: case 0x752039: return true; default: diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c index e0ea3a23f7cc68..e5bd9ef812de13 100644 --- a/sound/soc/codecs/rt722-sdca.c +++ b/sound/soc/codecs/rt722-sdca.c @@ -1330,7 +1330,7 @@ static struct snd_soc_dai_driver rt722_sdca_dai[] = { .capture = { .stream_name = "DP6 DMic Capture", .channels_min = 1, - .channels_max = 2, + .channels_max = 4, .rates = RT722_STEREO_RATES, .formats = RT722_FORMATS, }, @@ -1439,9 +1439,12 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) int loop_check, chk_cnt = 100, ret; unsigned int calib_status = 0; - /* Read eFuse */ - rt722_sdca_index_write(rt722, RT722_VENDOR_SPK_EFUSE, RT722_DC_CALIB_CTRL, - 0x4808); + /* Config analog bias */ + rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_ANALOG_BIAS_CTL3, + 0xa081); + /* GE related settings */ + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_GE_RELATED_CTL2, + 0xa009); /* Button A, B, C, D bypass mode */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_UMP_HID_CTL4, 0xcf00); @@ -1475,9 +1478,6 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) if ((calib_status & 0x0040) == 0x0) break; } - /* Release HP-JD, EN_CBJ_TIE_GL/R open, en_osw gating auto done bit */ - rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4, - 0x0010); /* Set ADC09 power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ADC0A_08_PDE_FLOAT_CTL, 0x2a12); @@ -1490,8 +1490,21 @@ static void rt722_sdca_jack_preset(struct rt722_sdca_priv *rt722) /* Set DAC03 and HP power entity floating control */ rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_DAC03_HP_PDE_FLOAT_CTL, 0x4040); + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_ENT_FLOAT_CTRL_1, + 0x4141); + rt722_sdca_index_write(rt722, RT722_VENDOR_HDA_CTL, RT722_FLOAT_CTRL_1, + 0x0101); /* Fine tune PDE40 latency */ regmap_write(rt722->regmap, 0x2f58, 0x07); + regmap_write(rt722->regmap, 0x2f03, 0x06); + /* MIC VRefo */ + rt722_sdca_index_update_bits(rt722, RT722_VENDOR_REG, + RT722_COMBO_JACK_AUTO_CTL1, 0x0200, 0x0200); + rt722_sdca_index_update_bits(rt722, RT722_VENDOR_REG, + RT722_VREFO_GAT, 0x4000, 0x4000); + /* Release HP-JD, EN_CBJ_TIE_GL/R open, en_osw gating auto done bit */ + rt722_sdca_index_write(rt722, RT722_VENDOR_REG, RT722_DIGITAL_MISC_CTRL4, + 0x0010); } int rt722_sdca_io_init(struct device *dev, struct sdw_slave *slave) diff --git a/sound/soc/codecs/rt722-sdca.h b/sound/soc/codecs/rt722-sdca.h index 44af8901352eb6..2464361a7958c6 100644 --- a/sound/soc/codecs/rt722-sdca.h +++ b/sound/soc/codecs/rt722-sdca.h @@ -69,6 +69,7 @@ struct rt722_sdca_dmic_kctrl_priv { #define RT722_COMBO_JACK_AUTO_CTL2 0x46 #define RT722_COMBO_JACK_AUTO_CTL3 0x47 #define RT722_DIGITAL_MISC_CTRL4 0x4a +#define RT722_VREFO_GAT 0x63 #define RT722_FSM_CTL 0x67 #define RT722_SDCA_INTR_REC 0x82 #define RT722_SW_CONFIG1 0x8a @@ -127,6 +128,8 @@ struct rt722_sdca_dmic_kctrl_priv { #define RT722_UMP_HID_CTL6 0x66 #define RT722_UMP_HID_CTL7 0x67 #define RT722_UMP_HID_CTL8 0x68 +#define RT722_FLOAT_CTRL_1 0x70 +#define RT722_ENT_FLOAT_CTRL_1 0x76 /* Parameter & Verb control 01 (0x1a)(NID:20h) */ #define RT722_HIDDEN_REG_SW_RESET (0x1 << 14) diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 3c025dabaf7a47..1253695bebd863 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -1155,6 +1155,7 @@ static int wsa881x_probe(struct sdw_slave *pdev, pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS, 0); pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop; pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY; + pdev->prop.clk_stop_mode1 = true; gpiod_direction_output(wsa881x->sd_n, !wsa881x->sd_n_val); wsa881x->regmap = devm_regmap_init_sdw(pdev, &wsa881x_regmap_config); diff --git a/sound/soc/intel/avs/icl.c b/sound/soc/intel/avs/icl.c index 9d9921e1cd4ded..d2554c8577326b 100644 --- a/sound/soc/intel/avs/icl.c +++ b/sound/soc/intel/avs/icl.c @@ -64,7 +64,7 @@ struct avs_icl_memwnd2_desc { struct avs_icl_memwnd2 { union { struct avs_icl_memwnd2_desc slot_desc[AVS_ICL_MEMWND2_SLOTS_COUNT]; - u8 rsvd[PAGE_SIZE]; + u8 rsvd[SZ_4K]; }; u8 slot_array[AVS_ICL_MEMWND2_SLOTS_COUNT][PAGE_SIZE]; } __packed; diff --git a/sound/soc/intel/avs/topology.c b/sound/soc/intel/avs/topology.c index 13061bd1488bb4..42b42903ae9de7 100644 --- a/sound/soc/intel/avs/topology.c +++ b/sound/soc/intel/avs/topology.c @@ -1582,6 +1582,8 @@ static int avs_widget_load(struct snd_soc_component *comp, int index, if (!le32_to_cpu(dw->priv.size)) return 0; + w->no_wname_in_kcontrol_name = true; + if (w->ignore_suspend && !AVS_S0IX_SUPPORTED) { dev_info_once(comp->dev, "Device does not support S0IX, check BIOS settings\n"); w->ignore_suspend = false; diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 05f38d1f7d824d..b41a1147f1c345 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -636,28 +636,30 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_USE_AMCR0F28), }, { + /* Asus T100TAF, unlike other T100TA* models this one has a mono speaker */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), }, .driver_data = (void *)(BYT_RT5640_IN1_MAP | BYT_RT5640_JD_SRC_JD2_IN4N | BYT_RT5640_OVCD_TH_2000UA | BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_MONO_SPEAKER | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, { + /* Asus T100TA and T100TAM, must come after T100TAF (mono spk) match */ .matches = { - DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TAF"), + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T100TA"), }, .driver_data = (void *)(BYT_RT5640_IN1_MAP | BYT_RT5640_JD_SRC_JD2_IN4N | BYT_RT5640_OVCD_TH_2000UA | BYT_RT5640_OVCD_SF_0P75 | - BYT_RT5640_MONO_SPEAKER | - BYT_RT5640_DIFF_MIC | - BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, { diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index cc84d4c81be9d3..238bda5f6b76fa 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -350,7 +350,9 @@ static int sof_init_environment(struct snd_sof_dev *sdev) } ret = sof_select_ipc_and_paths(sdev); - if (!ret && plat_data->ipc_type != base_profile->ipc_type) { + if (ret) { + goto err_machine_check; + } else if (plat_data->ipc_type != base_profile->ipc_type) { /* IPC type changed, re-initialize the ops */ sof_ops_free(sdev); diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c index 7c8aafca8fdef8..7275437ea8d8a5 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -330,14 +330,32 @@ EXPORT_SYMBOL_GPL(snd_sof_dbg_memory_info_init); int snd_sof_dbg_init(struct snd_sof_dev *sdev) { + struct snd_sof_pdata *plat_data = sdev->pdata; struct snd_sof_dsp_ops *ops = sof_ops(sdev); const struct snd_sof_debugfs_map *map; + struct dentry *fw_profile; int i; int err; /* use "sof" as top level debugFS dir */ sdev->debugfs_root = debugfs_create_dir("sof", NULL); + /* expose firmware/topology prefix/names for test purposes */ + fw_profile = debugfs_create_dir("fw_profile", sdev->debugfs_root); + + debugfs_create_str("fw_path", 0444, fw_profile, + (char **)&plat_data->fw_filename_prefix); + debugfs_create_str("fw_lib_path", 0444, fw_profile, + (char **)&plat_data->fw_lib_prefix); + debugfs_create_str("tplg_path", 0444, fw_profile, + (char **)&plat_data->tplg_filename_prefix); + debugfs_create_str("fw_name", 0444, fw_profile, + (char **)&plat_data->fw_filename); + debugfs_create_str("tplg_name", 0444, fw_profile, + (char **)&plat_data->tplg_filename); + debugfs_create_u32("ipc_type", 0444, fw_profile, + (u32 *)&plat_data->ipc_type); + /* init dfsentry list */ INIT_LIST_HEAD(&sdev->dfsentry_list); diff --git a/sound/soc/sof/intel/pci-lnl.c b/sound/soc/sof/intel/pci-lnl.c index b26ffe767fab55..b14e508f1f315b 100644 --- a/sound/soc/sof/intel/pci-lnl.c +++ b/sound/soc/sof/intel/pci-lnl.c @@ -35,6 +35,9 @@ static const struct sof_dev_desc lnl_desc = { .default_fw_path = { [SOF_IPC_TYPE_4] = "intel/sof-ipc4/lnl", }, + .default_lib_path = { + [SOF_IPC_TYPE_4] = "intel/sof-ipc4-lib/lnl", + }, .default_tplg_path = { [SOF_IPC_TYPE_4] = "intel/sof-ipc4-tplg", }, diff --git a/sound/soc/sof/ipc3-pcm.c b/sound/soc/sof/ipc3-pcm.c index 35769dd7905ebe..af0bf354cb209e 100644 --- a/sound/soc/sof/ipc3-pcm.c +++ b/sound/soc/sof/ipc3-pcm.c @@ -434,4 +434,5 @@ const struct sof_ipc_pcm_ops ipc3_pcm_ops = { .trigger = sof_ipc3_pcm_trigger, .dai_link_fixup = sof_ipc3_pcm_dai_link_fixup, .reset_hw_params_during_stop = true, + .d0i3_supported_in_s0ix = true, }; diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c index e915f9f87a6c35..4594470ed08b1e 100644 --- a/sound/soc/sof/ipc4-pcm.c +++ b/sound/soc/sof/ipc4-pcm.c @@ -37,6 +37,25 @@ struct sof_ipc4_timestamp_info { snd_pcm_sframes_t delay; }; +/** + * struct sof_ipc4_pcm_stream_priv - IPC4 specific private data + * @time_info: pointer to time info struct if it is supported, otherwise NULL + * @chain_dma_allocated: indicates the ChainDMA allocation state + */ +struct sof_ipc4_pcm_stream_priv { + struct sof_ipc4_timestamp_info *time_info; + + bool chain_dma_allocated; +}; + +static inline struct sof_ipc4_timestamp_info * +sof_ipc4_sps_to_time_info(struct snd_sof_pcm_stream *sps) +{ + struct sof_ipc4_pcm_stream_priv *stream_priv = sps->private; + + return stream_priv->time_info; +} + static int sof_ipc4_set_multi_pipeline_state(struct snd_sof_dev *sdev, u32 state, struct ipc4_pipeline_set_state_data *trigger_list) { @@ -253,14 +272,17 @@ sof_ipc4_update_pipeline_state(struct snd_sof_dev *sdev, int state, int cmd, */ static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev, - int direction, + struct snd_sof_pcm *spcm, int direction, struct snd_sof_pcm_stream_pipeline_list *pipeline_list, int state, int cmd) { struct sof_ipc4_fw_data *ipc4_data = sdev->private; + struct sof_ipc4_pcm_stream_priv *stream_priv; bool allocate, enable, set_fifo_size; struct sof_ipc4_msg msg = {{ 0 }}; - int i; + int ret, i; + + stream_priv = spcm->stream[direction].private; switch (state) { case SOF_IPC4_PIPE_RUNNING: /* Allocate and start chained dma */ @@ -281,6 +303,11 @@ static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev, set_fifo_size = false; break; case SOF_IPC4_PIPE_RESET: /* Disable and free chained DMA. */ + + /* ChainDMA can only be reset if it has been allocated */ + if (!stream_priv->chain_dma_allocated) + return 0; + allocate = false; enable = false; set_fifo_size = false; @@ -338,7 +365,12 @@ static int sof_ipc4_chain_dma_trigger(struct snd_sof_dev *sdev, if (enable) msg.primary |= SOF_IPC4_GLB_CHAIN_DMA_ENABLE_MASK; - return sof_ipc_tx_message_no_reply(sdev->ipc, &msg, 0); + ret = sof_ipc_tx_message_no_reply(sdev->ipc, &msg, 0); + /* Update the ChainDMA allocation state */ + if (!ret) + stream_priv->chain_dma_allocated = allocate; + + return ret; } static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, @@ -378,7 +410,7 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, * trigger function that handles the rest for the substream. */ if (pipeline->use_chain_dma) - return sof_ipc4_chain_dma_trigger(sdev, substream->stream, + return sof_ipc4_chain_dma_trigger(sdev, spcm, substream->stream, pipeline_list, state, cmd); /* allocate memory for the pipeline data */ @@ -452,7 +484,7 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component, * Invalidate the stream_start_offset to make sure that it is * going to be updated if the stream resumes */ - time_info = spcm->stream[substream->stream].private; + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); if (time_info) time_info->stream_start_offset = SOF_IPC4_INVALID_STREAM_POSITION; @@ -706,12 +738,16 @@ static int sof_ipc4_pcm_dai_link_fixup(struct snd_soc_pcm_runtime *rtd, static void sof_ipc4_pcm_free(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm) { struct snd_sof_pcm_stream_pipeline_list *pipeline_list; + struct sof_ipc4_pcm_stream_priv *stream_priv; int stream; for_each_pcm_streams(stream) { pipeline_list = &spcm->stream[stream].pipeline_list; kfree(pipeline_list->pipelines); pipeline_list->pipelines = NULL; + + stream_priv = spcm->stream[stream].private; + kfree(stream_priv->time_info); kfree(spcm->stream[stream].private); spcm->stream[stream].private = NULL; } @@ -721,7 +757,8 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm { struct snd_sof_pcm_stream_pipeline_list *pipeline_list; struct sof_ipc4_fw_data *ipc4_data = sdev->private; - struct sof_ipc4_timestamp_info *stream_info; + struct sof_ipc4_pcm_stream_priv *stream_priv; + struct sof_ipc4_timestamp_info *time_info; bool support_info = true; u32 abi_version; u32 abi_offset; @@ -749,33 +786,41 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm return -ENOMEM; } + stream_priv = kzalloc(sizeof(*stream_priv), GFP_KERNEL); + if (!stream_priv) { + sof_ipc4_pcm_free(sdev, spcm); + return -ENOMEM; + } + + spcm->stream[stream].private = stream_priv; + if (!support_info) continue; - stream_info = kzalloc(sizeof(*stream_info), GFP_KERNEL); - if (!stream_info) { + time_info = kzalloc(sizeof(*time_info), GFP_KERNEL); + if (!time_info) { sof_ipc4_pcm_free(sdev, spcm); return -ENOMEM; } - spcm->stream[stream].private = stream_info; + stream_priv->time_info = time_info; } return 0; } -static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *spcm) +static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *sps) { struct sof_ipc4_copier *host_copier = NULL; struct sof_ipc4_copier *dai_copier = NULL; struct sof_ipc4_llp_reading_slot llp_slot; - struct sof_ipc4_timestamp_info *info; + struct sof_ipc4_timestamp_info *time_info; struct snd_soc_dapm_widget *widget; struct snd_sof_dai *dai; int i; /* find host & dai to locate info in memory window */ - for_each_dapm_widgets(spcm->list, i, widget) { + for_each_dapm_widgets(sps->list, i, widget) { struct snd_sof_widget *swidget = widget->dobj.private; if (!swidget) @@ -795,44 +840,44 @@ static void sof_ipc4_build_time_info(struct snd_sof_dev *sdev, struct snd_sof_pc return; } - info = spcm->private; - info->host_copier = host_copier; - info->dai_copier = dai_copier; - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_gpdma_reading_slots) + - sdev->fw_info_box.offset; + time_info = sof_ipc4_sps_to_time_info(sps); + time_info->host_copier = host_copier; + time_info->dai_copier = dai_copier; + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_gpdma_reading_slots) + sdev->fw_info_box.offset; /* find llp slot used by current dai */ for (i = 0; i < SOF_IPC4_MAX_LLP_GPDMA_READING_SLOTS; i++) { - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id == dai_copier->data.gtw_cfg.node_id) break; - info->llp_offset += sizeof(llp_slot); + time_info->llp_offset += sizeof(llp_slot); } if (i < SOF_IPC4_MAX_LLP_GPDMA_READING_SLOTS) return; /* if no llp gpdma slot is used, check aggregated sdw slot */ - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_sndw_reading_slots) + - sdev->fw_info_box.offset; + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_sndw_reading_slots) + sdev->fw_info_box.offset; for (i = 0; i < SOF_IPC4_MAX_LLP_SNDW_READING_SLOTS; i++) { - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id == dai_copier->data.gtw_cfg.node_id) break; - info->llp_offset += sizeof(llp_slot); + time_info->llp_offset += sizeof(llp_slot); } if (i < SOF_IPC4_MAX_LLP_SNDW_READING_SLOTS) return; /* check EVAD slot */ - info->llp_offset = offsetof(struct sof_ipc4_fw_registers, llp_evad_reading_slot) + - sdev->fw_info_box.offset; - sof_mailbox_read(sdev, info->llp_offset, &llp_slot, sizeof(llp_slot)); + time_info->llp_offset = offsetof(struct sof_ipc4_fw_registers, + llp_evad_reading_slot) + sdev->fw_info_box.offset; + sof_mailbox_read(sdev, time_info->llp_offset, &llp_slot, sizeof(llp_slot)); if (llp_slot.node_id != dai_copier->data.gtw_cfg.node_id) - info->llp_offset = 0; + time_info->llp_offset = 0; } static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, @@ -849,7 +894,7 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, if (!spcm) return -EINVAL; - time_info = spcm->stream[substream->stream].private; + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); /* delay calculation is not supported by current fw_reg ABI */ if (!time_info) return 0; @@ -864,7 +909,7 @@ static int sof_ipc4_pcm_hw_params(struct snd_soc_component *component, static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream, - struct snd_sof_pcm_stream *stream, + struct snd_sof_pcm_stream *sps, struct sof_ipc4_timestamp_info *time_info) { struct sof_ipc4_copier *host_copier = time_info->host_copier; @@ -918,7 +963,7 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, struct sof_ipc4_timestamp_info *time_info; struct sof_ipc4_llp_reading_slot llp; snd_pcm_uframes_t head_cnt, tail_cnt; - struct snd_sof_pcm_stream *stream; + struct snd_sof_pcm_stream *sps; u64 dai_cnt, host_cnt, host_ptr; struct snd_sof_pcm *spcm; int ret; @@ -927,8 +972,8 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, if (!spcm) return -EOPNOTSUPP; - stream = &spcm->stream[substream->stream]; - time_info = stream->private; + sps = &spcm->stream[substream->stream]; + time_info = sof_ipc4_sps_to_time_info(sps); if (!time_info) return -EOPNOTSUPP; @@ -938,7 +983,7 @@ static int sof_ipc4_pcm_pointer(struct snd_soc_component *component, * the statistics is complete. And it will not change after the first initiailization. */ if (time_info->stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION) { - ret = sof_ipc4_get_stream_start_offset(sdev, substream, stream, time_info); + ret = sof_ipc4_get_stream_start_offset(sdev, substream, sps, time_info); if (ret < 0) return -EOPNOTSUPP; } @@ -1030,15 +1075,13 @@ static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component, { struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct sof_ipc4_timestamp_info *time_info; - struct snd_sof_pcm_stream *stream; struct snd_sof_pcm *spcm; spcm = snd_sof_find_spcm_dai(component, rtd); if (!spcm) return 0; - stream = &spcm->stream[substream->stream]; - time_info = stream->private; + time_info = sof_ipc4_sps_to_time_info(&spcm->stream[substream->stream]); /* * Report the stored delay value calculated in the pointer callback. * In the unlikely event that the calculation was skipped/aborted, the diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index f03cee94bce626..8804e00e7251b9 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -325,14 +325,13 @@ static int sof_pcm_trigger(struct snd_soc_component *component, ipc_first = true; break; case SNDRV_PCM_TRIGGER_SUSPEND: - if (sdev->system_suspend_target == SOF_SUSPEND_S0IX && + /* + * If DSP D0I3 is allowed during S0iX, set the suspend_ignored flag for + * D0I3-compatible streams to keep the firmware pipeline running + */ + if (pcm_ops && pcm_ops->d0i3_supported_in_s0ix && + sdev->system_suspend_target == SOF_SUSPEND_S0IX && spcm->stream[substream->stream].d0i3_compatible) { - /* - * trap the event, not sending trigger stop to - * prevent the FW pipelines from being stopped, - * and mark the flag to ignore the upcoming DAPM - * PM events. - */ spcm->stream[substream->stream].suspend_ignored = true; return 0; } diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h index 86bbb531e142c7..499b6084b52637 100644 --- a/sound/soc/sof/sof-audio.h +++ b/sound/soc/sof/sof-audio.h @@ -116,6 +116,7 @@ struct snd_sof_dai_config_data { * triggers. The FW keeps the host DMA running in this case and * therefore the host must do the same and should stop the DMA during * hw_free. + * @d0i3_supported_in_s0ix: Allow DSP D0I3 during S0iX */ struct sof_ipc_pcm_ops { int (*hw_params)(struct snd_soc_component *component, struct snd_pcm_substream *substream, @@ -135,6 +136,7 @@ struct sof_ipc_pcm_ops { bool reset_hw_params_during_stop; bool ipc_first_on_start; bool platform_stop_during_hw_free; + bool d0i3_supported_in_s0ix; }; /** diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c index aa37c4ab0adbd9..21cd41fec7a9cb 100644 --- a/sound/soc/tegra/tegra186_dspk.c +++ b/sound/soc/tegra/tegra186_dspk.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only +// SPDX-FileCopyrightText: Copyright (c) 2020-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved. // // tegra186_dspk.c - Tegra186 DSPK driver -// -// Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved. #include <linux/clk.h> #include <linux/device.h> @@ -241,14 +240,14 @@ static int tegra186_dspk_hw_params(struct snd_pcm_substream *substream, return -EINVAL; } - cif_conf.client_bits = TEGRA_ACIF_BITS_24; - switch (params_format(params)) { case SNDRV_PCM_FORMAT_S16_LE: cif_conf.audio_bits = TEGRA_ACIF_BITS_16; + cif_conf.client_bits = TEGRA_ACIF_BITS_16; break; case SNDRV_PCM_FORMAT_S32_LE: cif_conf.audio_bits = TEGRA_ACIF_BITS_32; + cif_conf.client_bits = TEGRA_ACIF_BITS_24; break; default: dev_err(dev, "unsupported format!\n"); diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c index b892d66f78470a..1e760c3155213d 100644 --- a/sound/soc/ti/davinci-mcasp.c +++ b/sound/soc/ti/davinci-mcasp.c @@ -2417,12 +2417,6 @@ static int davinci_mcasp_probe(struct platform_device *pdev) mcasp_reparent_fck(pdev); - ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component, - &davinci_mcasp_dai[mcasp->op_mode], 1); - - if (ret != 0) - goto err; - ret = davinci_mcasp_get_dma_type(mcasp); switch (ret) { case PCM_EDMA: @@ -2449,6 +2443,12 @@ static int davinci_mcasp_probe(struct platform_device *pdev) goto err; } + ret = devm_snd_soc_register_component(&pdev->dev, &davinci_mcasp_component, + &davinci_mcasp_dai[mcasp->op_mode], 1); + + if (ret != 0) + goto err; + no_audio: ret = davinci_mcasp_init_gpiochip(mcasp); if (ret) { diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py index 1d3a90d93fe267..270c28a0d09801 100644 --- a/tools/cgroup/memcg_slabinfo.py +++ b/tools/cgroup/memcg_slabinfo.py @@ -146,12 +146,11 @@ def detect_kernel_config(): def for_each_slab(prog): - PGSlab = 1 << prog.constant('PG_slab') - PGHead = 1 << prog.constant('PG_head') + PGSlab = ~prog.constant('PG_slab') for page in for_each_page(prog): try: - if page.flags.value_() & PGSlab: + if page.page_type.value_() == PGSlab: yield cast('struct slab *', page) except FaultError: pass diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index ae57bf69ad4af3..ae695911641b3b 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -94,6 +94,8 @@ static char *lic_version = "Unknown version"; static char full_domain_name[HV_KVP_EXCHANGE_MAX_VALUE_SIZE]; static struct utsname uts_buf; +#define CFG_HEADER "# Generated by Hyper-V key-value pair daemon. Please do not modify.\n" + /* * The location of the interface configuration file. */ @@ -1435,6 +1437,18 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) return HV_E_FAIL; } + /* Write the config file headers */ + error = fprintf(ifcfg_file, CFG_HEADER); + if (error < 0) { + error = HV_E_FAIL; + goto setval_error; + } + error = fprintf(nmfile, CFG_HEADER); + if (error < 0) { + error = HV_E_FAIL; + goto setval_error; + } + /* * First write out the MAC address. */ diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h index 570bb9794421b9..95483c7d81df74 100644 --- a/tools/include/linux/rbtree_augmented.h +++ b/tools/include/linux/rbtree_augmented.h @@ -158,13 +158,13 @@ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { - rb->__rb_parent_color = rb_color(rb) | (unsigned long)p; + rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { - rb->__rb_parent_color = (unsigned long)p | color; + rb->__rb_parent_color = (unsigned long)p + color; } static inline void diff --git a/tools/include/uapi/linux/memfd.h b/tools/include/uapi/linux/memfd.h new file mode 100644 index 00000000000000..01c0324e773316 --- /dev/null +++ b/tools/include/uapi/linux/memfd.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_MEMFD_H +#define _LINUX_MEMFD_H + +#include <asm-generic/hugetlb_encode.h> + +/* flags for memfd_create(2) (unsigned int) */ +#define MFD_CLOEXEC 0x0001U +#define MFD_ALLOW_SEALING 0x0002U +#define MFD_HUGETLB 0x0004U +/* not executable and sealed to prevent changing to executable. */ +#define MFD_NOEXEC_SEAL 0x0008U +/* executable */ +#define MFD_EXEC 0x0010U + +/* + * Huge page size encoding when MFD_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MFD_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MFD_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MFD_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MFD_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MFD_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MFD_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MFD_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MFD_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MFD_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB +#define MFD_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MFD_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB +#define MFD_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MFD_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MFD_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + +#endif /* _LINUX_MEMFD_H */ diff --git a/tools/include/uapi/linux/userfaultfd.h b/tools/include/uapi/linux/userfaultfd.h new file mode 100644 index 00000000000000..4283de22d5b659 --- /dev/null +++ b/tools/include/uapi/linux/userfaultfd.h @@ -0,0 +1,386 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * include/linux/userfaultfd.h + * + * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> + * Copyright (C) 2015 Red Hat, Inc. + * + */ + +#ifndef _LINUX_USERFAULTFD_H +#define _LINUX_USERFAULTFD_H + +#include <linux/types.h> + +/* ioctls for /dev/userfaultfd */ +#define USERFAULTFD_IOC 0xAA +#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00) + +/* + * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and + * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR. In + * userfaultfd.h we assumed the kernel was reading (instead _IOC_READ + * means the userland is reading). + */ +#define UFFD_API ((__u64)0xAA) +#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \ + UFFDIO_REGISTER_MODE_WP | \ + UFFDIO_REGISTER_MODE_MINOR) +#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ + UFFD_FEATURE_EVENT_FORK | \ + UFFD_FEATURE_EVENT_REMAP | \ + UFFD_FEATURE_EVENT_REMOVE | \ + UFFD_FEATURE_EVENT_UNMAP | \ + UFFD_FEATURE_MISSING_HUGETLBFS | \ + UFFD_FEATURE_MISSING_SHMEM | \ + UFFD_FEATURE_SIGBUS | \ + UFFD_FEATURE_THREAD_ID | \ + UFFD_FEATURE_MINOR_HUGETLBFS | \ + UFFD_FEATURE_MINOR_SHMEM | \ + UFFD_FEATURE_EXACT_ADDRESS | \ + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ + UFFD_FEATURE_WP_UNPOPULATED | \ + UFFD_FEATURE_POISON | \ + UFFD_FEATURE_WP_ASYNC | \ + UFFD_FEATURE_MOVE) +#define UFFD_API_IOCTLS \ + ((__u64)1 << _UFFDIO_REGISTER | \ + (__u64)1 << _UFFDIO_UNREGISTER | \ + (__u64)1 << _UFFDIO_API) +#define UFFD_API_RANGE_IOCTLS \ + ((__u64)1 << _UFFDIO_WAKE | \ + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_ZEROPAGE | \ + (__u64)1 << _UFFDIO_MOVE | \ + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_POISON) +#define UFFD_API_RANGE_IOCTLS_BASIC \ + ((__u64)1 << _UFFDIO_WAKE | \ + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_POISON) + +/* + * Valid ioctl command number range with this API is from 0x00 to + * 0x3F. UFFDIO_API is the fixed number, everything else can be + * changed by implementing a different UFFD_API. If sticking to the + * same UFFD_API more ioctl can be added and userland will be aware of + * which ioctl the running kernel implements through the ioctl command + * bitmask written by the UFFDIO_API. + */ +#define _UFFDIO_REGISTER (0x00) +#define _UFFDIO_UNREGISTER (0x01) +#define _UFFDIO_WAKE (0x02) +#define _UFFDIO_COPY (0x03) +#define _UFFDIO_ZEROPAGE (0x04) +#define _UFFDIO_MOVE (0x05) +#define _UFFDIO_WRITEPROTECT (0x06) +#define _UFFDIO_CONTINUE (0x07) +#define _UFFDIO_POISON (0x08) +#define _UFFDIO_API (0x3F) + +/* userfaultfd ioctl ids */ +#define UFFDIO 0xAA +#define UFFDIO_API _IOWR(UFFDIO, _UFFDIO_API, \ + struct uffdio_api) +#define UFFDIO_REGISTER _IOWR(UFFDIO, _UFFDIO_REGISTER, \ + struct uffdio_register) +#define UFFDIO_UNREGISTER _IOR(UFFDIO, _UFFDIO_UNREGISTER, \ + struct uffdio_range) +#define UFFDIO_WAKE _IOR(UFFDIO, _UFFDIO_WAKE, \ + struct uffdio_range) +#define UFFDIO_COPY _IOWR(UFFDIO, _UFFDIO_COPY, \ + struct uffdio_copy) +#define UFFDIO_ZEROPAGE _IOWR(UFFDIO, _UFFDIO_ZEROPAGE, \ + struct uffdio_zeropage) +#define UFFDIO_MOVE _IOWR(UFFDIO, _UFFDIO_MOVE, \ + struct uffdio_move) +#define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \ + struct uffdio_writeprotect) +#define UFFDIO_CONTINUE _IOWR(UFFDIO, _UFFDIO_CONTINUE, \ + struct uffdio_continue) +#define UFFDIO_POISON _IOWR(UFFDIO, _UFFDIO_POISON, \ + struct uffdio_poison) + +/* read() structure */ +struct uffd_msg { + __u8 event; + + __u8 reserved1; + __u16 reserved2; + __u32 reserved3; + + union { + struct { + __u64 flags; + __u64 address; + union { + __u32 ptid; + } feat; + } pagefault; + + struct { + __u32 ufd; + } fork; + + struct { + __u64 from; + __u64 to; + __u64 len; + } remap; + + struct { + __u64 start; + __u64 end; + } remove; + + struct { + /* unused reserved fields */ + __u64 reserved1; + __u64 reserved2; + __u64 reserved3; + } reserved; + } arg; +} __attribute__((packed)); + +/* + * Start at 0x12 and not at 0 to be more strict against bugs. + */ +#define UFFD_EVENT_PAGEFAULT 0x12 +#define UFFD_EVENT_FORK 0x13 +#define UFFD_EVENT_REMAP 0x14 +#define UFFD_EVENT_REMOVE 0x15 +#define UFFD_EVENT_UNMAP 0x16 + +/* flags for UFFD_EVENT_PAGEFAULT */ +#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ +#define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */ +#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */ + +struct uffdio_api { + /* userland asks for an API number and the features to enable */ + __u64 api; + /* + * Kernel answers below with the all available features for + * the API, this notifies userland of which events and/or + * which flags for each event are enabled in the current + * kernel. + * + * Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE + * are to be considered implicitly always enabled in all kernels as + * long as the uffdio_api.api requested matches UFFD_API. + * + * UFFD_FEATURE_MISSING_HUGETLBFS means an UFFDIO_REGISTER + * with UFFDIO_REGISTER_MODE_MISSING mode will succeed on + * hugetlbfs virtual memory ranges. Adding or not adding + * UFFD_FEATURE_MISSING_HUGETLBFS to uffdio_api.features has + * no real functional effect after UFFDIO_API returns, but + * it's only useful for an initial feature set probe at + * UFFDIO_API time. There are two ways to use it: + * + * 1) by adding UFFD_FEATURE_MISSING_HUGETLBFS to the + * uffdio_api.features before calling UFFDIO_API, an error + * will be returned by UFFDIO_API on a kernel without + * hugetlbfs missing support + * + * 2) the UFFD_FEATURE_MISSING_HUGETLBFS can not be added in + * uffdio_api.features and instead it will be set by the + * kernel in the uffdio_api.features if the kernel supports + * it, so userland can later check if the feature flag is + * present in uffdio_api.features after UFFDIO_API + * succeeded. + * + * UFFD_FEATURE_MISSING_SHMEM works the same as + * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem + * (i.e. tmpfs and other shmem based APIs). + * + * UFFD_FEATURE_SIGBUS feature means no page-fault + * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead + * a SIGBUS signal will be sent to the faulting process. + * + * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will + * be returned, if feature is not requested 0 will be returned. + * + * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults + * can be intercepted (via REGISTER_MODE_MINOR) for + * hugetlbfs-backed pages. + * + * UFFD_FEATURE_MINOR_SHMEM indicates the same support as + * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead. + * + * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page + * faults would be provided and the offset within the page would not be + * masked. + * + * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd + * write-protection mode is supported on both shmem and hugetlbfs. + * + * UFFD_FEATURE_WP_UNPOPULATED indicates that userfaultfd + * write-protection mode will always apply to unpopulated pages + * (i.e. empty ptes). This will be the default behavior for shmem + * & hugetlbfs, so this flag only affects anonymous memory behavior + * when userfault write-protection mode is registered. + * + * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection + * asynchronous mode is supported in which the write fault is + * automatically resolved and write-protection is un-set. + * It implies UFFD_FEATURE_WP_UNPOPULATED. + * + * UFFD_FEATURE_MOVE indicates that the kernel supports moving an + * existing page contents from userspace. + */ +#define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) +#define UFFD_FEATURE_EVENT_FORK (1<<1) +#define UFFD_FEATURE_EVENT_REMAP (1<<2) +#define UFFD_FEATURE_EVENT_REMOVE (1<<3) +#define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) +#define UFFD_FEATURE_MISSING_SHMEM (1<<5) +#define UFFD_FEATURE_EVENT_UNMAP (1<<6) +#define UFFD_FEATURE_SIGBUS (1<<7) +#define UFFD_FEATURE_THREAD_ID (1<<8) +#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) +#define UFFD_FEATURE_MINOR_SHMEM (1<<10) +#define UFFD_FEATURE_EXACT_ADDRESS (1<<11) +#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) +#define UFFD_FEATURE_WP_UNPOPULATED (1<<13) +#define UFFD_FEATURE_POISON (1<<14) +#define UFFD_FEATURE_WP_ASYNC (1<<15) +#define UFFD_FEATURE_MOVE (1<<16) + __u64 features; + + __u64 ioctls; +}; + +struct uffdio_range { + __u64 start; + __u64 len; +}; + +struct uffdio_register { + struct uffdio_range range; +#define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0) +#define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1) +#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2) + __u64 mode; + + /* + * kernel answers which ioctl commands are available for the + * range, keep at the end as the last 8 bytes aren't read. + */ + __u64 ioctls; +}; + +struct uffdio_copy { + __u64 dst; + __u64 src; + __u64 len; +#define UFFDIO_COPY_MODE_DONTWAKE ((__u64)1<<0) + /* + * UFFDIO_COPY_MODE_WP will map the page write protected on + * the fly. UFFDIO_COPY_MODE_WP is available only if the + * write protected ioctl is implemented for the range + * according to the uffdio_register.ioctls. + */ +#define UFFDIO_COPY_MODE_WP ((__u64)1<<1) + __u64 mode; + + /* + * "copy" is written by the ioctl and must be at the end: the + * copy_from_user will not read the last 8 bytes. + */ + __s64 copy; +}; + +struct uffdio_zeropage { + struct uffdio_range range; +#define UFFDIO_ZEROPAGE_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * "zeropage" is written by the ioctl and must be at the end: + * the copy_from_user will not read the last 8 bytes. + */ + __s64 zeropage; +}; + +struct uffdio_writeprotect { + struct uffdio_range range; +/* + * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range, + * unset the flag to undo protection of a range which was previously + * write protected. + * + * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up + * any wait thread after the operation succeeds. + * + * NOTE: Write protecting a region (WP=1) is unrelated to page faults, + * therefore DONTWAKE flag is meaningless with WP=1. Removing write + * protection (WP=0) in response to a page fault wakes the faulting + * task unless DONTWAKE is set. + */ +#define UFFDIO_WRITEPROTECT_MODE_WP ((__u64)1<<0) +#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE ((__u64)1<<1) + __u64 mode; +}; + +struct uffdio_continue { + struct uffdio_range range; +#define UFFDIO_CONTINUE_MODE_DONTWAKE ((__u64)1<<0) + /* + * UFFDIO_CONTINUE_MODE_WP will map the page write protected on + * the fly. UFFDIO_CONTINUE_MODE_WP is available only if the + * write protected ioctl is implemented for the range + * according to the uffdio_register.ioctls. + */ +#define UFFDIO_CONTINUE_MODE_WP ((__u64)1<<1) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 mapped; +}; + +struct uffdio_poison { + struct uffdio_range range; +#define UFFDIO_POISON_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 updated; +}; + +struct uffdio_move { + __u64 dst; + __u64 src; + __u64 len; + /* + * Especially if used to atomically remove memory from the + * address space the wake on the dst range is not needed. + */ +#define UFFDIO_MOVE_MODE_DONTWAKE ((__u64)1<<0) +#define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES ((__u64)1<<1) + __u64 mode; + /* + * "move" is written by the ioctl and must be at the end: the + * copy_from_user will not read the last 8 bytes. + */ + __s64 move; +}; + +/* + * Flags for the userfaultfd(2) system call itself. + */ + +/* + * Create a userfaultfd that can handle page faults only in user mode. + */ +#define UFFD_USER_MODE_ONLY 1 + +#endif /* _LINUX_USERFAULTFD_H */ diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c index 727396de6be54f..9e7307186b7f41 100644 --- a/tools/lib/rbtree.c +++ b/tools/lib/rbtree.c @@ -58,7 +58,7 @@ static inline void rb_set_black(struct rb_node *rb) { - rb->__rb_parent_color |= RB_BLACK; + rb->__rb_parent_color += RB_BLACK; } static inline struct rb_node *rb_red_parent(struct rb_node *red) diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 5fa7957f6e0f56..25810e18b0a732 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/arch/riscv/util/header.c b/tools/perf/arch/riscv/util/header.c index 4a41856938a888..1b29030021eeba 100644 --- a/tools/perf/arch/riscv/util/header.c +++ b/tools/perf/arch/riscv/util/header.c @@ -41,7 +41,7 @@ static char *_get_cpuid(void) char *mimpid = NULL; char *cpuid = NULL; int read; - unsigned long line_sz; + size_t line_sz; FILE *cpuinfo; cpuinfo = fopen(CPUINFO, "r"); diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h index c5c9d05f29da95..c0a2bb785b92b4 100644 --- a/tools/testing/radix-tree/linux/kernel.h +++ b/tools/testing/radix-tree/linux/kernel.h @@ -18,6 +18,8 @@ #define pr_info printk #define pr_debug printk #define pr_cont printk +#define schedule() +#define PAGE_SHIFT 12 #define __acquires(x) #define __releases(x) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 39ad96a18123f6..edcd26106557b4 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -205,6 +205,9 @@ __weak noinline struct file *bpf_testmod_return_ptr(int arg) case 5: return (void *)~(1ull << 30); /* trigger extable */ case 6: return &f; /* valid addr */ case 7: return (void *)((long)&f | 1); /* kernel tricks */ +#ifdef CONFIG_X86_64 + case 8: return (void *)VSYSCALL_ADDR; /* vsyscall page address */ +#endif default: return NULL; } } diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index fb4472ddffd81b..3c79ec9bf780f5 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -29,8 +29,8 @@ $(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat cp $< $@ chmod -x $@ $(OUTPUT)/load_address_4096: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie -static $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -static-pie $< -o $@ $(OUTPUT)/load_address_2097152: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie -static $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -static-pie $< -o $@ $(OUTPUT)/load_address_16777216: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie -static $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -static-pie $< -o $@ diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index ba3ddeda24bf52..d98702b6955df2 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -56,7 +56,6 @@ #include <asm/types.h> #include <ctype.h> #include <errno.h> -#include <limits.h> #include <stdbool.h> #include <stdint.h> #include <stdio.h> @@ -1159,7 +1158,7 @@ void __run_test(struct __fixture_metadata *f, struct __test_metadata *t) { struct __test_xfail *xfail; - char test_name[LINE_MAX]; + char *test_name; const char *diagnostic; /* reset test struct */ @@ -1167,8 +1166,12 @@ void __run_test(struct __fixture_metadata *f, t->trigger = 0; memset(t->results->reason, 0, sizeof(t->results->reason)); - snprintf(test_name, sizeof(test_name), "%s%s%s.%s", - f->name, variant->name[0] ? "." : "", variant->name, t->name); + if (asprintf(&test_name, "%s%s%s.%s", f->name, + variant->name[0] ? "." : "", variant->name, t->name) == -1) { + ksft_print_msg("ERROR ALLOCATING MEMORY\n"); + t->exit_code = KSFT_FAIL; + _exit(t->exit_code); + } ksft_print_msg(" RUN %s ...\n", test_name); @@ -1206,6 +1209,7 @@ void __run_test(struct __fixture_metadata *f, ksft_test_result_code(t->exit_code, test_name, diagnostic ? "%s" : NULL, diagnostic); + free(test_name); } static int test_harness_run(int argc, char **argv) diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index da2cade3bab0e6..1dae4a02957f9d 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -48,6 +48,15 @@ ifeq ($(KHDR_INCLUDES),) KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include endif +# In order to use newer items that haven't yet been added to the user's system +# header files, add $(TOOLS_INCLUDES) to the compiler invocation in each +# each selftest. +# You may need to add files to that location, or to refresh an existing file. In +# order to do that, run "make headers" from $(top_srcdir), then copy the +# header file that you want from $(top_srcdir)/usr/include/... , to the matching +# subdir in $(TOOLS_INCLUDE). +TOOLS_INCLUDES := -isystem $(top_srcdir)/tools/include/uapi + # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index d26e962f2ac490..0b9ab987601cca 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -47,3 +47,5 @@ mkdirty va_high_addr_switch hugetlb_fault_after_madv hugetlb_madv_vs_map +mseal_test +seal_elf diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index eb5f39a2668b44..1b07a48fc2ba4a 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -32,7 +32,7 @@ endif # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm TEST_GEN_FILES = cow @@ -59,6 +59,8 @@ TEST_GEN_FILES += mlock2-tests TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test +TEST_GEN_FILES += mseal_test +TEST_GEN_FILES += seal_elf TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += thuge-gen diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index d615767e396bec..db845dca8d1950 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -28,6 +28,15 @@ #define MiB (1024 * KiB) #define FORK_EXEC_CHILD_PRG_NAME "ksm_fork_exec_child" +#define MAP_MERGE_FAIL ((void *)-1) +#define MAP_MERGE_SKIP ((void *)-2) + +enum ksm_merge_mode { + KSM_MERGE_PRCTL, + KSM_MERGE_MADVISE, + KSM_MERGE_NONE, /* PRCTL already set */ +}; + static int mem_fd; static int ksm_fd; static int ksm_full_scans_fd; @@ -146,33 +155,34 @@ static int ksm_unmerge(void) return 0; } -static char *mmap_and_merge_range(char val, unsigned long size, int prot, - bool use_prctl) +static char *__mmap_and_merge_range(char val, unsigned long size, int prot, + enum ksm_merge_mode mode) { char *map; + char *err_map = MAP_MERGE_FAIL; int ret; /* Stabilize accounting by disabling KSM completely. */ if (ksm_unmerge()) { - ksft_test_result_fail("Disabling (unmerging) KSM failed\n"); - return MAP_FAILED; + ksft_print_msg("Disabling (unmerging) KSM failed\n"); + return err_map; } if (get_my_merging_pages() > 0) { - ksft_test_result_fail("Still pages merged\n"); - return MAP_FAILED; + ksft_print_msg("Still pages merged\n"); + return err_map; } map = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); if (map == MAP_FAILED) { - ksft_test_result_fail("mmap() failed\n"); - return MAP_FAILED; + ksft_print_msg("mmap() failed\n"); + return err_map; } /* Don't use THP. Ignore if THP are not around on a kernel. */ if (madvise(map, size, MADV_NOHUGEPAGE) && errno != EINVAL) { - ksft_test_result_fail("MADV_NOHUGEPAGE failed\n"); + ksft_print_msg("MADV_NOHUGEPAGE failed\n"); goto unmap; } @@ -180,27 +190,36 @@ static char *mmap_and_merge_range(char val, unsigned long size, int prot, memset(map, val, size); if (mprotect(map, size, prot)) { - ksft_test_result_skip("mprotect() failed\n"); + ksft_print_msg("mprotect() failed\n"); + err_map = MAP_MERGE_SKIP; goto unmap; } - if (use_prctl) { + switch (mode) { + case KSM_MERGE_PRCTL: ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); if (ret < 0 && errno == EINVAL) { - ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + ksft_print_msg("PR_SET_MEMORY_MERGE not supported\n"); + err_map = MAP_MERGE_SKIP; goto unmap; } else if (ret) { - ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + ksft_print_msg("PR_SET_MEMORY_MERGE=1 failed\n"); goto unmap; } - } else if (madvise(map, size, MADV_MERGEABLE)) { - ksft_test_result_fail("MADV_MERGEABLE failed\n"); - goto unmap; + break; + case KSM_MERGE_MADVISE: + if (madvise(map, size, MADV_MERGEABLE)) { + ksft_print_msg("MADV_MERGEABLE failed\n"); + goto unmap; + } + break; + case KSM_MERGE_NONE: + break; } /* Run KSM to trigger merging and wait. */ if (ksm_merge()) { - ksft_test_result_fail("Running KSM failed\n"); + ksft_print_msg("Running KSM failed\n"); goto unmap; } @@ -209,14 +228,31 @@ static char *mmap_and_merge_range(char val, unsigned long size, int prot, * accounted differently (depending on kernel support). */ if (val && !get_my_merging_pages()) { - ksft_test_result_fail("No pages got merged\n"); + ksft_print_msg("No pages got merged\n"); goto unmap; } return map; unmap: munmap(map, size); - return MAP_FAILED; + return err_map; +} + +static char *mmap_and_merge_range(char val, unsigned long size, int prot, + enum ksm_merge_mode mode) +{ + char *map; + char *ret = MAP_FAILED; + + map = __mmap_and_merge_range(val, size, prot, mode); + if (map == MAP_MERGE_FAIL) + ksft_test_result_fail("Merging memory failed"); + else if (map == MAP_MERGE_SKIP) + ksft_test_result_skip("Merging memory skipped"); + else + ret = map; + + return ret; } static void test_unmerge(void) @@ -226,7 +262,7 @@ static void test_unmerge(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); if (map == MAP_FAILED) return; @@ -264,7 +300,7 @@ static void test_unmerge_zero_pages(void) } /* Let KSM deduplicate zero pages. */ - map = mmap_and_merge_range(0x00, size, PROT_READ | PROT_WRITE, false); + map = mmap_and_merge_range(0x00, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); if (map == MAP_FAILED) return; @@ -312,7 +348,7 @@ static void test_unmerge_discarded(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); if (map == MAP_FAILED) return; @@ -344,7 +380,7 @@ static void test_unmerge_uffd_wp(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, false); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_MADVISE); if (map == MAP_FAILED) return; @@ -439,6 +475,36 @@ static void test_prctl(void) ksft_test_result_pass("Setting/clearing PR_SET_MEMORY_MERGE works\n"); } +static int test_child_ksm(void) +{ + const unsigned int size = 2 * MiB; + char *map; + + /* Test if KSM is enabled for the process. */ + if (prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0) != 1) + return -1; + + /* Test if merge could really happen. */ + map = __mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_NONE); + if (map == MAP_MERGE_FAIL) + return -2; + else if (map == MAP_MERGE_SKIP) + return -3; + + munmap(map, size); + return 0; +} + +static void test_child_ksm_err(int status) +{ + if (status == -1) + ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n"); + else if (status == -2) + ksft_test_result_fail("Merge in child failed\n"); + else if (status == -3) + ksft_test_result_skip("Merge in child skipped\n"); +} + /* Verify that prctl ksm flag is inherited. */ static void test_prctl_fork(void) { @@ -458,7 +524,7 @@ static void test_prctl_fork(void) child_pid = fork(); if (!child_pid) { - exit(prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0)); + exit(test_child_ksm()); } else if (child_pid < 0) { ksft_test_result_fail("fork() failed\n"); return; @@ -467,8 +533,11 @@ static void test_prctl_fork(void) if (waitpid(child_pid, &status, 0) < 0) { ksft_test_result_fail("waitpid() failed\n"); return; - } else if (WEXITSTATUS(status) != 1) { - ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n"); + } + + status = WEXITSTATUS(status); + if (status) { + test_child_ksm_err(status); return; } @@ -480,12 +549,6 @@ static void test_prctl_fork(void) ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); } -static int ksm_fork_exec_child(void) -{ - /* Test if KSM is enabled for the process. */ - return prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0) == 1; -} - static void test_prctl_fork_exec(void) { int ret, status; @@ -518,7 +581,7 @@ static void test_prctl_fork_exec(void) if (WIFEXITED(status)) { status = WEXITSTATUS(status); if (status) { - ksft_test_result_fail("KSM not enabled\n"); + test_child_ksm_err(status); return; } } else { @@ -545,7 +608,7 @@ static void test_prctl_unmerge(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, true); + map = mmap_and_merge_range(0xcf, size, PROT_READ | PROT_WRITE, KSM_MERGE_PRCTL); if (map == MAP_FAILED) return; @@ -568,7 +631,7 @@ static void test_prot_none(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0x11, size, PROT_NONE, false); + map = mmap_and_merge_range(0x11, size, PROT_NONE, KSM_MERGE_MADVISE); if (map == MAP_FAILED) goto unmap; @@ -599,7 +662,7 @@ int main(int argc, char **argv) int err; if (argc > 1 && !strcmp(argv[1], FORK_EXEC_CHILD_PRG_NAME)) { - exit(ksm_fork_exec_child() == 1 ? 0 : 1); + exit(test_child_ksm()); } #ifdef __NR_userfaultfd diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c index 200bedcdc32e9c..1e01d3ddc11c58 100644 --- a/tools/testing/selftests/mm/mdwe_test.c +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -7,6 +7,7 @@ #include <linux/mman.h> #include <linux/prctl.h> +#define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <sys/auxv.h> diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 9b298f6a04b371..9a0597310a7651 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -20,6 +20,7 @@ #include <unistd.h> #include <errno.h> #include <stdio.h> +#include <fcntl.h> #include "../kselftest.h" @@ -83,6 +84,45 @@ static void test_mlock_limit(int fd) pass("mlock limit is respected\n"); } +static void test_vmsplice(int fd, const char *desc) +{ + ssize_t transferred; + struct iovec iov; + int pipefd[2]; + char *mem; + + if (pipe(pipefd)) { + fail("pipe failed: %s\n", strerror(errno)); + return; + } + + mem = mmap(NULL, page_size, prot, mode, fd, 0); + if (mem == MAP_FAILED) { + fail("Unable to mmap secret memory\n"); + goto close_pipe; + } + + /* + * vmsplice() may use GUP-fast, which must also fail. Prefault the + * page table, so GUP-fast could find it. + */ + memset(mem, PATTERN, page_size); + + iov.iov_base = mem; + iov.iov_len = page_size; + transferred = vmsplice(pipefd[1], &iov, 1, 0); + + if (transferred < 0 && errno == EFAULT) + pass("vmsplice is blocked as expected with %s\n", desc); + else + fail("vmsplice: unexpected memory access with %s\n", desc); + + munmap(mem, page_size); +close_pipe: + close(pipefd[0]); + close(pipefd[1]); +} + static void try_process_vm_read(int fd, int pipefd[2]) { struct iovec liov, riov; @@ -187,7 +227,6 @@ static void test_remote_access(int fd, const char *name, return; } - ftruncate(fd, page_size); memset(mem, PATTERN, page_size); if (write(pipefd[1], &mem, sizeof(mem)) < 0) { @@ -258,7 +297,7 @@ static void prepare(void) strerror(errno)); } -#define NUM_TESTS 4 +#define NUM_TESTS 6 int main(int argc, char *argv[]) { @@ -277,9 +316,17 @@ int main(int argc, char *argv[]) ksft_exit_fail_msg("memfd_secret failed: %s\n", strerror(errno)); } + if (ftruncate(fd, page_size)) + ksft_exit_fail_msg("ftruncate failed: %s\n", strerror(errno)); test_mlock_limit(fd); test_file_apis(fd); + /* + * We have to run the first vmsplice test before any secretmem page was + * allocated for this fd. + */ + test_vmsplice(fd, "fresh page"); + test_vmsplice(fd, "existing page"); test_process_vm_read(fd); test_ptrace(fd); diff --git a/tools/testing/selftests/mm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 26f744188ad0c8..7f0d50fa361dcf 100644 --- a/tools/testing/selftests/mm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c @@ -20,8 +20,6 @@ static int get_vm_area(unsigned long addr, struct vm_boundaries *area) FILE *file; int ret = 1; char line[1024] = {0}; - char *end_addr; - char *stop; unsigned long start; unsigned long end; @@ -37,21 +35,10 @@ static int get_vm_area(unsigned long addr, struct vm_boundaries *area) memset(area, 0, sizeof(struct vm_boundaries)); while(fgets(line, 1024, file)) { - end_addr = strchr(line, '-'); - if (!end_addr) { + if (sscanf(line, "%lx-%lx", &start, &end) != 2) { ksft_print_msg("cannot parse /proc/self/maps\n"); goto out; } - *end_addr = '\0'; - end_addr++; - stop = strchr(end_addr, ' '); - if (!stop) { - ksft_print_msg("cannot parse /proc/self/maps\n"); - goto out; - } - - sscanf(line, "%lx", &start); - sscanf(end_addr, "%lx", &end); if (start <= addr && end > addr) { area->start = start; diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 2f8b991f78cb4c..1b03bcfaefdfa2 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -23,6 +23,7 @@ #define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */ #define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#define MAX(X, Y) ((X) > (Y) ? (X) : (Y)) #define SIZE_MB(m) ((size_t)m * (1024 * 1024)) #define SIZE_KB(k) ((size_t)k * 1024) @@ -69,6 +70,27 @@ enum { .expect_failure = should_fail \ } +/* compute square root using binary search */ +static unsigned long get_sqrt(unsigned long val) +{ + unsigned long low = 1; + + /* assuming rand_size is less than 1TB */ + unsigned long high = (1UL << 20); + + while (low <= high) { + unsigned long mid = low + (high - low) / 2; + unsigned long temp = mid * mid; + + if (temp == val) + return mid; + if (temp < val) + low = mid + 1; + high = mid - 1; + } + return low; +} + /* * Returns false if the requested remap region overlaps with an * existing mapping (e.g text, stack) else returns true. @@ -126,19 +148,21 @@ static unsigned long long get_mmap_min_addr(void) * Using /proc/self/maps, assert that the specified address range is contained * within a single mapping. */ -static bool is_range_mapped(FILE *maps_fp, void *start, void *end) +static bool is_range_mapped(FILE *maps_fp, unsigned long start, + unsigned long end) { char *line = NULL; size_t len = 0; bool success = false; + unsigned long first_val, second_val; rewind(maps_fp); while (getline(&line, &len, maps_fp) != -1) { - char *first = strtok(line, "- "); - void *first_val = (void *)strtol(first, NULL, 16); - char *second = strtok(NULL, "- "); - void *second_val = (void *) strtol(second, NULL, 16); + if (sscanf(line, "%lx-%lx", &first_val, &second_val) != 2) { + ksft_exit_fail_msg("cannot parse /proc/self/maps\n"); + break; + } if (first_val <= start && second_val >= end) { success = true; @@ -233,7 +257,8 @@ static void mremap_expand_merge(FILE *maps_fp, unsigned long page_size) goto out; } - success = is_range_mapped(maps_fp, start, start + 3 * page_size); + success = is_range_mapped(maps_fp, (unsigned long)start, + (unsigned long)(start + 3 * page_size)); munmap(start, 3 * page_size); out: @@ -272,7 +297,8 @@ static void mremap_expand_merge_offset(FILE *maps_fp, unsigned long page_size) goto out; } - success = is_range_mapped(maps_fp, start, start + 3 * page_size); + success = is_range_mapped(maps_fp, (unsigned long)start, + (unsigned long)(start + 3 * page_size)); munmap(start, 3 * page_size); out: @@ -296,7 +322,7 @@ out: * * |DDDDddddSSSSssss| */ -static void mremap_move_within_range(char pattern_seed) +static void mremap_move_within_range(unsigned int pattern_seed, char *rand_addr) { char *test_name = "mremap mremap move within range"; void *src, *dest; @@ -316,10 +342,7 @@ static void mremap_move_within_range(char pattern_seed) src = (void *)((unsigned long)src & ~(SIZE_MB(2) - 1)); /* Set byte pattern for source block. */ - srand(pattern_seed); - for (i = 0; i < SIZE_MB(2); i++) { - ((char *)src)[i] = (char) rand(); - } + memcpy(src, rand_addr, SIZE_MB(2)); dest = src - SIZE_MB(2); @@ -357,14 +380,14 @@ out: /* Returns the time taken for the remap on success else returns -1. */ static long long remap_region(struct config c, unsigned int threshold_mb, - char pattern_seed) + char *rand_addr) { void *addr, *src_addr, *dest_addr, *dest_preamble_addr; - int d; - unsigned long long t; + unsigned long long t, d; struct timespec t_start = {0, 0}, t_end = {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; unsigned long long threshold; + unsigned long num_chunks; if (threshold_mb == VALIDATION_NO_THRESHOLD) threshold = c.region_size; @@ -378,9 +401,7 @@ static long long remap_region(struct config c, unsigned int threshold_mb, } /* Set byte pattern for source block. */ - srand(pattern_seed); - for (t = 0; t < threshold; t++) - memset((char *) src_addr + t, (char) rand(), 1); + memcpy(src_addr, rand_addr, threshold); /* Mask to zero out lower bits of address for alignment */ align_mask = ~(c.dest_alignment - 1); @@ -420,9 +441,7 @@ static long long remap_region(struct config c, unsigned int threshold_mb, } /* Set byte pattern for the dest preamble block. */ - srand(pattern_seed); - for (d = 0; d < c.dest_preamble_size; d++) - memset((char *) dest_preamble_addr + d, (char) rand(), 1); + memcpy(dest_preamble_addr, rand_addr, c.dest_preamble_size); } clock_gettime(CLOCK_MONOTONIC, &t_start); @@ -436,15 +455,42 @@ static long long remap_region(struct config c, unsigned int threshold_mb, goto clean_up_dest_preamble; } - /* Verify byte pattern after remapping */ - srand(pattern_seed); - for (t = 0; t < threshold; t++) { - char c = (char) rand(); + /* + * Verify byte pattern after remapping. Employ an algorithm with a + * square root time complexity in threshold: divide the range into + * chunks, if memcmp() returns non-zero, only then perform an + * iteration in that chunk to find the mismatch index. + */ + num_chunks = get_sqrt(threshold); + for (unsigned long i = 0; i < num_chunks; ++i) { + size_t chunk_size = threshold / num_chunks; + unsigned long shift = i * chunk_size; + + if (!memcmp(dest_addr + shift, rand_addr + shift, chunk_size)) + continue; + + /* brute force iteration only over mismatch segment */ + for (t = shift; t < shift + chunk_size; ++t) { + if (((char *) dest_addr)[t] != rand_addr[t]) { + ksft_print_msg("Data after remap doesn't match at offset %llu\n", + t); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[t] & 0xff, + ((char *) dest_addr)[t] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + } - if (((char *) dest_addr)[t] != c) { + /* + * if threshold is not divisible by num_chunks, then check the + * last chunk + */ + for (t = num_chunks * (threshold / num_chunks); t < threshold; ++t) { + if (((char *) dest_addr)[t] != rand_addr[t]) { ksft_print_msg("Data after remap doesn't match at offset %llu\n", - t); - ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + t); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[t] & 0xff, ((char *) dest_addr)[t] & 0xff); ret = -1; goto clean_up_dest; @@ -452,22 +498,44 @@ static long long remap_region(struct config c, unsigned int threshold_mb, } /* Verify the dest preamble byte pattern after remapping */ - if (c.dest_preamble_size) { - srand(pattern_seed); - for (d = 0; d < c.dest_preamble_size; d++) { - char c = (char) rand(); - - if (((char *) dest_preamble_addr)[d] != c) { - ksft_print_msg("Preamble data after remap doesn't match at offset %d\n", - d); - ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, - ((char *) dest_preamble_addr)[d] & 0xff); + if (!c.dest_preamble_size) + goto no_preamble; + + num_chunks = get_sqrt(c.dest_preamble_size); + + for (unsigned long i = 0; i < num_chunks; ++i) { + size_t chunk_size = c.dest_preamble_size / num_chunks; + unsigned long shift = i * chunk_size; + + if (!memcmp(dest_preamble_addr + shift, rand_addr + shift, + chunk_size)) + continue; + + /* brute force iteration only over mismatched segment */ + for (d = shift; d < shift + chunk_size; ++d) { + if (((char *) dest_preamble_addr)[d] != rand_addr[d]) { + ksft_print_msg("Preamble data after remap doesn't match at offset %llu\n", + d); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[d] & 0xff, + ((char *) dest_preamble_addr)[d] & 0xff); ret = -1; goto clean_up_dest; } } } + for (d = num_chunks * (c.dest_preamble_size / num_chunks); d < c.dest_preamble_size; ++d) { + if (((char *) dest_preamble_addr)[d] != rand_addr[d]) { + ksft_print_msg("Preamble data after remap doesn't match at offset %llu\n", + d); + ksft_print_msg("Expected: %#x\t Got: %#x\n", rand_addr[d] & 0xff, + ((char *) dest_preamble_addr)[d] & 0xff); + ret = -1; + goto clean_up_dest; + } + } + +no_preamble: start_ns = t_start.tv_sec * NS_PER_SEC + t_start.tv_nsec; end_ns = t_end.tv_sec * NS_PER_SEC + t_end.tv_nsec; ret = end_ns - start_ns; @@ -494,7 +562,8 @@ out: * the beginning of the mapping just because the aligned * down address landed on a mapping that maybe does not exist. */ -static void mremap_move_1mb_from_start(char pattern_seed) +static void mremap_move_1mb_from_start(unsigned int pattern_seed, + char *rand_addr) { char *test_name = "mremap move 1mb from start at 1MB+256KB aligned src"; void *src = NULL, *dest = NULL; @@ -520,10 +589,7 @@ static void mremap_move_1mb_from_start(char pattern_seed) } /* Set byte pattern for source block. */ - srand(pattern_seed); - for (i = 0; i < SIZE_MB(2); i++) { - ((char *)src)[i] = (char) rand(); - } + memcpy(src, rand_addr, SIZE_MB(2)); /* * Unmap the beginning of dest so that the aligned address @@ -568,10 +634,10 @@ out: static void run_mremap_test_case(struct test test_case, int *failures, unsigned int threshold_mb, - unsigned int pattern_seed) + unsigned int pattern_seed, char *rand_addr) { long long remap_time = remap_region(test_case.config, threshold_mb, - pattern_seed); + rand_addr); if (remap_time < 0) { if (test_case.expect_failure) @@ -642,7 +708,15 @@ int main(int argc, char **argv) int failures = 0; int i, run_perf_tests; unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; + + /* hard-coded test configs */ + size_t max_test_variable_region_size = _2GB; + size_t max_test_constant_region_size = _2MB; + size_t dest_preamble_size = 10 * _4MB; + unsigned int pattern_seed; + char *rand_addr; + size_t rand_size; int num_expand_tests = 2; int num_misc_tests = 2; struct test test_cases[MAX_TEST] = {}; @@ -659,6 +733,31 @@ int main(int argc, char **argv) ksft_print_msg("Test configs:\n\tthreshold_mb=%u\n\tpattern_seed=%u\n\n", threshold_mb, pattern_seed); + /* + * set preallocated random array according to test configs; see the + * functions for the logic of setting the size + */ + if (!threshold_mb) + rand_size = MAX(max_test_variable_region_size, + max_test_constant_region_size); + else + rand_size = MAX(MIN(threshold_mb * _1MB, + max_test_variable_region_size), + max_test_constant_region_size); + rand_size = MAX(dest_preamble_size, rand_size); + + rand_addr = (char *)mmap(NULL, rand_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (rand_addr == MAP_FAILED) { + perror("mmap"); + ksft_exit_fail_msg("cannot mmap rand_addr\n"); + } + + /* fill stream of random bytes */ + srand(pattern_seed); + for (unsigned long i = 0; i < rand_size; ++i) + rand_addr[i] = (char) rand(); + page_size = sysconf(_SC_PAGESIZE); /* Expected mremap failures */ @@ -730,13 +829,13 @@ int main(int argc, char **argv) for (i = 0; i < ARRAY_SIZE(test_cases); i++) run_mremap_test_case(test_cases[i], &failures, threshold_mb, - pattern_seed); + pattern_seed, rand_addr); maps_fp = fopen("/proc/self/maps", "r"); if (maps_fp == NULL) { - ksft_print_msg("Failed to read /proc/self/maps: %s\n", strerror(errno)); - exit(KSFT_FAIL); + munmap(rand_addr, rand_size); + ksft_exit_fail_msg("Failed to read /proc/self/maps: %s\n", strerror(errno)); } mremap_expand_merge(maps_fp, page_size); @@ -744,17 +843,20 @@ int main(int argc, char **argv) fclose(maps_fp); - mremap_move_within_range(pattern_seed); - mremap_move_1mb_from_start(pattern_seed); + mremap_move_within_range(pattern_seed, rand_addr); + mremap_move_1mb_from_start(pattern_seed, rand_addr); if (run_perf_tests) { ksft_print_msg("\n%s\n", "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:"); for (i = 0; i < ARRAY_SIZE(perf_test_cases); i++) run_mremap_test_case(perf_test_cases[i], &failures, - threshold_mb, pattern_seed); + threshold_mb, pattern_seed, + rand_addr); } + munmap(rand_addr, rand_size); + if (failures > 0) ksft_exit_fail(); else diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c new file mode 100644 index 00000000000000..ca8dbee0c612e7 --- /dev/null +++ b/tools/testing/selftests/mm/mseal_test.c @@ -0,0 +1,1893 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sys/mman.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <stdbool.h> +#include "../kselftest.h" +#include <syscall.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <sys/stat.h> + +/* + * need those definition for manually build using gcc. + * gcc -I ../../../../usr/include -DDEBUG -O3 -DDEBUG -O3 mseal_test.c -o mseal_test + */ +#ifndef PKEY_DISABLE_ACCESS +# define PKEY_DISABLE_ACCESS 0x1 +#endif + +#ifndef PKEY_DISABLE_WRITE +# define PKEY_DISABLE_WRITE 0x2 +#endif + +#ifndef PKEY_BITS_PER_KEY +#define PKEY_BITS_PER_PKEY 2 +#endif + +#ifndef PKEY_MASK +#define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) +#endif + +#define FAIL_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_fail("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + +#define SKIP_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_skip("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + + +#define TEST_END_CHECK() {\ + ksft_test_result_pass("%s\n", __func__);\ + return;\ +test_end:\ + return;\ +} + +#ifndef u64 +#define u64 unsigned long long +#endif + +static unsigned long get_vma_size(void *addr, int *prot) +{ + FILE *maps; + char line[256]; + int size = 0; + uintptr_t addr_start, addr_end; + char protstr[5]; + *prot = 0; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) + return 0; + + while (fgets(line, sizeof(line), maps)) { + if (sscanf(line, "%lx-%lx %4s", &addr_start, &addr_end, protstr) == 3) { + if (addr_start == (uintptr_t) addr) { + size = addr_end - addr_start; + if (protstr[0] == 'r') + *prot |= 0x4; + if (protstr[1] == 'w') + *prot |= 0x2; + if (protstr[2] == 'x') + *prot |= 0x1; + break; + } + } + } + fclose(maps); + return size; +} + +/* + * define sys_xyx to call syscall directly. + */ +static int sys_mseal(void *start, size_t len) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mseal, start, len, 0); + return sret; +} + +static int sys_mprotect(void *ptr, size_t size, unsigned long prot) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mprotect, ptr, size, prot); + return sret; +} + +static int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int sret; + + errno = 0; + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); + return sret; +} + +static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, + unsigned long flags, unsigned long fd, unsigned long offset) +{ + void *sret; + + errno = 0; + sret = (void *) syscall(__NR_mmap, addr, len, prot, + flags, fd, offset); + return sret; +} + +static int sys_munmap(void *ptr, size_t size) +{ + int sret; + + errno = 0; + sret = syscall(__NR_munmap, ptr, size); + return sret; +} + +static int sys_madvise(void *start, size_t len, int types) +{ + int sret; + + errno = 0; + sret = syscall(__NR_madvise, start, len, types); + return sret; +} + +static int sys_pkey_alloc(unsigned long flags, unsigned long init_val) +{ + int ret = syscall(__NR_pkey_alloc, flags, init_val); + + return ret; +} + +static unsigned int __read_pkey_reg(void) +{ + unsigned int pkey_reg = 0; +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax, edx; + unsigned int ecx = 0; + + asm volatile(".byte 0x0f,0x01,0xee\n\t" + : "=a" (eax), "=d" (edx) + : "c" (ecx)); + pkey_reg = eax; +#endif + return pkey_reg; +} + +static void __write_pkey_reg(u64 pkey_reg) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax = pkey_reg; + unsigned int ecx = 0; + unsigned int edx = 0; + + asm volatile(".byte 0x0f,0x01,0xef\n\t" + : : "a" (eax), "c" (ecx), "d" (edx)); +#endif +} + +static unsigned long pkey_bit_position(int pkey) +{ + return pkey * PKEY_BITS_PER_PKEY; +} + +static u64 set_pkey_bits(u64 reg, int pkey, u64 flags) +{ + unsigned long shift = pkey_bit_position(pkey); + + /* mask out bits from pkey in old value */ + reg &= ~((u64)PKEY_MASK << shift); + /* OR in new bits for pkey */ + reg |= (flags & PKEY_MASK) << shift; + return reg; +} + +static void set_pkey(int pkey, unsigned long pkey_value) +{ + u64 new_pkey_reg; + + new_pkey_reg = set_pkey_bits(__read_pkey_reg(), pkey, pkey_value); + __write_pkey_reg(new_pkey_reg); +} + +static void setup_single_address(int size, void **ptrOut) +{ + void *ptr; + + ptr = sys_mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + *ptrOut = ptr; +} + +static void setup_single_address_rw(int size, void **ptrOut) +{ + void *ptr; + unsigned long mapflags = MAP_ANONYMOUS | MAP_PRIVATE; + + ptr = sys_mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0); + *ptrOut = ptr; +} + +static int clean_single_address(void *ptr, int size) +{ + int ret; + ret = munmap(ptr, size); + return ret; +} + +static int seal_single_address(void *ptr, int size) +{ + int ret; + ret = sys_mseal(ptr, size); + return ret; +} + +bool seal_support(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + + ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (ptr == (void *) -1) + return false; + + ret = sys_mseal(ptr, page_size); + if (ret < 0) + return false; + + return true; +} + +bool pkey_supported(void) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + int pkey = sys_pkey_alloc(0, 0); + + if (pkey > 0) + return true; +#endif + return false; +} + +static void test_seal_addseal(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_start(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* munmap 2 pages from ptr. */ + ret = sys_munmap(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail because 2 pages from ptr are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail because 2 pages from ptr are unmapped. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + ret = sys_mseal(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_middle(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* munmap 2 pages from ptr + page. */ + ret = sys_munmap(ptr + page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail, since middle 2 pages are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* we still can add seal to the first page and last page*/ + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mseal(ptr + 3 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_end(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap last 2 pages. */ + ret = sys_munmap(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail since last 2 pages are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* The first 2 pages is not sealed, and can add seals */ + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_multiple_vmas(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split the vma into 3. */ + ret = sys_mprotect(ptr + page_size, 2 * page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will get applied to all 4 pages - 3 VMAs. */ + ret = sys_mprotect(ptr, size, PROT_READ); + FAIL_TEST_IF_FALSE(!ret); + + /* use mprotect to split the vma into 3. */ + ret = sys_mprotect(ptr + page_size, 2 * page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mseal get applied to all 4 pages - 3 VMAs. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_split_start(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split at middle */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first page, this will split the VMA */ + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* add seal to the remain 3 pages */ + ret = sys_mseal(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_split_end(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split at middle */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the last page */ + ret = sys_mseal(ptr + 3 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* Adding seals to the first 3 pages */ + ret = sys_mseal(ptr, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_invalid_input(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(8 * page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + ret = clean_single_address(ptr + 4 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* invalid flag */ + ret = syscall(__NR_mseal, ptr, size, 0x20); + FAIL_TEST_IF_FALSE(ret < 0); + + /* unaligned address */ + ret = sys_mseal(ptr + 1, 2 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* length too big */ + ret = sys_mseal(ptr, 5 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* length overflow */ + ret = sys_mseal(ptr, UINT64_MAX/page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* start is not in a valid VMA */ + ret = sys_mseal(ptr - page_size, 5 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + TEST_END_CHECK(); +} + +static void test_seal_zero_length(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mprotect(ptr, 0, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal 0 length will be OK, same as mprotect */ + ret = sys_mseal(ptr, 0); + FAIL_TEST_IF_FALSE(!ret); + + /* verify the 4 pages are not sealed by previous call. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_zero_address(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + /* use mmap to change protection. */ + ptr = sys_mmap(0, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + FAIL_TEST_IF_FALSE(ptr == 0); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + /* verify the 4 pages are sealed by previous call. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret); + + TEST_END_CHECK(); +} + +static void test_seal_twice(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + /* apply the same seal will be OK. idempotent. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_start_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* the first page is sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* pages after the first page is not sealed. */ + ret = sys_mprotect(ptr + page_size, page_size * 3, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_end_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* first page is not sealed */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* last 3 page are sealed */ + ret = sys_mprotect(ptr + page_size, page_size * 3, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_unalign_len(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, page_size * 2 - 1); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 2 pages are sealed. */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 2, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_unalign_len_variant_2(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + if (seal) { + ret = seal_single_address(ptr, page_size * 2 + 1); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 3 pages are sealed. */ + ret = sys_mprotect(ptr, page_size * 3, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 3, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = seal_single_address(ptr, page_size * 4); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 2, page_size * 2, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma_with_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split as two vma. */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mseal can apply across 2 vma, also split them. */ + if (seal) { + ret = seal_single_address(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + } + + /* the first page is not sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* the second page is sealed. */ + ret = sys_mprotect(ptr + page_size, page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* the third page is sealed. */ + ret = sys_mprotect(ptr + 2 * page_size, page_size, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* the fouth page is not sealed. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_partial_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* seal one page. */ + if (seal) { + ret = seal_single_address(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mprotect first 2 page will fail, since the first page are sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma_with_gap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* use munmap to free two pages in the middle */ + ret = sys_munmap(ptr + page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail, because there is a gap in the address. */ + /* notes, internally mprotect still updated the first page. */ + ret = sys_mprotect(ptr, 4 * page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, 4 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* the first page is not sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + /* the last page is not sealed. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal all 4 pages. */ + if (seal) { + ret = sys_mseal(ptr, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mprotect is sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + + ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_merge(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split one page. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal first two pages. */ + if (seal) { + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 2 pages are sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* last 2 pages are not sealed. */ + ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + TEST_END_CHECK(); +} + +static void test_seal_munmap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 4 pages are sealed. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +/* + * allocate 4 pages, + * use mprotect to split it as two VMAs + * seal the whole range + * munmap will fail on both + */ +static void test_seal_munmap_two_vma(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_munmap(ptr, page_size * 2); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr + page_size, page_size * 2); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +/* + * allocate a VMA with 4 pages. + * munmap the middle 2 pages. + * seal the whole 4 pages, will fail. + * munmap the first page will be OK. + * munmap the last page will be OK. + */ +static void test_seal_munmap_vma_with_gap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_munmap(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + /* can't have gap in the middle. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + } + + ret = sys_munmap(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr + page_size * 2, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_munmap_start_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap the first page. */ + ret = sys_munmap(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the last 3 pages. */ + if (seal) { + ret = sys_mseal(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* unmap from the first page. */ + ret = sys_munmap(ptr, size); + if (seal) { + FAIL_TEST_IF_FALSE(ret < 0); + + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size * 3); + } else { + /* note: this will be OK, even the first page is */ + /* already unmapped. */ + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 0); + } + + TEST_END_CHECK(); +} + +static void test_munmap_end_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap last page. */ + ret = sys_munmap(ptr + page_size * 3, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first 3 pages. */ + if (seal) { + ret = sys_mseal(ptr, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* unmap all pages. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_munmap_middle_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap 2 pages in the middle. */ + ret = sys_munmap(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first page. */ + if (seal) { + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* munmap all 4 pages. */ + ret = sys_munmap(ptr, size); + if (seal) { + FAIL_TEST_IF_FALSE(ret < 0); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + + size = get_vma_size(ptr + page_size * 3, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + } else { + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 0); + + size = get_vma_size(ptr + page_size * 3, &prot); + FAIL_TEST_IF_FALSE(size == 0); + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_shrink(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* shrink from 4 pages to 2 pages. */ + ret2 = mremap(ptr, size, 2 * page_size, 0, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_expand(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + /* ummap last 2 pages. */ + ret = sys_munmap(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* expand from 2 page to 4 pages. */ + ret2 = mremap(ptr, 2 * page_size, 4 * page_size, 0, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 == ptr); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move(bool seal) +{ + void *ptr, *newPtr; + unsigned long page_size = getpagesize(); + unsigned long size = page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newPtr); + FAIL_TEST_IF_FALSE(newPtr != (void *)-1); + ret = clean_single_address(newPtr, size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* move from ptr to fixed address. */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newPtr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mmap_overwrite_prot(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to change protection. */ + ret2 = sys_mmap(ptr, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mmap_expand(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + /* ummap last 4 pages. */ + ret = sys_munmap(ptr + 8 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, 8 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to expand. */ + ret2 = sys_mmap(ptr, size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mmap_shrink(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to shrink. */ + ret2 = sys_mmap(ptr, 8 * page_size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_shrink_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move and shrink to fixed address */ + ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_expand_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(newAddr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move and expand to fixed address */ + ret2 = mremap(ptr, page_size, size, MREMAP_MAYMOVE | MREMAP_FIXED, + newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(newAddr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move to fixed address */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_fixed_zero(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * MREMAP_FIXED can move the mapping to zero address + */ + ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 == 0); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_dontunmap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move, and don't unmap src addr. */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_dontunmap_anyaddr(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * The 0xdeaddead should not have effect on dest addr + * when MREMAP_DONTUNMAP is set. + */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + 0xdeaddead); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + FAIL_TEST_IF_FALSE((long)ret2 != 0xdeaddead); + + } + + TEST_END_CHECK(); +} + + +static void test_seal_merge_and_split(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size; + int ret; + int prot; + + /* (24 RO) */ + setup_single_address(24 * page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect(NONE) to set out boundary */ + /* (1 NONE) (22 RO) (1 NONE) */ + ret = sys_mprotect(ptr, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(!ret); + ret = sys_mprotect(ptr + 23 * page_size, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 22 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + /* use mseal to split from beginning */ + /* (1 NONE) (1 RO_SEAL) (21 RO) (1 NONE) */ + ret = sys_mseal(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 2 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 21 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* use mseal to split from the end. */ + /* (1 NONE) (1 RO_SEAL) (20 RO) (1 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 22 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 22 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 2 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 20 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge with prev. */ + /* (1 NONE) (2 RO_SEAL) (19 RO) (1 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 2 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge with after. */ + /* (1 NONE) (2 RO_SEAL) (18 RO) (2 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 21 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 21 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 2 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* split and merge from prev */ + /* (1 NONE) (3 RO_SEAL) (17 RO) (2 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 1 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 3 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + ret = sys_munmap(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(ret < 0); + ret = sys_mprotect(ptr + 2 * page_size, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* split and merge from next */ + /* (1 NONE) (3 RO_SEAL) (16 RO) (3 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 20 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 20 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 3 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge from middle of prev and middle of next. */ + /* (1 NONE) (22 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, 20 * page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 22 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_rw(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address_rw(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't take effect on RW memory. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + /* base seal still apply. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_pkey(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int pkey; + + SKIP_TEST_IF_FALSE(pkey_supported()); + + setup_single_address_rw(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + pkey = sys_pkey_alloc(0, 0); + FAIL_TEST_IF_FALSE(pkey > 0); + + ret = sys_mprotect_pkey((void *)ptr, size, PROT_READ | PROT_WRITE, pkey); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't take effect if PKRU allow write. */ + set_pkey(pkey, 0); + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + /* sealing will take effect if PKRU deny write. */ + set_pkey(pkey, PKEY_DISABLE_WRITE); + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* base seal still apply. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_filebacked(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int fd; + unsigned long mapflags = MAP_PRIVATE; + + fd = memfd_create("test", 0); + FAIL_TEST_IF_FALSE(fd > 0); + + ret = fallocate(fd, 0, 0, size); + FAIL_TEST_IF_FALSE(!ret); + + ptr = sys_mmap(NULL, size, PROT_READ, mapflags, fd, 0); + FAIL_TEST_IF_FALSE(ptr != MAP_FAILED); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't apply for file backed mapping. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + close(fd); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_shared(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + unsigned long mapflags = MAP_ANONYMOUS | MAP_SHARED; + + ptr = sys_mmap(NULL, size, PROT_READ, mapflags, -1, 0); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't apply for shared mapping. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +int main(int argc, char **argv) +{ + bool test_seal = seal_support(); + + ksft_print_header(); + + if (!test_seal) + ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); + + if (!pkey_supported()) + ksft_print_msg("PKEY not supported\n"); + + ksft_set_plan(80); + + test_seal_addseal(); + test_seal_unmapped_start(); + test_seal_unmapped_middle(); + test_seal_unmapped_end(); + test_seal_multiple_vmas(); + test_seal_split_start(); + test_seal_split_end(); + test_seal_invalid_input(); + test_seal_zero_length(); + test_seal_twice(); + + test_seal_mprotect(false); + test_seal_mprotect(true); + + test_seal_start_mprotect(false); + test_seal_start_mprotect(true); + + test_seal_end_mprotect(false); + test_seal_end_mprotect(true); + + test_seal_mprotect_unalign_len(false); + test_seal_mprotect_unalign_len(true); + + test_seal_mprotect_unalign_len_variant_2(false); + test_seal_mprotect_unalign_len_variant_2(true); + + test_seal_mprotect_two_vma(false); + test_seal_mprotect_two_vma(true); + + test_seal_mprotect_two_vma_with_split(false); + test_seal_mprotect_two_vma_with_split(true); + + test_seal_mprotect_partial_mprotect(false); + test_seal_mprotect_partial_mprotect(true); + + test_seal_mprotect_two_vma_with_gap(false); + test_seal_mprotect_two_vma_with_gap(true); + + test_seal_mprotect_merge(false); + test_seal_mprotect_merge(true); + + test_seal_mprotect_split(false); + test_seal_mprotect_split(true); + + test_seal_munmap(false); + test_seal_munmap(true); + test_seal_munmap_two_vma(false); + test_seal_munmap_two_vma(true); + test_seal_munmap_vma_with_gap(false); + test_seal_munmap_vma_with_gap(true); + + test_munmap_start_freed(false); + test_munmap_start_freed(true); + test_munmap_middle_freed(false); + test_munmap_middle_freed(true); + test_munmap_end_freed(false); + test_munmap_end_freed(true); + + test_seal_mremap_shrink(false); + test_seal_mremap_shrink(true); + test_seal_mremap_expand(false); + test_seal_mremap_expand(true); + test_seal_mremap_move(false); + test_seal_mremap_move(true); + + test_seal_mremap_shrink_fixed(false); + test_seal_mremap_shrink_fixed(true); + test_seal_mremap_expand_fixed(false); + test_seal_mremap_expand_fixed(true); + test_seal_mremap_move_fixed(false); + test_seal_mremap_move_fixed(true); + test_seal_mremap_move_dontunmap(false); + test_seal_mremap_move_dontunmap(true); + test_seal_mremap_move_fixed_zero(false); + test_seal_mremap_move_fixed_zero(true); + test_seal_mremap_move_dontunmap_anyaddr(false); + test_seal_mremap_move_dontunmap_anyaddr(true); + test_seal_discard_ro_anon(false); + test_seal_discard_ro_anon(true); + test_seal_discard_ro_anon_on_rw(false); + test_seal_discard_ro_anon_on_rw(true); + test_seal_discard_ro_anon_on_shared(false); + test_seal_discard_ro_anon_on_shared(true); + test_seal_discard_ro_anon_on_filebacked(false); + test_seal_discard_ro_anon_on_filebacked(true); + test_seal_mmap_overwrite_prot(false); + test_seal_mmap_overwrite_prot(true); + test_seal_mmap_expand(false); + test_seal_mmap_expand(true); + test_seal_mmap_shrink(false); + test_seal_mmap_shrink(true); + + test_seal_merge_and_split(); + test_seal_zero_address(); + + test_seal_discard_ro_anon_on_pkey(false); + test_seal_discard_ro_anon_on_pkey(true); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 374a308174d2ba..48dc151f8fca8a 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -54,7 +54,6 @@ int test_nr; u64 shadow_pkey_reg; int dprint_in_signal; char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; -char buf[256]; void cat_into_file(char *str, char *file) { @@ -1745,42 +1744,6 @@ void pkey_setup_shadow(void) shadow_pkey_reg = __read_pkey_reg(); } -pid_t parent_pid; - -void restore_settings_atexit(void) -{ - if (parent_pid == getpid()) - cat_into_file(buf, "/proc/sys/vm/nr_hugepages"); -} - -void save_settings(void) -{ - int fd; - int err; - - if (geteuid()) - return; - - fd = open("/proc/sys/vm/nr_hugepages", O_RDONLY); - if (fd < 0) { - fprintf(stderr, "error opening\n"); - perror("error: "); - exit(__LINE__); - } - - /* -1 to guarantee leaving the trailing \0 */ - err = read(fd, buf, sizeof(buf)-1); - if (err < 0) { - fprintf(stderr, "error reading\n"); - perror("error: "); - exit(__LINE__); - } - - parent_pid = getpid(); - atexit(restore_settings_atexit); - close(fd); -} - int main(void) { int nr_iterations = 22; @@ -1788,7 +1751,6 @@ int main(void) srand((unsigned int)time(NULL)); - save_settings(); setup_handlers(); printf("has pkeys: %d\n", pkeys_supported); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index c2c542fe7b17bb..3157204b90476b 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -152,9 +152,13 @@ done < /proc/meminfo # both of these requirements into account and attempt to increase # number of huge pages available. nr_cpus=$(nproc) -hpgsize_MB=$((hpgsize_KB / 1024)) -half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128)) -needmem_KB=$((half_ufd_size_MB * 2 * 1024)) +uffd_min_KB=$((hpgsize_KB * nr_cpus * 2)) +hugetlb_min_KB=$((256 * 1024)) +if [[ $uffd_min_KB -gt $hugetlb_min_KB ]]; then + needmem_KB=$uffd_min_KB +else + needmem_KB=$hugetlb_min_KB +fi # set proper nr_hugepages if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then @@ -294,7 +298,8 @@ CATEGORY="userfaultfd" run_test ./uffd-unit-tests uffd_stress_bin=./uffd-stress CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 # Hugetlb tests require source and destination huge pages. Pass in half -# the size ($half_ufd_size_MB), which is used for *each*. +# the size of the free pages we have, which is used for *each*. +half_ufd_size_MB=$((freepgs / 2)) CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 @@ -385,6 +390,7 @@ CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 0 CATEGORY="ksm" run_test ./ksm_functional_tests # protection_keys tests +nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) if [ -x ./protection_keys_32 ] then CATEGORY="pkey" run_test ./protection_keys_32 @@ -394,6 +400,7 @@ if [ -x ./protection_keys_64 ] then CATEGORY="pkey" run_test ./protection_keys_64 fi +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages if [ -x ./soft-dirty ] then diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c new file mode 100644 index 00000000000000..f2babec79bb63d --- /dev/null +++ b/tools/testing/selftests/mm/seal_elf.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sys/mman.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <stdbool.h> +#include "../kselftest.h" +#include <syscall.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <sys/stat.h> + +/* + * need those definition for manually build using gcc. + * gcc -I ../../../../usr/include -DDEBUG -O3 -DDEBUG -O3 seal_elf.c -o seal_elf + */ +#define FAIL_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_fail("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + +#define SKIP_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_skip("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + + +#define TEST_END_CHECK() {\ + ksft_test_result_pass("%s\n", __func__);\ + return;\ +test_end:\ + return;\ +} + +#ifndef u64 +#define u64 unsigned long long +#endif + +/* + * define sys_xyx to call syscall directly. + */ +static int sys_mseal(void *start, size_t len) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mseal, start, len, 0); + return sret; +} + +static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, + unsigned long flags, unsigned long fd, unsigned long offset) +{ + void *sret; + + errno = 0; + sret = (void *) syscall(__NR_mmap, addr, len, prot, + flags, fd, offset); + return sret; +} + +static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mprotect, ptr, size, prot); + return sret; +} + +static bool seal_support(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + + ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (ptr == (void *) -1) + return false; + + ret = sys_mseal(ptr, page_size); + if (ret < 0) + return false; + + return true; +} + +const char somestr[4096] = {"READONLY"}; + +static void test_seal_elf(void) +{ + int ret; + FILE *maps; + char line[512]; + uintptr_t addr_start, addr_end; + char prot[5]; + char filename[256]; + unsigned long page_size = getpagesize(); + unsigned long long ptr = (unsigned long long) somestr; + char *somestr2 = (char *)somestr; + + /* + * Modify the protection of readonly somestr + */ + if (((unsigned long long)ptr % page_size) != 0) + ptr = (unsigned long long)ptr & ~(page_size - 1); + + ksft_print_msg("somestr = %s\n", somestr); + ksft_print_msg("change protection to rw\n"); + ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + *somestr2 = 'A'; + ksft_print_msg("somestr is modified to: %s\n", somestr); + ret = sys_mprotect((void *)ptr, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(!ret); + + maps = fopen("/proc/self/maps", "r"); + FAIL_TEST_IF_FALSE(maps); + + /* + * apply sealing to elf binary + */ + while (fgets(line, sizeof(line), maps)) { + if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]", + &addr_start, &addr_end, prot, filename) == 4) { + if (strlen(filename)) { + /* + * seal the mapping if read only. + */ + if (strstr(prot, "r-")) { + ret = sys_mseal((void *)addr_start, addr_end - addr_start); + FAIL_TEST_IF_FALSE(!ret); + ksft_print_msg("sealed: %lx-%lx %s %s\n", + addr_start, addr_end, prot, filename); + if ((uintptr_t) somestr >= addr_start && + (uintptr_t) somestr <= addr_end) + ksft_print_msg("mapping for somestr found\n"); + } + } + } + } + fclose(maps); + + ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + ksft_print_msg("somestr is sealed, mprotect is rejected\n"); + + TEST_END_CHECK(); +} + +int main(int argc, char **argv) +{ + bool test_seal = seal_support(); + + ksft_print_header(); + ksft_print_msg("pid=%d\n", getpid()); + + if (!test_seal) + ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); + + ksft_set_plan(1); + + test_seal_elf(); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index 7dbfa53d93a05f..bdfa5d085f0099 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -209,5 +209,5 @@ int main(int argc, char **argv) close(pagemap_fd); - return ksft_exit_pass(); + ksft_finished(); } diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 6c988bd2f33567..d3c7f5fb3e7b77 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -300,7 +300,7 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, char **addr) { size_t i; - int dummy; + int __attribute__((unused)) dummy = 0; srand(time(NULL)); diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 7bcf8d48256a66..4e4c1e311247ff 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -12,6 +12,8 @@ #include <errno.h> #include <sys/mman.h> #include <sys/time.h> +#include <fcntl.h> + #include "../kselftest.h" /* @@ -85,7 +87,7 @@ static int validate_lower_address_hint(void) char *ptr; ptr = mmap((void *) (1UL << 45), MAP_CHUNK_SIZE, PROT_READ | - PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr == MAP_FAILED) return 0; @@ -93,6 +95,66 @@ static int validate_lower_address_hint(void) return 1; } +static int validate_complete_va_space(void) +{ + unsigned long start_addr, end_addr, prev_end_addr; + char line[400]; + char prot[6]; + FILE *file; + int fd; + + fd = open("va_dump", O_CREAT | O_WRONLY, 0600); + unlink("va_dump"); + if (fd < 0) { + ksft_test_result_skip("cannot create or open dump file\n"); + ksft_finished(); + } + + file = fopen("/proc/self/maps", "r"); + if (file == NULL) + ksft_exit_fail_msg("cannot open /proc/self/maps\n"); + + prev_end_addr = 0; + while (fgets(line, sizeof(line), file)) { + unsigned long hop; + + if (sscanf(line, "%lx-%lx %s[rwxp-]", + &start_addr, &end_addr, prot) != 3) + ksft_exit_fail_msg("cannot parse /proc/self/maps\n"); + + /* end of userspace mappings; ignore vsyscall mapping */ + if (start_addr & (1UL << 63)) + return 0; + + /* /proc/self/maps must have gaps less than MAP_CHUNK_SIZE */ + if (start_addr - prev_end_addr >= MAP_CHUNK_SIZE) + return 1; + + prev_end_addr = end_addr; + + if (prot[0] != 'r') + continue; + + /* + * Confirm whether MAP_CHUNK_SIZE chunk can be found or not. + * If write succeeds, no need to check MAP_CHUNK_SIZE - 1 + * addresses after that. If the address was not held by this + * process, write would fail with errno set to EFAULT. + * Anyways, if write returns anything apart from 1, exit the + * program since that would mean a bug in /proc/self/maps. + */ + hop = 0; + while (start_addr + hop < end_addr) { + if (write(fd, (void *)(start_addr + hop), 1) != 1) + return 1; + lseek(fd, 0, SEEK_SET); + + hop += MAP_CHUNK_SIZE; + } + } + return 0; +} + int main(int argc, char *argv[]) { char *ptr[NR_CHUNKS_LOW]; @@ -105,13 +167,11 @@ int main(int argc, char *argv[]) for (i = 0; i < NR_CHUNKS_LOW; i++) { ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr[i] == MAP_FAILED) { - if (validate_lower_address_hint()) { - ksft_test_result_skip("Memory constraint not fulfilled\n"); - ksft_finished(); - } + if (validate_lower_address_hint()) + ksft_exit_fail_msg("mmap unexpectedly succeeded with hint\n"); break; } @@ -127,7 +187,7 @@ int main(int argc, char *argv[]) for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hind_addr(); hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (hptr[i] == MAP_FAILED) break; @@ -135,6 +195,10 @@ int main(int argc, char *argv[]) validate_addr(hptr[i], 1); } hchunks = i; + if (validate_complete_va_space()) { + ksft_test_result_fail("BUG in mmap() or /proc/self/maps\n"); + ksft_finished(); + } for (i = 0; i < lchunks; i++) munmap(ptr[i], MAP_CHUNK_SIZE); diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c index c537d52fafc586..a40541bb7c7dee 100644 --- a/tools/testing/selftests/riscv/hwprobe/cbo.c +++ b/tools/testing/selftests/riscv/hwprobe/cbo.c @@ -19,7 +19,7 @@ #include "hwprobe.h" #include "../../kselftest.h" -#define MK_CBO(fn) cpu_to_le32((fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15) +#define MK_CBO(fn) le32_bswap((uint32_t)(fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15) static char mem[4096] __aligned(4096) = { [0 ... 4095] = 0xa5 }; diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.h b/tools/testing/selftests/riscv/hwprobe/hwprobe.h index e3fccb390c4dc9..f3de970c32227b 100644 --- a/tools/testing/selftests/riscv/hwprobe/hwprobe.h +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h @@ -4,6 +4,16 @@ #include <stddef.h> #include <asm/hwprobe.h> +#if __BYTE_ORDER == __BIG_ENDIAN +# define le32_bswap(_x) \ + ((((_x) & 0x000000ffU) << 24) | \ + (((_x) & 0x0000ff00U) << 8) | \ + (((_x) & 0x00ff0000U) >> 8) | \ + (((_x) & 0xff000000U) >> 24)) +#else +# define le32_bswap(_x) (_x) +#endif + /* * Rather than relying on having a new enough libc to define this, just do it * ourselves. This way we don't need to be coupled to a new-enough libc to diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index b5d592d4099e85..d975a67673299f 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -158,6 +158,20 @@ static void handle_sigsys(int sig, siginfo_t *info, void *ucontext) /* In preparation for sigreturn. */ SYSCALL_DISPATCH_OFF(glob_sel); + + /* + * The tests for argument handling assume that `syscall(x) == x`. This + * is a NOP on x86 because the syscall number is passed in %rax, which + * happens to also be the function ABI return register. Other + * architectures may need to swizzle the arguments around. + */ +#if defined(__riscv) +/* REG_A7 is not defined in libc headers */ +# define REG_A7 (REG_A0 + 7) + + ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A0] = + ((ucontext_t *)ucontext)->uc_mcontext.__gregs[REG_A7]; +#endif } TEST(dispatch_and_return) diff --git a/tools/testing/selftests/x86/test_shadow_stack.c b/tools/testing/selftests/x86/test_shadow_stack.c index 757e6527f67e2a..ee909a7927f9d9 100644 --- a/tools/testing/selftests/x86/test_shadow_stack.c +++ b/tools/testing/selftests/x86/test_shadow_stack.c @@ -556,7 +556,7 @@ struct node { * looked at the shadow stack gaps. * 5. See if it landed in the gap. */ -int test_guard_gap(void) +int test_guard_gap_other_gaps(void) { void *free_area, *shstk, *test_map = (void *)0xFFFFFFFFFFFFFFFF; struct node *head = NULL, *cur; @@ -593,11 +593,64 @@ int test_guard_gap(void) if (shstk - test_map - PAGE_SIZE != PAGE_SIZE) return 1; - printf("[OK]\tGuard gap test\n"); + printf("[OK]\tGuard gap test, other mapping's gaps\n"); return 0; } +/* Tests respecting the guard gap of the mapping getting placed */ +int test_guard_gap_new_mappings_gaps(void) +{ + void *free_area, *shstk_start, *test_map = (void *)0xFFFFFFFFFFFFFFFF; + struct node *head = NULL, *cur; + int ret = 0; + + free_area = mmap(0, PAGE_SIZE * 4, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + munmap(free_area, PAGE_SIZE * 4); + + /* Test letting map_shadow_stack find a free space */ + shstk_start = mmap(free_area, PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (shstk_start == MAP_FAILED || shstk_start != free_area) + return 1; + + while (test_map > shstk_start) { + test_map = (void *)syscall(__NR_map_shadow_stack, 0, PAGE_SIZE, 0); + if (test_map == MAP_FAILED) { + printf("[INFO]\tmap_shadow_stack MAP_FAILED\n"); + ret = 1; + break; + } + + cur = malloc(sizeof(*cur)); + cur->mapping = test_map; + + cur->next = head; + head = cur; + + if (test_map == free_area + PAGE_SIZE) { + printf("[INFO]\tNew mapping has other mapping in guard gap!\n"); + ret = 1; + break; + } + } + + while (head) { + cur = head; + head = cur->next; + munmap(cur->mapping, PAGE_SIZE); + free(cur); + } + + munmap(shstk_start, PAGE_SIZE); + + if (!ret) + printf("[OK]\tGuard gap test, placement mapping's gaps\n"); + + return ret; +} + /* * Too complicated to pull it out of the 32 bit header, but also get the * 64 bit one needed above. Just define a copy here. @@ -850,9 +903,15 @@ int main(int argc, char *argv[]) goto out; } - if (test_guard_gap()) { + if (test_guard_gap_other_gaps()) { + ret = 1; + printf("[FAIL]\tGuard gap test, other mappings' gaps\n"); + goto out; + } + + if (test_guard_gap_new_mappings_gaps()) { ret = 1; - printf("[FAIL]\tGuard gap test\n"); + printf("[FAIL]\tGuard gap test, placement mapping's gaps\n"); goto out; } diff --git a/tools/writeback/wb_monitor.py b/tools/writeback/wb_monitor.py new file mode 100644 index 00000000000000..5e3591f1f9a9df --- /dev/null +++ b/tools/writeback/wb_monitor.py @@ -0,0 +1,172 @@ +#!/usr/bin/env drgn +# +# Copyright (C) 2024 Kemeng Shi <shikemeng@huaweicloud.com> +# Copyright (C) 2024 Huawei Inc + +desc = """ +This is a drgn script based on wq_monitor.py to monitor writeback info on +backing dev. For more info on drgn, visit https://github.com/osandov/drgn. + + writeback(kB) Amount of dirty pages are currently being written back to + disk. + + reclaimable(kB) Amount of pages are currently reclaimable. + + dirtied(kB) Amount of pages have been dirtied. + + wrttien(kB) Amount of dirty pages have been written back to disk. + + avg_wb(kBps) Smoothly estimated write bandwidth of writing dirty pages + back to disk. +""" + +import signal +import re +import time +import json + +import drgn +from drgn.helpers.linux.list import list_for_each_entry + +import argparse +parser = argparse.ArgumentParser(description=desc, + formatter_class=argparse.RawTextHelpFormatter) +parser.add_argument('bdi', metavar='REGEX', nargs='*', + help='Target backing device name patterns (all if empty)') +parser.add_argument('-i', '--interval', metavar='SECS', type=float, default=1, + help='Monitoring interval (0 to print once and exit)') +parser.add_argument('-j', '--json', action='store_true', + help='Output in json') +parser.add_argument('-c', '--cgroup', action='store_true', + help='show writeback of bdi in cgroup') +args = parser.parse_args() + +bdi_list = prog['bdi_list'] + +WB_RECLAIMABLE = prog['WB_RECLAIMABLE'] +WB_WRITEBACK = prog['WB_WRITEBACK'] +WB_DIRTIED = prog['WB_DIRTIED'] +WB_WRITTEN = prog['WB_WRITTEN'] +NR_WB_STAT_ITEMS = prog['NR_WB_STAT_ITEMS'] + +PAGE_SHIFT = prog['PAGE_SHIFT'] + +def K(x): + return x << (PAGE_SHIFT - 10) + +class Stats: + def dict(self, now): + return { 'timestamp' : now, + 'name' : self.name, + 'writeback' : self.stats[WB_WRITEBACK], + 'reclaimable' : self.stats[WB_RECLAIMABLE], + 'dirtied' : self.stats[WB_DIRTIED], + 'written' : self.stats[WB_WRITTEN], + 'avg_wb' : self.avg_bw, } + + def table_header_str(): + return f'{"":>16} {"writeback":>10} {"reclaimable":>12} ' \ + f'{"dirtied":>9} {"written":>9} {"avg_bw":>9}' + + def table_row_str(self): + out = f'{self.name[-16:]:16} ' \ + f'{self.stats[WB_WRITEBACK]:10} ' \ + f'{self.stats[WB_RECLAIMABLE]:12} ' \ + f'{self.stats[WB_DIRTIED]:9} ' \ + f'{self.stats[WB_WRITTEN]:9} ' \ + f'{self.avg_bw:9} ' + return out + + def show_header(): + if Stats.table_fmt: + print() + print(Stats.table_header_str()) + + def show_stats(self): + if Stats.table_fmt: + print(self.table_row_str()) + else: + print(self.dict(Stats.now)) + +class WbStats(Stats): + def __init__(self, wb): + bdi_name = wb.bdi.dev_name.string_().decode() + # avoid to use bdi.wb.memcg_css which is only defined when + # CONFIG_CGROUP_WRITEBACK is enabled + if wb == wb.bdi.wb.address_of_(): + ino = "1" + else: + ino = str(wb.memcg_css.cgroup.kn.id.value_()) + self.name = bdi_name + '_' + ino + + self.stats = [0] * NR_WB_STAT_ITEMS + for i in range(NR_WB_STAT_ITEMS): + if wb.stat[i].count >= 0: + self.stats[i] = int(K(wb.stat[i].count)) + else: + self.stats[i] = 0 + + self.avg_bw = int(K(wb.avg_write_bandwidth)) + +class BdiStats(Stats): + def __init__(self, bdi): + self.name = bdi.dev_name.string_().decode() + self.stats = [0] * NR_WB_STAT_ITEMS + self.avg_bw = 0 + + def collectStats(self, wb_stats): + for i in range(NR_WB_STAT_ITEMS): + self.stats[i] += wb_stats.stats[i] + + self.avg_bw += wb_stats.avg_bw + +exit_req = False + +def sigint_handler(signr, frame): + global exit_req + exit_req = True + +def main(): + # handle args + Stats.table_fmt = not args.json + interval = args.interval + cgroup = args.cgroup + + re_str = None + if args.bdi: + for r in args.bdi: + if re_str is None: + re_str = r + else: + re_str += '|' + r + + filter_re = re.compile(re_str) if re_str else None + + # monitoring loop + signal.signal(signal.SIGINT, sigint_handler) + + while not exit_req: + Stats.now = time.time() + + Stats.show_header() + for bdi in list_for_each_entry('struct backing_dev_info', bdi_list.address_of_(), 'bdi_list'): + bdi_stats = BdiStats(bdi) + if filter_re and not filter_re.search(bdi_stats.name): + continue + + for wb in list_for_each_entry('struct bdi_writeback', bdi.wb_list.address_of_(), 'bdi_node'): + wb_stats = WbStats(wb) + bdi_stats.collectStats(wb_stats) + if cgroup: + wb_stats.show_stats() + + bdi_stats.show_stats() + if cgroup and Stats.table_fmt: + print() + + if interval == 0: + break + time.sleep(interval) + +if __name__ == "__main__": + main() diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ff0a20565f9087..92c70c99420af1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2901,7 +2901,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, spinlock_t *ptl; int r; - r = follow_pte(vma->vm_mm, addr, &ptep, &ptl); + r = follow_pte(vma, addr, &ptep, &ptl); if (r) { /* * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does @@ -2916,7 +2916,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma, if (r) return r; - r = follow_pte(vma->vm_mm, addr, &ptep, &ptl); + r = follow_pte(vma, addr, &ptep, &ptl); if (r) return r; } |