diff options
240 files changed, 9207 insertions, 4664 deletions
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-damon b/Documentation/ABI/testing/sysfs-kernel-mm-damon index 9e282065cbcf..08b9df323560 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-damon +++ b/Documentation/ABI/testing/sysfs-kernel-mm-damon @@ -23,9 +23,10 @@ Date: Mar 2022 Contact: SeongJae Park <sj@kernel.org> Description: Writing 'on' or 'off' to this file makes the kdamond starts or stops, respectively. Reading the file returns the keywords - based on the current status. Writing 'update_schemes_stats' to - the file updates contents of schemes stats files of the - kdamond. + based on the current status. Writing 'commit' to this file + makes the kdamond reads the user inputs in the sysfs files + except 'state' again. Writing 'update_schemes_stats' to the + file updates contents of schemes stats files of the kdamond. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/pid Date: Mar 2022 @@ -40,14 +41,24 @@ Description: Writing a number 'N' to this file creates the number of directories for controlling each DAMON context named '0' to 'N-1' under the contexts/ directory. +What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/avail_operations +Date: Apr 2022 +Contact: SeongJae Park <sj@kernel.org> +Description: Reading this file returns the available monitoring operations + sets on the currently running kernel. + What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/operations Date: Mar 2022 Contact: SeongJae Park <sj@kernel.org> Description: Writing a keyword for a monitoring operations set ('vaddr' for - virtual address spaces monitoring, and 'paddr' for the physical - address space monitoring) to this file makes the context to use - the operations set. Reading the file returns the keyword for - the operations set the context is set to use. + virtual address spaces monitoring, 'fvaddr' for fixed virtual + address ranges monitoring, and 'paddr' for the physical address + space monitoring) to this file makes the context to use the + operations set. Reading the file returns the keyword for the + operations set the context is set to use. + + Note that only the operations sets that listed in + 'avail_operations' file are valid inputs. What: /sys/kernel/mm/damon/admin/kdamonds/<K>/contexts/<C>/monitoring_attrs/intervals/sample_us Date: Mar 2022 diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst index 54fe63745ed8..c73b16930449 100644 --- a/Documentation/admin-guide/blockdev/zram.rst +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -343,6 +343,11 @@ Admin can request writeback of those idle pages at right timing via:: With the command, zram will writeback idle pages from memory to the storage. +Additionally, if a user choose to writeback only huge and idle pages +this can be accomplished with:: + + echo huge_idle > /sys/block/zramX/writeback + If an admin wants to write a specific page in zram device to the backing device, they could write a page index into the interface. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 38aa01939e1e..176298f2f4de 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1208,6 +1208,34 @@ PAGE_SIZE multiple when read back. high limit is used and monitored properly, this limit's utility is limited to providing the final safety net. + memory.reclaim + A write-only nested-keyed file which exists for all cgroups. + + 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. + + memory.peak + A read-only single value file which exists on non-root + cgroups. + + The max memory usage recorded for the cgroup and its + descendants since the creation of the cgroup. + memory.oom.group A read-write single value file which exists on non-root cgroups. The default value is "0". @@ -1326,6 +1354,12 @@ PAGE_SIZE multiple when read back. Amount of cached filesystem data that is swap-backed, such as tmpfs, shm segments, shared anonymous mmap()s + zswap + Amount of memory consumed by the zswap compression backend. + + zswapped + Amount of application memory swapped out to zswap. + file_mapped Amount of cached filesystem data mapped with mmap() @@ -1516,6 +1550,21 @@ PAGE_SIZE multiple when read back. higher than the limit for an extended period of time. This reduces the impact on the workload and memory management. + memory.zswap.current + A read-only single value file which exists on non-root + cgroups. + + The total amount of memory consumed by the zswap compression + backend. + + memory.zswap.max + A read-write single value file which exists on non-root + cgroups. The default is "max". + + Zswap usage hard limit. If a cgroup's zswap pool reaches this + limit, it will refuse to take any more stores before existing + entries fault back in or are written out to disk. + memory.pressure A read-only nested-keyed file. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a9066cfb85a0..32073f873662 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1705,16 +1705,16 @@ boot-time allocation of gigantic hugepages is skipped. hugetlb_free_vmemmap= - [KNL] Reguires CONFIG_HUGETLB_PAGE_FREE_VMEMMAP + [KNL] Reguires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP enabled. Allows heavy hugetlb users to free up some more memory (7 * PAGE_SIZE for each 2MB hugetlb page). - Format: { on | off (default) } + Format: { [oO][Nn]/Y/y/1 | [oO][Ff]/N/n/0 (default) } - on: enable the feature - off: disable the feature + [oO][Nn]/Y/y/1: enable the feature + [oO][Ff]/N/n/0: disable the feature - Built with CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON=y, + Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y, the default is on. This is not compatible with memory_hotplug.memmap_on_memory. diff --git a/Documentation/admin-guide/mm/damon/reclaim.rst b/Documentation/admin-guide/mm/damon/reclaim.rst index 0af51a9705b1..46306f1f34b1 100644 --- a/Documentation/admin-guide/mm/damon/reclaim.rst +++ b/Documentation/admin-guide/mm/damon/reclaim.rst @@ -66,6 +66,17 @@ Setting it as ``N`` disables DAMON_RECLAIM. Note that DAMON_RECLAIM could do no real monitoring and reclamation due to the watermarks-based activation condition. Refer to below descriptions for the watermarks parameter for this. +commit_inputs +------------- + +Make DAMON_RECLAIM reads the input parameters again, except ``enabled``. + +Input parameters that updated while DAMON_RECLAIM is running are not applied +by default. Once this parameter is set as ``Y``, DAMON_RECLAIM reads values +of parametrs except ``enabled`` again. Once the re-reading is done, this +parameter is set as ``N``. If invalid parameters are found while the +re-reading, DAMON_RECLAIM will be disabled. + min_age ------- diff --git a/Documentation/admin-guide/mm/damon/usage.rst b/Documentation/admin-guide/mm/damon/usage.rst index 592ea9a50881..1bb7b72414b2 100644 --- a/Documentation/admin-guide/mm/damon/usage.rst +++ b/Documentation/admin-guide/mm/damon/usage.rst @@ -68,7 +68,7 @@ comma (","). :: │ kdamonds/nr_kdamonds │ │ 0/state,pid │ │ │ contexts/nr_contexts - │ │ │ │ 0/operations + │ │ │ │ 0/avail_operations,operations │ │ │ │ │ monitoring_attrs/ │ │ │ │ │ │ intervals/sample_us,aggr_us,update_us │ │ │ │ │ │ nr_regions/min,max @@ -121,10 +121,11 @@ In each kdamond directory, two files (``state`` and ``pid``) and one directory Reading ``state`` returns ``on`` if the kdamond is currently running, or ``off`` if it is not running. Writing ``on`` or ``off`` makes the kdamond be -in the state. Writing ``update_schemes_stats`` to ``state`` file updates the -contents of stats files for each DAMON-based operation scheme of the kdamond. -For details of the stats, please refer to :ref:`stats section -<sysfs_schemes_stats>`. +in the state. Writing ``commit`` to the ``state`` file makes kdamond reads the +user inputs in the sysfs files except ``state`` file again. Writing +``update_schemes_stats`` to ``state`` file updates the contents of stats files +for each DAMON-based operation scheme of the kdamond. For details of the +stats, please refer to :ref:`stats section <sysfs_schemes_stats>`. If the state is ``on``, reading ``pid`` shows the pid of the kdamond thread. @@ -143,17 +144,28 @@ be written to the file. contexts/<N>/ ------------- -In each context directory, one file (``operations``) and three directories -(``monitoring_attrs``, ``targets``, and ``schemes``) exist. +In each context directory, two files (``avail_operations`` and ``operations``) +and three directories (``monitoring_attrs``, ``targets``, and ``schemes``) +exist. DAMON supports multiple types of monitoring operations, including those for -virtual address space and the physical address space. You can set and get what -type of monitoring operations DAMON will use for the context by writing one of -below keywords to, and reading from the file. +virtual address space and the physical address space. You can get the list of +available monitoring operations set on the currently running kernel by reading +``avail_operations`` file. Based on the kernel configuration, the file will +list some or all of below keywords. - vaddr: Monitor virtual address spaces of specific processes + - fvaddr: Monitor fixed virtual address ranges - paddr: Monitor the physical address space of the system +Please refer to :ref:`regions sysfs directory <sysfs_regions>` for detailed +differences between the operations sets in terms of the monitoring target +regions. + +You can set and get what type of monitoring operations DAMON will use for the +context by writing one of the keywords listed in ``avail_operations`` file and +reading from the ``operations`` file. + contexts/<N>/monitoring_attrs/ ------------------------------ @@ -192,6 +204,8 @@ If you wrote ``vaddr`` to the ``contexts/<N>/operations``, each target should be a process. You can specify the process to DAMON by writing the pid of the process to the ``pid_target`` file. +.. _sysfs_regions: + targets/<N>/regions ------------------- @@ -202,9 +216,10 @@ can be covered. However, users could want to set the initial monitoring region to specific address ranges. In contrast, DAMON do not automatically sets and updates the monitoring target -regions when ``paddr`` monitoring operations set is being used (``paddr`` is -written to the ``contexts/<N>/operations``). Therefore, users should set the -monitoring target regions by themselves in the case. +regions when ``fvaddr`` or ``paddr`` monitoring operations sets are being used +(``fvaddr`` or ``paddr`` have written to the ``contexts/<N>/operations``). +Therefore, users should set the monitoring target regions by themselves in the +cases. For such cases, users can explicitly set the initial monitoring target regions as they want, by writing proper values to the files under this directory. diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index 0166f9de3428..a90330d0a837 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -164,7 +164,7 @@ default_hugepagesz will all result in 256 2M huge pages being allocated. Valid default huge page size is architecture dependent. hugetlb_free_vmemmap - When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set, this enables freeing + When CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is set, this enables optimizing unused vmemmap pages associated with each HugeTLB page. When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages`` diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst index 97d816791aca..b244f0202a03 100644 --- a/Documentation/admin-guide/mm/ksm.rst +++ b/Documentation/admin-guide/mm/ksm.rst @@ -184,6 +184,24 @@ The maximum possible ``pages_sharing/pages_shared`` ratio is limited by the ``max_page_sharing`` tunable. To increase the ratio ``max_page_sharing`` must be increased accordingly. +Monitoring KSM events +===================== + +There are some counters in /proc/vmstat that may be used to monitor KSM events. +KSM might help save memory, it's a tradeoff by may suffering delay on KSM COW +or on swapping in copy. Those events could help users evaluate whether or how +to use KSM. For example, if cow_ksm increases too fast, user may decrease the +range of madvise(, , MADV_MERGEABLE). + +cow_ksm + is incremented every time a KSM page triggers copy on write (COW) + when users try to write to a KSM page, we have to make a copy. + +ksm_swpin_copy + is incremented every time a KSM page is copied when swapping in + note that KSM page might be copied when swapping in because do_swap_page() + cannot do all the locking needed to reconstitute a cross-anon_vma KSM page. + -- Izik Eidus, Hugh Dickins, 17 Nov 2009 diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index f4804ce37c58..5c9aa171a0d3 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -62,6 +62,7 @@ Currently, these files are in /proc/sys/vm: - overcommit_memory - overcommit_ratio - page-cluster +- page_lock_unfairness - panic_on_oom - percpu_pagelist_high_fraction - stat_interval @@ -561,6 +562,45 @@ Change the minimum size of the hugepage pool. See Documentation/admin-guide/mm/hugetlbpage.rst +hugetlb_optimize_vmemmap +======================== + +This knob is not available when memory_hotplug.memmap_on_memory (kernel parameter) +is configured or the size of 'struct page' (a structure defined in +include/linux/mm_types.h) is not power of two (an unusual system config could +result in this). + +Enable (set to 1) or disable (set to 0) the feature of optimizing vmemmap pages +associated with each HugeTLB page. + +Once enabled, the vmemmap pages of subsequent allocation of HugeTLB pages from +buddy allocator will be optimized (7 pages per 2MB HugeTLB page and 4095 pages +per 1GB HugeTLB page), whereas already allocated HugeTLB pages will not be +optimized. When those optimized HugeTLB pages are freed from the HugeTLB pool +to the buddy allocator, the vmemmap pages representing that range needs to be +remapped again and the vmemmap pages discarded earlier need to be rellocated +again. If your use case is that HugeTLB pages are allocated 'on the fly' (e.g. +never explicitly allocating HugeTLB pages with 'nr_hugepages' but only set +'nr_overcommit_hugepages', those overcommitted HugeTLB pages are allocated 'on +the fly') instead of being pulled from the HugeTLB pool, you should weigh the +benefits of memory savings against the more overhead (~2x slower than before) +of allocation or freeing HugeTLB pages between the HugeTLB pool and the buddy +allocator. Another behavior to note is that if the system is under heavy memory +pressure, it could prevent the user from freeing HugeTLB pages from the HugeTLB +pool to the buddy allocator since the allocation of vmemmap pages could be +failed, you have to retry later if your system encounter this situation. + +Once disabled, the vmemmap pages of subsequent allocation of HugeTLB pages from +buddy allocator will not be optimized meaning the extra overhead at allocation +time from buddy allocator disappears, whereas already optimized HugeTLB pages +will not be affected. If you want to make sure there are no optimized HugeTLB +pages, you can set "nr_hugepages" to 0 first and then disable this. Note that +writing 0 to nr_hugepages will make any "in use" HugeTLB pages become surplus +pages. So, those surplus pages are still optimized until they are no longer +in use. You would need to wait for those surplus pages to be released before +there are no optimized pages in the system. + + nr_hugepages_mempolicy ====================== @@ -754,6 +794,14 @@ extra faults and I/O delays for following faults if they would have been part of that consecutive pages readahead would have brought in. +page_lock_unfairness +==================== + +This value determines the number of times that the page lock can be +stolen from under a waiter. After the lock is stolen the number of times +specified in this file (default is 5), the "fair lock handoff" semantics +will apply, and the waiter will only be awakened if the lock can be taken. + panic_on_oom ============ diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 7614a1fc30fa..1772fd457fed 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -4,39 +4,76 @@ The Kernel Address Sanitizer (KASAN) Overview -------- -KernelAddressSANitizer (KASAN) is a dynamic memory safety error detector -designed to find out-of-bound and use-after-free bugs. KASAN has three modes: +Kernel Address Sanitizer (KASAN) is a dynamic memory safety error detector +designed to find out-of-bounds and use-after-free bugs. -1. generic KASAN (similar to userspace ASan), -2. software tag-based KASAN (similar to userspace HWASan), -3. hardware tag-based KASAN (based on hardware memory tagging). +KASAN has three modes: -Generic KASAN is mainly used for debugging due to a large memory overhead. -Software tag-based KASAN can be used for dogfood testing as it has a lower -memory overhead that allows using it with real workloads. Hardware tag-based -KASAN comes with low memory and performance overheads and, therefore, can be -used in production. Either as an in-field memory bug detector or as a security -mitigation. +1. Generic KASAN +2. Software Tag-Based KASAN +3. Hardware Tag-Based KASAN -Software KASAN modes (#1 and #2) use compile-time instrumentation to insert -validity checks before every memory access and, therefore, require a compiler -version that supports that. +Generic KASAN, enabled with CONFIG_KASAN_GENERIC, is the mode intended for +debugging, similar to userspace ASan. This mode is supported on many CPU +architectures, but it has significant performance and memory overheads. -Generic KASAN is supported in GCC and Clang. With GCC, it requires version -8.3.0 or later. Any supported Clang version is compatible, but detection of -out-of-bounds accesses for global variables is only supported since Clang 11. +Software Tag-Based KASAN or SW_TAGS KASAN, enabled with CONFIG_KASAN_SW_TAGS, +can be used for both debugging and dogfood testing, similar to userspace HWASan. +This mode is only supported for arm64, but its moderate memory overhead allows +using it for testing on memory-restricted devices with real workloads. -Software tag-based KASAN mode is only supported in Clang. +Hardware Tag-Based KASAN or HW_TAGS KASAN, enabled with CONFIG_KASAN_HW_TAGS, +is the mode intended to be used as an in-field memory bug detector or as a +security mitigation. This mode only works on arm64 CPUs that support MTE +(Memory Tagging Extension), but it has low memory and performance overheads and +thus can be used in production. -The hardware KASAN mode (#3) relies on hardware to perform the checks but -still requires a compiler version that supports memory tagging instructions. -This mode is supported in GCC 10+ and Clang 12+. +For details about the memory and performance impact of each KASAN mode, see the +descriptions of the corresponding Kconfig options. -Both software KASAN modes work with SLUB and SLAB memory allocators, -while the hardware tag-based KASAN currently only supports SLUB. +The Generic and the Software Tag-Based modes are commonly referred to as the +software modes. The Software Tag-Based and the Hardware Tag-Based modes are +referred to as the tag-based modes. -Currently, generic KASAN is supported for the x86_64, arm, arm64, xtensa, s390, -and riscv architectures, and tag-based KASAN modes are supported only for arm64. +Support +------- + +Architectures +~~~~~~~~~~~~~ + +Generic KASAN is supported on x86_64, arm, arm64, powerpc, riscv, s390, and +xtensa, and the tag-based KASAN modes are supported only on arm64. + +Compilers +~~~~~~~~~ + +Software KASAN modes use compile-time instrumentation to insert validity checks +before every memory access and thus require a compiler version that provides +support for that. The Hardware Tag-Based mode relies on hardware to perform +these checks but still requires a compiler version that supports the memory +tagging instructions. + +Generic KASAN requires GCC version 8.3.0 or later +or any Clang version supported by the kernel. + +Software Tag-Based KASAN requires GCC 11+ +or any Clang version supported by the kernel. + +Hardware Tag-Based KASAN requires GCC 10+ or Clang 12+. + +Memory types +~~~~~~~~~~~~ + +Generic KASAN supports finding bugs in all of slab, page_alloc, vmap, vmalloc, +stack, and global memory. + +Software Tag-Based KASAN supports slab, page_alloc, vmalloc, and stack memory. + +Hardware Tag-Based KASAN supports slab, page_alloc, and non-executable vmalloc +memory. + +For slab, both software KASAN modes support SLUB and SLAB allocators, while +Hardware Tag-Based KASAN only supports SLUB. Usage ----- @@ -45,18 +82,59 @@ To enable KASAN, configure the kernel with:: CONFIG_KASAN=y -and choose between ``CONFIG_KASAN_GENERIC`` (to enable generic KASAN), -``CONFIG_KASAN_SW_TAGS`` (to enable software tag-based KASAN), and -``CONFIG_KASAN_HW_TAGS`` (to enable hardware tag-based KASAN). +and choose between ``CONFIG_KASAN_GENERIC`` (to enable Generic KASAN), +``CONFIG_KASAN_SW_TAGS`` (to enable Software Tag-Based KASAN), and +``CONFIG_KASAN_HW_TAGS`` (to enable Hardware Tag-Based KASAN). -For software modes, also choose between ``CONFIG_KASAN_OUTLINE`` and +For the software modes, also choose between ``CONFIG_KASAN_OUTLINE`` and ``CONFIG_KASAN_INLINE``. Outline and inline are compiler instrumentation types. -The former produces a smaller binary while the latter is 1.1-2 times faster. +The former produces a smaller binary while the latter is up to 2 times faster. To include alloc and free stack traces of affected slab objects into reports, enable ``CONFIG_STACKTRACE``. To include alloc and free stack traces of affected physical pages, enable ``CONFIG_PAGE_OWNER`` and boot with ``page_owner=on``. +Boot parameters +~~~~~~~~~~~~~~~ + +KASAN is affected by the generic ``panic_on_warn`` command line parameter. +When it is enabled, KASAN panics the kernel after printing a bug report. + +By default, KASAN prints a bug report only for the first invalid memory access. +With ``kasan_multi_shot``, KASAN prints a report on every invalid access. This +effectively disables ``panic_on_warn`` for KASAN reports. + +Alternatively, independent of ``panic_on_warn``, the ``kasan.fault=`` boot +parameter can be used to control panic and reporting behaviour: + +- ``kasan.fault=report`` or ``=panic`` controls whether to only print a KASAN + report or also panic the kernel (default: ``report``). The panic happens even + if ``kasan_multi_shot`` is enabled. + +Hardware Tag-Based KASAN mode (see the section about various modes below) is +intended for use in production as a security mitigation. Therefore, it supports +additional boot parameters that allow disabling KASAN or controlling features: + +- ``kasan=off`` or ``=on`` controls whether KASAN is enabled (default: ``on``). + +- ``kasan.mode=sync``, ``=async`` or ``=asymm`` controls whether KASAN + is configured in synchronous, asynchronous or asymmetric mode of + execution (default: ``sync``). + Synchronous mode: a bad access is detected immediately when a tag + check fault occurs. + Asynchronous mode: a bad access detection is delayed. When a tag check + fault occurs, the information is stored in hardware (in the TFSR_EL1 + register for arm64). The kernel periodically checks the hardware and + only reports tag faults during these checks. + Asymmetric mode: a bad access is detected synchronously on reads and + asynchronously on writes. + +- ``kasan.vmalloc=off`` or ``=on`` disables or enables tagging of vmalloc + allocations (default: ``on``). + +- ``kasan.stacktrace=off`` or ``=on`` disables or enables alloc and free stack + traces collection (default: ``on``). + Error reports ~~~~~~~~~~~~~ @@ -146,7 +224,7 @@ is either 8 or 16 aligned bytes depending on KASAN mode. Each number in the memory state section of the report shows the state of one of the memory granules that surround the accessed address. -For generic KASAN, the size of each memory granule is 8. The state of each +For Generic KASAN, the size of each memory granule is 8. The state of each granule is encoded in one shadow byte. Those 8 bytes can be accessible, partially accessible, freed, or be a part of a redzone. KASAN uses the following encoding for each shadow byte: 00 means that all 8 bytes of the corresponding @@ -171,47 +249,6 @@ traces point to places in code that interacted with the object but that are not directly present in the bad access stack trace. Currently, this includes call_rcu() and workqueue queuing. -Boot parameters -~~~~~~~~~~~~~~~ - -KASAN is affected by the generic ``panic_on_warn`` command line parameter. -When it is enabled, KASAN panics the kernel after printing a bug report. - -By default, KASAN prints a bug report only for the first invalid memory access. -With ``kasan_multi_shot``, KASAN prints a report on every invalid access. This -effectively disables ``panic_on_warn`` for KASAN reports. - -Alternatively, independent of ``panic_on_warn`` the ``kasan.fault=`` boot -parameter can be used to control panic and reporting behaviour: - -- ``kasan.fault=report`` or ``=panic`` controls whether to only print a KASAN - report or also panic the kernel (default: ``report``). The panic happens even - if ``kasan_multi_shot`` is enabled. - -Hardware tag-based KASAN mode (see the section about various modes below) is -intended for use in production as a security mitigation. Therefore, it supports -additional boot parameters that allow disabling KASAN or controlling features: - -- ``kasan=off`` or ``=on`` controls whether KASAN is enabled (default: ``on``). - -- ``kasan.mode=sync``, ``=async`` or ``=asymm`` controls whether KASAN - is configured in synchronous, asynchronous or asymmetric mode of - execution (default: ``sync``). - Synchronous mode: a bad access is detected immediately when a tag - check fault occurs. - Asynchronous mode: a bad access detection is delayed. When a tag check - fault occurs, the information is stored in hardware (in the TFSR_EL1 - register for arm64). The kernel periodically checks the hardware and - only reports tag faults during these checks. - Asymmetric mode: a bad access is detected synchronously on reads and - asynchronously on writes. - -- ``kasan.vmalloc=off`` or ``=on`` disables or enables tagging of vmalloc - allocations (default: ``on``). - -- ``kasan.stacktrace=off`` or ``=on`` disables or enables alloc and free stack - traces collection (default: ``on``). - Implementation details ---------------------- @@ -250,49 +287,46 @@ outline-instrumented kernel. Generic KASAN is the only mode that delays the reuse of freed objects via quarantine (see mm/kasan/quarantine.c for implementation). -Software tag-based KASAN +Software Tag-Based KASAN ~~~~~~~~~~~~~~~~~~~~~~~~ -Software tag-based KASAN uses a software memory tagging approach to checking +Software Tag-Based KASAN uses a software memory tagging approach to checking access validity. It is currently only implemented for the arm64 architecture. -Software tag-based KASAN uses the Top Byte Ignore (TBI) feature of arm64 CPUs +Software Tag-Based KASAN uses the Top Byte Ignore (TBI) feature of arm64 CPUs to store a pointer tag in the top byte of kernel pointers. It uses shadow memory to store memory tags associated with each 16-byte memory cell (therefore, it dedicates 1/16th of the kernel memory for shadow memory). -On each memory allocation, software tag-based KASAN generates a random tag, tags +On each memory allocation, Software Tag-Based KASAN generates a random tag, tags the allocated memory with this tag, and embeds the same tag into the returned pointer. -Software tag-based KASAN uses compile-time instrumentation to insert checks +Software Tag-Based KASAN uses compile-time instrumentation to insert checks before each memory access. These checks make sure that the tag of the memory that is being accessed is equal to the tag of the pointer that is used to access -this memory. In case of a tag mismatch, software tag-based KASAN prints a bug +this memory. In case of a tag mismatch, Software Tag-Based KASAN prints a bug report. -Software tag-based KASAN also has two instrumentation modes (outline, which +Software Tag-Based KASAN also has two instrumentation modes (outline, which emits callbacks to check memory accesses; and inline, which performs the shadow memory checks inline). With outline instrumentation mode, a bug report is printed from the function that performs the access check. With inline instrumentation, a ``brk`` instruction is emitted by the compiler, and a dedicated ``brk`` handler is used to print bug reports. -Software tag-based KASAN uses 0xFF as a match-all pointer tag (accesses through +Software Tag-Based KASAN uses 0xFF as a match-all pointer tag (accesses through pointers with the 0xFF pointer tag are not checked). The value 0xFE is currently reserved to tag freed memory regions. -Software tag-based KASAN currently only supports tagging of slab, page_alloc, -and vmalloc memory. - -Hardware tag-based KASAN +Hardware Tag-Based KASAN ~~~~~~~~~~~~~~~~~~~~~~~~ -Hardware tag-based KASAN is similar to the software mode in concept but uses +Hardware Tag-Based KASAN is similar to the software mode in concept but uses hardware memory tagging support instead of compiler instrumentation and shadow memory. -Hardware tag-based KASAN is currently only implemented for arm64 architecture +Hardware Tag-Based KASAN is currently only implemented for arm64 architecture and based on both arm64 Memory Tagging Extension (MTE) introduced in ARMv8.5 Instruction Set Architecture and Top Byte Ignore (TBI). @@ -302,21 +336,18 @@ access, hardware makes sure that the tag of the memory that is being accessed is equal to the tag of the pointer that is used to access this memory. In case of a tag mismatch, a fault is generated, and a report is printed. -Hardware tag-based KASAN uses 0xFF as a match-all pointer tag (accesses through +Hardware Tag-Based KASAN uses 0xFF as a match-all pointer tag (accesses through pointers with the 0xFF pointer tag are not checked). The value 0xFE is currently reserved to tag freed memory regions. -Hardware tag-based KASAN currently only supports tagging of slab, page_alloc, -and VM_ALLOC-based vmalloc memory. - -If the hardware does not support MTE (pre ARMv8.5), hardware tag-based KASAN +If the hardware does not support MTE (pre ARMv8.5), Hardware Tag-Based KASAN will not be enabled. In this case, all KASAN boot parameters are ignored. Note that enabling CONFIG_KASAN_HW_TAGS always results in in-kernel TBI being enabled. Even when ``kasan.mode=off`` is provided or when the hardware does not support MTE (but supports TBI). -Hardware tag-based KASAN only reports the first found bug. After that, MTE tag +Hardware Tag-Based KASAN only reports the first found bug. After that, MTE tag checking gets disabled. Shadow memory @@ -414,19 +445,18 @@ generic ``noinstr`` one. Note that disabling compiler instrumentation (either on a per-file or a per-function basis) makes KASAN ignore the accesses that happen directly in that code for software KASAN modes. It does not help when the accesses happen -indirectly (through calls to instrumented functions) or with the hardware -tag-based mode that does not use compiler instrumentation. +indirectly (through calls to instrumented functions) or with Hardware +Tag-Based KASAN, which does not use compiler instrumentation. For software KASAN modes, to disable KASAN reports in a part of the kernel code for the current task, annotate this part of the code with a ``kasan_disable_current()``/``kasan_enable_current()`` section. This also disables the reports for indirect accesses that happen through function calls. -For tag-based KASAN modes (include the hardware one), to disable access -checking, use ``kasan_reset_tag()`` or ``page_kasan_tag_reset()``. Note that -temporarily disabling access checking via ``page_kasan_tag_reset()`` requires -saving and restoring the per-page KASAN tag via -``page_kasan_tag``/``page_kasan_tag_set``. +For tag-based KASAN modes, to disable access checking, use +``kasan_reset_tag()`` or ``page_kasan_tag_reset()``. Note that temporarily +disabling access checking via ``page_kasan_tag_reset()`` requires saving and +restoring the per-page KASAN tag via ``page_kasan_tag``/``page_kasan_tag_set``. Tests ~~~~~ diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 515bc48ab58b..d1bf77ef3bc1 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -258,8 +258,9 @@ prototypes:: int (*launder_folio)(struct folio *); bool (*is_partially_uptodate)(struct folio *, size_t from, size_t count); int (*error_remove_page)(struct address_space *, struct page *); - int (*swap_activate)(struct file *); + int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span) int (*swap_deactivate)(struct file *); + int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); locking rules: All except dirty_folio and free_folio may block @@ -287,6 +288,7 @@ is_partially_uptodate: yes error_remove_page: yes swap_activate: no swap_deactivate: no +swap_rw: yes, unlocks ====================== ======================== ========= =============== ->write_begin(), ->write_end() and ->read_folio() may be called from @@ -386,15 +388,19 @@ cleaned, or an error value if not. Note that in order to prevent the folio getting mapped back in and redirtied, it needs to be kept locked across the entire operation. -->swap_activate will be called with a non-zero argument on -files backing (non block device backed) swapfiles. A return value -of zero indicates success, in which case this file can be used for -backing swapspace. The swapspace operations will be proxied to the -address space operations. +->swap_activate() will be called to prepare the given file for swap. It +should perform any validation and preparation necessary to ensure that +writes can be performed with minimal memory allocation. It should call +add_swap_extent(), or the helper iomap_swapfile_activate(), and return +the number of extents added. If IO should be submitted through +->swap_rw(), it should set SWP_FS_OPS, otherwise IO will be submitted +directly to the block device ``sis->bdev``. ->swap_deactivate() will be called in the sys_swapoff() path after ->swap_activate() returned success. +->swap_rw will be called for swap IO if SWP_FS_OPS was set by ->swap_activate(). + file_lock_operations ==================== diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 6a0dd99786f9..1bc91fb8c321 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -942,56 +942,73 @@ can be substantial. In many cases there are other means to find out additional memory using subsystem specific interfaces, for instance /proc/net/sockstat for TCP memory allocations. -The following is from a 16GB PIII, which has highmem enabled. -You may not have all of these fields. +Example output. You may not have all of these fields. :: > cat /proc/meminfo - MemTotal: 16344972 kB - MemFree: 13634064 kB - MemAvailable: 14836172 kB - Buffers: 3656 kB - Cached: 1195708 kB - SwapCached: 0 kB - Active: 891636 kB - Inactive: 1077224 kB - HighTotal: 15597528 kB - HighFree: 13629632 kB - LowTotal: 747444 kB - LowFree: 4432 kB - SwapTotal: 0 kB - SwapFree: 0 kB - Dirty: 968 kB - Writeback: 0 kB - AnonPages: 861800 kB - Mapped: 280372 kB - Shmem: 644 kB - KReclaimable: 168048 kB - Slab: 284364 kB - SReclaimable: 159856 kB - SUnreclaim: 124508 kB - PageTables: 24448 kB - NFS_Unstable: 0 kB - Bounce: 0 kB - WritebackTmp: 0 kB - CommitLimit: 7669796 kB - Committed_AS: 100056 kB - VmallocTotal: 112216 kB - VmallocUsed: 428 kB - VmallocChunk: 111088 kB - Percpu: 62080 kB - HardwareCorrupted: 0 kB - AnonHugePages: 49152 kB - ShmemHugePages: 0 kB - ShmemPmdMapped: 0 kB + MemTotal: 32858820 kB + MemFree: 21001236 kB + MemAvailable: 27214312 kB + Buffers: 581092 kB + Cached: 5587612 kB + SwapCached: 0 kB + Active: 3237152 kB + Inactive: 7586256 kB + Active(anon): 94064 kB + Inactive(anon): 4570616 kB + Active(file): 3143088 kB + Inactive(file): 3015640 kB + Unevictable: 0 kB + Mlocked: 0 kB + SwapTotal: 0 kB + SwapFree: 0 kB + Zswap: 1904 kB + Zswapped: 7792 kB + Dirty: 12 kB + Writeback: 0 kB + AnonPages: 4654780 kB + Mapped: 266244 kB + Shmem: 9976 kB + KReclaimable: 517708 kB + Slab: 660044 kB + SReclaimable: 517708 kB + SUnreclaim: 142336 kB + KernelStack: 11168 kB + PageTables: 20540 kB + NFS_Unstable: 0 kB + Bounce: 0 kB + WritebackTmp: 0 kB + CommitLimit: 16429408 kB + Committed_AS: 7715148 kB + VmallocTotal: 34359738367 kB + VmallocUsed: 40444 kB + VmallocChunk: 0 kB + Percpu: 29312 kB + HardwareCorrupted: 0 kB + AnonHugePages: 4149248 kB + ShmemHugePages: 0 kB + ShmemPmdMapped: 0 kB + FileHugePages: 0 kB + FilePmdMapped: 0 kB + CmaTotal: 0 kB + CmaFree: 0 kB + HugePages_Total: 0 + HugePages_Free: 0 + HugePages_Rsvd: 0 + HugePages_Surp: 0 + Hugepagesize: 2048 kB + Hugetlb: 0 kB + DirectMap4k: 401152 kB + DirectMap2M: 10008576 kB + DirectMap1G: 24117248 kB MemTotal Total usable RAM (i.e. physical RAM minus a few reserved bits and the kernel binary code) MemFree - The sum of LowFree+HighFree + Total free RAM. On highmem systems, the sum of LowFree+HighFree MemAvailable An estimate of how much memory is available for starting new applications, without swapping. Calculated from MemFree, @@ -1005,8 +1022,9 @@ Buffers Relatively temporary storage for raw disk blocks shouldn't get tremendously large (20MB or so) Cached - in-memory cache for files read from the disk (the - pagecache). Doesn't include SwapCached + In-memory cache for files read from the disk (the + pagecache) as well as tmpfs & shmem. + Doesn't include SwapCached. SwapCached Memory that once was swapped out, is swapped back in but still also is in the swapfile (if memory is needed it @@ -1018,6 +1036,11 @@ Active Inactive Memory which has been less recently used. It is more eligible to be reclaimed for other purposes +Unevictable + Memory allocated for userspace which cannot be reclaimed, such + as mlocked pages, ramfs backing pages, secret memfd pages etc. +Mlocked + Memory locked with mlock(). HighTotal, HighFree Highmem is all memory above ~860MB of physical memory. Highmem areas are for use by userspace programs, or @@ -1034,26 +1057,20 @@ SwapTotal SwapFree Memory which has been evicted from RAM, and is temporarily on the disk +Zswap + Memory consumed by the zswap backend (compressed size) +Zswapped + Amount of anonymous memory stored in zswap (original size) Dirty Memory which is waiting to get written back to the disk Writeback Memory which is actively being written back to the disk AnonPages Non-file backed pages mapped into userspace page tables -HardwareCorrupted - The amount of RAM/memory in KB, the kernel identifies as - corrupted. -AnonHugePages - Non-file backed huge pages mapped into userspace page tables Mapped files which have been mmaped, such as libraries Shmem Total memory used by shared memory (shmem) and tmpfs -ShmemHugePages - Memory used by shared memory (shmem) and tmpfs allocated - with huge pages -ShmemPmdMapped - Shared memory mapped into userspace with huge pages KReclaimable Kernel allocations that the kernel will attempt to reclaim under memory pressure. Includes SReclaimable (below), and other @@ -1064,9 +1081,10 @@ SReclaimable Part of Slab, that might be reclaimed, such as caches SUnreclaim Part of Slab, that cannot be reclaimed on memory pressure +KernelStack + Memory consumed by the kernel stacks of all tasks PageTables - amount of memory dedicated to the lowest level of page - tables. + Memory consumed by userspace page tables NFS_Unstable Always zero. Previous counted pages which had been written to the server, but has not been committed to stable storage. @@ -1098,7 +1116,7 @@ Committed_AS has been allocated by processes, even if it has not been "used" by them as of yet. A process which malloc()'s 1G of memory, but only touches 300M of it will show up as - using 1G. This 1G is memory which has been "committed" to + using 1G. This 1G is memory which has been "committed" to by the VM and can be used at any time by the allocating application. With strict overcommit enabled on the system (mode 2 in 'vm.overcommit_memory'), allocations which would @@ -1107,7 +1125,7 @@ Committed_AS not fail due to lack of memory once that memory has been successfully allocated. VmallocTotal - total size of vmalloc memory area + total size of vmalloc virtual address space VmallocUsed amount of vmalloc area which is used VmallocChunk @@ -1115,6 +1133,30 @@ VmallocChunk Percpu Memory allocated to the percpu allocator used to back percpu allocations. This stat excludes the cost of metadata. +HardwareCorrupted + The amount of RAM/memory in KB, the kernel identifies as + corrupted. +AnonHugePages + Non-file backed huge pages mapped into userspace page tables +ShmemHugePages + Memory used by shared memory (shmem) and tmpfs allocated + with huge pages +ShmemPmdMapped + Shared memory mapped into userspace with huge pages +FileHugePages + Memory used for filesystem data (page cache) allocated + with huge pages +FilePmdMapped + Page cache mapped into userspace with huge pages +CmaTotal + Memory reserved for the Contiguous Memory Allocator (CMA) +CmaFree + Free remaining memory in the CMA reserves +HugePages_Total, HugePages_Free, HugePages_Rsvd, HugePages_Surp, Hugepagesize, Hugetlb + See Documentation/admin-guide/mm/hugetlbpage.rst. +DirectMap4k, DirectMap2M, DirectMap1G + Breakdown of page table sizes used in the kernel's + identity mapping of RAM vmallocinfo ~~~~~~~~~~~ diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 12a011d2cbc6..08069ecd49a6 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -749,8 +749,9 @@ cache in your filesystem. The following members are defined: size_t count); void (*is_dirty_writeback)(struct folio *, bool *, bool *); int (*error_remove_page) (struct mapping *mapping, struct page *page); - int (*swap_activate)(struct file *); + int (*swap_activate)(struct swap_info_struct *sis, struct file *f, sector_t *span) int (*swap_deactivate)(struct file *); + int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; ``writepage`` @@ -948,15 +949,21 @@ cache in your filesystem. The following members are defined: unless you have them locked or reference counts increased. ``swap_activate`` - Called when swapon is used on a file to allocate space if - necessary and pin the block lookup information in memory. A - return value of zero indicates success, in which case this file - can be used to back swapspace. + + Called to prepare the given file for swap. It should perform + any validation and preparation necessary to ensure that writes + can be performed with minimal memory allocation. It should call + add_swap_extent(), or the helper iomap_swapfile_activate(), and + return the number of extents added. If IO should be submitted + through ->swap_rw(), it should set SWP_FS_OPS, otherwise IO will + be submitted directly to the block device ``sis->bdev``. ``swap_deactivate`` Called during swapoff on files where swap_activate was successful. +``swap_rw`` + Called to read or write swap pages when SWP_FS_OPS is set. The File Object =============== diff --git a/Documentation/vm/highmem.rst b/Documentation/vm/highmem.rst index 0f69a9fec34d..c9887f241c6c 100644 --- a/Documentation/vm/highmem.rst +++ b/Documentation/vm/highmem.rst @@ -50,61 +50,74 @@ space when they use mm context tags. Temporary Virtual Mappings ========================== -The kernel contains several ways of creating temporary mappings: +The kernel contains several ways of creating temporary mappings. The following +list shows them in order of preference of use. -* vmap(). This can be used to make a long duration mapping of multiple - physical pages into a contiguous virtual space. It needs global - synchronization to unmap. - -* kmap(). This permits a short duration mapping of a single page. It needs - global synchronization, but is amortized somewhat. It is also prone to - deadlocks when using in a nested fashion, and so it is not recommended for - new code. - -* kmap_atomic(). This permits a very short duration mapping of a single - page. Since the mapping is restricted to the CPU that issued it, it - performs well, but the issuing task is therefore required to stay on that - CPU until it has finished, lest some other task displace its mappings. +* kmap_local_page(). This function is used to require short term mappings. + It can be invoked from any context (including interrupts) but the mappings + can only be used in the context which acquired them. - kmap_atomic() may also be used by interrupt contexts, since it is does not - sleep and the caller may not sleep until after kunmap_atomic() is called. + This function should be preferred, where feasible, over all the others. - It may be assumed that k[un]map_atomic() won't fail. + These mappings are thread-local and CPU-local, meaning that the mapping + can only be accessed from within this thread and the thread is bound the + CPU while the mapping is active. Even if the thread is preempted (since + preemption is never disabled by the function) the CPU can not be + unplugged from the system via CPU-hotplug until the mapping is disposed. + It's valid to take pagefaults in a local kmap region, unless the context + in which the local mapping is acquired does not allow it for other reasons. -Using kmap_atomic -================= + kmap_local_page() always returns a valid virtual address and it is assumed + that kunmap_local() will never fail. -When and where to use kmap_atomic() is straightforward. It is used when code -wants to access the contents of a page that might be allocated from high memory -(see __GFP_HIGHMEM), for example a page in the pagecache. The API has two -functions, and they can be used in a manner similar to the following:: + Nesting kmap_local_page() and kmap_atomic() mappings is allowed to a certain + extent (up to KMAP_TYPE_NR) but their invocations have to be strictly ordered + because the map implementation is stack based. See kmap_local_page() kdocs + (included in the "Functions" section) for details on how to manage nested + mappings. - /* Find the page of interest. */ - struct page *page = find_get_page(mapping, offset); +* kmap_atomic(). This permits a very short duration mapping of a single + page. Since the mapping is restricted to the CPU that issued it, it + performs well, but the issuing task is therefore required to stay on that + CPU until it has finished, lest some other task displace its mappings. - /* Gain access to the contents of that page. */ - void *vaddr = kmap_atomic(page); + kmap_atomic() may also be used by interrupt contexts, since it does not + sleep and the callers too may not sleep until after kunmap_atomic() is + called. - /* Do something to the contents of that page. */ - memset(vaddr, 0, PAGE_SIZE); + Each call of kmap_atomic() in the kernel creates a non-preemptible section + and disable pagefaults. This could be a source of unwanted latency. Therefore + users should prefer kmap_local_page() instead of kmap_atomic(). - /* Unmap that page. */ - kunmap_atomic(vaddr); + It is assumed that k[un]map_atomic() won't fail. -Note that the kunmap_atomic() call takes the result of the kmap_atomic() call -not the argument. +* kmap(). This should be used to make short duration mapping of a single + page with no restrictions on preemption or migration. It comes with an + overhead as mapping space is restricted and protected by a global lock + for synchronization. When mapping is no longer needed, the address that + the page was mapped to must be released with kunmap(). -If you need to map two pages because you want to copy from one page to -another you need to keep the kmap_atomic calls strictly nested, like:: + Mapping changes must be propagated across all the CPUs. kmap() also + requires global TLB invalidation when the kmap's pool wraps and it might + block when the mapping space is fully utilized until a slot becomes + available. Therefore, kmap() is only callable from preemptible context. - vaddr1 = kmap_atomic(page1); - vaddr2 = kmap_atomic(page2); + All the above work is necessary if a mapping must last for a relatively + long time but the bulk of high-memory mappings in the kernel are + short-lived and only used in one place. This means that the cost of + kmap() is mostly wasted in such cases. kmap() was not intended for long + term mappings but it has morphed in that direction and its use is + strongly discouraged in newer code and the set of the preceding functions + should be preferred. - memcpy(vaddr1, vaddr2, PAGE_SIZE); + On 64-bit systems, calls to kmap_local_page(), kmap_atomic() and kmap() have + no real work to do because a 64-bit address space is more than sufficient to + address all the physical memory whose pages are permanently mapped. - kunmap_atomic(vaddr2); - kunmap_atomic(vaddr1); +* vmap(). This can be used to make a long duration mapping of multiple + physical pages into a contiguous virtual space. It needs global + synchronization to unmap. Cost of Temporary Mappings @@ -145,3 +158,10 @@ The general recommendation is that you don't use more than 8GiB on a 32-bit machine - although more might work for you and your workload, you're pretty much on your own - don't expect kernel developers to really care much if things come apart. + + +Functions +========= + +.. kernel-doc:: include/linux/highmem.h +.. kernel-doc:: include/linux/highmem-internal.h diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst index e72736d53604..575ccd40e30c 100644 --- a/Documentation/vm/index.rst +++ b/Documentation/vm/index.rst @@ -63,5 +63,6 @@ above structured documentation, or deleted if it has served its purpose. transhuge unevictable-lru vmalloced-kernel-stacks + vmemmap_dedup z3fold zsmalloc diff --git a/Documentation/vm/page_owner.rst b/Documentation/vm/page_owner.rst index 7e0c3f574e78..f5c954afe97c 100644 --- a/Documentation/vm/page_owner.rst +++ b/Documentation/vm/page_owner.rst @@ -121,6 +121,14 @@ Usage -r Sort by memory release time. -s Sort by stack trace. -t Sort by times (default). + --sort <order> Specify sorting order. Sorting syntax is [+|-]key[,[+|-]key[,...]]. + Choose a key from the **STANDARD FORMAT SPECIFIERS** section. The "+" is + optional since default direction is increasing numerical or lexicographic + order. Mixed use of abbreviated and complete-form of keys is allowed. + + Examples: + ./page_owner_sort <input> <output> --sort=n,+pid,-tgid + ./page_owner_sort <input> <output> --sort=at additional function:: @@ -129,7 +137,6 @@ Usage Specify culling rules.Culling syntax is key[,key[,...]].Choose a multi-letter key from the **STANDARD FORMAT SPECIFIERS** section. - <rules> is a single argument in the form of a comma-separated list, which offers a way to specify individual culling rules. The recognized keywords are described in the **STANDARD FORMAT SPECIFIERS** section below. @@ -137,7 +144,6 @@ Usage the STANDARD SORT KEYS section below. Mixed use of abbreviated and complete-form of keys is allowed. - Examples: ./page_owner_sort <input> <output> --cull=stacktrace ./page_owner_sort <input> <output> --cull=st,pid,name @@ -147,17 +153,44 @@ Usage -f Filter out the information of blocks whose memory has been released. Select: - --pid <PID> Select by pid. - --tgid <TGID> Select by tgid. - --name <command> Select by task command name. + --pid <pidlist> Select by pid. This selects the blocks whose process ID + numbers appear in <pidlist>. + --tgid <tgidlist> Select by tgid. This selects the blocks whose thread + group ID numbers appear in <tgidlist>. + --name <cmdlist> Select by task command name. This selects the blocks whose + task command name appear in <cmdlist>. + + <pidlist>, <tgidlist>, <cmdlist> are single arguments in the form of a comma-separated list, + which offers a way to specify individual selecting rules. + + + Examples: + ./page_owner_sort <input> <output> --pid=1 + ./page_owner_sort <input> <output> --tgid=1,2,3 + ./page_owner_sort <input> <output> --name name1,name2 STANDARD FORMAT SPECIFIERS ========================== :: + For --sort option: + + KEY LONG DESCRIPTION + p pid process ID + tg tgid thread group ID + n name task command name + st stacktrace stack trace of the page allocation + T txt full text of block + ft free_ts timestamp of the page when it was released + at alloc_ts timestamp of the page when it was allocated + ator allocator memory allocator for pages + + For --curl option: + KEY LONG DESCRIPTION p pid process ID tg tgid thread group ID n name task command name f free whether the page has been released or not - st stacktrace stace trace of the page allocation + st stacktrace stack trace of the page allocation + ator allocator memory allocator for pages diff --git a/Documentation/vm/vmemmap_dedup.rst b/Documentation/vm/vmemmap_dedup.rst new file mode 100644 index 000000000000..c9c495f62d12 --- /dev/null +++ b/Documentation/vm/vmemmap_dedup.rst @@ -0,0 +1,223 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================= +A vmemmap diet for HugeTLB and Device DAX +========================================= + +HugeTLB +======= + +The struct page structures (page structs) are used to describe a physical +page frame. By default, there is a one-to-one mapping from a page frame to +it's corresponding page struct. + +HugeTLB pages consist of multiple base page size pages and is supported by many +architectures. See Documentation/admin-guide/mm/hugetlbpage.rst for more +details. On the x86-64 architecture, HugeTLB pages of size 2MB and 1GB are +currently supported. Since the base page size on x86 is 4KB, a 2MB HugeTLB page +consists of 512 base pages and a 1GB HugeTLB page consists of 4096 base pages. +For each base page, there is a corresponding page struct. + +Within the HugeTLB subsystem, only the first 4 page structs are used to +contain unique information about a HugeTLB page. __NR_USED_SUBPAGE provides +this upper limit. The only 'useful' information in the remaining page structs +is the compound_head field, and this field is the same for all tail pages. + +By removing redundant page structs for HugeTLB pages, memory can be returned +to the buddy allocator for other uses. + +Different architectures support different HugeTLB pages. For example, the +following table is the HugeTLB page size supported by x86 and arm64 +architectures. Because arm64 supports 4k, 16k, and 64k base pages and +supports contiguous entries, so it supports many kinds of sizes of HugeTLB +page. + ++--------------+-----------+-----------------------------------------------+ +| Architecture | Page Size | HugeTLB Page Size | ++--------------+-----------+-----------+-----------+-----------+-----------+ +| x86-64 | 4KB | 2MB | 1GB | | | ++--------------+-----------+-----------+-----------+-----------+-----------+ +| | 4KB | 64KB | 2MB | 32MB | 1GB | +| +-----------+-----------+-----------+-----------+-----------+ +| arm64 | 16KB | 2MB | 32MB | 1GB | | +| +-----------+-----------+-----------+-----------+-----------+ +| | 64KB | 2MB | 512MB | 16GB | | ++--------------+-----------+-----------+-----------+-----------+-----------+ + +When the system boot up, every HugeTLB page has more than one struct page +structs which size is (unit: pages):: + + struct_size = HugeTLB_Size / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE + +Where HugeTLB_Size is the size of the HugeTLB page. We know that the size +of the HugeTLB page is always n times PAGE_SIZE. So we can get the following +relationship:: + + HugeTLB_Size = n * PAGE_SIZE + +Then:: + + struct_size = n * PAGE_SIZE / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE + = n * sizeof(struct page) / PAGE_SIZE + +We can use huge mapping at the pud/pmd level for the HugeTLB page. + +For the HugeTLB page of the pmd level mapping, then:: + + struct_size = n * sizeof(struct page) / PAGE_SIZE + = PAGE_SIZE / sizeof(pte_t) * sizeof(struct page) / PAGE_SIZE + = sizeof(struct page) / sizeof(pte_t) + = 64 / 8 + = 8 (pages) + +Where n is how many pte entries which one page can contains. So the value of +n is (PAGE_SIZE / sizeof(pte_t)). + +This optimization only supports 64-bit system, so the value of sizeof(pte_t) +is 8. And this optimization also applicable only when the size of struct page +is a power of two. In most cases, the size of struct page is 64 bytes (e.g. +x86-64 and arm64). So if we use pmd level mapping for a HugeTLB page, the +size of struct page structs of it is 8 page frames which size depends on the +size of the base page. + +For the HugeTLB page of the pud level mapping, then:: + + struct_size = PAGE_SIZE / sizeof(pmd_t) * struct_size(pmd) + = PAGE_SIZE / 8 * 8 (pages) + = PAGE_SIZE (pages) + +Where the struct_size(pmd) is the size of the struct page structs of a +HugeTLB page of the pmd level mapping. + +E.g.: A 2MB HugeTLB page on x86_64 consists in 8 page frames while 1GB +HugeTLB page consists in 4096. + +Next, we take the pmd level mapping of the HugeTLB page as an example to +show the internal implementation of this optimization. There are 8 pages +struct page structs associated with a HugeTLB page which is pmd mapped. + +Here is how things look before optimization:: + + HugeTLB struct pages(8 pages) page frame(8 pages) + +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ + | | | 0 | -------------> | 0 | + | | +-----------+ +-----------+ + | | | 1 | -------------> | 1 | + | | +-----------+ +-----------+ + | | | 2 | -------------> | 2 | + | | +-----------+ +-----------+ + | | | 3 | -------------> | 3 | + | | +-----------+ +-----------+ + | | | 4 | -------------> | 4 | + | PMD | +-----------+ +-----------+ + | level | | 5 | -------------> | 5 | + | mapping | +-----------+ +-----------+ + | | | 6 | -------------> | 6 | + | | +-----------+ +-----------+ + | | | 7 | -------------> | 7 | + | | +-----------+ +-----------+ + | | + | | + | | + +-----------+ + +The value of page->compound_head is the same for all tail pages. The first +page of page structs (page 0) associated with the HugeTLB page contains the 4 +page structs necessary to describe the HugeTLB. The only use of the remaining +pages of page structs (page 1 to page 7) is to point to page->compound_head. +Therefore, we can remap pages 1 to 7 to page 0. Only 1 page of page structs +will be used for each HugeTLB page. This will allow us to free the remaining +7 pages to the buddy allocator. + +Here is how things look after remapping:: + + HugeTLB struct pages(8 pages) page frame(8 pages) + +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ + | | | 0 | -------------> | 0 | + | | +-----------+ +-----------+ + | | | 1 | ---------------^ ^ ^ ^ ^ ^ ^ + | | +-----------+ | | | | | | + | | | 2 | -----------------+ | | | | | + | | +-----------+ | | | | | + | | | 3 | -------------------+ | | | | + | | +-----------+ | | | | + | | | 4 | ---------------------+ | | | + | PMD | +-----------+ | | | + | level | | 5 | -----------------------+ | | + | mapping | +-----------+ | | + | | | 6 | -------------------------+ | + | | +-----------+ | + | | | 7 | ---------------------------+ + | | +-----------+ + | | + | | + | | + +-----------+ + +When a HugeTLB is freed to the buddy system, we should allocate 7 pages for +vmemmap pages and restore the previous mapping relationship. + +For the HugeTLB page of the pud level mapping. It is similar to the former. +We also can use this approach to free (PAGE_SIZE - 1) vmemmap pages. + +Apart from the HugeTLB page of the pmd/pud level mapping, some architectures +(e.g. aarch64) provides a contiguous bit in the translation table entries +that hints to the MMU to indicate that it is one of a contiguous set of +entries that can be cached in a single TLB entry. + +The contiguous bit is used to increase the mapping size at the pmd and pte +(last) level. So this type of HugeTLB page can be optimized only when its +size of the struct page structs is greater than 1 page. + +Notice: The head vmemmap page is not freed to the buddy allocator and all +tail vmemmap pages are mapped to the head vmemmap page frame. So we can see +more than one struct page struct with PG_head (e.g. 8 per 2 MB HugeTLB page) +associated with each HugeTLB page. The compound_head() can handle this +correctly (more details refer to the comment above compound_head()). + +Device DAX +========== + +The device-dax interface uses the same tail deduplication technique explained +in the previous chapter, except when used with the vmemmap in +the device (altmap). + +The following page sizes are supported in DAX: PAGE_SIZE (4K on x86_64), +PMD_SIZE (2M on x86_64) and PUD_SIZE (1G on x86_64). + +The differences with HugeTLB are relatively minor. + +It only use 3 page structs for storing all information as opposed +to 4 on HugeTLB pages. + +There's no remapping of vmemmap given that device-dax memory is not part of +System RAM ranges initialized at boot. Thus the tail page deduplication +happens at a later stage when we populate the sections. HugeTLB reuses the +the head vmemmap page representing, whereas device-dax reuses the tail +vmemmap page. This results in only half of the savings compared to HugeTLB. + +Deduplicated tail pages are not mapped read-only. + +Here's how things look like on device-dax after the sections are populated:: + + +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ + | | | 0 | -------------> | 0 | + | | +-----------+ +-----------+ + | | | 1 | -------------> | 1 | + | | +-----------+ +-----------+ + | | | 2 | ----------------^ ^ ^ ^ ^ ^ + | | +-----------+ | | | | | + | | | 3 | ------------------+ | | | | + | | +-----------+ | | | | + | | | 4 | --------------------+ | | | + | PMD | +-----------+ | | | + | level | | 5 | ----------------------+ | | + | mapping | +-----------+ | | + | | | 6 | ------------------------+ | + | | +-----------+ | + | | | 7 | --------------------------+ + | | +-----------+ + | | + | | + | | + +-----------+ diff --git a/MAINTAINERS b/MAINTAINERS index 4395c11ff169..f806dfd786b2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5027,6 +5027,7 @@ F: Documentation/admin-guide/cgroup-v1/ F: Documentation/admin-guide/cgroup-v2.rst F: include/linux/cgroup* F: kernel/cgroup/ +F: tools/testing/selftests/cgroup/ CONTROL GROUP - BLOCK IO CONTROLLER (BLKIO) M: Tejun Heo <tj@kernel.org> @@ -5060,6 +5061,8 @@ L: linux-mm@kvack.org S: Maintained F: mm/memcontrol.c F: mm/swap_cgroup.c +F: tools/testing/selftests/cgroup/test_kmem.c +F: tools/testing/selftests/cgroup/test_memcontrol.c CORETEMP HARDWARE MONITORING DRIVER M: Fenghua Yu <fenghua.yu@intel.com> @@ -9064,16 +9067,20 @@ S: Orphan F: Documentation/networking/device_drivers/ethernet/huawei/hinic.rst F: drivers/net/ethernet/huawei/hinic/ -HUGETLB FILESYSTEM +HUGETLB SUBSYSTEM M: Mike Kravetz <mike.kravetz@oracle.com> +M: Muchun Song <songmuchun@bytedance.com> L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages F: Documentation/admin-guide/mm/hugetlbpage.rst F: Documentation/vm/hugetlbfs_reserv.rst +F: Documentation/vm/vmemmap_dedup.rst F: fs/hugetlbfs/ F: include/linux/hugetlb.h F: mm/hugetlb.c +F: mm/hugetlb_vmemmap.c +F: mm/hugetlb_vmemmap.h HVA ST MEDIA DRIVER M: Jean-Christophe Trotin <jean-christophe.trotin@foss.st.com> diff --git a/arch/alpha/include/asm/page.h b/arch/alpha/include/asm/page.h index 18f48a6f2ff6..8f3f5eecba28 100644 --- a/arch/alpha/include/asm/page.h +++ b/arch/alpha/include/asm/page.h @@ -18,7 +18,7 @@ extern void clear_page(void *page); #define clear_user_page(page, vaddr, pg) clear_page(page) #define alloc_zeroed_user_highpage_movable(vma, vaddr) \ - alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vmaddr) + alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, vma, vaddr) #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE_MOVABLE extern void copy_page(void * _to, void * _from); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index d550f5acfaf3..a4968845e67f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -45,6 +45,7 @@ config ARM64 select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_ELF_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -91,11 +92,13 @@ config ARM64 select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_PAGE_TABLE_CHECK select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) + select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_NO_INSTR select ARCH_HAS_UBSAN_SANITIZE_ALL diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index a074459f8f2f..7c2181c72116 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -6,6 +6,7 @@ #define __ASM_CACHE_H #include <asm/cputype.h> +#include <asm/mte-def.h> #define CTR_L1IP_SHIFT 14 #define CTR_L1IP_MASK 3 @@ -49,16 +50,22 @@ */ #define ARCH_DMA_MINALIGN (128) +#ifndef __ASSEMBLY__ + +#include <linux/bitops.h> +#include <linux/kasan-enabled.h> + #ifdef CONFIG_KASAN_SW_TAGS #define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT) #elif defined(CONFIG_KASAN_HW_TAGS) -#define ARCH_SLAB_MINALIGN MTE_GRANULE_SIZE +static inline unsigned int arch_slab_minalign(void) +{ + return kasan_hw_tags_enabled() ? MTE_GRANULE_SIZE : + __alignof__(unsigned long long); +} +#define arch_slab_minalign() arch_slab_minalign() #endif -#ifndef __ASSEMBLY__ - -#include <linux/bitops.h> - #define ICACHEF_ALIASING 0 #define ICACHEF_VPIPT 1 extern unsigned long __icache_flags; diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index d656822b13f1..1fd2846dbefe 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -39,8 +39,8 @@ extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, extern void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -extern void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +extern pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_HUGE_PTE_CLEAR extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz); diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h index e3e28f7daf62..5966ee4a6154 100644 --- a/arch/arm64/include/asm/mman.h +++ b/arch/arm64/include/asm/mman.h @@ -35,30 +35,6 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) } #define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) -static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) -{ - pteval_t prot = 0; - - if (vm_flags & VM_ARM64_BTI) - prot |= PTE_GP; - - /* - * There are two conditions required for returning a Normal Tagged - * memory type: (1) the user requested it via PROT_MTE passed to - * mmap() or mprotect() and (2) the corresponding vma supports MTE. We - * register (1) as VM_MTE in the vma->vm_flags and (2) as - * VM_MTE_ALLOWED. Note that the latter can only be set during the - * mmap() call since mprotect() does not accept MAP_* flags. - * Checking for VM_MTE only is sufficient since arch_validate_flags() - * does not permit (VM_MTE & !VM_MTE_ALLOWED). - */ - if (vm_flags & VM_MTE) - prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED); - - return __pgprot(prot); -} -#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) - static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) { diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h index a857bcacf0fe..9f79425fc65a 100644 --- a/arch/arm64/include/asm/mte-kasan.h +++ b/arch/arm64/include/asm/mte-kasan.h @@ -6,6 +6,7 @@ #define __ASM_MTE_KASAN_H #include <asm/compiler.h> +#include <asm/cputype.h> #include <asm/mte-def.h> #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 8f1661603b78..b9ba19dbdb69 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -10,6 +10,7 @@ #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/stack_pointer.h> +#include <asm/sysreg.h> static inline void set_my_cpu_offset(unsigned long off) { diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index b1e1b74d993c..62e0ebeed720 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -14,6 +14,7 @@ * Software defined PTE bits definition. */ #define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ +#define PTE_SWP_EXCLUSIVE (_AT(pteval_t, 1) << 2) /* only for swp ptes */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) #define PTE_DEVMAP (_AT(pteval_t, 1) << 57) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 45c358538f13..0b6632f18364 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -33,6 +33,7 @@ #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/sched.h> +#include <linux/page_table_check.h> #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE @@ -96,6 +97,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) +#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) #define pte_devmap(pte) (!!(pte_val(pte) & PTE_DEVMAP)) @@ -312,8 +314,8 @@ static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep, __func__, pte_val(old_pte), pte_val(pte)); } -static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) +static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) { if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte); @@ -343,6 +345,13 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, pte); } +static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + page_table_check_pte_set(mm, addr, ptep, pte); + return __set_pte_at(mm, addr, ptep, pte); +} + /* * Huge pte definitions. */ @@ -402,6 +411,22 @@ static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); } +#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return pte_val(pte) & PTE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); +} + #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/linux/pgtable.h @@ -438,6 +463,8 @@ static inline int pmd_trans_huge(pmd_t pmd) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_valid(pmd) pte_valid(pmd_pte(pmd)) +#define pmd_user(pmd) pte_user(pmd_pte(pmd)) +#define pmd_user_exec(pmd) pte_user_exec(pmd_pte(pmd)) #define pmd_cont(pmd) pte_cont(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) @@ -485,8 +512,19 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) -#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)) -#define set_pud_at(mm, addr, pudp, pud) set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)) +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + page_table_check_pmd_set(mm, addr, pmdp, pmd); + return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); +} + +static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + page_table_check_pud_set(mm, addr, pudp, pud); + return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); +} #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) #define __phys_to_p4d_val(phys) __phys_to_pte_val(phys) @@ -627,6 +665,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_present(pud) pte_present(pud_pte(pud)) #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) +#define pud_user(pud) pte_user(pud_pte(pud)) + static inline void set_pud(pud_t *pudp, pud_t pud) { @@ -799,6 +839,23 @@ static inline int pgd_devmap(pgd_t pgd) } #endif +#ifdef CONFIG_PAGE_TABLE_CHECK +static inline bool pte_user_accessible_page(pte_t pte) +{ + return pte_present(pte) && (pte_user(pte) || pte_user_exec(pte)); +} + +static inline bool pmd_user_accessible_page(pmd_t pmd) +{ + return pmd_present(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); +} + +static inline bool pud_user_accessible_page(pud_t pud) +{ + return pud_present(pud) && pud_user(pud); +} +#endif + /* * Atomic pte/pmd modifications. */ @@ -860,7 +917,11 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { - return __pte(xchg_relaxed(&pte_val(*ptep), 0)); + pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); + + page_table_check_pte_clear(mm, address, pte); + + return pte; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -868,7 +929,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { - return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp)); + pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); + + page_table_check_pmd_clear(mm, address, pmd); + + return pmd; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -902,6 +967,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { + page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif @@ -909,12 +975,13 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, /* * Encode and decode a swap entry: * bits 0-1: present (must be zero) - * bits 2-7: swap type + * bits 2: remember PG_anon_exclusive + * bits 3-7: swap type * bits 8-57: swap offset * bit 58: PTE_PROT_NONE (must be zero) */ -#define __SWP_TYPE_SHIFT 2 -#define __SWP_TYPE_BITS 6 +#define __SWP_TYPE_SHIFT 3 +#define __SWP_TYPE_BITS 5 #define __SWP_OFFSET_BITS 50 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) @@ -964,10 +1031,10 @@ 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 page *page) +static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { - if (system_supports_mte() && mte_restore_tags(entry, page)) - set_bit(PG_mte_tagged, &page->flags); + if (system_supports_mte() && mte_restore_tags(entry, &folio->page)) + set_bit(PG_mte_tagged, &folio->flags); } #endif /* CONFIG_ARM64_MTE */ diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index a06c6ac770d4..fc4f710e9820 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -75,6 +75,20 @@ EXPORT_SYMBOL_GPL(__sync_icache_dcache); */ void flush_dcache_page(struct page *page) { + /* + * Only the head page's flags of HugeTLB can be cleared since the tail + * vmemmap pages associated with each HugeTLB page are mapped with + * read-only when CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is enabled (more + * details can refer to vmemmap_remap_pte()). Although + * __sync_icache_dcache() only set PG_dcache_clean flag on the head + * page struct, there is more than one page struct with PG_dcache_clean + * associated with the HugeTLB page since the head vmemmap page frame + * is reused (more details can refer to the comments above + * page_fixed_fake_head()). + */ + if (hugetlb_optimize_vmemmap_enabled() && PageHuge(page)) + page = compound_head(page); + if (test_bit(PG_dcache_clean, &page->flags)) clear_bit(PG_dcache_clean, &page->flags); } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 64bb078e2e7b..0f0c17dfeb9c 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -502,19 +502,17 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); } -void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { size_t pgsize; int ncontig; - if (!pte_cont(READ_ONCE(*ptep))) { - ptep_clear_flush(vma, addr, ptep); - return; - } + if (!pte_cont(READ_ONCE(*ptep))) + return ptep_clear_flush(vma, addr, ptep); ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize); - clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig); + return get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig); } static int __init hugetlbpage_init(void) diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 77ada00280d9..78e9490f748d 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -55,3 +55,28 @@ static int __init adjust_protection_map(void) return 0; } arch_initcall(adjust_protection_map); + +pgprot_t vm_get_page_prot(unsigned long vm_flags) +{ + pteval_t prot = pgprot_val(protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); + + if (vm_flags & VM_ARM64_BTI) + prot |= PTE_GP; + + /* + * There are two conditions required for returning a Normal Tagged + * memory type: (1) the user requested it via PROT_MTE passed to + * mmap() or mprotect() and (2) the corresponding vma supports MTE. We + * register (1) as VM_MTE in the vma->vm_flags and (2) as + * VM_MTE_ALLOWED. Note that the latter can only be set during the + * mmap() call since mprotect() does not accept MAP_* flags. + * Checking for VM_MTE only is sufficient since arch_validate_flags() + * does not permit (VM_MTE & !VM_MTE_ALLOWED). + */ + if (vm_flags & VM_MTE) + prot |= PTE_ATTRINDX(MT_NORMAL_TAGGED); + + return __pgprot(prot); +} +EXPORT_SYMBOL(vm_get_page_prot); diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h index 688c7548b559..9638206bc44f 100644 --- a/arch/csky/include/asm/processor.h +++ b/arch/csky/include/asm/processor.h @@ -4,9 +4,9 @@ #define __ASM_CSKY_PROCESSOR_H #include <linux/bitops.h> +#include <linux/cache.h> #include <asm/ptrace.h> #include <asm/current.h> -#include <asm/cache.h> #include <abi/reg_ops.h> #include <abi/regdef.h> #include <abi/switch_context.h> diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h index 7e46ebde8c0c..026ead47cd53 100644 --- a/arch/ia64/include/asm/hugetlb.h +++ b/arch/ia64/include/asm/hugetlb.h @@ -23,9 +23,10 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, #define is_hugepage_only_range is_hugepage_only_range #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { + return *ptep; } #include <asm-generic/hugetlb.h> diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c index 816803636a75..a0fec82c56b8 100644 --- a/arch/ia64/kernel/uncached.c +++ b/arch/ia64/kernel/uncached.c @@ -261,7 +261,7 @@ static int __init uncached_init(void) { int nid; - for_each_node_state(nid, N_ONLINE) { + for_each_online_node(nid) { uncached_pools[nid].pool = gen_pool_create(PAGE_SHIFT, nid); mutex_init(&uncached_pools[nid].add_chunk_mutex); } diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h index c2144409c0c4..fd69c8808554 100644 --- a/arch/mips/include/asm/hugetlb.h +++ b/arch/mips/include/asm/hugetlb.h @@ -43,16 +43,19 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, } #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { + pte_t pte; + /* * clear the huge pte entry firstly, so that the other smp threads will * not get old pte entry after finishing flush_tlb_page and before * setting new huge pte entry */ - huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); flush_tlb_page(vma, addr); + return pte; } #define __HAVE_ARCH_HUGE_PTE_NONE diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index a69cf9efb0c1..f7f078c2872c 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -28,9 +28,10 @@ static inline int prepare_hugepage_range(struct file *file, } #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { + return *ptep; } #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a4e8dd889e29..2c9d7e55fff5 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -140,6 +140,7 @@ config PPC select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_VM_GET_PAGE_PROT if PPC_BOOK3S_64 select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_KEEP_MEMBLOCK select ARCH_MIGHT_HAVE_PC_PARPORT diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 875730d5af40..eecff2036869 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -13,7 +13,6 @@ /* * Common bits between hash and Radix page table */ -#define _PAGE_BIT_SWAP_TYPE 0 #define _PAGE_EXEC 0x00001 /* execute permission */ #define _PAGE_WRITE 0x00002 /* write access allowed */ @@ -751,17 +750,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) * Don't have overlapping bits with _PAGE_HPTEFLAGS \ * We filter HPTEFLAGS on set_pte. \ */ \ - BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & SWP_TYPE_MASK); \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \ + BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_EXCLUSIVE); \ } while (0) #define SWP_TYPE_BITS 5 -#define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ - & ((1UL << SWP_TYPE_BITS) - 1)) +#define SWP_TYPE_MASK ((1UL << SWP_TYPE_BITS) - 1) +#define __swp_type(x) ((x).val & SWP_TYPE_MASK) #define __swp_offset(x) (((x).val & PTE_RPN_MASK) >> PAGE_SHIFT) #define __swp_entry(type, offset) ((swp_entry_t) { \ - ((type) << _PAGE_BIT_SWAP_TYPE) \ - | (((offset) << PAGE_SHIFT) & PTE_RPN_MASK)}) + (type) | (((offset) << PAGE_SHIFT) & PTE_RPN_MASK)}) /* * swp_entry_t must be independent of pte bits. We build a swp_entry_t from * swap type and offset we get from swap and convert that to pte to find a @@ -774,11 +773,13 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #define __swp_entry_to_pmd(x) (pte_pmd(__swp_entry_to_pte(x))) #ifdef CONFIG_MEM_SOFT_DIRTY -#define _PAGE_SWP_SOFT_DIRTY (1UL << (SWP_TYPE_BITS + _PAGE_BIT_SWAP_TYPE)) +#define _PAGE_SWP_SOFT_DIRTY _PAGE_SOFT_DIRTY #else #define _PAGE_SWP_SOFT_DIRTY 0UL #endif /* CONFIG_MEM_SOFT_DIRTY */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_NON_IDEMPOTENT + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { @@ -796,6 +797,22 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ +#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_EXCLUSIVE)); +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return __pte_raw(pte_raw(pte) & cpu_to_be64(~_PAGE_SWP_EXCLUSIVE)); +} + static inline bool check_pte_access(unsigned long access, unsigned long ptev) { /* diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 6a1a1ac5743b..8a5674fd120d 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -43,11 +43,14 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, } #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { - huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + pte_t pte; + + pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); flush_hugetlb_page(vma, addr); + return pte; } #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index 7cb6d18f5cd6..1b024e64c8ec 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -24,18 +24,6 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) -static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) -{ -#ifdef CONFIG_PPC_MEM_KEYS - return (vm_flags & VM_SAO) ? - __pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) : - __pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags)); -#else - return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0); -#endif -} -#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) - static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO)) diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index 052e6590f84f..8b474ab32f67 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -7,6 +7,7 @@ #include <linux/mm_types.h> #include <linux/memblock.h> #include <linux/memremap.h> +#include <linux/pkeys.h> #include <linux/debugfs.h> #include <misc/cxl-base.h> @@ -549,3 +550,19 @@ unsigned long memremap_compat_align(void) } EXPORT_SYMBOL_GPL(memremap_compat_align); #endif + +pgprot_t vm_get_page_prot(unsigned long vm_flags) +{ + unsigned long prot = pgprot_val(protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); + + if (vm_flags & VM_SAO) + prot |= _PAGE_SAO; + +#ifdef CONFIG_PPC_MEM_KEYS + prot |= vmflag_to_pte_pkey_bits(vm_flags); +#endif + + return __pgprot(prot); +} +EXPORT_SYMBOL(vm_get_page_prot); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 52a4b0bdb502..c0853f1474a7 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -38,6 +38,7 @@ config RISCV select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU select ARCH_SUPPORTS_HUGETLBFS if MMU + select ARCH_SUPPORTS_PAGE_TABLE_CHECK select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 7e246e9f8d70..ba2494cbc24f 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -86,6 +86,11 @@ static inline int pud_leaf(pud_t pud) return pud_present(pud) && (pud_val(pud) & _PAGE_LEAF); } +static inline int pud_user(pud_t pud) +{ + return pud_val(pud) & _PAGE_USER; +} + static inline void set_pud(pud_t *pudp, pud_t pud) { *pudp = pud; diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 046b44225623..4200ddede880 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -114,6 +114,8 @@ #include <asm/pgtable-32.h> #endif /* CONFIG_64BIT */ +#include <linux/page_table_check.h> + #ifdef CONFIG_XIP_KERNEL #define XIP_FIXUP(addr) ({ \ uintptr_t __a = (uintptr_t)(addr); \ @@ -315,6 +317,11 @@ static inline int pte_exec(pte_t pte) return pte_val(pte) & _PAGE_EXEC; } +static inline int pte_user(pte_t pte) +{ + return pte_val(pte) & _PAGE_USER; +} + static inline int pte_huge(pte_t pte) { return pte_present(pte) && (pte_val(pte) & _PAGE_LEAF); @@ -446,7 +453,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) void flush_icache_pte(pte_t pte); -static inline void set_pte_at(struct mm_struct *mm, +static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval) { if (pte_present(pteval) && pte_exec(pteval)) @@ -455,10 +462,17 @@ static inline void set_pte_at(struct mm_struct *mm, set_pte(ptep, pteval); } +static inline void set_pte_at(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, pte_t pteval) +{ + page_table_check_pte_set(mm, addr, ptep, pteval); + __set_pte_at(mm, addr, ptep, pteval); +} + static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - set_pte_at(mm, addr, ptep, __pte(0)); + __set_pte_at(mm, addr, ptep, __pte(0)); } #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS @@ -479,7 +493,11 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { - return __pte(atomic_long_xchg((atomic_long_t *)ptep, 0)); + pte_t pte = __pte(atomic_long_xchg((atomic_long_t *)ptep, 0)); + + page_table_check_pte_clear(mm, address, pte); + + return pte; } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG @@ -546,6 +564,13 @@ static inline unsigned long pmd_pfn(pmd_t pmd) return ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT); } +#define __pud_to_phys(pud) (pud_val(pud) >> _PAGE_PFN_SHIFT << PAGE_SHIFT) + +static inline unsigned long pud_pfn(pud_t pud) +{ + return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT); +} + static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); @@ -567,6 +592,11 @@ static inline int pmd_young(pmd_t pmd) return pte_young(pmd_pte(pmd)); } +static inline int pmd_user(pmd_t pmd) +{ + return pte_user(pmd_pte(pmd)); +} + static inline pmd_t pmd_mkold(pmd_t pmd) { return pte_pmd(pte_mkold(pmd_pte(pmd))); @@ -600,14 +630,33 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - return set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); + page_table_check_pmd_set(mm, addr, pmdp, pmd); + return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd)); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - return set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); + page_table_check_pud_set(mm, addr, pudp, pud); + return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud)); +} + +#ifdef CONFIG_PAGE_TABLE_CHECK +static inline bool pte_user_accessible_page(pte_t pte) +{ + return pte_present(pte) && pte_user(pte); +} + +static inline bool pmd_user_accessible_page(pmd_t pmd) +{ + return pmd_leaf(pmd) && pmd_user(pmd); +} + +static inline bool pud_user_accessible_page(pud_t pud) +{ + return pud_leaf(pud) && pud_user(pud); } +#endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) @@ -634,7 +683,11 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { - return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp)); + pmd_t pmd = __pmd(atomic_long_xchg((atomic_long_t *)pmdp, 0)); + + page_table_check_pmd_clear(mm, address, pmd); + + return pmd; } #define __HAVE_ARCH_PMDP_SET_WRPROTECT @@ -648,6 +701,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { + page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd))); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index bea47e7cc6a0..f22beda9e6d5 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -50,10 +50,10 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, set_pte(ptep, __pte(_SEGMENT_ENTRY_EMPTY)); } -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { - huge_ptep_get_and_clear(vma->vm_mm, address, ptep); + return huge_ptep_get_and_clear(vma->vm_mm, address, ptep); } static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, @@ -85,6 +85,11 @@ static inline int huge_pte_none(pte_t pte) return pte_none(pte); } +static inline int huge_pte_none_mostly(pte_t pte) +{ + return huge_pte_none(pte); +} + static inline int huge_pte_write(pte_t pte) { return pte_write(pte); @@ -115,6 +120,21 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) return pte_modify(pte, newprot); } +static inline pte_t huge_pte_mkuffd_wp(pte_t pte) +{ + return pte; +} + +static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) +{ + return pte; +} + +static inline int huge_pte_uffd_wp(pte_t pte) +{ + return 0; +} + static inline bool gigantic_page_runtime_supported(void) { return true; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 9df679152620..a397b072a580 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -181,6 +181,8 @@ static inline int is_module_addr(void *addr) #define _PAGE_SOFT_DIRTY 0x000 #endif +#define _PAGE_SWP_EXCLUSIVE _PAGE_LARGE /* SW pte exclusive swap bit */ + /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL | _PAGE_DIRTY | \ _PAGE_YOUNG | _PAGE_SOFT_DIRTY) @@ -826,6 +828,22 @@ static inline int pmd_protnone(pmd_t pmd) } #endif +#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline int pte_swp_exclusive(pte_t pte) +{ + return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(_PAGE_SWP_EXCLUSIVE)); +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(_PAGE_SWP_EXCLUSIVE)); +} + static inline int pte_soft_dirty(pte_t pte) { return pte_val(pte) & _PAGE_SOFT_DIRTY; @@ -1712,18 +1730,18 @@ static inline int has_transparent_hugepage(void) /* * 64 bit swap entry format: * A page-table entry has some bits we have to treat in a special way. - * Bits 52 and bit 55 have to be zero, otherwise a specification - * exception will occur instead of a page translation exception. The - * specification exception has the bad habit not to store necessary - * information in the lowcore. - * Bits 54 and 63 are used to indicate the page type. + * Bits 54 and 63 are used to indicate the page type. Bit 53 marks the pte + * as invalid. * A swap pte is indicated by bit pattern (pte & 0x201) == 0x200 - * This leaves the bits 0-51 and bits 56-62 to store type and offset. - * We use the 5 bits from 57-61 for the type and the 52 bits from 0-51 - * for the offset. - * | offset |01100|type |00| + * | offset |E11XX|type |S0| * |0000000000111111111122222222223333333333444444444455|55555|55566|66| * |0123456789012345678901234567890123456789012345678901|23456|78901|23| + * + * Bits 0-51 store the offset. + * Bit 52 (E) is used to remember PG_anon_exclusive. + * Bits 57-61 store the type. + * Bit 62 (S) is used for softdirty tracking. + * Bits 55 and 56 (X) are unused. */ #define __SWP_OFFSET_MASK ((1UL << 52) - 1) diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index ae4de7b89210..4d3ba39e681c 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -21,9 +21,10 @@ static inline int prepare_hugepage_range(struct file *file, } #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { + return *ptep; } static inline void arch_clear_hugepage_flags(struct page *page) diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 9200bc04701c..85b573643af6 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -84,6 +84,7 @@ config SPARC64 select PERF_USE_VMALLOC select ARCH_HAVE_NMI_SAFE_CMPXCHG select HAVE_C_RECORDMCOUNT + select ARCH_HAS_VM_GET_PAGE_PROT select HAVE_ARCH_AUDITSYSCALL select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h index 53838a173f62..0a26cca24232 100644 --- a/arch/sparc/include/asm/hugetlb.h +++ b/arch/sparc/include/asm/hugetlb.h @@ -21,9 +21,10 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) { + return *ptep; } #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT diff --git a/arch/sparc/include/asm/mman.h b/arch/sparc/include/asm/mman.h index 274217e7ed70..af9c10c83dc5 100644 --- a/arch/sparc/include/asm/mman.h +++ b/arch/sparc/include/asm/mman.h @@ -46,12 +46,6 @@ static inline unsigned long sparc_calc_vm_prot_bits(unsigned long prot) } } -#define arch_vm_get_page_prot(vm_flags) sparc_vm_get_page_prot(vm_flags) -static inline pgprot_t sparc_vm_get_page_prot(unsigned long vm_flags) -{ - return (vm_flags & VM_SPARC_ADI) ? __pgprot(_PAGE_MCD_4V) : __pgprot(0); -} - #define arch_validate_prot(prot, addr) sparc_validate_prot(prot, addr) static inline int sparc_validate_prot(unsigned long prot, unsigned long addr) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 8b1911591581..f6174df2d5af 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -3184,3 +3184,15 @@ void copy_highpage(struct page *to, struct page *from) } } EXPORT_SYMBOL(copy_highpage); + +pgprot_t vm_get_page_prot(unsigned long vm_flags) +{ + unsigned long prot = pgprot_val(protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); + + if (vm_flags & VM_SPARC_ADI) + prot |= _PAGE_MCD_4V; + + return __pgprot(prot); +} +EXPORT_SYMBOL(vm_get_page_prot); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6f59517c4356..cf531fbcd229 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -76,7 +76,6 @@ config X86 select ARCH_HAS_EARLY_DEBUG if KGDB select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER - select ARCH_HAS_FILTER_PGPROT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 @@ -95,6 +94,7 @@ config X86 select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_VM_GET_PAGE_PROT select ARCH_HAS_DEBUG_WX select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -121,6 +121,7 @@ config X86 select ARCH_WANTS_NO_INSTR select ARCH_WANT_GENERAL_HUGETLB select ARCH_WANT_HUGE_PMD_SHARE + select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP if X86_64 select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_THP_SWAP if X86_64 select ARCH_HAS_PARANOID_L1D_FLUSH diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 62ab07e24aef..44e2d6f1dbaa 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -649,11 +649,6 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) -static inline pgprot_t arch_filter_pgprot(pgprot_t prot) -{ - return canon_pgprot(prot); -} - static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) @@ -1077,16 +1072,6 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, return pte; } -#define __HAVE_ARCH_PTEP_CLEAR -static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - if (IS_ENABLED(CONFIG_PAGE_TABLE_CHECK)) - ptep_get_and_clear(mm, addr, ptep); - else - pte_clear(mm, addr, ptep); -} - #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) @@ -1173,6 +1158,11 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, } } #endif + +#define __HAVE_ARCH_PMDP_INVALIDATE_AD +extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + /* * Page table pages are page-aligned. The lower half of the top * level is used for userspace and the top half for the kernel. @@ -1291,6 +1281,23 @@ static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } +#ifdef _PAGE_SWP_EXCLUSIVE +#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE); +} +#endif /* _PAGE_SWP_EXCLUSIVE */ #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) @@ -1430,6 +1437,23 @@ static inline bool arch_faults_on_old_pte(void) return false; } +#ifdef CONFIG_PAGE_TABLE_CHECK +static inline bool pte_user_accessible_page(pte_t pte) +{ + return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); +} + +static inline bool pmd_user_accessible_page(pmd_t pmd) +{ + return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && (pmd_val(pmd) & _PAGE_USER); +} + +static inline bool pud_user_accessible_page(pud_t pud) +{ + return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && (pud_val(pud) & _PAGE_USER); +} +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 56d0399a0cd1..e479491da8d5 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -186,7 +186,7 @@ static inline void native_pgd_clear(pgd_t *pgd) * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names - * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|F|SD|0| <- swp entry + * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| E|F|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above @@ -203,6 +203,8 @@ static inline void native_pgd_clear(pgd_t *pgd) * F (2) in swp entry is used to record when a pagetable is * writeprotected by userfaultfd WP support. * + * E (3) in swp entry is used to rememeber PG_anon_exclusive. + * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. * diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 91ac10654570..70e360a2e5fb 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -163,4 +163,9 @@ extern unsigned int ptrs_per_p4d; #define PGD_KERNEL_START ((PAGE_SIZE / 2) / sizeof(pgd_t)) +/* + * We borrow bit 3 to remember PG_anon_exclusive. + */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_PWT + #endif /* _ASM_X86_PGTABLE_64_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 407084d9fd99..bdaf8391e2e0 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -110,9 +110,11 @@ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) #define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP) +#define _PAGE_SOFTW4 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW4) #else #define _PAGE_NX (_AT(pteval_t, 0)) #define _PAGE_DEVMAP (_AT(pteval_t, 0)) +#define _PAGE_SOFTW4 (_AT(pteval_t, 0)) #endif #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 98fa0a114074..4af5579c7ef7 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -259,6 +259,103 @@ static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); +static inline bool pte_flags_need_flush(unsigned long oldflags, + unsigned long newflags, + bool ignore_access) +{ + /* + * Flags that require a flush when cleared but not when they are set. + * Only include flags that would not trigger spurious page-faults. + * Non-present entries are not cached. Hardware would set the + * dirty/access bit if needed without a fault. + */ + const pteval_t flush_on_clear = _PAGE_DIRTY | _PAGE_PRESENT | + _PAGE_ACCESSED; + const pteval_t software_flags = _PAGE_SOFTW1 | _PAGE_SOFTW2 | + _PAGE_SOFTW3 | _PAGE_SOFTW4; + const pteval_t flush_on_change = _PAGE_RW | _PAGE_USER | _PAGE_PWT | + _PAGE_PCD | _PAGE_PSE | _PAGE_GLOBAL | _PAGE_PAT | + _PAGE_PAT_LARGE | _PAGE_PKEY_BIT0 | _PAGE_PKEY_BIT1 | + _PAGE_PKEY_BIT2 | _PAGE_PKEY_BIT3 | _PAGE_NX; + unsigned long diff = oldflags ^ newflags; + + BUILD_BUG_ON(flush_on_clear & software_flags); + BUILD_BUG_ON(flush_on_clear & flush_on_change); + BUILD_BUG_ON(flush_on_change & software_flags); + + /* Ignore software flags */ + diff &= ~software_flags; + + if (ignore_access) + diff &= ~_PAGE_ACCESSED; + + /* + * Did any of the 'flush_on_clear' flags was clleared set from between + * 'oldflags' and 'newflags'? + */ + if (diff & oldflags & flush_on_clear) + return true; + + /* Flush on modified flags. */ + if (diff & flush_on_change) + return true; + + /* Ensure there are no flags that were left behind */ + if (IS_ENABLED(CONFIG_DEBUG_VM) && + (diff & ~(flush_on_clear | software_flags | flush_on_change))) { + VM_WARN_ON_ONCE(1); + return true; + } + + return false; +} + +/* + * pte_needs_flush() checks whether permissions were demoted and require a + * flush. It should only be used for userspace PTEs. + */ +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + /* !PRESENT -> * ; no need for flush */ + if (!(pte_flags(oldpte) & _PAGE_PRESENT)) + return false; + + /* PFN changed ; needs flush */ + if (pte_pfn(oldpte) != pte_pfn(newpte)) + return true; + + /* + * check PTE flags; ignore access-bit; see comment in + * ptep_clear_flush_young(). + */ + return pte_flags_need_flush(pte_flags(oldpte), pte_flags(newpte), + true); +} +#define pte_needs_flush pte_needs_flush + +/* + * huge_pmd_needs_flush() checks whether permissions were demoted and require a + * flush. It should only be used for userspace huge PMDs. + */ +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) +{ + /* !PRESENT -> * ; no need for flush */ + if (!(pmd_flags(oldpmd) & _PAGE_PRESENT)) + return false; + + /* PFN changed ; needs flush */ + if (pmd_pfn(oldpmd) != pmd_pfn(newpmd)) + return true; + + /* + * check PMD flags; do not ignore access-bit; see + * pmdp_clear_flush_young(). + */ + return pte_flags_need_flush(pmd_flags(oldpmd), pmd_flags(newpmd), + false); +} +#define huge_pmd_needs_flush huge_pmd_needs_flush + #endif /* !MODULE */ static inline void __native_tlb_flush_global(unsigned long cr4) diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h index d4a8d0424bfb..775dbd3aff73 100644 --- a/arch/x86/include/uapi/asm/mman.h +++ b/arch/x86/include/uapi/asm/mman.h @@ -5,20 +5,6 @@ #define MAP_32BIT 0x40 /* only give out 32bit addresses */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS -/* - * Take the 4 protection key bits out of the vma->vm_flags - * value and turn them in to the bits that we can put in - * to a pte. - * - * Only override these if Protection Keys are available - * (which is only on 64-bit). - */ -#define arch_vm_get_page_prot(vm_flags) __pgprot( \ - ((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) | \ - ((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) | \ - ((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) | \ - ((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0)) - #define arch_calc_vm_prot_bits(prot, key) ( \ ((key) & 0x1 ? VM_PKEY_BIT0 : 0) | \ ((key) & 0x2 ? VM_PKEY_BIT1 : 0) | \ diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index d957dc15b371..f8220fd2c169 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -20,7 +20,7 @@ CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ - pgtable.o physaddr.o tlb.o cpu_entry_area.o maccess.o + pgtable.o physaddr.o tlb.o cpu_entry_area.o maccess.o pgprot.o obj-y += pat/ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 61d0ab154f96..cb290a2f0747 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1269,7 +1269,7 @@ static struct kcore_list kcore_vsyscall; static void __init register_page_bootmem_info(void) { -#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP) +#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP) int i; for_each_online_node(i) diff --git a/arch/x86/mm/pgprot.c b/arch/x86/mm/pgprot.c new file mode 100644 index 000000000000..763742782286 --- /dev/null +++ b/arch/x86/mm/pgprot.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/export.h> +#include <linux/mm.h> +#include <asm/pgtable.h> + +pgprot_t vm_get_page_prot(unsigned long vm_flags) +{ + unsigned long val = pgprot_val(protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); + +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + /* + * Take the 4 protection key bits out of the vma->vm_flags value and + * turn them in to the bits that we can put in to a pte. + * + * Only override these if Protection Keys are available (which is only + * on 64-bit). + */ + if (vm_flags & VM_PKEY_BIT0) + val |= _PAGE_PKEY_BIT0; + if (vm_flags & VM_PKEY_BIT1) + val |= _PAGE_PKEY_BIT1; + if (vm_flags & VM_PKEY_BIT2) + val |= _PAGE_PKEY_BIT2; + if (vm_flags & VM_PKEY_BIT3) + val |= _PAGE_PKEY_BIT3; +#endif + + val = __sme_set(val); + if (val & _PAGE_PRESENT) + val &= __supported_pte_mask; + return __pgprot(val); +} +EXPORT_SYMBOL(vm_get_page_prot); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 3481b35cb4ec..a932d7712d85 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -608,6 +608,16 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, return young; } + +pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + /* + * No flush is necessary. Once an invalid PTE is established, the PTE's + * access and dirty bits cannot be updated. + */ + return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); +} #endif /** @@ -676,9 +686,8 @@ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) * * No 512GB pages yet -- always return 0 */ -int p4d_clear_huge(p4d_t *p4d) +void p4d_clear_huge(p4d_t *p4d) { - return 0; } #endif diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 7222ff9b5e05..084d67fd55cc 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -636,10 +636,9 @@ static int __add_memory_block(struct memory_block *memory) } ret = xa_err(xa_store(&memory_blocks, memory->dev.id, memory, GFP_KERNEL)); - if (ret) { - put_device(&memory->dev); + if (ret) device_unregister(&memory->dev); - } + return ret; } diff --git a/drivers/base/node.c b/drivers/base/node.c index ec8bb24a5a22..0ac6376ef7a1 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -682,6 +682,7 @@ static int register_node(struct node *node, int num) */ void unregister_node(struct node *node) { + compaction_unregister_node(node); hugetlb_unregister_node(node); /* no-op, if memoryless node */ node_remove_accesses(node); node_remove_caches(node); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index e2cb51810e89..f1dda4ef22cc 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -190,8 +190,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) */ if (dio) { if (queue_logical_block_size(lo->lo_queue) >= sb_bsize && - !(lo->lo_offset & dio_align) && - mapping->a_ops->direct_IO) + !(lo->lo_offset & dio_align) && + (file->f_mode & FMODE_CAN_ODIRECT)) use_dio = true; else use_dio = false; diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index 668c6bf2554d..d4100b0c083e 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 config ZRAM tristate "Compressed RAM block device support" - depends on BLOCK && SYSFS && ZSMALLOC && CRYPTO + depends on BLOCK && SYSFS && MMU depends on CRYPTO_LZO || CRYPTO_ZSTD || CRYPTO_LZ4 || CRYPTO_LZ4HC || CRYPTO_842 + select ZSMALLOC help Creates virtual block devices called /dev/zramX (X = 0, 1, ...). Pages written to these disks are compressed and stored in memory diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 6853dd3c7d3a..b8549c61ff2c 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -639,8 +639,8 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, #define PAGE_WB_SIG "page_index=" #define PAGE_WRITEBACK 0 -#define HUGE_WRITEBACK 1 -#define IDLE_WRITEBACK 2 +#define HUGE_WRITEBACK (1<<0) +#define IDLE_WRITEBACK (1<<1) static ssize_t writeback_store(struct device *dev, @@ -660,6 +660,8 @@ static ssize_t writeback_store(struct device *dev, mode = IDLE_WRITEBACK; else if (sysfs_streq(buf, "huge")) mode = HUGE_WRITEBACK; + else if (sysfs_streq(buf, "huge_idle")) + mode = IDLE_WRITEBACK | HUGE_WRITEBACK; else { if (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1)) return -EINVAL; @@ -721,10 +723,10 @@ static ssize_t writeback_store(struct device *dev, zram_test_flag(zram, index, ZRAM_UNDER_WB)) goto next; - if (mode == IDLE_WRITEBACK && + if (mode & IDLE_WRITEBACK && !zram_test_flag(zram, index, ZRAM_IDLE)) goto next; - if (mode == HUGE_WRITEBACK && + if (mode & HUGE_WRITEBACK && !zram_test_flag(zram, index, ZRAM_HUGE)) goto next; /* @@ -1142,15 +1144,14 @@ static ssize_t bd_stat_show(struct device *dev, static ssize_t debug_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { - int version = 1; + int version = 2; struct zram *zram = dev_to_zram(dev); ssize_t ret; down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "version: %d\n%8llu %8llu\n", + "version: %d\n%8llu\n", version, - (u64)atomic64_read(&zram->stats.writestall), (u64)atomic64_read(&zram->stats.miss_free)); up_read(&zram->init_lock); @@ -1366,7 +1367,6 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, } kunmap_atomic(mem); -compress_again: zstrm = zcomp_stream_get(zram->comp); src = kmap_atomic(page); ret = zcomp_compress(zstrm, src, &comp_len); @@ -1375,39 +1375,20 @@ compress_again: if (unlikely(ret)) { zcomp_stream_put(zram->comp); pr_err("Compression failed! err=%d\n", ret); - zs_free(zram->mem_pool, handle); return ret; } if (comp_len >= huge_class_size) comp_len = PAGE_SIZE; - /* - * handle allocation has 2 paths: - * a) fast path is executed with preemption disabled (for - * per-cpu streams) and has __GFP_DIRECT_RECLAIM bit clear, - * since we can't sleep; - * b) slow path enables preemption and attempts to allocate - * the page with __GFP_DIRECT_RECLAIM bit set. we have to - * put per-cpu compression stream and, thus, to re-do - * the compression once handle is allocated. - * - * if we have a 'non-null' handle here then we are coming - * from the slow path and handle has already been allocated. - */ - if (!handle) - handle = zs_malloc(zram->mem_pool, comp_len, - __GFP_KSWAPD_RECLAIM | - __GFP_NOWARN | - __GFP_HIGHMEM | - __GFP_MOVABLE); - if (!handle) { + + handle = zs_malloc(zram->mem_pool, comp_len, + __GFP_KSWAPD_RECLAIM | + __GFP_NOWARN | + __GFP_HIGHMEM | + __GFP_MOVABLE); + + if (unlikely(!handle)) { zcomp_stream_put(zram->comp); - atomic64_inc(&zram->stats.writestall); - handle = zs_malloc(zram->mem_pool, comp_len, - GFP_NOIO | __GFP_HIGHMEM | - __GFP_MOVABLE); - if (handle) - goto compress_again; return -ENOMEM; } @@ -1965,7 +1946,6 @@ static int zram_add(void) if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, zram->disk->queue); ret = device_add_disk(NULL, zram->disk, zram_disk_groups); if (ret) goto out_cleanup_disk; diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 80c3b43b4828..158c91e54850 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -81,7 +81,6 @@ struct zram_stats { atomic64_t huge_pages_since; /* no. of huge pages since zram set up */ atomic64_t pages_stored; /* no. of pages currently stored */ atomic_long_t max_used_pages; /* no. of maximum pages stored */ - atomic64_t writestall; /* no. of write slow paths */ atomic64_t miss_free; /* no. of missed free */ #ifdef CONFIG_ZRAM_WRITEBACK atomic64_t bd_count; /* no. of pages in backing device */ diff --git a/drivers/firmware/smccc/kvm_guest.c b/drivers/firmware/smccc/kvm_guest.c index 2d3e866decaa..89a68e7eeaa6 100644 --- a/drivers/firmware/smccc/kvm_guest.c +++ b/drivers/firmware/smccc/kvm_guest.c @@ -4,6 +4,7 @@ #include <linux/arm-smccc.h> #include <linux/bitmap.h> +#include <linux/cache.h> #include <linux/kernel.h> #include <linux/string.h> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c index 65552bb7d2f2..e83cb1c09610 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c @@ -184,7 +184,7 @@ static int kgd_hqd_load(struct amdgpu_device *adev, void *mqd, /* read_user_ptr may take the mm->mmap_lock. * release srbm_mutex to avoid circular dependency between - * srbm_mutex->mm_sem->reservation_ww_class_mutex->srbm_mutex. + * srbm_mutex->mmap_lock->reservation_ww_class_mutex->srbm_mutex. */ release_queue(adev); valid_wptr = read_user_wptr(mm, wptr, wptr_val); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c index 9dc5f2a0cc07..870f352837fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c @@ -208,7 +208,7 @@ static int kgd_hqd_load(struct amdgpu_device *adev, void *mqd, /* read_user_ptr may take the mm->mmap_lock. * release srbm_mutex to avoid circular dependency between - * srbm_mutex->mm_sem->reservation_ww_class_mutex->srbm_mutex. + * srbm_mutex->mmap_lock->reservation_ww_class_mutex->srbm_mutex. */ release_queue(adev); valid_wptr = read_user_wptr(mm, wptr, wptr_val); diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 5b324f245265..38119311284d 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -102,7 +102,7 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo, * @bo: The buffer object * @vmf: The fault structure handed to the callback * - * vm callbacks like fault() and *_mkwrite() allow for the mm_sem to be dropped + * vm callbacks like fault() and *_mkwrite() allow for the mmap_lock to be dropped * during long waits, and after the wait the callback will be restarted. This * is to allow other threads using the same virtual memory space concurrent * access to map(), unmap() completely unrelated buffer objects. TTM buffer diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index e7d6b679596d..e07486f01999 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -2476,10 +2476,10 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm) VIRTIO_MEM_DEFAULT_OFFLINE_THRESHOLD); /* - * TODO: once alloc_contig_range() works reliably with pageblock - * granularity on ZONE_NORMAL, use pageblock_nr_pages instead. + * alloc_contig_range() works reliably with pageblock + * granularity on ZONE_NORMAL, use pageblock_nr_pages. */ - sb_size = PAGE_SIZE * MAX_ORDER_NR_PAGES; + sb_size = PAGE_SIZE * pageblock_nr_pages; sb_size = max_t(uint64_t, vm->device_block_size, sb_size); if (sb_size < memory_block_size_bytes() && !force_bbm) { diff --git a/fs/Kconfig b/fs/Kconfig index 30b751c7f11a..5976eb33535f 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -245,19 +245,27 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS -config HUGETLB_PAGE_FREE_VMEMMAP +# +# Select this config option from the architecture Kconfig, if it is preferred +# to enable the feature of minimizing overhead of struct page associated with +# each HugeTLB page. +# +config ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP + bool + +config HUGETLB_PAGE_OPTIMIZE_VMEMMAP def_bool HUGETLB_PAGE - depends on X86_64 + depends on ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP depends on SPARSEMEM_VMEMMAP -config HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON - bool "Default freeing vmemmap pages of HugeTLB to on" +config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON + bool "Default optimizing vmemmap pages of HugeTLB to on" default n - depends on HUGETLB_PAGE_FREE_VMEMMAP + depends on HUGETLB_PAGE_OPTIMIZE_VMEMMAP help - When using HUGETLB_PAGE_FREE_VMEMMAP, the freeing unused vmemmap + When using HUGETLB_PAGE_OPTIMIZE_VMEMMAP, the optimizing unused vmemmap pages associated with each HugeTLB page is default off. Say Y here - to enable freeing vmemmap pages of HugeTLB by default. It can then + to enable optimizing vmemmap pages of HugeTLB by default. It can then be disabled on the command line via hugetlb_free_vmemmap=off. config MEMFD_CREATE diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 06003bb9cbe9..580a847aa8b5 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4906,6 +4906,10 @@ static int cifs_swap_activate(struct swap_info_struct *sis, cifs_dbg(FYI, "swap activate\n"); + if (!swap_file->f_mapping->a_ops->swap_rw) + /* Cannot support swap */ + return -EINVAL; + spin_lock(&inode->i_lock); blocks = inode->i_blocks; isize = inode->i_size; @@ -4934,7 +4938,8 @@ static int cifs_swap_activate(struct swap_info_struct *sis, * from reading or writing the file */ - return 0; + sis->flags |= SWP_FS_OPS; + return add_swap_extent(sis, 0, sis->max, 0); } static void cifs_swap_deactivate(struct file *file) @@ -24,6 +24,7 @@ #include <linux/sizes.h> #include <linux/mmu_notifier.h> #include <linux/iomap.h> +#include <linux/rmap.h> #include <asm/pgalloc.h> #define CREATE_TRACE_POINTS @@ -789,95 +790,12 @@ static void *dax_insert_entry(struct xa_state *xas, return entry; } -static inline -unsigned long pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma) -{ - unsigned long address; - - address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); - return address; -} - -/* Walk all mappings of a given index of a file and writeprotect them */ -static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index, - unsigned long pfn) -{ - struct vm_area_struct *vma; - pte_t pte, *ptep = NULL; - pmd_t *pmdp = NULL; - spinlock_t *ptl; - - i_mmap_lock_read(mapping); - vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) { - struct mmu_notifier_range range; - unsigned long address; - - cond_resched(); - - if (!(vma->vm_flags & VM_SHARED)) - continue; - - address = pgoff_address(index, vma); - - /* - * follow_invalidate_pte() will use the range to call - * mmu_notifier_invalidate_range_start() on our behalf before - * taking any lock. - */ - if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep, - &pmdp, &ptl)) - continue; - - /* - * No need to call mmu_notifier_invalidate_range() as we are - * downgrading page table protection not changing it to point - * to a new page. - * - * See Documentation/vm/mmu_notifier.rst - */ - if (pmdp) { -#ifdef CONFIG_FS_DAX_PMD - pmd_t pmd; - - if (pfn != pmd_pfn(*pmdp)) - goto unlock_pmd; - if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp)) - goto unlock_pmd; - - flush_cache_page(vma, address, pfn); - pmd = pmdp_invalidate(vma, address, pmdp); - pmd = pmd_wrprotect(pmd); - pmd = pmd_mkclean(pmd); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); -unlock_pmd: -#endif - spin_unlock(ptl); - } else { - if (pfn != pte_pfn(*ptep)) - goto unlock_pte; - if (!pte_dirty(*ptep) && !pte_write(*ptep)) - goto unlock_pte; - - flush_cache_page(vma, address, pfn); - pte = ptep_clear_flush(vma, address, ptep); - pte = pte_wrprotect(pte); - pte = pte_mkclean(pte); - set_pte_at(vma->vm_mm, address, ptep, pte); -unlock_pte: - pte_unmap_unlock(ptep, ptl); - } - - mmu_notifier_invalidate_range_end(&range); - } - i_mmap_unlock_read(mapping); -} - static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev, struct address_space *mapping, void *entry) { - unsigned long pfn, index, count; + unsigned long pfn, index, count, end; long ret = 0; + struct vm_area_struct *vma; /* * A page got tagged dirty in DAX mapping? Something is seriously @@ -935,8 +853,16 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev, pfn = dax_to_pfn(entry); count = 1UL << dax_entry_order(entry); index = xas->xa_index & ~(count - 1); + end = index + count - 1; + + /* Walk all mappings of a given index of a file and writeprotect them */ + i_mmap_lock_read(mapping); + vma_interval_tree_foreach(vma, &mapping->i_mmap, index, end) { + pfn_mkclean_range(pfn, count, index, vma); + cond_resched(); + } + i_mmap_unlock_read(mapping); - dax_entry_mkclean(mapping, index, pfn); dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE); /* * After we have flushed the cache, we can clear the dirty tag. There diff --git a/fs/exec.c b/fs/exec.c index e3e55d5e0be1..14b4b3755580 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -758,6 +758,7 @@ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_size; unsigned long stack_expand; unsigned long rlim_stack; + struct mmu_gather tlb; #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ @@ -812,8 +813,11 @@ int setup_arg_pages(struct linux_binprm *bprm, vm_flags |= mm->def_flags; vm_flags |= VM_STACK_INCOMPLETE_SETUP; - ret = mprotect_fixup(vma, &prev, vma->vm_start, vma->vm_end, + tlb_gather_mmu(&tlb, mm); + ret = mprotect_fixup(&tlb, vma, &prev, vma->vm_start, vma->vm_end, vm_flags); + tlb_finish_mmu(&tlb); + if (ret) goto out_unlock; BUG_ON(prev != vma); diff --git a/fs/fcntl.c b/fs/fcntl.c index f15d885b9796..34a3faa4886d 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -56,11 +56,10 @@ static int setfl(int fd, struct file * filp, unsigned long arg) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ - if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT)) { - if (!filp->f_mapping || !filp->f_mapping->a_ops || - !filp->f_mapping->a_ops->direct_IO) - return -EINVAL; - } + if (!S_ISFIFO(inode->i_mode) && + (arg & O_DIRECT) && + !(filp->f_mode & FMODE_CAN_ODIRECT)) + return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 2de9ca5d260d..22d2b94339ed 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -405,7 +405,8 @@ static void remove_huge_page(struct page *page) } static void -hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end) +hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, + zap_flags_t zap_flags) { struct vm_area_struct *vma; @@ -439,7 +440,7 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end) } unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end, - NULL); + NULL, zap_flags); } } @@ -517,7 +518,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vmdelete_list(&mapping->i_mmap, index * pages_per_huge_page(h), - (index + 1) * pages_per_huge_page(h)); + (index + 1) * pages_per_huge_page(h), + ZAP_FLAG_DROP_MARKER); i_mmap_unlock_write(mapping); } @@ -583,7 +585,8 @@ static void hugetlb_vmtruncate(struct inode *inode, loff_t offset) i_mmap_lock_write(mapping); i_size_write(inode, offset); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) - hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0); + hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0, + ZAP_FLAG_DROP_MARKER); i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, offset, LLONG_MAX); } @@ -616,8 +619,8 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) i_mmap_lock_write(mapping); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, - hole_start >> PAGE_SHIFT, - hole_end >> PAGE_SHIFT); + hole_start >> PAGE_SHIFT, + hole_end >> PAGE_SHIFT, 0); i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, hole_start, hole_end); inode_unlock(inode); @@ -1048,12 +1051,12 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) if (sbinfo->spool) { long free_pages; - spin_lock(&sbinfo->spool->lock); + spin_lock_irq(&sbinfo->spool->lock); buf->f_blocks = sbinfo->spool->max_hpages; free_pages = sbinfo->spool->max_hpages - sbinfo->spool->used_hpages; buf->f_bavail = buf->f_bfree = free_pages; - spin_unlock(&sbinfo->spool->lock); + spin_unlock_irq(&sbinfo->spool->lock); buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 11c566d8769f..4eb2a8380a28 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -153,28 +153,25 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq, } /** - * nfs_direct_IO - NFS address space operation for direct I/O + * nfs_swap_rw - NFS address space operation for swap I/O * @iocb: target I/O control block * @iter: I/O buffer * - * The presence of this routine in the address space ops vector means - * the NFS client supports direct I/O. However, for most direct IO, we - * shunt off direct read and write requests before the VFS gets them, - * so this method is only ever called for swap. + * Perform IO to the swap-file. This is much like direct IO. */ -ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter) { - struct inode *inode = iocb->ki_filp->f_mapping->host; - - /* we only support swap file calling nfs_direct_IO */ - if (!IS_SWAPFILE(inode)) - return 0; + ssize_t ret; VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE); if (iov_iter_rw(iter) == READ) - return nfs_file_direct_read(iocb, iter, true); - return nfs_file_direct_write(iocb, iter, true); + ret = nfs_file_direct_read(iocb, iter, true); + else + ret = nfs_file_direct_write(iocb, iter, true); + if (ret < 0) + return ret; + return 0; } static void nfs_direct_release_pages(struct page **pages, unsigned int npages) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d764b3ce7905..6f5425e89ca6 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -69,6 +69,8 @@ nfs_file_open(struct inode *inode, struct file *filp) return res; res = nfs_open(inode, filp); + if (res == 0) + filp->f_mode |= FMODE_CAN_ODIRECT; return res; } @@ -480,6 +482,7 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, { unsigned long blocks; long long isize; + int ret; struct inode *inode = file_inode(file); struct rpc_clnt *clnt = NFS_CLIENT(inode); struct nfs_client *cl = NFS_SERVER(inode)->nfs_client; @@ -493,13 +496,22 @@ static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, return -EINVAL; } - *span = sis->pages; + ret = rpc_clnt_swap_activate(clnt); + if (ret) + return ret; + ret = add_swap_extent(sis, 0, sis->max, 0); + if (ret < 0) { + rpc_clnt_swap_deactivate(clnt); + return ret; + } + *span = sis->pages; if (cl->rpc_ops->enable_swap) cl->rpc_ops->enable_swap(inode); - return rpc_clnt_swap_activate(clnt); + sis->flags |= SWP_FS_OPS; + return ret; } static void nfs_swap_deactivate(struct file *file) @@ -523,7 +535,6 @@ const struct address_space_operations nfs_file_aops = { .write_end = nfs_write_end, .invalidate_folio = nfs_invalidate_folio, .release_folio = nfs_release_folio, - .direct_IO = nfs_direct_IO, #ifdef CONFIG_MIGRATION .migratepage = nfs_migrate_page, #endif @@ -532,6 +543,7 @@ const struct address_space_operations nfs_file_aops = { .error_remove_page = generic_error_remove_page, .swap_activate = nfs_swap_activate, .swap_deactivate = nfs_swap_deactivate, + .swap_rw = nfs_swap_rw, }; /* diff --git a/fs/open.c b/fs/open.c index 1315253e0247..7b50d7a2f51d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -834,16 +834,15 @@ static int do_dentry_open(struct file *f, if ((f->f_mode & FMODE_WRITE) && likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; + if (f->f_mapping->a_ops && f->f_mapping->a_ops->direct_IO) + f->f_mode |= FMODE_CAN_ODIRECT; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); - /* NB: we're sure to have correct a_ops only after f_op->open */ - if (f->f_flags & O_DIRECT) { - if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO) - return -EINVAL; - } + if ((f->f_flags & O_DIRECT) && !(f->f_mode & FMODE_CAN_ODIRECT)) + return -EINVAL; /* * XXX: Huge page cache doesn't support writing yet. Drop all page diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index fa125feed0ff..9d69b4dbb8c4 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -82,11 +82,8 @@ static int ovl_change_flags(struct file *file, unsigned int flags) if (((flags ^ file->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; - if (flags & O_DIRECT) { - if (!file->f_mapping->a_ops || - !file->f_mapping->a_ops->direct_IO) - return -EINVAL; - } + if ((flags & O_DIRECT) && !(file->f_mode & FMODE_CAN_ODIRECT)) + return -EINVAL; if (file->f_op->check_flags) { err = file->f_op->check_flags(flags); @@ -306,8 +303,7 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) ret = -EINVAL; if (iocb->ki_flags & IOCB_DIRECT && - (!real.file->f_mapping->a_ops || - !real.file->f_mapping->a_ops->direct_IO)) + !(real.file->f_mode & FMODE_CAN_ODIRECT)) goto out_fdput; old_cred = ovl_override_creds(file_inode(file)->i_sb); @@ -367,8 +363,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) ret = -EINVAL; if (iocb->ki_flags & IOCB_DIRECT && - (!real.file->f_mapping->a_ops || - !real.file->f_mapping->a_ops->direct_IO)) + !(real.file->f_mode & FMODE_CAN_ODIRECT)) goto out_fdput; if (!ovl_should_sync(OVL_FS(inode->i_sb))) diff --git a/fs/proc/base.c b/fs/proc/base.c index c1031843cc6a..8dfa36a99c74 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3154,6 +3154,22 @@ static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, } #endif /* CONFIG_LIVEPATCH */ +#ifdef CONFIG_KSM +static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + struct mm_struct *mm; + + mm = get_task_mm(task); + if (mm) { + seq_printf(m, "%lu\n", mm->ksm_merging_pages); + mmput(mm); + } + + return 0; +} +#endif /* CONFIG_KSM */ + #ifdef CONFIG_STACKLEAK_METRICS static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) @@ -3285,6 +3301,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif +#ifdef CONFIG_KSM + ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) @@ -3618,6 +3637,9 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_SECCOMP_CACHE_DEBUG ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache), #endif +#ifdef CONFIG_KSM + ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages), +#endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 6fa761c9cc78..6e89f0e2fd20 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -86,6 +86,13 @@ 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)); + seq_printf(m, "Zswapped: %8lu kB\n", + (unsigned long)atomic_read(&zswap_stored_pages) << + (PAGE_SHIFT - 10)); +#endif show_val_kb(m, "Dirty: ", global_node_page_state(NR_FILE_DIRTY)); show_val_kb(m, "Writeback: ", diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f46060eb91b5..2d04e3470d4c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1421,6 +1421,8 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, migration = is_migration_entry(entry); if (is_pfn_swap_entry(entry)) page = pfn_swap_entry_to_page(entry); + if (pte_marker_entry_uffd_wp(entry)) + flags |= PM_UFFD_WP; } if (page && !PageAnon(page)) @@ -1556,10 +1558,15 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, if (page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; + if (huge_pte_uffd_wp(pte)) + flags |= PM_UFFD_WP; + flags |= PM_PRESENT; if (pm->show_pfn) frame = pte_pfn(pte) + ((addr & ~hmask) >> PAGE_SHIFT); + } else if (pte_swp_uffd_wp_any(pte)) { + flags |= PM_UFFD_WP; } for (; addr != end; addr += PAGE_SIZE) { @@ -1873,8 +1880,6 @@ static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, return 0; page = pte_page(huge_pte); - if (!page) - return 0; md = walk->private; gather_stats(page, md, pte_dirty(huge_pte), 1); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index aa0c47cb0d16..e943370107d0 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -29,6 +29,7 @@ #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> +#include <linux/swapops.h> int sysctl_unprivileged_userfaultfd __read_mostly; @@ -249,9 +250,10 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, /* * Lockless access: we're in a wait_event so it's ok if it - * changes under us. + * changes under us. PTE markers should be handled the same as none + * ptes here. */ - if (huge_pte_none(pte)) + if (huge_pte_none_mostly(pte)) ret = true; if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; @@ -330,9 +332,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, pte = pte_offset_map(pmd, address); /* * Lockless access: we're in a wait_event so it's ok if it - * changes under us. + * changes under us. PTE markers should be handled the same as none + * ptes here. */ - if (pte_none(*pte)) + if (pte_none_mostly(*pte)) ret = true; if (!pte_write(*pte) && (reason & VM_UFFD_WP)) ret = true; @@ -1255,24 +1258,6 @@ static __always_inline int validate_range(struct mm_struct *mm, return 0; } -static inline bool vma_can_userfault(struct vm_area_struct *vma, - unsigned long vm_flags) -{ - /* FIXME: add WP support to hugetlbfs and shmem */ - if (vm_flags & VM_UFFD_WP) { - if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) - return false; - } - - if (vm_flags & VM_UFFD_MINOR) { - if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma))) - return false; - } - - return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || - vma_is_shmem(vma); -} - static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { @@ -1954,6 +1939,9 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; #endif +#ifndef CONFIG_PTE_MARKER_UFFD_WP + uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM; +#endif uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 8e1e6244a89d..a57d667addd2 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -2,6 +2,9 @@ #ifndef _ASM_GENERIC_HUGETLB_H #define _ASM_GENERIC_HUGETLB_H +#include <linux/swap.h> +#include <linux/swapops.h> + static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) { return mk_pte(page, pgprot); @@ -32,6 +35,21 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) return pte_modify(pte, newprot); } +static inline pte_t huge_pte_mkuffd_wp(pte_t pte) +{ + return pte_mkuffd_wp(pte); +} + +static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) +{ + return pte_clear_uffd_wp(pte); +} + +static inline int huge_pte_uffd_wp(pte_t pte) +{ + return pte_uffd_wp(pte); +} + #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) @@ -66,10 +84,10 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, #endif #ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - ptep_clear_flush(vma, addr, ptep); + return ptep_clear_flush(vma, addr, ptep); } #endif @@ -80,6 +98,12 @@ static inline int huge_pte_none(pte_t pte) } #endif +/* Please refer to comments above pte_none_mostly() for the usage */ +static inline int huge_pte_none_mostly(pte_t pte) +{ + return huge_pte_none(pte) || is_pte_marker(pte); +} + #ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT static inline pte_t huge_pte_wrprotect(pte_t pte) { diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index 10789cf51d16..8ffd64e7a24c 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -30,6 +30,8 @@ typedef struct { pud_t pud; } pmd_t; static inline int pud_none(pud_t pud) { return 0; } static inline int pud_bad(pud_t pud) { return 0; } static inline int pud_present(pud_t pud) { return 1; } +static inline int pud_user(pud_t pud) { return 0; } +static inline int pud_leaf(pud_t pud) { return 0; } static inline void pud_clear(pud_t *pud) { } #define pmd_ERROR(pmd) (pud_ERROR((pmd).pud)) diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index eee6f7763a39..ff3e82553a76 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -658,6 +658,20 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, } while (0) #endif +#ifndef pte_needs_flush +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + return true; +} +#endif + +#ifndef huge_pmd_needs_flush +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) +{ + return true; +} +#endif + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/linux/cma.h b/include/linux/cma.h index a6f637342740..63873b93deaa 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -17,11 +17,11 @@ #define CMA_MAX_NAME 64 /* - * TODO: once the buddy -- especially pageblock merging and alloc_contig_range() + * the buddy -- especially pageblock merging and alloc_contig_range() * -- can deal with only some pageblocks of a higher-order page being * MIGRATE_CMA, we can use pageblock_nr_pages. */ -#define CMA_MIN_ALIGNMENT_PAGES MAX_ORDER_NR_PAGES +#define CMA_MIN_ALIGNMENT_PAGES pageblock_nr_pages #define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES) struct cma; diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 34bce35c808d..52a9ff65faee 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -177,7 +177,7 @@ static inline bool compaction_withdrawn(enum compact_result result) bool compaction_zonelist_suitable(struct alloc_context *ac, int order, int alloc_flags); -extern int kcompactd_run(int nid); +extern void kcompactd_run(int nid); extern void kcompactd_stop(int nid); extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx); @@ -212,9 +212,8 @@ static inline bool compaction_withdrawn(enum compact_result result) return true; } -static inline int kcompactd_run(int nid) +static inline void kcompactd_run(int nid) { - return 0; } static inline void kcompactd_stop(int nid) { diff --git a/include/linux/damon.h b/include/linux/damon.h index f23cbfa4248d..7c62da31ce4b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -261,10 +261,14 @@ struct damos { * enum damon_ops_id - Identifier for each monitoring operations implementation * * @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces + * @DAMON_OPS_FVADDR: Monitoring operations for only fixed ranges of virtual + * address spaces * @DAMON_OPS_PADDR: Monitoring operations for the physical address space + * @NR_DAMON_OPS: Number of monitoring operations implementations */ enum damon_ops_id { DAMON_OPS_VADDR, + DAMON_OPS_FVADDR, DAMON_OPS_PADDR, NR_DAMON_OPS, }; @@ -340,6 +344,7 @@ struct damon_operations { * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. + * @after_wmarks_check: Called after each schemes' watermarks check. * @after_sampling: Called after each sampling. * @after_aggregation: Called after each aggregation. * @before_terminate: Called before terminating the monitoring. @@ -350,6 +355,11 @@ struct damon_operations { * respectively. Therefore, those are good places for installing and cleaning * @private. * + * The monitoring thread calls @after_wmarks_check after each DAMON-based + * operation schemes' watermarks check. If users need to make changes to the + * attributes of the monitoring context while it's deactivated due to the + * watermarks, this is the good place to do. + * * The monitoring thread calls @after_sampling and @after_aggregation for each * of the sampling intervals and aggregation intervals, respectively. * Therefore, users can safely access the monitoring results without additional @@ -362,6 +372,7 @@ struct damon_callback { void *private; int (*before_start)(struct damon_ctx *context); + int (*after_wmarks_check)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); void (*before_terminate)(struct damon_ctx *context); @@ -484,6 +495,8 @@ static inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, + unsigned int nr_ranges); struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, @@ -509,6 +522,7 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); +bool damon_is_registered_ops(enum damon_ops_id id); int damon_register_ops(struct damon_operations *ops); int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id); diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 2d04f6448cde..9f6e25467844 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -20,6 +20,7 @@ struct fault_attr { atomic_t space; unsigned long verbose; bool task_filter; + bool no_warn; unsigned long stacktrace_depth; unsigned long require_start; unsigned long require_end; @@ -39,6 +40,7 @@ struct fault_attr { .ratelimit_state = RATELIMIT_STATE_INIT_DISABLED, \ .verbose = 2, \ .dname = NULL, \ + .no_warn = false, \ } #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER diff --git a/include/linux/fs.h b/include/linux/fs.h index f58ae40235ab..1225f8c75650 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -162,6 +162,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) +/* File supports DIRECT IO */ +#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -376,6 +379,7 @@ struct address_space_operations { int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); + int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; @@ -457,6 +461,11 @@ static inline void i_mmap_unlock_write(struct address_space *mapping) up_write(&mapping->i_mmap_rwsem); } +static inline int i_mmap_trylock_read(struct address_space *mapping) +{ + return down_read_trylock(&mapping->i_mmap_rwsem); +} + static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 3e3d36fc2109..2d2ccae933c2 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -367,7 +367,7 @@ static inline int gfp_migratetype(const gfp_t gfp_flags) return MIGRATE_UNMOVABLE; /* Group based on mobility */ - return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; + return (__force unsigned long)(gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT @@ -613,13 +613,8 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -struct page *alloc_pages_vma(gfp_t gfp_mask, int order, - struct vm_area_struct *vma, unsigned long addr, - bool hugepage); struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { @@ -629,16 +624,17 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ - alloc_pages(gfp_mask, order) #define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ folio_alloc(gfp, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -#define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, false) +static inline struct page *alloc_page_vma(gfp_t gfp, + struct vm_area_struct *vma, unsigned long addr) +{ + struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false); + + return &folio->page; +} extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 337bd9f32921..cddb42ff0473 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -246,9 +246,21 @@ static inline bool is_kmap_addr(const void *x) #endif /* CONFIG_HIGHMEM */ -/* - * Prevent people trying to call kunmap_atomic() as if it were kunmap() - * kunmap_atomic() should get the return value of kmap_atomic, not the page. +/** + * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - deprecated! + * @__addr: Virtual address to be unmapped + * + * Unmaps an address previously mapped by kmap_atomic() and re-enables + * pagefaults. Depending on PREEMP_RT configuration, re-enables also + * migration and preemption. Users should not count on these side effects. + * + * Mappings should be unmapped in the reverse order that they were mapped. + * See kmap_local_page() for details on nesting. + * + * @__addr can be any address within the mapped page, so there is no need + * to subtract any offset that has been added. In contrast to kunmap(), + * this function takes the address returned from kmap_atomic(), not the + * page passed to it. The compiler will warn you if you pass the page. */ #define kunmap_atomic(__addr) \ do { \ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 39bb9b47fa9c..3af34de54330 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -37,7 +37,7 @@ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() - * @addr: Virtual address to be unmapped + * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. @@ -138,23 +138,46 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); * * Returns: The virtual address of the mapping * - * Effectively a wrapper around kmap_local_page() which disables pagefaults - * and preemption. + * In fact a wrapper around kmap_local_page() which also disables pagefaults + * and, depending on PREEMPT_RT configuration, also CPU migration and + * preemption. Therefore users should not count on the latter two side effects. + * + * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. - */ -static inline void *kmap_atomic(struct page *page); - -/** - * kunmap_atomic - Unmap the virtual address mapped by kmap_atomic() - * @addr: Virtual address to be unmapped * - * Counterpart to kmap_atomic(). + * It is used in atomic context when code wants to access the contents of a + * page that might be allocated from high memory (see __GFP_HIGHMEM), for + * example a page in the pagecache. The API has two functions, and they + * can be used in a manner similar to the following: + * + * -- Find the page of interest. -- + * struct page *page = find_get_page(mapping, offset); + * + * -- Gain access to the contents of that page. -- + * void *vaddr = kmap_atomic(page); + * + * -- Do something to the contents of that page. -- + * memset(vaddr, 0, PAGE_SIZE); + * + * -- Unmap that page. -- + * kunmap_atomic(vaddr); * - * Effectively a wrapper around kunmap_local() which additionally undoes - * the side effects of kmap_atomic(), i.e. reenabling pagefaults and - * preemption. + * Note that the kunmap_atomic() call takes the result of the kmap_atomic() + * call, not the argument. + * + * If you need to map two pages because you want to copy from one page to + * another you need to keep the kmap_atomic calls strictly nested, like: + * + * vaddr1 = kmap_atomic(page1); + * vaddr2 = kmap_atomic(page2); + * + * memcpy(vaddr1, vaddr2, PAGE_SIZE); + * + * kunmap_atomic(vaddr2); + * kunmap_atomic(vaddr1); */ +static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ static inline unsigned int nr_free_highpages(void); @@ -191,6 +214,8 @@ static inline void clear_user_highpage(struct page *page, unsigned long vaddr) * @vma: The VMA the page is to be allocated for * @vaddr: The virtual address the page will be inserted into * + * Returns: The allocated and zeroed HIGHMEM page + * * This function will allocate a page for a VMA that the caller knows will * be able to migrate in the future using move_pages() or reclaimed * @@ -358,6 +383,8 @@ static inline void memcpy_to_page(struct page *page, size_t offset, static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); + + VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2999190adc22..de29821231c9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -36,8 +36,9 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); -int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, - pgprot_t newprot, unsigned long cp_flags); +int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, pgprot_t pgprot, bool write); @@ -172,6 +173,20 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + struct inode *inode; + + if (!vma->vm_file) + return false; + + inode = vma->vm_file->f_inode; + + return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) && + (vma->vm_flags & VM_EXEC) && + !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); +} + bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ @@ -347,7 +362,6 @@ static inline void prep_transhuge_page(struct page *page) {} static inline bool can_split_folio(struct folio *folio, int *pextra_pins) { - BUILD_BUG(); return false; } static inline int diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ac2a1d758a80..0f2894d01333 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -137,17 +137,19 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); -int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); +int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, + struct vm_area_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, unsigned long *, long, unsigned int, int *); void unmap_hugepage_range(struct vm_area_struct *, - unsigned long, unsigned long, struct page *); + unsigned long, unsigned long, struct page *, + zap_flags_t); void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, - struct page *ref_page); + struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); @@ -160,7 +162,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep); + struct page **pagep, + bool wp_copy); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -210,7 +213,8 @@ struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address, int pmd_huge(pmd_t pmd); int pud_huge(pud_t pud); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot); + unsigned long address, unsigned long end, pgprot_t newprot, + unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); @@ -266,7 +270,9 @@ static inline struct page *follow_huge_addr(struct mm_struct *mm, } static inline int copy_hugetlb_page_range(struct mm_struct *dst, - struct mm_struct *src, struct vm_area_struct *vma) + struct mm_struct *src, + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { BUG(); return 0; @@ -356,7 +362,8 @@ static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep) + struct page **pagep, + bool wp_copy) { BUG(); return 0; @@ -395,14 +402,16 @@ static inline void move_hugetlb_state(struct page *oldpage, static inline unsigned long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, - unsigned long end, pgprot_t newprot) + unsigned long end, pgprot_t newprot, + unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { BUG(); } @@ -623,8 +632,8 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP - unsigned int nr_free_vmemmap_pages; +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP + unsigned int optimize_vmemmap_pages; #endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ @@ -1084,6 +1093,17 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr pte_t *ptep, pte_t pte, unsigned long sz) { } + +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + return *ptep; +} + +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, diff --git a/include/linux/kasan.h b/include/linux/kasan.h index ceebcb9de7bf..b092277bf48d 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -23,10 +23,10 @@ struct task_struct; typedef unsigned int __bitwise kasan_vmalloc_flags_t; -#define KASAN_VMALLOC_NONE 0x00u -#define KASAN_VMALLOC_INIT 0x01u -#define KASAN_VMALLOC_VM_ALLOC 0x02u -#define KASAN_VMALLOC_PROT_NORMAL 0x04u +#define KASAN_VMALLOC_NONE ((__force kasan_vmalloc_flags_t)0x00u) +#define KASAN_VMALLOC_INIT ((__force kasan_vmalloc_flags_t)0x01u) +#define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) +#define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 2fcc01891b47..392d34c3c59a 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -3,8 +3,6 @@ #define _LINUX_KHUGEPAGED_H #include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */ -#include <linux/shmem_fs.h> - #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; @@ -12,10 +10,12 @@ extern struct attribute_group khugepaged_attr_group; extern int khugepaged_init(void); extern void khugepaged_destroy(void); extern int start_stop_khugepaged(void); -extern int __khugepaged_enter(struct mm_struct *mm); +extern bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags); +extern void __khugepaged_enter(struct mm_struct *mm); extern void __khugepaged_exit(struct mm_struct *mm); -extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags); +extern void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags); extern void khugepaged_min_free_kbytes_update(void); #ifdef CONFIG_SHMEM extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr); @@ -40,11 +40,10 @@ static inline void collapse_pte_mapped_thp(struct mm_struct *mm, (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) -static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags)) - return __khugepaged_enter(mm); - return 0; + __khugepaged_enter(mm); } static inline void khugepaged_exit(struct mm_struct *mm) @@ -53,36 +52,29 @@ static inline void khugepaged_exit(struct mm_struct *mm) __khugepaged_exit(mm); } -static inline int khugepaged_enter(struct vm_area_struct *vma, +static inline void khugepaged_enter(struct vm_area_struct *vma, unsigned long vm_flags) { - if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) - if ((khugepaged_always() || - (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) || - (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && - !(vm_flags & VM_NOHUGEPAGE) && - !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - if (__khugepaged_enter(vma->vm_mm)) - return -ENOMEM; - return 0; + if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && + khugepaged_enabled()) { + if (hugepage_vma_check(vma, vm_flags)) + __khugepaged_enter(vma->vm_mm); + } } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline void khugepaged_exit(struct mm_struct *mm) { } -static inline int khugepaged_enter(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter(struct vm_area_struct *vma, + unsigned long vm_flags) { - return 0; } -static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) +static inline void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags) { - return 0; } static inline void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 0630e545f4cb..0b4f17418f64 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -79,7 +79,7 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, } static inline void rmap_walk_ksm(struct folio *folio, - const struct rmap_walk_control *rwc) + struct rmap_walk_control *rwc) { } diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 89b14729d59f..9ecead1042b9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -35,6 +35,8 @@ enum memcg_stat_item { MEMCG_PERCPU_B, MEMCG_VMALLOC, MEMCG_KMEM, + MEMCG_ZSWAP_B, + MEMCG_ZSWAPPED, MEMCG_NR_STAT, }; @@ -252,6 +254,10 @@ struct mem_cgroup { /* Range enforcement for interrupt charges */ struct work_struct high_work; +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + unsigned long zswap_max; +#endif + unsigned long soft_limit; /* vmpressure notifications */ @@ -937,10 +943,6 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -#ifdef CONFIG_MEMCG_SWAP -extern bool cgroup_memory_noswap; -#endif - void folio_memcg_lock(struct folio *folio); void folio_memcg_unlock(struct folio *folio); void lock_page_memcg(struct page *page); @@ -1061,6 +1063,15 @@ static inline void count_memcg_page_event(struct page *page, count_memcg_events(memcg, idx, 1); } +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) +{ + struct mem_cgroup *memcg = folio_memcg(folio); + + if (memcg) + count_memcg_events(memcg, idx, nr); +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { @@ -1268,6 +1279,10 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) return NULL; } +static inline void obj_cgroup_put(struct obj_cgroup *objcg) +{ +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } @@ -1498,6 +1513,11 @@ static inline void count_memcg_page_event(struct page *page, { } +static inline void count_memcg_folio_events(struct folio *folio, + enum vm_event_item idx, unsigned long nr) +{ +} + static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { @@ -1684,6 +1704,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); struct obj_cgroup *get_obj_cgroup_from_current(void); +struct obj_cgroup *get_obj_cgroup_from_page(struct page *page); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); @@ -1720,6 +1741,20 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_obj(void *p); +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_kmem_disabled()) + return; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + count_memcg_events(memcg, idx, 1); + rcu_read_unlock(); +} + #else static inline bool mem_cgroup_kmem_disabled(void) { @@ -1746,6 +1781,11 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } +static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) +{ + return NULL; +} + static inline bool memcg_kmem_enabled(void) { return false; @@ -1761,6 +1801,30 @@ static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) return NULL; } +static inline void count_objcg_event(struct obj_cgroup *objcg, + enum vm_event_item idx) +{ +} + #endif /* CONFIG_MEMCG_KMEM */ +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); +void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); +void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); +#else +static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) +{ + return true; +} +static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, + size_t size) +{ +} +#endif + #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 1ce6f8044f1e..20d7edf62a6a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -15,6 +15,7 @@ struct memory_block; struct memory_group; struct resource; struct vmem_altmap; +struct dev_pagemap; #ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION /* @@ -122,6 +123,7 @@ typedef int __bitwise mhp_t; struct mhp_params { struct vmem_altmap *altmap; pgprot_t pgprot; + struct dev_pagemap *pgmap; }; bool mhp_range_allowed(u64 start, u64 size, bool need_mapping); @@ -333,7 +335,8 @@ extern void remove_pfn_range_from_zone(struct zone *zone, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); + unsigned long nr_pages, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); extern void sparse_remove_section(struct mem_section *ms, unsigned long pfn, unsigned long nr_pages, unsigned long map_offset, struct vmem_altmap *altmap); @@ -348,4 +351,13 @@ void arch_remove_linear_mapping(u64 start, u64 size); extern bool mhp_supports_memmap_on_memory(unsigned long size); #endif /* CONFIG_MEMORY_HOTPLUG */ +#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY +bool mhp_memmap_on_memory(void); +#else +static inline bool mhp_memmap_on_memory(void) +{ + return false; +} +#endif + #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 90e75d5a54d6..069a89e847f3 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -47,16 +47,7 @@ void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); -extern bool numa_demotion_enabled; -extern void migrate_on_reclaim_init(void); -#ifdef CONFIG_HOTPLUG_CPU -extern void set_migration_target_nodes(void); #else -static inline void set_migration_target_nodes(void) {} -#endif -#else - -static inline void set_migration_target_nodes(void) {} static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t new, @@ -82,9 +73,23 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, return -ENOSYS; } -#define numa_demotion_enabled false #endif /* CONFIG_MIGRATION */ +#if defined(CONFIG_MIGRATION) && defined(CONFIG_NUMA) +extern void set_migration_target_nodes(void); +extern void migrate_on_reclaim_init(void); +extern bool numa_demotion_enabled; +extern int next_demotion_node(int node); +#else +static inline void set_migration_target_nodes(void) {} +static inline void migrate_on_reclaim_init(void) {} +static inline int next_demotion_node(int node) +{ + return NUMA_NO_NODE; +} +#define numa_demotion_enabled false +#endif + #ifdef CONFIG_COMPACTION extern int PageMovable(struct page *page); extern void __SetPageMovable(struct page *page, struct address_space *mapping); @@ -100,6 +105,11 @@ static inline void __ClearPageMovable(struct page *page) } #endif +static inline bool folio_test_movable(struct folio *folio) +{ + return PageMovable(&folio->page); +} + #ifdef CONFIG_NUMA_BALANCING extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); @@ -172,15 +182,6 @@ struct migrate_vma { int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); -int next_demotion_node(int node); - -#else /* CONFIG_MIGRATION disabled: */ - -static inline int next_demotion_node(int node) -{ - return NUMA_NO_NODE; -} - #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index b0183450e484..f85e5a4c070b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1575,13 +1575,14 @@ static inline bool page_maybe_dma_pinned(struct page *page) /* * This should most likely only be called during fork() to see whether we - * should break the cow immediately for a page on the src mm. + * should break the cow immediately for an anon page on the src mm. + * + * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq. */ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, struct page *page) { - if (!is_cow_mapping(vma->vm_flags)) - return false; + VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1)); if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; @@ -1845,9 +1846,6 @@ 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_invalidate_pte(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, pte_t **ptepp, - pmd_t **pmdpp, spinlock_t **ptlp); int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, @@ -1969,10 +1967,11 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) -extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, +extern unsigned long change_protection(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, unsigned long cp_flags); -extern int mprotect_fixup(struct vm_area_struct *vma, +extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); @@ -3005,6 +3004,45 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) return 0; } +/* + * Indicates for which pages that are write-protected in the page table, + * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the + * GUP pin will remain consistent with the pages mapped into the page tables + * of the MM. + * + * Temporary unmapping of PageAnonExclusive() pages or clearing of + * PageAnonExclusive() has to protect against concurrent GUP: + * * Ordinary GUP: Using the PT lock + * * GUP-fast and fork(): mm->write_protect_seq + * * GUP-fast and KSM or temporary unmapping (swap, migration): + * clear/invalidate+flush of the page table entry + * + * Must be called with the (sub)page that's actually referenced via the + * page table entry, which might not necessarily be the head page for a + * PTE-mapped THP. + */ +static inline bool gup_must_unshare(unsigned int flags, struct page *page) +{ + /* + * FOLL_WRITE is implicitly handled correctly as the page table entry + * has to be writable -- and if it references (part of) an anonymous + * folio, that part is required to be marked exclusive. + */ + if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) + return false; + /* + * Note: PageAnon(page) is stable until the page is actually getting + * freed. + */ + if (!PageAnon(page)) + return false; + /* + * Note that PageKsm() pages cannot be exclusive, and consequently, + * cannot get pinned. + */ + return !PageAnonExclusive(page); +} + typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); @@ -3149,7 +3187,7 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP int vmemmap_remap_free(unsigned long start, unsigned long end, unsigned long reuse); int vmemmap_remap_alloc(unsigned long start, unsigned long end, @@ -3158,13 +3196,14 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end, void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, - unsigned long nr_pages, int nid, struct vmem_altmap *altmap); + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap); + struct vmem_altmap *altmap, struct page *reuse); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, @@ -3252,7 +3291,6 @@ enum mf_action_page_type { MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, - MF_MSG_DIFFERENT_PAGE_SIZE, MF_MSG_UNKNOWN, }; @@ -3391,4 +3429,12 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif +/* + * Whether to drop the pte markers, for example, the uffd-wp information for + * file-backed memory. This should only be specified when we will completely + * drop the page in the mm, either by truncation or unmapping of the vma. By + * default, the flag is not set. + */ +#define ZAP_FLAG_DROP_MARKER ((__force zap_flags_t) BIT(0)) + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index ac32125745ab..7b25b53c474a 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -6,6 +6,8 @@ #include <linux/huge_mm.h> #include <linux/swap.h> #include <linux/string.h> +#include <linux/userfaultfd_k.h> +#include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -316,5 +318,46 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm) return atomic_read(&mm->tlb_flush_pending) > 1; } +/* + * If this pte is wr-protected by uffd-wp in any form, arm the special pte to + * replace a none pte. NOTE! This should only be called when *pte is already + * cleared so we will never accidentally replace something valuable. Meanwhile + * none pte also means we are not demoting the pte so tlb flushed is not needed. + * E.g., when pte cleared the caller should have taken care of the tlb flush. + * + * Must be called with pgtable lock held so that no thread will see the none + * pte, and if they see it, they'll fault and serialize at the pgtable lock. + * + * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. + */ +static inline void +pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, + pte_t *pte, pte_t pteval) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + bool arm_uffd_pte = false; + + /* The current status of the pte should be "cleared" before calling */ + WARN_ON_ONCE(!pte_none(*pte)); + + if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) + return; + + /* A uffd-wp wr-protected normal pte */ + if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) + arm_uffd_pte = true; + + /* + * A uffd-wp wr-protected swap pte. Note: this should even cover an + * existing pte marker with uffd-wp bit set. + */ + if (unlikely(pte_swp_uffd_wp_any(pteval))) + arm_uffd_pte = true; + + if (unlikely(arm_uffd_pte)) + set_pte_at(vma->vm_mm, addr, pte, + make_pte_marker(PTE_MARKER_UFFD_WP)); +#endif +} #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8834e38c06a4..b34ff2cdbc4f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -655,6 +655,13 @@ struct mm_struct { #ifdef CONFIG_IOMMU_SVA u32 pasid; #endif +#ifdef CONFIG_KSM + /* + * Represent how many pages of this process are involved in KSM + * merging. + */ + unsigned long ksm_merging_pages; +#endif } __randomize_layout; /* @@ -812,6 +819,11 @@ typedef struct { * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark + * exclusive) a possibly shared anonymous page that is + * mapped R/O. + * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. + * We should only access orig_pte if this flag set. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -831,6 +843,10 @@ typedef struct { * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. + * + * The combination FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE is illegal. + * FAULT_FLAG_UNSHARE is ignored and treated like an ordinary read fault when + * no existing R/O-mapped anonymous page is encountered. */ enum fault_flag { FAULT_FLAG_WRITE = 1 << 0, @@ -843,6 +859,10 @@ enum fault_flag { FAULT_FLAG_REMOTE = 1 << 7, FAULT_FLAG_INSTRUCTION = 1 << 8, FAULT_FLAG_INTERRUPTIBLE = 1 << 9, + FAULT_FLAG_UNSHARE = 1 << 10, + FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, }; +typedef unsigned int __bitwise zap_flags_t; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mman.h b/include/linux/mman.h index b66e91b8176c..58b3abd457a3 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -93,10 +93,6 @@ static inline void vm_unacct_memory(long pages) #define arch_calc_vm_flag_bits(flags) 0 #endif -#ifndef arch_vm_get_page_prot -#define arch_vm_get_page_prot(vm_flags) __pgprot(0) -#endif - #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 46ffab808f03..aab70355d64f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -54,10 +54,7 @@ enum migratetype { * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by - * __free_pageblock_cma() function. What is important though - * is that a range of pageblocks must be aligned to - * MAX_ORDER_NR_PAGES should biggest page be bigger than - * a single pageblock. + * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 1bba71757d62..a17c337dbdf1 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -507,7 +507,7 @@ static inline const struct cred *nfs_file_cred(struct file *file) /* * linux/fs/nfs/direct.c */ -extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); +int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter); ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, bool swap); ssize_t nfs_file_direct_write(struct kiocb *iocb, diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 567c3ddba2c4..c6199dbe2591 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -375,14 +375,13 @@ static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, } #if MAX_NUMNODES > 1 -#define for_each_node_mask(node, mask) \ - for ((node) = first_node(mask); \ - (node) < MAX_NUMNODES; \ - (node) = next_node((node), (mask))) +#define for_each_node_mask(node, mask) \ + for ((node) = first_node(mask); \ + (node >= 0) && (node) < MAX_NUMNODES; \ + (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ -#define for_each_node_mask(node, mask) \ - if (!nodes_empty(mask)) \ - for ((node) = 0; (node) < 1; (node)++) +#define for_each_node_mask(node, mask) \ + for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index af10149a6c31..e66f7aa3191d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -142,6 +142,15 @@ enum pageflags { PG_readahead = PG_reclaim, + /* + * Depending on the way an anonymous folio can be mapped into a page + * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped + * THP), PG_anon_exclusive may be set only for the head page or for + * tail pages of an anonymous folio. For now, we only expect it to be + * set on tail pages for PTE-mapped THP. + */ + PG_anon_exclusive = PG_mappedtodisk, + /* Filesystems */ PG_checked = PG_owner_priv_1, @@ -176,7 +185,7 @@ enum pageflags { * Indicates that at least one subpage is hwpoisoned in the * THP. */ - PG_has_hwpoisoned = PG_mappedtodisk, + PG_has_hwpoisoned = PG_error, #endif /* non-lru isolated movable page */ @@ -190,18 +199,18 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, - hugetlb_free_vmemmap_enabled_key); +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, + hugetlb_optimize_vmemmap_key); -static __always_inline bool hugetlb_free_vmemmap_enabled(void) +static __always_inline bool hugetlb_optimize_vmemmap_enabled(void) { - return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, - &hugetlb_free_vmemmap_enabled_key); + return static_branch_maybe(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, + &hugetlb_optimize_vmemmap_key); } /* - * If the feature of freeing some vmemmap pages associated with each HugeTLB + * If the feature of optimizing vmemmap pages associated with each HugeTLB * page is enabled, the head vmemmap page frame is reused and all of the tail * vmemmap addresses map to the head vmemmap page frame (furture details can * refer to the figure at the head of the mm/hugetlb_vmemmap.c). In other @@ -218,7 +227,7 @@ static __always_inline bool hugetlb_free_vmemmap_enabled(void) */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { - if (!hugetlb_free_vmemmap_enabled()) + if (!hugetlb_optimize_vmemmap_enabled()) return page; /* @@ -247,7 +256,7 @@ static inline const struct page *page_fixed_fake_head(const struct page *page) return page; } -static inline bool hugetlb_free_vmemmap_enabled(void) +static inline bool hugetlb_optimize_vmemmap_enabled(void) { return false; } @@ -641,6 +650,11 @@ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) +static __always_inline bool folio_mapping_flags(struct folio *folio) +{ + return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; +} + static __always_inline int PageMappingFlags(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; @@ -1002,6 +1016,34 @@ extern bool is_free_buddy_page(struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); +static __always_inline int PageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void SetPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void ClearPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + +static __always_inline void __ClearPageAnonExclusive(struct page *page) +{ + VM_BUG_ON_PGFLAGS(!PageAnon(page), page); + VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + __clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); +} + #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 572458016331..5456b7be38ae 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,6 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -struct page *has_unmovable_pages(struct zone *zone, struct page *page, - int migratetype, int flags); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); @@ -44,7 +42,7 @@ int move_freepages_block(struct zone *zone, struct page *page, */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype, int flags); + int migratetype, int flags, gfp_t gfp_flags); /* * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. @@ -52,7 +50,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, */ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype); + int migratetype); /* * Test all pages in [start_pfn, end_pfn) are isolated or not. diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index f4f4077b97aa..3cdc16cfd867 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -12,6 +12,7 @@ #include <linux/bug.h> #include <linux/errno.h> #include <asm-generic/pgtable_uffd.h> +#include <linux/page_table_check.h> #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS @@ -259,14 +260,6 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif -#ifndef __HAVE_ARCH_PTEP_CLEAR -static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - pte_clear(mm, addr, ptep); -} -#endif - #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, @@ -274,10 +267,17 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = *ptep; pte_clear(mm, address, ptep); + page_table_check_pte_clear(mm, address, pte); return pte; } #endif +static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + ptep_get_and_clear(mm, addr, ptep); +} + #ifndef __HAVE_ARCH_PTEP_GET static inline pte_t ptep_get(pte_t *ptep) { @@ -347,7 +347,10 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, pmd_t *pmdp) { pmd_t pmd = *pmdp; + pmd_clear(pmdp); + page_table_check_pmd_clear(mm, address, pmd); + return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ @@ -359,6 +362,8 @@ static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, pud_t pud = *pudp; pud_clear(pudp); + page_table_check_pud_clear(mm, address, pud); + return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ @@ -570,6 +575,26 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif +#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD + +/* + * pmdp_invalidate_ad() invalidates the PMD while changing a transparent + * hugepage mapping in the page tables. This function is similar to + * pmdp_invalidate(), but should only be used if the access and dirty bits would + * not be cleared by the software in the new PMD value. The function ensures + * that hardware changes of the access and dirty bits updates would not be lost. + * + * Doing so can allow in certain architectures to avoid a TLB flush in most + * cases. Yet, another TLB flush might be necessary later if the PMD update + * itself requires such flush (e.g., if protection was set to be stricter). Yet, + * even when a TLB flush is needed because of the update, the caller may be able + * to batch these TLB flushing operations, so fewer TLB flush operations are + * needed. + */ +extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); +#endif + #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { @@ -738,7 +763,7 @@ static inline void arch_swap_invalidate_area(int type) #endif #ifndef __HAVE_ARCH_SWAP_RESTORE -static inline void arch_swap_restore(swp_entry_t entry, struct page *page) +static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) { } #endif @@ -1003,6 +1028,35 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define arch_start_context_switch(prev) do {} while (0) #endif +/* + * When replacing an anonymous page by a real (!non) swap entry, we clear + * PG_anon_exclusive from the page and instead remember whether the flag was + * set in the swp pte. During fork(), we have to mark the entry as !exclusive + * (possibly shared). On swapin, we use that information to restore + * PG_anon_exclusive, which is very helpful in cases where we might have + * additional (e.g., FOLL_GET) references on a page and wouldn't be able to + * detect exclusivity. + * + * These functions don't apply to non-swap entries (e.g., migration, hwpoison, + * ...). + */ +#ifndef __HAVE_ARCH_PTE_SWP_EXCLUSIVE +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return pte; +} + +static inline int pte_swp_exclusive(pte_t pte) +{ + return false; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return pte; +} +#endif + #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) @@ -1394,16 +1448,13 @@ static inline int pmd_protnone(pmd_t pmd) #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); -int p4d_clear_huge(p4d_t *p4d); +void p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } -static inline int p4d_clear_huge(p4d_t *p4d) -{ - return 0; -} +static inline void p4d_clear_huge(p4d_t *p4d) { } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); @@ -1426,10 +1477,7 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } -static inline int p4d_clear_huge(p4d_t *p4d) -{ - return 0; -} +static inline void p4d_clear_huge(p4d_t *p4d) { } static inline int pud_clear_huge(pud_t *pud) { return 0; diff --git a/include/linux/printk.h b/include/linux/printk.h index cd26aab0ab2a..10ec29bc0135 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -6,7 +6,6 @@ #include <linux/init.h> #include <linux/kern_levels.h> #include <linux/linkage.h> -#include <linux/cache.h> #include <linux/ratelimit_types.h> #include <linux/once_lite.h> diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 17230c458341..9ec23138e410 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -12,6 +12,7 @@ #include <linux/memcontrol.h> #include <linux/highmem.h> #include <linux/pagemap.h> +#include <linux/memremap.h> /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -127,6 +128,11 @@ static inline void anon_vma_lock_read(struct anon_vma *anon_vma) down_read(&anon_vma->root->rwsem); } +static inline int anon_vma_trylock_read(struct anon_vma *anon_vma) +{ + return down_read_trylock(&anon_vma->root->rwsem); +} + static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); @@ -159,34 +165,133 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, struct anon_vma *page_get_anon_vma(struct page *page); -/* bitflags for do_page_add_anon_rmap() */ -#define RMAP_EXCLUSIVE 0x01 -#define RMAP_COMPOUND 0x02 +/* RMAP flags, currently only relevant for some anon rmap operations. */ +typedef int __bitwise rmap_t; + +/* + * No special request: if the page is a subpage of a compound page, it is + * mapped via a PTE. The mapped (sub)page is possibly shared between processes. + */ +#define RMAP_NONE ((__force rmap_t)0) + +/* The (sub)page is exclusive to a single process. */ +#define RMAP_EXCLUSIVE ((__force rmap_t)BIT(0)) + +/* + * The compound page is not mapped via PTEs, but instead via a single PMD and + * should be accounted accordingly. + */ +#define RMAP_COMPOUND ((__force rmap_t)BIT(1)) /* * rmap interfaces called when adding or removing pte of page */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, bool compound); -void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, int flags); + unsigned long address, rmap_t flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address, bool compound); + unsigned long address); void page_add_file_rmap(struct page *, struct vm_area_struct *, bool compound); void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); + void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long address); + unsigned long address, rmap_t flags); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long address); -static inline void page_dup_rmap(struct page *page, bool compound) +static inline void __page_dup_rmap(struct page *page, bool compound) { atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } +static inline void page_dup_file_rmap(struct page *page, bool compound) +{ + __page_dup_rmap(page, compound); +} + +/** + * page_try_dup_anon_rmap - try duplicating a mapping of an already mapped + * anonymous page + * @page: the page to duplicate the mapping for + * @compound: the page is mapped as compound or as a small page + * @vma: the source vma + * + * The caller needs to hold the PT lock and the vma->vma_mm->write_protect_seq. + * + * Duplicating the mapping can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * If duplicating the mapping succeeds, the page has to be mapped R/O into + * the parent and the child. It must *not* get mapped writable after this call. + * + * Returns 0 if duplicating the mapping succeeded. Returns -EBUSY otherwise. + */ +static inline int page_try_dup_anon_rmap(struct page *page, bool compound, + struct vm_area_struct *vma) +{ + VM_BUG_ON_PAGE(!PageAnon(page), page); + + /* + * No need to check+clear for already shared pages, including KSM + * pages. + */ + if (!PageAnonExclusive(page)) + goto dup; + + /* + * If this page may have been pinned by the parent process, + * don't allow to duplicate the mapping but instead require to e.g., + * copy the page immediately for the child so that we'll always + * guarantee the pinned page won't be randomly replaced in the + * future on write faults. + */ + if (likely(!is_device_private_page(page) && + unlikely(page_needs_cow_for_dma(vma, page)))) + return -EBUSY; + + ClearPageAnonExclusive(page); + /* + * It's okay to share the anon page between both processes, mapping + * the page R/O into both processes. + */ +dup: + __page_dup_rmap(page, compound); + return 0; +} + +/** + * page_try_share_anon_rmap - try marking an exclusive anonymous page possibly + * shared to prepare for KSM or temporary unmapping + * @page: the exclusive anonymous page to try marking possibly shared + * + * The caller needs to hold the PT lock and has to have the page table entry + * cleared/invalidated+flushed, to properly sync against GUP-fast. + * + * This is similar to page_try_dup_anon_rmap(), however, not used during fork() + * to duplicate a mapping, but instead to prepare for KSM or temporarily + * unmapping a page (swap, migration) via page_remove_rmap(). + * + * Marking the page shared can only fail if the page may be pinned; device + * private pages cannot get pinned and consequently this function cannot fail. + * + * Returns 0 if marking the page possibly shared succeeded. Returns -EBUSY + * otherwise. + */ +static inline int page_try_share_anon_rmap(struct page *page) +{ + VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); + + /* See page_try_dup_anon_rmap(). */ + if (likely(!is_device_private_page(page) && + unlikely(page_maybe_dma_pinned(page)))) + return -EBUSY; + + ClearPageAnonExclusive(page); + return 0; +} + /* * Called from mm/vmscan.c to handle paging out */ @@ -261,19 +366,19 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int folio_mkclean(struct folio *); +int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, + struct vm_area_struct *vma); + void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -/* - * Called by memory-failure.c to kill processes. - */ -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); -void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() + * try_lock: bail out if the rmap lock is contended + * contended: indicate the rmap traversal bailed out due to lock contention * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default @@ -281,6 +386,8 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); */ struct rmap_walk_control { void *arg; + bool try_lock; + bool contended; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. @@ -288,12 +395,20 @@ struct rmap_walk_control { bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct folio *folio); - struct anon_vma *(*anon_lock)(struct folio *folio); + struct anon_vma *(*anon_lock)(struct folio *folio, + struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc); -void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); + +/* + * Called by memory-failure.c to kill processes. + */ +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, + struct rmap_walk_control *rwc); +void page_unlock_anon_vma_read(struct anon_vma *anon_vma); #else /* !CONFIG_MMU */ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 4d9e3a656875..4d0a5be28b70 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -57,7 +57,8 @@ static inline int get_dumpable(struct mm_struct *mm) #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ +#define MMF_VM_HUGEPAGE 17 /* set when mm is available for + khugepaged */ /* * This one-shot flag is dropped due to necessity of changing exe once again * on NFS restore diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index ab51d3cd39bd..a68f982f22d1 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -56,7 +56,7 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; -extern int shmem_init(void); +extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); @@ -145,11 +145,11 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, + bool zeropage, bool wp_copy, struct page **pagep); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ - src_addr, zeropage, pagep) ({ BUG(); 0; }) + src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 58bb9392775d..0fefdf528e0d 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -217,6 +217,18 @@ void kmem_dump_obj(void *object); #endif /* + * Arches can define this function if they want to decide the minimum slab + * alignment at runtime. The value returned by the function must be a power + * of two and >= ARCH_SLAB_MINALIGN. + */ +#ifndef arch_slab_minalign +static inline unsigned int arch_slab_minalign(void) +{ + return ARCH_SLAB_MINALIGN; +} +#endif + +/* * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. diff --git a/include/linux/swap.h b/include/linux/swap.h index 27093b477c5f..f3ae17b43f20 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -56,6 +56,19 @@ static inline int current_is_kswapd(void) */ /* + * PTE markers are used to persist information onto PTEs that are mapped with + * file-backed memories. As its name "PTE" hints, it should only be applied to + * the leaves of pgtables. + */ +#ifdef CONFIG_PTE_MARKER +#define SWP_PTE_MARKER_NUM 1 +#define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM) +#else +#define SWP_PTE_MARKER_NUM 0 +#endif + +/* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/vm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can @@ -78,12 +91,19 @@ static inline int current_is_kswapd(void) #endif /* - * NUMA node memory migration support + * Page migration support. + * + * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and + * indicates that the referenced (part of) an anonymous page is exclusive to + * a single process. For SWP_MIGRATION_WRITE, that information is implicit: + * (part of) an anonymous page that are mapped writable are exclusive to a + * single process. */ #ifdef CONFIG_MIGRATION -#define SWP_MIGRATION_NUM 2 -#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) -#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_NUM 3 +#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) +#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) +#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif @@ -100,7 +120,7 @@ static inline int current_is_kswapd(void) #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is @@ -148,8 +168,8 @@ struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of - * disk blocks. A list of swap extents maps the entire swapfile. (Where the - * term `swapfile' refers to either a blockdevice or an IS_REG file. Apart + * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the + * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. @@ -420,62 +440,18 @@ extern void kswapd_stop(int nid); #ifdef CONFIG_SWAP -#include <linux/blk_types.h> /* for bio_end_io_t */ - -/* linux/mm/page_io.c */ -extern int swap_readpage(struct page *page, bool do_poll); -extern int swap_writepage(struct page *page, struct writeback_control *wbc); -extern void end_swap_bio_write(struct bio *bio); -extern int __swap_writepage(struct page *page, struct writeback_control *wbc, - bio_end_io_t end_write_func); -bool swap_dirty_folio(struct address_space *mapping, struct folio *folio); - int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); -/* linux/mm/swap_state.c */ -/* One swap address space for each 64M swap space */ -#define SWAP_ADDRESS_SPACE_SHIFT 14 -#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) -extern struct address_space *swapper_spaces[]; -#define swap_address_space(entry) \ - (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ - >> SWAP_ADDRESS_SPACE_SHIFT]) static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } -extern void show_swap_cache_info(void); -extern int add_to_swap(struct page *page); -extern void *get_shadow_from_swap_cache(swp_entry_t entry); -extern int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp, void **shadowp); -extern void __delete_from_swap_cache(struct page *page, - swp_entry_t entry, void *shadow); -extern void delete_from_swap_cache(struct page *); -extern void clear_shadow_from_swap_cache(int type, unsigned long begin, - unsigned long end); -extern void free_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); -extern struct page *lookup_swap_cache(swp_entry_t entry, - struct vm_area_struct *vma, - unsigned long addr); -struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); -extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool do_poll); -extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr, - bool *new_page_allocated); -extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); -extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, - struct vm_fault *vmf); - /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; @@ -494,7 +470,7 @@ static inline long get_nr_swap_pages(void) } extern void si_swapinfo(struct sysinfo *); -extern swp_entry_t get_swap_page(struct page *page); +swp_entry_t folio_alloc_swap(struct folio *folio); extern void put_swap_page(struct page *page, 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); @@ -509,7 +485,6 @@ 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); extern sector_t swapdev_block(int, pgoff_t); -extern int page_swapcount(struct page *); extern int __swap_count(swp_entry_t entry); extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); @@ -528,12 +503,6 @@ static inline void put_swap_device(struct swap_info_struct *si) } #else /* CONFIG_SWAP */ - -static inline int swap_readpage(struct page *page, bool do_poll) -{ - return 0; -} - static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; @@ -548,11 +517,6 @@ static inline void put_swap_device(struct swap_info_struct *si) { } -static inline struct address_space *swap_address_space(swp_entry_t entry) -{ - return NULL; -} - #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL @@ -567,14 +531,6 @@ static inline struct address_space *swap_address_space(swp_entry_t entry) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); -static inline void free_swap_cache(struct page *page) -{ -} - -static inline void show_swap_cache_info(void) -{ -} - /* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ #define free_swap_and_cache(e) is_pfn_swap_entry(e) @@ -600,71 +556,6 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp) { } -static inline struct page *swap_cluster_readahead(swp_entry_t entry, - gfp_t gfp_mask, struct vm_fault *vmf) -{ - return NULL; -} - -static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, - struct vm_fault *vmf) -{ - return NULL; -} - -static inline int swap_writepage(struct page *p, struct writeback_control *wbc) -{ - return 0; -} - -static inline struct page *lookup_swap_cache(swp_entry_t swp, - struct vm_area_struct *vma, - unsigned long addr) -{ - return NULL; -} - -static inline -struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) -{ - return find_get_page(mapping, index); -} - -static inline int add_to_swap(struct page *page) -{ - return 0; -} - -static inline void *get_shadow_from_swap_cache(swp_entry_t entry) -{ - return NULL; -} - -static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, - gfp_t gfp_mask, void **shadowp) -{ - return -1; -} - -static inline void __delete_from_swap_cache(struct page *page, - swp_entry_t entry, void *shadow) -{ -} - -static inline void delete_from_swap_cache(struct page *page) -{ -} - -static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, - unsigned long end) -{ -} - -static inline int page_swapcount(struct page *page) -{ - return 0; -} - static inline int __swap_count(swp_entry_t entry) { return 0; @@ -685,13 +576,19 @@ static inline int try_to_free_swap(struct page *page) return 0; } -static inline swp_entry_t get_swap_page(struct page *page) +static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; return entry; } +static inline int add_swap_extent(struct swap_info_struct *sis, + unsigned long start_page, + unsigned long nr_pages, sector_t start_block) +{ + return -EINVAL; +} #endif /* CONFIG_SWAP */ #ifdef CONFIG_THP_SWAP @@ -723,6 +620,11 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) } #endif +#ifdef CONFIG_ZSWAP +extern u64 zswap_pool_total_size; +extern atomic_t zswap_stored_pages; +#endif + #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) @@ -736,15 +638,20 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { } #endif +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) +{ + cgroup_throttle_swaprate(&folio->page, gfp); +} #ifdef CONFIG_MEMCG_SWAP void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); -extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); -static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); +static inline int mem_cgroup_try_charge_swap(struct folio *folio, + swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_try_charge_swap(page, entry); + return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); @@ -762,7 +669,7 @@ static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } -static inline int mem_cgroup_try_charge_swap(struct page *page, +static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h index 347f1a304190..15adfb8c813a 100644 --- a/include/linux/swap_slots.h +++ b/include/linux/swap_slots.h @@ -24,7 +24,7 @@ struct swap_slots_cache { void disable_swap_slots_cache_lock(void); void reenable_swap_slots_cache_unlock(void); void enable_swap_slots_cache(void); -int free_swap_slot(swp_entry_t entry); +void free_swap_slot(swp_entry_t entry); extern bool swap_slot_cache_enabled; diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d356ab4047f7..fe220df499f1 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -13,10 +13,10 @@ * get good packing density in that tree, so the index should be dense in * the low-order bits. * - * We arrange the `type' and `offset' fields so that `type' is at the seven + * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for - * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry(). + * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ @@ -26,6 +26,8 @@ /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { + if (pte_swp_exclusive(pte)) + pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) @@ -194,6 +196,7 @@ static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || + swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } @@ -202,11 +205,26 @@ static inline int is_writable_migration_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ); +} + +static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); +} + static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_WRITE, offset); @@ -224,6 +242,11 @@ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) return swp_entry(0, 0); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -244,9 +267,92 @@ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return 0; +} #endif +typedef unsigned long pte_marker; + +#define PTE_MARKER_UFFD_WP BIT(0) +#define PTE_MARKER_MASK (PTE_MARKER_UFFD_WP) + +#ifdef CONFIG_PTE_MARKER + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + return swp_entry(SWP_PTE_MARKER, marker); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_PTE_MARKER; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return swp_offset(entry) & PTE_MARKER_MASK; +} + +static inline bool is_pte_marker(pte_t pte) +{ + return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); +} + +#else /* CONFIG_PTE_MARKER */ + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + /* This should never be called if !CONFIG_PTE_MARKER */ + WARN_ON_ONCE(1); + return swp_entry(0, 0); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return false; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return 0; +} + +static inline bool is_pte_marker(pte_t pte) +{ + return false; +} + +#endif /* CONFIG_PTE_MARKER */ + +static inline pte_t make_pte_marker(pte_marker marker) +{ + return swp_entry_to_pte(make_pte_marker_entry(marker)); +} + +/* + * This is a special version to check pte_none() just to cover the case when + * the pte is a pte marker. It existed because in many cases the pte marker + * should be seen as a none pte; it's just that we have stored some information + * onto the none pte so it becomes not-none any more. + * + * It should be used when the pte is file-backed, ram-based and backing + * userspace pages, like shmem. It is not needed upon pgtables that do not + * support pte markers at all. For example, it's not needed on anonymous + * memory, kernel-only memory (including when the system is during-boot), + * non-ram based generic file-system. It's fine to be used even there, but the + * extra pte marker check will be pure overhead. + * + * For systems configured with !CONFIG_PTE_MARKER this will be automatically + * optimized to pte_none(). + */ +static inline int pte_none_mostly(pte_t pte) +{ + return pte_none(pte) || is_pte_marker(pte); +} + static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset(entry)); @@ -274,7 +380,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION -extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, @@ -304,10 +410,10 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) static inline int is_pmd_migration_entry(pmd_t pmd) { - return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); + return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else -static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); @@ -387,18 +493,10 @@ static inline void num_poisoned_pages_inc(void) } #endif -#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \ - defined(CONFIG_DEVICE_PRIVATE) static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } -#else -static inline int non_swap_entry(swp_entry_t entry) -{ - return 0; -} -#endif #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 33cea484d1ad..732b522bacb7 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -15,7 +15,10 @@ #include <linux/fcntl.h> #include <linux/mm.h> +#include <linux/swap.h> +#include <linux/swapops.h> #include <asm-generic/pgtable_uffd.h> +#include <linux/hugetlb_inline.h> /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) @@ -94,6 +97,18 @@ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } +/* + * Don't do fault around for either WP or MINOR registered uffd range. For + * MINOR registered range, fault around will be a total disaster and ptes can + * be installed without notifications; for WP it should mostly be fine as long + * as the fault around checks for pte_none() before the installation, however + * to be super safe we just forbid it. + */ +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); +} + static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; @@ -126,6 +141,25 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma) return vma->vm_flags & __VM_UFFD_FLAGS; } +static inline bool vma_can_userfault(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + if (vm_flags & VM_UFFD_MINOR) + return is_vm_hugetlb_page(vma) || vma_is_shmem(vma); + +#ifndef CONFIG_PTE_MARKER_UFFD_WP + /* + * If user requested uffd-wp but not enabled pte markers for + * uffd-wp, then shmem & hugetlbfs are not supported but only + * anonymous. + */ + if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) + return false; +#endif + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || + vma_is_shmem(vma); +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); @@ -234,6 +268,56 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm, { } +static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ +static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_UFFD_WP); +#else + return false; +#endif +} + +static inline bool pte_marker_uffd_wp(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + swp_entry_t entry; + + if (!is_swap_pte(pte)) + return false; + + entry = pte_to_swp_entry(pte); + + return pte_marker_entry_uffd_wp(entry); +#else + return false; +#endif +} + +/* + * Returns true if this is a swap pte and was uffd-wp wr-protected in either + * forms (pte marker or a normal swap pte), false otherwise. + */ +static inline bool pte_swp_uffd_wp_any(pte_t pte) +{ +#ifdef CONFIG_PTE_MARKER_UFFD_WP + if (!is_swap_pte(pte)) + return false; + + if (pte_swp_uffd_wp(pte)) + return true; + + if (pte_marker_uffd_wp(pte)) + return true; +#endif + return false; +} + #endif /* _LINUX_USERFAULTFD_K_H */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 16a0a4fd000b..404024486fa5 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -133,6 +133,13 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSM_SWPIN_COPY, #endif #endif +#ifdef CONFIG_KSM + COW_KSM, +#endif +#ifdef CONFIG_ZSWAP + ZSWPIN, + ZSWPOUT, +#endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fec248ab1fec..32b35f21cb97 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -80,6 +80,13 @@ struct writeback_control { unsigned punt_to_cgroup:1; /* cgrp punting, see __REQ_CGROUP_PUNT */ + /* To enable batching of swap writes to non-block-device backends, + * "plug" can be set point to a 'struct swap_iocb *'. When all swap + * writes have been submitted, if with swap_iocb is not NULL, + * swap_write_unplug() should be called. + */ + struct swap_iocb **swap_plug; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 1e694fd239b9..d0337a41141c 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -374,7 +374,6 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_BUDDY, "free buddy page" ) \ EM ( MF_MSG_DAX, "dax page" ) \ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ - EM ( MF_MSG_DIFFERENT_PAGE_SIZE, "different page size" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) /* diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 290f07eb050a..9ae94ef3e270 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -1344,13 +1344,13 @@ TRACE_EVENT(alloc_extent_state, TP_STRUCT__entry( __field(const struct extent_state *, state) - __field(gfp_t, mask) + __field(unsigned long, mask) __field(const void*, ip) ), TP_fast_assign( __entry->state = state, - __entry->mask = mask, + __entry->mask = (__force unsigned long)mask, __entry->ip = (const void *)IP ), diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index c6d5d70dc7a5..3313eb83c117 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -162,13 +162,13 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages, TP_STRUCT__entry( __field(int, order) - __field(gfp_t, gfp_mask) + __field(unsigned long, gfp_mask) __field(int, prio) ), TP_fast_assign( __entry->order = order; - __entry->gfp_mask = gfp_mask; + __entry->gfp_mask = (__force unsigned long)gfp_mask; __entry->prio = prio; ), diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index ddc8c944f417..f76668305ac5 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -24,7 +24,7 @@ DECLARE_EVENT_CLASS(kmem_alloc, __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( @@ -32,7 +32,7 @@ DECLARE_EVENT_CLASS(kmem_alloc, __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s", @@ -75,7 +75,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) __field( int, node ) ), @@ -84,7 +84,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), @@ -208,14 +208,14 @@ TRACE_EVENT(mm_page_alloc, TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), @@ -229,20 +229,23 @@ TRACE_EVENT(mm_page_alloc, DECLARE_EVENT_CLASS(mm_page, - TP_PROTO(struct page *page, unsigned int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype, + int percpu_refill), - TP_ARGS(page, order, migratetype), + TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) + __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; + __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", @@ -250,14 +253,15 @@ DECLARE_EVENT_CLASS(mm_page, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, - __entry->order == 0) + __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, - TP_PROTO(struct page *page, unsigned int order, int migratetype), + TP_PROTO(struct page *page, unsigned int order, int migratetype, + int percpu_refill), - TP_ARGS(page, order, migratetype) + TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 6532119a6bf1..e87cb2b80ed3 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -13,49 +13,51 @@ * Thus most bits set go first. */ -#define __def_gfpflag_names \ - {(unsigned long)GFP_TRANSHUGE, "GFP_TRANSHUGE"}, \ - {(unsigned long)GFP_TRANSHUGE_LIGHT, "GFP_TRANSHUGE_LIGHT"}, \ - {(unsigned long)GFP_HIGHUSER_MOVABLE, "GFP_HIGHUSER_MOVABLE"},\ - {(unsigned long)GFP_HIGHUSER, "GFP_HIGHUSER"}, \ - {(unsigned long)GFP_USER, "GFP_USER"}, \ - {(unsigned long)GFP_KERNEL_ACCOUNT, "GFP_KERNEL_ACCOUNT"}, \ - {(unsigned long)GFP_KERNEL, "GFP_KERNEL"}, \ - {(unsigned long)GFP_NOFS, "GFP_NOFS"}, \ - {(unsigned long)GFP_ATOMIC, "GFP_ATOMIC"}, \ - {(unsigned long)GFP_NOIO, "GFP_NOIO"}, \ - {(unsigned long)GFP_NOWAIT, "GFP_NOWAIT"}, \ - {(unsigned long)GFP_DMA, "GFP_DMA"}, \ - {(unsigned long)__GFP_HIGHMEM, "__GFP_HIGHMEM"}, \ - {(unsigned long)GFP_DMA32, "GFP_DMA32"}, \ - {(unsigned long)__GFP_HIGH, "__GFP_HIGH"}, \ - {(unsigned long)__GFP_ATOMIC, "__GFP_ATOMIC"}, \ - {(unsigned long)__GFP_IO, "__GFP_IO"}, \ - {(unsigned long)__GFP_FS, "__GFP_FS"}, \ - {(unsigned long)__GFP_NOWARN, "__GFP_NOWARN"}, \ - {(unsigned long)__GFP_RETRY_MAYFAIL, "__GFP_RETRY_MAYFAIL"}, \ - {(unsigned long)__GFP_NOFAIL, "__GFP_NOFAIL"}, \ - {(unsigned long)__GFP_NORETRY, "__GFP_NORETRY"}, \ - {(unsigned long)__GFP_COMP, "__GFP_COMP"}, \ - {(unsigned long)__GFP_ZERO, "__GFP_ZERO"}, \ - {(unsigned long)__GFP_NOMEMALLOC, "__GFP_NOMEMALLOC"}, \ - {(unsigned long)__GFP_MEMALLOC, "__GFP_MEMALLOC"}, \ - {(unsigned long)__GFP_HARDWALL, "__GFP_HARDWALL"}, \ - {(unsigned long)__GFP_THISNODE, "__GFP_THISNODE"}, \ - {(unsigned long)__GFP_RECLAIMABLE, "__GFP_RECLAIMABLE"}, \ - {(unsigned long)__GFP_MOVABLE, "__GFP_MOVABLE"}, \ - {(unsigned long)__GFP_ACCOUNT, "__GFP_ACCOUNT"}, \ - {(unsigned long)__GFP_WRITE, "__GFP_WRITE"}, \ - {(unsigned long)__GFP_RECLAIM, "__GFP_RECLAIM"}, \ - {(unsigned long)__GFP_DIRECT_RECLAIM, "__GFP_DIRECT_RECLAIM"},\ - {(unsigned long)__GFP_KSWAPD_RECLAIM, "__GFP_KSWAPD_RECLAIM"},\ - {(unsigned long)__GFP_ZEROTAGS, "__GFP_ZEROTAGS"} \ +#define gfpflag_string(flag) {(__force unsigned long)flag, #flag} + +#define __def_gfpflag_names \ + gfpflag_string(GFP_TRANSHUGE), \ + gfpflag_string(GFP_TRANSHUGE_LIGHT), \ + gfpflag_string(GFP_HIGHUSER_MOVABLE), \ + gfpflag_string(GFP_HIGHUSER), \ + gfpflag_string(GFP_USER), \ + gfpflag_string(GFP_KERNEL_ACCOUNT), \ + gfpflag_string(GFP_KERNEL), \ + gfpflag_string(GFP_NOFS), \ + gfpflag_string(GFP_ATOMIC), \ + gfpflag_string(GFP_NOIO), \ + gfpflag_string(GFP_NOWAIT), \ + gfpflag_string(GFP_DMA), \ + gfpflag_string(__GFP_HIGHMEM), \ + gfpflag_string(GFP_DMA32), \ + gfpflag_string(__GFP_HIGH), \ + gfpflag_string(__GFP_ATOMIC), \ + gfpflag_string(__GFP_IO), \ + gfpflag_string(__GFP_FS), \ + gfpflag_string(__GFP_NOWARN), \ + gfpflag_string(__GFP_RETRY_MAYFAIL), \ + gfpflag_string(__GFP_NOFAIL), \ + gfpflag_string(__GFP_NORETRY), \ + gfpflag_string(__GFP_COMP), \ + gfpflag_string(__GFP_ZERO), \ + gfpflag_string(__GFP_NOMEMALLOC), \ + gfpflag_string(__GFP_MEMALLOC), \ + gfpflag_string(__GFP_HARDWALL), \ + gfpflag_string(__GFP_THISNODE), \ + gfpflag_string(__GFP_RECLAIMABLE), \ + gfpflag_string(__GFP_MOVABLE), \ + gfpflag_string(__GFP_ACCOUNT), \ + gfpflag_string(__GFP_WRITE), \ + gfpflag_string(__GFP_RECLAIM), \ + gfpflag_string(__GFP_DIRECT_RECLAIM), \ + gfpflag_string(__GFP_KSWAPD_RECLAIM), \ + gfpflag_string(__GFP_ZEROTAGS) #ifdef CONFIG_KASAN_HW_TAGS -#define __def_gfpflag_names_kasan , \ - {(unsigned long)__GFP_SKIP_ZERO, "__GFP_SKIP_ZERO"}, \ - {(unsigned long)__GFP_SKIP_KASAN_POISON, "__GFP_SKIP_KASAN_POISON"}, \ - {(unsigned long)__GFP_SKIP_KASAN_UNPOISON, "__GFP_SKIP_KASAN_UNPOISON"} +#define __def_gfpflag_names_kasan , \ + gfpflag_string(__GFP_SKIP_ZERO), \ + gfpflag_string(__GFP_SKIP_KASAN_POISON), \ + gfpflag_string(__GFP_SKIP_KASAN_UNPOISON) #else #define __def_gfpflag_names_kasan #endif diff --git a/include/trace/events/percpu.h b/include/trace/events/percpu.h index df112a64f6c9..5b8211ca8950 100644 --- a/include/trace/events/percpu.h +++ b/include/trace/events/percpu.h @@ -6,15 +6,20 @@ #define _TRACE_PERCPU_H #include <linux/tracepoint.h> +#include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, - TP_PROTO(bool reserved, bool is_atomic, size_t size, - size_t align, void *base_addr, int off, void __percpu *ptr), + TP_PROTO(unsigned long call_site, + bool reserved, bool is_atomic, size_t size, + size_t align, void *base_addr, int off, + void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), - TP_ARGS(reserved, is_atomic, size, align, base_addr, off, ptr), + TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, + ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( + __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) @@ -22,9 +27,11 @@ TRACE_EVENT(percpu_alloc_percpu, __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) + __field( size_t, bytes_alloc ) + __field( unsigned long, gfp_flags ) ), - TP_fast_assign( + __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; @@ -32,12 +39,16 @@ TRACE_EVENT(percpu_alloc_percpu, __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; + __entry->bytes_alloc = bytes_alloc; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), - TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p", + TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", + (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, - __entry->base_addr, __entry->off, __entry->ptr) + __entry->base_addr, __entry->off, __entry->ptr, + __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index de136dbd623a..d2123dd960d5 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -96,14 +96,14 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd, __field( int, nid ) __field( int, zid ) __field( int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->nid = nid; __entry->zid = zid; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", @@ -120,12 +120,12 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template, TP_STRUCT__entry( __field( int, order ) - __field( gfp_t, gfp_flags ) + __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("order=%d gfp_flags=%s", @@ -210,7 +210,7 @@ TRACE_EVENT(mm_shrink_slab_start, __field(void *, shrink) __field(int, nid) __field(long, nr_objects_to_shrink) - __field(gfp_t, gfp_flags) + __field(unsigned long, gfp_flags) __field(unsigned long, cache_items) __field(unsigned long long, delta) __field(unsigned long, total_scan) @@ -222,7 +222,7 @@ TRACE_EVENT(mm_shrink_slab_start, __entry->shrink = shr->scan_objects; __entry->nid = sc->nid; __entry->nr_objects_to_shrink = nr_objects_to_shrink; - __entry->gfp_flags = sc->gfp_mask; + __entry->gfp_flags = (__force unsigned long)sc->gfp_mask; __entry->cache_items = cache_items; __entry->delta = delta; __entry->total_scan = total_scan; @@ -297,7 +297,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __field(unsigned long, nr_scanned) __field(unsigned long, nr_skipped) __field(unsigned long, nr_taken) - __field(isolate_mode_t, isolate_mode) + __field(unsigned int, isolate_mode) __field(int, lru) ), @@ -308,7 +308,7 @@ TRACE_EVENT(mm_vmscan_lru_isolate, __entry->nr_scanned = nr_scanned; __entry->nr_skipped = nr_skipped; __entry->nr_taken = nr_taken; - __entry->isolate_mode = isolate_mode; + __entry->isolate_mode = (__force unsigned int)isolate_mode; __entry->lru = lru; ), @@ -446,13 +446,13 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin, TP_STRUCT__entry( __field(int, nid) __field(int, order) - __field(gfp_t, gfp_flags) + __field(unsigned long, gfp_flags) ), TP_fast_assign( __entry->nid = nid; __entry->order = order; - __entry->gfp_flags = gfp_flags; + __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("nid=%d order=%d gfp_flags=%s", diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index ef739054cb1c..7d32b1e797fb 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -33,7 +33,8 @@ UFFD_FEATURE_THREAD_ID | \ UFFD_FEATURE_MINOR_HUGETLBFS | \ UFFD_FEATURE_MINOR_SHMEM | \ - UFFD_FEATURE_EXACT_ADDRESS) + UFFD_FEATURE_EXACT_ADDRESS | \ + UFFD_FEATURE_WP_HUGETLBFS_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -47,7 +48,8 @@ #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ - (__u64)1 << _UFFDIO_CONTINUE) + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_WRITEPROTECT) /* * Valid ioctl command number range with this API is from 0x00 to @@ -194,6 +196,9 @@ struct uffdio_api { * 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. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -207,6 +212,7 @@ struct uffdio_api { #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) __u64 features; __u64 ioctls; diff --git a/init/Kconfig b/init/Kconfig index 0c80853762d9..9300cb6abea8 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -352,23 +352,6 @@ config DEFAULT_HOSTNAME but you may wish to use a different default here to make a minimal system more usable with less configuration. -# -# For some reason microblaze and nios2 hard code SWAP=n. Hopefully we can -# add proper SWAP support to them, in which case this can be remove. -# -config ARCH_NO_SWAP - bool - -config SWAP - bool "Support for paging of anonymous memory (swap)" - depends on MMU && BLOCK && !ARCH_NO_SWAP - default y - help - This option allows you to choose whether you want to have support - for so called swap devices or swap files in your kernel that are - used to provide more virtual memory than the actual RAM present - in your computer. If unsure say Y. - config SYSVIPC bool "System V IPC" help @@ -1666,16 +1649,6 @@ config ADVISE_SYSCALLS applications use these syscalls, you can disable this option to save space. -config HAVE_ARCH_USERFAULTFD_WP - bool - help - Arch has userfaultfd write protection support - -config HAVE_ARCH_USERFAULTFD_MINOR - bool - help - Arch has userfaultfd minor fault support - config MEMBARRIER bool "Enable membarrier() system call" if EXPERT default y @@ -1740,13 +1713,6 @@ config KALLSYMS_BASE_RELATIVE # syscall, maps, verifier -config USERFAULTFD - bool "Enable userfaultfd() system call" - depends on MMU - help - Enable the userfaultfd() system call that allows to intercept and - handle page faults in userland. - config ARCH_HAS_MEMBARRIER_CALLBACKS bool @@ -1893,112 +1859,6 @@ config COMPAT_BRK On non-ancient distros (post-2000 ones) N is usually a safe choice. -choice - prompt "Choose SLAB allocator" - default SLUB - help - This option allows to select a slab allocator. - -config SLAB - bool "SLAB" - depends on !PREEMPT_RT - select HAVE_HARDENED_USERCOPY_ALLOCATOR - help - The regular slab allocator that is established and known to work - well in all environments. It organizes cache hot objects in - per cpu and per node queues. - -config SLUB - bool "SLUB (Unqueued Allocator)" - select HAVE_HARDENED_USERCOPY_ALLOCATOR - help - SLUB is a slab allocator that minimizes cache line usage - instead of managing queues of cached objects (SLAB approach). - Per cpu caching is realized using slabs of objects instead - of queues of objects. SLUB can use memory efficiently - and has enhanced diagnostics. SLUB is the default choice for - a slab allocator. - -config SLOB - depends on EXPERT - bool "SLOB (Simple Allocator)" - depends on !PREEMPT_RT - help - SLOB replaces the stock allocator with a drastically simpler - allocator. SLOB is generally more space efficient but - does not perform as well on large systems. - -endchoice - -config SLAB_MERGE_DEFAULT - bool "Allow slab caches to be merged" - default y - depends on SLAB || SLUB - help - For reduced kernel memory fragmentation, slab caches can be - merged when they share the same size and other characteristics. - This carries a risk of kernel heap overflows being able to - overwrite objects from merged caches (and more easily control - cache layout), which makes such heap attacks easier to exploit - by attackers. By keeping caches unmerged, these kinds of exploits - can usually only damage objects in the same cache. To disable - merging at runtime, "slab_nomerge" can be passed on the kernel - command line. - -config SLAB_FREELIST_RANDOM - bool "Randomize slab freelist" - depends on SLAB || SLUB - help - Randomizes the freelist order used on creating new pages. This - security feature reduces the predictability of the kernel slab - allocator against heap overflows. - -config SLAB_FREELIST_HARDENED - bool "Harden slab freelist metadata" - depends on SLAB || SLUB - help - Many kernel heap attacks try to target slab cache metadata and - other infrastructure. This options makes minor performance - sacrifices to harden the kernel slab allocator against common - freelist exploit methods. Some slab implementations have more - sanity-checking than others. This option is most effective with - CONFIG_SLUB. - -config SHUFFLE_PAGE_ALLOCATOR - bool "Page allocator randomization" - default SLAB_FREELIST_RANDOM && ACPI_NUMA - help - Randomization of the page allocator improves the average - utilization of a direct-mapped memory-side-cache. See section - 5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI - 6.2a specification for an example of how a platform advertises - the presence of a memory-side-cache. There are also incidental - security benefits as it reduces the predictability of page - allocations to compliment SLAB_FREELIST_RANDOM, but the - default granularity of shuffling on the "MAX_ORDER - 1" i.e, - 10th order of pages is selected based on cache utilization - benefits on x86. - - While the randomization improves cache utilization it may - negatively impact workloads on platforms without a cache. For - this reason, by default, the randomization is enabled only - after runtime detection of a direct-mapped memory-side-cache. - Otherwise, the randomization may be force enabled with the - 'page_alloc.shuffle' kernel command line parameter. - - Say Y if unsure. - -config SLUB_CPU_PARTIAL - default y - depends on SLUB && SMP - bool "SLUB per cpu partial cache" - help - Per cpu partial caches accelerate objects allocation and freeing - that is local to a processor at the price of more indeterminism - in the latency of the free. On overflow these caches will be cleared - which requires the taking of locks that may cause latency spikes. - Typically one would choose no for a realtime system. - config MMAP_ALLOW_UNINITIALIZED bool "Allow mmapped anonymous memory to be uninitialized" depends on EXPERT && !MMU diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 6b12f06ee18c..4ea227c9c1ad 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -4,6 +4,7 @@ #ifndef __BPF_LRU_LIST_H_ #define __BPF_LRU_LIST_H_ +#include <linux/cache.h> #include <linux/list.h> #include <linux/spinlock_types.h> diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index a9bc3c98f76a..2eaa327f8158 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -180,7 +180,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); - page_add_new_anon_rmap(new_page, vma, addr, false); + page_add_new_anon_rmap(new_page, vma, addr); lru_cache_add_inactive_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/kernel/fork.c b/kernel/fork.c index 254ab63c1106..124829ed0163 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -612,9 +612,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, retval = ksm_fork(mm, oldmm); if (retval) goto out; - retval = khugepaged_fork(mm, oldmm); - if (retval) - goto out; + khugepaged_fork(mm, oldmm); prev = NULL; for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 1f3e620188a2..f0973da583e0 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only + # This config refers to the generic KASAN mode. config HAVE_ARCH_KASAN bool @@ -15,9 +16,8 @@ config HAVE_ARCH_KASAN_VMALLOC config ARCH_DISABLE_KASAN_INLINE bool help - An architecture might not support inline instrumentation. - When this option is selected, inline and stack instrumentation are - disabled. + Disables both inline and stack instrumentation. Selected by + architectures that do not support these instrumentation types. config CC_HAS_KASAN_GENERIC def_bool $(cc-option, -fsanitize=kernel-address) @@ -26,13 +26,13 @@ config CC_HAS_KASAN_SW_TAGS def_bool $(cc-option, -fsanitize=kernel-hwaddress) # This option is only required for software KASAN modes. -# Old GCC versions don't have proper support for no_sanitize_address. +# Old GCC versions do not have proper support for no_sanitize_address. # See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=89124 for details. config CC_HAS_WORKING_NOSANITIZE_ADDRESS def_bool !CC_IS_GCC || GCC_VERSION >= 80300 menuconfig KASAN - bool "KASAN: runtime memory debugger" + bool "KASAN: dynamic memory safety error detector" depends on (((HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC) || \ (HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS)) && \ CC_HAS_WORKING_NOSANITIZE_ADDRESS) || \ @@ -40,10 +40,13 @@ menuconfig KASAN depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB) select STACKDEPOT_ALWAYS_INIT help - Enables KASAN (KernelAddressSANitizer) - runtime memory debugger, - designed to find out-of-bounds accesses and use-after-free bugs. + Enables KASAN (Kernel Address Sanitizer) - a dynamic memory safety + error detector designed to find out-of-bounds and use-after-free bugs. + See Documentation/dev-tools/kasan.rst for details. + For better error reports, also enable CONFIG_STACKTRACE. + if KASAN choice @@ -51,75 +54,71 @@ choice default KASAN_GENERIC help KASAN has three modes: - 1. generic KASAN (similar to userspace ASan, - x86_64/arm64/xtensa, enabled with CONFIG_KASAN_GENERIC), - 2. software tag-based KASAN (arm64 only, based on software - memory tagging (similar to userspace HWASan), enabled with - CONFIG_KASAN_SW_TAGS), and - 3. hardware tag-based KASAN (arm64 only, based on hardware - memory tagging, enabled with CONFIG_KASAN_HW_TAGS). - All KASAN modes are strictly debugging features. + 1. Generic KASAN (supported by many architectures, enabled with + CONFIG_KASAN_GENERIC, similar to userspace ASan), + 2. Software Tag-Based KASAN (arm64 only, based on software memory + tagging, enabled with CONFIG_KASAN_SW_TAGS, similar to userspace + HWASan), and + 3. Hardware Tag-Based KASAN (arm64 only, based on hardware memory + tagging, enabled with CONFIG_KASAN_HW_TAGS). - For better error reports enable CONFIG_STACKTRACE. + See Documentation/dev-tools/kasan.rst for details about each mode. config KASAN_GENERIC - bool "Generic mode" + bool "Generic KASAN" depends on HAVE_ARCH_KASAN && CC_HAS_KASAN_GENERIC depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS select SLUB_DEBUG if SLUB select CONSTRUCTORS help - Enables generic KASAN mode. + Enables Generic KASAN. - This mode is supported in both GCC and Clang. With GCC it requires - version 8.3.0 or later. Any supported Clang version is compatible, - but detection of out-of-bounds accesses for global variables is - supported only since Clang 11. + Requires GCC 8.3.0+ or Clang. - This mode consumes about 1/8th of available memory at kernel start - and introduces an overhead of ~x1.5 for the rest of the allocations. + Consumes about 1/8th of available memory at kernel start and adds an + overhead of ~50% for dynamic allocations. The performance slowdown is ~x3. - Currently CONFIG_KASAN_GENERIC doesn't work with CONFIG_DEBUG_SLAB - (the resulting kernel does not boot). + (Incompatible with CONFIG_DEBUG_SLAB: the kernel does not boot.) config KASAN_SW_TAGS - bool "Software tag-based mode" + bool "Software Tag-Based KASAN" depends on HAVE_ARCH_KASAN_SW_TAGS && CC_HAS_KASAN_SW_TAGS depends on CC_HAS_WORKING_NOSANITIZE_ADDRESS select SLUB_DEBUG if SLUB select CONSTRUCTORS help - Enables software tag-based KASAN mode. + Enables Software Tag-Based KASAN. - This mode require software memory tagging support in the form of - HWASan-like compiler instrumentation. + Requires GCC 11+ or Clang. - Currently this mode is only implemented for arm64 CPUs and relies on - Top Byte Ignore. This mode requires Clang. + Supported only on arm64 CPUs and relies on Top Byte Ignore. - This mode consumes about 1/16th of available memory at kernel start - and introduces an overhead of ~20% for the rest of the allocations. - This mode may potentially introduce problems relating to pointer - casting and comparison, as it embeds tags into the top byte of each - pointer. + Consumes about 1/16th of available memory at kernel start and + add an overhead of ~20% for dynamic allocations. - Currently CONFIG_KASAN_SW_TAGS doesn't work with CONFIG_DEBUG_SLAB - (the resulting kernel does not boot). + May potentially introduce problems related to pointer casting and + comparison, as it embeds a tag into the top byte of each pointer. + + (Incompatible with CONFIG_DEBUG_SLAB: the kernel does not boot.) config KASAN_HW_TAGS - bool "Hardware tag-based mode" + bool "Hardware Tag-Based KASAN" depends on HAVE_ARCH_KASAN_HW_TAGS depends on SLUB help - Enables hardware tag-based KASAN mode. + Enables Hardware Tag-Based KASAN. + + Requires GCC 10+ or Clang 12+. - This mode requires hardware memory tagging support, and can be used - by any architecture that provides it. + Supported only on arm64 CPUs starting from ARMv8.5 and relies on + Memory Tagging Extension and Top Byte Ignore. - Currently this mode is only implemented for arm64 CPUs starting from - ARMv8.5 and relies on Memory Tagging Extension and Top Byte Ignore. + Consumes about 1/32nd of available memory. + + May potentially introduce problems related to pointer casting and + comparison, as it embeds a tag into the top byte of each pointer. endchoice @@ -131,83 +130,80 @@ choice config KASAN_OUTLINE bool "Outline instrumentation" help - Before every memory access compiler insert function call - __asan_load*/__asan_store*. These functions performs check - of shadow memory. This is slower than inline instrumentation, - however it doesn't bloat size of kernel's .text section so - much as inline does. + Makes the compiler insert function calls that check whether the memory + is accessible before each memory access. Slower than KASAN_INLINE, but + does not bloat the size of the kernel's .text section so much. config KASAN_INLINE bool "Inline instrumentation" depends on !ARCH_DISABLE_KASAN_INLINE help - Compiler directly inserts code checking shadow memory before - memory accesses. This is faster than outline (in some workloads - it gives about x2 boost over outline instrumentation), but - make kernel's .text size much bigger. + Makes the compiler directly insert memory accessibility checks before + each memory access. Faster than KASAN_OUTLINE (gives ~x2 boost for + some workloads), but makes the kernel's .text size much bigger. endchoice config KASAN_STACK - bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST + bool "Stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST depends on KASAN_GENERIC || KASAN_SW_TAGS depends on !ARCH_DISABLE_KASAN_INLINE default y if CC_IS_GCC help - The LLVM stack address sanitizer has a know problem that - causes excessive stack usage in a lot of functions, see - https://bugs.llvm.org/show_bug.cgi?id=38809 - Disabling asan-stack makes it safe to run kernels build - with clang-8 with KASAN enabled, though it loses some of - the functionality. - This feature is always disabled when compile-testing with clang - to avoid cluttering the output in stack overflow warnings, - but clang users can still enable it for builds without - CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe - to use and enabled by default. - If the architecture disables inline instrumentation, stack - instrumentation is also disabled as it adds inline-style - instrumentation that is run unconditionally. + Disables stack instrumentation and thus KASAN's ability to detect + out-of-bounds bugs in stack variables. + + With Clang, stack instrumentation has a problem that causes excessive + stack usage, see https://bugs.llvm.org/show_bug.cgi?id=38809. Thus, + with Clang, this option is deemed unsafe. + + This option is always disabled when compile-testing with Clang to + avoid cluttering the log with stack overflow warnings. + + With GCC, enabling stack instrumentation is assumed to be safe. + + If the architecture disables inline instrumentation via + ARCH_DISABLE_KASAN_INLINE, stack instrumentation gets disabled + as well, as it adds inline-style instrumentation that is run + unconditionally. config KASAN_TAGS_IDENTIFY - bool "Enable memory corruption identification" + bool "Memory corruption type identification" depends on KASAN_SW_TAGS || KASAN_HW_TAGS help - This option enables best-effort identification of bug type - (use-after-free or out-of-bounds) at the cost of increased - memory consumption. + Enables best-effort identification of the bug types (use-after-free + or out-of-bounds) at the cost of increased memory consumption. + Only applicable for the tag-based KASAN modes. config KASAN_VMALLOC bool "Check accesses to vmalloc allocations" depends on HAVE_ARCH_KASAN_VMALLOC help - This mode makes KASAN check accesses to vmalloc allocations for - validity. + Makes KASAN check the validity of accesses to vmalloc allocations. - With software KASAN modes, checking is done for all types of vmalloc - allocations. Enabling this option leads to higher memory usage. + With software KASAN modes, all types vmalloc allocations are + checked. Enabling this option leads to higher memory usage. - With hardware tag-based KASAN, only VM_ALLOC mappings are checked. - There is no additional memory usage. + With Hardware Tag-Based KASAN, only non-executable VM_ALLOC mappings + are checked. There is no additional memory usage. config KASAN_KUNIT_TEST tristate "KUnit-compatible tests of KASAN bug detection capabilities" if !KUNIT_ALL_TESTS depends on KASAN && KUNIT default KUNIT_ALL_TESTS help - This is a KUnit test suite doing various nasty things like - out of bounds and use after free accesses. It is useful for testing - kernel debugging features like KASAN. + A KUnit-based KASAN test suite. Triggers different kinds of + out-of-bounds and use-after-free accesses. Useful for testing whether + KASAN can detect certain bug types. For more information on KUnit and unit tests in general, please refer - to the KUnit documentation in Documentation/dev-tools/kunit. + to the KUnit documentation in Documentation/dev-tools/kunit/. config KASAN_MODULE_TEST tristate "KUnit-incompatible tests of KASAN bug detection capabilities" depends on m && KASAN && !KASAN_HW_TAGS help - This is a part of the KASAN test suite that is incompatible with - KUnit. Currently includes tests that do bad copy_from/to_user - accesses. + A part of the KASAN test suite that is not integrated with KUnit. + Incompatible with Hardware Tag-Based KASAN. endif # KASAN diff --git a/lib/fault-inject.c b/lib/fault-inject.c index ce12621b4275..423784d9c058 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -41,6 +41,9 @@ EXPORT_SYMBOL_GPL(setup_fault_attr); static void fail_dump(struct fault_attr *attr) { + if (attr->no_warn) + return; + if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) { printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n" "name %pd, interval %lu, probability %lu, " diff --git a/lib/kstrtox.c b/lib/kstrtox.c index 886510d248e5..08c14019841a 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -340,7 +340,7 @@ EXPORT_SYMBOL(kstrtos8); * @s: input string * @res: result * - * This routine returns 0 iff the first character is one of 'Yy1Nn0', or + * This routine returns 0 iff the first character is one of 'YyTt1NnFf0', or * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value * pointed to by res is updated upon finding a match. */ @@ -353,11 +353,15 @@ int kstrtobool(const char *s, bool *res) switch (s[0]) { case 'y': case 'Y': + case 't': + case 'T': case '1': *res = true; return 0; case 'n': case 'N': + case 'f': + case 'F': case '0': *res = false; return 0; diff --git a/mm/Kconfig b/mm/Kconfig index 034d87953600..905c205e14f3 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -2,6 +2,311 @@ menu "Memory Management options" +# +# For some reason microblaze and nios2 hard code SWAP=n. Hopefully we can +# add proper SWAP support to them, in which case this can be remove. +# +config ARCH_NO_SWAP + bool + +config ZPOOL + bool + +menuconfig SWAP + bool "Support for paging of anonymous memory (swap)" + depends on MMU && BLOCK && !ARCH_NO_SWAP + default y + help + This option allows you to choose whether you want to have support + for so called swap devices or swap files in your kernel that are + used to provide more virtual memory than the actual RAM present + in your computer. If unsure say Y. + +config ZSWAP + bool "Compressed cache for swap pages (EXPERIMENTAL)" + depends on SWAP + select FRONTSWAP + select CRYPTO + select ZPOOL + help + A lightweight compressed cache for swap pages. It takes + pages that are in the process of being swapped out and attempts to + compress them into a dynamically allocated RAM-based memory pool. + This can result in a significant I/O reduction on swap device and, + in the case where decompressing from RAM is faster that swap device + reads, can also improve workload performance. + + This is marked experimental because it is a new feature (as of + v3.11) that interacts heavily with memory reclaim. While these + interactions don't cause any known issues on simple memory setups, + they have not be fully explored on the large set of potential + configurations and workloads that exist. + +config ZSWAP_DEFAULT_ON + bool "Enable the compressed cache for swap pages by default" + depends on ZSWAP + help + If selected, the compressed cache for swap pages will be enabled + at boot, otherwise it will be disabled. + + The selection made here can be overridden by using the kernel + command line 'zswap.enabled=' option. + +choice + prompt "Default compressor" + depends on ZSWAP + default ZSWAP_COMPRESSOR_DEFAULT_LZO + help + Selects the default compression algorithm for the compressed cache + for swap pages. + + For an overview what kind of performance can be expected from + a particular compression algorithm please refer to the benchmarks + available at the following LWN page: + https://lwn.net/Articles/751795/ + + If in doubt, select 'LZO'. + + The selection made here can be overridden by using the kernel + command line 'zswap.compressor=' option. + +config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE + bool "Deflate" + select CRYPTO_DEFLATE + help + Use the Deflate algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_LZO + bool "LZO" + select CRYPTO_LZO + help + Use the LZO algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_842 + bool "842" + select CRYPTO_842 + help + Use the 842 algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_LZ4 + bool "LZ4" + select CRYPTO_LZ4 + help + Use the LZ4 algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC + bool "LZ4HC" + select CRYPTO_LZ4HC + help + Use the LZ4HC algorithm as the default compression algorithm. + +config ZSWAP_COMPRESSOR_DEFAULT_ZSTD + bool "zstd" + select CRYPTO_ZSTD + help + Use the zstd algorithm as the default compression algorithm. +endchoice + +config ZSWAP_COMPRESSOR_DEFAULT + string + depends on ZSWAP + default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE + default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO + default "842" if ZSWAP_COMPRESSOR_DEFAULT_842 + default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4 + default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC + default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD + default "" + +choice + prompt "Default allocator" + depends on ZSWAP + default ZSWAP_ZPOOL_DEFAULT_ZBUD + help + Selects the default allocator for the compressed cache for + swap pages. + The default is 'zbud' for compatibility, however please do + read the description of each of the allocators below before + making a right choice. + + The selection made here can be overridden by using the kernel + command line 'zswap.zpool=' option. + +config ZSWAP_ZPOOL_DEFAULT_ZBUD + bool "zbud" + select ZBUD + help + Use the zbud allocator as the default allocator. + +config ZSWAP_ZPOOL_DEFAULT_Z3FOLD + bool "z3fold" + select Z3FOLD + help + Use the z3fold allocator as the default allocator. + +config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC + bool "zsmalloc" + select ZSMALLOC + help + Use the zsmalloc allocator as the default allocator. +endchoice + +config ZSWAP_ZPOOL_DEFAULT + string + depends on ZSWAP + default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD + default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD + default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC + default "" + +config ZBUD + tristate "2:1 compression allocator (zbud)" + depends on ZSWAP + help + A special purpose allocator for storing compressed pages. + It is designed to store up to two compressed pages per physical + page. While this design limits storage density, it has simple and + deterministic reclaim properties that make it preferable to a higher + density approach when reclaim will be used. + +config Z3FOLD + tristate "3:1 compression allocator (z3fold)" + depends on ZSWAP + help + A special purpose allocator for storing compressed pages. + It is designed to store up to three compressed pages per physical + page. It is a ZBUD derivative so the simplicity and determinism are + still there. + +config ZSMALLOC + tristate + prompt "N:1 compression allocator (zsmalloc)" if ZSWAP + depends on MMU + help + zsmalloc is a slab-based memory allocator designed to store + pages of various compression levels efficiently. It achieves + the highest storage density with the least amount of fragmentation. + +config ZSMALLOC_STAT + bool "Export zsmalloc statistics" + depends on ZSMALLOC + select DEBUG_FS + help + This option enables code in the zsmalloc to collect various + statistics about what's happening in zsmalloc and exports that + information to userspace via debugfs. + If unsure, say N. + +menu "SLAB allocator options" + +choice + prompt "Choose SLAB allocator" + default SLUB + help + This option allows to select a slab allocator. + +config SLAB + bool "SLAB" + depends on !PREEMPT_RT + select HAVE_HARDENED_USERCOPY_ALLOCATOR + help + The regular slab allocator that is established and known to work + well in all environments. It organizes cache hot objects in + per cpu and per node queues. + +config SLUB + bool "SLUB (Unqueued Allocator)" + select HAVE_HARDENED_USERCOPY_ALLOCATOR + help + SLUB is a slab allocator that minimizes cache line usage + instead of managing queues of cached objects (SLAB approach). + Per cpu caching is realized using slabs of objects instead + of queues of objects. SLUB can use memory efficiently + and has enhanced diagnostics. SLUB is the default choice for + a slab allocator. + +config SLOB + depends on EXPERT + bool "SLOB (Simple Allocator)" + depends on !PREEMPT_RT + help + SLOB replaces the stock allocator with a drastically simpler + allocator. SLOB is generally more space efficient but + does not perform as well on large systems. + +endchoice + +config SLAB_MERGE_DEFAULT + bool "Allow slab caches to be merged" + default y + depends on SLAB || SLUB + help + For reduced kernel memory fragmentation, slab caches can be + merged when they share the same size and other characteristics. + This carries a risk of kernel heap overflows being able to + overwrite objects from merged caches (and more easily control + cache layout), which makes such heap attacks easier to exploit + by attackers. By keeping caches unmerged, these kinds of exploits + can usually only damage objects in the same cache. To disable + merging at runtime, "slab_nomerge" can be passed on the kernel + command line. + +config SLAB_FREELIST_RANDOM + bool "Randomize slab freelist" + depends on SLAB || SLUB + help + Randomizes the freelist order used on creating new pages. This + security feature reduces the predictability of the kernel slab + allocator against heap overflows. + +config SLAB_FREELIST_HARDENED + bool "Harden slab freelist metadata" + depends on SLAB || SLUB + help + Many kernel heap attacks try to target slab cache metadata and + other infrastructure. This options makes minor performance + sacrifices to harden the kernel slab allocator against common + freelist exploit methods. Some slab implementations have more + sanity-checking than others. This option is most effective with + CONFIG_SLUB. + +config SLUB_CPU_PARTIAL + default y + depends on SLUB && SMP + bool "SLUB per cpu partial cache" + help + Per cpu partial caches accelerate objects allocation and freeing + that is local to a processor at the price of more indeterminism + in the latency of the free. On overflow these caches will be cleared + which requires the taking of locks that may cause latency spikes. + Typically one would choose no for a realtime system. + +endmenu # SLAB allocator options + +config SHUFFLE_PAGE_ALLOCATOR + bool "Page allocator randomization" + default SLAB_FREELIST_RANDOM && ACPI_NUMA + help + Randomization of the page allocator improves the average + utilization of a direct-mapped memory-side-cache. See section + 5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI + 6.2a specification for an example of how a platform advertises + the presence of a memory-side-cache. There are also incidental + security benefits as it reduces the predictability of page + allocations to compliment SLAB_FREELIST_RANDOM, but the + default granularity of shuffling on the "MAX_ORDER - 1" i.e, + 10th order of pages is selected based on cache utilization + benefits on x86. + + While the randomization improves cache utilization it may + negatively impact workloads on platforms without a cache. For + this reason, by default, the randomization is enabled only + after runtime detection of a direct-mapped memory-side-cache. + Otherwise, the randomization may be force enabled with the + 'page_alloc.shuffle' kernel command line parameter. + + Say Y if unsure. + config SELECT_MEMORY_MODEL def_bool y depends on ARCH_SELECT_MEMORY_MODEL @@ -126,15 +431,20 @@ config HAVE_BOOTMEM_INFO_NODE config ARCH_ENABLE_MEMORY_HOTPLUG bool +config ARCH_ENABLE_MEMORY_HOTREMOVE + bool + # eventually, we can have this option just 'select SPARSEMEM' -config MEMORY_HOTPLUG - bool "Allow for memory hot-add" +menuconfig MEMORY_HOTPLUG + bool "Memory hotplug" select MEMORY_ISOLATION depends on SPARSEMEM depends on ARCH_ENABLE_MEMORY_HOTPLUG depends on 64BIT select NUMA_KEEP_MEMINFO if NUMA +if MEMORY_HOTPLUG + config MEMORY_HOTPLUG_DEFAULT_ONLINE bool "Online the newly added memory blocks by default" depends on MEMORY_HOTPLUG @@ -150,9 +460,6 @@ config MEMORY_HOTPLUG_DEFAULT_ONLINE Say N here if you want the default policy to keep all hot-plugged memory blocks in 'offline' state. -config ARCH_ENABLE_MEMORY_HOTREMOVE - bool - config MEMORY_HOTREMOVE bool "Allow for memory hot remove" select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) @@ -164,6 +471,8 @@ config MHP_MEMMAP_ON_MEMORY depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE +endif # MEMORY_HOTPLUG + # Heavily threaded applications may benefit from splitting the mm-wide # page_table_lock, so that faults on different parts of the user address # space can be handled with less contention: split it at this NR_CPUS. @@ -378,7 +687,13 @@ config NOMMU_INITIAL_TRIM_EXCESS See Documentation/admin-guide/mm/nommu-mmap.rst for more information. -config TRANSPARENT_HUGEPAGE +config ARCH_WANT_GENERAL_HUGETLB + bool + +config ARCH_WANTS_THP_SWAP + def_bool n + +menuconfig TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT select COMPACTION @@ -393,6 +708,8 @@ config TRANSPARENT_HUGEPAGE If memory constrained on embedded, you may want to say N. +if TRANSPARENT_HUGEPAGE + choice prompt "Transparent Hugepage Support sysfs defaults" depends on TRANSPARENT_HUGEPAGE @@ -417,12 +734,6 @@ choice benefit. endchoice -config ARCH_WANT_GENERAL_HUGETLB - bool - -config ARCH_WANTS_THP_SWAP - def_bool n - config THP_SWAP def_bool y depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP @@ -433,6 +744,19 @@ config THP_SWAP For selection by architectures with reasonable THP sizes. +config READ_ONLY_THP_FOR_FS + bool "Read-only THP for filesystems (EXPERIMENTAL)" + depends on TRANSPARENT_HUGEPAGE && SHMEM + + help + Allow khugepaged to put read-only file-backed pages in THP. + + This is marked experimental because it is a new feature. Write + support of file THPs will be developed in the next few release + cycles. + +endif # TRANSPARENT_HUGEPAGE + # # UP and nommu archs use km based percpu allocator # @@ -517,188 +841,6 @@ config MEM_SOFT_DIRTY See Documentation/admin-guide/mm/soft-dirty.rst for more details. -config ZSWAP - bool "Compressed cache for swap pages (EXPERIMENTAL)" - depends on SWAP && CRYPTO=y - select FRONTSWAP - select ZPOOL - help - A lightweight compressed cache for swap pages. It takes - pages that are in the process of being swapped out and attempts to - compress them into a dynamically allocated RAM-based memory pool. - This can result in a significant I/O reduction on swap device and, - in the case where decompressing from RAM is faster that swap device - reads, can also improve workload performance. - - This is marked experimental because it is a new feature (as of - v3.11) that interacts heavily with memory reclaim. While these - interactions don't cause any known issues on simple memory setups, - they have not be fully explored on the large set of potential - configurations and workloads that exist. - -choice - prompt "Compressed cache for swap pages default compressor" - depends on ZSWAP - default ZSWAP_COMPRESSOR_DEFAULT_LZO - help - Selects the default compression algorithm for the compressed cache - for swap pages. - - For an overview what kind of performance can be expected from - a particular compression algorithm please refer to the benchmarks - available at the following LWN page: - https://lwn.net/Articles/751795/ - - If in doubt, select 'LZO'. - - The selection made here can be overridden by using the kernel - command line 'zswap.compressor=' option. - -config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE - bool "Deflate" - select CRYPTO_DEFLATE - help - Use the Deflate algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_LZO - bool "LZO" - select CRYPTO_LZO - help - Use the LZO algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_842 - bool "842" - select CRYPTO_842 - help - Use the 842 algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_LZ4 - bool "LZ4" - select CRYPTO_LZ4 - help - Use the LZ4 algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC - bool "LZ4HC" - select CRYPTO_LZ4HC - help - Use the LZ4HC algorithm as the default compression algorithm. - -config ZSWAP_COMPRESSOR_DEFAULT_ZSTD - bool "zstd" - select CRYPTO_ZSTD - help - Use the zstd algorithm as the default compression algorithm. -endchoice - -config ZSWAP_COMPRESSOR_DEFAULT - string - depends on ZSWAP - default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE - default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO - default "842" if ZSWAP_COMPRESSOR_DEFAULT_842 - default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4 - default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC - default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD - default "" - -choice - prompt "Compressed cache for swap pages default allocator" - depends on ZSWAP - default ZSWAP_ZPOOL_DEFAULT_ZBUD - help - Selects the default allocator for the compressed cache for - swap pages. - The default is 'zbud' for compatibility, however please do - read the description of each of the allocators below before - making a right choice. - - The selection made here can be overridden by using the kernel - command line 'zswap.zpool=' option. - -config ZSWAP_ZPOOL_DEFAULT_ZBUD - bool "zbud" - select ZBUD - help - Use the zbud allocator as the default allocator. - -config ZSWAP_ZPOOL_DEFAULT_Z3FOLD - bool "z3fold" - select Z3FOLD - help - Use the z3fold allocator as the default allocator. - -config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC - bool "zsmalloc" - select ZSMALLOC - help - Use the zsmalloc allocator as the default allocator. -endchoice - -config ZSWAP_ZPOOL_DEFAULT - string - depends on ZSWAP - default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD - default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD - default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC - default "" - -config ZSWAP_DEFAULT_ON - bool "Enable the compressed cache for swap pages by default" - depends on ZSWAP - help - If selected, the compressed cache for swap pages will be enabled - at boot, otherwise it will be disabled. - - The selection made here can be overridden by using the kernel - command line 'zswap.enabled=' option. - -config ZPOOL - tristate "Common API for compressed memory storage" - help - Compressed memory storage API. This allows using either zbud or - zsmalloc. - -config ZBUD - tristate "Low (Up to 2x) density storage for compressed pages" - depends on ZPOOL - help - A special purpose allocator for storing compressed pages. - It is designed to store up to two compressed pages per physical - page. While this design limits storage density, it has simple and - deterministic reclaim properties that make it preferable to a higher - density approach when reclaim will be used. - -config Z3FOLD - tristate "Up to 3x density storage for compressed pages" - depends on ZPOOL - help - A special purpose allocator for storing compressed pages. - It is designed to store up to three compressed pages per physical - page. It is a ZBUD derivative so the simplicity and determinism are - still there. - -config ZSMALLOC - tristate "Memory allocator for compressed pages" - depends on MMU - help - zsmalloc is a slab-based memory allocator designed to store - compressed RAM pages. zsmalloc uses virtual memory mapping - in order to reduce fragmentation. However, this results in a - non-standard allocator interface where a handle, not a pointer, is - returned by an alloc(). This handle must be mapped in order to - access the allocated space. - -config ZSMALLOC_STAT - bool "Export zsmalloc statistics" - depends on ZSMALLOC - select DEBUG_FS - help - This option enables code in the zsmalloc to collect various - statistics about what's happening in zsmalloc and exports that - information to userspace via debugfs. - If unsure, say N. - config GENERIC_EARLY_IOREMAP bool @@ -762,7 +904,7 @@ config ARCH_HAS_CURRENT_STACK_POINTER register alias named "current_stack_pointer", this config can be selected. -config ARCH_HAS_FILTER_PGPROT +config ARCH_HAS_VM_GET_PAGE_PROT bool config ARCH_HAS_PTE_DEVMAP @@ -855,17 +997,6 @@ comment "GUP_TEST needs to have DEBUG_FS enabled" config GUP_GET_PTE_LOW_HIGH bool -config READ_ONLY_THP_FOR_FS - bool "Read-only THP for filesystems (EXPERIMENTAL)" - depends on TRANSPARENT_HUGEPAGE && SHMEM - - help - Allow khugepaged to put read-only file-backed pages in THP. - - This is marked experimental because it is a new feature. Write - support of file THPs will be developed in the next few release - cycles. - config ARCH_HAS_PTE_SPECIAL bool @@ -909,6 +1040,40 @@ config ANON_VMA_NAME area from being merged with adjacent virtual memory areas due to the difference in their name. +config USERFAULTFD + bool "Enable userfaultfd() system call" + depends on MMU + help + Enable the userfaultfd() system call that allows to intercept and + handle page faults in userland. + +config HAVE_ARCH_USERFAULTFD_WP + bool + help + Arch has userfaultfd write protection support + +config HAVE_ARCH_USERFAULTFD_MINOR + bool + help + Arch has userfaultfd minor fault support + +config PTE_MARKER + bool + + help + Allows to create marker PTEs for file-backed memory. + +config PTE_MARKER_UFFD_WP + bool "Userfaultfd write protection support for shmem/hugetlbfs" + default y + depends on HAVE_ARCH_USERFAULTFD_WP + select PTE_MARKER + + help + Allows to create marker PTEs for userfaultfd write protection + purposes. It is required to enable userfaultfd write protection on + file-backed memory types like shmem and hugetlbfs. + source "mm/damon/Kconfig" endmenu diff --git a/mm/Makefile b/mm/Makefile index 4cc13f3179a5..6f9ffa968a1a 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -77,7 +77,7 @@ obj-$(CONFIG_FRONTSWAP) += frontswap.o obj-$(CONFIG_ZSWAP) += zswap.o obj-$(CONFIG_HAS_DMA) += dmapool.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o -obj-$(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP) += hugetlb_vmemmap.o +obj-$(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP) += hugetlb_vmemmap.o obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o diff --git a/mm/compaction.c b/mm/compaction.c index fe915db6149b..1f89b969c12b 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -317,7 +317,6 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, } page += (1 << PAGE_ALLOC_COSTLY_ORDER); - pfn += (1 << PAGE_ALLOC_COSTLY_ORDER); } while (page <= end_page); return false; @@ -514,15 +513,12 @@ static bool compact_lock_irqsave(spinlock_t *lock, unsigned long *flags, * very heavily contended. The lock should be periodically unlocked to avoid * having disabled IRQs for a long time, even when there is nobody waiting on * the lock. It might also be that allowing the IRQs will result in - * need_resched() becoming true. If scheduling is needed, async compaction - * aborts. Sync compaction schedules. + * need_resched() becoming true. If scheduling is needed, compaction schedules. * Either compaction type will also abort if a fatal signal is pending. * In either case if the lock was locked, it is dropped and not regained. * - * Returns true if compaction should abort due to fatal signal pending, or - * async compaction due to need_resched() - * Returns false when compaction can continue (sync compaction might have - * scheduled) + * Returns true if compaction should abort due to fatal signal pending. + * Returns false when compaction can continue. */ static bool compact_unlock_should_abort(spinlock_t *lock, unsigned long flags, bool *locked, struct compact_control *cc) @@ -575,9 +571,9 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, /* * Periodically drop the lock (if held) regardless of its * contention, to give chance to IRQs. Abort if fatal signal - * pending or async compaction detects need_resched() + * pending. */ - if (!(blockpfn % SWAP_CLUSTER_MAX) + if (!(blockpfn % COMPACT_CLUSTER_MAX) && compact_unlock_should_abort(&cc->zone->lock, flags, &locked, cc)) break; @@ -603,13 +599,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (!PageBuddy(page)) goto isolate_fail; - /* - * If we already hold the lock, we can skip some rechecking. - * Note that if we hold the lock now, checked_pageblock was - * already set in some previous iteration (or strict is true), - * so it is correct to skip the suitable migration target - * recheck as well. - */ + /* If we already hold the lock, we can skip some rechecking. */ if (!locked) { locked = compact_lock_irqsave(&cc->zone->lock, &flags, cc); @@ -872,7 +862,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * contention, to give chance to IRQs. Abort completely if * a fatal signal is pending. */ - if (!(low_pfn % SWAP_CLUSTER_MAX)) { + if (!(low_pfn % COMPACT_CLUSTER_MAX)) { if (locked) { unlock_page_lruvec_irqrestore(locked, flags); locked = NULL; @@ -899,7 +889,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * not falsely conclude that the block should be skipped. */ if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) { - if (!cc->ignore_skip_hint && get_pageblock_skip(page)) { + if (!isolation_suitable(cc, page)) { low_pfn = end_pfn; page = NULL; goto isolate_abort; @@ -918,7 +908,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* Do not report -EBUSY down the chain */ if (ret == -EBUSY) ret = 0; - low_pfn += (1UL << compound_order(page)) - 1; + low_pfn += compound_nr(page) - 1; goto isolate_fail; } @@ -1542,7 +1532,7 @@ fast_isolate_freepages(struct compact_control *cc) * not found, be pessimistic for direct compaction * and use the min mark. */ - if (highest) { + if (highest >= min_pfn) { page = pfn_to_page(highest); cc->free_pfn = highest; } else { @@ -1587,7 +1577,7 @@ static void isolate_freepages(struct compact_control *cc) unsigned int stride; /* Try a small search of the free lists for a candidate */ - isolate_start_pfn = fast_isolate_freepages(cc); + fast_isolate_freepages(cc); if (cc->nr_freepages) goto splitmap; @@ -1624,7 +1614,7 @@ static void isolate_freepages(struct compact_control *cc) * This can iterate a massively long zone without finding any * suitable migration targets, so periodically check resched. */ - if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))) + if (!(block_start_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages))) cond_resched(); page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, @@ -1858,6 +1848,8 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) update_fast_start_pfn(cc, free_pfn); pfn = pageblock_start_pfn(free_pfn); + if (pfn < cc->zone->zone_start_pfn) + pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; found_block = true; set_pageblock_skip(freepage); @@ -1931,7 +1923,7 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) * many pageblocks unsuitable, so periodically check if we * need to schedule. */ - if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))) + if (!(low_pfn % (COMPACT_CLUSTER_MAX * pageblock_nr_pages))) cond_resched(); page = pageblock_pfn_to_page(block_start_pfn, @@ -1951,12 +1943,12 @@ static isolate_migrate_t isolate_migratepages(struct compact_control *cc) continue; /* - * For async compaction, also only scan in MOVABLE blocks - * without huge pages. Async compaction is optimistic to see - * if the minimum amount of work satisfies the allocation. - * The cached PFN is updated as it's possible that all - * remaining blocks between source and target are unsuitable - * and the compaction scanners fail to meet. + * For async direct compaction, only scan the pageblocks of the + * same migratetype without huge pages. Async direct compaction + * is optimistic to see if the minimum amount of work satisfies + * the allocation. The cached PFN is updated as it's possible + * that all remaining blocks between source and target are + * unsuitable and the compaction scanners fail to meet. */ if (!suitable_migration_source(cc, page)) { update_cached_migrate(cc, block_end_pfn); @@ -2144,29 +2136,16 @@ static enum compact_result __compact_finished(struct compact_control *cc) * other migratetype buddy lists. */ if (find_suitable_fallback(area, order, migratetype, - true, &can_steal) != -1) { - - /* movable pages are OK in any pageblock */ - if (migratetype == MIGRATE_MOVABLE) - return COMPACT_SUCCESS; - + true, &can_steal) != -1) /* - * We are stealing for a non-movable allocation. Make - * sure we finish compacting the current pageblock - * first so it is as free as possible and we won't - * have to steal another one soon. This only applies - * to sync compaction, as async compaction operates - * on pageblocks of the same migratetype. + * Movable pages are OK in any pageblock. If we are + * stealing for a non-movable allocation, make sure + * we finish compacting the current pageblock first + * (which is assured by the above migrate_pfn align + * check) so it is as free as possible and we won't + * have to steal another one soon. */ - if (cc->mode == MIGRATE_ASYNC || - IS_ALIGNED(cc->migrate_pfn, - pageblock_nr_pages)) { - return COMPACT_SUCCESS; - } - - ret = COMPACT_CONTINUE; - break; - } + return COMPACT_SUCCESS; } out: @@ -2301,7 +2280,7 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, available += zone_page_state_snapshot(zone, NR_FREE_PAGES); compact_result = __compaction_suitable(zone, order, alloc_flags, ac->highest_zoneidx, available); - if (compact_result != COMPACT_SKIPPED) + if (compact_result == COMPACT_CONTINUE) return true; } @@ -2592,7 +2571,7 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, struct page **capture) { - int may_perform_io = gfp_mask & __GFP_IO; + int may_perform_io = (__force int)(gfp_mask & __GFP_IO); struct zoneref *z; struct zone *zone; enum compact_result rc = COMPACT_SKIPPED; @@ -3016,21 +2995,18 @@ static int kcompactd(void *p) * This kcompactd start function will be called by init and node-hot-add. * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added. */ -int kcompactd_run(int nid) +void kcompactd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); - int ret = 0; if (pgdat->kcompactd) - return 0; + return; pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid); if (IS_ERR(pgdat->kcompactd)) { pr_err("Failed to start kcompactd on node %d\n", nid); - ret = PTR_ERR(pgdat->kcompactd); pgdat->kcompactd = NULL; } - return ret; } /* @@ -3065,7 +3041,8 @@ static int kcompactd_cpu_online(unsigned int cpu) if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids) /* One of our CPUs online: restore mask */ - set_cpus_allowed_ptr(pgdat->kcompactd, mask); + if (pgdat->kcompactd) + set_cpus_allowed_ptr(pgdat->kcompactd, mask); } return 0; } diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h index b4085deb9fa0..573669566f84 100644 --- a/mm/damon/core-test.h +++ b/mm/damon/core-test.h @@ -232,6 +232,41 @@ static void damon_test_split_regions_of(struct kunit *test) damon_destroy_ctx(c); } +static void damon_test_ops_registration(struct kunit *test) +{ + struct damon_ctx *c = damon_new_ctx(); + struct damon_operations ops, bak; + + /* DAMON_OPS_{V,P}ADDR are registered on subsys_initcall */ + KUNIT_EXPECT_EQ(test, damon_select_ops(c, DAMON_OPS_VADDR), 0); + KUNIT_EXPECT_EQ(test, damon_select_ops(c, DAMON_OPS_PADDR), 0); + + /* Double-registration is prohibited */ + ops.id = DAMON_OPS_VADDR; + KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), -EINVAL); + ops.id = DAMON_OPS_PADDR; + KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), -EINVAL); + + /* Unknown ops id cannot be registered */ + KUNIT_EXPECT_EQ(test, damon_select_ops(c, NR_DAMON_OPS), -EINVAL); + + /* Registration should success after unregistration */ + mutex_lock(&damon_ops_lock); + bak = damon_registered_ops[DAMON_OPS_VADDR]; + damon_registered_ops[DAMON_OPS_VADDR] = (struct damon_operations){}; + mutex_unlock(&damon_ops_lock); + + ops.id = DAMON_OPS_VADDR; + KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), 0); + + mutex_lock(&damon_ops_lock); + damon_registered_ops[DAMON_OPS_VADDR] = bak; + mutex_unlock(&damon_ops_lock); + + /* Check double-registration failure again */ + KUNIT_EXPECT_EQ(test, damon_register_ops(&ops), -EINVAL); +} + static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_test_target), KUNIT_CASE(damon_test_regions), @@ -240,6 +275,7 @@ static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damon_test_merge_two), KUNIT_CASE(damon_test_merge_regions_of), KUNIT_CASE(damon_test_split_regions_of), + KUNIT_CASE(damon_test_ops_registration), {}, }; diff --git a/mm/damon/core.c b/mm/damon/core.c index 5ce8d7c867f0..7d25dc582fe3 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -30,7 +30,7 @@ static DEFINE_MUTEX(damon_ops_lock); static struct damon_operations damon_registered_ops[NR_DAMON_OPS]; /* Should be called under damon_ops_lock with id smaller than NR_DAMON_OPS */ -static bool damon_registered_ops_id(enum damon_ops_id id) +static bool __damon_is_registered_ops(enum damon_ops_id id) { struct damon_operations empty_ops = {}; @@ -40,6 +40,24 @@ static bool damon_registered_ops_id(enum damon_ops_id id) } /** + * damon_is_registered_ops() - Check if a given damon_operations is registered. + * @id: Id of the damon_operations to check if registered. + * + * Return: true if the ops is set, false otherwise. + */ +bool damon_is_registered_ops(enum damon_ops_id id) +{ + bool registered; + + if (id >= NR_DAMON_OPS) + return false; + mutex_lock(&damon_ops_lock); + registered = __damon_is_registered_ops(id); + mutex_unlock(&damon_ops_lock); + return registered; +} + +/** * damon_register_ops() - Register a monitoring operations set to DAMON. * @ops: monitoring operations set to register. * @@ -56,7 +74,7 @@ int damon_register_ops(struct damon_operations *ops) return -EINVAL; mutex_lock(&damon_ops_lock); /* Fail for already registered ops */ - if (damon_registered_ops_id(ops->id)) { + if (__damon_is_registered_ops(ops->id)) { err = -EINVAL; goto out; } @@ -84,7 +102,7 @@ int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id) return -EINVAL; mutex_lock(&damon_ops_lock); - if (!damon_registered_ops_id(id)) + if (!__damon_is_registered_ops(id)) err = -EINVAL; else ctx->ops = damon_registered_ops[id]; @@ -139,6 +157,79 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t) damon_free_region(r); } +/* + * Check whether a region is intersecting an address range + * + * Returns true if it is. + */ +static bool damon_intersect(struct damon_region *r, + struct damon_addr_range *re) +{ + return !(r->ar.end <= re->start || re->end <= r->ar.start); +} + +/* + * damon_set_regions() - Set regions of a target for given address ranges. + * @t: the given target. + * @ranges: array of new monitoring target ranges. + * @nr_ranges: length of @ranges. + * + * This function adds new regions to, or modify existing regions of a + * monitoring target to fit in specific ranges. + * + * Return: 0 if success, or negative error code otherwise. + */ +int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges, + unsigned int nr_ranges) +{ + struct damon_region *r, *next; + unsigned int i; + + /* Remove regions which are not in the new ranges */ + damon_for_each_region_safe(r, next, t) { + for (i = 0; i < nr_ranges; i++) { + if (damon_intersect(r, &ranges[i])) + break; + } + if (i == nr_ranges) + damon_destroy_region(r, t); + } + + /* Add new regions or resize existing regions to fit in the ranges */ + for (i = 0; i < nr_ranges; i++) { + struct damon_region *first = NULL, *last, *newr; + struct damon_addr_range *range; + + range = &ranges[i]; + /* Get the first/last regions intersecting with the range */ + damon_for_each_region(r, t) { + if (damon_intersect(r, range)) { + if (!first) + first = r; + last = r; + } + if (r->ar.start >= range->end) + break; + } + if (!first) { + /* no region intersects with this range */ + newr = damon_new_region( + ALIGN_DOWN(range->start, + DAMON_MIN_REGION), + ALIGN(range->end, DAMON_MIN_REGION)); + if (!newr) + return -ENOMEM; + damon_insert_region(newr, damon_prev_region(r), r, t); + } else { + /* resize intersecting regions to fit in this range */ + first->ar.start = ALIGN_DOWN(range->start, + DAMON_MIN_REGION); + last->ar.end = ALIGN(range->end, DAMON_MIN_REGION); + } + } + return 0; +} + struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, @@ -1033,6 +1124,10 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) return 0; kdamond_usleep(min_wait_time); + + if (ctx->callback.after_wmarks_check && + ctx->callback.after_wmarks_check(ctx)) + break; } return -EBUSY; } @@ -1042,7 +1137,7 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) */ static int kdamond_fn(void *data) { - struct damon_ctx *ctx = (struct damon_ctx *)data; + struct damon_ctx *ctx = data; struct damon_target *t; struct damon_region *r, *next; unsigned int max_nr_accesses = 0; @@ -1059,14 +1154,18 @@ static int kdamond_fn(void *data) sz_limit = damon_region_sz_limit(ctx); while (!kdamond_need_stop(ctx) && !done) { - if (kdamond_wait_activation(ctx)) + if (kdamond_wait_activation(ctx)) { + done = true; continue; + } if (ctx->ops.prepare_access_checks) ctx->ops.prepare_access_checks(ctx); if (ctx->callback.after_sampling && - ctx->callback.after_sampling(ctx)) + ctx->callback.after_sampling(ctx)) { done = true; + continue; + } kdamond_usleep(ctx->sample_interval); @@ -1078,8 +1177,10 @@ static int kdamond_fn(void *data) max_nr_accesses / 10, sz_limit); if (ctx->callback.after_aggregation && - ctx->callback.after_aggregation(ctx)) + ctx->callback.after_aggregation(ctx)) { done = true; + continue; + } kdamond_apply_schemes(ctx); kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index e346cc10d143..10ef20b2003f 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -73,8 +73,7 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr) } #ifdef CONFIG_MMU_NOTIFIER - if (mmu_notifier_clear_young(mm, addr, - addr + ((1UL) << HPAGE_PMD_SHIFT))) + if (mmu_notifier_clear_young(mm, addr, addr + HPAGE_PMD_SIZE)) referenced = true; #endif /* CONFIG_MMU_NOTIFIER */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 21474ae63bc7..b40ff5811bb2 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -106,7 +106,7 @@ static bool __damon_pa_young(struct folio *folio, struct vm_area_struct *vma, result->accessed = pmd_young(*pvmw.pmd) || !folio_test_idle(folio) || mmu_notifier_test_young(vma->vm_mm, addr); - result->page_sz = ((1UL) << HPAGE_PMD_SHIFT); + result->page_sz = HPAGE_PMD_SIZE; #else WARN_ON_ONCE(1); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index e34c4d0c4d93..8efbfb24f3a1 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -28,7 +28,18 @@ * this. */ static bool enabled __read_mostly; -module_param(enabled, bool, 0600); + +/* + * Make DAMON_RECLAIM reads the input parameters again, except ``enabled``. + * + * Input parameters that updated while DAMON_RECLAIM is running are not applied + * by default. Once this parameter is set as ``Y``, DAMON_RECLAIM reads values + * of parametrs except ``enabled`` again. Once the re-reading is done, this + * parameter is set as ``N``. If invalid parameters are found while the + * re-reading, DAMON_RECLAIM will be disabled. + */ +static bool commit_inputs __read_mostly; +module_param(commit_inputs, bool, 0600); /* * Time threshold for cold memory regions identification in microseconds. @@ -227,7 +238,7 @@ static int walk_system_ram(struct resource *res, void *arg) { struct damon_reclaim_ram_walk_arg *a = arg; - if (a->end - a->start < res->end - res->start) { + if (a->end - a->start < resource_size(res)) { a->start = res->start; a->end = res->end; } @@ -290,57 +301,56 @@ static struct damos *damon_reclaim_new_scheme(void) return scheme; } -static int damon_reclaim_turn(bool on) +static int damon_reclaim_apply_parameters(void) { - struct damon_region *region; struct damos *scheme; - int err; - - if (!on) { - err = damon_stop(&ctx, 1); - if (!err) - kdamond_pid = -1; - return err; - } + struct damon_addr_range addr_range; + int err = 0; err = damon_set_attrs(ctx, sample_interval, aggr_interval, 0, min_nr_regions, max_nr_regions); if (err) return err; + /* Will be freed by next 'damon_set_schemes()' below */ + scheme = damon_reclaim_new_scheme(); + if (!scheme) + return -ENOMEM; + err = damon_set_schemes(ctx, &scheme, 1); + if (err) + return err; + if (monitor_region_start > monitor_region_end) return -EINVAL; if (!monitor_region_start && !monitor_region_end && !get_monitoring_region(&monitor_region_start, &monitor_region_end)) return -EINVAL; - /* DAMON will free this on its own when finish monitoring */ - region = damon_new_region(monitor_region_start, monitor_region_end); - if (!region) - return -ENOMEM; - damon_add_region(region, target); + addr_range.start = monitor_region_start; + addr_range.end = monitor_region_end; + return damon_set_regions(target, &addr_range, 1); +} - /* Will be freed by 'damon_set_schemes()' below */ - scheme = damon_reclaim_new_scheme(); - if (!scheme) { - err = -ENOMEM; - goto free_region_out; +static int damon_reclaim_turn(bool on) +{ + int err; + + if (!on) { + err = damon_stop(&ctx, 1); + if (!err) + kdamond_pid = -1; + return err; } - err = damon_set_schemes(ctx, &scheme, 1); + + err = damon_reclaim_apply_parameters(); if (err) - goto free_scheme_out; + return err; err = damon_start(&ctx, 1, true); - if (!err) { - kdamond_pid = ctx->kdamond->pid; - return 0; - } - -free_scheme_out: - damon_destroy_scheme(scheme); -free_region_out: - damon_destroy_region(region, target); - return err; + if (err) + return err; + kdamond_pid = ctx->kdamond->pid; + return 0; } #define ENABLE_CHECK_INTERVAL_MS 1000 @@ -358,14 +368,39 @@ static void damon_reclaim_timer_fn(struct work_struct *work) enabled = last_enabled; } - schedule_delayed_work(&damon_reclaim_timer, + if (enabled) + schedule_delayed_work(&damon_reclaim_timer, msecs_to_jiffies(ENABLE_CHECK_INTERVAL_MS)); } static DECLARE_DELAYED_WORK(damon_reclaim_timer, damon_reclaim_timer_fn); +static int enabled_store(const char *val, + const struct kernel_param *kp) +{ + int rc = param_set_bool(val, kp); + + if (rc < 0) + return rc; + + if (enabled) + schedule_delayed_work(&damon_reclaim_timer, 0); + + return 0; +} + +static const struct kernel_param_ops enabled_param_ops = { + .set = enabled_store, + .get = param_get_bool, +}; + +module_param_cb(enabled, &enabled_param_ops, &enabled, 0600); +MODULE_PARM_DESC(enabled, + "Enable or disable DAMON_RECLAIM (default: disabled)"); + static int damon_reclaim_after_aggregation(struct damon_ctx *c) { struct damos *s; + int err = 0; /* update the stats parameter */ damon_for_each_scheme(s, c) { @@ -375,7 +410,23 @@ static int damon_reclaim_after_aggregation(struct damon_ctx *c) bytes_reclaimed_regions = s->stat.sz_applied; nr_quota_exceeds = s->stat.qt_exceeds; } - return 0; + + if (commit_inputs) { + err = damon_reclaim_apply_parameters(); + commit_inputs = false; + } + return err; +} + +static int damon_reclaim_after_wmarks_check(struct damon_ctx *c) +{ + int err = 0; + + if (commit_inputs) { + err = damon_reclaim_apply_parameters(); + commit_inputs = false; + } + return err; } static int __init damon_reclaim_init(void) @@ -387,6 +438,7 @@ static int __init damon_reclaim_init(void) if (damon_select_ops(ctx, DAMON_OPS_PADDR)) return -EINVAL; + ctx->callback.after_wmarks_check = damon_reclaim_after_wmarks_check; ctx->callback.after_aggregation = damon_reclaim_after_aggregation; target = damon_new_target(); diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index 48e434cd43d8..09f9e8ca3d1f 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1694,6 +1694,7 @@ static struct kobj_type damon_sysfs_attrs_ktype = { /* This should match with enum damon_ops_id */ static const char * const damon_sysfs_ops_strs[] = { "vaddr", + "fvaddr", "paddr", }; @@ -1810,6 +1811,21 @@ static void damon_sysfs_context_rm_dirs(struct damon_sysfs_context *context) kobject_put(&context->schemes->kobj); } +static ssize_t avail_operations_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + enum damon_ops_id id; + int len = 0; + + for (id = 0; id < NR_DAMON_OPS; id++) { + if (!damon_is_registered_ops(id)) + continue; + len += sysfs_emit_at(buf, len, "%s\n", + damon_sysfs_ops_strs[id]); + } + return len; +} + static ssize_t operations_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -1840,10 +1856,14 @@ static void damon_sysfs_context_release(struct kobject *kobj) kfree(container_of(kobj, struct damon_sysfs_context, kobj)); } +static struct kobj_attribute damon_sysfs_context_avail_operations_attr = + __ATTR_RO_MODE(avail_operations, 0400); + static struct kobj_attribute damon_sysfs_context_operations_attr = __ATTR_RW_MODE(operations, 0600); static struct attribute *damon_sysfs_context_attrs[] = { + &damon_sysfs_context_avail_operations_attr.attr, &damon_sysfs_context_operations_attr.attr, NULL, }; @@ -2033,6 +2053,54 @@ static bool damon_sysfs_ctx_running(struct damon_ctx *ctx) return running; } +/* + * enum damon_sysfs_cmd - Commands for a specific kdamond. + */ +enum damon_sysfs_cmd { + /* @DAMON_SYSFS_CMD_ON: Turn the kdamond on. */ + DAMON_SYSFS_CMD_ON, + /* @DAMON_SYSFS_CMD_OFF: Turn the kdamond off. */ + DAMON_SYSFS_CMD_OFF, + /* @DAMON_SYSFS_CMD_COMMIT: Update kdamond inputs. */ + DAMON_SYSFS_CMD_COMMIT, + /* + * @DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS: Update scheme stats sysfs + * files. + */ + DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS, + /* + * @NR_DAMON_SYSFS_CMDS: Total number of DAMON sysfs commands. + */ + NR_DAMON_SYSFS_CMDS, +}; + +/* Should match with enum damon_sysfs_cmd */ +static const char * const damon_sysfs_cmd_strs[] = { + "on", + "off", + "commit", + "update_schemes_stats", +}; + +/* + * struct damon_sysfs_cmd_request - A request to the DAMON callback. + * @cmd: The command that needs to be handled by the callback. + * @kdamond: The kobject wrapper that associated to the kdamond thread. + * + * This structure represents a sysfs command request that need to access some + * DAMON context-internal data. Because DAMON context-internal data can be + * safely accessed from DAMON callbacks without additional synchronization, the + * request will be handled by the DAMON callback. None-``NULL`` @kdamond means + * the request is valid. + */ +struct damon_sysfs_cmd_request { + enum damon_sysfs_cmd cmd; + struct damon_sysfs_kdamond *kdamond; +}; + +/* Current DAMON callback request. Protected by damon_sysfs_lock. */ +static struct damon_sysfs_cmd_request damon_sysfs_cmd_request; + static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -2046,7 +2114,9 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, else running = damon_sysfs_ctx_running(ctx); - return sysfs_emit(buf, "%s\n", running ? "on" : "off"); + return sysfs_emit(buf, "%s\n", running ? + damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] : + damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_OFF]); } static int damon_sysfs_set_attrs(struct damon_ctx *ctx, @@ -2066,7 +2136,8 @@ static void damon_sysfs_destroy_targets(struct damon_ctx *ctx) struct damon_target *t, *next; damon_for_each_target_safe(t, next, ctx) { - if (ctx->ops.id == DAMON_OPS_VADDR) + if (ctx->ops.id == DAMON_OPS_VADDR || + ctx->ops.id == DAMON_OPS_FVADDR) put_pid(t->pid); damon_destroy_target(t); } @@ -2075,28 +2146,89 @@ static void damon_sysfs_destroy_targets(struct damon_ctx *ctx) static int damon_sysfs_set_regions(struct damon_target *t, struct damon_sysfs_regions *sysfs_regions) { - int i; + struct damon_addr_range *ranges = kmalloc_array(sysfs_regions->nr, + sizeof(*ranges), GFP_KERNEL | __GFP_NOWARN); + int i, err = -EINVAL; + if (!ranges) + return -ENOMEM; for (i = 0; i < sysfs_regions->nr; i++) { struct damon_sysfs_region *sys_region = sysfs_regions->regions_arr[i]; - struct damon_region *prev, *r; if (sys_region->start > sys_region->end) - return -EINVAL; - r = damon_new_region(sys_region->start, sys_region->end); - if (!r) - return -ENOMEM; - damon_add_region(r, t); - if (damon_nr_regions(t) > 1) { - prev = damon_prev_region(r); - if (prev->ar.end > r->ar.start) { - damon_destroy_region(r, t); - return -EINVAL; - } - } + goto out; + + ranges[i].start = sys_region->start; + ranges[i].end = sys_region->end; + if (i == 0) + continue; + if (ranges[i - 1].end > ranges[i].start) + goto out; } + err = damon_set_regions(t, ranges, sysfs_regions->nr); +out: + kfree(ranges); + return err; + +} + +static int damon_sysfs_add_target(struct damon_sysfs_target *sys_target, + struct damon_ctx *ctx) +{ + struct damon_target *t = damon_new_target(); + int err = -EINVAL; + + if (!t) + return -ENOMEM; + if (ctx->ops.id == DAMON_OPS_VADDR || + ctx->ops.id == DAMON_OPS_FVADDR) { + t->pid = find_get_pid(sys_target->pid); + if (!t->pid) + goto destroy_targets_out; + } + damon_add_target(ctx, t); + err = damon_sysfs_set_regions(t, sys_target->regions); + if (err) + goto destroy_targets_out; return 0; + +destroy_targets_out: + damon_sysfs_destroy_targets(ctx); + return err; +} + +/* + * Search a target in a context that corresponds to the sysfs target input. + * + * Return: pointer to the target if found, NULL if not found, or negative + * error code if the search failed. + */ +static struct damon_target *damon_sysfs_existing_target( + struct damon_sysfs_target *sys_target, struct damon_ctx *ctx) +{ + struct pid *pid; + struct damon_target *t; + + if (ctx->ops.id == DAMON_OPS_PADDR) { + /* Up to only one target for paddr could exist */ + damon_for_each_target(t, ctx) + return t; + return NULL; + } + + /* ops.id should be DAMON_OPS_VADDR or DAMON_OPS_FVADDR */ + pid = find_get_pid(sys_target->pid); + if (!pid) + return ERR_PTR(-EINVAL); + damon_for_each_target(t, ctx) { + if (t->pid == pid) { + put_pid(pid); + return t; + } + } + put_pid(pid); + return NULL; } static int damon_sysfs_set_targets(struct damon_ctx *ctx, @@ -2104,28 +2236,22 @@ static int damon_sysfs_set_targets(struct damon_ctx *ctx, { int i, err; - for (i = 0; i < sysfs_targets->nr; i++) { - struct damon_sysfs_target *sys_target = - sysfs_targets->targets_arr[i]; - struct damon_target *t = damon_new_target(); + /* Multiple physical address space monitoring targets makes no sense */ + if (ctx->ops.id == DAMON_OPS_PADDR && sysfs_targets->nr > 1) + return -EINVAL; - if (!t) { - damon_sysfs_destroy_targets(ctx); - return -ENOMEM; - } - if (ctx->ops.id == DAMON_OPS_VADDR) { - t->pid = find_get_pid(sys_target->pid); - if (!t->pid) { - damon_sysfs_destroy_targets(ctx); - return -EINVAL; - } - } - damon_add_target(ctx, t); - err = damon_sysfs_set_regions(t, sys_target->regions); - if (err) { - damon_sysfs_destroy_targets(ctx); + for (i = 0; i < sysfs_targets->nr; i++) { + struct damon_sysfs_target *st = sysfs_targets->targets_arr[i]; + struct damon_target *t = damon_sysfs_existing_target(st, ctx); + + if (IS_ERR(t)) + return PTR_ERR(t); + if (!t) + err = damon_sysfs_add_target(st, ctx); + else + err = damon_sysfs_set_regions(t, st->regions); + if (err) return err; - } } return 0; } @@ -2183,7 +2309,7 @@ static void damon_sysfs_before_terminate(struct damon_ctx *ctx) { struct damon_target *t, *next; - if (ctx->ops.id != DAMON_OPS_VADDR) + if (ctx->ops.id != DAMON_OPS_VADDR && ctx->ops.id != DAMON_OPS_FVADDR) return; mutex_lock(&ctx->kdamond_lock); @@ -2194,6 +2320,115 @@ static void damon_sysfs_before_terminate(struct damon_ctx *ctx) mutex_unlock(&ctx->kdamond_lock); } +/* + * damon_sysfs_upd_schemes_stats() - Update schemes stats sysfs files. + * @kdamond: The kobject wrapper that associated to the kdamond thread. + * + * This function reads the schemes stats of specific kdamond and update the + * related values for sysfs files. This function should be called from DAMON + * callbacks while holding ``damon_syfs_lock``, to safely access the DAMON + * contexts-internal data and DAMON sysfs variables. + */ +static int damon_sysfs_upd_schemes_stats(struct damon_sysfs_kdamond *kdamond) +{ + struct damon_ctx *ctx = kdamond->damon_ctx; + struct damon_sysfs_schemes *sysfs_schemes; + struct damos *scheme; + int schemes_idx = 0; + + if (!ctx) + return -EINVAL; + sysfs_schemes = kdamond->contexts->contexts_arr[0]->schemes; + damon_for_each_scheme(scheme, ctx) { + struct damon_sysfs_stats *sysfs_stats; + + sysfs_stats = sysfs_schemes->schemes_arr[schemes_idx++]->stats; + sysfs_stats->nr_tried = scheme->stat.nr_tried; + sysfs_stats->sz_tried = scheme->stat.sz_tried; + sysfs_stats->nr_applied = scheme->stat.nr_applied; + sysfs_stats->sz_applied = scheme->stat.sz_applied; + sysfs_stats->qt_exceeds = scheme->stat.qt_exceeds; + } + return 0; +} + +static inline bool damon_sysfs_kdamond_running( + struct damon_sysfs_kdamond *kdamond) +{ + return kdamond->damon_ctx && + damon_sysfs_ctx_running(kdamond->damon_ctx); +} + +/* + * damon_sysfs_commit_input() - Commit user inputs to a running kdamond. + * @kdamond: The kobject wrapper for the associated kdamond. + * + * If the sysfs input is wrong, the kdamond will be terminated. + */ +static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond) +{ + struct damon_ctx *ctx = kdamond->damon_ctx; + struct damon_sysfs_context *sys_ctx; + int err = 0; + + if (!damon_sysfs_kdamond_running(kdamond)) + return -EINVAL; + /* TODO: Support multiple contexts per kdamond */ + if (kdamond->contexts->nr != 1) + return -EINVAL; + + sys_ctx = kdamond->contexts->contexts_arr[0]; + + err = damon_select_ops(ctx, sys_ctx->ops_id); + if (err) + return err; + err = damon_sysfs_set_attrs(ctx, sys_ctx->attrs); + if (err) + return err; + err = damon_sysfs_set_targets(ctx, sys_ctx->targets); + if (err) + return err; + err = damon_sysfs_set_schemes(ctx, sys_ctx->schemes); + if (err) + return err; + return err; +} + +/* + * damon_sysfs_cmd_request_callback() - DAMON callback for handling requests. + * @c: The DAMON context of the callback. + * + * This function is periodically called back from the kdamond thread for @c. + * Then, it checks if there is a waiting DAMON sysfs request and handles it. + */ +static int damon_sysfs_cmd_request_callback(struct damon_ctx *c) +{ + struct damon_sysfs_kdamond *kdamond; + int err = 0; + + /* avoid deadlock due to concurrent state_store('off') */ + if (!mutex_trylock(&damon_sysfs_lock)) + return 0; + kdamond = damon_sysfs_cmd_request.kdamond; + if (!kdamond || kdamond->damon_ctx != c) + goto out; + switch (damon_sysfs_cmd_request.cmd) { + case DAMON_SYSFS_CMD_UPDATE_SCHEMES_STATS: + err = damon_sysfs_upd_schemes_stats(kdamond); + break; + case DAMON_SYSFS_CMD_COMMIT: + err = damon_sysfs_commit_input(kdamond); + break; + default: + break; + } + /* Mark the request as invalid now. */ + damon_sysfs_cmd_request.kdamond = NULL; +out: + mutex_unlock(&damon_sysfs_lock); + return err; +} + static struct damon_ctx *damon_sysfs_build_ctx( struct damon_sysfs_context *sys_ctx) { @@ -2216,6 +2451,8 @@ static struct damon_ctx *damon_sysfs_build_ctx( if (err) goto out; + ctx->callback.after_wmarks_check = damon_sysfs_cmd_request_callback; + ctx->callback.after_aggregation = damon_sysfs_cmd_request_callback; ctx->callback.before_terminate = damon_sysfs_before_terminate; return ctx; @@ -2232,6 +2469,8 @@ static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond) if (kdamond->damon_ctx && damon_sysfs_ctx_running(kdamond->damon_ctx)) return -EBUSY; + if (damon_sysfs_cmd_request.kdamond == kdamond) + return -EBUSY; /* TODO: support multiple contexts per kdamond */ if (kdamond->contexts->nr != 1) return -EINVAL; @@ -2264,28 +2503,62 @@ static int damon_sysfs_turn_damon_off(struct damon_sysfs_kdamond *kdamond) */ } -static int damon_sysfs_update_schemes_stats(struct damon_sysfs_kdamond *kdamond) -{ - struct damon_ctx *ctx = kdamond->damon_ctx; - struct damos *scheme; - int schemes_idx = 0; +/* + * damon_sysfs_handle_cmd() - Handle a command for a specific kdamond. + * @cmd: The command to handle. + * @kdamond: The kobject wrapper for the associated kdamond. + * + * This function handles a DAMON sysfs command for a kdamond. For commands + * that need to access running DAMON context-internal data, it requests + * handling of the command to the DAMON callback + * (@damon_sysfs_cmd_request_callback()) and wait until it is properly handled, + * or the context is completed. + * + * Return: 0 on success, negative error code otherwise. + */ +static int damon_sysfs_handle_cmd(enum damon_sysfs_cmd cmd, + struct damon_sysfs_kdamond *kdamond) +{ + bool need_wait = true; + + /* Handle commands that doesn't access DAMON context-internal data */ + switch (cmd) { + case DAMON_SYSFS_CMD_ON: + return damon_sysfs_turn_damon_on(kdamond); + case DAMON_SYSFS_CMD_OFF: + return damon_sysfs_turn_damon_off(kdamond); + default: + break; + } - if (!ctx) + /* Pass the command to DAMON callback for safe DAMON context access */ + if (damon_sysfs_cmd_request.kdamond) + return -EBUSY; + if (!damon_sysfs_kdamond_running(kdamond)) return -EINVAL; - mutex_lock(&ctx->kdamond_lock); - damon_for_each_scheme(scheme, ctx) { - struct damon_sysfs_schemes *sysfs_schemes; - struct damon_sysfs_stats *sysfs_stats; + damon_sysfs_cmd_request.cmd = cmd; + damon_sysfs_cmd_request.kdamond = kdamond; - sysfs_schemes = kdamond->contexts->contexts_arr[0]->schemes; - sysfs_stats = sysfs_schemes->schemes_arr[schemes_idx++]->stats; - sysfs_stats->nr_tried = scheme->stat.nr_tried; - sysfs_stats->sz_tried = scheme->stat.sz_tried; - sysfs_stats->nr_applied = scheme->stat.nr_applied; - sysfs_stats->sz_applied = scheme->stat.sz_applied; - sysfs_stats->qt_exceeds = scheme->stat.qt_exceeds; + /* + * wait until damon_sysfs_cmd_request_callback() handles the request + * from kdamond context + */ + mutex_unlock(&damon_sysfs_lock); + while (need_wait) { + schedule_timeout_idle(msecs_to_jiffies(100)); + if (!mutex_trylock(&damon_sysfs_lock)) + continue; + if (!damon_sysfs_cmd_request.kdamond) { + /* damon_sysfs_cmd_request_callback() handled */ + need_wait = false; + } else if (!damon_sysfs_kdamond_running(kdamond)) { + /* kdamond has already finished */ + need_wait = false; + damon_sysfs_cmd_request.kdamond = NULL; + } + mutex_unlock(&damon_sysfs_lock); } - mutex_unlock(&ctx->kdamond_lock); + mutex_lock(&damon_sysfs_lock); return 0; } @@ -2294,18 +2567,17 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, { struct damon_sysfs_kdamond *kdamond = container_of(kobj, struct damon_sysfs_kdamond, kobj); - ssize_t ret; + enum damon_sysfs_cmd cmd; + ssize_t ret = -EINVAL; if (!mutex_trylock(&damon_sysfs_lock)) return -EBUSY; - if (sysfs_streq(buf, "on")) - ret = damon_sysfs_turn_damon_on(kdamond); - else if (sysfs_streq(buf, "off")) - ret = damon_sysfs_turn_damon_off(kdamond); - else if (sysfs_streq(buf, "update_schemes_stats")) - ret = damon_sysfs_update_schemes_stats(kdamond); - else - ret = -EINVAL; + for (cmd = 0; cmd < NR_DAMON_SYSFS_CMDS; cmd++) { + if (sysfs_streq(buf, damon_sysfs_cmd_strs[cmd])) { + ret = damon_sysfs_handle_cmd(cmd, kdamond); + break; + } + } mutex_unlock(&damon_sysfs_lock); if (!ret) ret = count; @@ -2424,6 +2696,12 @@ static int damon_sysfs_kdamonds_add_dirs(struct damon_sysfs_kdamonds *kdamonds, if (damon_sysfs_nr_running_ctxs(kdamonds->kdamonds_arr, kdamonds->nr)) return -EBUSY; + for (i = 0; i < kdamonds->nr; i++) { + if (damon_sysfs_cmd_request.kdamond == + kdamonds->kdamonds_arr[i]) + return -EBUSY; + } + damon_sysfs_kdamonds_rm_dirs(kdamonds); if (!nr_kdamonds) return 0; diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h index 1a55bb6c36c3..d4f55f349100 100644 --- a/mm/damon/vaddr-test.h +++ b/mm/damon/vaddr-test.h @@ -109,7 +109,7 @@ static struct damon_region *__nth_region_of(struct damon_target *t, int idx) } /* - * Test 'damon_va_apply_three_regions()' + * Test 'damon_set_regions()' * * test kunit object * regions an array containing start/end addresses of current @@ -124,7 +124,7 @@ static struct damon_region *__nth_region_of(struct damon_target *t, int idx) * the change, DAMON periodically reads the mappings, simplifies it to the * three regions, and updates the monitoring target regions to fit in the three * regions. The update of current target regions is the role of - * 'damon_va_apply_three_regions()'. + * 'damon_set_regions()'. * * This test passes the given target regions and the new three regions that * need to be applied to the function and check whether it updates the regions @@ -145,7 +145,7 @@ static void damon_do_test_apply_three_regions(struct kunit *test, damon_add_region(r, t); } - damon_va_apply_three_regions(t, three_regions); + damon_set_regions(t, three_regions, 3); for (i = 0; i < nr_expected / 2; i++) { r = __nth_region_of(t, i); @@ -281,14 +281,16 @@ static void damon_test_split_evenly_succ(struct kunit *test, KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces); damon_for_each_region(r, t) { - if (i == nr_pieces - 1) + if (i == nr_pieces - 1) { + KUNIT_EXPECT_EQ(test, + r->ar.start, start + i * expected_width); + KUNIT_EXPECT_EQ(test, r->ar.end, end); break; + } KUNIT_EXPECT_EQ(test, r->ar.start, start + i++ * expected_width); KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width); } - KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width); - KUNIT_EXPECT_EQ(test, r->ar.end, end); damon_free_target(t); } diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index b2ec0aa1ff45..59e1653799f8 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -282,77 +282,6 @@ static void damon_va_init(struct damon_ctx *ctx) } /* - * Functions for the dynamic monitoring target regions update - */ - -/* - * Check whether a region is intersecting an address range - * - * Returns true if it is. - */ -static bool damon_intersect(struct damon_region *r, - struct damon_addr_range *re) -{ - return !(r->ar.end <= re->start || re->end <= r->ar.start); -} - -/* - * Update damon regions for the three big regions of the given target - * - * t the given target - * bregions the three big regions of the target - */ -static void damon_va_apply_three_regions(struct damon_target *t, - struct damon_addr_range bregions[3]) -{ - struct damon_region *r, *next; - unsigned int i; - - /* Remove regions which are not in the three big regions now */ - damon_for_each_region_safe(r, next, t) { - for (i = 0; i < 3; i++) { - if (damon_intersect(r, &bregions[i])) - break; - } - if (i == 3) - damon_destroy_region(r, t); - } - - /* Adjust intersecting regions to fit with the three big regions */ - for (i = 0; i < 3; i++) { - struct damon_region *first = NULL, *last; - struct damon_region *newr; - struct damon_addr_range *br; - - br = &bregions[i]; - /* Get the first and last regions which intersects with br */ - damon_for_each_region(r, t) { - if (damon_intersect(r, br)) { - if (!first) - first = r; - last = r; - } - if (r->ar.start >= br->end) - break; - } - if (!first) { - /* no damon_region intersects with this big region */ - newr = damon_new_region( - ALIGN_DOWN(br->start, - DAMON_MIN_REGION), - ALIGN(br->end, DAMON_MIN_REGION)); - if (!newr) - continue; - damon_insert_region(newr, damon_prev_region(r), r, t); - } else { - first->ar.start = ALIGN_DOWN(br->start, - DAMON_MIN_REGION); - last->ar.end = ALIGN(br->end, DAMON_MIN_REGION); - } - } -} - -/* * Update regions for current memory mappings */ static void damon_va_update(struct damon_ctx *ctx) @@ -363,7 +292,7 @@ static void damon_va_update(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { if (damon_va_three_regions(t, three_regions)) continue; - damon_va_apply_three_regions(t, three_regions); + damon_set_regions(t, three_regions, 3); } } @@ -513,7 +442,7 @@ static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr, if (pmd_young(*pmd) || !page_is_idle(page) || mmu_notifier_test_young(walk->mm, addr)) { - *priv->page_sz = ((1UL) << HPAGE_PMD_SHIFT); + *priv->page_sz = HPAGE_PMD_SIZE; priv->young = true; } put_page(page); @@ -753,8 +682,19 @@ static int __init damon_va_initcall(void) .apply_scheme = damon_va_apply_scheme, .get_scheme_score = damon_va_scheme_score, }; - - return damon_register_ops(&ops); + /* ops for fixed virtual address ranges */ + struct damon_operations ops_fvaddr = ops; + int err; + + /* Don't set the monitoring target regions for the entire mapping */ + ops_fvaddr.id = DAMON_OPS_FVADDR; + ops_fvaddr.init = NULL; + ops_fvaddr.update = NULL; + + err = damon_register_ops(&ops); + if (err) + return err; + return damon_register_ops(&ops_fvaddr); }; subsys_initcall(damon_va_initcall); diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index db2abd9e415b..1ab091f49fc0 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -93,7 +93,7 @@ struct pgtable_debug_args { static void __init pte_basic_tests(struct pgtable_debug_args *args, int idx) { - pgprot_t prot = protection_map[idx]; + pgprot_t prot = vm_get_page_prot(idx); pte_t pte = pfn_pte(args->fixed_pte_pfn, prot); unsigned long val = idx, *ptr = &val; @@ -101,7 +101,7 @@ static void __init pte_basic_tests(struct pgtable_debug_args *args, int idx) /* * This test needs to be executed after the given page table entry - * is created with pfn_pte() to make sure that protection_map[idx] + * is created with pfn_pte() to make sure that vm_get_page_prot(idx) * does not have the dirty bit enabled from the beginning. This is * important for platforms like arm64 where (!PTE_RDONLY) indicate * dirty bit being set. @@ -190,7 +190,7 @@ static void __init pte_savedwrite_tests(struct pgtable_debug_args *args) #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx) { - pgprot_t prot = protection_map[idx]; + pgprot_t prot = vm_get_page_prot(idx); unsigned long val = idx, *ptr = &val; pmd_t pmd; @@ -202,7 +202,7 @@ static void __init pmd_basic_tests(struct pgtable_debug_args *args, int idx) /* * This test needs to be executed after the given page table entry - * is created with pfn_pmd() to make sure that protection_map[idx] + * is created with pfn_pmd() to make sure that vm_get_page_prot(idx) * does not have the dirty bit enabled from the beginning. This is * important for platforms like arm64 where (!PTE_RDONLY) indicate * dirty bit being set. @@ -325,7 +325,7 @@ static void __init pmd_savedwrite_tests(struct pgtable_debug_args *args) #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) { - pgprot_t prot = protection_map[idx]; + pgprot_t prot = vm_get_page_prot(idx); unsigned long val = idx, *ptr = &val; pud_t pud; @@ -337,7 +337,7 @@ static void __init pud_basic_tests(struct pgtable_debug_args *args, int idx) /* * This test needs to be executed after the given page table entry - * is created with pfn_pud() to make sure that protection_map[idx] + * is created with pfn_pud() to make sure that vm_get_page_prot(idx) * does not have the dirty bit enabled from the beginning. This is * important for platforms like arm64 where (!PTE_RDONLY) indicate * dirty bit being set. @@ -837,6 +837,19 @@ static void __init pmd_soft_dirty_tests(struct pgtable_debug_args *args) { } static void __init pmd_swap_soft_dirty_tests(struct pgtable_debug_args *args) { } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static void __init pte_swap_exclusive_tests(struct pgtable_debug_args *args) +{ +#ifdef __HAVE_ARCH_PTE_SWP_EXCLUSIVE + pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot); + + pr_debug("Validating PTE swap exclusive\n"); + pte = pte_swp_mkexclusive(pte); + WARN_ON(!pte_swp_exclusive(pte)); + pte = pte_swp_clear_exclusive(pte); + WARN_ON(pte_swp_exclusive(pte)); +#endif /* __HAVE_ARCH_PTE_SWP_EXCLUSIVE */ +} + static void __init pte_swap_tests(struct pgtable_debug_args *args) { swp_entry_t swp; @@ -1106,14 +1119,14 @@ static int __init init_args(struct pgtable_debug_args *args) /* * Initialize the debugging data. * - * protection_map[0] (or even protection_map[8]) will help create - * page table entries with PROT_NONE permission as required for - * pxx_protnone_tests(). + * vm_get_page_prot(VM_NONE) or vm_get_page_prot(VM_SHARED|VM_NONE) + * will help create page table entries with PROT_NONE permission as + * required for pxx_protnone_tests(). */ memset(args, 0, sizeof(*args)); args->vaddr = get_random_vaddr(); args->page_prot = vm_get_page_prot(VMFLAGS); - args->page_prot_none = protection_map[0]; + args->page_prot_none = vm_get_page_prot(VM_NONE); args->is_contiguous_page = false; args->pud_pfn = ULONG_MAX; args->pmd_pfn = ULONG_MAX; @@ -1248,12 +1261,19 @@ static int __init debug_vm_pgtable(void) return ret; /* - * Iterate over the protection_map[] to make sure that all + * Iterate over each possible vm_flags to make sure that all * the basic page table transformation validations just hold * true irrespective of the starting protection value for a * given page table entry. + * + * Protection based vm_flags combinatins are always linear + * and increasing i.e starting from VM_NONE and going upto + * (VM_SHARED | READ | WRITE | EXEC). */ - for (idx = 0; idx < ARRAY_SIZE(protection_map); idx++) { +#define VM_FLAGS_START (VM_NONE) +#define VM_FLAGS_END (VM_SHARED | VM_EXEC | VM_WRITE | VM_READ) + + for (idx = VM_FLAGS_START; idx <= VM_FLAGS_END; idx++) { pte_basic_tests(&args, idx); pmd_basic_tests(&args, idx); pud_basic_tests(&args, idx); @@ -1288,6 +1308,8 @@ static int __init debug_vm_pgtable(void) pte_swap_soft_dirty_tests(&args); pmd_swap_soft_dirty_tests(&args); + pte_swap_exclusive_tests(&args); + pte_swap_tests(&args); pmd_swap_tests(&args); diff --git a/mm/failslab.c b/mm/failslab.c index f92fed91ac23..58df9789f1d2 100644 --- a/mm/failslab.c +++ b/mm/failslab.c @@ -30,6 +30,9 @@ bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) if (failslab.cache_filter && !(s->flags & SLAB_FAILSLAB)) return false; + if (gfpflags & __GFP_NOWARN) + failslab.attr.no_warn = true; + return should_fail(&failslab.attr, s->object_size); } diff --git a/mm/filemap.c b/mm/filemap.c index fa0ca674450f..9daeaab36081 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3376,6 +3376,11 @@ again: vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; + /* + * NOTE: If there're PTE markers, we'll leave them to be + * handled in the specific fault path, and it'll prohibit the + * fault-around logic. + */ if (!pte_none(*vmf->pte)) goto unlock; @@ -29,6 +29,39 @@ struct follow_page_context { unsigned int page_mask; }; +static inline void sanity_check_pinned_pages(struct page **pages, + unsigned long npages) +{ + if (!IS_ENABLED(CONFIG_DEBUG_VM)) + return; + + /* + * We only pin anonymous pages if they are exclusive. Once pinned, we + * can no longer turn them possibly shared and PageAnonExclusive() will + * stick around until the page is freed. + * + * We'd like to verify that our pinned anonymous pages are still mapped + * exclusively. The issue with anon THP is that we don't know how + * they are/were mapped when pinning them. However, for anon + * THP we can assume that either the given page (PTE-mapped THP) or + * the head page (PMD-mapped THP) should be PageAnonExclusive(). If + * neither is the case, there is certainly something wrong. + */ + for (; npages; npages--, pages++) { + struct page *page = *pages; + struct folio *folio = page_folio(page); + + if (!folio_test_anon(folio)) + continue; + if (!folio_test_large(folio) || folio_test_hugetlb(folio)) + VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); + else + /* Either a PTE-mapped or a PMD-mapped THP. */ + VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) && + !PageAnonExclusive(page), page); + } +} + /* * Return the folio with ref appropriately incremented, * or NULL if that failed. @@ -204,6 +237,7 @@ bool __must_check try_grab_page(struct page *page, unsigned int flags) */ void unpin_user_page(struct page *page) { + sanity_check_pinned_pages(&page, 1); gup_put_folio(page_folio(page), 1, FOLL_PIN); } EXPORT_SYMBOL(unpin_user_page); @@ -272,6 +306,7 @@ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, return; } + sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); /* @@ -344,6 +379,23 @@ 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) +{ + unsigned long i; + struct folio *folio; + unsigned int nr; + + /* + * Don't perform any sanity checks because we might have raced with + * fork() and some anonymous pages might now actually be shared -- + * which is why we're unpinning after all. + */ + for (i = 0; i < npages; i += nr) { + folio = gup_folio_next(pages, npages, i, &nr); + gup_put_folio(folio, nr, FOLL_PIN); + } +} + /** * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. @@ -367,6 +419,7 @@ void unpin_user_pages(struct page **pages, unsigned long npages) if (WARN_ON(IS_ERR_VALUE(npages))) return; + sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); @@ -506,6 +559,14 @@ retry: } } + if (!pte_write(pte) && gup_must_unshare(flags, page)) { + page = ERR_PTR(-EMLINK); + goto out; + } + + VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && + !PageAnonExclusive(page), page); + /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */ if (unlikely(!try_grab_page(page, flags))) { page = ERR_PTR(-ENOMEM); @@ -732,6 +793,11 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches * the device's dev_pagemap metadata to avoid repeating expensive lookups. * + * When getting an anonymous page and the caller has to trigger unsharing + * of a shared anonymous page first, -EMLINK is returned. The caller should + * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only + * relevant with FOLL_PIN and !FOLL_WRITE. + * * On output, the @ctx->page_mask is set according to the size of the page. * * Return: the mapped (struct page *), %NULL if no mapping exists, or @@ -787,6 +853,9 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, if (vma_is_secretmem(vma)) return NULL; + if (foll_flags & FOLL_PIN) + return NULL; + page = follow_page_mask(vma, address, foll_flags, &ctx); if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); @@ -852,7 +921,8 @@ unmap: * is, *@locked will be set to 0 and -EBUSY returned. */ static int faultin_page(struct vm_area_struct *vma, - unsigned long address, unsigned int *flags, int *locked) + unsigned long address, unsigned int *flags, bool unshare, + int *locked) { unsigned int fault_flags = 0; vm_fault_t ret; @@ -874,6 +944,11 @@ static int faultin_page(struct vm_area_struct *vma, */ fault_flags |= FAULT_FLAG_TRIED; } + if (unshare) { + fault_flags |= FAULT_FLAG_UNSHARE; + /* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */ + VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE); + } ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_ERROR) { @@ -1095,8 +1170,9 @@ retry: cond_resched(); page = follow_page_mask(vma, start, foll_flags, &ctx); - if (!page) { - ret = faultin_page(vma, start, &foll_flags, locked); + if (!page || PTR_ERR(page) == -EMLINK) { + ret = faultin_page(vma, start, &foll_flags, + PTR_ERR(page) == -EMLINK, locked); switch (ret) { case 0: goto retry; @@ -2227,6 +2303,11 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, goto pte_unmap; } + if (!pte_write(pte) && gup_must_unshare(flags, page)) { + gup_put_folio(folio, 1, flags); + goto pte_unmap; + } + /* * We need to make the page accessible if and only if we are * going to access its content (the FOLL_PIN case). Please @@ -2407,6 +2488,11 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, return 0; } + if (!pte_write(pte) && gup_must_unshare(flags, &folio->page)) { + gup_put_folio(folio, refs, flags); + return 0; + } + *nr += refs; folio_set_referenced(folio); return 1; @@ -2468,6 +2554,11 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } + if (!pmd_write(orig) && gup_must_unshare(flags, &folio->page)) { + gup_put_folio(folio, refs, flags); + return 0; + } + *nr += refs; folio_set_referenced(folio); return 1; @@ -2503,6 +2594,11 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } + if (!pud_write(orig) && gup_must_unshare(flags, &folio->page)) { + gup_put_folio(folio, refs, flags); + return 0; + } + *nr += refs; folio_set_referenced(folio); return 1; @@ -2740,8 +2836,10 @@ static unsigned long lockless_pages_from_mm(unsigned long start, */ if (gup_flags & FOLL_PIN) { if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { - unpin_user_pages(pages, nr_pinned); + unpin_user_pages_lockless(pages, nr_pinned); return 0; + } else { + sanity_check_pinned_pages(pages, nr_pinned); } } return nr_pinned; @@ -2900,6 +2998,9 @@ int pin_user_pages_fast(unsigned long start, int nr_pages, if (WARN_ON_ONCE(gup_flags & FOLL_GET)) return -EINVAL; + if (WARN_ON_ONCE(!pages)) + return -EINVAL; + gup_flags |= FOLL_PIN; return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages); } @@ -2922,6 +3023,9 @@ int pin_user_pages_fast_only(unsigned long start, int nr_pages, */ if (WARN_ON_ONCE(gup_flags & FOLL_GET)) return 0; + + if (WARN_ON_ONCE(!pages)) + return 0; /* * FOLL_FAST_ONLY is required in order to match the API description of * this routine: no fall back to regular ("slow") GUP. @@ -2949,8 +3053,7 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only); * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. Or NULL, if caller - * only intends to ensure the pages are faulted in. + * Should be at least nr_pages long. * @vmas: array of pointers to vmas corresponding to each page. * Or NULL if the caller does not require them. * @locked: pointer to lock flag indicating whether lock is held and @@ -2973,6 +3076,9 @@ long pin_user_pages_remote(struct mm_struct *mm, if (WARN_ON_ONCE(gup_flags & FOLL_GET)) return -EINVAL; + if (WARN_ON_ONCE(!pages)) + return -EINVAL; + gup_flags |= FOLL_PIN; return __get_user_pages_remote(mm, start, nr_pages, gup_flags, pages, vmas, locked); @@ -2986,8 +3092,7 @@ EXPORT_SYMBOL(pin_user_pages_remote); * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. Or NULL, if caller - * only intends to ensure the pages are faulted in. + * Should be at least nr_pages long. * @vmas: array of pointers to vmas corresponding to each page. * Or NULL if the caller does not require them. * @@ -3005,6 +3110,9 @@ long pin_user_pages(unsigned long start, unsigned long nr_pages, if (WARN_ON_ONCE(gup_flags & FOLL_GET)) return -EINVAL; + if (WARN_ON_ONCE(!pages)) + return -EINVAL; + gup_flags |= FOLL_PIN; return __gup_longterm_locked(current->mm, start, nr_pages, pages, vmas, gup_flags); @@ -3023,6 +3131,9 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, if (WARN_ON_ONCE(gup_flags & FOLL_GET)) return -EINVAL; + if (WARN_ON_ONCE(!pages)) + return -EINVAL; + gup_flags |= FOLL_PIN; return get_user_pages_unlocked(start, nr_pages, pages, gup_flags); } @@ -239,7 +239,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, pte_t pte = *ptep; uint64_t pfn_req_flags = *hmm_pfn; - if (pte_none(pte)) { + if (pte_none_mostly(pte)) { required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); if (required_fault) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 910a138e9859..a77c78a2b6b5 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -39,6 +39,7 @@ #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" +#include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/thp.h> @@ -68,13 +69,6 @@ static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; -static inline bool file_thp_enabled(struct vm_area_struct *vma) -{ - return transhuge_vma_enabled(vma, vma->vm_flags) && vma->vm_file && - !inode_is_open_for_write(vma->vm_file->f_inode) && - (vma->vm_flags & VM_EXEC); -} - bool transparent_hugepage_active(struct vm_area_struct *vma) { /* The addr is used to check if the vma size fits */ @@ -86,8 +80,8 @@ bool transparent_hugepage_active(struct vm_area_struct *vma) return __transparent_hugepage_enabled(vma); if (vma_is_shmem(vma)) return shmem_huge_enabled(vma); - if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) - return file_thp_enabled(vma); + if (transhuge_vma_enabled(vma, vma->vm_flags) && file_thp_enabled(vma)) + return true; return false; } @@ -647,7 +641,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr, true); + page_add_new_anon_rmap(page, vma, haddr); lru_cache_add_inactive_or_unevictable(page, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); @@ -725,15 +719,15 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; gfp_t gfp; - struct page *page; + struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; if (!transhuge_vma_suitable(vma, haddr)) return VM_FAULT_FALLBACK; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; - if (unlikely(khugepaged_enter(vma, vma->vm_flags))) - return VM_FAULT_OOM; + khugepaged_enter(vma, vma->vm_flags); + if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm) && transparent_hugepage_use_zero_page()) { @@ -774,13 +768,12 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) return ret; } gfp = vma_thp_gfp_mask(vma); - page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); - if (unlikely(!page)) { + folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true); + if (unlikely(!folio)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - prep_transhuge_page(page); - return __do_huge_pmd_anonymous_page(vmf, page, gfp); + return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp); } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1054,7 +1047,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, swp_entry_t entry = pmd_to_swp_entry(pmd); VM_BUG_ON(!is_pmd_migration_entry(pmd)); - if (is_writable_migration_entry(entry)) { + if (!is_readable_migration_entry(entry)) { entry = make_readable_migration_entry( swp_offset(entry)); pmd = swp_entry_to_pmd(entry); @@ -1097,23 +1090,16 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); - /* - * If this page is a potentially pinned page, split and retry the fault - * with smaller page size. Normally this should not happen because the - * userspace should use MADV_DONTFORK upon pinned regions. This is a - * best effort that the pinned pages won't be replaced by another - * random page during the coming copy-on-write. - */ - if (unlikely(page_needs_cow_for_dma(src_vma, src_page))) { + get_page(src_page); + if (unlikely(page_try_dup_anon_rmap(src_page, true, src_vma))) { + /* Page maybe pinned: split and retry the fault on PTEs. */ + put_page(src_page); pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); __split_huge_pmd(src_vma, src_pmd, addr, false, NULL); return -EAGAIN; } - - get_page(src_page); - page_dup_rmap(src_page, true); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); out_zero_page: mm_inc_nr_ptes(dst_mm); @@ -1217,14 +1203,10 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* No huge zero pud yet */ } - /* Please refer to comments in copy_huge_pmd() */ - if (unlikely(page_needs_cow_for_dma(vma, pud_page(pud)))) { - spin_unlock(src_ptl); - spin_unlock(dst_ptl); - __split_huge_pud(vma, src_pud, addr); - return -EAGAIN; - } - + /* + * TODO: once we support anonymous pages, use page_try_dup_anon_rmap() + * and split if duplicating fails. + */ pudp_set_wrprotect(src_mm, addr, src_pud); pud = pud_mkold(pud_wrprotect(pud)); set_pud_at(dst_mm, addr, dst_pud, pud); @@ -1282,6 +1264,7 @@ unlock: vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; @@ -1290,6 +1273,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); + VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE)); + VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE)); + if (is_huge_zero_pmd(orig_pmd)) goto fallback; @@ -1303,6 +1289,10 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) page = pmd_page(orig_pmd); VM_BUG_ON_PAGE(!PageHead(page), page); + /* Early check when only holding the PT lock. */ + if (PageAnonExclusive(page)) + goto reuse; + if (!trylock_page(page)) { get_page(page); spin_unlock(vmf->ptl); @@ -1317,8 +1307,14 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) put_page(page); } + /* Recheck after temporarily dropping the PT lock. */ + if (PageAnonExclusive(page)) { + unlock_page(page); + goto reuse; + } + /* - * See do_wp_page(): we can only map the page writable if there are + * See do_wp_page(): we can only reuse the page exclusively if there are * no additional references. Note that we always drain the LRU * pagevecs immediately after adding a THP. */ @@ -1328,11 +1324,18 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) try_to_free_swap(page); if (page_count(page) == 1) { pmd_t entry; + + page_move_anon_rmap(page, vma); + unlock_page(page); +reuse: + if (unlikely(unshare)) { + spin_unlock(vmf->ptl); + return 0; + } entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); - unlock_page(page); spin_unlock(vmf->ptl); return VM_FAULT_WRITE; } @@ -1379,6 +1382,12 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page = pmd_page(*pmd); VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + if (!pmd_write(*pmd) && gup_must_unshare(flags, page)) + return ERR_PTR(-EMLINK); + + VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && + !PageAnonExclusive(page), page); + if (!try_grab_page(page, flags)) return ERR_PTR(-ENOMEM); @@ -1692,18 +1701,21 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, * or if prot_numa but THP migration is not supported * - HPAGE_PMD_NR if protections changed and TLB flush necessary */ -int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, pgprot_t newprot, unsigned long cp_flags) +int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, pgprot_t newprot, + unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; - pmd_t entry; + pmd_t oldpmd, entry; bool preserve_write; int ret; bool prot_numa = cp_flags & MM_CP_PROT_NUMA; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + tlb_change_page_size(tlb, HPAGE_PMD_SIZE); + if (prot_numa && !thp_migration_supported()) return 1; @@ -1717,6 +1729,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (is_swap_pmd(*pmd)) { swp_entry_t entry = pmd_to_swp_entry(*pmd); + struct page *page = pfn_swap_entry_to_page(entry); VM_BUG_ON(!is_pmd_migration_entry(*pmd)); if (is_writable_migration_entry(entry)) { @@ -1725,8 +1738,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * A protection check is difficult so * just be safe and disable write */ - entry = make_readable_migration_entry( - swp_offset(entry)); + if (PageAnon(page)) + entry = make_readable_exclusive_migration_entry(swp_offset(entry)); + else + entry = make_readable_migration_entry(swp_offset(entry)); newpmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*pmd)) newpmd = pmd_swp_mksoft_dirty(newpmd); @@ -1778,12 +1793,12 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * The race makes MADV_DONTNEED miss the huge pmd and don't clear it * which may break userspace. * - * pmdp_invalidate() is required to make sure we don't miss + * pmdp_invalidate_ad() is required to make sure we don't miss * dirty/young flags set by hardware. */ - entry = pmdp_invalidate(vma, addr, pmd); + oldpmd = pmdp_invalidate_ad(vma, addr, pmd); - entry = pmd_modify(entry, newprot); + entry = pmd_modify(oldpmd, newprot); if (preserve_write) entry = pmd_mk_savedwrite(entry); if (uffd_wp) { @@ -1799,6 +1814,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, } ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); + + if (huge_pmd_needs_flush(oldpmd, entry)) + tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE); + BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry)); unlock: spin_unlock(ptl); @@ -1946,6 +1965,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable_t pgtable; pmd_t old_pmd, _pmd; bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false; + bool anon_exclusive = false; unsigned long addr; int i; @@ -2027,6 +2047,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); + if (PageAnon(page)) + anon_exclusive = is_readable_exclusive_migration_entry(entry); young = false; soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); @@ -2038,8 +2060,26 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, young = pmd_young(old_pmd); soft_dirty = pmd_soft_dirty(old_pmd); uffd_wp = pmd_uffd_wp(old_pmd); + VM_BUG_ON_PAGE(!page_count(page), page); page_ref_add(page, HPAGE_PMD_NR - 1); + + /* + * Without "freeze", we'll simply split the PMD, propagating the + * PageAnonExclusive() flag for each PTE by setting it for + * each subpage -- no need to (temporarily) clear. + * + * With "freeze" we want to replace mapped pages by + * migration entries right away. This is only possible if we + * managed to clear PageAnonExclusive() -- see + * set_pmd_migration_entry(). + * + * In case we cannot clear PageAnonExclusive(), split the PMD + * only and let try_to_migrate_one() fail later. + */ + anon_exclusive = PageAnon(page) && PageAnonExclusive(page); + if (freeze && anon_exclusive && page_try_share_anon_rmap(page)) + freeze = false; } /* @@ -2061,6 +2101,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, if (write) swp_entry = make_writable_migration_entry( page_to_pfn(page + i)); + else if (anon_exclusive) + swp_entry = make_readable_exclusive_migration_entry( + page_to_pfn(page + i)); else swp_entry = make_readable_migration_entry( page_to_pfn(page + i)); @@ -2072,6 +2115,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } else { entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); entry = maybe_mkwrite(entry, vma); + if (anon_exclusive) + SetPageAnonExclusive(page + i); if (!write) entry = pte_wrprotect(entry); if (!young) @@ -2249,8 +2294,6 @@ static void unmap_page(struct page *page) try_to_migrate(folio, ttu_flags); else try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); - - VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); } static void remap_page(struct folio *folio, unsigned long nr) @@ -2305,6 +2348,13 @@ static void __split_huge_page_tail(struct page *head, int tail, * * After successful get_page_unless_zero() might follow flags change, * for example lock_page() which set PG_waiters. + * + * Note that for mapped sub-pages of an anonymous THP, + * PG_anon_exclusive has been cleared in unmap_page() and is stored in + * the migration entry instead from where remap_page() will restore it. + * We can still have PG_anon_exclusive set on effectively unmapped and + * unreferenced sub-pages of an anonymous THP: we can simply drop + * PG_anon_exclusive (-> PG_mappedtodisk) for these here. */ page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (head->flags & @@ -3035,25 +3085,35 @@ late_initcall(split_huge_pages_debugfs); #endif #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION -void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; + bool anon_exclusive; pmd_t pmdval; swp_entry_t entry; pmd_t pmdswp; if (!(pvmw->pmd && !pvmw->pte)) - return; + return 0; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = pmdp_invalidate(vma, address, pvmw->pmd); + + anon_exclusive = PageAnon(page) && PageAnonExclusive(page); + if (anon_exclusive && page_try_share_anon_rmap(page)) { + set_pmd_at(mm, address, pvmw->pmd, pmdval); + return -EBUSY; + } + if (pmd_dirty(pmdval)) set_page_dirty(page); if (pmd_write(pmdval)) entry = make_writable_migration_entry(page_to_pfn(page)); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry(page_to_pfn(page)); else entry = make_readable_migration_entry(page_to_pfn(page)); pmdswp = swp_entry_to_pmd(entry); @@ -3063,6 +3123,8 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, page_remove_rmap(page, vma, true); put_page(page); trace_set_migration_pmd(address, pmd_val(pmdswp)); + + return 0; } void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) @@ -3087,10 +3149,17 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); - if (PageAnon(new)) - page_add_anon_rmap(new, vma, mmun_start, true); - else + if (PageAnon(new)) { + rmap_t rmap_flags = RMAP_COMPOUND; + + if (!is_readable_migration_entry(entry)) + rmap_flags |= RMAP_EXCLUSIVE; + + page_add_anon_rmap(new, vma, mmun_start, rmap_flags); + } else { page_add_file_rmap(new, vma, true); + } + VM_BUG_ON(pmd_write(pmde) && PageAnon(new) && !PageAnonExclusive(new)); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); /* No need to invalidate - it was non-present before */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3fc721789743..01f0e2e5ab48 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -370,7 +370,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) } static inline long -hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from, +hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, long to, struct hstate *h, struct hugetlb_cgroup *cg, long *regions_needed) { @@ -379,7 +379,7 @@ hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from, if (!regions_needed) { nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); - list_add(&nrg->link, rg->link.prev); + list_add(&nrg->link, rg); coalesce_file_region(map, nrg); } else *regions_needed += 1; @@ -402,47 +402,52 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t, long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; - struct file_region *rg = NULL, *trg = NULL; + struct file_region *iter, *trg = NULL; + struct list_head *rg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range - * [last_accounted_offset, rg->from), at every iteration, with some + * [last_accounted_offset, iter->from), at every iteration, with some * bounds checking. */ - list_for_each_entry_safe(rg, trg, head, link) { + list_for_each_entry_safe(iter, trg, head, link) { /* Skip irrelevant regions that start before our range. */ - if (rg->from < f) { + if (iter->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ - if (rg->to > last_accounted_offset) - last_accounted_offset = rg->to; + if (iter->to > last_accounted_offset) + last_accounted_offset = iter->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ - if (rg->from >= t) + if (iter->from >= t) { + rg = iter->link.prev; break; + } - /* Add an entry for last_accounted_offset -> rg->from, and + /* Add an entry for last_accounted_offset -> iter->from, and * update last_accounted_offset. */ - if (rg->from > last_accounted_offset) - add += hugetlb_resv_map_add(resv, rg, + if (iter->from > last_accounted_offset) + add += hugetlb_resv_map_add(resv, iter->link.prev, last_accounted_offset, - rg->from, h, h_cg, + iter->from, h, h_cg, regions_needed); - last_accounted_offset = rg->to; + last_accounted_offset = iter->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ + if (!rg) + rg = head->prev; if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); @@ -1535,7 +1540,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; - if (alloc_huge_page_vmemmap(h, page)) { + if (hugetlb_vmemmap_alloc(h, page)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the @@ -1612,7 +1617,7 @@ static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { - if (free_vmemmap_pages_per_hpage(h)) + if (hugetlb_optimize_vmemmap_pages(h)) flush_work(&free_hpage_work); } @@ -1672,6 +1677,8 @@ void free_huge_page(struct page *page) VM_BUG_ON_PAGE(page_mapcount(page), page); hugetlb_set_page_subpool(page, NULL); + if (PageAnon(page)) + __ClearPageAnonExclusive(page); page->mapping = NULL; restore_reserve = HPageRestoreReserve(page); ClearHPageRestoreReserve(page); @@ -1732,7 +1739,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void __prep_new_huge_page(struct hstate *h, struct page *page) { - free_huge_page_vmemmap(h, page); + hugetlb_vmemmap_free(h, page); INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); hugetlb_set_page_subpool(page, NULL); @@ -2105,7 +2112,7 @@ retry: * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. */ - rc = alloc_huge_page_vmemmap(h, head); + rc = hugetlb_vmemmap_alloc(h, head); if (!rc) { /* * Move PageHWPoison flag from head page to the raw @@ -2979,8 +2986,6 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; - if (nid != NUMA_NO_NODE && nid >= nr_online_nodes) - return 0; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), @@ -3088,7 +3093,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) } /* do node specific alloc */ - for (i = 0; i < nr_online_nodes; i++) { + for_each_online_node(i) { if (h->max_huge_pages_node[i] > 0) { hugetlb_hstate_alloc_pages_onenode(h, i); node_specific_alloc = true; @@ -3420,7 +3425,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) remove_hugetlb_page_for_demote(h, page, false); spin_unlock_irq(&hugetlb_lock); - rc = alloc_huge_page_vmemmap(h, page); + rc = hugetlb_vmemmap_alloc(h, page); if (rc) { /* Allocation of vmemmmap failed, we can not demote page */ spin_lock_irq(&hugetlb_lock); @@ -4052,7 +4057,7 @@ static int __init hugetlb_init(void) default_hstate.max_huge_pages = default_hstate_max_huge_pages; - for (i = 0; i < nr_online_nodes; i++) + for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } @@ -4119,6 +4124,20 @@ bool __init __weak hugetlb_node_alloc_supported(void) { return true; } + +static void __init hugepages_clear_pages_in_node(void) +{ + if (!hugetlb_max_hstate) { + default_hstate_max_huge_pages = 0; + memset(default_hugepages_in_node, 0, + MAX_NUMNODES * sizeof(unsigned int)); + } else { + parsed_hstate->max_huge_pages = 0; + memset(parsed_hstate->max_huge_pages_node, 0, + MAX_NUMNODES * sizeof(unsigned int)); + } +} + /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz @@ -4138,7 +4157,7 @@ static int __init hugepages_setup(char *s) if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; - return 0; + return 1; } /* @@ -4154,7 +4173,7 @@ static int __init hugepages_setup(char *s) if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); - return 0; + return 1; } while (*p) { @@ -4165,11 +4184,11 @@ static int __init hugepages_setup(char *s) if (p[count] == ':') { if (!hugetlb_node_alloc_supported()) { pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); - return 0; + return 1; } - if (tmp >= nr_online_nodes) + if (tmp >= MAX_NUMNODES || !node_online(tmp)) goto invalid; - node = array_index_nospec(tmp, nr_online_nodes); + node = array_index_nospec(tmp, MAX_NUMNODES); p += count + 1; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) @@ -4206,7 +4225,8 @@ static int __init hugepages_setup(char *s) invalid: pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); - return 0; + hugepages_clear_pages_in_node(); + return 1; } __setup("hugepages=", hugepages_setup); @@ -4227,7 +4247,7 @@ static int __init hugepagesz_setup(char *s) if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); - return 0; + return 1; } h = size_to_hstate(size); @@ -4242,7 +4262,7 @@ static int __init hugepagesz_setup(char *s) if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); - return 0; + return 1; } /* @@ -4273,14 +4293,14 @@ static int __init default_hugepagesz_setup(char *s) parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); - return 0; + return 1; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); - return 0; + return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); @@ -4297,7 +4317,7 @@ static int __init default_hugepagesz_setup(char *s) */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; - for (i = 0; i < nr_online_nodes; i++) + for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) @@ -4699,24 +4719,27 @@ hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma) + struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma) { pte_t *src_pte, *dst_pte, entry, dst_entry; struct page *ptepage; unsigned long addr; - bool cow = is_cow_mapping(vma->vm_flags); - struct hstate *h = hstate_vma(vma); + bool cow = is_cow_mapping(src_vma->vm_flags); + struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); unsigned long npages = pages_per_huge_page(h); - struct address_space *mapping = vma->vm_file->f_mapping; + struct address_space *mapping = src_vma->vm_file->f_mapping; struct mmu_notifier_range range; int ret = 0; if (cow) { - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src, - vma->vm_start, - vma->vm_end); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src_vma, src, + src_vma->vm_start, + src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); + mmap_assert_write_locked(src); + raw_write_seqcount_begin(&src->write_protect_seq); } else { /* * For shared mappings i_mmap_rwsem must be held to call @@ -4727,12 +4750,12 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, i_mmap_lock_read(mapping); } - for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { + for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr, sz); if (!src_pte) continue; - dst_pte = huge_pte_alloc(dst, vma, addr, sz); + dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; @@ -4767,8 +4790,9 @@ again: } else if (unlikely(is_hugetlb_entry_migration(entry) || is_hugetlb_entry_hwpoisoned(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); + bool uffd_wp = huge_pte_uffd_wp(entry); - if (is_writable_migration_entry(swp_entry) && cow) { + if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. @@ -4776,38 +4800,53 @@ again: swp_entry = make_readable_migration_entry( swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); + if (userfaultfd_wp(src_vma) && uffd_wp) + entry = huge_pte_mkuffd_wp(entry); set_huge_swap_pte_at(src, addr, src_pte, entry, sz); } + if (!userfaultfd_wp(dst_vma) && uffd_wp) + entry = huge_pte_clear_uffd_wp(entry); set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz); + } else if (unlikely(is_pte_marker(entry))) { + /* + * We copy the pte marker only if the dst vma has + * uffd-wp enabled. + */ + if (userfaultfd_wp(dst_vma)) + set_huge_pte_at(dst, addr, dst_pte, entry); } else { entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); /* - * This is a rare case where we see pinned hugetlb - * pages while they're prone to COW. We need to do the - * COW earlier during fork. + * Failing to duplicate the anon rmap is a rare case + * where we see pinned hugetlb pages while they're + * prone to COW. We need to do the COW earlier during + * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ - if (unlikely(page_needs_cow_for_dma(vma, ptepage))) { + if (!PageAnon(ptepage)) { + page_dup_file_rmap(ptepage, true); + } else if (page_try_dup_anon_rmap(ptepage, true, + src_vma)) { pte_t src_pte_old = entry; struct page *new; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ - new = alloc_huge_page(vma, addr, 1); + new = alloc_huge_page(dst_vma, addr, 1); if (IS_ERR(new)) { put_page(ptepage); ret = PTR_ERR(new); break; } - copy_user_huge_page(new, ptepage, addr, vma, + copy_user_huge_page(new, ptepage, addr, dst_vma, npages); put_page(ptepage); @@ -4817,13 +4856,13 @@ again: spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); if (!pte_same(src_pte_old, entry)) { - restore_reserve_on_error(h, vma, addr, + restore_reserve_on_error(h, dst_vma, addr, new); put_page(new); /* dst_entry won't change as in child */ goto again; } - hugetlb_install_page(vma, dst_pte, addr, new); + hugetlb_install_page(dst_vma, dst_pte, addr, new); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; @@ -4841,7 +4880,6 @@ again: entry = huge_pte_wrprotect(entry); } - page_dup_rmap(ptepage, true); set_huge_pte_at(dst, addr, dst_pte, entry); hugetlb_count_add(npages, dst); } @@ -4849,10 +4887,12 @@ again: spin_unlock(dst_ptl); } - if (cow) + if (cow) { + raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); - else + } else { i_mmap_unlock_read(mapping); + } return ret; } @@ -4896,10 +4936,17 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, unsigned long old_addr_copy; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; + bool shared_pmd = false; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + /* + * In case of shared PMDs, we should cover the maximum possible + * range. + */ + flush_cache_range(vma, range.start, range.end); + mmu_notifier_invalidate_range_start(&range); /* Prevent race with file truncation */ i_mmap_lock_write(mapping); @@ -4916,8 +4963,10 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, */ old_addr_copy = old_addr; - if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) + if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) { + shared_pmd = true; continue; + } dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) @@ -4925,7 +4974,11 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte); } - flush_tlb_range(vma, old_end - len, old_end); + + if (shared_pmd) + flush_tlb_range(vma, range.start, range.end); + else + flush_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); @@ -4934,7 +4987,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, - struct page *ref_page) + struct page *ref_page, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -4990,7 +5043,18 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { - huge_pte_clear(mm, address, ptep, sz); + /* + * If the pte was wr-protected by uffd-wp in any of the + * swap forms, meanwhile the caller does not want to + * drop the uffd-wp bit in this zap, then replace the + * pte with a marker. + */ + if (pte_swp_uffd_wp_any(pte) && + !(zap_flags & ZAP_FLAG_DROP_MARKER)) + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); + else + huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } @@ -5018,7 +5082,11 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); - + /* Leave a uffd-wp pte marker if needed */ + if (huge_pte_uffd_wp(pte) && + !(zap_flags & ZAP_FLAG_DROP_MARKER)) + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, vma, true); @@ -5052,9 +5120,10 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { - __unmap_hugepage_range(tlb, vma, start, end, ref_page); + __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags); /* * Clear this flag so that x86's huge_pmd_share page_table_shareable @@ -5070,12 +5139,13 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) + unsigned long end, struct page *ref_page, + zap_flags_t zap_flags) { struct mmu_gather tlb; tlb_gather_mmu(&tlb, vma->vm_mm); - __unmap_hugepage_range(&tlb, vma, start, end, ref_page); + __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags); tlb_finish_mmu(&tlb); } @@ -5130,21 +5200,22 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, - address + huge_page_size(h), page); + address + huge_page_size(h), page, 0); } i_mmap_unlock_write(mapping); } /* - * Hugetlb_cow() should be called with page lock of the original hugepage held. + * hugetlb_wp() should be called with page lock of the original hugepage held. * Called with hugetlb_fault_mutex_table held and pte_page locked so we * 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_cow(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *ptep, +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 page *pagecache_page, spinlock_t *ptl) { + const bool unshare = flags & FAULT_FLAG_UNSHARE; pte_t pte; struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; @@ -5153,17 +5224,26 @@ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr = address & huge_page_mask(h); struct mmu_notifier_range range; + VM_BUG_ON(unshare && (flags & FOLL_WRITE)); + VM_BUG_ON(!unshare && !(flags & FOLL_WRITE)); + pte = huge_ptep_get(ptep); old_page = pte_page(pte); retry_avoidcopy: - /* If no-one else is actually using this page, avoid the copy - * and just make the page writable */ + /* + * If no-one else is actually using this page, we're the exclusive + * owner and can reuse this page. + */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { - page_move_anon_rmap(old_page, vma); - set_huge_ptep_writable(vma, haddr, ptep); + if (!PageAnonExclusive(old_page)) + page_move_anon_rmap(old_page, vma); + if (likely(!unshare)) + set_huge_ptep_writable(vma, haddr, ptep); return 0; } + VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page), + old_page); /* * If the process that created a MAP_PRIVATE mapping is about to @@ -5262,13 +5342,13 @@ retry_avoidcopy: if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { ClearHPageRestoreReserve(new_page); - /* Break COW */ + /* Break COW or unshare */ huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); page_remove_rmap(old_page, vma, true); hugepage_add_new_anon_rmap(new_page, vma, haddr); set_huge_pte_at(mm, haddr, ptep, - make_huge_pte(vma, new_page, 1)); + make_huge_pte(vma, new_page, !unshare)); SetHPageMigratable(new_page); /* Make the old page be freed below */ new_page = old_page; @@ -5276,7 +5356,10 @@ retry_avoidcopy: spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: - /* No restore in case of successful pagetable update (Break COW) */ + /* + * No restore in case of successful pagetable update (Break COW or + * unshare) + */ if (new_page != old_page) restore_reserve_on_error(h, vma, haddr, new_page); put_page(new_page); @@ -5386,7 +5469,8 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, 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, unsigned int flags) + unsigned long address, pte_t *ptep, + pte_t old_pte, unsigned int flags) { struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; @@ -5401,7 +5485,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed - * COW. Warn that such a situation has occurred as it may not be obvious + * COW/unsharing. Warn that such a situation has occurred as it may not + * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", @@ -5512,22 +5597,29 @@ retry: ptl = huge_pte_lock(h, mm, ptep); ret = 0; - if (!huge_pte_none(huge_ptep_get(ptep))) + /* If pte changed from under us, retry */ + if (!pte_same(huge_ptep_get(ptep), old_pte)) goto backout; if (anon_rmap) { ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, vma, haddr); } else - page_dup_rmap(page, true); + page_dup_file_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); + /* + * If this pte was previously wr-protected, keep it wr-protected even + * if populated. + */ + if (unlikely(pte_marker_uffd_wp(old_pte))) + new_pte = huge_pte_wrprotect(huge_pte_mkuffd_wp(new_pte)); set_huge_pte_at(mm, haddr, ptep, new_pte); hugetlb_count_add(pages_per_huge_page(h), mm); if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_cow(mm, vma, address, ptep, page, ptl); + ret = hugetlb_wp(mm, vma, address, ptep, flags, page, ptl); } spin_unlock(ptl); @@ -5639,8 +5731,10 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); - if (huge_pte_none(entry)) { - ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); + /* PTE markers should be handled the same way as none pte */ + if (huge_pte_none_mostly(entry)) { + ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, + entry, flags); goto out_mutex; } @@ -5657,14 +5751,15 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, goto out_mutex; /* - * If we are going to COW the mapping later, we examine the pending - * reservations for this page now. This will ensure that any + * If we are going to COW/unshare the mapping later, we examine the + * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. For private mappings, we also lookup the pagecache * page now as it is used to determine if a reservation has been * consumed. */ - if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { + if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && + !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto out_mutex; @@ -5679,12 +5774,32 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); - /* Check for a racing update before calling hugetlb_cow */ + /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) 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)) { + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .real_address = address, + .flags = flags, + }; + + spin_unlock(ptl); + if (pagecache_page) { + unlock_page(pagecache_page); + put_page(pagecache_page); + } + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + return handle_userfault(&vmf, VM_UFFD_WP); + } + /* - * hugetlb_cow() requires page locks of pte_page(entry) and + * hugetlb_wp() requires page locks of pte_page(entry) and * pagecache_page, so here we need take the former one * when page != pagecache_page or !pagecache_page. */ @@ -5697,13 +5812,14 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, get_page(page); - if (flags & FAULT_FLAG_WRITE) { + if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(entry)) { - ret = hugetlb_cow(mm, vma, address, ptep, - pagecache_page, ptl); + ret = hugetlb_wp(mm, vma, address, ptep, flags, + pagecache_page, ptl); goto out_put_page; + } else if (likely(flags & FAULT_FLAG_WRITE)) { + entry = huge_pte_mkdirty(entry); } - entry = huge_pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (huge_ptep_set_access_flags(vma, haddr, ptep, entry, @@ -5746,7 +5862,8 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, enum mcopy_atomic_mode mode, - struct page **pagep) + struct page **pagep, + bool wp_copy) { bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); struct hstate *h = hstate_vma(dst_vma); @@ -5876,27 +5993,43 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_unlock; ret = -EEXIST; - if (!huge_pte_none(huge_ptep_get(dst_pte))) + /* + * We allow to overwrite a pte marker: consider when both MISSING|WP + * registered, we firstly wr-protect a none pte which has no page cache + * page backing it, then access the page. + */ + if (!huge_pte_none_mostly(huge_ptep_get(dst_pte))) goto out_release_unlock; if (vm_shared) { - page_dup_rmap(page, true); + page_dup_file_rmap(page, true); } else { ClearHPageRestoreReserve(page); hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); } - /* For CONTINUE on a non-shared VMA, don't set VM_WRITE for CoW. */ - if (is_continue && !vm_shared) + /* + * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY + * with wp flag set, don't set pte write bit. + */ + if (wp_copy || (is_continue && !vm_shared)) writable = 0; else writable = dst_vma->vm_flags & VM_WRITE; _dst_pte = make_huge_pte(dst_vma, page, writable); - if (writable) - _dst_pte = huge_pte_mkdirty(_dst_pte); + /* + * Always mark UFFDIO_COPY page dirty; note that this may not be + * extremely important for hugetlbfs for now since swapping is not + * supported, but we should still be clear in that this page cannot be + * thrown away at will, even if write bit not set. + */ + _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); + if (wp_copy) + _dst_pte = huge_pte_mkuffd_wp(_dst_pte); + set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); (void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte, @@ -5940,6 +6073,25 @@ static void record_subpages_vmas(struct page *page, struct vm_area_struct *vma, } } +static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte, + bool *unshare) +{ + pte_t pteval = huge_ptep_get(pte); + + *unshare = false; + if (is_swap_pte(pteval)) + return true; + if (huge_pte_write(pteval)) + return false; + if (flags & FOLL_WRITE) + return true; + if (gup_must_unshare(flags, pte_page(pteval))) { + *unshare = true; + return true; + } + return false; +} + long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, @@ -5954,6 +6106,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, while (vaddr < vma->vm_end && remainder) { pte_t *pte; spinlock_t *ptl = NULL; + bool unshare = false; int absent; struct page *page; @@ -6004,9 +6157,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * both cases, and because we can't follow correct pages * directly from any kind of swap entries. */ - if (absent || is_swap_pte(huge_ptep_get(pte)) || - ((flags & FOLL_WRITE) && - !huge_pte_write(huge_ptep_get(pte)))) { + if (absent || + __follow_hugetlb_must_fault(flags, pte, &unshare)) { vm_fault_t ret; unsigned int fault_flags = 0; @@ -6014,6 +6166,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, spin_unlock(ptl); if (flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; + else if (unshare) + fault_flags |= FAULT_FLAG_UNSHARE; if (locked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; @@ -6055,6 +6209,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); + VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && + !PageAnonExclusive(page), page); + /* * If subpage information not requested, update counters * and skip the same_page loop below. @@ -6117,16 +6274,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, } unsigned long hugetlb_change_protection(struct vm_area_struct *vma, - unsigned long address, unsigned long end, pgprot_t newprot) + unsigned long address, unsigned long end, + pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); - unsigned long pages = 0; + unsigned long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; + bool uffd_wp = cp_flags & MM_CP_UFFD_WP; + bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond @@ -6142,13 +6302,19 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, mmu_notifier_invalidate_range_start(&range); i_mmap_lock_write(vma->vm_file->f_mapping); - for (; address < end; address += huge_page_size(h)) { + for (; address < end; address += psize) { spinlock_t *ptl; - ptep = huge_pte_offset(mm, address, huge_page_size(h)); + ptep = huge_pte_offset(mm, address, psize); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, &address, ptep)) { + /* + * When uffd-wp is enabled on the vma, unshare + * shouldn't happen at all. Warn about it if it + * happened due to some reason. + */ + WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); shared_pmd = true; @@ -6161,20 +6327,37 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); + struct page *page = pfn_swap_entry_to_page(entry); - if (is_writable_migration_entry(entry)) { + if (!is_readable_migration_entry(entry)) { pte_t newpte; - entry = make_readable_migration_entry( - swp_offset(entry)); + if (PageAnon(page)) + entry = make_readable_exclusive_migration_entry( + swp_offset(entry)); + else + entry = make_readable_migration_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); set_huge_swap_pte_at(mm, address, ptep, - newpte, huge_page_size(h)); + newpte, psize); pages++; } spin_unlock(ptl); continue; } + if (unlikely(pte_marker_uffd_wp(pte))) { + /* + * This is changing a non-present pte into a none pte, + * no need for huge_ptep_modify_prot_start/commit(). + */ + if (uffd_wp_resolve) + huge_pte_clear(mm, address, ptep, psize); + } if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); @@ -6182,8 +6365,18 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); + if (uffd_wp) + pte = huge_pte_mkuffd_wp(huge_pte_wrprotect(pte)); + else if (uffd_wp_resolve) + pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; + } else { + /* None pte */ + if (unlikely(uffd_wp)) + /* Safe to modify directly (none->non-present). */ + set_huge_pte_at(mm, address, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP)); } spin_unlock(ptl); } @@ -6686,9 +6879,11 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, spinlock_t *ptl; pte_t pte; - /* FOLL_GET and FOLL_PIN are mutually exclusive. */ - if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == - (FOLL_PIN | FOLL_GET))) + /* + * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via + * follow_hugetlb_page(). + */ + if (WARN_ON_ONCE(flags & FOLL_PIN)) return NULL; retry: @@ -6776,7 +6971,9 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb) spin_lock_irq(&hugetlb_lock); if (PageHeadHuge(page)) { *hugetlb = true; - if (HPageFreed(page) || HPageMigratable(page)) + if (HPageFreed(page)) + ret = 0; + else if (HPageMigratable(page)) ret = get_page_unless_zero(page); else ret = -EBUSY; @@ -6866,6 +7063,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) if (start >= end) return; + flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. @@ -6951,7 +7149,7 @@ void __init hugetlb_cma_reserve(int order) if (hugetlb_cma_size_in_node[nid] == 0) continue; - if (!node_state(nid, N_ONLINE)) { + if (!node_online(nid)) { pr_warn("hugetlb_cma: invalid node %d specified\n", nid); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; @@ -6990,7 +7188,7 @@ void __init hugetlb_cma_reserve(int order) } reserved = 0; - for_each_node_state(nid, N_ONLINE) { + for_each_online_node(nid) { int res; char name[CMA_MAX_NAME]; diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 791626983c2e..fcd9f7872064 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -1,181 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Free some vmemmap pages of HugeTLB + * Optimize vmemmap pages associated with HugeTLB * * Copyright (c) 2020, Bytedance. All rights reserved. * * Author: Muchun Song <songmuchun@bytedance.com> * - * The struct page structures (page structs) are used to describe a physical - * page frame. By default, there is a one-to-one mapping from a page frame to - * it's corresponding page struct. - * - * HugeTLB pages consist of multiple base page size pages and is supported by - * many architectures. See hugetlbpage.rst in the Documentation directory for - * more details. On the x86-64 architecture, HugeTLB pages of size 2MB and 1GB - * are currently supported. Since the base page size on x86 is 4KB, a 2MB - * HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of - * 4096 base pages. For each base page, there is a corresponding page struct. - * - * Within the HugeTLB subsystem, only the first 4 page structs are used to - * contain unique information about a HugeTLB page. __NR_USED_SUBPAGE provides - * this upper limit. The only 'useful' information in the remaining page structs - * is the compound_head field, and this field is the same for all tail pages. - * - * By removing redundant page structs for HugeTLB pages, memory can be returned - * to the buddy allocator for other uses. - * - * Different architectures support different HugeTLB pages. For example, the - * following table is the HugeTLB page size supported by x86 and arm64 - * architectures. Because arm64 supports 4k, 16k, and 64k base pages and - * supports contiguous entries, so it supports many kinds of sizes of HugeTLB - * page. - * - * +--------------+-----------+-----------------------------------------------+ - * | Architecture | Page Size | HugeTLB Page Size | - * +--------------+-----------+-----------+-----------+-----------+-----------+ - * | x86-64 | 4KB | 2MB | 1GB | | | - * +--------------+-----------+-----------+-----------+-----------+-----------+ - * | | 4KB | 64KB | 2MB | 32MB | 1GB | - * | +-----------+-----------+-----------+-----------+-----------+ - * | arm64 | 16KB | 2MB | 32MB | 1GB | | - * | +-----------+-----------+-----------+-----------+-----------+ - * | | 64KB | 2MB | 512MB | 16GB | | - * +--------------+-----------+-----------+-----------+-----------+-----------+ - * - * When the system boot up, every HugeTLB page has more than one struct page - * structs which size is (unit: pages): - * - * struct_size = HugeTLB_Size / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE - * - * Where HugeTLB_Size is the size of the HugeTLB page. We know that the size - * of the HugeTLB page is always n times PAGE_SIZE. So we can get the following - * relationship. - * - * HugeTLB_Size = n * PAGE_SIZE - * - * Then, - * - * struct_size = n * PAGE_SIZE / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE - * = n * sizeof(struct page) / PAGE_SIZE - * - * We can use huge mapping at the pud/pmd level for the HugeTLB page. - * - * For the HugeTLB page of the pmd level mapping, then - * - * struct_size = n * sizeof(struct page) / PAGE_SIZE - * = PAGE_SIZE / sizeof(pte_t) * sizeof(struct page) / PAGE_SIZE - * = sizeof(struct page) / sizeof(pte_t) - * = 64 / 8 - * = 8 (pages) - * - * Where n is how many pte entries which one page can contains. So the value of - * n is (PAGE_SIZE / sizeof(pte_t)). - * - * This optimization only supports 64-bit system, so the value of sizeof(pte_t) - * is 8. And this optimization also applicable only when the size of struct page - * is a power of two. In most cases, the size of struct page is 64 bytes (e.g. - * x86-64 and arm64). So if we use pmd level mapping for a HugeTLB page, the - * size of struct page structs of it is 8 page frames which size depends on the - * size of the base page. - * - * For the HugeTLB page of the pud level mapping, then - * - * struct_size = PAGE_SIZE / sizeof(pmd_t) * struct_size(pmd) - * = PAGE_SIZE / 8 * 8 (pages) - * = PAGE_SIZE (pages) - * - * Where the struct_size(pmd) is the size of the struct page structs of a - * HugeTLB page of the pmd level mapping. - * - * E.g.: A 2MB HugeTLB page on x86_64 consists in 8 page frames while 1GB - * HugeTLB page consists in 4096. - * - * Next, we take the pmd level mapping of the HugeTLB page as an example to - * show the internal implementation of this optimization. There are 8 pages - * struct page structs associated with a HugeTLB page which is pmd mapped. - * - * Here is how things look before optimization. - * - * HugeTLB struct pages(8 pages) page frame(8 pages) - * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ - * | | | 0 | -------------> | 0 | - * | | +-----------+ +-----------+ - * | | | 1 | -------------> | 1 | - * | | +-----------+ +-----------+ - * | | | 2 | -------------> | 2 | - * | | +-----------+ +-----------+ - * | | | 3 | -------------> | 3 | - * | | +-----------+ +-----------+ - * | | | 4 | -------------> | 4 | - * | PMD | +-----------+ +-----------+ - * | level | | 5 | -------------> | 5 | - * | mapping | +-----------+ +-----------+ - * | | | 6 | -------------> | 6 | - * | | +-----------+ +-----------+ - * | | | 7 | -------------> | 7 | - * | | +-----------+ +-----------+ - * | | - * | | - * | | - * +-----------+ - * - * The value of page->compound_head is the same for all tail pages. The first - * page of page structs (page 0) associated with the HugeTLB page contains the 4 - * page structs necessary to describe the HugeTLB. The only use of the remaining - * pages of page structs (page 1 to page 7) is to point to page->compound_head. - * Therefore, we can remap pages 1 to 7 to page 0. Only 1 page of page structs - * will be used for each HugeTLB page. This will allow us to free the remaining - * 7 pages to the buddy allocator. - * - * Here is how things look after remapping. - * - * HugeTLB struct pages(8 pages) page frame(8 pages) - * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ - * | | | 0 | -------------> | 0 | - * | | +-----------+ +-----------+ - * | | | 1 | ---------------^ ^ ^ ^ ^ ^ ^ - * | | +-----------+ | | | | | | - * | | | 2 | -----------------+ | | | | | - * | | +-----------+ | | | | | - * | | | 3 | -------------------+ | | | | - * | | +-----------+ | | | | - * | | | 4 | ---------------------+ | | | - * | PMD | +-----------+ | | | - * | level | | 5 | -----------------------+ | | - * | mapping | +-----------+ | | - * | | | 6 | -------------------------+ | - * | | +-----------+ | - * | | | 7 | ---------------------------+ - * | | +-----------+ - * | | - * | | - * | | - * +-----------+ - * - * When a HugeTLB is freed to the buddy system, we should allocate 7 pages for - * vmemmap pages and restore the previous mapping relationship. - * - * For the HugeTLB page of the pud level mapping. It is similar to the former. - * We also can use this approach to free (PAGE_SIZE - 1) vmemmap pages. - * - * Apart from the HugeTLB page of the pmd/pud level mapping, some architectures - * (e.g. aarch64) provides a contiguous bit in the translation table entries - * that hints to the MMU to indicate that it is one of a contiguous set of - * entries that can be cached in a single TLB entry. - * - * The contiguous bit is used to increase the mapping size at the pmd and pte - * (last) level. So this type of HugeTLB page can be optimized only when its - * size of the struct page structs is greater than 1 page. - * - * Notice: The head vmemmap page is not freed to the buddy allocator and all - * tail vmemmap pages are mapped to the head vmemmap page frame. So we can see - * more than one struct page struct with PG_head (e.g. 8 per 2 MB HugeTLB page) - * associated with each HugeTLB page. The compound_head() can handle this - * correctly (more details refer to the comment above compound_head()). + * See Documentation/vm/vmemmap_dedup.rst */ #define pr_fmt(fmt) "HugeTLB: " fmt +#include <linux/memory_hotplug.h> #include "hugetlb_vmemmap.h" /* @@ -188,53 +23,63 @@ #define RESERVE_VMEMMAP_NR 1U #define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT) -DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, - hugetlb_free_vmemmap_enabled_key); -EXPORT_SYMBOL(hugetlb_free_vmemmap_enabled_key); +enum vmemmap_optimize_mode { + VMEMMAP_OPTIMIZE_OFF, + VMEMMAP_OPTIMIZE_ON, +}; -static int __init early_hugetlb_free_vmemmap_param(char *buf) -{ - /* We cannot optimize if a "struct page" crosses page boundaries. */ - if (!is_power_of_2(sizeof(struct page))) { - pr_warn("cannot free vmemmap pages because \"struct page\" crosses page boundaries\n"); - return 0; - } +DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, + hugetlb_optimize_vmemmap_key); +EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key); - if (!buf) - return -EINVAL; +static enum vmemmap_optimize_mode vmemmap_optimize_mode = + IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON); - if (!strcmp(buf, "on")) - static_branch_enable(&hugetlb_free_vmemmap_enabled_key); - else if (!strcmp(buf, "off")) - static_branch_disable(&hugetlb_free_vmemmap_enabled_key); - else - return -EINVAL; +static void vmemmap_optimize_mode_switch(enum vmemmap_optimize_mode to) +{ + if (vmemmap_optimize_mode == to) + return; - return 0; + if (to == VMEMMAP_OPTIMIZE_OFF) + static_branch_dec(&hugetlb_optimize_vmemmap_key); + else + static_branch_inc(&hugetlb_optimize_vmemmap_key); + WRITE_ONCE(vmemmap_optimize_mode, to); } -early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param); -static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h) +static int __init hugetlb_vmemmap_early_param(char *buf) { - return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT; + bool enable; + enum vmemmap_optimize_mode mode; + + if (kstrtobool(buf, &enable)) + return -EINVAL; + + mode = enable ? VMEMMAP_OPTIMIZE_ON : VMEMMAP_OPTIMIZE_OFF; + vmemmap_optimize_mode_switch(mode); + + return 0; } +early_param("hugetlb_free_vmemmap", hugetlb_vmemmap_early_param); /* * Previously discarded vmemmap pages will be allocated and remapping * after this function returns zero. */ -int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head) { int ret; unsigned long vmemmap_addr = (unsigned long)head; - unsigned long vmemmap_end, vmemmap_reuse; + unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages; if (!HPageVmemmapOptimized(head)) return 0; - vmemmap_addr += RESERVE_VMEMMAP_SIZE; - vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); - vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_pages = hugetlb_optimize_vmemmap_pages(h); + vmemmap_end = vmemmap_addr + (vmemmap_pages << PAGE_SHIFT); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + /* * The pages which the vmemmap virtual address range [@vmemmap_addr, * @vmemmap_end) are mapped to are freed to the buddy allocator, and @@ -244,30 +89,40 @@ int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) */ ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse, GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE); - if (!ret) + if (!ret) { ClearHPageVmemmapOptimized(head); + static_branch_dec(&hugetlb_optimize_vmemmap_key); + } return ret; } -void free_huge_page_vmemmap(struct hstate *h, struct page *head) +void hugetlb_vmemmap_free(struct hstate *h, struct page *head) { unsigned long vmemmap_addr = (unsigned long)head; - unsigned long vmemmap_end, vmemmap_reuse; + unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages; - if (!free_vmemmap_pages_per_hpage(h)) + vmemmap_pages = hugetlb_optimize_vmemmap_pages(h); + if (!vmemmap_pages) return; - vmemmap_addr += RESERVE_VMEMMAP_SIZE; - vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); - vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF) + return; + + static_branch_inc(&hugetlb_optimize_vmemmap_key); + + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_end = vmemmap_addr + (vmemmap_pages << PAGE_SHIFT); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; /* * Remap the vmemmap virtual address range [@vmemmap_addr, @vmemmap_end) * to the page which @vmemmap_reuse is mapped to, then free the pages * which the range [@vmemmap_addr, @vmemmap_end] is mapped to. */ - if (!vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse)) + if (vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse)) + static_branch_dec(&hugetlb_optimize_vmemmap_key); + else SetHPageVmemmapOptimized(head); } @@ -278,14 +133,17 @@ void __init hugetlb_vmemmap_init(struct hstate *h) /* * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct - * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, + * page structs that can be used when CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP, * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page. */ BUILD_BUG_ON(__NR_USED_SUBPAGE >= RESERVE_VMEMMAP_SIZE / sizeof(struct page)); - if (!hugetlb_free_vmemmap_enabled()) + if (!is_power_of_2(sizeof(struct page))) { + pr_warn_once("cannot optimize vmemmap pages because \"struct page\" crosses page boundaries\n"); + static_branch_disable(&hugetlb_optimize_vmemmap_key); return; + } vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT; /* @@ -297,8 +155,57 @@ void __init hugetlb_vmemmap_init(struct hstate *h) * hugetlbpage.rst for more details. */ if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR)) - h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR; + h->optimize_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR; + + pr_info("can optimize %d vmemmap pages for %s\n", + h->optimize_vmemmap_pages, h->name); +} + +#ifdef CONFIG_PROC_SYSCTL +static int hugetlb_optimize_vmemmap_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, + loff_t *ppos) +{ + int ret; + enum vmemmap_optimize_mode mode; + static DEFINE_MUTEX(sysctl_mutex); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&sysctl_mutex); + mode = vmemmap_optimize_mode; + table->data = &mode; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (write && !ret) + vmemmap_optimize_mode_switch(mode); + mutex_unlock(&sysctl_mutex); - pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages, - h->name); + return ret; +} + +static struct ctl_table hugetlb_vmemmap_sysctls[] = { + { + .procname = "hugetlb_optimize_vmemmap", + .maxlen = sizeof(enum vmemmap_optimize_mode), + .mode = 0644, + .proc_handler = hugetlb_optimize_vmemmap_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static __init int hugetlb_vmemmap_sysctls_init(void) +{ + /* + * If "memory_hotplug.memmap_on_memory" is enabled or "struct page" + * crosses page boundaries, the vmemmap pages cannot be optimized. + */ + if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page))) + register_sysctl_init("vm", hugetlb_vmemmap_sysctls); + + return 0; } +late_initcall(hugetlb_vmemmap_sysctls_init); +#endif /* CONFIG_PROC_SYSCTL */ diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h index cb2bef8f9e73..109b0a53b6fe 100644 --- a/mm/hugetlb_vmemmap.h +++ b/mm/hugetlb_vmemmap.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Free some vmemmap pages of HugeTLB + * Optimize vmemmap pages associated with HugeTLB * * Copyright (c) 2020, Bytedance. All rights reserved. * @@ -10,26 +10,26 @@ #define _LINUX_HUGETLB_VMEMMAP_H #include <linux/hugetlb.h> -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -int alloc_huge_page_vmemmap(struct hstate *h, struct page *head); -void free_huge_page_vmemmap(struct hstate *h, struct page *head); +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head); +void hugetlb_vmemmap_free(struct hstate *h, struct page *head); void hugetlb_vmemmap_init(struct hstate *h); /* - * How many vmemmap pages associated with a HugeTLB page that can be freed - * to the buddy allocator. + * How many vmemmap pages associated with a HugeTLB page that can be + * optimized and freed to the buddy allocator. */ -static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h) +static inline unsigned int hugetlb_optimize_vmemmap_pages(struct hstate *h) { - return h->nr_free_vmemmap_pages; + return h->optimize_vmemmap_pages; } #else -static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +static inline int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head) { return 0; } -static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head) +static inline void hugetlb_vmemmap_free(struct hstate *h, struct page *head) { } @@ -37,9 +37,9 @@ static inline void hugetlb_vmemmap_init(struct hstate *h) { } -static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h) +static inline unsigned int hugetlb_optimize_vmemmap_pages(struct hstate *h) { return 0; } -#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */ +#endif /* CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP */ #endif /* _LINUX_HUGETLB_VMEMMAP_H */ diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index bb0cea5468cb..5c0cddd81505 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -65,6 +65,7 @@ DEFINE_DEBUGFS_ATTRIBUTE(unpoison_fops, NULL, hwpoison_unpoison, "%lli\n"); static void pfn_inject_exit(void) { + hwpoison_filter_enable = 0; debugfs_remove_recursive(hwpoison_dir); } diff --git a/mm/internal.h b/mm/internal.h index cf16280ce132..64e61b032dac 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -35,6 +35,21 @@ struct folio_batch; /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) +/* + * Different from WARN_ON_ONCE(), no warning will be issued + * when we specify __GFP_NOWARN. + */ +#define WARN_ON_ONCE_GFP(cond, gfp) ({ \ + static bool __section(".data.once") __warned; \ + int __ret_warn_once = !!(cond); \ + \ + if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ + __warned = true; \ + WARN_ON(1); \ + } \ + unlikely(__ret_warn_once); \ +}) + void page_writeback_init(void); static inline void *folio_raw_mapping(struct folio *folio) @@ -212,6 +227,67 @@ struct alloc_context { }; /* + * This function returns the order of a free page in the buddy system. In + * general, page_zone(page)->lock must be held by the caller to prevent the + * page from being allocated in parallel and returning garbage as the order. + * If a caller does not hold page_zone(page)->lock, it must guarantee that the + * page cannot be allocated or merged in parallel. Alternatively, it must + * handle invalid values gracefully, and use buddy_order_unsafe() below. + */ +static inline unsigned int buddy_order(struct page *page) +{ + /* PageBuddy() must be checked by the caller */ + return page_private(page); +} + +/* + * Like buddy_order(), but for callers who cannot afford to hold the zone lock. + * PageBuddy() should be checked first by the caller to minimize race window, + * and invalid values must be handled gracefully. + * + * READ_ONCE is used so that if the caller assigns the result into a local + * variable and e.g. tests it for valid range before using, the compiler cannot + * decide to remove the variable and inline the page_private(page) multiple + * times, potentially observing different values in the tests and the actual + * use of the result. + */ +#define buddy_order_unsafe(page) READ_ONCE(page_private(page)) + +/* + * This function checks whether a page is free && is the buddy + * we can coalesce a page and its buddy if + * (a) the buddy is not in a hole (check before calling!) && + * (b) the buddy is in the buddy system && + * (c) a page and its buddy have the same order && + * (d) a page and its buddy are in the same zone. + * + * For recording whether a page is in the buddy system, we set PageBuddy. + * Setting, clearing, and testing PageBuddy is serialized by zone->lock. + * + * For recording page's order, we use page_private(page). + */ +static inline bool page_is_buddy(struct page *page, struct page *buddy, + unsigned int order) +{ + if (!page_is_guard(buddy) && !PageBuddy(buddy)) + return false; + + if (buddy_order(buddy) != order) + return false; + + /* + * zone check is done late to avoid uselessly calculating + * zone/node ids for pages that could never merge. + */ + if (page_zone_id(page) != page_zone_id(buddy)) + return false; + + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + + return true; +} + +/* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * @@ -234,6 +310,35 @@ __find_buddy_pfn(unsigned long page_pfn, unsigned int order) return page_pfn ^ (1 << order); } +/* + * Find the buddy of @page and validate it. + * @page: The input page + * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the + * function is used in the performance-critical __free_one_page(). + * @order: The order of the page + * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to + * page_to_pfn(). + * + * The found buddy can be a non PageBuddy, out of @page's zone, or its order is + * not the same as @page. The validation is necessary before use it. + * + * Return: the found buddy page or NULL if not found. + */ +static inline struct page *find_buddy_page_pfn(struct page *page, + unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) +{ + unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); + struct page *buddy; + + buddy = page + (__buddy_pfn - pfn); + if (buddy_pfn) + *buddy_pfn = __buddy_pfn; + + if (page_is_buddy(page, buddy, order)) + return buddy; + return NULL; +} + extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); @@ -269,6 +374,9 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); +void split_free_page(struct page *free_page, + int order, unsigned long split_pfn_offset); + #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* @@ -312,7 +420,7 @@ struct compact_control { bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ - bool contended; /* Signal lock or sched contention */ + bool contended; /* Signal lock contention */ bool rescan; /* Rescanning the same pageblock */ bool alloc_contig; /* alloc_contig_range allocation */ }; @@ -332,38 +440,14 @@ isolate_freepages_range(struct compact_control *cc, int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); + +int __alloc_contig_migrate_range(struct compact_control *cc, + unsigned long start, unsigned long end); #endif int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); /* - * This function returns the order of a free page in the buddy system. In - * general, page_zone(page)->lock must be held by the caller to prevent the - * page from being allocated in parallel and returning garbage as the order. - * If a caller does not hold page_zone(page)->lock, it must guarantee that the - * page cannot be allocated or merged in parallel. Alternatively, it must - * handle invalid values gracefully, and use buddy_order_unsafe() below. - */ -static inline unsigned int buddy_order(struct page *page) -{ - /* PageBuddy() must be checked by the caller */ - return page_private(page); -} - -/* - * Like buddy_order(), but for callers who cannot afford to hold the zone lock. - * PageBuddy() should be checked first by the caller to minimize race window, - * and invalid values must be handled gracefully. - * - * READ_ONCE is used so that if the caller assigns the result into a local - * variable and e.g. tests it for valid range before using, the compiler cannot - * decide to remove the variable and inline the page_private(page) multiple - * times, potentially observing different values in the tests and the actual - * use of the result. - */ -#define buddy_order_unsafe(page) READ_ONCE(page_private(page)) - -/* * These three helpers classifies VMAs for virtual memory accounting. */ @@ -462,26 +546,22 @@ void mlock_page_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* - * At what user virtual address is page expected in 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. + * Return the start of user virtual address at the specific offset within + * a vma. */ static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) +vma_pgoff_address(pgoff_t pgoff, unsigned long nr_pages, + struct vm_area_struct *vma) { - pgoff_t pgoff; unsigned long address; - VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ - pgoff = page_to_pgoff(page); if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; - } else if (PageHead(page) && - pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { + } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { @@ -491,6 +571,18 @@ vma_address(struct page *page, struct vm_area_struct *vma) } /* + * 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. */ @@ -634,6 +726,9 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask) } #endif +/* + * mm/memory-failure.c + */ extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; @@ -643,6 +738,14 @@ extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; +#ifdef CONFIG_MEMORY_FAILURE +void clear_hwpoisoned_pages(struct page *memmap, int nr_pages); +#else +static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) +{ +} +#endif + extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/mm/kasan/common.c b/mm/kasan/common.c index d9079ec11f31..c40c0e7b3b5f 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -117,7 +117,7 @@ void __kasan_poison_pages(struct page *page, unsigned int order, bool init) { if (likely(!PageHighMem(page))) kasan_poison(page_address(page), PAGE_SIZE << order, - KASAN_FREE_PAGE, init); + KASAN_PAGE_FREE, init); } /* @@ -254,7 +254,7 @@ void __kasan_poison_slab(struct slab *slab) for (i = 0; i < compound_nr(page); i++) page_kasan_tag_reset(page + i); kasan_poison(page_address(page), page_size(page), - KASAN_KMALLOC_REDZONE, false); + KASAN_SLAB_REDZONE, false); } void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object) @@ -265,7 +265,7 @@ void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object) void __kasan_poison_object_data(struct kmem_cache *cache, void *object) { kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), - KASAN_KMALLOC_REDZONE, false); + KASAN_SLAB_REDZONE, false); } /* @@ -357,7 +357,7 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object, } kasan_poison(object, round_up(cache->object_size, KASAN_GRANULE_SIZE), - KASAN_KMALLOC_FREE, init); + KASAN_SLAB_FREE, init); if ((IS_ENABLED(CONFIG_KASAN_GENERIC) && !quarantine)) return false; @@ -414,7 +414,7 @@ void __kasan_slab_free_mempool(void *ptr, unsigned long ip) if (unlikely(!folio_test_slab(folio))) { if (____kasan_kfree_large(ptr, ip)) return; - kasan_poison(ptr, folio_size(folio), KASAN_FREE_PAGE, false); + kasan_poison(ptr, folio_size(folio), KASAN_PAGE_FREE, false); } else { struct slab *slab = folio_slab(folio); @@ -505,7 +505,7 @@ static inline void *____kasan_kmalloc(struct kmem_cache *cache, redzone_end = round_up((unsigned long)(object + cache->object_size), KASAN_GRANULE_SIZE); kasan_poison((void *)redzone_start, redzone_end - redzone_start, - KASAN_KMALLOC_REDZONE, false); + KASAN_SLAB_REDZONE, false); /* * Save alloc info (if possible) for kmalloc() allocations. diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index a25ad4090615..437fcc7e77cf 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -369,14 +369,14 @@ void kasan_set_free_info(struct kmem_cache *cache, kasan_set_track(&free_meta->free_track, GFP_NOWAIT); /* The object was freed and has free track set. */ - *(u8 *)kasan_mem_to_shadow(object) = KASAN_KMALLOC_FREETRACK; + *(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREETRACK; } struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, void *object, u8 tag) { - if (*(u8 *)kasan_mem_to_shadow(object) != KASAN_KMALLOC_FREETRACK) + if (*(u8 *)kasan_mem_to_shadow(object) != KASAN_SLAB_FREETRACK) return NULL; - /* Free meta must be present with KASAN_KMALLOC_FREETRACK. */ + /* Free meta must be present with KASAN_SLAB_FREETRACK. */ return &kasan_get_free_meta(cache, object)->free_track; } diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index b01b4bbe0409..610d60d6e5b8 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -42,6 +42,7 @@ static inline bool kasan_sync_fault_possible(void) { return kasan_mode == KASAN_MODE_SYNC || kasan_mode == KASAN_MODE_ASYMM; } + #else static inline bool kasan_stack_collection_enabled(void) @@ -73,47 +74,41 @@ static inline bool kasan_sync_fault_possible(void) #define KASAN_MEMORY_PER_SHADOW_PAGE (KASAN_GRANULE_SIZE << PAGE_SHIFT) #ifdef CONFIG_KASAN_GENERIC -#define KASAN_FREE_PAGE 0xFF /* page was freed */ -#define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */ -#define KASAN_KMALLOC_REDZONE 0xFC /* redzone inside slub object */ -#define KASAN_KMALLOC_FREE 0xFB /* object was freed (kmem_cache_free/kfree) */ -#define KASAN_VMALLOC_INVALID 0xF8 /* unallocated space in vmapped page */ +#define KASAN_PAGE_FREE 0xFF /* freed page */ +#define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocation */ +#define KASAN_SLAB_REDZONE 0xFC /* redzone for slab object */ +#define KASAN_SLAB_FREE 0xFB /* freed slab object */ +#define KASAN_VMALLOC_INVALID 0xF8 /* inaccessible space in vmap area */ #else -#define KASAN_FREE_PAGE KASAN_TAG_INVALID -#define KASAN_PAGE_REDZONE KASAN_TAG_INVALID -#define KASAN_KMALLOC_REDZONE KASAN_TAG_INVALID -#define KASAN_KMALLOC_FREE KASAN_TAG_INVALID -#define KASAN_VMALLOC_INVALID KASAN_TAG_INVALID /* only for SW_TAGS */ +#define KASAN_PAGE_FREE KASAN_TAG_INVALID +#define KASAN_PAGE_REDZONE KASAN_TAG_INVALID +#define KASAN_SLAB_REDZONE KASAN_TAG_INVALID +#define KASAN_SLAB_FREE KASAN_TAG_INVALID +#define KASAN_VMALLOC_INVALID KASAN_TAG_INVALID /* only used for SW_TAGS */ #endif #ifdef CONFIG_KASAN_GENERIC -#define KASAN_KMALLOC_FREETRACK 0xFA /* object was freed and has free track set */ -#define KASAN_GLOBAL_REDZONE 0xF9 /* redzone for global variable */ +#define KASAN_SLAB_FREETRACK 0xFA /* freed slab object with free track */ +#define KASAN_GLOBAL_REDZONE 0xF9 /* redzone for global variable */ -/* - * Stack redzone shadow values - * (Those are compiler's ABI, don't change them) - */ -#define KASAN_STACK_LEFT 0xF1 -#define KASAN_STACK_MID 0xF2 -#define KASAN_STACK_RIGHT 0xF3 -#define KASAN_STACK_PARTIAL 0xF4 +/* Stack redzone shadow values. Compiler ABI, do not change. */ +#define KASAN_STACK_LEFT 0xF1 +#define KASAN_STACK_MID 0xF2 +#define KASAN_STACK_RIGHT 0xF3 +#define KASAN_STACK_PARTIAL 0xF4 -/* - * alloca redzone shadow values - */ +/* alloca redzone shadow values. */ #define KASAN_ALLOCA_LEFT 0xCA #define KASAN_ALLOCA_RIGHT 0xCB +/* alloca redzone size. Compiler ABI, do not change. */ #define KASAN_ALLOCA_REDZONE_SIZE 32 -/* - * Stack frame marker (compiler ABI). - */ +/* Stack frame marker. Compiler ABI, do not change. */ #define KASAN_CURRENT_STACK_FRAME_MAGIC 0x41B58AB3 -/* Don't break randconfig/all*config builds */ +/* Dummy value to avoid breaking randconfig/all*config builds. */ #ifndef KASAN_ABI_VERSION #define KASAN_ABI_VERSION 1 #endif @@ -141,21 +136,21 @@ struct kasan_report_info { unsigned long ip; }; -/* The layout of struct dictated by compiler */ +/* Do not change the struct layout: compiler ABI. */ struct kasan_source_location { const char *filename; int line_no; int column_no; }; -/* The layout of struct dictated by compiler */ +/* Do not change the struct layout: compiler ABI. */ struct kasan_global { const void *beg; /* Address of the beginning of the global variable. */ size_t size; /* Size of the global variable. */ - size_t size_with_redzone; /* Size of the variable + size of the red zone. 32 bytes aligned */ + size_t size_with_redzone; /* Size of the variable + size of the redzone. 32 bytes aligned. */ const void *name; const void *module_name; /* Name of the module where the global variable is declared. */ - unsigned long has_dynamic_init; /* This needed for C++ */ + unsigned long has_dynamic_init; /* This is needed for C++. */ #if KASAN_ABI_VERSION >= 4 struct kasan_source_location *location; #endif @@ -164,9 +159,7 @@ struct kasan_global { #endif }; -/** - * Structures to keep alloc and free tracks * - */ +/* Structures for keeping alloc and free tracks. */ #define KASAN_STACK_DEPTH 64 @@ -183,11 +176,8 @@ struct kasan_track { struct kasan_alloc_meta { struct kasan_track alloc_track; + /* Generic mode stores free track in kasan_free_meta. */ #ifdef CONFIG_KASAN_GENERIC - /* - * The auxiliary stack is stored into struct kasan_alloc_meta. - * The free stack is stored into struct kasan_free_meta. - */ depot_stack_handle_t aux_stack[2]; #else struct kasan_track free_track[KASAN_NR_FREE_STACKS]; @@ -203,18 +193,18 @@ struct qlist_node { }; /* - * Generic mode either stores free meta in the object itself or in the redzone - * after the object. In the former case free meta offset is 0, in the latter - * case it has some sane value smaller than INT_MAX. Use INT_MAX as free meta - * offset when free meta isn't present. + * Free meta is stored either in the object itself or in the redzone after the + * object. In the former case, free meta offset is 0. In the latter case, the + * offset is between 0 and INT_MAX. INT_MAX marks that free meta is not present. */ #define KASAN_NO_FREE_META INT_MAX +/* + * Free meta is only used by Generic mode while the object is in quarantine. + * After that, slab allocator stores the freelist pointer in the object. + */ struct kasan_free_meta { #ifdef CONFIG_KASAN_GENERIC - /* This field is used while the object is in the quarantine. - * Otherwise it might be used for the allocator freelist. - */ struct qlist_node quarantine_link; struct kasan_track free_track; #endif @@ -417,9 +407,10 @@ static inline void kasan_unpoison(const void *addr, size_t size, bool init) return; /* * Explicitly initialize the memory with the precise object size to - * avoid overwriting the SLAB redzone. This disables initialization in - * the arch code and may thus lead to performance penalty. The penalty - * is accepted since SLAB redzones aren't enabled in production builds. + * avoid overwriting the slab redzone. This disables initialization in + * the arch code and may thus lead to performance penalty. This penalty + * does not affect production builds, as slab redzones are not enabled + * there. */ if (__slub_debug_enabled() && init && ((unsigned long)size & KASAN_GRANULE_MASK)) { @@ -503,8 +494,9 @@ void kasan_restore_multi_shot(bool enabled); /* * Exported functions for interfaces called from assembly or from generated - * code. Declarations here to avoid warning about missing declarations. + * code. Declared here to avoid warnings about missing declarations. */ + asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); void __asan_register_globals(struct kasan_global *globals, size_t size); void __asan_unregister_globals(struct kasan_global *globals, size_t size); @@ -573,4 +565,4 @@ void __hwasan_storeN_noabort(unsigned long addr, size_t size); void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size); -#endif +#endif /* __MM_KASAN_KASAN_H */ diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 0a9def8ce5e8..75585077eb6d 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -99,6 +99,17 @@ static unsigned long quarantine_size; static DEFINE_RAW_SPINLOCK(quarantine_lock); DEFINE_STATIC_SRCU(remove_cache_srcu); +#ifdef CONFIG_PREEMPT_RT +struct cpu_shrink_qlist { + raw_spinlock_t lock; + struct qlist_head qlist; +}; + +static DEFINE_PER_CPU(struct cpu_shrink_qlist, shrink_qlist) = { + .lock = __RAW_SPIN_LOCK_UNLOCKED(shrink_qlist.lock), +}; +#endif + /* Maximum size of the global queue. */ static unsigned long quarantine_max_size; @@ -152,7 +163,7 @@ static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache) * As the object now gets freed from the quarantine, assume that its * free track is no longer valid. */ - *(u8 *)kasan_mem_to_shadow(object) = KASAN_KMALLOC_FREE; + *(u8 *)kasan_mem_to_shadow(object) = KASAN_SLAB_FREE; ___cache_free(cache, object, _THIS_IP_); @@ -308,10 +319,31 @@ static void qlist_move_cache(struct qlist_head *from, } } -static void per_cpu_remove_cache(void *arg) +#ifndef CONFIG_PREEMPT_RT +static void __per_cpu_remove_cache(struct qlist_head *q, void *arg) { struct kmem_cache *cache = arg; struct qlist_head to_free = QLIST_INIT; + + qlist_move_cache(q, &to_free, cache); + qlist_free_all(&to_free, cache); +} +#else +static void __per_cpu_remove_cache(struct qlist_head *q, void *arg) +{ + struct kmem_cache *cache = arg; + unsigned long flags; + struct cpu_shrink_qlist *sq; + + sq = this_cpu_ptr(&shrink_qlist); + raw_spin_lock_irqsave(&sq->lock, flags); + qlist_move_cache(q, &sq->qlist, cache); + raw_spin_unlock_irqrestore(&sq->lock, flags); +} +#endif + +static void per_cpu_remove_cache(void *arg) +{ struct qlist_head *q; q = this_cpu_ptr(&cpu_quarantine); @@ -322,8 +354,7 @@ static void per_cpu_remove_cache(void *arg) */ if (READ_ONCE(q->offline)) return; - qlist_move_cache(q, &to_free, cache); - qlist_free_all(&to_free, cache); + __per_cpu_remove_cache(q, arg); } /* Free all quarantined objects belonging to cache. */ @@ -341,6 +372,21 @@ void kasan_quarantine_remove_cache(struct kmem_cache *cache) */ on_each_cpu(per_cpu_remove_cache, cache, 1); +#ifdef CONFIG_PREEMPT_RT + { + int cpu; + struct cpu_shrink_qlist *sq; + + for_each_online_cpu(cpu) { + sq = per_cpu_ptr(&shrink_qlist, cpu); + raw_spin_lock_irqsave(&sq->lock, flags); + qlist_move_cache(&sq->qlist, &to_free, cache); + raw_spin_unlock_irqrestore(&sq->lock, flags); + } + qlist_free_all(&to_free, cache); + } +#endif + raw_spin_lock_irqsave(&quarantine_lock, flags); for (i = 0; i < QUARANTINE_BATCHES; i++) { if (qlist_empty(&global_quarantine[i])) diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c index efc5e79a103f..6689fb9a919b 100644 --- a/mm/kasan/report_generic.c +++ b/mm/kasan/report_generic.c @@ -66,7 +66,7 @@ static const char *get_shadow_bug_type(struct kasan_report_info *info) bug_type = "out-of-bounds"; break; case KASAN_PAGE_REDZONE: - case KASAN_KMALLOC_REDZONE: + case KASAN_SLAB_REDZONE: bug_type = "slab-out-of-bounds"; break; case KASAN_GLOBAL_REDZONE: @@ -78,9 +78,9 @@ static const char *get_shadow_bug_type(struct kasan_report_info *info) case KASAN_STACK_PARTIAL: bug_type = "stack-out-of-bounds"; break; - case KASAN_FREE_PAGE: - case KASAN_KMALLOC_FREE: - case KASAN_KMALLOC_FREETRACK: + case KASAN_PAGE_FREE: + case KASAN_SLAB_FREE: + case KASAN_SLAB_FREETRACK: bug_type = "use-after-free"; break; case KASAN_ALLOCA_LEFT: diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 11a954763be9..4e7cd4c8e687 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -21,6 +21,8 @@ #include <linux/log2.h> #include <linux/memblock.h> #include <linux/moduleparam.h> +#include <linux/notifier.h> +#include <linux/panic_notifier.h> #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/sched/clock.h> @@ -67,8 +69,11 @@ static int param_set_sample_interval(const char *val, const struct kernel_param if (ret < 0) return ret; - if (!num) /* Using 0 to indicate KFENCE is disabled. */ + /* Using 0 to indicate KFENCE is disabled. */ + if (!num && READ_ONCE(kfence_enabled)) { + pr_info("disabled\n"); WRITE_ONCE(kfence_enabled, false); + } *((unsigned long *)kp->arg) = num; @@ -99,6 +104,10 @@ module_param_named(skip_covered_thresh, kfence_skip_covered_thresh, ulong, 0644) static bool kfence_deferrable __read_mostly = IS_ENABLED(CONFIG_KFENCE_DEFERRABLE); module_param_named(deferrable, kfence_deferrable, bool, 0444); +/* If true, check all canary bytes on panic. */ +static bool kfence_check_on_panic __read_mostly; +module_param_named(check_on_panic, kfence_check_on_panic, bool, 0444); + /* The pool of pages used for guard pages and objects. */ char *__kfence_pool __read_mostly; EXPORT_SYMBOL(__kfence_pool); /* Export for test modules. */ @@ -737,6 +746,31 @@ static int __init kfence_debugfs_init(void) late_initcall(kfence_debugfs_init); +/* === Panic Notifier ====================================================== */ + +static void kfence_check_all_canary(void) +{ + int i; + + for (i = 0; i < CONFIG_KFENCE_NUM_OBJECTS; i++) { + struct kfence_metadata *meta = &kfence_metadata[i]; + + if (meta->state == KFENCE_OBJECT_ALLOCATED) + for_each_canary(meta, check_canary_byte); + } +} + +static int kfence_check_canary_callback(struct notifier_block *nb, + unsigned long reason, void *arg) +{ + kfence_check_all_canary(); + return NOTIFY_OK; +} + +static struct notifier_block kfence_check_canary_notifier = { + .notifier_call = kfence_check_canary_callback, +}; + /* === Allocation Gate Timer ================================================ */ static struct delayed_work kfence_timer; @@ -814,6 +848,9 @@ static void kfence_init_enable(void) else INIT_DELAYED_WORK(&kfence_timer, toggle_allocation_gate); + if (kfence_check_on_panic) + atomic_notifier_chain_register(&panic_notifier_list, &kfence_check_canary_notifier); + WRITE_ONCE(kfence_enabled, true); queue_delayed_work(system_unbound_wq, &kfence_timer, 0); @@ -874,6 +911,7 @@ static int kfence_enable_late(void) WRITE_ONCE(kfence_enabled, true); queue_delayed_work(system_unbound_wq, &kfence_timer, 0); + pr_info("re-enabled\n"); return 0; } diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index 96206a4ee9ab..a97bffe0cc3e 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -296,10 +296,9 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat if (policy == ALLOCATE_ANY) return alloc; - if (policy == ALLOCATE_LEFT && IS_ALIGNED((unsigned long)alloc, PAGE_SIZE)) + if (policy == ALLOCATE_LEFT && PAGE_ALIGNED(alloc)) return alloc; - if (policy == ALLOCATE_RIGHT && - !IS_ALIGNED((unsigned long)alloc, PAGE_SIZE)) + if (policy == ALLOCATE_RIGHT && !PAGE_ALIGNED(alloc)) return alloc; } else if (policy == ALLOCATE_NONE) return alloc; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a4e5eaf3eb01..16be62d493cd 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -365,9 +365,7 @@ int hugepage_madvise(struct vm_area_struct *vma, * register it here without waiting a page fault that * may not happen any time soon. */ - if (!(*vm_flags & VM_NO_KHUGEPAGED) && - khugepaged_enter_vma_merge(vma, *vm_flags)) - return -ENOMEM; + khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; @@ -439,12 +437,19 @@ static inline int khugepaged_test_exit(struct mm_struct *mm) return atomic_read(&mm->mm_users) == 0; } -static bool hugepage_vma_check(struct vm_area_struct *vma, - unsigned long vm_flags) +bool hugepage_vma_check(struct vm_area_struct *vma, + unsigned long vm_flags) { if (!transhuge_vma_enabled(vma, vm_flags)) return false; + if (vm_flags & VM_NO_KHUGEPAGED) + return false; + + /* Don't run khugepaged against DAX vma */ + if (vma_is_dax(vma)) + return false; + if (vma->vm_file && !IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR)) return false; @@ -458,35 +463,31 @@ static bool hugepage_vma_check(struct vm_area_struct *vma, return false; /* Only regular file is valid */ - if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && - (vm_flags & VM_EXEC)) { - struct inode *inode = vma->vm_file->f_inode; + if (file_thp_enabled(vma)) + return true; - return !inode_is_open_for_write(inode) && - S_ISREG(inode->i_mode); - } - - if (!vma->anon_vma || vma->vm_ops) + if (!vma->anon_vma || !vma_is_anonymous(vma)) return false; if (vma_is_temporary_stack(vma)) return false; - return !(vm_flags & VM_NO_KHUGEPAGED); + + return true; } -int __khugepaged_enter(struct mm_struct *mm) +void __khugepaged_enter(struct mm_struct *mm) { struct mm_slot *mm_slot; int wakeup; mm_slot = alloc_mm_slot(); if (!mm_slot) - return -ENOMEM; + return; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(khugepaged_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { free_mm_slot(mm_slot); - return 0; + return; } spin_lock(&khugepaged_mm_lock); @@ -502,28 +503,18 @@ int __khugepaged_enter(struct mm_struct *mm) mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); - - return 0; } -int khugepaged_enter_vma_merge(struct vm_area_struct *vma, - unsigned long vm_flags) +void khugepaged_enter_vma(struct vm_area_struct *vma, + unsigned long vm_flags) { - unsigned long hstart, hend; - - /* - * khugepaged only supports read-only files for non-shmem files. - * khugepaged does not yet work on special mappings. And - * file-private shmem THP is not supported. - */ - if (!hugepage_vma_check(vma, vm_flags)) - return 0; - - hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; - hend = vma->vm_end & HPAGE_PMD_MASK; - if (hstart < hend) - return khugepaged_enter(vma, vm_flags); - return 0; + if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && + khugepaged_enabled() && + (((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < + (vma->vm_end & HPAGE_PMD_MASK))) { + if (hugepage_vma_check(vma, vm_flags)) + __khugepaged_enter(vma->vm_mm); + } } void __khugepaged_exit(struct mm_struct *mm) @@ -972,7 +963,7 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, if (!hugepage_vma_check(vma, vma->vm_flags)) return SCAN_VMA_CHECK; /* Anon VMA expected */ - if (!vma->anon_vma || vma->vm_ops) + if (!vma->anon_vma || !vma_is_anonymous(vma)) return SCAN_VMA_CHECK; return 0; } @@ -1183,7 +1174,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(new_page, vma, address, true); + page_add_new_anon_rmap(new_page, vma, address); lru_cache_add_inactive_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); @@ -1456,6 +1447,10 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE)) return; + /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ + if (userfaultfd_wp(vma)) + return; + hpage = find_lock_page(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (!hpage) @@ -1591,7 +1586,15 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) * reverse order. Trylock is a way to avoid deadlock. */ if (mmap_write_trylock(mm)) { - if (!khugepaged_test_exit(mm)) + /* + * When a vma is registered with uffd-wp, we can't + * recycle the pmd pgtable because there can be pte + * markers installed. Skip it only, so the rest mm/vma + * can still have the same file mapped hugely, however + * it'll always mapped in small page size for uffd-wp + * registered ranges. + */ + if (!khugepaged_test_exit(mm) && !userfaultfd_wp(vma)) collapse_and_free_pmd(mm, vma, addr, pmd); mmap_write_unlock(mm); } else { @@ -638,6 +638,9 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node) ksm_pages_sharing--; else ksm_pages_shared--; + + rmap_item->mm->ksm_merging_pages--; + VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); @@ -785,6 +788,9 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) ksm_pages_sharing--; else ksm_pages_shared--; + + rmap_item->mm->ksm_merging_pages--; + VM_BUG_ON(stable_node->rmap_hlist_len <= 0); stable_node->rmap_hlist_len--; @@ -866,6 +872,7 @@ static inline struct stable_node *page_stable_node(struct page *page) static inline void set_page_stable_node(struct page *page, struct stable_node *stable_node) { + VM_BUG_ON_PAGE(PageAnon(page) && PageAnonExclusive(page), page); page->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM); } @@ -1038,6 +1045,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, int swapped; int err = -EFAULT; struct mmu_notifier_range range; + bool anon_exclusive; pvmw.address = page_address_in_vma(page, vma); if (pvmw.address == -EFAULT) @@ -1055,9 +1063,10 @@ 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); if (pte_write(*pvmw.pte) || pte_dirty(*pvmw.pte) || (pte_protnone(*pvmw.pte) && pte_savedwrite(*pvmw.pte)) || - mm_tlb_flush_pending(mm)) { + anon_exclusive || mm_tlb_flush_pending(mm)) { pte_t entry; swapped = PageSwapCache(page); @@ -1085,6 +1094,12 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; } + + if (anon_exclusive && page_try_share_anon_rmap(page)) { + set_pte_at(mm, pvmw.address, pvmw.pte, entry); + goto out_unlock; + } + if (pte_dirty(entry)) set_page_dirty(page); @@ -1143,6 +1158,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, pte_unmap_unlock(ptep, ptl); goto out_mn; } + VM_BUG_ON_PAGE(PageAnonExclusive(page), page); + VM_BUG_ON_PAGE(PageAnon(kpage) && PageAnonExclusive(kpage), kpage); /* * No need to check ksm_use_zero_pages here: we can only have a @@ -1150,7 +1167,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, */ if (!is_zero_pfn(page_to_pfn(kpage))) { get_page(kpage); - page_add_anon_rmap(kpage, vma, addr, false); + page_add_anon_rmap(kpage, vma, addr, RMAP_NONE); newpte = mk_pte(kpage, vma->vm_page_prot); } else { newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage), @@ -1573,7 +1590,7 @@ again: * the rbtree instead as a regular stable_node (in * order to collapse the stable_node chain if a single * stable_node dup was found in it). In such case the - * stable_node is overwritten by the calleee to point + * stable_node is overwritten by the callee to point * to the stable_node_dup that was collapsed in the * stable rbtree and stable_node will be equal to * stable_node_dup like if the chain never existed. @@ -2007,6 +2024,8 @@ static void stable_tree_append(struct rmap_item *rmap_item, ksm_pages_sharing++; else ksm_pages_shared++; + + rmap_item->mm->ksm_merging_pages++; } /* @@ -2591,7 +2610,7 @@ struct page *ksm_might_need_to_copy(struct page *page, return new_page; } -void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc) +void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { struct stable_node *stable_node; struct rmap_item *rmap_item; @@ -2615,7 +2634,13 @@ again: struct vm_area_struct *vma; cond_resched(); - anon_vma_lock_read(anon_vma); + if (!anon_vma_trylock_read(anon_vma)) { + if (rwc->try_lock) { + rwc->contended = true; + return; + } + anon_vma_lock_read(anon_vma); + } anon_vma_interval_tree_foreach(vmac, &anon_vma->rb_root, 0, ULONG_MAX) { unsigned long addr; diff --git a/mm/madvise.c b/mm/madvise.c index 1873616a37d2..4d6592488b51 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -35,6 +35,7 @@ #include <asm/tlb.h> #include "internal.h" +#include "swap.h" struct madvise_walk_private { struct mmu_gather *tlb; @@ -197,6 +198,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, pte_t *orig_pte; struct vm_area_struct *vma = walk->private; unsigned long index; + struct swap_iocb *splug = NULL; if (pmd_none_or_trans_huge_or_clear_bad(pmd)) return 0; @@ -218,10 +220,11 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, continue; page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, - vma, index, false); + vma, index, false, &splug); if (page) put_page(page); } + swap_read_unplug(splug); return 0; } @@ -237,6 +240,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); pgoff_t end_index = linear_page_index(vma, end + PAGE_SIZE - 1); struct page *page; + struct swap_iocb *splug = NULL; rcu_read_lock(); xas_for_each(&xas, page, end_index) { @@ -249,13 +253,14 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, swap = radix_to_swp_entry(page); page = read_swap_cache_async(swap, GFP_HIGHUSER_MOVABLE, - NULL, 0, false); + NULL, 0, false, &splug); if (page) put_page(page); rcu_read_lock(); } rcu_read_unlock(); + swap_read_unplug(splug); lru_add_drain(); /* Push any new pages onto the LRU now */ } @@ -432,12 +437,12 @@ regular_page: if (split_huge_page(page)) { unlock_page(page); put_page(page); - pte_offset_map_lock(mm, pmd, addr, &ptl); + orig_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); break; } unlock_page(page); put_page(page); - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte--; addr -= PAGE_SIZE; continue; @@ -648,12 +653,12 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, if (split_huge_page(page)) { unlock_page(page); put_page(page); - pte_offset_map_lock(mm, pmd, addr, &ptl); + orig_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); goto out; } unlock_page(page); put_page(page); - pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte--; addr -= PAGE_SIZE; continue; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 598fece89e2b..abec50f31fe6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -67,6 +67,7 @@ #include <net/sock.h> #include <net/ip.h> #include "slab.h" +#include "swap.h" #include <linux/uaccess.h> @@ -89,7 +90,7 @@ static bool cgroup_memory_nokmem __ro_after_init; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP -bool cgroup_memory_noswap __ro_after_init; +static bool cgroup_memory_noswap __ro_after_init; #else #define cgroup_memory_noswap 1 #endif @@ -209,7 +210,6 @@ static struct move_charge_struct { enum res_type { _MEM, _MEMSWAP, - _OOM_TYPE, _KMEM, _TCP, }; @@ -217,8 +217,6 @@ enum res_type { #define MEMFILE_PRIVATE(x, val) ((x) << 16 | (val)) #define MEMFILE_TYPE(val) ((val) >> 16 & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) -/* Used for OOM notifier */ -#define OOM_CONTROL (0) /* * Iteration constructs for visiting all cgroups (under a tree). If @@ -1013,9 +1011,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, if (!root) root = root_mem_cgroup; - if (prev && !reclaim) - pos = prev; - rcu_read_lock(); if (reclaim) { @@ -1024,7 +1019,13 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, mz = root->nodeinfo[reclaim->pgdat->node_id]; iter = &mz->iter; - if (prev && reclaim->generation != iter->generation) + /* + * On start, join the current reclaim iteration cycle. + * Exit when a concurrent walker completes it. + */ + if (!prev) + reclaim->generation = iter->generation; + else if (reclaim->generation != iter->generation) goto out_unlock; while (1) { @@ -1041,6 +1042,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, */ (void)cmpxchg(&iter->position, pos, NULL); } + } else if (prev) { + pos = prev; } if (pos) @@ -1065,15 +1068,10 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, * is provided by the caller, so we know it's alive * and kicking, and don't take an extra reference. */ - memcg = mem_cgroup_from_css(css); - - if (css == &root->css) - break; - - if (css_tryget(css)) + if (css == &root->css || css_tryget(css)) { + memcg = mem_cgroup_from_css(css); break; - - memcg = NULL; + } } if (reclaim) { @@ -1089,8 +1087,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, if (!memcg) iter->generation++; - else if (!prev) - reclaim->generation = iter->generation; } out_unlock: @@ -1402,6 +1398,10 @@ static const struct memory_stat memory_stats[] = { { "sock", MEMCG_SOCK }, { "vmalloc", MEMCG_VMALLOC }, { "shmem", NR_SHMEM }, +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + { "zswap", MEMCG_ZSWAP_B }, + { "zswapped", MEMCG_ZSWAPPED }, +#endif { "file_mapped", NR_FILE_MAPPED }, { "file_dirty", NR_FILE_DIRTY }, { "file_writeback", NR_WRITEBACK }, @@ -1436,6 +1436,7 @@ static int memcg_page_state_unit(int item) { switch (item) { case MEMCG_PERCPU_B: + case MEMCG_ZSWAP_B: case NR_SLAB_RECLAIMABLE_B: case NR_SLAB_UNRECLAIMABLE_B: case WORKINGSET_REFAULT_ANON: @@ -1516,6 +1517,13 @@ static char *memory_stat_format(struct mem_cgroup *memcg) seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED), memcg_events(memcg, PGLAZYFREED)); +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + seq_buf_printf(&s, "%s %lu\n", vm_event_name(ZSWPIN), + memcg_events(memcg, ZSWPIN)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(ZSWPOUT), + memcg_events(memcg, ZSWPOUT)); +#endif + #ifdef CONFIG_TRANSPARENT_HUGEPAGE seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC), memcg_events(memcg, THP_FAULT_ALLOC)); @@ -2887,6 +2895,19 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p) return page_memcg_check(folio_page(folio, 0)); } +static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg) +{ + struct obj_cgroup *objcg = NULL; + + for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) { + objcg = rcu_dereference(memcg->objcg); + if (objcg && obj_cgroup_tryget(objcg)) + break; + objcg = NULL; + } + return objcg; +} + __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) { struct obj_cgroup *objcg = NULL; @@ -2900,15 +2921,32 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) memcg = active_memcg(); else memcg = mem_cgroup_from_task(current); - - for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) { - objcg = rcu_dereference(memcg->objcg); - if (objcg && obj_cgroup_tryget(objcg)) - break; - objcg = NULL; - } + objcg = __get_obj_cgroup_from_memcg(memcg); rcu_read_unlock(); + return objcg; +} + +struct obj_cgroup *get_obj_cgroup_from_page(struct page *page) +{ + struct obj_cgroup *objcg; + + if (!memcg_kmem_enabled() || memcg_kmem_bypass()) + return NULL; + + if (PageMemcgKmem(page)) { + objcg = __folio_objcg(page_folio(page)); + obj_cgroup_get(objcg); + } else { + struct mem_cgroup *memcg; + rcu_read_lock(); + memcg = __folio_memcg(page_folio(page)); + if (memcg) + objcg = __get_obj_cgroup_from_memcg(memcg); + else + objcg = NULL; + rcu_read_unlock(); + } return objcg; } @@ -3387,7 +3425,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, int loop = 0; struct mem_cgroup_tree_per_node *mctz; unsigned long excess; - unsigned long nr_scanned; if (order > 0) return 0; @@ -3415,13 +3452,10 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, if (!mz) break; - nr_scanned = 0; reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat, - gfp_mask, &nr_scanned); + gfp_mask, total_scanned); nr_reclaimed += reclaimed; - *total_scanned += nr_scanned; spin_lock_irq(&mctz->lock); - __mem_cgroup_remove_exceeded(mz, mctz); /* * If we failed to reclaim anything from this memory cgroup @@ -4893,7 +4927,6 @@ static struct cftype mem_cgroup_legacy_files[] = { .name = "oom_control", .seq_show = mem_cgroup_oom_control_read, .write_u64 = mem_cgroup_oom_control_write, - .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL), }, { .name = "pressure_level", @@ -5151,6 +5184,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + memcg->zswap_max = PAGE_COUNTER_MAX; +#endif page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); if (parent) { memcg->swappiness = mem_cgroup_swappiness(parent); @@ -5649,10 +5685,14 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, if (pte_present(ptent)) page = mc_handle_present_pte(vma, addr, ptent); + else if (pte_none_mostly(ptent)) + /* + * PTE markers should be treated as a none pte here, separated + * from other swap handling below. + */ + page = mc_handle_file_pte(vma, addr, ptent); else if (is_swap_pte(ptent)) page = mc_handle_swap_pte(vma, ptent, &ent); - else if (pte_none(ptent)) - page = mc_handle_file_pte(vma, addr, ptent); if (!page && !ent.val) return ret; @@ -6108,6 +6148,14 @@ static u64 memory_current_read(struct cgroup_subsys_state *css, return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE; } +static u64 memory_peak_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + return (u64)memcg->memory.watermark * PAGE_SIZE; +} + static int memory_min_show(struct seq_file *m, void *v) { return seq_puts_memcg_tunable(m, @@ -6365,6 +6413,46 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of, return nbytes; } +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 err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "", &nr_to_reclaim); + if (err) + return err; + + while (nr_reclaimed < nr_to_reclaim) { + unsigned long reclaimed; + + if (signal_pending(current)) + return -EINTR; + + /* + * This is the final attempt, drain percpu lru caches in the + * hope of introducing more evictable pages for + * try_to_free_mem_cgroup_pages(). + */ + if (!nr_retries) + lru_add_drain_all(); + + reclaimed = try_to_free_mem_cgroup_pages(memcg, + nr_to_reclaim - nr_reclaimed, + GFP_KERNEL, true); + + if (!reclaimed && !nr_retries--) + return -EAGAIN; + + nr_reclaimed += reclaimed; + } + + return nbytes; +} + static struct cftype memory_files[] = { { .name = "current", @@ -6372,6 +6460,11 @@ static struct cftype memory_files[] = { .read_u64 = memory_current_read, }, { + .name = "peak", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = memory_peak_read, + }, + { .name = "min", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = memory_min_show, @@ -6423,6 +6516,11 @@ static struct cftype memory_files[] = { .seq_show = memory_oom_group_show, .write = memory_oom_group_write, }, + { + .name = "reclaim", + .flags = CFTYPE_NS_DELEGATABLE, + .write = memory_reclaim, + }, { } /* terminate */ }; @@ -6593,9 +6691,6 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root, return; parent = parent_mem_cgroup(memcg); - /* No parent means a non-hierarchical mode on v1 memcg */ - if (!parent) - return; if (parent == root) { memcg->memory.emin = READ_ONCE(memcg->memory.min); @@ -7125,17 +7220,17 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) } /** - * __mem_cgroup_try_charge_swap - try charging swap space for a page - * @page: page being added to swap + * __mem_cgroup_try_charge_swap - try charging swap space for a folio + * @folio: folio being added to swap * @entry: swap entry to charge * - * Try to charge @page's memcg for the swap space at @entry. + * Try to charge @folio's memcg for the swap space at @entry. * * Returns 0 on success, -ENOMEM on failure. */ -int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { - unsigned int nr_pages = thp_nr_pages(page); + unsigned int nr_pages = folio_nr_pages(folio); struct page_counter *counter; struct mem_cgroup *memcg; unsigned short oldid; @@ -7143,9 +7238,9 @@ int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; - memcg = page_memcg(page); + memcg = folio_memcg(folio); - VM_WARN_ON_ONCE_PAGE(!memcg, page); + VM_WARN_ON_ONCE_FOLIO(!memcg, folio); if (!memcg) return 0; @@ -7168,7 +7263,7 @@ int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) if (nr_pages > 1) mem_cgroup_id_get_many(memcg, nr_pages - 1); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages); - VM_BUG_ON_PAGE(oldid, page); + VM_BUG_ON_FOLIO(oldid, folio); mod_memcg_state(memcg, MEMCG_SWAP, nr_pages); return 0; @@ -7371,6 +7466,148 @@ static struct cftype memsw_files[] = { { }, /* terminate */ }; +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +/** + * obj_cgroup_may_zswap - check if this cgroup can zswap + * @objcg: the object cgroup + * + * Check if the hierarchical zswap limit has been reached. + * + * This doesn't check for specific headroom, and it is not atomic + * either. But with zswap, the size of the allocation is only known + * once compression has occured, and this optimistic pre-check avoids + * spending cycles on compression when there is already no room left + * or zswap is disabled altogether somewhere in the hierarchy. + */ +bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg, *original_memcg; + bool ret = true; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return true; + + original_memcg = get_mem_cgroup_from_objcg(objcg); + for (memcg = original_memcg; memcg != root_mem_cgroup; + memcg = parent_mem_cgroup(memcg)) { + unsigned long max = READ_ONCE(memcg->zswap_max); + unsigned long pages; + + if (max == PAGE_COUNTER_MAX) + continue; + if (max == 0) { + ret = false; + break; + } + + cgroup_rstat_flush(memcg->css.cgroup); + pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE; + if (pages < max) + continue; + ret = false; + break; + } + mem_cgroup_put(original_memcg); + return ret; +} + +/** + * obj_cgroup_charge_zswap - charge compression backend memory + * @objcg: the object cgroup + * @size: size of compressed object + * + * This forces the charge after obj_cgroup_may_swap() allowed + * compression and storage in zwap for this cgroup to go ahead. + */ +void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size) +{ + struct mem_cgroup *memcg; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return; + + VM_WARN_ON_ONCE(!(current->flags & PF_MEMALLOC)); + + /* PF_MEMALLOC context, charging must succeed */ + if (obj_cgroup_charge(objcg, GFP_KERNEL, size)) + VM_WARN_ON_ONCE(1); + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + mod_memcg_state(memcg, MEMCG_ZSWAP_B, size); + mod_memcg_state(memcg, MEMCG_ZSWAPPED, 1); + rcu_read_unlock(); +} + +/** + * obj_cgroup_uncharge_zswap - uncharge compression backend memory + * @objcg: the object cgroup + * @size: size of compressed object + * + * Uncharges zswap memory on page in. + */ +void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) +{ + struct mem_cgroup *memcg; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return; + + obj_cgroup_uncharge(objcg, size); + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + mod_memcg_state(memcg, MEMCG_ZSWAP_B, -size); + mod_memcg_state(memcg, MEMCG_ZSWAPPED, -1); + rcu_read_unlock(); +} + +static u64 zswap_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + cgroup_rstat_flush(css->cgroup); + return memcg_page_state(mem_cgroup_from_css(css), MEMCG_ZSWAP_B); +} + +static int zswap_max_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->zswap_max)); +} + +static ssize_t zswap_max_write(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 long max; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &max); + if (err) + return err; + + xchg(&memcg->zswap_max, max); + + return nbytes; +} + +static struct cftype zswap_files[] = { + { + .name = "zswap.current", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = zswap_current_read, + }, + { + .name = "zswap.max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = zswap_max_show, + .write = zswap_max_write, + }, + { } /* terminate */ +}; +#endif /* CONFIG_MEMCG_KMEM && CONFIG_ZSWAP */ + /* * If mem_cgroup_swap_init() is implemented as a subsys_initcall() * instead of a core_initcall(), this could mean cgroup_memory_noswap still @@ -7389,7 +7626,9 @@ static int __init mem_cgroup_swap_init(void) WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, swap_files)); WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_files)); - +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) + WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, zswap_files)); +#endif return 0; } core_initcall(mem_cgroup_swap_init); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d4a4adcca01f..b85661cbdc4a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -59,6 +59,7 @@ #include <linux/page-isolation.h> #include <linux/pagewalk.h> #include <linux/shmem_fs.h> +#include "swap.h" #include "internal.h" #include "ras/ras_event.h" @@ -484,7 +485,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, struct anon_vma *av; pgoff_t pgoff; - av = folio_lock_anon_vma_read(folio); + av = folio_lock_anon_vma_read(folio, NULL); if (av == NULL) /* Not actually mapped anymore */ return; @@ -622,7 +623,7 @@ static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct hwp_walk *hwp = (struct hwp_walk *)walk->private; + struct hwp_walk *hwp = walk->private; int ret = 0; pte_t *ptep, *mapped_pte; spinlock_t *ptl; @@ -656,7 +657,7 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct hwp_walk *hwp = (struct hwp_walk *)walk->private; + struct hwp_walk *hwp = walk->private; pte_t pte = huge_ptep_get(ptep); struct hstate *h = hstate_vma(walk->vma); @@ -733,7 +734,6 @@ static const char * const action_page_types[] = { [MF_MSG_BUDDY] = "free buddy page", [MF_MSG_DAX] = "dax page", [MF_MSG_UNSPLIT_THP] = "unsplit thp", - [MF_MSG_DIFFERENT_PAGE_SIZE] = "different page size", [MF_MSG_UNKNOWN] = "unknown page", }; @@ -1041,12 +1041,11 @@ static int me_huge_page(struct page_state *ps, struct page *p) res = MF_FAILED; unlock_page(hpage); /* - * migration entry prevents later access on error anonymous - * hugepage, so we can free and dissolve it into buddy to - * save healthy subpages. + * migration entry prevents later access on error hugepage, + * so we can free and dissolve it into buddy to save healthy + * subpages. */ - if (PageAnon(hpage)) - put_page(hpage); + put_page(hpage); if (__page_handle_poison(p)) { page_ref_inc(p); res = MF_RECOVERED; @@ -1133,6 +1132,7 @@ static void action_result(unsigned long pfn, enum mf_action_page_type type, { trace_memory_failure_event(pfn, type, result); + num_poisoned_pages_inc(); pr_err("Memory failure: %#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]); } @@ -1179,13 +1179,11 @@ void ClearPageHWPoisonTakenOff(struct page *page) */ static inline bool HWPoisonHandlable(struct page *page, unsigned long flags) { - bool movable = false; - - /* Soft offline could mirgate non-LRU movable pages */ + /* Soft offline could migrate non-LRU movable pages */ if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page)) - movable = true; + return true; - return movable || PageLRU(page) || is_free_buddy_page(page); + return PageLRU(page) || is_free_buddy_page(page); } static int __get_hwpoison_page(struct page *page, unsigned long flags) @@ -1521,7 +1519,9 @@ int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) if (flags & MF_COUNT_INCREASED) { ret = 1; count_increased = true; - } else if (HPageFreed(head) || HPageMigratable(head)) { + } else if (HPageFreed(head)) { + ret = 0; + } else if (HPageMigratable(head)) { ret = get_page_unless_zero(head); if (ret) count_increased = true; @@ -1588,8 +1588,6 @@ retry: goto out; } - num_poisoned_pages_inc(); - /* * Handling free hugepage. The possible race with hugepage allocation * or demotion can be prevented by PageHWPoison flag. @@ -1605,16 +1603,6 @@ retry: return res == MF_RECOVERED ? 0 : -EBUSY; } - /* - * The page could have changed compound pages due to race window. - * If this happens just bail out. - */ - if (!PageHuge(p) || compound_head(p) != head) { - action_result(pfn, MF_MSG_DIFFERENT_PAGE_SIZE, MF_IGNORED); - res = -EBUSY; - goto out; - } - page_flags = head->flags; /* @@ -1762,7 +1750,7 @@ static DEFINE_MUTEX(mf_mutex); * enabled and no spinlocks hold. * * Return: 0 for successfully handled the memory error, - * -EOPNOTSUPP for memory_filter() filtered the error event, + * -EOPNOTSUPP for hwpoison_filter() filtered the error event, * < 0(except -EOPNOTSUPP) on failure. */ int memory_failure(unsigned long pfn, int flags) @@ -1811,11 +1799,12 @@ try_again: res = -EHWPOISON; if (flags & MF_ACTION_REQUIRED) res = kill_accessing_process(current, pfn, flags); + if (flags & MF_COUNT_INCREASED) + put_page(p); goto unlock_mutex; } hpage = compound_head(p); - num_poisoned_pages_inc(); /* * We need/can do nothing about count=0 pages. @@ -1839,7 +1828,6 @@ try_again: /* We lost the race, try again */ if (retry) { ClearPageHWPoison(p); - num_poisoned_pages_dec(); retry = false; goto try_again; } @@ -1902,8 +1890,7 @@ try_again: */ if (PageCompound(p)) { if (retry) { - if (TestClearPageHWPoison(p)) - num_poisoned_pages_dec(); + ClearPageHWPoison(p); unlock_page(p); put_page(p); flags &= ~MF_COUNT_INCREASED; @@ -1925,8 +1912,7 @@ try_again: page_flags = p->flags; if (hwpoison_filter(p)) { - if (TestClearPageHWPoison(p)) - num_poisoned_pages_dec(); + TestClearPageHWPoison(p); unlock_page(p); put_page(p); res = -EOPNOTSUPP; @@ -2088,28 +2074,6 @@ core_initcall(memory_failure_init); pr_info(fmt, pfn); \ }) -static inline int clear_page_hwpoison(struct ratelimit_state *rs, struct page *p) -{ - if (TestClearPageHWPoison(p)) { - unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", - page_to_pfn(p), rs); - num_poisoned_pages_dec(); - return 1; - } - return 0; -} - -static inline int unpoison_taken_off_page(struct ratelimit_state *rs, - struct page *p) -{ - if (put_page_back_buddy(p)) { - unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", - page_to_pfn(p), rs); - return 0; - } - return -EBUSY; -} - /** * unpoison_memory - Unpoison a previously poisoned page * @pfn: Page number of the to be unpoisoned page @@ -2127,6 +2091,7 @@ int unpoison_memory(unsigned long pfn) struct page *page; struct page *p; int ret = -EBUSY; + int freeit = 0; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -2167,18 +2132,15 @@ int unpoison_memory(unsigned long pfn) ret = get_hwpoison_page(p, MF_UNPOISON); if (!ret) { - if (clear_page_hwpoison(&unpoison_rs, page)) - ret = 0; - else - ret = -EBUSY; + ret = TestClearPageHWPoison(page) ? 0 : -EBUSY; } else if (ret < 0) { if (ret == -EHWPOISON) { - ret = unpoison_taken_off_page(&unpoison_rs, p); + ret = put_page_back_buddy(p) ? 0 : -EBUSY; } else unpoison_pr_info("Unpoison: failed to grab page %#lx\n", pfn, &unpoison_rs); } else { - int freeit = clear_page_hwpoison(&unpoison_rs, p); + freeit = !!TestClearPageHWPoison(p); put_page(page); if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) { @@ -2189,6 +2151,11 @@ int unpoison_memory(unsigned long pfn) unlock_mutex: mutex_unlock(&mf_mutex); + if (!ret || freeit) { + num_poisoned_pages_dec(); + unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", + page_to_pfn(p), &unpoison_rs); + } return ret; } EXPORT_SYMBOL(unpoison_memory); @@ -2323,7 +2290,9 @@ static void put_ref_page(struct page *page) * @pfn: pfn to soft-offline * @flags: flags. Same as memory_failure(). * - * Returns 0 on success, otherwise negated errno. + * Returns 0 on success + * -EOPNOTSUPP for hwpoison_filter() filtered the error event + * < 0 otherwise negated errno. * * Soft offline a page, by migration or invalidation, * without killing anything. This is for the case when @@ -2374,6 +2343,16 @@ retry: ret = get_hwpoison_page(page, flags | MF_SOFT_OFFLINE); put_online_mems(); + if (hwpoison_filter(page)) { + if (ret > 0) + put_page(page); + else + put_ref_page(ref_page); + + mutex_unlock(&mf_mutex); + return -EOPNOTSUPP; + } + if (ret > 0) { ret = soft_offline_in_use_page(page); } else if (ret == 0) { @@ -2388,3 +2367,24 @@ retry: return ret; } + +void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) +{ + int i; + + /* + * A further optimization is to have per section refcounted + * num_poisoned_pages. But that would need more space per memmap, so + * for now just do a quick global check to speed up this routine in the + * absence of bad pages. + */ + if (atomic_long_read(&num_poisoned_pages) == 0) + return; + + for (i = 0; i < nr_pages; i++) { + if (PageHWPoison(&memmap[i])) { + num_poisoned_pages_dec(); + ClearPageHWPoison(&memmap[i]); + } + } +} diff --git a/mm/memory.c b/mm/memory.c index 2a12028a3749..54bcd5327b74 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -86,6 +86,7 @@ #include "pgalloc-track.h" #include "internal.h" +#include "swap.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. @@ -99,6 +100,8 @@ struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif +static vm_fault_t do_fault(struct vm_fault *vmf); + /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end @@ -720,12 +723,14 @@ static void restore_exclusive_pte(struct vm_area_struct *vma, else if (is_writable_device_exclusive_entry(entry)) pte = maybe_mkwrite(pte_mkdirty(pte), vma); + VM_BUG_ON(pte_write(pte) && !(PageAnon(page) && PageAnonExclusive(page))); + /* * No need to take a page reference as one was already * created when the swap entry was made. */ if (PageAnon(page)) - page_add_anon_rmap(page, vma, address, false); + page_add_anon_rmap(page, vma, address, RMAP_NONE); else /* * Currently device exclusive access only supports anonymous @@ -790,17 +795,23 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, &src_mm->mmlist); spin_unlock(&mmlist_lock); } + /* Mark the swap entry as shared. */ + if (pte_swp_exclusive(*src_pte)) { + pte = pte_swp_clear_exclusive(*src_pte); + set_pte_at(src_mm, addr, src_pte, pte); + } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { page = pfn_swap_entry_to_page(entry); rss[mm_counter(page)]++; - if (is_writable_migration_entry(entry) && + if (!is_readable_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* - * COW mappings require pages in both - * parent and child to be set to read. + * COW mappings require pages in both parent and child + * to be set to read. A previously exclusive entry is + * now shared. */ entry = make_readable_migration_entry( swp_offset(entry)); @@ -825,7 +836,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ get_page(page); rss[mm_counter(page)]++; - page_dup_rmap(page, false); + /* Cannot fail as these pages cannot get pinned. */ + BUG_ON(page_try_dup_anon_rmap(page, false, src_vma)); /* * We do not preserve soft-dirty information, because so @@ -854,6 +866,14 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (try_restore_exclusive_pte(src_pte, src_vma, addr)) return -EBUSY; return -ENOENT; + } else if (is_pte_marker_entry(entry)) { + /* + * We're copying the pgtable should only because dst_vma has + * uffd-wp enabled, do sanity check. + */ + WARN_ON_ONCE(!userfaultfd_wp(dst_vma)); + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); @@ -862,19 +882,11 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } /* - * Copy a present and normal page if necessary. + * Copy a present and normal page. * - * NOTE! The usual case is that this doesn't need to do - * anything, and can just return a positive value. That - * will let the caller know that it can just increase - * the page refcount and re-use the pte the traditional - * way. - * - * But _if_ we need to copy it because it needs to be - * pinned in the parent (and the child should get its own - * copy rather than just a reference to the same page), - * we'll do that here and return zero to let the caller - * know we're done. + * NOTE! The usual case is that this isn't required; + * instead, the caller can just increase the page refcount + * and re-use the pte the traditional way. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation @@ -884,25 +896,10 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, - struct page **prealloc, pte_t pte, struct page *page) + struct page **prealloc, struct page *page) { struct page *new_page; - - /* - * What we want to do is to check whether this page may - * have been pinned by the parent process. If so, - * instead of wrprotect the pte on both sides, we copy - * the page immediately so that we'll always guarantee - * the pinned page won't be randomly replaced in the - * future. - * - * The page pinning checks are just "has this mm ever - * seen pinning", along with the (inexact) check of - * the page count. That might give false positives for - * for pinning, but it will work correctly. - */ - if (likely(!page_needs_cow_for_dma(src_vma, page))) - return 1; + pte_t pte; new_page = *prealloc; if (!new_page) @@ -915,7 +912,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); - page_add_new_anon_rmap(new_page, dst_vma, addr, false); + page_add_new_anon_rmap(new_page, dst_vma, addr); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; @@ -944,16 +941,24 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, struct page *page; page = vm_normal_page(src_vma, addr, pte); - if (page) { - int retval; - - retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, - addr, rss, prealloc, pte, page); - if (retval <= 0) - return retval; - + if (page && PageAnon(page)) { + /* + * If this page may have been pinned by the parent process, + * copy the page immediately for the child so that we'll always + * guarantee the pinned page won't be randomly replaced in the + * future. + */ get_page(page); - page_dup_rmap(page, false); + if (unlikely(page_try_dup_anon_rmap(page, false, src_vma))) { + /* Page maybe pinned, we have to copy. */ + put_page(page); + return copy_present_page(dst_vma, src_vma, dst_pte, src_pte, + addr, rss, prealloc, page); + } + rss[mm_counter(page)]++; + } else if (page) { + get_page(page); + page_dup_file_rmap(page, false); rss[mm_counter(page)]++; } @@ -965,6 +970,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } + VM_BUG_ON(page && PageAnon(page) && PageAnonExclusive(page)); /* * If it's a shared mapping, mark it clean in @@ -1222,6 +1228,38 @@ copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, return 0; } +/* + * Return true if the vma needs to copy the pgtable during this fork(). Return + * false when we can speed up fork() by allowing lazy page faults later until + * when the child accesses the memory range. + */ +static bool +vma_needs_copy(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) +{ + /* + * Always copy pgtables when dst_vma has uffd-wp enabled even if it's + * file-backed (e.g. shmem). Because when uffd-wp is enabled, pgtable + * contains uffd-wp protection information, that's something we can't + * retrieve from page cache, and skip copying will lose those info. + */ + if (userfaultfd_wp(dst_vma)) + return true; + + if (src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) + return true; + + if (src_vma->anon_vma) + return true; + + /* + * Don't copy ptes where a page fault will fill them correctly. Fork + * becomes much lighter when there are big shared or private readonly + * mappings. The tradeoff is that copy_page_range is more efficient + * than faulting. + */ + return false; +} + int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { @@ -1235,18 +1273,11 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) bool is_cow; int ret; - /* - * Don't copy ptes where a page fault will fill them correctly. - * Fork becomes much lighter when there are big shared or private - * readonly mappings. The tradeoff is that copy_page_range is more - * efficient than faulting. - */ - if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && - !src_vma->anon_vma) + if (!vma_needs_copy(dst_vma, src_vma)) return 0; if (is_vm_hugetlb_page(src_vma)) - return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); + return copy_hugetlb_page_range(dst_mm, src_mm, dst_vma, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* @@ -1308,6 +1339,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) struct zap_details { struct folio *single_folio; /* Locked folio to be unmapped */ bool even_cows; /* Zap COWed private pages too? */ + zap_flags_t zap_flags; /* Extra flags for zapping */ }; /* Whether we should zap all COWed (private) pages too */ @@ -1336,6 +1368,29 @@ static inline bool should_zap_page(struct zap_details *details, struct page *pag return !PageAnon(page); } +static inline bool zap_drop_file_uffd_wp(struct zap_details *details) +{ + if (!details) + return false; + + return details->zap_flags & ZAP_FLAG_DROP_MARKER; +} + +/* + * This function makes sure that we'll replace the none pte with an uffd-wp + * swap special pte marker when necessary. Must be with the pgtable lock held. + */ +static inline void +zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, + unsigned long addr, pte_t *pte, + struct zap_details *details, pte_t pteval) +{ + if (zap_drop_file_uffd_wp(details)) + return; + + pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); +} + static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, @@ -1373,6 +1428,8 @@ again: ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); + zap_install_uffd_wp_if_needed(vma, addr, pte, details, + ptent); if (unlikely(!page)) continue; @@ -1403,6 +1460,13 @@ again: page = pfn_swap_entry_to_page(entry); if (unlikely(!should_zap_page(details, page))) continue; + /* + * Both device private/exclusive mappings should only + * work with anonymous page so far, so we don't need to + * consider uffd-wp bit when zap. For more information, + * see zap_install_uffd_wp_if_needed(). + */ + WARN_ON_ONCE(!vma_is_anonymous(vma)); rss[mm_counter(page)]--; if (is_device_private_entry(entry)) page_remove_rmap(page, vma, false); @@ -1419,6 +1483,10 @@ again: if (!should_zap_page(details, page)) continue; rss[mm_counter(page)]--; + } else if (pte_marker_entry_uffd_wp(entry)) { + /* Only drop the uffd-wp marker if explicitly requested */ + if (!zap_drop_file_uffd_wp(details)) + continue; } else if (is_hwpoison_entry(entry)) { if (!should_zap_cows(details)) continue; @@ -1427,6 +1495,7 @@ again: WARN_ON_ONCE(1); } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + zap_install_uffd_wp_if_needed(vma, addr, pte, details, ptent); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); @@ -1605,8 +1674,11 @@ static void unmap_single_vma(struct mmu_gather *tlb, * safe to do nothing in this case. */ if (vma->vm_file) { + zap_flags_t zap_flags = details ? + details->zap_flags : 0; i_mmap_lock_write(vma->vm_file->f_mapping); - __unmap_hugepage_range_final(tlb, vma, start, end, NULL); + __unmap_hugepage_range_final(tlb, vma, start, end, + NULL, zap_flags); i_mmap_unlock_write(vma->vm_file->f_mapping); } } else @@ -1637,12 +1709,17 @@ void unmap_vmas(struct mmu_gather *tlb, unsigned long end_addr) { struct mmu_notifier_range range; + struct zap_details details = { + .zap_flags = ZAP_FLAG_DROP_MARKER, + /* Careful - we need to zap private pages too! */ + .even_cows = true, + }; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) - unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); + unmap_single_vma(tlb, vma, start_addr, end_addr, &details); mmu_notifier_invalidate_range_end(&range); } @@ -2755,8 +2832,8 @@ static inline int pte_unmap_same(struct vm_fault *vmf) return same; } -static inline bool cow_user_page(struct page *dst, struct page *src, - struct vm_fault *vmf) +static inline bool __wp_page_copy_user(struct page *dst, struct page *src, + struct vm_fault *vmf) { bool ret; void *kaddr; @@ -2963,6 +3040,10 @@ static inline void wp_page_reuse(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; + + VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE)); + VM_BUG_ON(PageAnon(page) && !PageAnonExclusive(page)); + /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely @@ -2981,7 +3062,8 @@ static inline void wp_page_reuse(struct vm_fault *vmf) } /* - * Handle the case of a page which we actually need to copy to a new page. + * Handle the case of a page which we actually need to copy to a new page, + * either due to COW or unsharing. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. @@ -2998,6 +3080,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf) */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct page *old_page = vmf->page; @@ -3020,7 +3103,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) if (!new_page) goto oom; - if (!cow_user_page(new_page, old_page, vmf)) { + if (!__wp_page_copy_user(new_page, old_page, vmf)) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on @@ -3062,7 +3145,14 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (unlikely(unshare)) { + if (pte_soft_dirty(vmf->orig_pte)) + entry = pte_mksoft_dirty(entry); + if (pte_uffd_wp(vmf->orig_pte)) + entry = pte_mkuffd_wp(entry); + } else { + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + } /* * Clear the pte entry and flush it first, before updating the @@ -3072,13 +3162,14 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) * some TLBs while the old PTE remains in others. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); - page_add_new_anon_rmap(new_page, vma, vmf->address, false); + page_add_new_anon_rmap(new_page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ + BUG_ON(unshare && pte_write(entry)); set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { @@ -3128,7 +3219,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) free_swap_cache(old_page); put_page(old_page); } - return page_copied ? VM_FAULT_WRITE : 0; + return (page_copied && !unshare) ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: @@ -3228,18 +3319,22 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) } /* - * This routine handles present pages, when users try to write - * to a shared page. It is done by copying the page to a new address - * and decrementing the shared-page counter for the old page. + * This routine handles present pages, when + * * users try to write to a shared page (FAULT_FLAG_WRITE) + * * GUP wants to take a R/O pin on a possibly shared anonymous page + * (FAULT_FLAG_UNSHARE) + * + * It is done by copying the page to a new address and decrementing the + * shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). - * Thus we can safely just mark it writable once we've done any necessary - * COW. + * Thus, with FAULT_FLAG_WRITE, we can safely just mark it writable once we've + * done any necessary COW. * - * We also mark the page dirty at this point even though the page will - * change only once the write actually happens. This avoids a few races, - * and potentially makes it more efficient. + * In case of FAULT_FLAG_WRITE, we also mark the page dirty at this point even + * though the page will change only once the write actually happens. This + * avoids a few races, and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. @@ -3248,23 +3343,35 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; - if (userfaultfd_pte_wp(vma, *vmf->pte)) { - pte_unmap_unlock(vmf->pte, vmf->ptl); - return handle_userfault(vmf, VM_UFFD_WP); - } + VM_BUG_ON(unshare && (vmf->flags & FAULT_FLAG_WRITE)); + VM_BUG_ON(!unshare && !(vmf->flags & FAULT_FLAG_WRITE)); - /* - * Userfaultfd write-protect can defer flushes. Ensure the TLB - * is flushed in this case before copying. - */ - if (unlikely(userfaultfd_wp(vmf->vma) && - mm_tlb_flush_pending(vmf->vma->vm_mm))) - flush_tlb_page(vmf->vma, vmf->address); + if (likely(!unshare)) { + if (userfaultfd_pte_wp(vma, *vmf->pte)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return handle_userfault(vmf, VM_UFFD_WP); + } + + /* + * Userfaultfd write-protect can defer flushes. Ensure the TLB + * is flushed in this case before copying. + */ + if (unlikely(userfaultfd_wp(vmf->vma) && + mm_tlb_flush_pending(vmf->vma->vm_mm))) + flush_tlb_page(vmf->vma, vmf->address); + } vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { + if (unlikely(unshare)) { + /* No anonymous page -> nothing to do. */ + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } + /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. @@ -3288,6 +3395,13 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) struct page *page = vmf->page; /* + * If the page is exclusive to this process we must reuse the + * page without further checks. + */ + if (PageAnonExclusive(page)) + goto reuse; + + /* * We have to verify under page lock: these early checks are * just an optimization to avoid locking the page and freeing * the swapcache if there is little hope that we can reuse. @@ -3317,9 +3431,19 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * and the page is locked, it's dark out, and we're wearing * sunglasses. Hit it. */ + page_move_anon_rmap(page, vma); unlock_page(page); +reuse: + if (unlikely(unshare)) { + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; + } wp_page_reuse(vmf); return VM_FAULT_WRITE; + } else if (unshare) { + /* No anonymous page -> nothing to do. */ + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); @@ -3331,6 +3455,10 @@ copy: get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); +#ifdef CONFIG_KSM + if (PageKsm(vmf->page)) + count_vm_event(COW_KSM); +#endif return wp_page_copy(vmf); } @@ -3387,6 +3515,7 @@ void unmap_mapping_folio(struct folio *folio) details.even_cows = false; details.single_folio = folio; + details.zap_flags = ZAP_FLAG_DROP_MARKER; i_mmap_lock_read(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) @@ -3508,6 +3637,59 @@ static inline bool should_try_to_free_swap(struct page *page, page_count(page) == 2; } +static vm_fault_t pte_marker_clear(struct vm_fault *vmf) +{ + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + /* + * Be careful so that we will only recover a special uffd-wp pte into a + * none pte. Otherwise it means the pte could have changed, so retry. + */ + if (is_pte_marker(*vmf->pte)) + pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); + pte_unmap_unlock(vmf->pte, vmf->ptl); + return 0; +} + +/* + * This is actually a page-missing access, but with uffd-wp special pte + * installed. It means this pte was wr-protected before being unmapped. + */ +static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf) +{ + /* + * Just in case there're leftover special ptes even after the region + * got unregistered - we can simply clear them. We can also do that + * proactively when e.g. when we do UFFDIO_UNREGISTER upon some uffd-wp + * ranges, but it should be more efficient to be done lazily here. + */ + if (unlikely(!userfaultfd_wp(vmf->vma) || vma_is_anonymous(vmf->vma))) + return pte_marker_clear(vmf); + + /* do_fault() can handle pte markers too like none pte */ + return do_fault(vmf); +} + +static vm_fault_t handle_pte_marker(struct vm_fault *vmf) +{ + swp_entry_t entry = pte_to_swp_entry(vmf->orig_pte); + unsigned long marker = pte_marker_get(entry); + + /* + * PTE markers should always be with file-backed memories, and the + * marker should never be empty. If anything weird happened, the best + * thing to do is to kill the process along with its mm. + */ + if (WARN_ON_ONCE(vma_is_anonymous(vmf->vma) || !marker)) + return VM_FAULT_SIGBUS; + + if (pte_marker_entry_uffd_wp(entry)) + return pte_marker_handle_uffd_wp(vmf); + + /* This is an unknown pte marker */ + return VM_FAULT_SIGBUS; +} + /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. @@ -3521,10 +3703,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; struct swap_info_struct *si = NULL; + rmap_t rmap_flags = RMAP_NONE; + bool exclusive = false; swp_entry_t entry; pte_t pte; int locked; - int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; @@ -3544,6 +3727,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; + } else if (is_pte_marker_entry(entry)) { + ret = handle_pte_marker(vmf); } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; @@ -3585,7 +3770,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* To provide entry to swap_readpage() */ set_page_private(page, entry.val); - swap_readpage(page, true); + swap_readpage(page, true, NULL); set_page_private(page, 0); } } else { @@ -3677,6 +3862,57 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) } /* + * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte + * must never point at an anonymous page in the swapcache that is + * PG_anon_exclusive. Sanity check that this holds and especially, that + * no filesystem set PG_mappedtodisk on a page in the swapcache. Sanity + * check after taking the PT lock and making sure that nobody + * concurrently faulted in this page and set PG_anon_exclusive. + */ + BUG_ON(!PageAnon(page) && PageMappedToDisk(page)); + BUG_ON(PageAnon(page) && PageAnonExclusive(page)); + + /* + * Check under PT lock (to protect against concurrent fork() sharing + * the swap entry concurrently) for certainly exclusive pages. + */ + if (!PageKsm(page)) { + /* + * Note that pte_swp_exclusive() == false for architectures + * without __HAVE_ARCH_PTE_SWP_EXCLUSIVE. + */ + exclusive = pte_swp_exclusive(vmf->orig_pte); + if (page != swapcache) { + /* + * We have a fresh page that is not exposed to the + * swapcache -> certainly exclusive. + */ + exclusive = true; + } else if (exclusive && PageWriteback(page) && + data_race(si->flags & SWP_STABLE_WRITES)) { + /* + * This is tricky: not all swap backends support + * concurrent page modifications while under writeback. + * + * So if we stumble over such a page in the swapcache + * we must not set the page exclusive, otherwise we can + * map it writable without further checks and modify it + * while still under writeback. + * + * For these problematic swap backends, simply drop the + * exclusive marker: this is perfectly fine as we start + * writeback only if we fully unmapped the page and + * there are no unexpected references on the page after + * unmapping succeeded. After fully unmapped, no + * further GUP references (FOLL_GET and FOLL_PIN) can + * appear, so dropping the exclusive marker and mapping + * it only R/O is fine. + */ + exclusive = false; + } + } + + /* * Remove the swap entry and conditionally try to free up the swapcache. * We're already holding a reference on the page but haven't mapped it * yet. @@ -3690,16 +3926,18 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) pte = mk_pte(page, vma->vm_page_prot); /* - * Same logic as in do_wp_page(); however, optimize for fresh pages - * that are certainly not shared because we just allocated them without - * exposing them to the swapcache. + * Same logic as in do_wp_page(); however, optimize for pages that are + * certainly not shared either because we just allocated them without + * exposing them to the swapcache or because the swap entry indicates + * exclusivity. */ - if ((vmf->flags & FAULT_FLAG_WRITE) && !PageKsm(page) && - (page != swapcache || page_count(page) == 1)) { - pte = maybe_mkwrite(pte_mkdirty(pte), vma); - vmf->flags &= ~FAULT_FLAG_WRITE; - ret |= VM_FAULT_WRITE; - exclusive = RMAP_EXCLUSIVE; + if (!PageKsm(page) && (exclusive || page_count(page) == 1)) { + if (vmf->flags & FAULT_FLAG_WRITE) { + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + vmf->flags &= ~FAULT_FLAG_WRITE; + ret |= VM_FAULT_WRITE; + } + rmap_flags |= RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) @@ -3712,12 +3950,13 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { - page_add_new_anon_rmap(page, vma, vmf->address, false); + page_add_new_anon_rmap(page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(page, vma); } else { - do_page_add_anon_rmap(page, vma, vmf->address, exclusive); + page_add_anon_rmap(page, vma, vmf->address, rmap_flags); } + VM_BUG_ON(!PageAnon(page) || (pte_write(pte) && !PageAnonExclusive(page))); set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); @@ -3862,7 +4101,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, vmf->address, false); + page_add_new_anon_rmap(page, vma, vmf->address); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); @@ -4032,6 +4271,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; + bool uffd_wp = pte_marker_uffd_wp(vmf->orig_pte); bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = vmf->address != addr; pte_t entry; @@ -4046,10 +4286,12 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (unlikely(uffd_wp)) + entry = pte_mkuffd_wp(pte_wrprotect(entry)); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); + page_add_new_anon_rmap(page, vma, addr); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); @@ -4058,6 +4300,14 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) set_pte_at(vma->vm_mm, addr, vmf->pte, entry); } +static bool vmf_pte_changed(struct vm_fault *vmf) +{ + if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) + return !pte_same(*vmf->pte, vmf->orig_pte); + + return !pte_none(*vmf->pte); +} + /** * finish_fault - finish page fault once we have prepared the page to fault * @@ -4116,7 +4366,7 @@ vm_fault_t finish_fault(struct vm_fault *vmf) vmf->address, &vmf->ptl); ret = 0; /* Re-check under ptl */ - if (likely(pte_none(*vmf->pte))) + if (likely(!vmf_pte_changed(vmf))) do_set_pte(vmf, page, vmf->address); else ret = VM_FAULT_NOPAGE; @@ -4219,9 +4469,21 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); } +/* Return true if we should do read fault-around, false otherwise */ +static inline bool should_fault_around(struct vm_fault *vmf) +{ + /* No ->map_pages? No way to fault around... */ + if (!vmf->vma->vm_ops->map_pages) + return false; + + if (uffd_disable_fault_around(vmf->vma)) + return false; + + return fault_around_bytes >> PAGE_SHIFT > 1; +} + static vm_fault_t do_read_fault(struct vm_fault *vmf) { - struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; /* @@ -4229,12 +4491,10 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf) * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { - if (likely(!userfaultfd_minor(vmf->vma))) { - ret = do_fault_around(vmf); - if (ret) - return ret; - } + if (should_fault_around(vmf)) { + ret = do_fault_around(vmf); + if (ret) + return ret; } ret = __do_fault(vmf); @@ -4504,8 +4764,11 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { + const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; + if (vma_is_anonymous(vmf->vma)) { - if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) + if (likely(!unshare) && + userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); return do_huge_pmd_wp_page(vmf); } @@ -4581,6 +4844,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) * concurrent faults and from rmap lookups. */ vmf->pte = NULL; + vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; } else { /* * If a huge pmd materialized under us just retry later. Use @@ -4604,6 +4868,7 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; + vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID; /* * some architectures can have larger ptes than wordsize, @@ -4640,10 +4905,11 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } - if (vmf->flags & FAULT_FLAG_WRITE) { + if (vmf->flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!pte_write(entry)) return do_wp_page(vmf); - entry = pte_mkdirty(entry); + else if (likely(vmf->flags & FAULT_FLAG_WRITE)) + entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, @@ -4684,7 +4950,6 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; - unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; p4d_t *p4d; @@ -4709,9 +4974,11 @@ retry_pud: barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { - /* NUMA case for anonymous PUDs would go here */ - - if (dirty && !pud_write(orig_pud)) { + /* + * TODO once we support anonymous PUDs: NUMA case and + * FAULT_FLAG_UNSHARE handling. + */ + if ((flags & FAULT_FLAG_WRITE) && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4749,7 +5016,8 @@ retry_pud: if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf); - if (dirty && !pmd_write(vmf.orig_pmd)) { + if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && + !pmd_write(vmf.orig_pmd)) { ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4949,9 +5217,29 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } #endif /* __PAGETABLE_PMD_FOLDED */ -int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, pte_t **ptepp, - pmd_t **pmdpp, spinlock_t **ptlp) +/** + * follow_pte - look up PTE at a user virtual address + * @mm: the mm_struct of the target address space + * @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. + * + * 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. + * + * Return: zero on success, -ve otherwise. + */ +int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; @@ -4974,35 +5262,9 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); - if (pmd_huge(*pmd)) { - if (!pmdpp) - goto out; - - if (range) { - mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, - NULL, mm, address & PMD_MASK, - (address & PMD_MASK) + PMD_SIZE); - mmu_notifier_invalidate_range_start(range); - } - *ptlp = pmd_lock(mm, pmd); - if (pmd_huge(*pmd)) { - *pmdpp = pmd; - return 0; - } - spin_unlock(*ptlp); - if (range) - mmu_notifier_invalidate_range_end(range); - } - if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; - if (range) { - mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, - address & PAGE_MASK, - (address & PAGE_MASK) + PAGE_SIZE); - mmu_notifier_invalidate_range_start(range); - } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; @@ -5010,38 +5272,9 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, return 0; unlock: pte_unmap_unlock(ptep, *ptlp); - if (range) - mmu_notifier_invalidate_range_end(range); out: return -EINVAL; } - -/** - * follow_pte - look up PTE at a user virtual address - * @mm: the mm_struct of the target address space - * @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. - * - * 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. - * - * Return: zero on success, -ve otherwise. - */ -int follow_pte(struct mm_struct *mm, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp) -{ - return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); -} EXPORT_SYMBOL_GPL(follow_pte); /** diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 416b38ca8def..1213d0c67a53 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -42,14 +42,31 @@ #include "internal.h" #include "shuffle.h" +#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY +static int memmap_on_memory_set(const char *val, const struct kernel_param *kp) +{ + if (hugetlb_optimize_vmemmap_enabled()) + return 0; + return param_set_bool(val, kp); +} + +static const struct kernel_param_ops memmap_on_memory_ops = { + .flags = KERNEL_PARAM_OPS_FL_NOARG, + .set = memmap_on_memory_set, + .get = param_get_bool, +}; /* * memory_hotplug.memmap_on_memory parameter */ static bool memmap_on_memory __ro_after_init; -#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY -module_param(memmap_on_memory, bool, 0444); +module_param_cb(memmap_on_memory, &memmap_on_memory_ops, &memmap_on_memory, 0444); MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug"); + +bool mhp_memmap_on_memory(void) +{ + return memmap_on_memory; +} #endif enum { @@ -303,7 +320,7 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, int err; struct vmem_altmap *altmap = params->altmap; - if (WARN_ON_ONCE(!params->pgprot.pgprot)) + if (WARN_ON_ONCE(!pgprot_val(params->pgprot))) return -EINVAL; VM_BUG_ON(!mhp_range_allowed(PFN_PHYS(pfn), nr_pages * PAGE_SIZE, false)); @@ -328,7 +345,8 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, /* Select all remaining pages up to the next section boundary */ cur_nr_pages = min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn); - err = sparse_add_section(nid, pfn, cur_nr_pages, altmap); + err = sparse_add_section(nid, pfn, cur_nr_pages, altmap, + params->pgmap); if (err) break; cond_resched(); @@ -1288,9 +1306,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size) * altmap as an alternative source of memory, and we do not exactly * populate a single PMD. */ - return memmap_on_memory && - !hugetlb_free_vmemmap_enabled() && - IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) && + return mhp_memmap_on_memory() && size == memory_block_size_bytes() && IS_ALIGNED(vmemmap_size, PMD_SIZE) && IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT)); @@ -1836,7 +1852,8 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - MEMORY_OFFLINE | REPORT_FAILURE); + MEMORY_OFFLINE | REPORT_FAILURE, + GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL); if (ret) { reason = "failure to isolate range"; goto failed_removal_pcplists_disabled; @@ -2074,7 +2091,7 @@ static int __ref try_remove_memory(u64 start, u64 size) * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in * the same granularity it was added - a single memory block. */ - if (memmap_on_memory) { + if (mhp_memmap_on_memory()) { nr_vmemmap_pages = walk_memory_blocks(start, size, NULL, get_nr_vmemmap_pages_cb); if (nr_vmemmap_pages) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8c74107a2b15..d39b01fd52fe 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -104,6 +104,7 @@ #include <linux/swapops.h> #include <asm/tlbflush.h> +#include <asm/tlb.h> #include <linux/uaccess.h> #include "internal.h" @@ -350,7 +351,7 @@ static void mpol_rebind_preferred(struct mempolicy *pol, */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { - if (!pol) + if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) @@ -440,12 +441,11 @@ static inline bool queue_pages_required(struct page *page, } /* - * queue_pages_pmd() has four possible return values: + * queue_pages_pmd() has three possible return values: * 0 - pages are placed on the right node or queued successfully, or * special page is met, i.e. huge zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. - * 2 - THP was split. * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing page was already on a node that does not follow the * policy. @@ -507,18 +507,13 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, struct page *page; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - int ret; bool has_unmovable = false; pte_t *pte, *mapped_pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); - if (ptl) { - ret = queue_pages_pmd(pmd, ptl, addr, end, walk); - if (ret != 2) - return ret; - } - /* THP was split, fall through to pte walk */ + if (ptl) + return queue_pages_pmd(pmd, ptl, addr, end, walk); if (pmd_trans_unstable(pmd)) return 0; @@ -636,12 +631,18 @@ unlock: unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { + struct mmu_gather tlb; int nr_updated; - nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA); + tlb_gather_mmu(&tlb, vma->vm_mm); + + nr_updated = change_protection(&tlb, vma, addr, end, PAGE_NONE, + MM_CP_PROT_NUMA); if (nr_updated) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); + tlb_finish_mmu(&tlb); + return nr_updated; } #else @@ -2135,44 +2136,55 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, } /** - * alloc_pages_vma - Allocate a page for a VMA. + * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. - * @order: Order of the GFP allocation. + * @order: Order of the folio. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual address of the allocation. Must be inside @vma. * @hugepage: For hugepages try only the preferred node if possible. * - * Allocate a page for a specific address in @vma, using the appropriate + * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. When @vma is not NULL the caller must hold the mmap_lock * of the mm_struct of the VMA to prevent it from going away. Should be - * used for all allocations for pages that will be mapped into user space. + * used for all allocations for folios that will be mapped into user space. * - * Return: The page on success or NULL if allocation fails. + * Return: The folio on success or NULL if allocation fails. */ -struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage) { struct mempolicy *pol; int node = numa_node_id(); - struct page *page; + struct folio *folio; int preferred_nid; nodemask_t *nmask; pol = get_vma_policy(vma, addr); if (pol->mode == MPOL_INTERLEAVE) { + struct page *page; unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); + gfp |= __GFP_COMP; page = alloc_page_interleave(gfp, order, nid); + if (page && order > 1) + prep_transhuge_page(page); + folio = (struct folio *)page; goto out; } if (pol->mode == MPOL_PREFERRED_MANY) { + struct page *page; + node = policy_node(gfp, pol, node); + gfp |= __GFP_COMP; page = alloc_pages_preferred_many(gfp, order, node, pol); mpol_cond_put(pol); + if (page && order > 1) + prep_transhuge_page(page); + folio = (struct folio *)page; goto out; } @@ -2199,8 +2211,8 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ - page = __alloc_pages_node(hpage_node, - gfp | __GFP_THISNODE | __GFP_NORETRY, order); + folio = __folio_alloc_node(gfp | __GFP_THISNODE | + __GFP_NORETRY, order, hpage_node); /* * If hugepage allocations are configured to always @@ -2208,8 +2220,9 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ - if (!page && (gfp & __GFP_DIRECT_RECLAIM)) - page = __alloc_pages(gfp, order, hpage_node, nmask); + if (!folio && (gfp & __GFP_DIRECT_RECLAIM)) + folio = __folio_alloc(gfp, order, hpage_node, + nmask); goto out; } @@ -2217,25 +2230,12 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); - page = __alloc_pages(gfp, order, preferred_nid, nmask); + folio = __folio_alloc(gfp, order, preferred_nid, nmask); mpol_cond_put(pol); out: - return page; -} -EXPORT_SYMBOL(alloc_pages_vma); - -struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, bool hugepage) -{ - struct folio *folio; - - folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr, - hugepage); - if (folio && order > 1) - prep_transhuge_page(&folio->page); - return folio; } +EXPORT_SYMBOL(vma_alloc_folio); /** * alloc_pages - Allocate pages. diff --git a/mm/memremap.c b/mm/memremap.c index af0223605e69..2b92e97cb25b 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -287,6 +287,7 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) { struct mhp_params params = { .altmap = pgmap_altmap(pgmap), + .pgmap = pgmap, .pgprot = PAGE_KERNEL, }; const int nr_range = pgmap->nr_range; @@ -459,6 +460,15 @@ void free_zone_device_page(struct page *page) mem_cgroup_uncharge(page_folio(page)); /* + * 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); + + /* * When a device managed page is freed, the page->mapping field * may still contain a (stale) mapping value. For example, the * lower bits of page->mapping may still identify the page as an diff --git a/mm/migrate.c b/mm/migrate.c index 21d82636c291..e51588e95f57 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -177,6 +177,7 @@ static bool remove_migration_pte(struct folio *folio, DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { + rmap_t rmap_flags = RMAP_NONE; pte_t pte; swp_entry_t entry; struct page *new; @@ -211,6 +212,9 @@ static bool remove_migration_pte(struct folio *folio, else if (pte_swp_uffd_wp(*pvmw.pte)) pte = pte_mkuffd_wp(pte); + if (folio_test_anon(folio) && !is_readable_migration_entry(entry)) + rmap_flags |= RMAP_EXCLUSIVE; + if (unlikely(is_device_private_page(new))) { if (pte_write(pte)) entry = make_writable_device_private_entry( @@ -232,15 +236,17 @@ static bool remove_migration_pte(struct folio *folio, pte = pte_mkhuge(pte); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) - hugepage_add_anon_rmap(new, vma, pvmw.address); + hugepage_add_anon_rmap(new, vma, pvmw.address, + rmap_flags); else - page_dup_rmap(new, true); + page_dup_file_rmap(new, true); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); } else #endif { if (folio_test_anon(folio)) - page_add_anon_rmap(new, vma, pvmw.address, false); + page_add_anon_rmap(new, vma, pvmw.address, + rmap_flags); else page_add_file_rmap(new, vma, false); set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); @@ -471,11 +477,6 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, xas_lock_irq(&xas); expected_count = 2 + page_has_private(page); - if (page_count(page) != expected_count || xas_load(&xas) != page) { - xas_unlock_irq(&xas); - return -EAGAIN; - } - if (!page_ref_freeze(page, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; @@ -517,6 +518,12 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) folio_set_workingset(newfolio); if (folio_test_checked(folio)) folio_set_checked(newfolio); + /* + * PG_anon_exclusive (-> PG_mappedtodisk) is always migrated via + * migration entries. We can still have PG_anon_exclusive set on an + * effectively unmapped and unreferenced first sub-pages of an + * anonymous THP: we can simply copy it here via PG_mappedtodisk. + */ if (folio_test_mappedtodisk(folio)) folio_set_mappedtodisk(newfolio); @@ -836,21 +843,21 @@ static int fallback_migrate_page(struct address_space *mapping, * < 0 - error code * MIGRATEPAGE_SUCCESS - success */ -static int move_to_new_page(struct page *newpage, struct page *page, +static int move_to_new_folio(struct folio *dst, struct folio *src, enum migrate_mode mode) { struct address_space *mapping; int rc = -EAGAIN; - bool is_lru = !__PageMovable(page); + bool is_lru = !__PageMovable(&src->page); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(src), src); + VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst); - mapping = page_mapping(page); + mapping = folio_mapping(src); if (likely(is_lru)) { if (!mapping) - rc = migrate_page(mapping, newpage, page, mode); + rc = migrate_page(mapping, &dst->page, &src->page, mode); else if (mapping->a_ops->migratepage) /* * Most pages have a mapping and most filesystems @@ -859,54 +866,54 @@ static int move_to_new_page(struct page *newpage, struct page *page, * migratepage callback. This is the most common path * for page migration. */ - rc = mapping->a_ops->migratepage(mapping, newpage, - page, mode); + rc = mapping->a_ops->migratepage(mapping, &dst->page, + &src->page, mode); else - rc = fallback_migrate_page(mapping, newpage, - page, mode); + rc = fallback_migrate_page(mapping, &dst->page, + &src->page, mode); } else { /* * In case of non-lru page, it could be released after * isolation step. In that case, we shouldn't try migration. */ - VM_BUG_ON_PAGE(!PageIsolated(page), page); - if (!PageMovable(page)) { + VM_BUG_ON_FOLIO(!folio_test_isolated(src), src); + if (!folio_test_movable(src)) { rc = MIGRATEPAGE_SUCCESS; - ClearPageIsolated(page); + folio_clear_isolated(src); goto out; } - rc = mapping->a_ops->migratepage(mapping, newpage, - page, mode); + rc = mapping->a_ops->migratepage(mapping, &dst->page, + &src->page, mode); WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS && - !PageIsolated(page)); + !folio_test_isolated(src)); } /* - * When successful, old pagecache page->mapping must be cleared before - * page is freed; but stats require that PageAnon be left as PageAnon. + * When successful, old pagecache src->mapping must be cleared before + * src is freed; but stats require that PageAnon be left as PageAnon. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (__PageMovable(page)) { - VM_BUG_ON_PAGE(!PageIsolated(page), page); + if (__PageMovable(&src->page)) { + VM_BUG_ON_FOLIO(!folio_test_isolated(src), src); /* * We clear PG_movable under page_lock so any compactor * cannot try to migrate this page. */ - ClearPageIsolated(page); + folio_clear_isolated(src); } /* - * Anonymous and movable page->mapping will be cleared by + * Anonymous and movable src->mapping will be cleared by * free_pages_prepare so don't reset it here for keeping * the type to work PageAnon, for example. */ - if (!PageMappingFlags(page)) - page->mapping = NULL; + if (!folio_mapping_flags(src)) + src->mapping = NULL; - if (likely(!is_zone_device_page(newpage))) - flush_dcache_folio(page_folio(newpage)); + if (likely(!folio_is_zone_device(dst))) + flush_dcache_folio(dst); } out: return rc; @@ -994,7 +1001,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, goto out_unlock; if (unlikely(!is_lru)) { - rc = move_to_new_page(newpage, page, mode); + rc = move_to_new_folio(dst, folio, mode); goto out_unlock_both; } @@ -1025,7 +1032,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, } if (!page_mapped(page)) - rc = move_to_new_page(newpage, page, mode); + rc = move_to_new_folio(dst, folio, mode); /* * When successful, push newpage to LRU immediately: so that if it @@ -1230,7 +1237,6 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, goto put_anon; if (page_mapped(hpage)) { - bool mapping_locked = false; enum ttu_flags ttu = 0; if (!PageAnon(hpage)) { @@ -1244,19 +1250,18 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (unlikely(!mapping)) goto unlock_put_anon; - mapping_locked = true; - ttu |= TTU_RMAP_LOCKED; + ttu = TTU_RMAP_LOCKED; } try_to_migrate(src, ttu); page_was_mapped = 1; - if (mapping_locked) + if (ttu & TTU_RMAP_LOCKED) i_mmap_unlock_write(mapping); } if (!page_mapped(hpage)) - rc = move_to_new_page(new_hpage, hpage, mode); + rc = move_to_new_folio(dst, src, mode); if (page_was_mapped) remove_migration_ptes(src, @@ -1412,14 +1417,11 @@ retry: nr_thp_split++; goto retry; } - - nr_failed_pages += nr_subpages; - break; - } - /* Hugetlb migration is unsupported */ - if (!no_subpage_counting) + } else if (!no_subpage_counting) { nr_failed++; + } + nr_failed_pages += nr_subpages; break; case -ENOMEM: @@ -1434,28 +1436,30 @@ retry: nr_thp_split++; goto retry; } - - nr_failed_pages += nr_subpages; - goto out; + } else if (!no_subpage_counting) { + nr_failed++; } - if (!no_subpage_counting) - nr_failed++; nr_failed_pages += nr_subpages; + /* + * There might be some subpages of fail-to-migrate THPs + * left in thp_split_pages list. Move them back to migration + * list so that they could be put back to the right list by + * the caller otherwise the page refcnt will be leaked. + */ + list_splice_init(&thp_split_pages, from); + nr_thp_failed += thp_retry; goto out; case -EAGAIN: - if (is_thp) { + if (is_thp) thp_retry++; - break; - } - retry++; + else + retry++; break; case MIGRATEPAGE_SUCCESS: nr_succeeded += nr_subpages; - if (is_thp) { + if (is_thp) nr_thp_succeeded++; - break; - } break; default: /* @@ -1464,14 +1468,11 @@ retry: * removed from migration page list and not * retried in the next outer loop. */ - if (is_thp) { + if (is_thp) nr_thp_failed++; - nr_failed_pages += nr_subpages; - break; - } - - if (!no_subpage_counting) + else if (!no_subpage_counting) nr_failed++; + nr_failed_pages += nr_subpages; break; } @@ -1606,8 +1607,8 @@ static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, mmap_read_lock(mm); err = -EFAULT; - vma = find_vma(mm, addr); - if (!vma || addr < vma->vm_start || !vma_migratable(vma)) + vma = vma_lookup(mm, addr); + if (!vma || !vma_migratable(vma)) goto out; /* FOLL_DUMP to ignore special (like zero) pages */ @@ -1802,13 +1803,18 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, goto set_status; /* FOLL_DUMP to ignore special (like zero) pages */ - page = follow_page(vma, addr, FOLL_DUMP); + page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); err = PTR_ERR(page); if (IS_ERR(page)) goto set_status; - err = page ? page_to_nid(page) : -ENOENT; + if (page) { + err = page_to_nid(page); + put_page(page); + } else { + err = -ENOENT; + } set_status: *status = err; @@ -1844,16 +1850,12 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, const void __user * __user *pages, int __user *status) { -#define DO_PAGES_STAT_CHUNK_NR 16 +#define DO_PAGES_STAT_CHUNK_NR 16UL const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; int chunk_status[DO_PAGES_STAT_CHUNK_NR]; while (nr_pages) { - unsigned long chunk_nr; - - chunk_nr = nr_pages; - if (chunk_nr > DO_PAGES_STAT_CHUNK_NR) - chunk_nr = DO_PAGES_STAT_CHUNK_NR; + unsigned long chunk_nr = min(nr_pages, DO_PAGES_STAT_CHUNK_NR); if (in_compat_syscall()) { if (get_compat_pages_array(chunk_pages, pages, @@ -1969,7 +1971,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, #ifdef CONFIG_NUMA_BALANCING /* * Returns true if this is a safe migration target node for misplaced NUMA - * pages. Currently it only checks the watermarks which crude + * pages. Currently it only checks the watermarks which is crude. */ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, unsigned long nr_migrate_pages) @@ -1979,7 +1981,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat, for (z = pgdat->nr_zones - 1; z >= 0; z--) { struct zone *zone = pgdat->node_zones + z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; /* Avoid waking kswapd by allocating pages_to_migrate pages. */ @@ -2015,7 +2017,6 @@ static struct page *alloc_misplaced_dst_page(struct page *page, static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { - int page_lru; int nr_pages = thp_nr_pages(page); int order = compound_order(page); @@ -2032,7 +2033,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)) return 0; for (z = pgdat->nr_zones - 1; z >= 0; z--) { - if (populated_zone(pgdat->node_zones + z)) + if (managed_zone(pgdat->node_zones + z)) break; } wakeup_kswapd(pgdat->node_zones + z, 0, order, ZONE_MOVABLE); @@ -2042,8 +2043,7 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) if (isolate_lru_page(page)) return 0; - page_lru = page_is_file_lru(page); - mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page), nr_pages); /* @@ -2116,7 +2116,6 @@ out: return 0; } #endif /* CONFIG_NUMA_BALANCING */ -#endif /* CONFIG_NUMA */ /* * node_demotion[] example: @@ -2250,7 +2249,6 @@ out: return target; } -#if defined(CONFIG_HOTPLUG_CPU) /* Disable reclaim-based migration. */ static void __disable_all_migrate_targets(void) { @@ -2353,8 +2351,8 @@ out_clear: */ static void __set_migration_target_nodes(void) { - nodemask_t next_pass = NODE_MASK_NONE; - nodemask_t this_pass = NODE_MASK_NONE; + nodemask_t next_pass; + nodemask_t this_pass; nodemask_t used_targets = NODE_MASK_NONE; int node, best_distance; @@ -2443,6 +2441,7 @@ void set_migration_target_nodes(void) * __set_migration_target_nodes() can be used as opposed to * set_migration_target_nodes(). */ +#ifdef CONFIG_MEMORY_HOTPLUG static int __meminit migrate_on_reclaim_callback(struct notifier_block *self, unsigned long action, void *_arg) { @@ -2488,15 +2487,17 @@ static int __meminit migrate_on_reclaim_callback(struct notifier_block *self, return notifier_from_errno(0); } +#endif void __init migrate_on_reclaim_init(void) { - node_demotion = kmalloc_array(nr_node_ids, - sizeof(struct demotion_nodes), - GFP_KERNEL); + node_demotion = kcalloc(nr_node_ids, + sizeof(struct demotion_nodes), + GFP_KERNEL); WARN_ON(!node_demotion); - +#ifdef CONFIG_MEMORY_HOTPLUG hotplug_memory_notifier(migrate_on_reclaim_callback, 100); +#endif /* * At this point, all numa nodes with memory/CPus have their state * properly set, so we can build the demotion order now. @@ -2507,7 +2508,6 @@ void __init migrate_on_reclaim_init(void) set_migration_target_nodes(); cpus_read_unlock(); } -#endif /* CONFIG_HOTPLUG_CPU */ bool numa_demotion_enabled = false; @@ -2523,12 +2523,11 @@ static ssize_t numa_demotion_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) - numa_demotion_enabled = true; - else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) - numa_demotion_enabled = false; - else - return -EINVAL; + ssize_t ret; + + ret = kstrtobool(buf, &numa_demotion_enabled); + if (ret) + return ret; return count; } @@ -2568,4 +2567,5 @@ delete_obj: return err; } subsys_initcall(numa_init_sysfs); -#endif +#endif /* CONFIG_SYSFS */ +#endif /* CONFIG_NUMA */ diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 70c7dc05bbfc..5052093d0262 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -184,15 +184,34 @@ again: * set up a special migration page table entry now. */ if (trylock_page(page)) { + bool anon_exclusive; pte_t swp_pte; + anon_exclusive = PageAnon(page) && PageAnonExclusive(page); + if (anon_exclusive) { + flush_cache_page(vma, addr, pte_pfn(*ptep)); + ptep_clear_flush(vma, addr, ptep); + + if (page_try_share_anon_rmap(page)) { + set_pte_at(mm, addr, ptep, pte); + unlock_page(page); + put_page(page); + mpfn = 0; + goto next; + } + } else { + ptep_get_and_clear(mm, addr, ptep); + } + migrate->cpages++; - ptep_get_and_clear(mm, addr, ptep); /* Setup special migration page table entry */ if (mpfn & MIGRATE_PFN_WRITE) entry = make_writable_migration_entry( page_to_pfn(page)); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry( + page_to_pfn(page)); else entry = make_readable_migration_entry( page_to_pfn(page)); @@ -610,7 +629,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, goto unlock_abort; inc_mm_counter(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, addr, false); + page_add_new_anon_rmap(page, vma, addr); if (!is_zone_device_page(page)) lru_cache_add_inactive_or_unevictable(page, vma); get_page(page); diff --git a/mm/mincore.c b/mm/mincore.c index 9122676b54d6..fa200c14185f 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -20,6 +20,7 @@ #include <linux/pgtable.h> #include <linux/uaccess.h> +#include "swap.h" static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -121,7 +122,8 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, for (; addr != end; ptep++, addr += PAGE_SIZE) { pte_t pte = *ptep; - if (pte_none(pte)) + /* We need to do cache lookup too for pte markers */ + if (pte_none_mostly(pte)) __mincore_unmapped_range(addr, addr + PAGE_SIZE, vma, vec); else if (pte_present(pte)) diff --git a/mm/mmap.c b/mm/mmap.c index 313b57d55a63..2b9305ed0dda 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -102,26 +102,31 @@ static void unmap_region(struct mm_struct *mm, * x: (yes) yes */ pgprot_t protection_map[16] __ro_after_init = { - __P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111, - __S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111 + [VM_NONE] = __P000, + [VM_READ] = __P001, + [VM_WRITE] = __P010, + [VM_WRITE | VM_READ] = __P011, + [VM_EXEC] = __P100, + [VM_EXEC | VM_READ] = __P101, + [VM_EXEC | VM_WRITE] = __P110, + [VM_EXEC | VM_WRITE | VM_READ] = __P111, + [VM_SHARED] = __S000, + [VM_SHARED | VM_READ] = __S001, + [VM_SHARED | VM_WRITE] = __S010, + [VM_SHARED | VM_WRITE | VM_READ] = __S011, + [VM_SHARED | VM_EXEC] = __S100, + [VM_SHARED | VM_EXEC | VM_READ] = __S101, + [VM_SHARED | VM_EXEC | VM_WRITE] = __S110, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = __S111 }; -#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT -static inline pgprot_t arch_filter_pgprot(pgprot_t prot) -{ - return prot; -} -#endif - +#ifndef CONFIG_ARCH_HAS_VM_GET_PAGE_PROT pgprot_t vm_get_page_prot(unsigned long vm_flags) { - pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags & - (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) | - pgprot_val(arch_vm_get_page_prot(vm_flags))); - - return arch_filter_pgprot(ret); + return protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]; } EXPORT_SYMBOL(vm_get_page_prot); +#endif /* CONFIG_ARCH_HAS_VM_GET_PAGE_PROT */ static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { @@ -1218,7 +1223,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, end, prev->vm_pgoff, NULL, prev); if (err) return NULL; - khugepaged_enter_vma_merge(prev, vm_flags); + khugepaged_enter_vma(prev, vm_flags); return prev; } @@ -1245,7 +1250,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, } if (err) return NULL; - khugepaged_enter_vma_merge(area, vm_flags); + khugepaged_enter_vma(area, vm_flags); return area; } @@ -1280,7 +1285,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * - * NOTE! This runs with mm_sem held for reading, so it is possible that + * NOTE! This runs with mmap_lock held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton @@ -1294,7 +1299,7 @@ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct * * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just - * a read lock on the mm_sem. + * a read lock on the mmap_lock. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { @@ -1842,6 +1847,13 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } vma_link(mm, vma, prev, rb_link, rb_parent); + + /* + * vma_merge() calls khugepaged_enter_vma() either, the below + * call covers the non-merge case. + */ + khugepaged_enter_vma(vma, vma->vm_flags); + /* Once vma denies write, undo our temporary denial count */ unmap_writable: if (file && vm_flags & VM_SHARED) @@ -2340,15 +2352,8 @@ static int acct_stack_growth(struct vm_area_struct *vma, return -ENOMEM; /* mlock limit tests */ - if (vma->vm_flags & VM_LOCKED) { - unsigned long locked; - unsigned long limit; - locked = mm->locked_vm + grow; - limit = rlimit(RLIMIT_MEMLOCK); - limit >>= PAGE_SHIFT; - if (locked > limit && !capable(CAP_IPC_LOCK)) - return -ENOMEM; - } + if (mlock_future_check(mm, vma->vm_flags, grow << PAGE_SHIFT)) + return -ENOMEM; /* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : @@ -2452,7 +2457,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) } } anon_vma_unlock_write(vma->anon_vma); - khugepaged_enter_vma_merge(vma, vma->vm_flags); + khugepaged_enter_vma(vma, vma->vm_flags); validate_mm(mm); return error; } @@ -2530,7 +2535,7 @@ int expand_downwards(struct vm_area_struct *vma, } } anon_vma_unlock_write(vma->anon_vma); - khugepaged_enter_vma_merge(vma, vma->vm_flags); + khugepaged_enter_vma(vma, vma->vm_flags); validate_mm(mm); return error; } @@ -3553,7 +3558,7 @@ int mm_take_all_locks(struct mm_struct *mm) struct vm_area_struct *vma; struct anon_vma_chain *avc; - BUG_ON(mmap_read_trylock(mm)); + mmap_assert_write_locked(mm); mutex_lock(&mm_all_locks_mutex); @@ -3633,7 +3638,7 @@ void mm_drop_all_locks(struct mm_struct *mm) struct vm_area_struct *vma; struct anon_vma_chain *avc; - BUG_ON(mmap_read_trylock(mm)); + mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for (vma = mm->mmap; vma; vma = vma->vm_next) { diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index afb7185ffdc4..a71924bd38c0 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -47,8 +47,20 @@ static void tlb_batch_pages_flush(struct mmu_gather *tlb) struct mmu_gather_batch *batch; for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { - free_pages_and_swap_cache(batch->pages, batch->nr); - batch->nr = 0; + struct page **pages = batch->pages; + + do { + /* + * limit free batch count when PAGE_SIZE > 4K + */ + unsigned int nr = min(512U, batch->nr); + + free_pages_and_swap_cache(pages, nr); + pages += nr; + batch->nr -= nr; + + cond_resched(); + } while (batch->nr); } tlb->active = &tlb->local; } diff --git a/mm/mprotect.c b/mm/mprotect.c index b69ce7a7b2b7..ba5592655ee3 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -30,15 +30,17 @@ #include <linux/mm_inline.h> #include <linux/pgtable.h> #include <linux/sched/sysctl.h> +#include <linux/userfaultfd_k.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> +#include <asm/tlb.h> #include "internal.h" -static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, pgprot_t newprot, - unsigned long cp_flags) +static unsigned long change_pte_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, + unsigned long end, pgprot_t newprot, unsigned long cp_flags) { pte_t *pte, oldpte; spinlock_t *ptl; @@ -49,6 +51,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + tlb_change_page_size(tlb, PAGE_SIZE); + /* * Can be called with only the mmap_lock for reading by * prot_numa so we must check the pmd isn't constantly @@ -149,9 +153,12 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptent = pte_mkwrite(ptent); } ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent); + if (pte_needs_flush(oldpte, ptent)) + tlb_flush_pte_range(tlb, addr, PAGE_SIZE); pages++; } else if (is_swap_pte(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); + struct page *page = pfn_swap_entry_to_page(entry); pte_t newpte; if (is_writable_migration_entry(entry)) { @@ -159,8 +166,11 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * A protection check is difficult so * just be safe and disable write */ - entry = make_readable_migration_entry( - swp_offset(entry)); + if (PageAnon(page)) + entry = make_readable_exclusive_migration_entry( + swp_offset(entry)); + else + entry = make_readable_migration_entry(swp_offset(entry)); newpte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(oldpte)) newpte = pte_swp_mksoft_dirty(newpte); @@ -184,6 +194,17 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, newpte = pte_swp_mksoft_dirty(newpte); if (pte_swp_uffd_wp(oldpte)) newpte = pte_swp_mkuffd_wp(newpte); + } else if (pte_marker_entry_uffd_wp(entry)) { + /* + * If this is uffd-wp pte marker and we'd like + * to unprotect it, drop it; the next page + * fault will trigger without uffd trapping. + */ + if (uffd_wp_resolve) { + pte_clear(vma->vm_mm, addr, pte); + pages++; + } + continue; } else { newpte = oldpte; } @@ -197,6 +218,20 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, set_pte_at(vma->vm_mm, addr, pte, newpte); pages++; } + } else { + /* It must be an none page, or what else?.. */ + WARN_ON_ONCE(!pte_none(oldpte)); + if (unlikely(uffd_wp && !vma_is_anonymous(vma))) { + /* + * For file-backed mem, we need to be able to + * wr-protect a none pte, because even if the + * pte is none, the page/swap cache could + * exist. Doing that by install a marker. + */ + set_pte_at(vma->vm_mm, addr, pte, + make_pte_marker(PTE_MARKER_UFFD_WP)); + pages++; + } } } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); @@ -230,9 +265,42 @@ static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd) return 0; } -static inline unsigned long change_pmd_range(struct vm_area_struct *vma, - pud_t *pud, unsigned long addr, unsigned long end, - pgprot_t newprot, unsigned long cp_flags) +/* Return true if we're uffd wr-protecting file-backed memory, or false */ +static inline bool +uffd_wp_protect_file(struct vm_area_struct *vma, unsigned long cp_flags) +{ + return (cp_flags & MM_CP_UFFD_WP) && !vma_is_anonymous(vma); +} + +/* + * If wr-protecting the range for file-backed, populate pgtable for the case + * when pgtable is empty but page cache exists. When {pte|pmd|...}_alloc() + * failed it means no memory, we don't have a better option but stop. + */ +#define change_pmd_prepare(vma, pmd, cp_flags) \ + do { \ + if (unlikely(uffd_wp_protect_file(vma, cp_flags))) { \ + if (WARN_ON_ONCE(pte_alloc(vma->vm_mm, pmd))) \ + break; \ + } \ + } while (0) +/* + * This is the general pud/p4d/pgd version of change_pmd_prepare(). We need to + * have separate change_pmd_prepare() because pte_alloc() returns 0 on success, + * while {pmd|pud|p4d}_alloc() returns the valid pointer on success. + */ +#define change_prepare(vma, high, low, addr, cp_flags) \ + do { \ + if (unlikely(uffd_wp_protect_file(vma, cp_flags))) { \ + low##_t *p = low##_alloc(vma->vm_mm, high, addr); \ + if (WARN_ON_ONCE(p == NULL)) \ + break; \ + } \ + } while (0) + +static inline unsigned long change_pmd_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pud_t *pud, unsigned long addr, + unsigned long end, pgprot_t newprot, unsigned long cp_flags) { pmd_t *pmd; unsigned long next; @@ -248,6 +316,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, next = pmd_addr_end(addr, end); + change_pmd_prepare(vma, pmd, cp_flags); /* * Automatic NUMA balancing walks the tables with mmap_lock * held for read. It's possible a parallel update to occur @@ -269,11 +338,22 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, } if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { - if (next - addr != HPAGE_PMD_SIZE) { + if ((next - addr != HPAGE_PMD_SIZE) || + uffd_wp_protect_file(vma, cp_flags)) { __split_huge_pmd(vma, pmd, addr, false, NULL); + /* + * For file-backed, the pmd could have been + * cleared; make sure pmd populated if + * necessary, then fall-through to pte level. + */ + change_pmd_prepare(vma, pmd, cp_flags); } else { - int nr_ptes = change_huge_pmd(vma, pmd, addr, - newprot, cp_flags); + /* + * change_huge_pmd() does not defer TLB flushes, + * so no need to propagate the tlb argument. + */ + int nr_ptes = change_huge_pmd(tlb, vma, pmd, + addr, newprot, cp_flags); if (nr_ptes) { if (nr_ptes == HPAGE_PMD_NR) { @@ -287,8 +367,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, } /* fall through, the trans huge pmd just split */ } - this_pages = change_pte_range(vma, pmd, addr, next, newprot, - cp_flags); + this_pages = change_pte_range(tlb, vma, pmd, addr, next, + newprot, cp_flags); pages += this_pages; next: cond_resched(); @@ -302,9 +382,9 @@ next: return pages; } -static inline unsigned long change_pud_range(struct vm_area_struct *vma, - p4d_t *p4d, unsigned long addr, unsigned long end, - pgprot_t newprot, unsigned long cp_flags) +static inline unsigned long change_pud_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, + unsigned long end, pgprot_t newprot, unsigned long cp_flags) { pud_t *pud; unsigned long next; @@ -313,18 +393,19 @@ static inline unsigned long change_pud_range(struct vm_area_struct *vma, pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); + change_prepare(vma, pud, pmd, addr, cp_flags); if (pud_none_or_clear_bad(pud)) continue; - pages += change_pmd_range(vma, pud, addr, next, newprot, + pages += change_pmd_range(tlb, vma, pud, addr, next, newprot, cp_flags); } while (pud++, addr = next, addr != end); return pages; } -static inline unsigned long change_p4d_range(struct vm_area_struct *vma, - pgd_t *pgd, unsigned long addr, unsigned long end, - pgprot_t newprot, unsigned long cp_flags) +static inline unsigned long change_p4d_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, + unsigned long end, pgprot_t newprot, unsigned long cp_flags) { p4d_t *p4d; unsigned long next; @@ -333,46 +414,44 @@ static inline unsigned long change_p4d_range(struct vm_area_struct *vma, p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); + change_prepare(vma, p4d, pud, addr, cp_flags); if (p4d_none_or_clear_bad(p4d)) continue; - pages += change_pud_range(vma, p4d, addr, next, newprot, + pages += change_pud_range(tlb, vma, p4d, addr, next, newprot, cp_flags); } while (p4d++, addr = next, addr != end); return pages; } -static unsigned long change_protection_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, pgprot_t newprot, - unsigned long cp_flags) +static unsigned long change_protection_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long addr, + unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; unsigned long next; - unsigned long start = addr; unsigned long pages = 0; BUG_ON(addr >= end); pgd = pgd_offset(mm, addr); - flush_cache_range(vma, addr, end); - inc_tlb_flush_pending(mm); + tlb_start_vma(tlb, vma); do { next = pgd_addr_end(addr, end); + change_prepare(vma, pgd, p4d, addr, cp_flags); if (pgd_none_or_clear_bad(pgd)) continue; - pages += change_p4d_range(vma, pgd, addr, next, newprot, + pages += change_p4d_range(tlb, vma, pgd, addr, next, newprot, cp_flags); } while (pgd++, addr = next, addr != end); - /* Only flush the TLB if we actually modified any entries: */ - if (pages) - flush_tlb_range(vma, start, end); - dec_tlb_flush_pending(mm); + tlb_end_vma(tlb, vma); return pages; } -unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, +unsigned long change_protection(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { @@ -381,9 +460,10 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL); if (is_vm_hugetlb_page(vma)) - pages = hugetlb_change_protection(vma, start, end, newprot); + pages = hugetlb_change_protection(vma, start, end, newprot, + cp_flags); else - pages = change_protection_range(vma, start, end, newprot, + pages = change_protection_range(tlb, vma, start, end, newprot, cp_flags); return pages; @@ -417,8 +497,9 @@ static const struct mm_walk_ops prot_none_walk_ops = { }; int -mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, - unsigned long start, unsigned long end, unsigned long newflags) +mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, + struct vm_area_struct **pprev, unsigned long start, + unsigned long end, unsigned long newflags) { struct mm_struct *mm = vma->vm_mm; unsigned long oldflags = vma->vm_flags; @@ -505,7 +586,7 @@ success: dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot); vma_set_page_prot(vma); - change_protection(vma, start, end, vma->vm_page_prot, + change_protection(tlb, vma, start, end, vma->vm_page_prot, dirty_accountable ? MM_CP_DIRTY_ACCT : 0); /* @@ -539,6 +620,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP); const bool rier = (current->personality & READ_IMPLIES_EXEC) && (prot & PROT_READ); + struct mmu_gather tlb; start = untagged_addr(start); @@ -598,6 +680,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, else prev = vma->vm_prev; + tlb_gather_mmu(&tlb, current->mm); for (nstart = start ; ; ) { unsigned long mask_off_old_flags; unsigned long newflags; @@ -624,18 +707,18 @@ static int do_mprotect_pkey(unsigned long start, size_t len, /* newflags >> 4 shift VM_MAY% in place of VM_% */ if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) { error = -EACCES; - goto out; + break; } /* Allow architectures to sanity-check the new flags */ if (!arch_validate_flags(newflags)) { error = -EINVAL; - goto out; + break; } error = security_file_mprotect(vma, reqprot, prot); if (error) - goto out; + break; tmp = vma->vm_end; if (tmp > end) @@ -644,27 +727,28 @@ static int do_mprotect_pkey(unsigned long start, size_t len, if (vma->vm_ops && vma->vm_ops->mprotect) { error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags); if (error) - goto out; + break; } - error = mprotect_fixup(vma, &prev, nstart, tmp, newflags); + error = mprotect_fixup(&tlb, vma, &prev, nstart, tmp, newflags); if (error) - goto out; + break; nstart = tmp; if (nstart < prev->vm_end) nstart = prev->vm_end; if (nstart >= end) - goto out; + break; vma = prev->vm_next; if (!vma || vma->vm_start != nstart) { error = -ENOMEM; - goto out; + break; } prot = reqprot; } + tlb_finish_mmu(&tlb); out: mmap_write_unlock(current->mm); return error; diff --git a/mm/mremap.c b/mm/mremap.c index 0b93fac76851..b522cd0259a0 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -490,12 +490,12 @@ unsigned long move_page_tables(struct vm_area_struct *vma, return 0; old_end = old_addr + len; - flush_cache_range(vma, old_addr, old_end); if (is_vm_hugetlb_page(vma)) return move_hugetlb_page_tables(vma, new_vma, old_addr, new_addr, len); + flush_cache_range(vma, old_addr, old_end); mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, old_addr, old_end); mmu_notifier_invalidate_range_start(&range); @@ -766,14 +766,8 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) return ERR_PTR(-EFAULT); - if (vma->vm_flags & VM_LOCKED) { - unsigned long locked, lock_limit; - locked = mm->locked_vm << PAGE_SHIFT; - lock_limit = rlimit(RLIMIT_MEMLOCK); - locked += new_len - old_len; - if (locked > lock_limit && !capable(CAP_IPC_LOCK)) - return ERR_PTR(-EAGAIN); - } + if (mlock_future_check(mm, vma->vm_flags, new_len - old_len)) + return ERR_PTR(-EAGAIN); if (!may_expand_vm(mm, vma->vm_flags, (new_len - old_len) >> PAGE_SHIFT)) @@ -826,9 +820,9 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, goto out; } - if (old_len >= new_len) { + if (old_len > new_len) { ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap); - if (ret && old_len != new_len) + if (ret) goto out; old_len = new_len; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index fa1117db4610..359dc1da3636 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -650,18 +650,25 @@ static unsigned int bdi_min_ratio; int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { + unsigned int delta; int ret = 0; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { - min_ratio -= bdi->min_ratio; - if (bdi_min_ratio + min_ratio < 100) { - bdi_min_ratio += min_ratio; - bdi->min_ratio += min_ratio; + if (min_ratio < bdi->min_ratio) { + delta = bdi->min_ratio - min_ratio; + bdi_min_ratio -= delta; + bdi->min_ratio = min_ratio; } else { - ret = -EINVAL; + delta = min_ratio - bdi->min_ratio; + if (bdi_min_ratio + delta < 100) { + bdi_min_ratio += delta; + bdi->min_ratio = min_ratio; + } else { + ret = -EINVAL; + } } } spin_unlock_bh(&bdi_lock); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0e42038382c1..bc93a82e51e6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -81,6 +81,7 @@ #include "internal.h" #include "shuffle.h" #include "page_reporting.h" +#include "swap.h" /* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */ typedef int __bitwise fpi_t; @@ -867,40 +868,6 @@ static inline void set_buddy_order(struct page *page, unsigned int order) __SetPageBuddy(page); } -/* - * This function checks whether a page is free && is the buddy - * we can coalesce a page and its buddy if - * (a) the buddy is not in a hole (check before calling!) && - * (b) the buddy is in the buddy system && - * (c) a page and its buddy have the same order && - * (d) a page and its buddy are in the same zone. - * - * For recording whether a page is in the buddy system, we set PageBuddy. - * Setting, clearing, and testing PageBuddy is serialized by zone->lock. - * - * For recording page's order, we use page_private(page). - */ -static inline bool page_is_buddy(struct page *page, struct page *buddy, - unsigned int order) -{ - if (!page_is_guard(buddy) && !PageBuddy(buddy)) - return false; - - if (buddy_order(buddy) != order) - return false; - - /* - * zone check is done late to avoid uselessly calculating - * zone/node ids for pages that could never merge. - */ - if (page_zone_id(page) != page_zone_id(buddy)) - return false; - - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); - - return true; -} - #ifdef CONFIG_COMPACTION static inline struct capture_control *task_capc(struct zone *zone) { @@ -1009,18 +976,17 @@ static inline bool buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, struct page *page, unsigned int order) { - struct page *higher_page, *higher_buddy; - unsigned long combined_pfn; + unsigned long higher_page_pfn; + struct page *higher_page; if (order >= MAX_ORDER - 2) return false; - combined_pfn = buddy_pfn & pfn; - higher_page = page + (combined_pfn - pfn); - buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1); - higher_buddy = higher_page + (buddy_pfn - combined_pfn); + higher_page_pfn = buddy_pfn & pfn; + higher_page = page + (higher_page_pfn - pfn); - return page_is_buddy(higher_page, higher_buddy, order + 1); + return find_buddy_page_pfn(higher_page, higher_page_pfn, order + 1, + NULL) != NULL; } /* @@ -1053,7 +1019,6 @@ static inline void __free_one_page(struct page *page, int migratetype, fpi_t fpi_flags) { struct capture_control *capc = task_capc(zone); - unsigned int max_order = pageblock_order; unsigned long buddy_pfn; unsigned long combined_pfn; struct page *buddy; @@ -1069,18 +1034,32 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); -continue_merging: - while (order < max_order) { + while (order < MAX_ORDER - 1) { if (compaction_capture(capc, page, order, migratetype)) { __mod_zone_freepage_state(zone, -(1 << order), migratetype); return; } - buddy_pfn = __find_buddy_pfn(pfn, order); - buddy = page + (buddy_pfn - pfn); - if (!page_is_buddy(page, buddy, order)) + buddy = find_buddy_page_pfn(page, pfn, order, &buddy_pfn); + if (!buddy) goto done_merging; + + if (unlikely(order >= pageblock_order)) { + /* + * We want to prevent merge between freepages on pageblock + * without fallbacks and normal pageblock. Without this, + * pageblock isolation could cause incorrect freepage or CMA + * accounting or HIGHATOMIC accounting. + */ + int buddy_mt = get_pageblock_migratetype(buddy); + + if (migratetype != buddy_mt + && (!migratetype_is_mergeable(migratetype) || + !migratetype_is_mergeable(buddy_mt))) + goto done_merging; + } + /* * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page, * merge with it and move up one order. @@ -1094,32 +1073,6 @@ continue_merging: pfn = combined_pfn; order++; } - if (order < MAX_ORDER - 1) { - /* If we are here, it means order is >= pageblock_order. - * We want to prevent merge between freepages on pageblock - * without fallbacks and normal pageblock. Without this, - * pageblock isolation could cause incorrect freepage or CMA - * accounting or HIGHATOMIC accounting. - * - * We don't want to hit this code for the more frequent - * low-order merging. - */ - int buddy_mt; - - buddy_pfn = __find_buddy_pfn(pfn, order); - buddy = page + (buddy_pfn - pfn); - - if (!page_is_buddy(page, buddy, order)) - goto done_merging; - buddy_mt = get_pageblock_migratetype(buddy); - - if (migratetype != buddy_mt - && (!migratetype_is_mergeable(migratetype) || - !migratetype_is_mergeable(buddy_mt))) - goto done_merging; - max_order = order + 1; - goto continue_merging; - } done_merging: set_buddy_order(page, order); @@ -1141,6 +1094,48 @@ done_merging: 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 + * + * 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. + */ +void split_free_page(struct page *free_page, + 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; + + if (split_pfn_offset == 0) + return; + + spin_lock_irqsave(&zone->lock, flags); + 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(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); + } + spin_unlock_irqrestore(&zone->lock, flags); +} /* * 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 @@ -2476,6 +2471,9 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, del_page_from_free_list(page, zone, current_order); 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); return page; } @@ -2999,7 +2997,7 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, zone_page_state(zone, NR_FREE_PAGES) / 2) { page = __rmqueue_cma_fallback(zone, order); if (page) - goto out; + return page; } } retry: @@ -3012,9 +3010,6 @@ retry: alloc_flags)) goto retry; } -out: - if (page) - trace_mm_page_alloc_zone_locked(page, order, migratetype); return page; } @@ -3733,11 +3728,8 @@ struct page *rmqueue(struct zone *preferred_zone, * reserved for high-order atomic allocation, so order-0 * request should skip it. */ - if (order > 0 && alloc_flags & ALLOC_HARDER) { + if (order > 0 && alloc_flags & ALLOC_HARDER) page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); - if (page) - trace_mm_page_alloc_zone_locked(page, order, migratetype); - } if (!page) { page = __rmqueue(zone, order, migratetype, alloc_flags); if (!page) @@ -3799,6 +3791,9 @@ static bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) (gfp_mask & __GFP_DIRECT_RECLAIM)) return false; + if (gfp_mask & __GFP_NOWARN) + fail_page_alloc.attr.no_warn = true; + return should_fail(&fail_page_alloc.attr, 1 << order); } @@ -4068,7 +4063,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, { struct zoneref *z; struct zone *zone; - struct pglist_data *last_pgdat_dirty_limit = NULL; + struct pglist_data *last_pgdat = NULL; + bool last_pgdat_dirty_ok = false; bool no_fallback; retry: @@ -4107,13 +4103,13 @@ retry: * dirty-throttling and the flusher threads. */ if (ac->spread_dirty_pages) { - if (last_pgdat_dirty_limit == zone->zone_pgdat) - continue; + if (last_pgdat != zone->zone_pgdat) { + last_pgdat = zone->zone_pgdat; + last_pgdat_dirty_ok = node_dirty_ok(zone->zone_pgdat); + } - if (!node_dirty_ok(zone->zone_pgdat)) { - last_pgdat_dirty_limit = zone->zone_pgdat; + if (!last_pgdat_dirty_ok) continue; - } } if (no_fallback && nr_online_nodes > 1 && @@ -4346,7 +4342,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, */ /* Exhausted what can be done so it's blame time */ - if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) { + if (out_of_memory(&oc) || + WARN_ON_ONCE_GFP(gfp_mask & __GFP_NOFAIL, gfp_mask)) { *did_some_progress = 1; /* @@ -4677,9 +4674,12 @@ static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask, for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx, ac->nodemask) { - if (last_pgdat != zone->zone_pgdat) + if (!managed_zone(zone)) + continue; + if (last_pgdat != zone->zone_pgdat) { wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx); - last_pgdat = zone->zone_pgdat; + last_pgdat = zone->zone_pgdat; + } } } @@ -5117,7 +5117,7 @@ nopage: * All existing users of the __GFP_NOFAIL are blockable, so warn * of any new users that actually require GFP_NOWAIT */ - if (WARN_ON_ONCE(!can_direct_reclaim)) + if (WARN_ON_ONCE_GFP(!can_direct_reclaim, gfp_mask)) goto fail; /* @@ -5125,7 +5125,7 @@ nopage: * because we cannot reclaim anything and only can loop waiting * for somebody to do a work for us */ - WARN_ON_ONCE(current->flags & PF_MEMALLOC); + WARN_ON_ONCE_GFP(current->flags & PF_MEMALLOC, gfp_mask); /* * non failing costly orders are a hard requirement which we @@ -5133,7 +5133,7 @@ nopage: * so that we can identify them and convert them to something * else. */ - WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER); + WARN_ON_ONCE_GFP(order > PAGE_ALLOC_COSTLY_ORDER, gfp_mask); /* * Help non-failing allocations by giving them access to memory @@ -5379,10 +5379,8 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, * There are several places where we assume that the order value is sane * so bail out early if the request is out of bound. */ - if (unlikely(order >= MAX_ORDER)) { - WARN_ON_ONCE(!(gfp & __GFP_NOWARN)); + if (WARN_ON_ONCE_GFP(order >= MAX_ORDER, gfp)) return NULL; - } gfp &= gfp_allowed_mask; /* @@ -6171,7 +6169,6 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write, } -#define MAX_NODE_LOAD (nr_online_nodes) static int node_load[MAX_NUMNODES]; /** @@ -6218,7 +6215,7 @@ int find_next_best_node(int node, nodemask_t *used_node_mask) val += PENALTY_FOR_NODE_WITH_CPUS; /* Slight preference for less loaded node */ - val *= (MAX_NODE_LOAD*MAX_NUMNODES); + val *= MAX_NUMNODES; val += node_load[n]; if (val < min_val) { @@ -6284,13 +6281,12 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) static void build_zonelists(pg_data_t *pgdat) { static int node_order[MAX_NUMNODES]; - int node, load, nr_nodes = 0; + int node, nr_nodes = 0; nodemask_t used_mask = NODE_MASK_NONE; int local_node, prev_node; /* NUMA-aware ordering of nodes */ local_node = pgdat->node_id; - load = nr_online_nodes; prev_node = local_node; memset(node_order, 0, sizeof(node_order)); @@ -6302,11 +6298,10 @@ static void build_zonelists(pg_data_t *pgdat) */ if (node_distance(local_node, node) != node_distance(local_node, prev_node)) - node_load[node] += load; + node_load[node] += 1; node_order[nr_nodes++] = node; prev_node = node; - load--; } build_zonelists_in_node_order(pgdat, node_order, nr_nodes); @@ -6645,6 +6640,21 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, } } +/* + * With compound page geometry and when struct pages are stored in ram most + * tail pages are reused. Consequently, the amount of unique struct pages to + * initialize is a lot smaller that the total amount of struct pages being + * mapped. This is a paired / mild layering violation with explicit knowledge + * of how the sparse_vmemmap internals handle compound pages in the lack + * of an altmap. See vmemmap_populate_compound_pages(). + */ +static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap, + unsigned long nr_pages) +{ + return is_power_of_2(sizeof(struct page)) && + !altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages; +} + static void __ref memmap_init_compound(struct page *head, unsigned long head_pfn, unsigned long zone_idx, int nid, @@ -6709,7 +6719,7 @@ void __ref memmap_init_zone_device(struct zone *zone, continue; memmap_init_compound(page, pfn, zone_idx, nid, pgmap, - pfns_per_compound); + compound_nr_pages(altmap, pfns_per_compound)); } pr_info("%s initialised %lu pages in %ums\n", __func__, @@ -7870,7 +7880,7 @@ static void __init find_zone_movable_pfns_for_nodes(void) usable_startpfn = memblock_region_memory_base_pfn(r); - if (usable_startpfn < 0x100000) { + if (usable_startpfn < PHYS_PFN(SZ_4G)) { mem_below_4gb_not_mirrored = true; continue; } @@ -8949,136 +8959,7 @@ void *__init alloc_large_system_hash(const char *tablename, return table; } -/* - * This function checks whether pageblock includes unmovable pages or not. - * - * PageLRU check without isolation or lru_lock could race so that - * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable - * check without lock_page also may miss some movable non-lru pages at - * race condition. So you can't expect this function should be exact. - * - * Returns a page without holding a reference. If the caller wants to - * dereference that page (e.g., dumping), it has to make sure that it - * cannot get removed (e.g., via memory unplug) concurrently. - * - */ -struct page *has_unmovable_pages(struct zone *zone, struct page *page, - int migratetype, int flags) -{ - unsigned long iter = 0; - unsigned long pfn = page_to_pfn(page); - unsigned long offset = pfn % pageblock_nr_pages; - - if (is_migrate_cma_page(page)) { - /* - * CMA allocations (alloc_contig_range) really need to mark - * isolate CMA pageblocks even when they are not movable in fact - * so consider them movable here. - */ - if (is_migrate_cma(migratetype)) - return NULL; - - return page; - } - - for (; iter < pageblock_nr_pages - offset; iter++) { - page = pfn_to_page(pfn + iter); - - /* - * Both, bootmem allocations and memory holes are marked - * PG_reserved and are unmovable. We can even have unmovable - * allocations inside ZONE_MOVABLE, for example when - * specifying "movablecore". - */ - if (PageReserved(page)) - return page; - - /* - * If the zone is movable and we have ruled out all reserved - * pages then it should be reasonably safe to assume the rest - * is movable. - */ - if (zone_idx(zone) == ZONE_MOVABLE) - continue; - - /* - * Hugepages are not in LRU lists, but they're movable. - * THPs are on the LRU, but need to be counted as #small pages. - * We need not scan over tail pages because we don't - * handle each tail page individually in migration. - */ - if (PageHuge(page) || PageTransCompound(page)) { - struct page *head = compound_head(page); - unsigned int skip_pages; - - if (PageHuge(page)) { - if (!hugepage_migration_supported(page_hstate(head))) - return page; - } else if (!PageLRU(head) && !__PageMovable(head)) { - return page; - } - - skip_pages = compound_nr(head) - (page - head); - iter += skip_pages - 1; - continue; - } - - /* - * We can't use page_count without pin a page - * because another CPU can free compound page. - * This check already skips compound tails of THP - * because their page->_refcount is zero at all time. - */ - if (!page_ref_count(page)) { - if (PageBuddy(page)) - iter += (1 << buddy_order(page)) - 1; - continue; - } - - /* - * The HWPoisoned page may be not in buddy system, and - * page_count() is not 0. - */ - if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) - continue; - - /* - * We treat all PageOffline() pages as movable when offlining - * to give drivers a chance to decrement their reference count - * in MEM_GOING_OFFLINE in order to indicate that these pages - * can be offlined as there are no direct references anymore. - * For actually unmovable PageOffline() where the driver does - * not support this, we will fail later when trying to actually - * move these pages that still have a reference count > 0. - * (false negatives in this function only) - */ - if ((flags & MEMORY_OFFLINE) && PageOffline(page)) - continue; - - if (__PageMovable(page) || PageLRU(page)) - continue; - - /* - * If there are RECLAIMABLE pages, we need to check - * it. But now, memory offline itself doesn't call - * shrink_node_slabs() and it still to be fixed. - */ - return page; - } - return NULL; -} - #ifdef CONFIG_CONTIG_ALLOC -static unsigned long pfn_max_align_down(unsigned long pfn) -{ - return ALIGN_DOWN(pfn, MAX_ORDER_NR_PAGES); -} - -static unsigned long pfn_max_align_up(unsigned long pfn) -{ - return ALIGN(pfn, MAX_ORDER_NR_PAGES); -} - #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* Usage: See admin-guide/dynamic-debug-howto.rst */ @@ -9101,7 +8982,7 @@ static inline void alloc_contig_dump_pages(struct list_head *page_list) #endif /* [start, end) must belong to a single zone. */ -static int __alloc_contig_migrate_range(struct compact_control *cc, +int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end) { /* This function is based on compact_zone() from compaction.c. */ @@ -9151,7 +9032,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, lru_cache_enable(); if (ret < 0) { - if (ret == -EBUSY) + if (!(cc->gfp_mask & __GFP_NOWARN) && ret == -EBUSY) alloc_contig_dump_pages(&cc->migratepages); putback_movable_pages(&cc->migratepages); return ret; @@ -9169,8 +9050,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, * be either of the two. * @gfp_mask: GFP mask to use during compaction * - * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES - * aligned. The PFN range must belong to a single zone. + * The PFN range does not have to be pageblock aligned. The PFN range must + * belong to a single zone. * * The first thing this routine does is attempt to MIGRATE_ISOLATE all * pageblocks in the range. Once isolated, the pageblocks should not @@ -9184,7 +9065,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask) { unsigned long outer_start, outer_end; - unsigned int order; + int order; int ret = 0; struct compact_control cc = { @@ -9203,14 +9084,11 @@ int alloc_contig_range(unsigned long start, unsigned long end, * What we do here is we mark all pageblocks in range as * MIGRATE_ISOLATE. Because pageblock and max order pages may * have different sizes, and due to the way page allocator - * work, we align the range to biggest of the two pages so - * that page allocator won't try to merge buddies from - * different pageblocks and change MIGRATE_ISOLATE to some - * other migration type. + * work, start_isolate_page_range() has special handlings for this. * * Once the pageblocks are marked as MIGRATE_ISOLATE, we * migrate the pages from an unaligned range (ie. pages that - * we are interested in). This will put all the pages in + * we are interested in). This will put all the pages in * range back to page allocator as MIGRATE_ISOLATE. * * When this is done, we take the pages in range from page @@ -9223,10 +9101,9 @@ int alloc_contig_range(unsigned long start, unsigned long end, * put back to page allocator so that buddy can use them. */ - ret = start_isolate_page_range(pfn_max_align_down(start), - pfn_max_align_up(end), migratetype, 0); + ret = start_isolate_page_range(start, end, migratetype, 0, gfp_mask); if (ret) - return ret; + goto done; drain_all_pages(cc.zone); @@ -9246,7 +9123,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, ret = 0; /* - * Pages from [start, end) are within a MAX_ORDER_NR_PAGES + * Pages from [start, end) are within a pageblock_nr_pages * aligned blocks that are marked as MIGRATE_ISOLATE. What's * more, all pages in [start, end) are free in page allocator. * What we are going to do is to allocate all pages from @@ -9305,8 +9182,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, free_contig_range(end, outer_end - end); done: - undo_isolate_page_range(pfn_max_align_down(start), - pfn_max_align_up(end), migratetype); + undo_isolate_page_range(start, end, migratetype); return ret; } EXPORT_SYMBOL(alloc_contig_range); @@ -9625,7 +9501,6 @@ bool put_page_back_buddy(struct page *page) ClearPageHWPoisonTakenOff(page); __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE); if (TestClearPageHWPoison(page)) { - num_poisoned_pages_dec(); ret = true; } } diff --git a/mm/page_ext.c b/mm/page_ext.c index 2e66d934d63f..3dc715d7ac29 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -320,7 +320,7 @@ static int __meminit online_page_ext(unsigned long start_pfn, * online__pages(), and start_pfn should exist. */ nid = pfn_to_nid(start_pfn); - VM_BUG_ON(!node_state(nid, N_ONLINE)); + VM_BUG_ON(!node_online(nid)); } for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) diff --git a/mm/page_idle.c b/mm/page_idle.c index fc0435abf909..bc08332a609c 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -86,11 +86,12 @@ static bool page_idle_clear_pte_refs_one(struct folio *folio, static void page_idle_clear_pte_refs(struct page *page) { struct folio *folio = page_folio(page); + /* - * Since rwc.arg is unused, rwc is effectively immutable, so we - * can make it static const to save some cycles and stack. + * Since rwc.try_lock is unused, rwc is effectively immutable, so we + * can make it static to save some cycles and stack. */ - static const struct rmap_walk_control rwc = { + static struct rmap_walk_control rwc = { .rmap_one = page_idle_clear_pte_refs_one, .anon_lock = folio_lock_anon_vma_read, }; diff --git a/mm/page_io.c b/mm/page_io.c index a9444e67ec20..68318134dc92 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -26,6 +26,7 @@ #include <linux/uio.h> #include <linux/sched/task.h> #include <linux/delayacct.h> +#include "swap.h" void end_swap_bio_write(struct bio *bio) { @@ -234,55 +235,119 @@ static void bio_associate_blkg_from_page(struct bio *bio, struct page *page) #define bio_associate_blkg_from_page(bio, page) do { } while (0) #endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */ -int __swap_writepage(struct page *page, struct writeback_control *wbc, - bio_end_io_t end_write_func) +struct swap_iocb { + struct kiocb iocb; + struct bio_vec bvec[SWAP_CLUSTER_MAX]; + int pages; + int len; +}; +static mempool_t *sio_pool; + +int sio_pool_init(void) { - struct bio *bio; - int ret; - struct swap_info_struct *sis = page_swap_info(page); + if (!sio_pool) { + mempool_t *pool = mempool_create_kmalloc_pool( + SWAP_CLUSTER_MAX, sizeof(struct swap_iocb)); + if (cmpxchg(&sio_pool, NULL, pool)) + mempool_destroy(pool); + } + if (!sio_pool) + return -ENOMEM; + return 0; +} - VM_BUG_ON_PAGE(!PageSwapCache(page), page); - if (data_race(sis->flags & SWP_FS_OPS)) { - struct kiocb kiocb; - struct file *swap_file = sis->swap_file; - struct address_space *mapping = swap_file->f_mapping; - struct bio_vec bv = { - .bv_page = page, - .bv_len = PAGE_SIZE, - .bv_offset = 0 - }; - struct iov_iter from; - - iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE); - init_sync_kiocb(&kiocb, swap_file); - kiocb.ki_pos = page_file_offset(page); +static void sio_write_complete(struct kiocb *iocb, long ret) +{ + struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb); + struct page *page = sio->bvec[0].bv_page; + int p; - set_page_writeback(page); - unlock_page(page); - ret = mapping->a_ops->direct_IO(&kiocb, &from); - if (ret == PAGE_SIZE) { - count_vm_event(PSWPOUT); - ret = 0; - } else { - /* - * In the case of swap-over-nfs, this can be a - * temporary failure if the system has limited - * memory for allocating transmit buffers. - * Mark the page dirty and avoid - * folio_rotate_reclaimable but rate-limit the - * messages but do not flag PageError like - * the normal direct-to-bio case as it could - * be temporary. - */ + if (ret != sio->len) { + /* + * In the case of swap-over-nfs, this can be a + * temporary failure if the system has limited + * memory for allocating transmit buffers. + * Mark the page dirty and avoid + * folio_rotate_reclaimable but rate-limit the + * messages but do not flag PageError like + * the normal direct-to-bio case as it could + * be temporary. + */ + pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n", + ret, page_file_offset(page)); + for (p = 0; p < sio->pages; p++) { + page = sio->bvec[p].bv_page; set_page_dirty(page); ClearPageReclaim(page); - pr_err_ratelimited("Write error on dio swapfile (%llu)\n", - page_file_offset(page)); } - end_page_writeback(page); - return ret; + } else { + for (p = 0; p < sio->pages; p++) + count_swpout_vm_event(sio->bvec[p].bv_page); } + for (p = 0; p < sio->pages; p++) + end_page_writeback(sio->bvec[p].bv_page); + + mempool_free(sio, sio_pool); +} + +static int swap_writepage_fs(struct page *page, struct writeback_control *wbc) +{ + struct swap_iocb *sio = NULL; + struct swap_info_struct *sis = page_swap_info(page); + struct file *swap_file = sis->swap_file; + loff_t pos = page_file_offset(page); + + set_page_writeback(page); + unlock_page(page); + if (wbc->swap_plug) + sio = *wbc->swap_plug; + if (sio) { + if (sio->iocb.ki_filp != swap_file || + sio->iocb.ki_pos + sio->len != pos) { + swap_write_unplug(sio); + sio = NULL; + } + } + if (!sio) { + sio = mempool_alloc(sio_pool, GFP_NOIO); + init_sync_kiocb(&sio->iocb, swap_file); + sio->iocb.ki_complete = sio_write_complete; + sio->iocb.ki_pos = pos; + sio->pages = 0; + sio->len = 0; + } + sio->bvec[sio->pages].bv_page = page; + sio->bvec[sio->pages].bv_len = thp_size(page); + sio->bvec[sio->pages].bv_offset = 0; + sio->len += thp_size(page); + sio->pages += 1; + if (sio->pages == ARRAY_SIZE(sio->bvec) || !wbc->swap_plug) { + swap_write_unplug(sio); + sio = NULL; + } + if (wbc->swap_plug) + *wbc->swap_plug = sio; + + return 0; +} + +int __swap_writepage(struct page *page, struct writeback_control *wbc, + bio_end_io_t end_write_func) +{ + struct bio *bio; + int ret; + struct swap_info_struct *sis = page_swap_info(page); + + VM_BUG_ON_PAGE(!PageSwapCache(page), page); + /* + * ->flags can be updated non-atomicially (scan_swap_map_slots), + * but that will never affect SWP_FS_OPS, so the data_race + * is safe. + */ + if (data_race(sis->flags & SWP_FS_OPS)) + return swap_writepage_fs(page, wbc); + ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc); if (!ret) { count_swpout_vm_event(page); @@ -305,7 +370,83 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, return 0; } -int swap_readpage(struct page *page, bool synchronous) +void swap_write_unplug(struct swap_iocb *sio) +{ + struct iov_iter from; + struct address_space *mapping = sio->iocb.ki_filp->f_mapping; + int ret; + + iov_iter_bvec(&from, WRITE, sio->bvec, sio->pages, sio->len); + ret = mapping->a_ops->swap_rw(&sio->iocb, &from); + if (ret != -EIOCBQUEUED) + sio_write_complete(&sio->iocb, ret); +} + +static void sio_read_complete(struct kiocb *iocb, long ret) +{ + struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb); + int p; + + if (ret == sio->len) { + for (p = 0; p < sio->pages; p++) { + struct page *page = sio->bvec[p].bv_page; + + SetPageUptodate(page); + unlock_page(page); + } + count_vm_events(PSWPIN, sio->pages); + } else { + for (p = 0; p < sio->pages; p++) { + struct page *page = sio->bvec[p].bv_page; + + SetPageError(page); + ClearPageUptodate(page); + unlock_page(page); + } + pr_alert_ratelimited("Read-error on swap-device\n"); + } + mempool_free(sio, sio_pool); +} + +static void swap_readpage_fs(struct page *page, + struct swap_iocb **plug) +{ + struct swap_info_struct *sis = page_swap_info(page); + struct swap_iocb *sio = NULL; + loff_t pos = page_file_offset(page); + + if (plug) + sio = *plug; + if (sio) { + if (sio->iocb.ki_filp != sis->swap_file || + sio->iocb.ki_pos + sio->len != pos) { + swap_read_unplug(sio); + sio = NULL; + } + } + if (!sio) { + sio = mempool_alloc(sio_pool, GFP_KERNEL); + init_sync_kiocb(&sio->iocb, sis->swap_file); + sio->iocb.ki_pos = pos; + sio->iocb.ki_complete = sio_read_complete; + sio->pages = 0; + sio->len = 0; + } + sio->bvec[sio->pages].bv_page = page; + sio->bvec[sio->pages].bv_len = thp_size(page); + sio->bvec[sio->pages].bv_offset = 0; + sio->len += thp_size(page); + sio->pages += 1; + if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) { + swap_read_unplug(sio); + sio = NULL; + } + if (plug) + *plug = sio; +} + +int swap_readpage(struct page *page, bool synchronous, + struct swap_iocb **plug) { struct bio *bio; int ret = 0; @@ -333,12 +474,7 @@ int swap_readpage(struct page *page, bool synchronous) } if (data_race(sis->flags & SWP_FS_OPS)) { - struct file *swap_file = sis->swap_file; - struct address_space *mapping = swap_file->f_mapping; - - ret = mapping->a_ops->read_folio(swap_file, page_folio(page)); - if (!ret) - count_vm_event(PSWPIN); + swap_readpage_fs(page, plug); goto out; } @@ -383,19 +519,14 @@ out: return ret; } -bool swap_dirty_folio(struct address_space *mapping, struct folio *folio) +void __swap_read_unplug(struct swap_iocb *sio) { - struct swap_info_struct *sis = swp_swap_info(folio_swap_entry(folio)); - - if (data_race(sis->flags & SWP_FS_OPS)) { - const struct address_space_operations *aops; - - mapping = sis->swap_file->f_mapping; - aops = mapping->a_ops; + struct iov_iter from; + struct address_space *mapping = sio->iocb.ki_filp->f_mapping; + int ret; - VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio); - return aops->dirty_folio(mapping, folio); - } else { - return noop_dirty_folio(mapping, folio); - } + iov_iter_bvec(&from, READ, sio->bvec, sio->pages, sio->len); + ret = mapping->a_ops->swap_rw(&sio->iocb, &from); + if (ret != -EIOCBQUEUED) + sio_read_complete(&sio->iocb, ret); } diff --git a/mm/page_isolation.c b/mm/page_isolation.c index f67c4c70f17f..c643c8420809 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -15,11 +15,142 @@ #define CREATE_TRACE_POINTS #include <trace/events/page_isolation.h> -static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags) +/* + * This function checks whether the range [start_pfn, end_pfn) includes + * unmovable pages or not. The range must fall into a single pageblock and + * consequently belong to a single zone. + * + * PageLRU check without isolation or lru_lock could race so that + * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable + * check without lock_page also may miss some movable non-lru pages at + * race condition. So you can't expect this function should be exact. + * + * Returns a page without holding a reference. If the caller wants to + * dereference that page (e.g., dumping), it has to make sure that it + * cannot get removed (e.g., via memory unplug) concurrently. + * + */ +static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long end_pfn, + int migratetype, int flags) +{ + struct page *page = pfn_to_page(start_pfn); + struct zone *zone = page_zone(page); + unsigned long pfn; + + VM_BUG_ON(ALIGN_DOWN(start_pfn, pageblock_nr_pages) != + ALIGN_DOWN(end_pfn - 1, pageblock_nr_pages)); + + if (is_migrate_cma_page(page)) { + /* + * CMA allocations (alloc_contig_range) really need to mark + * isolate CMA pageblocks even when they are not movable in fact + * so consider them movable here. + */ + if (is_migrate_cma(migratetype)) + return NULL; + + return page; + } + + for (pfn = start_pfn; pfn < end_pfn; pfn++) { + page = pfn_to_page(pfn); + + /* + * Both, bootmem allocations and memory holes are marked + * PG_reserved and are unmovable. We can even have unmovable + * allocations inside ZONE_MOVABLE, for example when + * specifying "movablecore". + */ + if (PageReserved(page)) + return page; + + /* + * If the zone is movable and we have ruled out all reserved + * pages then it should be reasonably safe to assume the rest + * is movable. + */ + if (zone_idx(zone) == ZONE_MOVABLE) + continue; + + /* + * Hugepages are not in LRU lists, but they're movable. + * THPs are on the LRU, but need to be counted as #small pages. + * We need not scan over tail pages because we don't + * handle each tail page individually in migration. + */ + if (PageHuge(page) || PageTransCompound(page)) { + struct page *head = compound_head(page); + unsigned int skip_pages; + + if (PageHuge(page)) { + if (!hugepage_migration_supported(page_hstate(head))) + return page; + } else if (!PageLRU(head) && !__PageMovable(head)) { + return page; + } + + skip_pages = compound_nr(head) - (page - head); + pfn += skip_pages - 1; + continue; + } + + /* + * We can't use page_count without pin a page + * because another CPU can free compound page. + * This check already skips compound tails of THP + * because their page->_refcount is zero at all time. + */ + if (!page_ref_count(page)) { + if (PageBuddy(page)) + pfn += (1 << buddy_order(page)) - 1; + continue; + } + + /* + * The HWPoisoned page may be not in buddy system, and + * page_count() is not 0. + */ + if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) + continue; + + /* + * We treat all PageOffline() pages as movable when offlining + * to give drivers a chance to decrement their reference count + * in MEM_GOING_OFFLINE in order to indicate that these pages + * can be offlined as there are no direct references anymore. + * For actually unmovable PageOffline() where the driver does + * not support this, we will fail later when trying to actually + * move these pages that still have a reference count > 0. + * (false negatives in this function only) + */ + if ((flags & MEMORY_OFFLINE) && PageOffline(page)) + continue; + + if (__PageMovable(page) || PageLRU(page)) + continue; + + /* + * If there are RECLAIMABLE pages, we need to check + * it. But now, memory offline itself doesn't call + * shrink_node_slabs() and it still to be fixed. + */ + return page; + } + return NULL; +} + +/* + * This function set pageblock migratetype to isolate if no unmovable page is + * present in [start_pfn, end_pfn). The pageblock must intersect with + * [start_pfn, end_pfn). + */ +static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags, + unsigned long start_pfn, unsigned long end_pfn) { struct zone *zone = page_zone(page); struct page *unmovable; unsigned long flags; + unsigned long check_unmovable_start, check_unmovable_end; spin_lock_irqsave(&zone->lock, flags); @@ -36,8 +167,16 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ /* * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. * We just check MOVABLE pages. + * + * Pass the intersection of [start_pfn, end_pfn) and the page's pageblock + * to avoid redundant checks. */ - unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags); + check_unmovable_start = max(page_to_pfn(page), start_pfn); + check_unmovable_end = min(ALIGN(page_to_pfn(page) + 1, pageblock_nr_pages), + end_pfn); + + 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); @@ -64,13 +203,12 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ return -EBUSY; } -static void unset_migratetype_isolate(struct page *page, unsigned migratetype) +static void unset_migratetype_isolate(struct page *page, int migratetype) { struct zone *zone; unsigned long flags, nr_pages; bool isolated_page = false; unsigned int order; - unsigned long pfn, buddy_pfn; struct page *buddy; zone = page_zone(page); @@ -89,11 +227,9 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) if (PageBuddy(page)) { order = buddy_order(page); if (order >= pageblock_order && order < MAX_ORDER - 1) { - pfn = page_to_pfn(page); - buddy_pfn = __find_buddy_pfn(pfn, order); - buddy = page + (buddy_pfn - pfn); - - if (!is_migrate_isolate_page(buddy)) { + buddy = find_buddy_page_pfn(page, page_to_pfn(page), + order, NULL); + if (buddy && !is_migrate_isolate_page(buddy)) { isolated_page = !!__isolate_free_page(page, order); /* * Isolating a free page in an isolated pageblock @@ -144,11 +280,198 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) } /** + * isolate_single_pageblock() -- tries to isolate a pageblock that might be + * within a free or in-use page. + * @boundary_pfn: pageblock-aligned pfn that a page might cross + * @flags: isolation flags + * @gfp_flags: GFP flags used for migrating pages + * @isolate_before: isolate the pageblock before the boundary_pfn + * + * Free and in-use pages can be as big as MAX_ORDER-1 and contain more than one + * pageblock. When not all pageblocks within a page are isolated at the same + * time, free page accounting can go wrong. For example, in the case of + * MAX_ORDER-1 = pageblock_order + 1, a MAX_ORDER-1 page has two pagelbocks. + * [ MAX_ORDER-1 ] + * [ pageblock0 | pageblock1 ] + * When either pageblock is isolated, if it is a free page, the page is not + * split into separate migratetype lists, which is supposed to; if it is an + * in-use page and freed later, __free_one_page() does not split the free page + * either. The function handles this by splitting the free page or migrating + * the in-use page then splitting the free page. + */ +static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, + gfp_t gfp_flags, bool isolate_before) +{ + unsigned char saved_mt; + unsigned long start_pfn; + unsigned long isolate_pageblock; + unsigned long pfn; + struct zone *zone; + int ret; + + VM_BUG_ON(!IS_ALIGNED(boundary_pfn, pageblock_nr_pages)); + + if (isolate_before) + isolate_pageblock = boundary_pfn - pageblock_nr_pages; + else + isolate_pageblock = boundary_pfn; + + /* + * scan at the beginning of MAX_ORDER_NR_PAGES aligned range to avoid + * only isolating a subset of pageblocks from a bigger than pageblock + * free or in-use page. Also make sure all to-be-isolated pageblocks + * are within the same zone. + */ + zone = page_zone(pfn_to_page(isolate_pageblock)); + start_pfn = max(ALIGN_DOWN(isolate_pageblock, MAX_ORDER_NR_PAGES), + zone->zone_start_pfn); + + saved_mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock)); + ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt, flags, + isolate_pageblock, isolate_pageblock + pageblock_nr_pages); + + if (ret) + return ret; + + /* + * Bail out early when the to-be-isolated pageblock does not form + * a free or in-use page across boundary_pfn: + * + * 1. isolate before boundary_pfn: the page after is not online + * 2. isolate after boundary_pfn: the page before is not online + * + * This also ensures correctness. Without it, when isolate after + * boundary_pfn and [start_pfn, boundary_pfn) are not online, + * __first_valid_page() will return unexpected NULL in the for loop + * below. + */ + if (isolate_before) { + if (!pfn_to_online_page(boundary_pfn)) + return 0; + } else { + if (!pfn_to_online_page(boundary_pfn - 1)) + return 0; + } + + for (pfn = start_pfn; pfn < boundary_pfn;) { + struct page *page = __first_valid_page(pfn, boundary_pfn - pfn); + + 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) + split_free_page(page, order, boundary_pfn - 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 (PageCompound(page)) { + unsigned long nr_pages = compound_nr(page); + struct page *head = compound_head(page); + unsigned long head_pfn = page_to_pfn(head); + + if (head_pfn + nr_pages <= boundary_pfn) { + 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; + int page_mt = get_pageblock_migratetype(page); + bool isolate_page = !is_migrate_isolate_page(page); + struct compact_control cc = { + .nr_migratepages = 0, + .order = -1, + .zone = page_zone(pfn_to_page(head_pfn)), + .mode = MIGRATE_SYNC, + .ignore_skip_hint = true, + .no_set_skip_hint = true, + .gfp_mask = gfp_flags, + .alloc_contig = true, + }; + 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); + + /* + * 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_ORDER-1, 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_ORDER) + goto failed; + outer_pfn &= ~0UL << order; + } + pfn = outer_pfn; + continue; + } else +#endif + goto failed; + } + + pfn++; + } + return 0; +failed: + /* restore the original migratetype */ + unset_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt); + return -EBUSY; +} + +/** * start_isolate_page_range() - make page-allocation-type of range of pages to * be MIGRATE_ISOLATE. * @start_pfn: The lower PFN of the range to be isolated. * @end_pfn: The upper PFN of the range to be isolated. - * start_pfn/end_pfn must be aligned to pageblock_order. * @migratetype: Migrate type to set in error recovery. * @flags: The following flags are allowed (they can be combined in * a bit mask) @@ -157,6 +480,8 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * and PageOffline() pages. * REPORT_FAILURE - report details about the failure to * isolate the range + * @gfp_flags: GFP flags used for migrating pages that sit across the + * range boundaries. * * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in * the range will never be allocated. Any free pages and pages freed in the @@ -165,6 +490,10 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * pages in the range finally, the caller have to free all pages in the range. * test_page_isolated() can be used for test it. * + * The function first tries to isolate the pageblocks at the beginning and end + * of the range, since there might be pages across the range boundaries. + * Afterwards, it isolates the rest of the range. + * * There is no high level synchronization mechanism that prevents two threads * from trying to isolate overlapping ranges. If this happens, one thread * will notice pageblocks in the overlapping range already set to isolate. @@ -185,20 +514,38 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * Return: 0 on success and -EBUSY if any part of range cannot be isolated. */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype, int flags) + int migratetype, int flags, gfp_t gfp_flags) { unsigned long pfn; struct page *page; + /* isolation is done at page block granularity */ + unsigned long isolate_start = ALIGN_DOWN(start_pfn, pageblock_nr_pages); + unsigned long isolate_end = ALIGN(end_pfn, pageblock_nr_pages); + int ret; + + /* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */ + ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false); + if (ret) + return ret; - BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); - BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages)); + /* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */ + ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true); + if (ret) { + unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype); + return ret; + } - for (pfn = start_pfn; - pfn < end_pfn; + /* skip isolated pageblocks at the beginning and end */ + for (pfn = isolate_start + pageblock_nr_pages; + pfn < isolate_end - pageblock_nr_pages; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); - if (page && set_migratetype_isolate(page, migratetype, flags)) { - undo_isolate_page_range(start_pfn, pfn, migratetype); + if (page && set_migratetype_isolate(page, migratetype, flags, + start_pfn, end_pfn)) { + undo_isolate_page_range(isolate_start, pfn, migratetype); + unset_migratetype_isolate( + pfn_to_page(isolate_end - pageblock_nr_pages), + migratetype); return -EBUSY; } } @@ -209,16 +556,16 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, * Make isolated pages available again. */ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - unsigned migratetype) + int migratetype) { unsigned long pfn; struct page *page; + unsigned long isolate_start = ALIGN_DOWN(start_pfn, pageblock_nr_pages); + unsigned long isolate_end = ALIGN(end_pfn, pageblock_nr_pages); - BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); - BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages)); - for (pfn = start_pfn; - pfn < end_pfn; + for (pfn = isolate_start; + pfn < isolate_end; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); if (!page || !is_migrate_isolate_page(page)) diff --git a/mm/page_owner.c b/mm/page_owner.c index 2743062e92c2..e4c6f3f1695b 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -34,7 +34,7 @@ struct page_owner { pid_t tgid; }; -static bool page_owner_enabled = false; +static bool page_owner_enabled __initdata; DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; @@ -171,7 +171,7 @@ static inline void __set_page_owner_handle(struct page_ext *page_ext, page_owner->pid = current->pid; page_owner->tgid = current->tgid; page_owner->ts_nsec = local_clock(); - strlcpy(page_owner->comm, current->comm, + strscpy(page_owner->comm, current->comm, sizeof(page_owner->comm)); __set_bit(PAGE_EXT_OWNER, &page_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 2458281bff89..3692bea2ea2c 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -52,23 +52,6 @@ static struct page_table_check *get_page_table_check(struct page_ext *page_ext) return (void *)(page_ext) + page_table_check_ops.offset; } -static inline bool pte_user_accessible_page(pte_t pte) -{ - return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); -} - -static inline bool pmd_user_accessible_page(pmd_t pmd) -{ - return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && - (pmd_val(pmd) & _PAGE_USER); -} - -static inline bool pud_user_accessible_page(pud_t pud) -{ - return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && - (pud_val(pud) & _PAGE_USER); -} - /* * An enty is removed from the page table, decrement the counters for that page * verify that it is of correct type and counters do not become negative. @@ -177,7 +160,7 @@ void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, if (pmd_user_accessible_page(pmd)) { page_table_check_clear(mm, addr, pmd_pfn(pmd), - PMD_PAGE_SIZE >> PAGE_SHIFT); + PMD_SIZE >> PAGE_SHIFT); } } EXPORT_SYMBOL(__page_table_check_pmd_clear); @@ -190,7 +173,7 @@ void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr, if (pud_user_accessible_page(pud)) { page_table_check_clear(mm, addr, pud_pfn(pud), - PUD_PAGE_SIZE >> PAGE_SHIFT); + PUD_SIZE >> PAGE_SHIFT); } } EXPORT_SYMBOL(__page_table_check_pud_clear); @@ -219,7 +202,7 @@ void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, __page_table_check_pmd_clear(mm, addr, *pmdp); if (pmd_user_accessible_page(pmd)) { page_table_check_set(mm, addr, pmd_pfn(pmd), - PMD_PAGE_SIZE >> PAGE_SHIFT, + PMD_SIZE >> PAGE_SHIFT, pmd_write(pmd)); } } @@ -234,7 +217,7 @@ void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, __page_table_check_pud_clear(mm, addr, *pudp); if (pud_user_accessible_page(pud)) { page_table_check_set(mm, addr, pud_pfn(pud), - PUD_PAGE_SIZE >> PAGE_SHIFT, + PUD_SIZE >> PAGE_SHIFT, pud_write(pud)); } } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 14a5cda73dee..c10f839fc410 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -210,16 +210,10 @@ restart: */ pmde = READ_ONCE(*pvmw->pmd); - if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { + if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde) || + (pmd_present(pmde) && pmd_devmap(pmde))) { pvmw->ptl = pmd_lock(mm, pvmw->pmd); pmde = *pvmw->pmd; - if (likely(pmd_trans_huge(pmde))) { - if (pvmw->flags & PVMW_MIGRATION) - return not_found(pvmw); - if (!check_pmd(pmd_pfn(pmde), pvmw)) - return not_found(pvmw); - return true; - } if (!pmd_present(pmde)) { swp_entry_t entry; @@ -232,6 +226,13 @@ restart: return not_found(pvmw); return true; } + if (likely(pmd_trans_huge(pmde) || pmd_devmap(pmde))) { + if (pvmw->flags & PVMW_MIGRATION) + return not_found(pvmw); + if (!check_pmd(pmd_pfn(pmde), pvmw)) + return not_found(pvmw); + return true; + } /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h index 411d1593ef23..70b1ea23f4d2 100644 --- a/mm/percpu-internal.h +++ b/mm/percpu-internal.h @@ -113,7 +113,6 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } -#ifdef CONFIG_MEMCG_KMEM /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes @@ -123,13 +122,14 @@ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) */ static inline size_t pcpu_obj_full_size(size_t size) { - size_t extra_size; + size_t extra_size = 0; - extra_size = size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); +#ifdef CONFIG_MEMCG_KMEM + extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); +#endif return size * num_possible_cpus() + extra_size; } -#endif /* CONFIG_MEMCG_KMEM */ #ifdef CONFIG_PERCPU_STATS diff --git a/mm/percpu.c b/mm/percpu.c index ea28db283044..3633eeefaa0d 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1884,8 +1884,9 @@ area_found: ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); kmemleak_alloc_percpu(ptr, size, gfp); - trace_percpu_alloc_percpu(reserved, is_atomic, size, align, - chunk->base_addr, off, ptr); + trace_percpu_alloc_percpu(_RET_IP_, reserved, is_atomic, size, align, + chunk->base_addr, off, ptr, + pcpu_obj_full_size(size), gfp); pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 6523fda274e5..90ab721a12a8 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -201,6 +201,14 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, } #endif +#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD +pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + return pmdp_invalidate(vma, address, pmdp); +} +#endif + #ifndef pmdp_collapse_flush pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) diff --git a/mm/rmap.c b/mm/rmap.c index fedb82371efe..5bcb334cd6f2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -73,6 +73,7 @@ #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> +#include <linux/mm_inline.h> #include <asm/tlbflush.h> @@ -298,7 +299,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) * Reuse existing anon_vma if its degree lower than two, * that means it has no vma and only one anon_vma child. * - * Do not chose parent anon_vma, otherwise first child + * Do not choose parent anon_vma, otherwise first child * will always reuse it. Root anon_vma is never reused: * it has self-parent reference and at least one child. */ @@ -526,9 +527,11 @@ out: * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a - * reference like with page_get_anon_vma() and then block on the mutex. + * reference like with page_get_anon_vma() and then block on the mutex + * on !rwc->try_lock case. */ -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio) +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, + struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; @@ -556,6 +559,12 @@ struct anon_vma *folio_lock_anon_vma_read(struct folio *folio) goto out; } + if (rwc && rwc->try_lock) { + anon_vma = NULL; + rwc->contended = true; + goto out; + } + /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; @@ -882,7 +891,8 @@ static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) * * Quick test_and_clear_referenced for all mappings of a folio, * - * Return: The number of mappings which referenced the folio. + * Return: The number of mappings which referenced the folio. Return -1 if + * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) @@ -896,6 +906,7 @@ int folio_referenced(struct folio *folio, int is_locked, .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, + .try_lock = true, }; *vm_flags = 0; @@ -926,15 +937,15 @@ int folio_referenced(struct folio *folio, int is_locked, if (we_locked) folio_unlock(folio); - return pra.referenced; + return rwc.contended ? -1 : pra.referenced; } -static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, - unsigned long address, void *arg) +static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { - DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); + int cleaned = 0; + struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; - int *cleaned = arg; + unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that @@ -942,16 +953,16 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, - vma_address_end(&pvmw)); + vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); - while (page_vma_mapped_walk(&pvmw)) { + while (page_vma_mapped_walk(pvmw)) { int ret = 0; - address = pvmw.address; - if (pvmw.pte) { + address = pvmw->address; + if (pvmw->pte) { pte_t entry; - pte_t *pte = pvmw.pte; + pte_t *pte = pvmw->pte; if (!pte_dirty(*pte) && !pte_write(*pte)) continue; @@ -964,13 +975,14 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - pmd_t *pmd = pvmw.pmd; + pmd_t *pmd = pvmw->pmd; pmd_t entry; if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; - flush_cache_page(vma, address, folio_pfn(folio)); + flush_cache_range(vma, address, + address + HPAGE_PMD_SIZE); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); @@ -990,11 +1002,22 @@ static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, * See Documentation/vm/mmu_notifier.rst */ if (ret) - (*cleaned)++; + cleaned++; } mmu_notifier_invalidate_range_end(&range); + return cleaned; +} + +static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, + unsigned long address, void *arg) +{ + DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); + int *cleaned = arg; + + *cleaned += page_vma_mkclean_one(&pvmw); + return true; } @@ -1032,6 +1055,38 @@ int folio_mkclean(struct folio *folio) EXPORT_SYMBOL_GPL(folio_mkclean); /** + * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of + * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) + * within the @vma of shared mappings. And since clean PTEs + * should also be readonly, write protects them too. + * @pfn: start pfn. + * @nr_pages: number of physically contiguous pages srarting with @pfn. + * @pgoff: page offset that the @pfn mapped with. + * @vma: vma that @pfn mapped within. + * + * Returns the number of cleaned PTEs (including PMDs). + */ +int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, + struct vm_area_struct *vma) +{ + struct page_vma_mapped_walk pvmw = { + .pfn = pfn, + .nr_pages = nr_pages, + .pgoff = pgoff, + .vma = vma, + .flags = PVMW_SYNC, + }; + + if (invalid_mkclean_vma(vma, NULL)) + return 0; + + pvmw.address = vma_pgoff_address(pgoff, nr_pages, vma); + VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); + + return page_vma_mkclean_one(&pvmw); +} + +/** * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma * @vma: the vma the page belongs to @@ -1044,6 +1099,7 @@ EXPORT_SYMBOL_GPL(folio_mkclean); void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; + struct page *subpage = page; page = compound_head(page); @@ -1057,6 +1113,7 @@ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); + SetPageAnonExclusive(subpage); } /** @@ -1074,7 +1131,7 @@ static void __page_set_anon_rmap(struct page *page, BUG_ON(!anon_vma); if (PageAnon(page)) - return; + goto out; /* * If the page isn't exclusively mapped into this vma, @@ -1093,6 +1150,9 @@ static void __page_set_anon_rmap(struct page *page, anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); page->index = linear_page_index(vma, address); +out: + if (exclusive) + SetPageAnonExclusive(page); } /** @@ -1127,7 +1187,7 @@ static void __page_check_anon_rmap(struct page *page, * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped - * @compound: charge the page as compound or small page + * @flags: the rmap flags * * The caller needs to hold the pte lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, @@ -1135,18 +1195,7 @@ static void __page_check_anon_rmap(struct page *page, * (but PageKsm is never downgraded to PageAnon). */ void page_add_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address, bool compound) -{ - do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0); -} - -/* - * Special version of the above for do_swap_page, which often runs - * into pages that are exclusively owned by the current process. - * Everybody else should continue to use page_add_anon_rmap above. - */ -void do_page_add_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address, int flags) + struct vm_area_struct *vma, unsigned long address, rmap_t flags) { bool compound = flags & RMAP_COMPOUND; bool first; @@ -1165,6 +1214,8 @@ void do_page_add_anon_rmap(struct page *page, } else { first = atomic_inc_and_test(&page->_mapcount); } + VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); + VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); if (first) { int nr = compound ? thp_nr_pages(page) : 1; @@ -1185,7 +1236,7 @@ void do_page_add_anon_rmap(struct page *page, /* address might be in next vma when migration races vma_adjust */ else if (first) __page_set_anon_rmap(page, vma, address, - flags & RMAP_EXCLUSIVE); + !!(flags & RMAP_EXCLUSIVE)); else __page_check_anon_rmap(page, vma, address); @@ -1193,19 +1244,22 @@ void do_page_add_anon_rmap(struct page *page, } /** - * page_add_new_anon_rmap - add pte mapping to a new anonymous page + * page_add_new_anon_rmap - add mapping to a new anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped - * @compound: charge the page as compound or small page + * + * If it's a compound page, it is accounted as a compound page. As the page + * is new, it's assume to get mapped exclusively by a single process. * * Same as page_add_anon_rmap but must only be called on *new* pages. * This means the inc-and-test can be bypassed. * Page does not have to be locked. */ void page_add_new_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address, bool compound) + struct vm_area_struct *vma, unsigned long address) { + const bool compound = PageCompound(page); int nr = compound ? thp_nr_pages(page) : 1; VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); @@ -1218,8 +1272,6 @@ void page_add_new_anon_rmap(struct page *page, __mod_lruvec_page_state(page, NR_ANON_THPS, nr); } else { - /* Anon THP always mapped first with PMD */ - VM_BUG_ON_PAGE(PageTransCompound(page), page); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } @@ -1425,7 +1477,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; - bool ret = true; + bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; @@ -1481,59 +1533,81 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, subpage = folio_page(folio, pte_pfn(*pvmw.pte) - folio_pfn(folio)); address = pvmw.address; + anon_exclusive = folio_test_anon(folio) && + PageAnonExclusive(subpage); - if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { + if (folio_test_hugetlb(folio)) { /* - * To call huge_pmd_unshare, i_mmap_rwsem must be - * held in write mode. Caller needs to explicitly - * do this outside rmap routines. + * The try_to_unmap() is only passed a hugetlb page + * in the case where the hugetlb page is poisoned. */ - VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); - if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { - /* - * huge_pmd_unshare unmapped an entire PMD - * page. There is no way of knowing exactly - * which PMDs may be cached for this mm, so - * we must flush them all. start/end were - * already adjusted above to cover this range. - */ - flush_cache_range(vma, range.start, range.end); - flush_tlb_range(vma, range.start, range.end); - mmu_notifier_invalidate_range(mm, range.start, - range.end); + VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); + /* + * huge_pmd_unshare may unmap an entire PMD page. + * There is no way of knowing exactly which PMDs may + * be cached for this mm, so we must flush them all. + * start/end were already adjusted above to cover this + * range. + */ + flush_cache_range(vma, range.start, range.end); + if (!folio_test_anon(folio)) { /* - * The ref count of the PMD page was dropped - * which is part of the way map counting - * is done for shared PMDs. Return 'true' - * here. When there is no other sharing, - * huge_pmd_unshare returns false and we will - * unmap the actual page and drop map count - * to zero. + * To call huge_pmd_unshare, i_mmap_rwsem must be + * held in write mode. Caller needs to explicitly + * do this outside rmap routines. */ - page_vma_mapped_walk_done(&pvmw); - break; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); + + if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { + flush_tlb_range(vma, range.start, range.end); + mmu_notifier_invalidate_range(mm, range.start, + range.end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } } - } - - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); - if (should_defer_flush(mm, flags)) { + pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); + } else { + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); /* - * We clear the PTE but do not flush so potentially - * a remote CPU could still be writing to the folio. - * If the entry was previously clean then the - * architecture must guarantee that a clear->dirty - * transition on a cached TLB entry is written through - * and traps if the PTE is unmapped. + * Nuke the page table entry. When having to clear + * PageAnonExclusive(), we always have to flush. */ - pteval = ptep_get_and_clear(mm, address, pvmw.pte); + if (should_defer_flush(mm, flags) && !anon_exclusive) { + /* + * We clear the PTE but do not flush so potentially + * a remote CPU could still be writing to the folio. + * If the entry was previously clean then the + * architecture must guarantee that a clear->dirty + * transition on a cached TLB entry is written through + * and traps if the PTE is unmapped. + */ + pteval = ptep_get_and_clear(mm, address, pvmw.pte); - set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); - } else { - pteval = ptep_clear_flush(vma, address, pvmw.pte); + set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); + } else { + pteval = ptep_clear_flush(vma, address, pvmw.pte); + } } + /* + * Now the pte is cleared. If this pte was uffd-wp armed, + * we may want to replace a none pte with a marker pte if + * it's file-backed, so we don't lose the tracking info. + */ + pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); + /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); @@ -1637,11 +1711,31 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, break; } if (arch_unmap_one(mm, vma, address, pteval) < 0) { + swap_free(entry); + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + if (anon_exclusive && + page_try_share_anon_rmap(subpage)) { + swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } + /* + * Note: We *don't* remember if the page was mapped + * exclusively in the swap pte if the architecture + * doesn't support __HAVE_ARCH_PTE_SWP_EXCLUSIVE. In + * that case, swapin code has to re-determine that + * manually and might detect the page as possibly + * shared, for example, if there are other references on + * the page or if the page is under writeback. We made + * sure that there are no GUP pins on the page that + * would rely on it, so for GUP pins this is fine. + */ if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) @@ -1651,6 +1745,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); + if (anon_exclusive) + swp_pte = pte_swp_mkexclusive(swp_pte); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) @@ -1741,7 +1837,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; - bool ret = true; + bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; @@ -1791,7 +1887,11 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); - set_pmd_migration_entry(&pvmw, subpage); + if (set_pmd_migration_entry(&pvmw, subpage)) { + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } continue; } #endif @@ -1802,44 +1902,53 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, subpage = folio_page(folio, pte_pfn(*pvmw.pte) - folio_pfn(folio)); address = pvmw.address; + anon_exclusive = folio_test_anon(folio) && + PageAnonExclusive(subpage); - if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { + if (folio_test_hugetlb(folio)) { /* - * To call huge_pmd_unshare, i_mmap_rwsem must be - * held in write mode. Caller needs to explicitly - * do this outside rmap routines. + * huge_pmd_unshare may unmap an entire PMD page. + * There is no way of knowing exactly which PMDs may + * be cached for this mm, so we must flush them all. + * start/end were already adjusted above to cover this + * range. */ - VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); - if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { - /* - * huge_pmd_unshare unmapped an entire PMD - * page. There is no way of knowing exactly - * which PMDs may be cached for this mm, so - * we must flush them all. start/end were - * already adjusted above to cover this range. - */ - flush_cache_range(vma, range.start, range.end); - flush_tlb_range(vma, range.start, range.end); - mmu_notifier_invalidate_range(mm, range.start, - range.end); + flush_cache_range(vma, range.start, range.end); + if (!folio_test_anon(folio)) { /* - * The ref count of the PMD page was dropped - * which is part of the way map counting - * is done for shared PMDs. Return 'true' - * here. When there is no other sharing, - * huge_pmd_unshare returns false and we will - * unmap the actual page and drop map count - * to zero. + * To call huge_pmd_unshare, i_mmap_rwsem must be + * held in write mode. Caller needs to explicitly + * do this outside rmap routines. */ - page_vma_mapped_walk_done(&pvmw); - break; + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); + + if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { + flush_tlb_range(vma, range.start, range.end); + mmu_notifier_invalidate_range(mm, range.start, + range.end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } } - } - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); - pteval = ptep_clear_flush(vma, address, pvmw.pte); + /* Nuke the hugetlb page table entry */ + pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); + } else { + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); + /* Nuke the page table entry. */ + pteval = ptep_clear_flush(vma, address, pvmw.pte); + } /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) @@ -1853,6 +1962,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, swp_entry_t entry; pte_t swp_pte; + if (anon_exclusive) + BUG_ON(page_try_share_anon_rmap(subpage)); + /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration @@ -1861,6 +1973,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, entry = pte_to_swp_entry(pteval); if (is_writable_device_private_entry(entry)) entry = make_writable_migration_entry(pfn); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry(pfn); else entry = make_readable_migration_entry(pfn); swp_pte = swp_entry_to_pte(entry); @@ -1920,7 +2034,22 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, pte_t swp_pte; if (arch_unmap_one(mm, vma, address, pteval) < 0) { - set_pte_at(mm, address, pvmw.pte, pteval); + if (folio_test_hugetlb(folio)) + set_huge_pte_at(mm, address, pvmw.pte, pteval); + else + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) && + !anon_exclusive, subpage); + if (anon_exclusive && + page_try_share_anon_rmap(subpage)) { + if (folio_test_hugetlb(folio)) + set_huge_pte_at(mm, address, pvmw.pte, pteval); + else + set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; @@ -1934,6 +2063,9 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, if (pte_write(pteval)) entry = make_writable_migration_entry( page_to_pfn(subpage)); + else if (anon_exclusive) + entry = make_readable_exclusive_migration_entry( + page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); @@ -1943,7 +2075,11 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); - set_pte_at(mm, address, pvmw.pte, swp_pte); + if (folio_test_hugetlb(folio)) + set_huge_swap_pte_at(mm, address, pvmw.pte, + swp_pte, vma_mmu_pagesize(vma)); + else + set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), compound_order(&folio->page)); /* @@ -2148,7 +2284,7 @@ static bool folio_make_device_exclusive(struct folio *folio, /** * make_device_exclusive_range() - Mark a range for exclusive use by a device - * @mm: mm_struct of assoicated target process + * @mm: mm_struct of associated target process * @start: start of the region to mark for exclusive device access * @end: end address of region * @pages: returns the pages which were successfully marked for exclusive access @@ -2210,12 +2346,12 @@ void __put_anon_vma(struct anon_vma *anon_vma) } static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, - const struct rmap_walk_control *rwc) + struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) - return rwc->anon_lock(folio); + return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() @@ -2227,7 +2363,17 @@ static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, if (!anon_vma) return NULL; + if (anon_vma_trylock_read(anon_vma)) + goto out; + + if (rwc->try_lock) { + anon_vma = NULL; + rwc->contended = true; + goto out; + } + anon_vma_lock_read(anon_vma); +out: return anon_vma; } @@ -2241,7 +2387,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, * contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, - const struct rmap_walk_control *rwc, bool locked) + struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; @@ -2289,7 +2435,7 @@ static void rmap_walk_anon(struct folio *folio, * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, - const struct rmap_walk_control *rwc, bool locked) + struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = folio_mapping(folio); pgoff_t pgoff_start, pgoff_end; @@ -2308,8 +2454,18 @@ static void rmap_walk_file(struct folio *folio, pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; - if (!locked) + if (!locked) { + if (i_mmap_trylock_read(mapping)) + goto lookup; + + if (rwc->try_lock) { + rwc->contended = true; + return; + } + i_mmap_lock_read(mapping); + } +lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(&folio->page, vma); @@ -2331,7 +2487,7 @@ done: i_mmap_unlock_read(mapping); } -void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc) +void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); @@ -2342,7 +2498,7 @@ void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc) } /* Like rmap_walk, but caller holds relevant rmap lock */ -void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc) +void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); @@ -2357,9 +2513,11 @@ void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc) * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. + * + * RMAP_COMPOUND is ignored. */ -void hugepage_add_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) +void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, + unsigned long address, rmap_t flags) { struct anon_vma *anon_vma = vma->anon_vma; int first; @@ -2368,8 +2526,11 @@ void hugepage_add_anon_rmap(struct page *page, BUG_ON(!anon_vma); /* address might be in next vma when migration races vma_adjust */ first = atomic_inc_and_test(compound_mapcount_ptr(page)); + VM_BUG_ON_PAGE(!first && (flags & RMAP_EXCLUSIVE), page); + VM_BUG_ON_PAGE(!first && PageAnonExclusive(page), page); if (first) - __page_set_anon_rmap(page, vma, address, 0); + __page_set_anon_rmap(page, vma, address, + !!(flags & RMAP_EXCLUSIVE)); } void hugepage_add_new_anon_rmap(struct page *page, diff --git a/mm/shmem.c b/mm/shmem.c index f3e8de8ff75c..da30c769b376 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -34,10 +34,10 @@ #include <linux/export.h> #include <linux/swap.h> #include <linux/uio.h> -#include <linux/khugepaged.h> #include <linux/hugetlb.h> #include <linux/fs_parser.h> #include <linux/swapfile.h> +#include "swap.h" static struct vfsmount *shm_mnt; @@ -134,8 +134,8 @@ static unsigned long shmem_default_max_inodes(void) } #endif -static int shmem_swapin_page(struct inode *inode, pgoff_t index, - struct page **pagep, enum sgp_type sgp, +static int shmem_swapin_folio(struct inode *inode, pgoff_t index, + struct folio **foliop, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type); static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, @@ -553,7 +553,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, LIST_HEAD(to_remove); struct inode *inode; struct shmem_inode_info *info; - struct page *page; + struct folio *folio; unsigned long batch = sc ? sc->nr_to_scan : 128; int split = 0; @@ -597,6 +597,7 @@ next: list_for_each_safe(pos, next, &list) { int ret; + pgoff_t index; info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; @@ -604,14 +605,14 @@ next: if (nr_to_split && split >= nr_to_split) goto move_back; - page = find_get_page(inode->i_mapping, - (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); - if (!page) + index = (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT; + folio = filemap_get_folio(inode->i_mapping, index); + if (!folio) goto drop; /* No huge page at the end of the file: nothing to split */ - if (!PageTransHuge(page)) { - put_page(page); + if (!folio_test_large(folio)) { + folio_put(folio); goto drop; } @@ -622,14 +623,14 @@ next: * Waiting for the lock may lead to deadlock in the * reclaim path. */ - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); goto move_back; } - ret = split_huge_page(page); - unlock_page(page); - put_page(page); + ret = split_huge_page(&folio->page); + folio_unlock(folio); + folio_put(folio); /* If split failed move the inode on the list back to shrinklist */ if (ret) @@ -694,36 +695,35 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, /* * Like add_to_page_cache_locked, but error if expected item has gone. */ -static int shmem_add_to_page_cache(struct page *page, +static int shmem_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t index, void *expected, gfp_t gfp, struct mm_struct *charge_mm) { - XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); - unsigned long nr = compound_nr(page); + XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); + long nr = folio_nr_pages(folio); int error; - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(index != round_down(index, nr), page); - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageSwapBacked(page), page); - VM_BUG_ON(expected && PageTransHuge(page)); + VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio); + VM_BUG_ON(expected && folio_test_large(folio)); - page_ref_add(page, nr); - page->mapping = mapping; - page->index = index; + folio_ref_add(folio, nr); + folio->mapping = mapping; + folio->index = index; - if (!PageSwapCache(page)) { - error = mem_cgroup_charge(page_folio(page), charge_mm, gfp); + if (!folio_test_swapcache(folio)) { + error = mem_cgroup_charge(folio, charge_mm, gfp); if (error) { - if (PageTransHuge(page)) { + if (folio_test_pmd_mappable(folio)) { count_vm_event(THP_FILE_FALLBACK); count_vm_event(THP_FILE_FALLBACK_CHARGE); } goto error; } } - cgroup_throttle_swaprate(page, gfp); + folio_throttle_swaprate(folio, gfp); do { xas_lock_irq(&xas); @@ -735,16 +735,16 @@ static int shmem_add_to_page_cache(struct page *page, xas_set_err(&xas, -EEXIST); goto unlock; } - xas_store(&xas, page); + xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; - if (PageTransHuge(page)) { + if (folio_test_pmd_mappable(folio)) { count_vm_event(THP_FILE_ALLOC); - __mod_lruvec_page_state(page, NR_SHMEM_THPS, nr); + __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); } mapping->nrpages += nr; - __mod_lruvec_page_state(page, NR_FILE_PAGES, nr); - __mod_lruvec_page_state(page, NR_SHMEM, nr); + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); + __lruvec_stat_mod_folio(folio, NR_SHMEM, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); @@ -756,8 +756,8 @@ unlock: return 0; error: - page->mapping = NULL; - page_ref_sub(page, nr); + folio->mapping = NULL; + folio_ref_sub(folio, nr); return error; } @@ -1158,69 +1158,63 @@ static void shmem_evict_inode(struct inode *inode) } static int shmem_find_swap_entries(struct address_space *mapping, - pgoff_t start, unsigned int nr_entries, - struct page **entries, pgoff_t *indices, - unsigned int type) + pgoff_t start, struct folio_batch *fbatch, + pgoff_t *indices, unsigned int type) { XA_STATE(xas, &mapping->i_pages, start); - struct page *page; + struct folio *folio; swp_entry_t entry; - unsigned int ret = 0; - - if (!nr_entries) - return 0; rcu_read_lock(); - xas_for_each(&xas, page, ULONG_MAX) { - if (xas_retry(&xas, page)) + xas_for_each(&xas, folio, ULONG_MAX) { + if (xas_retry(&xas, folio)) continue; - if (!xa_is_value(page)) + if (!xa_is_value(folio)) continue; - entry = radix_to_swp_entry(page); + entry = radix_to_swp_entry(folio); if (swp_type(entry) != type) continue; - indices[ret] = xas.xa_index; - entries[ret] = page; + indices[folio_batch_count(fbatch)] = xas.xa_index; + if (!folio_batch_add(fbatch, folio)) + break; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } - if (++ret == nr_entries) - break; } rcu_read_unlock(); - return ret; + return xas.xa_index; } /* * Move the swapped pages for an inode to page cache. Returns the count * of pages swapped in, or the error in case of failure. */ -static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec, - pgoff_t *indices) +static int shmem_unuse_swap_entries(struct inode *inode, + struct folio_batch *fbatch, pgoff_t *indices) { int i = 0; int ret = 0; int error = 0; struct address_space *mapping = inode->i_mapping; - for (i = 0; i < pvec.nr; i++) { - struct page *page = pvec.pages[i]; + for (i = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; - if (!xa_is_value(page)) + if (!xa_is_value(folio)) continue; - error = shmem_swapin_page(inode, indices[i], - &page, SGP_CACHE, + error = shmem_swapin_folio(inode, indices[i], + &folio, SGP_CACHE, mapping_gfp_mask(mapping), NULL, NULL); if (error == 0) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); ret++; } if (error == -ENOMEM) @@ -1237,26 +1231,23 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type) { struct address_space *mapping = inode->i_mapping; pgoff_t start = 0; - struct pagevec pvec; + struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; int ret = 0; - pagevec_init(&pvec); do { - unsigned int nr_entries = PAGEVEC_SIZE; - - pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, - pvec.pages, indices, type); - if (pvec.nr == 0) { + folio_batch_init(&fbatch); + shmem_find_swap_entries(mapping, start, &fbatch, indices, type); + if (folio_batch_count(&fbatch) == 0) { ret = 0; break; } - ret = shmem_unuse_swap_entries(inode, pvec, indices); + ret = shmem_unuse_swap_entries(inode, &fbatch, indices); if (ret < 0) break; - start = indices[pvec.nr - 1]; + start = indices[folio_batch_count(&fbatch) - 1]; } while (true); return ret; @@ -1312,6 +1303,7 @@ int shmem_unuse(unsigned int type) */ static int shmem_writepage(struct page *page, struct writeback_control *wbc) { + struct folio *folio = page_folio(page); struct shmem_inode_info *info; struct address_space *mapping; struct inode *inode; @@ -1385,7 +1377,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) SetPageUptodate(page); } - swap = get_swap_page(page); + swap = folio_alloc_swap(folio); if (!swap.val) goto redirty; @@ -1521,13 +1513,13 @@ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) return result; } -static struct page *shmem_alloc_hugepage(gfp_t gfp, +static struct folio *shmem_alloc_hugefolio(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct address_space *mapping = info->vfs_inode.i_mapping; pgoff_t hindex; - struct page *page; + struct folio *folio; hindex = round_down(index, HPAGE_PMD_NR); if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, @@ -1535,34 +1527,37 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); - page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, &pvma, 0, true); + folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, &pvma, 0, true); shmem_pseudo_vma_destroy(&pvma); - if (page) - prep_transhuge_page(page); - else + if (!folio) count_vm_event(THP_FILE_FALLBACK); - return page; + return folio; } -static struct page *shmem_alloc_page(gfp_t gfp, +static struct folio *shmem_alloc_folio(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; - struct page *page; + struct folio *folio; shmem_pseudo_vma_init(&pvma, info, index); - page = alloc_page_vma(gfp, &pvma, 0); + folio = vma_alloc_folio(gfp, 0, &pvma, 0, false); shmem_pseudo_vma_destroy(&pvma); - return page; + return folio; +} + +static struct page *shmem_alloc_page(gfp_t gfp, + struct shmem_inode_info *info, pgoff_t index) +{ + return &shmem_alloc_folio(gfp, info, index)->page; } -static struct page *shmem_alloc_and_acct_page(gfp_t gfp, - struct inode *inode, +static struct folio *shmem_alloc_and_acct_folio(gfp_t gfp, struct inode *inode, pgoff_t index, bool huge) { struct shmem_inode_info *info = SHMEM_I(inode); - struct page *page; + struct folio *folio; int nr; int err = -ENOSPC; @@ -1574,13 +1569,13 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp, goto failed; if (huge) - page = shmem_alloc_hugepage(gfp, info, index); + folio = shmem_alloc_hugefolio(gfp, info, index); else - page = shmem_alloc_page(gfp, info, index); - if (page) { - __SetPageLocked(page); - __SetPageSwapBacked(page); - return page; + folio = shmem_alloc_folio(gfp, info, index); + if (folio) { + __folio_set_locked(folio); + __folio_set_swapbacked(folio); + return folio; } err = -ENOMEM; @@ -1601,9 +1596,9 @@ failed: * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); * but for now it is a simple matter of zone. */ -static bool shmem_should_replace_page(struct page *page, gfp_t gfp) +static bool shmem_should_replace_folio(struct folio *folio, gfp_t gfp) { - return page_zonenum(page) > gfp_zone(gfp); + return folio_zonenum(folio) > gfp_zone(gfp); } static int shmem_replace_page(struct page **pagep, gfp_t gfp, @@ -1682,8 +1677,8 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, * Returns 0 and the page in pagep if success. On failure, returns the * error code and NULL in *pagep. */ -static int shmem_swapin_page(struct inode *inode, pgoff_t index, - struct page **pagep, enum sgp_type sgp, +static int shmem_swapin_folio(struct inode *inode, pgoff_t index, + struct folio **foliop, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type) { @@ -1691,12 +1686,13 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct shmem_inode_info *info = SHMEM_I(inode); struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL; struct page *page; + struct folio *folio = NULL; swp_entry_t swap; int error; - VM_BUG_ON(!*pagep || !xa_is_value(*pagep)); - swap = radix_to_swp_entry(*pagep); - *pagep = NULL; + VM_BUG_ON(!*foliop || !xa_is_value(*foliop)); + swap = radix_to_swp_entry(*foliop); + *foliop = NULL; /* Look it up and read it in.. */ page = lookup_swap_cache(swap, NULL, 0); @@ -1714,33 +1710,35 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, goto failed; } } + folio = page_folio(page); /* We have to do this with page locked to prevent races */ - lock_page(page); - if (!PageSwapCache(page) || page_private(page) != swap.val || + folio_lock(folio); + if (!folio_test_swapcache(folio) || + folio_swap_entry(folio).val != swap.val || !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; goto unlock; } - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { error = -EIO; goto failed; } - wait_on_page_writeback(page); + folio_wait_writeback(folio); /* * Some architectures may have to restore extra metadata to the - * physical page after reading from swap. + * folio after reading from swap. */ - arch_swap_restore(swap, page); + arch_swap_restore(swap, folio); - if (shmem_should_replace_page(page, gfp)) { + if (shmem_should_replace_folio(folio, gfp)) { error = shmem_replace_page(&page, gfp, info, index); if (error) goto failed; } - error = shmem_add_to_page_cache(page, mapping, index, + error = shmem_add_to_page_cache(folio, mapping, index, swp_to_radix_entry(swap), gfp, charge_mm); if (error) @@ -1752,21 +1750,21 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, spin_unlock_irq(&info->lock); if (sgp == SGP_WRITE) - mark_page_accessed(page); + folio_mark_accessed(folio); - delete_from_swap_cache(page); - set_page_dirty(page); + delete_from_swap_cache(&folio->page); + folio_mark_dirty(folio); swap_free(swap); - *pagep = page; + *foliop = folio; return 0; failed: if (!shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; unlock: - if (page) { - unlock_page(page); - put_page(page); + if (folio) { + folio_unlock(folio); + folio_put(folio); } return error; @@ -1791,7 +1789,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo; struct mm_struct *charge_mm; - struct page *page; + struct folio *folio; pgoff_t hindex = index; gfp_t huge_gfp; int error; @@ -1809,39 +1807,37 @@ repeat: sbinfo = SHMEM_SB(inode->i_sb); charge_mm = vma ? vma->vm_mm : NULL; - page = pagecache_get_page(mapping, index, - FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0); - - if (page && vma && userfaultfd_minor(vma)) { - if (!xa_is_value(page)) { - unlock_page(page); - put_page(page); + folio = __filemap_get_folio(mapping, index, FGP_ENTRY | FGP_LOCK, 0); + if (folio && vma && userfaultfd_minor(vma)) { + if (!xa_is_value(folio)) { + folio_unlock(folio); + folio_put(folio); } *fault_type = handle_userfault(vmf, VM_UFFD_MINOR); return 0; } - if (xa_is_value(page)) { - error = shmem_swapin_page(inode, index, &page, + if (xa_is_value(folio)) { + error = shmem_swapin_folio(inode, index, &folio, sgp, gfp, vma, fault_type); if (error == -EEXIST) goto repeat; - *pagep = page; + *pagep = &folio->page; return error; } - if (page) { - hindex = page->index; + if (folio) { + hindex = folio->index; if (sgp == SGP_WRITE) - mark_page_accessed(page); - if (PageUptodate(page)) + folio_mark_accessed(folio); + if (folio_test_uptodate(folio)) goto out; /* fallocated page */ if (sgp != SGP_READ) goto clear; - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); } /* @@ -1868,17 +1864,16 @@ repeat: huge_gfp = vma_thp_gfp_mask(vma); huge_gfp = limit_gfp_mask(huge_gfp, gfp); - page = shmem_alloc_and_acct_page(huge_gfp, inode, index, true); - if (IS_ERR(page)) { + folio = shmem_alloc_and_acct_folio(huge_gfp, inode, index, true); + if (IS_ERR(folio)) { alloc_nohuge: - page = shmem_alloc_and_acct_page(gfp, inode, - index, false); + folio = shmem_alloc_and_acct_folio(gfp, inode, index, false); } - if (IS_ERR(page)) { + if (IS_ERR(folio)) { int retry = 5; - error = PTR_ERR(page); - page = NULL; + error = PTR_ERR(folio); + folio = NULL; if (error != -ENOSPC) goto unlock; /* @@ -1897,29 +1892,26 @@ alloc_nohuge: goto unlock; } - if (PageTransHuge(page)) - hindex = round_down(index, HPAGE_PMD_NR); - else - hindex = index; + hindex = round_down(index, folio_nr_pages(folio)); if (sgp == SGP_WRITE) - __SetPageReferenced(page); + __folio_set_referenced(folio); - error = shmem_add_to_page_cache(page, mapping, hindex, + error = shmem_add_to_page_cache(folio, mapping, hindex, NULL, gfp & GFP_RECLAIM_MASK, charge_mm); if (error) goto unacct; - lru_cache_add(page); + folio_add_lru(folio); spin_lock_irq(&info->lock); - info->alloced += compound_nr(page); - inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page); + info->alloced += folio_nr_pages(folio); + inode->i_blocks += BLOCKS_PER_PAGE << folio_order(folio); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); alloced = true; - if (PageTransHuge(page) && + if (folio_test_pmd_mappable(folio) && DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) < hindex + HPAGE_PMD_NR - 1) { /* @@ -1950,22 +1942,21 @@ clear: * but SGP_FALLOC on a page fallocated earlier must initialize * it now, lest undo on failure cancel our earlier guarantee. */ - if (sgp != SGP_WRITE && !PageUptodate(page)) { - int i; + if (sgp != SGP_WRITE && !folio_test_uptodate(folio)) { + long i, n = folio_nr_pages(folio); - for (i = 0; i < compound_nr(page); i++) { - clear_highpage(page + i); - flush_dcache_page(page + i); - } - SetPageUptodate(page); + for (i = 0; i < n; i++) + clear_highpage(folio_page(folio, i)); + flush_dcache_folio(folio); + folio_mark_uptodate(folio); } /* Perhaps the file has been truncated since we checked */ if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { if (alloced) { - ClearPageDirty(page); - delete_from_page_cache(page); + folio_clear_dirty(folio); + filemap_remove_folio(folio); spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); @@ -1974,24 +1965,24 @@ clear: goto unlock; } out: - *pagep = page + index - hindex; + *pagep = folio_page(folio, index - hindex); return 0; /* * Error recovery. */ unacct: - shmem_inode_unacct_blocks(inode, compound_nr(page)); + shmem_inode_unacct_blocks(inode, folio_nr_pages(folio)); - if (PageTransHuge(page)) { - unlock_page(page); - put_page(page); + if (folio_test_large(folio)) { + folio_unlock(folio); + folio_put(folio); goto alloc_nohuge; } unlock: - if (page) { - unlock_page(page); - put_page(page); + if (folio) { + folio_unlock(folio); + folio_put(folio); } if (error == -ENOSPC && !once++) { spin_lock_irq(&info->lock); @@ -2239,11 +2230,6 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); vma->vm_ops = &shmem_vm_ops; - if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && - ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < - (vma->vm_end & HPAGE_PMD_MASK)) { - khugepaged_enter(vma, vma->vm_flags); - } return 0; } @@ -2318,7 +2304,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, + bool zeropage, bool wp_copy, struct page **pagep) { struct inode *inode = file_inode(dst_vma->vm_file); @@ -2327,6 +2313,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); void *page_kaddr; + struct folio *folio; struct page *page; int ret; pgoff_t max_off; @@ -2385,13 +2372,14 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (unlikely(pgoff >= max_off)) goto out_release; - ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, + folio = page_folio(page); + ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL, gfp & GFP_RECLAIM_MASK, dst_mm); if (ret) goto out_release; ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, - page, true, false); + page, true, wp_copy); if (ret) goto out_delete_from_cache; @@ -3487,6 +3475,10 @@ static int shmem_reconfigure(struct fs_context *fc) raw_spin_lock(&sbinfo->stat_lock); inodes = sbinfo->max_inodes - sbinfo->free_inodes; + if (ctx->blocks > S64_MAX) { + err = "Number of blocks too large"; + goto out; + } if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) { if (!sbinfo->max_blocks) { err = "Cannot retroactively limit size"; @@ -3888,7 +3880,7 @@ static struct file_system_type shmem_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; -int __init shmem_init(void) +void __init shmem_init(void) { int error; @@ -3913,14 +3905,13 @@ int __init shmem_init(void) else shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */ #endif - return 0; + return; out1: unregister_filesystem(&shmem_fs_type); out2: shmem_destroy_inodecache(); shm_mnt = ERR_PTR(error); - return error; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) @@ -3998,14 +3989,12 @@ static struct file_system_type shmem_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; -int __init shmem_init(void) +void __init shmem_init(void) { BUG_ON(register_filesystem(&shmem_fs_type) != 0); shm_mnt = kern_mount(&shmem_fs_type); BUG_ON(IS_ERR(shm_mnt)); - - return 0; } int shmem_unuse(unsigned int type) @@ -4145,12 +4134,6 @@ int shmem_zero_setup(struct vm_area_struct *vma) vma->vm_file = file; vma->vm_ops = &shmem_vm_ops; - if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && - ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < - (vma->vm_end & HPAGE_PMD_MASK)) { - khugepaged_enter(vma, vma->vm_flags); - } - return 0; } diff --git a/mm/slab.c b/mm/slab.c index a301f266efd1..f8cd00f4ba13 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2994,10 +2994,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) cachep->ctor(objp); - if (ARCH_SLAB_MINALIGN && - ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { - pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n", - objp, (int)ARCH_SLAB_MINALIGN); + if ((unsigned long)objp & (arch_slab_minalign() - 1)) { + pr_err("0x%px: not aligned to arch_slab_minalign()=%u\n", objp, + arch_slab_minalign()); } return objp; } diff --git a/mm/slab_common.c b/mm/slab_common.c index d1f3133847ad..77c3adf40e50 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -155,8 +155,7 @@ static unsigned int calculate_alignment(slab_flags_t flags, align = max(align, ralign); } - if (align < ARCH_SLAB_MINALIGN) - align = ARCH_SLAB_MINALIGN; + align = max(align, arch_slab_minalign()); return ALIGN(align, sizeof(void *)); } diff --git a/mm/slob.c b/mm/slob.c index 40ea6e2d4ccd..f47811f09aca 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -478,9 +478,11 @@ static __always_inline void * __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) { unsigned int *m; - int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + unsigned int minalign; void *ret; + minalign = max_t(unsigned int, ARCH_KMALLOC_MINALIGN, + arch_slab_minalign()); gfp &= gfp_allowed_mask; might_alloc(gfp); @@ -493,7 +495,7 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) * kmalloc()'d objects. */ if (is_power_of_2(size)) - align = max(minalign, (int) size); + align = max_t(unsigned int, minalign, size); if (!size) return ZERO_SIZE_PTR; @@ -555,8 +557,11 @@ void kfree(const void *block) sp = virt_to_folio(block); if (folio_test_slab(sp)) { - int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + unsigned int align = max_t(unsigned int, + ARCH_KMALLOC_MINALIGN, + arch_slab_minalign()); unsigned int *m = (unsigned int *)(block - align); + slob_free(m, *m + align); } else { unsigned int order = folio_order(sp); @@ -573,7 +578,7 @@ EXPORT_SYMBOL(kfree); size_t __ksize(const void *block) { struct folio *folio; - int align; + unsigned int align; unsigned int *m; BUG_ON(!block); @@ -584,7 +589,8 @@ size_t __ksize(const void *block) if (unlikely(!folio_test_slab(folio))) return folio_size(folio); - align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + align = max_t(unsigned int, ARCH_KMALLOC_MINALIGN, + arch_slab_minalign()); m = (unsigned int *)(block - align); return SLOB_UNITS(*m) * SLOB_UNIT; } diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 8aecd6b3896c..f4fa61dbbee3 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -34,7 +34,7 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP /** * struct vmemmap_remap_walk - walk vmemmap page table * @@ -420,7 +420,7 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end, return 0; } -#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */ +#endif /* CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP */ /* * Allocate a block of memory to be used to back the virtual memory map @@ -533,16 +533,31 @@ void __meminit vmemmap_verify(pte_t *pte, int node, } pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap) + struct vmem_altmap *altmap, + struct page *reuse) { pte_t *pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { pte_t entry; void *p; - p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap); - if (!p) - return NULL; + if (!reuse) { + p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap); + if (!p) + return NULL; + } else { + /* + * When a PTE/PMD entry is freed from the init_mm + * there's a a free_pages() call to this page allocated + * above. Thus this get_page() is paired with the + * put_page_testzero() on the freeing path. + * This can only called by certain ZONE_DEVICE path, + * and through vmemmap_populate_compound_pages() when + * slab is available. + */ + get_page(reuse); + p = page_to_virt(reuse); + } entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); set_pte_at(&init_mm, addr, pte, entry); } @@ -608,49 +623,166 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) return pgd; } -int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end, - int node, struct vmem_altmap *altmap) +static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node, + struct vmem_altmap *altmap, + struct page *reuse) { - unsigned long addr = start; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; + pgd = vmemmap_pgd_populate(addr, node); + if (!pgd) + return NULL; + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return NULL; + pud = vmemmap_pud_populate(p4d, addr, node); + if (!pud) + return NULL; + pmd = vmemmap_pmd_populate(pud, addr, node); + if (!pmd) + return NULL; + pte = vmemmap_pte_populate(pmd, addr, node, altmap, reuse); + if (!pte) + return NULL; + vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + return pte; +} + +static int __meminit vmemmap_populate_range(unsigned long start, + unsigned long end, int node, + struct vmem_altmap *altmap, + struct page *reuse) +{ + unsigned long addr = start; + pte_t *pte; + for (; addr < end; addr += PAGE_SIZE) { - pgd = vmemmap_pgd_populate(addr, node); - if (!pgd) - return -ENOMEM; - p4d = vmemmap_p4d_populate(pgd, addr, node); - if (!p4d) + pte = vmemmap_populate_address(addr, node, altmap, reuse); + if (!pte) return -ENOMEM; - pud = vmemmap_pud_populate(p4d, addr, node); - if (!pud) + } + + return 0; +} + +int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap) +{ + return vmemmap_populate_range(start, end, node, altmap, NULL); +} + +/* + * For compound pages bigger than section size (e.g. x86 1G compound + * pages with 2M subsection size) fill the rest of sections as tail + * pages. + * + * Note that memremap_pages() resets @nr_range value and will increment + * it after each range successful onlining. Thus the value or @nr_range + * at section memmap populate corresponds to the in-progress range + * being onlined here. + */ +static bool __meminit reuse_compound_section(unsigned long start_pfn, + struct dev_pagemap *pgmap) +{ + unsigned long nr_pages = pgmap_vmemmap_nr(pgmap); + unsigned long offset = start_pfn - + PHYS_PFN(pgmap->ranges[pgmap->nr_range].start); + + return !IS_ALIGNED(offset, nr_pages) && nr_pages > PAGES_PER_SUBSECTION; +} + +static pte_t * __meminit compound_section_tail_page(unsigned long addr) +{ + pte_t *pte; + + addr -= PAGE_SIZE; + + /* + * Assuming sections are populated sequentially, the previous section's + * page data can be reused. + */ + pte = pte_offset_kernel(pmd_off_k(addr), addr); + if (!pte) + return NULL; + + return pte; +} + +static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, + unsigned long start, + unsigned long end, int node, + struct dev_pagemap *pgmap) +{ + unsigned long size, addr; + pte_t *pte; + int rc; + + if (reuse_compound_section(start_pfn, pgmap)) { + pte = compound_section_tail_page(start); + if (!pte) return -ENOMEM; - pmd = vmemmap_pmd_populate(pud, addr, node); - if (!pmd) + + /* + * Reuse the page that was populated in the prior iteration + * with just tail struct pages. + */ + return vmemmap_populate_range(start, end, node, NULL, + pte_page(*pte)); + } + + size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page)); + for (addr = start; addr < end; addr += size) { + unsigned long next = addr, last = addr + size; + + /* Populate the head page vmemmap page */ + pte = vmemmap_populate_address(addr, node, NULL, NULL); + if (!pte) return -ENOMEM; - pte = vmemmap_pte_populate(pmd, addr, node, altmap); + + /* Populate the tail pages vmemmap page */ + next = addr + PAGE_SIZE; + pte = vmemmap_populate_address(next, node, NULL, NULL); if (!pte) return -ENOMEM; - vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); + + /* + * Reuse the previous page for the rest of tail pages + * See layout diagram in Documentation/vm/vmemmap_dedup.rst + */ + next += PAGE_SIZE; + rc = vmemmap_populate_range(next, last, node, NULL, + pte_page(*pte)); + if (rc) + return -ENOMEM; } return 0; } struct page * __meminit __populate_section_memmap(unsigned long pfn, - unsigned long nr_pages, int nid, struct vmem_altmap *altmap) + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { unsigned long start = (unsigned long) pfn_to_page(pfn); unsigned long end = start + nr_pages * sizeof(struct page); + int r; if (WARN_ON_ONCE(!IS_ALIGNED(pfn, PAGES_PER_SUBSECTION) || !IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION))) return NULL; - if (vmemmap_populate(start, end, nid, altmap)) + if (is_power_of_2(sizeof(struct page)) && + pgmap && pgmap_vmemmap_nr(pgmap) > 1 && !altmap) + r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap); + else + r = vmemmap_populate(start, end, nid, altmap); + + if (r < 0) return NULL; return pfn_to_page(pfn); diff --git a/mm/sparse.c b/mm/sparse.c index 952f06d8f373..cb3bfae64036 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -427,7 +427,8 @@ static unsigned long __init section_map_size(void) } struct page __init *__populate_section_memmap(unsigned long pfn, - unsigned long nr_pages, int nid, struct vmem_altmap *altmap) + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { unsigned long size = section_map_size(); struct page *map = sparse_buffer_alloc(size); @@ -524,7 +525,7 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin, break; map = __populate_section_memmap(pfn, PAGES_PER_SECTION, - nid, NULL); + nid, NULL, NULL); if (!map) { pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.", __func__, nid); @@ -629,9 +630,10 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) #ifdef CONFIG_SPARSEMEM_VMEMMAP static struct page * __meminit populate_section_memmap(unsigned long pfn, - unsigned long nr_pages, int nid, struct vmem_altmap *altmap) + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { - return __populate_section_memmap(pfn, nr_pages, nid, altmap); + return __populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap); } static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, @@ -700,7 +702,8 @@ static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages) } #else struct page * __meminit populate_section_memmap(unsigned long pfn, - unsigned long nr_pages, int nid, struct vmem_altmap *altmap) + unsigned long nr_pages, int nid, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { return kvmalloc_node(array_size(sizeof(struct page), PAGES_PER_SECTION), GFP_KERNEL, nid); @@ -823,7 +826,8 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, } static struct page * __meminit section_activate(int nid, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap) + unsigned long nr_pages, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { struct mem_section *ms = __pfn_to_section(pfn); struct mem_section_usage *usage = NULL; @@ -855,7 +859,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn, if (nr_pages < PAGES_PER_SECTION && early_section(ms)) return pfn_to_page(pfn); - memmap = populate_section_memmap(pfn, nr_pages, nid, altmap); + memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap); if (!memmap) { section_deactivate(pfn, nr_pages, altmap); return ERR_PTR(-ENOMEM); @@ -869,7 +873,8 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn, * @nid: The node to add section on * @start_pfn: start pfn of the memory range * @nr_pages: number of pfns to add in the section - * @altmap: device page map + * @altmap: alternate pfns to allocate the memmap backing store + * @pgmap: alternate compound page geometry for devmap mappings * * This is only intended for hotplug. * @@ -883,7 +888,8 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn, * * -ENOMEM - Out of memory. */ int __meminit sparse_add_section(int nid, unsigned long start_pfn, - unsigned long nr_pages, struct vmem_altmap *altmap) + unsigned long nr_pages, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) { unsigned long section_nr = pfn_to_section_nr(start_pfn); struct mem_section *ms; @@ -894,7 +900,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, if (ret < 0) return ret; - memmap = section_activate(nid, start_pfn, nr_pages, altmap); + memmap = section_activate(nid, start_pfn, nr_pages, altmap, pgmap); if (IS_ERR(memmap)) return PTR_ERR(memmap); @@ -916,33 +922,6 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, return 0; } -#ifdef CONFIG_MEMORY_FAILURE -static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) -{ - int i; - - /* - * A further optimization is to have per section refcounted - * num_poisoned_pages. But that would need more space per memmap, so - * for now just do a quick global check to speed up this routine in the - * absence of bad pages. - */ - if (atomic_long_read(&num_poisoned_pages) == 0) - return; - - for (i = 0; i < nr_pages; i++) { - if (PageHWPoison(&memmap[i])) { - num_poisoned_pages_dec(); - ClearPageHWPoison(&memmap[i]); - } - } -} -#else -static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) -{ -} -#endif - void sparse_remove_section(struct mem_section *ms, unsigned long pfn, unsigned long nr_pages, unsigned long map_offset, struct vmem_altmap *altmap) diff --git a/mm/swap.c b/mm/swap.c index 7e320ec08c6a..f3922a96b2e9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -166,10 +166,10 @@ EXPORT_SYMBOL(put_pages_list); * @pages: array that receives pointers to the pages pinned. * Should be at least nr_segs long. * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. Each page returned must be released - * with a put_page() call when it is finished with. + * Returns number of pages pinned. This may be fewer than the number requested. + * If nr_segs is 0 or negative, returns 0. If no pages were pinned, returns 0. + * Each page returned must be released with a put_page() call when it is + * finished with. */ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, struct page **pages) @@ -748,7 +748,7 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ -inline void __lru_add_drain_all(bool force_all_cpus) +static inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number diff --git a/mm/swap.h b/mm/swap.h new file mode 100644 index 000000000000..0193797b0c92 --- /dev/null +++ b/mm/swap.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MM_SWAP_H +#define _MM_SWAP_H + +#ifdef CONFIG_SWAP +#include <linux/blk_types.h> /* for bio_end_io_t */ + +/* linux/mm/page_io.c */ +int sio_pool_init(void); +struct swap_iocb; +int swap_readpage(struct page *page, bool do_poll, + struct swap_iocb **plug); +void __swap_read_unplug(struct swap_iocb *plug); +static inline void swap_read_unplug(struct swap_iocb *plug) +{ + if (unlikely(plug)) + __swap_read_unplug(plug); +} +void swap_write_unplug(struct swap_iocb *sio); +int swap_writepage(struct page *page, struct writeback_control *wbc); +void end_swap_bio_write(struct bio *bio); +int __swap_writepage(struct page *page, struct writeback_control *wbc, + bio_end_io_t end_write_func); + +/* linux/mm/swap_state.c */ +/* One swap address space for each 64M swap space */ +#define SWAP_ADDRESS_SPACE_SHIFT 14 +#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) +extern struct address_space *swapper_spaces[]; +#define swap_address_space(entry) \ + (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ + >> SWAP_ADDRESS_SPACE_SHIFT]) + +void show_swap_cache_info(void); +bool add_to_swap(struct folio *folio); +void *get_shadow_from_swap_cache(swp_entry_t entry); +int add_to_swap_cache(struct page *page, swp_entry_t entry, + gfp_t gfp, void **shadowp); +void __delete_from_swap_cache(struct page *page, + swp_entry_t entry, void *shadow); +void delete_from_swap_cache(struct page *page); +void clear_shadow_from_swap_cache(int type, unsigned long begin, + unsigned long end); +void free_swap_cache(struct page *page); +struct page *lookup_swap_cache(swp_entry_t entry, + struct vm_area_struct *vma, + unsigned long addr); +struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index); + +struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, + struct vm_area_struct *vma, + unsigned long addr, + bool do_poll, + struct swap_iocb **plug); +struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, + struct vm_area_struct *vma, + unsigned long addr, + bool *new_page_allocated); +struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, + struct vm_fault *vmf); +struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, + struct vm_fault *vmf); + +static inline unsigned int page_swap_flags(struct page *page) +{ + return page_swap_info(page)->flags; +} +#else /* CONFIG_SWAP */ +struct swap_iocb; +static inline int swap_readpage(struct page *page, bool do_poll, + struct swap_iocb **plug) +{ + return 0; +} +static inline void swap_write_unplug(struct swap_iocb *sio) +{ +} + +static inline struct address_space *swap_address_space(swp_entry_t entry) +{ + return NULL; +} + +static inline void free_swap_cache(struct page *page) +{ +} + +static inline void show_swap_cache_info(void) +{ +} + +static inline struct page *swap_cluster_readahead(swp_entry_t entry, + gfp_t gfp_mask, struct vm_fault *vmf) +{ + return NULL; +} + +static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, + struct vm_fault *vmf) +{ + return NULL; +} + +static inline int swap_writepage(struct page *p, struct writeback_control *wbc) +{ + return 0; +} + +static inline struct page *lookup_swap_cache(swp_entry_t swp, + struct vm_area_struct *vma, + unsigned long addr) +{ + return NULL; +} + +static inline +struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) +{ + return find_get_page(mapping, index); +} + +static inline bool add_to_swap(struct folio *folio) +{ + return false; +} + +static inline void *get_shadow_from_swap_cache(swp_entry_t entry) +{ + return NULL; +} + +static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, + gfp_t gfp_mask, void **shadowp) +{ + return -1; +} + +static inline void __delete_from_swap_cache(struct page *page, + swp_entry_t entry, void *shadow) +{ +} + +static inline void delete_from_swap_cache(struct page *page) +{ +} + +static inline void clear_shadow_from_swap_cache(int type, unsigned long begin, + unsigned long end) +{ +} + +static inline unsigned int page_swap_flags(struct page *page) +{ + return 0; +} +#endif /* CONFIG_SWAP */ +#endif /* _MM_SWAP_H */ diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 2b5531840583..2a65a89b5b4d 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -117,7 +117,7 @@ static int alloc_swap_slot_cache(unsigned int cpu) /* * Do allocation outside swap_slots_cache_mutex - * as kvzalloc could trigger reclaim and get_swap_page, + * as kvzalloc could trigger reclaim and folio_alloc_swap, * which can lock swap_slots_cache_mutex. */ slots = kvcalloc(SWAP_SLOTS_CACHE_SIZE, sizeof(swp_entry_t), @@ -213,7 +213,7 @@ static void __drain_swap_slots_cache(unsigned int type) * this function can be invoked in the cpu * hot plug path: * cpu_up -> lock cpu_hotplug -> cpu hotplug state callback - * -> memory allocation -> direct reclaim -> get_swap_page + * -> memory allocation -> direct reclaim -> folio_alloc_swap * -> drain_swap_slots_cache * * Hence the loop over current online cpu below could miss cpu that @@ -258,7 +258,7 @@ out_unlock: /* called with swap slot cache's alloc lock held */ static int refill_swap_slots_cache(struct swap_slots_cache *cache) { - if (!use_swap_slot_cache || cache->nr) + if (!use_swap_slot_cache) return 0; cache->cur = 0; @@ -269,7 +269,7 @@ static int refill_swap_slots_cache(struct swap_slots_cache *cache) return cache->nr; } -int free_swap_slot(swp_entry_t entry) +void free_swap_slot(swp_entry_t entry) { struct swap_slots_cache *cache; @@ -297,20 +297,18 @@ int free_swap_slot(swp_entry_t entry) direct_free: swapcache_free_entries(&entry, 1); } - - return 0; } -swp_entry_t get_swap_page(struct page *page) +swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; struct swap_slots_cache *cache; entry.val = 0; - if (PageTransHuge(page)) { + if (folio_test_large(folio)) { if (IS_ENABLED(CONFIG_THP_SWAP)) - get_swap_pages(1, &entry, HPAGE_PMD_NR); + get_swap_pages(1, &entry, folio_nr_pages(folio)); goto out; } @@ -344,8 +342,8 @@ repeat: get_swap_pages(1, &entry, 1); out: - if (mem_cgroup_try_charge_swap(page, entry)) { - put_swap_page(page, entry); + if (mem_cgroup_try_charge_swap(folio, entry)) { + put_swap_page(&folio->page, entry); entry.val = 0; } return entry; diff --git a/mm/swap_state.c b/mm/swap_state.c index 013856004825..b9e4ed2e90bf 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -23,6 +23,7 @@ #include <linux/huge_mm.h> #include <linux/shmem_fs.h> #include "internal.h" +#include "swap.h" /* * swapper_space is a fiction, retained to simplify the path through @@ -30,7 +31,7 @@ */ static const struct address_space_operations swap_aops = { .writepage = swap_writepage, - .dirty_folio = swap_dirty_folio, + .dirty_folio = noop_dirty_folio, #ifdef CONFIG_MIGRATION .migratepage = migrate_page, #endif @@ -175,23 +176,26 @@ void __delete_from_swap_cache(struct page *page, } /** - * add_to_swap - allocate swap space for a page - * @page: page we want to move to swap + * add_to_swap - allocate swap space for a folio + * @folio: folio we want to move to swap * - * Allocate swap space for the page and add the page to the - * swap cache. Caller needs to hold the page lock. + * Allocate swap space for the folio and add the folio to the + * swap cache. + * + * Context: Caller needs to hold the folio lock. + * Return: Whether the folio was added to the swap cache. */ -int add_to_swap(struct page *page) +bool add_to_swap(struct folio *folio) { swp_entry_t entry; int err; - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageUptodate(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); - entry = get_swap_page(page); + entry = folio_alloc_swap(folio); if (!entry.val) - return 0; + return false; /* * XArray node allocations from PF_MEMALLOC contexts could @@ -204,7 +208,7 @@ int add_to_swap(struct page *page) /* * Add it to the swap cache. */ - err = add_to_swap_cache(page, entry, + err = add_to_swap_cache(&folio->page, entry, __GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL); if (err) /* @@ -213,22 +217,23 @@ int add_to_swap(struct page *page) */ goto fail; /* - * Normally the page will be dirtied in unmap because its pte should be - * dirty. A special case is MADV_FREE page. The page's pte could have - * dirty bit cleared but the page's SwapBacked bit is still set because - * clearing the dirty bit and SwapBacked bit has no lock protected. For - * such page, unmap will not set dirty bit for it, so page reclaim will - * not write the page out. This can cause data corruption when the page - * is swap in later. Always setting the dirty bit for the page solves - * the problem. + * Normally the folio will be dirtied in unmap because its + * pte should be dirty. A special case is MADV_FREE page. The + * page's pte could have dirty bit cleared but the folio's + * SwapBacked flag is still set because clearing the dirty bit + * and SwapBacked flag has no lock protected. For such folio, + * unmap will not set dirty bit for it, so folio reclaim will + * not write the folio out. This can cause data corruption when + * the folio is swapped in later. Always setting the dirty flag + * for the folio solves the problem. */ - set_page_dirty(page); + folio_mark_dirty(folio); - return 1; + return true; fail: - put_swap_page(page, entry); - return 0; + put_swap_page(&folio->page, entry); + return false; } /* @@ -519,14 +524,16 @@ fail_unlock: * the swap entry is no longer in use. */ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, - struct vm_area_struct *vma, unsigned long addr, bool do_poll) + struct vm_area_struct *vma, + unsigned long addr, bool do_poll, + struct swap_iocb **plug) { bool page_was_allocated; struct page *retpage = __read_swap_cache_async(entry, gfp_mask, vma, addr, &page_was_allocated); if (page_was_allocated) - swap_readpage(retpage, do_poll); + swap_readpage(retpage, do_poll, plug); return retpage; } @@ -620,6 +627,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, unsigned long mask; struct swap_info_struct *si = swp_swap_info(entry); struct blk_plug plug; + struct swap_iocb *splug = NULL; bool do_poll = true, page_allocated; struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address; @@ -646,7 +654,7 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, if (!page) continue; if (page_allocated) { - swap_readpage(page, false); + swap_readpage(page, false, &splug); if (offset != entry_offset) { SetPageReadahead(page); count_vm_event(SWAP_RA); @@ -655,10 +663,12 @@ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, put_page(page); } blk_finish_plug(&plug); + swap_read_unplug(splug); lru_add_drain(); /* Push any new pages onto the LRU now */ skip: - return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll); + /* The page was likely read above, so no need for plugging here */ + return read_swap_cache_async(entry, gfp_mask, vma, addr, do_poll, NULL); } int init_swap_address_space(unsigned int type, unsigned long nr_pages) @@ -789,6 +799,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, struct vm_fault *vmf) { struct blk_plug plug; + struct swap_iocb *splug = NULL; struct vm_area_struct *vma = vmf->vma; struct page *page; pte_t *pte, pentry; @@ -807,9 +818,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte; i++, pte++) { pentry = *pte; - if (pte_none(pentry)) - continue; - if (pte_present(pentry)) + if (!is_swap_pte(pentry)) continue; entry = pte_to_swp_entry(pentry); if (unlikely(non_swap_entry(entry))) @@ -819,7 +828,7 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, if (!page) continue; if (page_allocated) { - swap_readpage(page, false); + swap_readpage(page, false, &splug); if (i != ra_info.offset) { SetPageReadahead(page); count_vm_event(SWAP_RA); @@ -828,10 +837,12 @@ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, put_page(page); } blk_finish_plug(&plug); + swap_read_unplug(splug); lru_add_drain(); skip: + /* The page was likely read above, so no need for plugging here */ return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address, - ra_info.win == 1); + ra_info.win == 1, NULL); } /** @@ -865,18 +876,15 @@ static ssize_t vma_ra_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) - enable_vma_readahead = true; - else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) - enable_vma_readahead = false; - else - return -EINVAL; + ssize_t ret; + + ret = kstrtobool(buf, &enable_vma_readahead); + if (ret) + return ret; return count; } -static struct kobj_attribute vma_ra_enabled_attr = - __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show, - vma_ra_enabled_store); +static struct kobj_attribute vma_ra_enabled_attr = __ATTR_RW(vma_ra_enabled); static struct attribute *swap_attrs[] = { &vma_ra_enabled_attr.attr, diff --git a/mm/swapfile.c b/mm/swapfile.c index 6aec1b24f440..94b4ff43ead0 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -45,6 +45,7 @@ #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> +#include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); @@ -77,9 +78,9 @@ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. - * This is used by get_swap_page() instead of swap_active_head + * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, - * but get_swap_page() doesn't need to look at full ones. + * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock @@ -775,6 +776,22 @@ static void set_cluster_next(struct swap_info_struct *si, unsigned long next) this_cpu_write(*si->cluster_next_cpu, next); } +static bool swap_offset_available_and_locked(struct swap_info_struct *si, + unsigned long offset) +{ + if (data_race(!si->swap_map[offset])) { + spin_lock(&si->lock); + return true; + } + + if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { + spin_lock(&si->lock); + return true; + } + + return false; +} + static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[]) @@ -952,15 +969,8 @@ done: scan: spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { - if (data_race(!si->swap_map[offset])) { - spin_lock(&si->lock); - goto checks; - } - if (vm_swap_full() && - READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { - spin_lock(&si->lock); + if (swap_offset_available_and_locked(si, offset)) goto checks; - } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; @@ -969,15 +979,8 @@ scan: } offset = si->lowest_bit; while (offset < scan_base) { - if (data_race(!si->swap_map[offset])) { - spin_lock(&si->lock); + if (swap_offset_available_and_locked(si, offset)) goto checks; - } - if (vm_swap_full() && - READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { - spin_lock(&si->lock); - goto checks; - } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; @@ -1122,7 +1125,7 @@ noswap: return n_ret; } -static struct swap_info_struct *__swap_info_get(swp_entry_t entry) +static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset; @@ -1137,8 +1140,13 @@ static struct swap_info_struct *__swap_info_get(swp_entry_t entry) offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; + if (data_race(!p->swap_map[swp_offset(entry)])) + goto bad_free; return p; +bad_free: + pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); + goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; @@ -1151,23 +1159,6 @@ out: return NULL; } -static struct swap_info_struct *_swap_info_get(swp_entry_t entry) -{ - struct swap_info_struct *p; - - p = __swap_info_get(entry); - if (!p) - goto out; - if (data_race(!p->swap_map[swp_offset(entry)])) - goto bad_free; - return p; - -bad_free: - pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); -out: - return NULL; -} - static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { @@ -1283,6 +1274,7 @@ bad_nofile: out: return NULL; put_out: + pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } @@ -1440,7 +1432,7 @@ void swapcache_free_entries(swp_entry_t *entries, int n) * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ -int page_swapcount(struct page *page) +static int page_swapcount(struct page *page) { int count = 0; struct swap_info_struct *p; @@ -1797,13 +1789,28 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, goto out; } + /* See do_swap_page() */ + BUG_ON(!PageAnon(page) && PageMappedToDisk(page)); + BUG_ON(PageAnon(page) && PageAnonExclusive(page)); + dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); if (page == swapcache) { - page_add_anon_rmap(page, vma, addr, false); + rmap_t rmap_flags = RMAP_NONE; + + /* + * See do_swap_page(): PageWriteback() would be problematic. + * However, we do a wait_on_page_writeback() just before this + * call and have the page locked. + */ + VM_BUG_ON_PAGE(PageWriteback(page), page); + if (pte_swp_exclusive(*pte)) + rmap_flags |= RMAP_EXCLUSIVE; + + page_add_anon_rmap(page, vma, addr, rmap_flags); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, addr, false); + page_add_new_anon_rmap(page, vma, addr); lru_cache_add_inactive_or_unevictable(page, vma); } set_pte_at(vma->vm_mm, addr, pte, @@ -1984,9 +1991,9 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type) } /* - * Scan swap_map (or frontswap_map if frontswap parameter is true) - * from current position to next entry still in use. Return 0 - * if there are no inuse entries after prev till end of the map. + * Scan swap_map from current position to next entry still in use. + * Return 0 if there are no inuse entries after prev till end of + * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) @@ -2094,11 +2101,12 @@ retry: * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * - * Limit the number of retries? No: when mmget_not_zero() above fails, - * that mm is likely to be freeing swap from exit_mmap(), which proceeds - * at its own independent pace; and even shmem_writepage() could have - * been preempted after get_swap_page(), temporarily hiding that swap. - * It's easy and robust (though cpu-intensive) just to keep retrying. + * Limit the number of retries? No: when mmget_not_zero() + * above fails, that mm is likely to be freeing swap from + * exit_mmap(), which proceeds at its own independent pace; + * and even shmem_writepage() could have been preempted after + * folio_alloc_swap(), temporarily hiding that swap. It's easy + * and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) @@ -2201,8 +2209,8 @@ EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages - * onto a contiguous range of disk blocks. An ordered list of swap extents - * is built at swapon time and is then used at swap_writepage/swap_readpage + * onto a contiguous range of disk blocks. A rbtree of swap extents is + * built at swapon time and is then used at swap_writepage/swap_readpage * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. @@ -2210,12 +2218,12 @@ EXPORT_SYMBOL_GPL(add_swap_extent); * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap - * extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK + * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks - * and will parse them into an ordered extent list, in PAGE_SIZE chunks. If - * some stray blocks are found which do not fall within the PAGE_SIZE alignment + * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray + * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * @@ -2224,10 +2232,7 @@ EXPORT_SYMBOL_GPL(add_swap_extent); * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of - * extents in the list. To avoid much list walking, we cache the previous - * search location in `curr_swap_extent', and start new searches from there. - * This is extremely effective. The average number of iterations in - * map_swap_page() has been measured at about 0.3 per page. - akpm. + * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { @@ -2244,12 +2249,13 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); - if (ret >= 0) - sis->flags |= SWP_ACTIVATED; - if (!ret) { - sis->flags |= SWP_FS_OPS; - ret = add_swap_extent(sis, 0, sis->max, 0); - *span = sis->pages; + if (ret < 0) + return ret; + sis->flags |= SWP_ACTIVATED; + if ((sis->flags & SWP_FS_OPS) && + sio_pool_init() != 0) { + destroy_swap_extents(sis); + return -ENOMEM; } return ret; } @@ -2311,7 +2317,7 @@ static void _enable_swap_info(struct swap_info_struct *p) * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. - * swap_avail_head needs to be priority ordered for get_swap_page(), + * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ @@ -3314,8 +3320,7 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) unlock_out: unlock_cluster_or_swap_info(p, ci); - if (p) - put_swap_device(p); + put_swap_device(p); return err; } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index e9bb6db002aa..4f4892a5f767 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -16,6 +16,7 @@ #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <asm/tlbflush.h> +#include <asm/tlb.h> #include "internal.h" static __always_inline @@ -77,10 +78,19 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, * Always mark a PTE as write-protected when needed, regardless of * VM_WRITE, which the user might change. */ - if (wp_copy) + if (wp_copy) { _dst_pte = pte_mkuffd_wp(_dst_pte); - else if (writable) + writable = false; + } + + if (writable) _dst_pte = pte_mkwrite(_dst_pte); + else + /* + * We need this to make sure write bit removed; as mk_pte() + * could return a pte with write bit set. + */ + _dst_pte = pte_wrprotect(_dst_pte); dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); @@ -95,7 +105,12 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, } ret = -EEXIST; - if (!pte_none(*dst_pte)) + /* + * We allow to overwrite a pte marker: consider when both MISSING|WP + * registered, we firstly wr-protect a none pte which has no page cache + * page backing it, then access the page. + */ + if (!pte_none_mostly(*dst_pte)) goto out_unlock; if (page_in_cache) { @@ -104,7 +119,7 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, lru_cache_add(page); page_add_file_rmap(page, dst_vma, false); } else { - page_add_new_anon_rmap(page, dst_vma, dst_addr, false); + page_add_new_anon_rmap(page, dst_vma, dst_addr); lru_cache_add_inactive_or_unevictable(page, dst_vma); } @@ -290,7 +305,8 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - enum mcopy_atomic_mode mode) + enum mcopy_atomic_mode mode, + bool wp_copy) { int vm_shared = dst_vma->vm_flags & VM_SHARED; ssize_t err; @@ -378,7 +394,7 @@ retry: } if (mode != MCOPY_ATOMIC_CONTINUE && - !huge_pte_none(huge_ptep_get(dst_pte))) { + !huge_pte_none_mostly(huge_ptep_get(dst_pte))) { err = -EEXIST; mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); @@ -386,7 +402,8 @@ retry: } err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, - dst_addr, src_addr, mode, &page); + dst_addr, src_addr, mode, &page, + wp_copy); mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); @@ -441,7 +458,8 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - enum mcopy_atomic_mode mode); + enum mcopy_atomic_mode mode, + bool wp_copy); #endif /* CONFIG_HUGETLB_PAGE */ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, @@ -479,11 +497,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, dst_addr); } else { - VM_WARN_ON_ONCE(wp_copy); err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, mode != MCOPY_ATOMIC_NORMAL, - page); + wp_copy, page); } return err; @@ -562,7 +579,8 @@ retry: */ if (is_vm_hugetlb_page(dst_vma)) return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, - src_start, len, mcopy_mode); + src_start, len, mcopy_mode, + wp_copy); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; @@ -687,6 +705,8 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, atomic_t *mmap_changing) { struct vm_area_struct *dst_vma; + unsigned long page_mask; + struct mmu_gather tlb; pgprot_t newprot; int err; @@ -712,24 +732,30 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, err = -ENOENT; dst_vma = find_dst_vma(dst_mm, start, len); - /* - * Make sure the vma is not shared, that the dst range is - * both valid and fully within a single existing vma. - */ - if (!dst_vma || (dst_vma->vm_flags & VM_SHARED)) + + if (!dst_vma) goto out_unlock; if (!userfaultfd_wp(dst_vma)) goto out_unlock; - if (!vma_is_anonymous(dst_vma)) + if (!vma_can_userfault(dst_vma, dst_vma->vm_flags)) goto out_unlock; + if (is_vm_hugetlb_page(dst_vma)) { + err = -EINVAL; + page_mask = vma_kernel_pagesize(dst_vma) - 1; + if ((start & page_mask) || (len & page_mask)) + goto out_unlock; + } + if (enable_wp) newprot = vm_get_page_prot(dst_vma->vm_flags & ~(VM_WRITE)); else newprot = vm_get_page_prot(dst_vma->vm_flags); - change_protection(dst_vma, start, start + len, newprot, + tlb_gather_mmu(&tlb, dst_mm); + change_protection(&tlb, dst_vma, start, start + len, newprot, enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE); + tlb_finish_mmu(&tlb); err = 0; out_unlock: diff --git a/mm/util.c b/mm/util.c index ac63e5ca8b21..29f4f773dc7b 100644 --- a/mm/util.c +++ b/mm/util.c @@ -27,6 +27,7 @@ #include <linux/uaccess.h> #include "internal.h" +#include "swap.h" /** * kfree_const - conditionally free memory diff --git a/mm/vmalloc.c b/mm/vmalloc.c index cadfbb5155ea..07db42455dd4 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -389,18 +389,15 @@ static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, { p4d_t *p4d; unsigned long next; - int cleared; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); - cleared = p4d_clear_huge(p4d); - if (cleared || p4d_bad(*p4d)) + p4d_clear_huge(p4d); + if (p4d_bad(*p4d)) *mask |= PGTBL_P4D_MODIFIED; - if (cleared) - continue; if (p4d_none_or_clear_bad(p4d)) continue; vunmap_pud_range(p4d, addr, next, mask); @@ -478,6 +475,9 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, return -EBUSY; if (WARN_ON(!page)) return -ENOMEM; + if (WARN_ON(!pfn_valid(page_to_pfn(page)))) + return -EINVAL; + set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1938,11 +1938,10 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) return ERR_PTR(err); } - vbq = &get_cpu_var(vmap_block_queue); + vbq = raw_cpu_ptr(&vmap_block_queue); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_var(vmap_block_queue); return vaddr; } @@ -2021,7 +2020,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) order = get_order(size); rcu_read_lock(); - vbq = &get_cpu_var(vmap_block_queue); + vbq = raw_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; @@ -2044,7 +2043,6 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) break; } - put_cpu_var(vmap_block_queue); rcu_read_unlock(); /* Allocate new block if nothing was found */ @@ -2895,7 +2893,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, /* memory allocation should consider mempolicy, we can't * wrongly use nearest node when nid == NUMA_NO_NODE, * otherwise memory may be allocated in only one node, - * but mempolcy want to alloc memory by interleaving. + * 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, diff --git a/mm/vmscan.c b/mm/vmscan.c index edc89f26b738..f7d9a683e3a7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -59,6 +59,7 @@ #include <linux/sched/sysctl.h> #include "internal.h" +#include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> @@ -527,13 +528,8 @@ static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) return false; - if (sc) { - if (sc->no_demotion) - return false; - /* It is pointless to do demotion in memcg reclaim */ - if (cgroup_reclaim(sc)) - return false; - } + if (sc && sc->no_demotion) + return false; if (next_demotion_node(nid) == NUMA_NO_NODE) return false; @@ -587,7 +583,7 @@ unsigned long zone_reclaimable_pages(struct zone *zone) * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use - * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list) + * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) @@ -595,7 +591,7 @@ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, unsigned long size = 0; int zid; - for (zid = 0; zid <= zone_idx && zid < MAX_NR_ZONES; zid++) { + for (zid = 0; zid <= zone_idx; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) @@ -1031,7 +1027,7 @@ static bool skip_throttle_noprogress(pg_data_t *pgdat) for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; reclaimable += zone_reclaimable_pages(zone); @@ -1155,7 +1151,8 @@ typedef enum { * pageout is called by shrink_page_list() for each dirty page. * Calls ->writepage(). */ -static pageout_t pageout(struct folio *folio, struct address_space *mapping) +static pageout_t pageout(struct folio *folio, struct address_space *mapping, + struct swap_iocb **plug) { /* * If the folio is dirty, only perform writeback if that write @@ -1200,6 +1197,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping) .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, + .swap_plug = plug, }; folio_set_reclaim(folio); @@ -1388,6 +1386,10 @@ static enum page_references folio_check_references(struct folio *folio, if (vm_flags & VM_LOCKED) return PAGEREF_ACTIVATE; + /* rmap lock contention: rotate */ + if (referenced_ptes == -1) + return PAGEREF_KEEP; + if (referenced_ptes) { /* * All mapped folios start out with page table @@ -1411,14 +1413,14 @@ static enum page_references folio_check_references(struct folio *folio, /* * Activate file-backed executable folios after first usage. */ - if ((vm_flags & VM_EXEC) && !folio_test_swapbacked(folio)) + if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) return PAGEREF_ACTIVATE; return PAGEREF_KEEP; } /* Reclaim if clean, defer dirty folios to writeback */ - if (referenced_folio && !folio_test_swapbacked(folio)) + if (referenced_folio && folio_is_file_lru(folio)) return PAGEREF_RECLAIM_CLEAN; return PAGEREF_RECLAIM; @@ -1432,7 +1434,10 @@ static void folio_check_dirty_writeback(struct folio *folio, /* * Anonymous pages are not handled by flushers and must be written - * from reclaim context. Do not stall reclaim based on them + * from reclaim context. Do not stall reclaim based on them. + * MADV_FREE anonymous pages are put into inactive file list too. + * They could be mistakenly treated as file lru. So further anon + * test is needed. */ if (!folio_is_file_lru(folio) || (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { @@ -1501,6 +1506,22 @@ static unsigned int demote_page_list(struct list_head *demote_pages, return nr_succeeded; } +static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) +{ + if (gfp_mask & __GFP_FS) + return true; + if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO)) + return false; + /* + * We can "enter_fs" for swap-cache with only __GFP_IO + * providing this isn't SWP_FS_OPS. + * ->flags can be updated non-atomicially (scan_swap_map_slots), + * but that will never affect SWP_FS_OPS, so the data_race + * is safe. + */ + return !data_race(page_swap_flags(&folio->page) & SWP_FS_OPS); +} + /* * shrink_page_list() returns the number of reclaimed pages */ @@ -1516,6 +1537,7 @@ static unsigned int shrink_page_list(struct list_head *page_list, unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; bool do_demote_pass; + struct swap_iocb *plug = NULL; memset(stat, 0, sizeof(*stat)); cond_resched(); @@ -1524,41 +1546,36 @@ static unsigned int shrink_page_list(struct list_head *page_list, retry: while (!list_empty(page_list)) { struct address_space *mapping; - struct page *page; struct folio *folio; enum page_references references = PAGEREF_RECLAIM; - bool dirty, writeback, may_enter_fs; + bool dirty, writeback; unsigned int nr_pages; cond_resched(); folio = lru_to_folio(page_list); list_del(&folio->lru); - page = &folio->page; - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto keep; - VM_BUG_ON_PAGE(PageActive(page), page); + VM_BUG_ON_FOLIO(folio_test_active(folio), folio); - nr_pages = compound_nr(page); + nr_pages = folio_nr_pages(folio); - /* Account the number of base pages even though THP */ + /* Account the number of base pages */ sc->nr_scanned += nr_pages; - if (unlikely(!page_evictable(page))) + if (unlikely(!folio_evictable(folio))) goto activate_locked; - if (!sc->may_unmap && page_mapped(page)) + if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; - may_enter_fs = (sc->gfp_mask & __GFP_FS) || - (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); - /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing - * pages if the tail of the LRU is all dirty unqueued pages. + * folios if the tail of the LRU is all dirty unqueued folios. */ folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) @@ -1568,50 +1585,51 @@ retry: stat->nr_unqueued_dirty += nr_pages; /* - * Treat this page as congested if the underlying BDI is or if - * pages are cycling through the LRU so quickly that the - * pages marked for immediate reclaim are making it to the - * end of the LRU a second time. + * Treat this folio as congested if folios are cycling + * through the LRU so quickly that the folios marked + * for immediate reclaim are making it to the end of + * the LRU a second time. */ - mapping = page_mapping(page); - if (writeback && PageReclaim(page)) + if (writeback && folio_test_reclaim(folio)) stat->nr_congested += nr_pages; /* - * If a page at the tail of the LRU is under writeback, there + * If a folio at the tail of the LRU is under writeback, there * are three cases to consider. * - * 1) If reclaim is encountering an excessive number of pages - * under writeback and this page is both under writeback and - * PageReclaim then it indicates that pages are being queued - * for IO but are being recycled through the LRU before the - * IO can complete. Waiting on the page itself risks an - * indefinite stall if it is impossible to writeback the - * page due to IO error or disconnected storage so instead - * note that the LRU is being scanned too quickly and the - * caller can stall after page list has been processed. + * 1) If reclaim is encountering an excessive number + * of folios under writeback and this folio has both + * the writeback and reclaim flags set, then it + * indicates that folios are being queued for I/O but + * are being recycled through the LRU before the I/O + * can complete. Waiting on the folio itself risks an + * indefinite stall if it is impossible to writeback + * the folio due to I/O error or disconnected storage + * so instead note that the LRU is being scanned too + * quickly and the caller can stall after the folio + * list has been processed. * - * 2) Global or new memcg reclaim encounters a page that is + * 2) Global or new memcg reclaim encounters a folio that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, - * not to fs). In this case mark the page for immediate + * not to fs). In this case mark the folio for immediate * reclaim and continue scanning. * - * Require may_enter_fs because we would wait on fs, which - * may not have submitted IO yet. And the loop driver might - * enter reclaim, and deadlock if it waits on a page for + * Require may_enter_fs() because we would wait on fs, which + * may not have submitted I/O yet. And the loop driver might + * enter reclaim, and deadlock if it waits on a folio for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * - * 3) Legacy memcg encounters a page that is already marked - * PageReclaim. memcg does not have any dirty pages + * 3) Legacy memcg encounters a folio that already has the + * reclaim flag set. memcg does not have any dirty folio * throttling so we could easily OOM just because too many - * pages are in writeback and there is nothing else to + * folios are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * - * In cases 1) and 2) we activate the pages to get them out of - * the way while we continue scanning for clean pages on the + * In cases 1) and 2) we activate the folios to get them out of + * the way while we continue scanning for clean folios on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. @@ -1619,38 +1637,42 @@ retry: * memory pressure on the cache working set any longer than it * takes to write them to disk. */ - if (PageWriteback(page)) { + if (folio_test_writeback(folio)) { /* Case 1 above */ if (current_is_kswapd() && - PageReclaim(page) && + folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || - !PageReclaim(page) || !may_enter_fs) { + !folio_test_reclaim(folio) || + !may_enter_fs(folio, sc->gfp_mask)) { /* - * This is slightly racy - end_page_writeback() - * might have just cleared PageReclaim, then - * setting PageReclaim here end up interpreted - * as PageReadahead - but that does not matter - * enough to care. What we do want is for this - * page to have PageReclaim set next time memcg - * reclaim reaches the tests above, so it will - * then wait_on_page_writeback() to avoid OOM; - * and it's also appropriate in global reclaim. + * This is slightly racy - + * folio_end_writeback() might have + * just cleared the reclaim flag, then + * setting the reclaim flag here ends up + * interpreted as the readahead flag - but + * that does not matter enough to care. + * What we do want is for this folio to + * have the reclaim flag set next time + * memcg reclaim reaches the tests above, + * so it will then wait for writeback to + * avoid OOM; and it's also appropriate + * in global reclaim. */ - SetPageReclaim(page); + folio_set_reclaim(folio); stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { - unlock_page(page); - wait_on_page_writeback(page); - /* then go back and try same page again */ - list_add_tail(&page->lru, page_list); + folio_unlock(folio); + folio_wait_writeback(folio); + /* then go back and try same folio again */ + list_add_tail(&folio->lru, page_list); continue; } } @@ -1666,37 +1688,37 @@ retry: goto keep_locked; case PAGEREF_RECLAIM: case PAGEREF_RECLAIM_CLEAN: - ; /* try to reclaim the page below */ + ; /* try to reclaim the folio below */ } /* - * Before reclaiming the page, try to relocate + * Before reclaiming the folio, try to relocate * its contents to another node. */ if (do_demote_pass && - (thp_migration_supported() || !PageTransHuge(page))) { - list_add(&page->lru, &demote_pages); - unlock_page(page); + (thp_migration_supported() || !folio_test_large(folio))) { + list_add(&folio->lru, &demote_pages); + folio_unlock(folio); continue; } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. - * Lazyfree page could be freed directly + * Lazyfree folio could be freed directly */ - if (PageAnon(page) && PageSwapBacked(page)) { - if (!PageSwapCache(page)) { + if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { + if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) goto keep_locked; - if (PageTransHuge(page)) { - /* cannot split THP, skip it */ + if (folio_test_large(folio)) { + /* cannot split folio, skip it */ if (!can_split_folio(folio, NULL)) goto activate_locked; /* - * Split pages without a PMD map right + * Split folios without a PMD map right * away. Chances are some or all of the * tail pages can be freed without IO. */ @@ -1705,8 +1727,8 @@ retry: page_list)) goto activate_locked; } - if (!add_to_swap(page)) { - if (!PageTransHuge(page)) + if (!add_to_swap(folio)) { + if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, @@ -1715,94 +1737,92 @@ retry: #ifdef CONFIG_TRANSPARENT_HUGEPAGE count_vm_event(THP_SWPOUT_FALLBACK); #endif - if (!add_to_swap(page)) + if (!add_to_swap(folio)) goto activate_locked_split; } - - may_enter_fs = true; - - /* Adding to swap updated mapping */ - mapping = page_mapping(page); } - } else if (PageSwapBacked(page) && PageTransHuge(page)) { - /* Split shmem THP */ + } else if (folio_test_swapbacked(folio) && + folio_test_large(folio)) { + /* Split shmem folio */ if (split_folio_to_list(folio, page_list)) goto keep_locked; } /* - * THP may get split above, need minus tail pages and update - * nr_pages to avoid accounting tail pages twice. - * - * The tail pages that are added into swap cache successfully - * reach here. + * If the folio was split above, the tail pages will make + * their own pass through this function and be accounted + * then. */ - if ((nr_pages > 1) && !PageTransHuge(page)) { + if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* - * The page is mapped into the page tables of one or more + * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ - if (page_mapped(page)) { + if (folio_mapped(folio)) { enum ttu_flags flags = TTU_BATCH_FLUSH; - bool was_swapbacked = PageSwapBacked(page); + bool was_swapbacked = folio_test_swapbacked(folio); - if (PageTransHuge(page) && - thp_order(page) >= HPAGE_PMD_ORDER) + if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; try_to_unmap(folio, flags); - if (page_mapped(page)) { + if (folio_mapped(folio)) { stat->nr_unmap_fail += nr_pages; - if (!was_swapbacked && PageSwapBacked(page)) + if (!was_swapbacked && + folio_test_swapbacked(folio)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } - if (PageDirty(page)) { + mapping = folio_mapping(folio); + if (folio_test_dirty(folio)) { /* - * Only kswapd can writeback filesystem pages + * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid - * injecting inefficient single-page IO into + * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only - * write pages when we've encountered many - * dirty pages, and when we've already scanned - * the rest of the LRU for clean pages and see - * the same dirty pages again (PageReclaim). + * write folios when we've encountered many + * dirty folios, and when we've already scanned + * the rest of the LRU for clean folios and see + * the same dirty folios again (with the reclaim + * flag set). */ - if (page_is_file_lru(page) && - (!current_is_kswapd() || !PageReclaim(page) || + if (folio_is_file_lru(folio) && + (!current_is_kswapd() || + !folio_test_reclaim(folio) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. - * Similar in principal to deactivate_page() - * except we already have the page isolated + * Similar in principle to deactivate_page() + * except we already have the folio isolated * and know it's dirty */ - inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); - SetPageReclaim(page); + node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, + nr_pages); + folio_set_reclaim(folio); goto activate_locked; } if (references == PAGEREF_RECLAIM_CLEAN) goto keep_locked; - if (!may_enter_fs) + if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* - * Page is dirty. Flush the TLB if a writable entry - * potentially exists to avoid CPU writes after IO + * Folio is dirty. Flush the TLB if a writable entry + * potentially exists to avoid CPU writes after I/O * starts and then write it out here. */ try_to_unmap_flush_dirty(); - switch (pageout(folio, mapping)) { + switch (pageout(folio, mapping, &plug)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: @@ -1810,91 +1830,94 @@ retry: case PAGE_SUCCESS: stat->nr_pageout += nr_pages; - if (PageWriteback(page)) + if (folio_test_writeback(folio)) goto keep; - if (PageDirty(page)) + if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go - * ahead and try to reclaim the page. + * ahead and try to reclaim the folio. */ - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto keep; - if (PageDirty(page) || PageWriteback(page)) + if (folio_test_dirty(folio) || + folio_test_writeback(folio)) goto keep_locked; - mapping = page_mapping(page); + mapping = folio_mapping(folio); fallthrough; case PAGE_CLEAN: - ; /* try to free the page below */ + ; /* try to free the folio below */ } } /* - * If the page has buffers, try to free the buffer mappings - * associated with this page. If we succeed we try to free - * the page as well. + * If the folio has buffers, try to free the buffer + * mappings associated with this folio. If we succeed + * we try to free the folio as well. * - * We do this even if the page is PageDirty(). - * try_to_release_page() does not perform I/O, but it is - * possible for a page to have PageDirty set, but it is actually - * clean (all its buffers are clean). This happens if the - * buffers were written out directly, with submit_bh(). ext3 - * will do this, as well as the blockdev mapping. - * try_to_release_page() will discover that cleanness and will - * drop the buffers and mark the page clean - it can be freed. + * We do this even if the folio is dirty. + * filemap_release_folio() does not perform I/O, but it + * is possible for a folio to have the dirty flag set, + * but it is actually clean (all its buffers are clean). + * This happens if the buffers were written out directly, + * with submit_bh(). ext3 will do this, as well as + * the blockdev mapping. filemap_release_folio() will + * discover that cleanness and will drop the buffers + * and mark the folio clean - it can be freed. * - * Rarely, pages can have buffers and no ->mapping. These are - * the pages which were not successfully invalidated in - * truncate_cleanup_page(). We try to drop those buffers here - * and if that worked, and the page is no longer mapped into - * process address space (page_count == 1) it can be freed. - * Otherwise, leave the page on the LRU so it is swappable. + * Rarely, folios can have buffers and no ->mapping. + * These are the folios which were not successfully + * invalidated in truncate_cleanup_folio(). We try to + * drop those buffers here and if that worked, and the + * folio is no longer mapped into process address space + * (refcount == 1) it can be freed. Otherwise, leave + * the folio on the LRU so it is swappable. */ - if (page_has_private(page)) { - if (!try_to_release_page(page, sc->gfp_mask)) + if (folio_has_private(folio)) { + if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; - if (!mapping && page_count(page) == 1) { - unlock_page(page); - if (put_page_testzero(page)) + if (!mapping && folio_ref_count(folio) == 1) { + folio_unlock(folio); + if (folio_put_testzero(folio)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free - * this page shortly, so we may + * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ - nr_reclaimed++; + nr_reclaimed += nr_pages; continue; } } } - if (PageAnon(page) && !PageSwapBacked(page)) { + if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ - if (!page_ref_freeze(page, 1)) + if (!folio_ref_freeze(folio, 1)) goto keep_locked; /* - * The page has only one reference left, which is + * The folio has only one reference left, which is * from the isolation. After the caller puts the - * page back on lru and drops the reference, the - * page will be freed anyway. It doesn't matter - * which lru it goes. So we don't bother checking - * PageDirty here. + * folio back on the lru and drops the reference, the + * folio will be freed anyway. It doesn't matter + * which lru it goes on. So we don't bother checking + * the dirty flag here. */ - count_vm_event(PGLAZYFREED); - count_memcg_page_event(page, PGLAZYFREED); + count_vm_events(PGLAZYFREED, nr_pages); + count_memcg_folio_events(folio, PGLAZYFREED, nr_pages); } else if (!mapping || !__remove_mapping(mapping, folio, true, sc->target_mem_cgroup)) goto keep_locked; - unlock_page(page); + folio_unlock(folio); free_it: /* - * THP may get swapped out in a whole, need account - * all base pages. + * Folio may get swapped out as a whole, need to account + * all pages in it. */ nr_reclaimed += nr_pages; @@ -1902,10 +1925,10 @@ free_it: * Is there need to periodically free_page_list? It would * appear not as the counts should be low */ - if (unlikely(PageTransHuge(page))) - destroy_compound_page(page); + if (unlikely(folio_test_large(folio))) + destroy_compound_page(&folio->page); else - list_add(&page->lru, &free_pages); + list_add(&folio->lru, &free_pages); continue; activate_locked_split: @@ -1919,29 +1942,31 @@ activate_locked_split: } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ - if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || - PageMlocked(page))) - try_to_free_swap(page); - VM_BUG_ON_PAGE(PageActive(page), page); - if (!PageMlocked(page)) { - int type = page_is_file_lru(page); - SetPageActive(page); + if (folio_test_swapcache(folio) && + (mem_cgroup_swap_full(&folio->page) || + folio_test_mlocked(folio))) + try_to_free_swap(&folio->page); + VM_BUG_ON_FOLIO(folio_test_active(folio), folio); + if (!folio_test_mlocked(folio)) { + int type = folio_is_file_lru(folio); + folio_set_active(folio); stat->nr_activate[type] += nr_pages; - count_memcg_page_event(page, PGACTIVATE); + count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: - unlock_page(page); + folio_unlock(folio); keep: - list_add(&page->lru, &ret_pages); - VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); + list_add(&folio->lru, &ret_pages); + VM_BUG_ON_FOLIO(folio_test_lru(folio) || + folio_test_unevictable(folio), folio); } /* 'page_list' is always empty here */ - /* Migrate pages selected for demotion */ + /* Migrate folios selected for demotion */ nr_reclaimed += demote_page_list(&demote_pages, pgdat); - /* Pages that could not be demoted are still in @demote_pages */ + /* Folios that could not be demoted are still in @demote_pages */ if (!list_empty(&demote_pages)) { - /* Pages which failed to demoted go back on @page_list for retry: */ + /* Folios which weren't demoted go back on @page_list for retry: */ list_splice_init(&demote_pages, page_list); do_demote_pass = false; goto retry; @@ -1956,6 +1981,8 @@ keep: list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); + if (plug) + swap_write_unplug(plug); return nr_reclaimed; } @@ -2117,8 +2144,8 @@ move: * Splice any skipped pages to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX - * scanning would soon rescan the same pages to skip and put the - * system at risk of premature OOM. + * scanning would soon rescan the same pages to skip and waste lots + * of cpu cycles. */ if (!list_empty(&pages_skipped)) { int zid; @@ -2297,10 +2324,9 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec, } /* - * If a kernel thread (such as nfsd for loop-back mounts) services - * a backing device by writing to the page cache it sets PF_LOCAL_THROTTLE. - * In that case we should only throttle if the backing device it is - * writing to is congested. In other cases it is safe to throttle. + * If a kernel thread (such as nfsd for loop-back mounts) services a backing + * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case + * we should not throttle. Otherwise it is safe to do so. */ static int current_may_throttle(void) { @@ -2472,8 +2498,9 @@ static void shrink_active_list(unsigned long nr_to_scan, } } + /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, - &vm_flags)) { + &vm_flags) != 0) { /* * Identify referenced, file-backed active pages and * give them one more trip around the active list. So @@ -2517,14 +2544,12 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_deactivate, nr_rotated, sc->priority, file); } -unsigned long reclaim_pages(struct list_head *page_list) +static unsigned int reclaim_page_list(struct list_head *page_list, + struct pglist_data *pgdat) { - int nid = NUMA_NO_NODE; - unsigned int nr_reclaimed = 0; - LIST_HEAD(node_page_list); struct reclaim_stat dummy_stat; - struct page *page; - unsigned int noreclaim_flag; + unsigned int nr_reclaimed; + struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_writepage = 1, @@ -2533,14 +2558,32 @@ unsigned long reclaim_pages(struct list_head *page_list) .no_demotion = 1, }; + nr_reclaimed = shrink_page_list(page_list, pgdat, &sc, &dummy_stat, false); + while (!list_empty(page_list)) { + folio = lru_to_folio(page_list); + list_del(&folio->lru); + folio_putback_lru(folio); + } + + return nr_reclaimed; +} + +unsigned long reclaim_pages(struct list_head *page_list) +{ + int nid; + unsigned int nr_reclaimed = 0; + LIST_HEAD(node_page_list); + struct page *page; + unsigned int noreclaim_flag; + + if (list_empty(page_list)) + return nr_reclaimed; + noreclaim_flag = memalloc_noreclaim_save(); - while (!list_empty(page_list)) { + nid = page_to_nid(lru_to_page(page_list)); + do { page = lru_to_page(page_list); - if (nid == NUMA_NO_NODE) { - nid = page_to_nid(page); - INIT_LIST_HEAD(&node_page_list); - } if (nid == page_to_nid(page)) { ClearPageActive(page); @@ -2548,28 +2591,11 @@ unsigned long reclaim_pages(struct list_head *page_list) continue; } - nr_reclaimed += shrink_page_list(&node_page_list, - NODE_DATA(nid), - &sc, &dummy_stat, false); - while (!list_empty(&node_page_list)) { - page = lru_to_page(&node_page_list); - list_del(&page->lru); - putback_lru_page(page); - } - - nid = NUMA_NO_NODE; - } + nr_reclaimed += reclaim_page_list(&node_page_list, NODE_DATA(nid)); + nid = page_to_nid(lru_to_page(page_list)); + } while (!list_empty(page_list)); - if (!list_empty(&node_page_list)) { - nr_reclaimed += shrink_page_list(&node_page_list, - NODE_DATA(nid), - &sc, &dummy_stat, false); - while (!list_empty(&node_page_list)) { - page = lru_to_page(&node_page_list); - list_del(&page->lru); - putback_lru_page(page); - } - } + nr_reclaimed += reclaim_page_list(&node_page_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); @@ -2646,9 +2672,7 @@ enum scan_balance { /* * Determine how aggressively the anon and file LRU lists should be - * scanned. The relative value of each set of LRU lists is determined - * by looking at the fraction of the pages scanned we did rotate back - * onto the active list instead of evict. + * scanned. * * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan @@ -3912,7 +3936,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) } /* - * If a node has no populated zone within highest_zoneidx, it does not + * If a node has no managed zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ @@ -4552,7 +4576,6 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) /* * This kswapd start function will be called by init and node-hot-add. - * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. */ void kswapd_run(int nid) { @@ -4699,7 +4722,8 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(p, &sc.reclaim_state); - if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) { + if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages || + node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. diff --git a/mm/vmstat.c b/mm/vmstat.c index b75b1a64b54c..da525bfb6f4a 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1393,6 +1393,13 @@ const char * const vmstat_text[] = { "ksm_swpin_copy", #endif #endif +#ifdef CONFIG_KSM + "cow_ksm", +#endif +#ifdef CONFIG_ZSWAP + "zswpin", + "zswpout", +#endif #ifdef CONFIG_X86 "direct_map_level2_splits", "direct_map_level3_splits", @@ -2111,9 +2118,7 @@ void __init init_mm_internals(void) start_shepherd_timer(); #endif -#if defined(CONFIG_MIGRATION) && defined(CONFIG_HOTPLUG_CPU) migrate_on_reclaim_init(); -#endif #ifdef CONFIG_PROC_FS proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); diff --git a/mm/z3fold.c b/mm/z3fold.c index b3c0577b8095..83b5a3514427 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -297,9 +297,6 @@ static inline void free_handle(unsigned long handle, struct z3fold_header *zhdr) int i; bool is_free; - if (handle & (1 << PAGE_HEADLESS)) - return; - if (WARN_ON(*(unsigned long *)handle == 0)) return; @@ -345,7 +342,7 @@ static struct file_system_type z3fold_fs = { }; static struct vfsmount *z3fold_mnt; -static int z3fold_mount(void) +static int __init z3fold_mount(void) { int ret = 0; @@ -420,7 +417,6 @@ static void free_z3fold_page(struct page *page, bool headless) __ClearPageMovable(page); unlock_page(page); } - ClearPagePrivate(page); __free_page(page); } @@ -521,6 +517,8 @@ static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) list_add(&zhdr->buddy, &pool->stale); queue_work(pool->release_wq, &pool->work); spin_unlock(&pool->stale_lock); + + atomic64_dec(&pool->pages_nr); } static void release_z3fold_page(struct kref *ref) @@ -738,13 +736,9 @@ static struct z3fold_header *compact_single_buddy(struct z3fold_header *zhdr) return new_zhdr; out_fail: - if (new_zhdr) { - if (kref_put(&new_zhdr->refcount, release_z3fold_page_locked)) - atomic64_dec(&pool->pages_nr); - else { - add_to_unbuddied(pool, new_zhdr); - z3fold_page_unlock(new_zhdr); - } + if (new_zhdr && !kref_put(&new_zhdr->refcount, release_z3fold_page_locked)) { + add_to_unbuddied(pool, new_zhdr); + z3fold_page_unlock(new_zhdr); } return NULL; @@ -817,10 +811,8 @@ static void do_compact_page(struct z3fold_header *zhdr, bool locked) list_del_init(&zhdr->buddy); spin_unlock(&pool->lock); - if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) { - atomic64_dec(&pool->pages_nr); + if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) return; - } if (test_bit(PAGE_STALE, &page->private) || test_and_set_bit(PAGE_CLAIMED, &page->private)) { @@ -830,9 +822,7 @@ static void do_compact_page(struct z3fold_header *zhdr, bool locked) if (!zhdr->foreign_handles && buddy_single(zhdr) && zhdr->mapped_count == 0 && compact_single_buddy(zhdr)) { - if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) - atomic64_dec(&pool->pages_nr); - else { + if (!kref_put(&zhdr->refcount, release_z3fold_page_locked)) { clear_bit(PAGE_CLAIMED, &page->private); z3fold_page_unlock(zhdr); } @@ -877,7 +867,6 @@ lookup: /* Re-check under lock. */ spin_lock(&pool->lock); - l = &unbuddied[i]; if (unlikely(zhdr != list_first_entry(READ_ONCE(l), struct z3fold_header, buddy)) || !z3fold_page_trylock(zhdr)) { @@ -1064,9 +1053,6 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool) * performed first. If no suitable free region is found, then a new page is * allocated and added to the pool to satisfy the request. * - * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used - * as z3fold pool pages. - * * Return: 0 if success and handle is set, otherwise -EINVAL if the size or * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate * a new page. @@ -1094,10 +1080,8 @@ retry: if (zhdr) { bud = get_free_buddy(zhdr, chunks); if (bud == HEADLESS) { - if (kref_put(&zhdr->refcount, + if (!kref_put(&zhdr->refcount, release_z3fold_page_locked)) - atomic64_dec(&pool->pages_nr); - else z3fold_page_unlock(zhdr); pr_err("No free chunks in unbuddied\n"); WARN_ON(1); @@ -1190,9 +1174,9 @@ headless: * @handle: handle associated with the allocation returned by z3fold_alloc() * * In the case that the z3fold page in which the allocation resides is under - * reclaim, as indicated by the PG_reclaim flag being set, this function - * only sets the first|last_chunks to 0. The page is actually freed - * once both buddies are evicted (see z3fold_reclaim_page() below). + * reclaim, as indicated by the PAGE_CLAIMED flag being set, this function + * only sets the first|middle|last_chunks to 0. The page is actually freed + * once all buddies are evicted (see z3fold_reclaim_page() below). */ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) { @@ -1244,13 +1228,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) if (!page_claimed) free_handle(handle, zhdr); - if (kref_put(&zhdr->refcount, release_z3fold_page_locked_list)) { - atomic64_dec(&pool->pages_nr); + if (kref_put(&zhdr->refcount, release_z3fold_page_locked_list)) return; - } if (page_claimed) { /* the page has not been claimed by us */ - z3fold_page_unlock(zhdr); + put_z3fold_header(zhdr); return; } if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) { @@ -1259,9 +1241,6 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) return; } if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) { - spin_lock(&pool->lock); - list_del_init(&zhdr->buddy); - spin_unlock(&pool->lock); zhdr->cpu = -1; kref_get(&zhdr->refcount); clear_bit(PAGE_CLAIMED, &page->private); @@ -1358,9 +1337,7 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) break; } if (!z3fold_page_trylock(zhdr)) { - if (kref_put(&zhdr->refcount, - release_z3fold_page)) - atomic64_dec(&pool->pages_nr); + kref_put(&zhdr->refcount, release_z3fold_page); zhdr = NULL; continue; /* can't evict at this point */ } @@ -1371,10 +1348,8 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) */ if (zhdr->foreign_handles || test_and_set_bit(PAGE_CLAIMED, &page->private)) { - if (kref_put(&zhdr->refcount, + if (!kref_put(&zhdr->refcount, release_z3fold_page_locked)) - atomic64_dec(&pool->pages_nr); - else z3fold_page_unlock(zhdr); zhdr = NULL; continue; /* can't evict such page */ @@ -1452,7 +1427,6 @@ next: if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) { kmem_cache_free(pool->c_handle, slots); - atomic64_dec(&pool->pages_nr); return 0; } /* @@ -1638,7 +1612,6 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa INIT_LIST_HEAD(&new_zhdr->buddy); new_mapping = page_mapping(page); __ClearPageMovable(page); - ClearPagePrivate(page); get_page(newpage); z3fold_page_lock(new_zhdr); @@ -1658,7 +1631,6 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work); - page_mapcount_reset(page); clear_bit(PAGE_CLAIMED, &page->private); put_page(page); return 0; @@ -1676,10 +1648,8 @@ static void z3fold_page_putback(struct page *page) if (!list_empty(&zhdr->buddy)) list_del_init(&zhdr->buddy); INIT_LIST_HEAD(&page->lru); - if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) { - atomic64_dec(&pool->pages_nr); + if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) return; - } spin_lock(&pool->lock); list_add(&page->lru, &pool->lru); spin_unlock(&pool->lock); diff --git a/mm/zswap.c b/mm/zswap.c index 3efd8cae315e..104835b379ec 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -36,13 +36,15 @@ #include <linux/pagemap.h> #include <linux/workqueue.h> +#include "swap.h" + /********************************* * statistics **********************************/ /* Total bytes used by the compressed storage */ -static u64 zswap_pool_total_size; +u64 zswap_pool_total_size; /* The number of compressed pages currently stored in zswap */ -static atomic_t zswap_stored_pages = ATOMIC_INIT(0); +atomic_t zswap_stored_pages = ATOMIC_INIT(0); /* The number of same-value filled pages currently stored in zswap */ static atomic_t zswap_same_filled_pages = ATOMIC_INIT(0); @@ -186,6 +188,7 @@ struct zswap_entry { unsigned long handle; unsigned long value; }; + struct obj_cgroup *objcg; }; struct zswap_header { @@ -357,6 +360,10 @@ static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry) */ static void zswap_free_entry(struct zswap_entry *entry) { + if (entry->objcg) { + obj_cgroup_uncharge_zswap(entry->objcg, entry->length); + obj_cgroup_put(entry->objcg); + } if (!entry->length) atomic_dec(&zswap_same_filled_pages); else { @@ -1094,6 +1101,8 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, struct zswap_entry *entry, *dupentry; struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; + struct obj_cgroup *objcg = NULL; + struct zswap_pool *pool; int ret; unsigned int hlen, dlen = PAGE_SIZE; unsigned long handle, value; @@ -1113,17 +1122,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, goto reject; } + objcg = get_obj_cgroup_from_page(page); + if (objcg && !obj_cgroup_may_zswap(objcg)) + goto shrink; + /* reclaim space if needed */ if (zswap_is_full()) { - struct zswap_pool *pool; - zswap_pool_limit_hit++; zswap_pool_reached_full = true; - pool = zswap_pool_last_get(); - if (pool) - queue_work(shrink_wq, &pool->shrink_work); - ret = -ENOMEM; - goto reject; + goto shrink; } if (zswap_pool_reached_full) { @@ -1225,6 +1232,13 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, entry->length = dlen; insert_entry: + entry->objcg = objcg; + 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); do { @@ -1241,6 +1255,7 @@ insert_entry: /* update stats */ atomic_inc(&zswap_stored_pages); zswap_update_total_size(); + count_vm_event(ZSWPOUT); return 0; @@ -1250,7 +1265,16 @@ put_dstmem: freepage: zswap_entry_cache_free(entry); reject: + if (objcg) + obj_cgroup_put(objcg); return ret; + +shrink: + pool = zswap_pool_last_get(); + if (pool) + queue_work(shrink_wq, &pool->shrink_work); + ret = -ENOMEM; + goto reject; } /* @@ -1283,11 +1307,10 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, zswap_fill_page(dst, entry->value); kunmap_atomic(dst); ret = 0; - goto freeentry; + goto stats; } if (!zpool_can_sleep_mapped(entry->pool->zpool)) { - tmp = kmalloc(entry->length, GFP_ATOMIC); if (!tmp) { ret = -ENOMEM; @@ -1302,10 +1325,8 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, src += sizeof(struct zswap_header); if (!zpool_can_sleep_mapped(entry->pool->zpool)) { - memcpy(tmp, src, entry->length); src = tmp; - zpool_unmap_handle(entry->pool->zpool, entry->handle); } @@ -1324,7 +1345,10 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, kfree(tmp); BUG_ON(ret); - +stats: + count_vm_event(ZSWPIN); + if (entry->objcg) + count_objcg_event(entry->objcg, ZSWPIN); freeentry: spin_lock(&tree->lock); zswap_entry_put(tree, entry); diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 4297d580e3f8..4c52cc6f2f9c 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -19,6 +19,7 @@ #include "cgroup_util.h" #include "../clone3/clone3_selftests.h" +/* Returns read len on success, or -errno on failure. */ static ssize_t read_text(const char *path, char *buf, size_t max_len) { ssize_t len; @@ -26,35 +27,29 @@ static ssize_t read_text(const char *path, char *buf, size_t max_len) fd = open(path, O_RDONLY); if (fd < 0) - return fd; + return -errno; len = read(fd, buf, max_len - 1); - if (len < 0) - goto out; - buf[len] = 0; -out: + if (len >= 0) + buf[len] = 0; + close(fd); - return len; + return len < 0 ? -errno : len; } +/* Returns written len on success, or -errno on failure. */ static ssize_t write_text(const char *path, char *buf, ssize_t len) { int fd; fd = open(path, O_WRONLY | O_APPEND); if (fd < 0) - return fd; + return -errno; len = write(fd, buf, len); - if (len < 0) { - close(fd); - return len; - } - close(fd); - - return len; + return len < 0 ? -errno : len; } char *cg_name(const char *root, const char *name) @@ -87,16 +82,16 @@ char *cg_control(const char *cgroup, const char *control) return ret; } +/* Returns 0 on success, or -errno on failure. */ int cg_read(const char *cgroup, const char *control, char *buf, size_t len) { char path[PATH_MAX]; + ssize_t ret; snprintf(path, sizeof(path), "%s/%s", cgroup, control); - if (read_text(path, buf, len) >= 0) - return 0; - - return -1; + ret = read_text(path, buf, len); + return ret >= 0 ? 0 : ret; } int cg_read_strcmp(const char *cgroup, const char *control, @@ -177,17 +172,15 @@ long cg_read_lc(const char *cgroup, const char *control) return cnt; } +/* Returns 0 on success, or -errno on failure. */ int cg_write(const char *cgroup, const char *control, char *buf) { char path[PATH_MAX]; - ssize_t len = strlen(buf); + ssize_t len = strlen(buf), ret; snprintf(path, sizeof(path), "%s/%s", cgroup, control); - - if (write_text(path, buf, len) == len) - return 0; - - return -1; + ret = write_text(path, buf, len); + return ret == len ? 0 : ret; } int cg_write_numeric(const char *cgroup, const char *control, long value) @@ -547,6 +540,18 @@ int set_oom_adj_score(int pid, int score) return 0; } +int proc_mount_contains(const char *option) +{ + char buf[4 * PAGE_SIZE]; + ssize_t read; + + read = read_text("/proc/mounts", buf, sizeof(buf)); + if (read < 0) + return read; + + return strstr(buf, option) != NULL; +} + ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size) { char path[PATH_MAX]; @@ -557,7 +562,8 @@ ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t else snprintf(path, sizeof(path), "/proc/%d/%s", pid, item); - return read_text(path, buf, size); + size = read_text(path, buf, size); + return size < 0 ? -1 : size; } int proc_read_strstr(int pid, bool thread, const char *item, const char *needle) diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 2ee2119281d7..c92df4e5d395 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -52,6 +52,7 @@ extern int is_swap_enabled(void); extern int set_oom_adj_score(int pid, int score); extern int cg_wait_for_proc_count(const char *cgroup, int count); extern int cg_killall(const char *cgroup); +int proc_mount_contains(const char *option); extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size); extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle); extern pid_t clone_into_cgroup(int cgroup_fd); diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 36ccf2322e21..44a974ec472c 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -21,6 +21,9 @@ #include "../kselftest.h" #include "cgroup_util.h" +static bool has_localevents; +static bool has_recursiveprot; + /* * This test creates two nested cgroups with and without enabling * the memory controller. @@ -211,13 +214,17 @@ static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg) static int alloc_anon_noexit(const char *cgroup, void *arg) { int ppid = getppid(); + size_t size = (unsigned long)arg; + char *buf, *ptr; - if (alloc_anon(cgroup, arg)) - return -1; + buf = malloc(size); + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) + *ptr = 0; while (getppid() == ppid) sleep(1); + free(buf); return 0; } @@ -244,8 +251,8 @@ static int cg_test_proc_killed(const char *cgroup) * A/B memory.min = 50M, memory.current = 50M * A/B/C memory.min = 75M, memory.current = 50M * A/B/D memory.min = 25M, memory.current = 50M - * A/B/E memory.min = 500M, memory.current = 0 - * A/B/F memory.min = 0, memory.current = 50M + * A/B/E memory.min = 0, memory.current = 50M + * A/B/F memory.min = 500M, memory.current = 0 * * Usages are pagecache, but the test keeps a running * process in every leaf cgroup. @@ -255,7 +262,7 @@ static int cg_test_proc_killed(const char *cgroup) * A/B memory.current ~= 50M * A/B/C memory.current ~= 33M * A/B/D memory.current ~= 17M - * A/B/E memory.current ~= 0 + * A/B/F memory.current ~= 0 * * After that it tries to allocate more than there is * unprotected memory in A available, and checks @@ -321,7 +328,7 @@ static int test_memcg_min(const char *root) if (cg_create(children[i])) goto cleanup; - if (i == 2) + if (i > 2) continue; cg_run_nowait(children[i], alloc_pagecache_50M_noexit, @@ -336,9 +343,9 @@ static int test_memcg_min(const char *root) goto cleanup; if (cg_write(children[1], "memory.min", "25M")) goto cleanup; - if (cg_write(children[2], "memory.min", "500M")) + if (cg_write(children[2], "memory.min", "0")) goto cleanup; - if (cg_write(children[3], "memory.min", "0")) + if (cg_write(children[3], "memory.min", "500M")) goto cleanup; attempts = 0; @@ -364,7 +371,7 @@ static int test_memcg_min(const char *root) if (!values_close(c[1], MB(17), 10)) goto cleanup; - if (!values_close(c[2], 0, 1)) + if (c[3] != 0) goto cleanup; if (!cg_run(parent[2], alloc_anon, (void *)MB(170))) @@ -401,8 +408,8 @@ cleanup: * A/B memory.low = 50M, memory.current = 50M * A/B/C memory.low = 75M, memory.current = 50M * A/B/D memory.low = 25M, memory.current = 50M - * A/B/E memory.low = 500M, memory.current = 0 - * A/B/F memory.low = 0, memory.current = 50M + * A/B/E memory.low = 0, memory.current = 50M + * A/B/F memory.low = 500M, memory.current = 0 * * Usages are pagecache. * Then it creates A/G an creates a significant @@ -412,7 +419,7 @@ cleanup: * A/B memory.current ~= 50M * A/B/ memory.current ~= 33M * A/B/D memory.current ~= 17M - * A/B/E memory.current ~= 0 + * A/B/F memory.current ~= 0 * * After that it tries to allocate more than there is * unprotected memory in A available, @@ -476,7 +483,7 @@ static int test_memcg_low(const char *root) if (cg_create(children[i])) goto cleanup; - if (i == 2) + if (i > 2) continue; if (cg_run(children[i], alloc_pagecache_50M, (void *)(long)fd)) @@ -491,9 +498,9 @@ static int test_memcg_low(const char *root) goto cleanup; if (cg_write(children[1], "memory.low", "25M")) goto cleanup; - if (cg_write(children[2], "memory.low", "500M")) + if (cg_write(children[2], "memory.low", "0")) goto cleanup; - if (cg_write(children[3], "memory.low", "0")) + if (cg_write(children[3], "memory.low", "500M")) goto cleanup; if (cg_run(parent[2], alloc_anon, (void *)MB(148))) @@ -511,7 +518,7 @@ static int test_memcg_low(const char *root) if (!values_close(c[1], MB(17), 10)) goto cleanup; - if (!values_close(c[2], 0, 1)) + if (c[3] != 0) goto cleanup; if (cg_run(parent[2], alloc_anon, (void *)MB(166))) { @@ -521,15 +528,18 @@ static int test_memcg_low(const char *root) } for (i = 0; i < ARRAY_SIZE(children); i++) { + int no_low_events_index = has_recursiveprot ? 2 : 1; + oom = cg_read_key_long(children[i], "memory.events", "oom "); low = cg_read_key_long(children[i], "memory.events", "low "); if (oom) goto cleanup; - if (i < 2 && low <= 0) + if (i <= no_low_events_index && low <= 0) goto cleanup; - if (i >= 2 && low) + if (i > no_low_events_index && low) goto cleanup; + } ret = KSFT_PASS; @@ -558,9 +568,14 @@ static int alloc_pagecache_max_30M(const char *cgroup, void *arg) { size_t size = MB(50); int ret = -1; - long current; + long current, high, max; int fd; + high = cg_read_long(cgroup, "memory.high"); + max = cg_read_long(cgroup, "memory.max"); + if (high != MB(30) && max != MB(30)) + return -1; + fd = get_temp_fd(); if (fd < 0) return -1; @@ -569,7 +584,7 @@ static int alloc_pagecache_max_30M(const char *cgroup, void *arg) goto cleanup; current = cg_read_long(cgroup, "memory.current"); - if (current <= MB(29) || current > MB(30)) + if (!values_close(current, MB(30), 5)) goto cleanup; ret = 0; @@ -607,7 +622,7 @@ static int test_memcg_high(const char *root) if (cg_write(memcg, "memory.high", "30M")) goto cleanup; - if (cg_run(memcg, alloc_anon, (void *)MB(100))) + if (cg_run(memcg, alloc_anon, (void *)MB(31))) goto cleanup; if (!cg_run(memcg, alloc_pagecache_50M_check, NULL)) @@ -756,6 +771,111 @@ cleanup: return ret; } +/* + * This test checks that memory.reclaim reclaims the given + * amount of memory (from both anon and file, if possible). + */ +static int test_memcg_reclaim(const char *root) +{ + int ret = KSFT_FAIL, fd, retries; + char *memcg; + long current, expected_usage, to_reclaim; + char buf[64]; + + memcg = cg_name(root, "memcg_test"); + if (!memcg) + goto cleanup; + + if (cg_create(memcg)) + goto cleanup; + + current = cg_read_long(memcg, "memory.current"); + if (current != 0) + goto cleanup; + + fd = get_temp_fd(); + if (fd < 0) + goto cleanup; + + cg_run_nowait(memcg, alloc_pagecache_50M_noexit, (void *)(long)fd); + + /* + * If swap is enabled, try to reclaim from both anon and file, else try + * to reclaim from file only. + */ + if (is_swap_enabled()) { + cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(50)); + expected_usage = MB(100); + } else + expected_usage = MB(50); + + /* + * Wait until current usage reaches the expected usage (or we run out of + * retries). + */ + retries = 5; + while (!values_close(cg_read_long(memcg, "memory.current"), + expected_usage, 10)) { + if (retries--) { + sleep(1); + continue; + } else { + fprintf(stderr, + "failed to allocate %ld for memcg reclaim test\n", + expected_usage); + goto cleanup; + } + } + + /* + * Reclaim until current reaches 30M, this makes sure we hit both anon + * and file if swap is enabled. + */ + retries = 5; + while (true) { + int err; + + current = cg_read_long(memcg, "memory.current"); + to_reclaim = current - MB(30); + + /* + * We only keep looping if we get EAGAIN, which means we could + * not reclaim the full amount. + */ + if (to_reclaim <= 0) + goto cleanup; + + + snprintf(buf, sizeof(buf), "%ld", to_reclaim); + err = cg_write(memcg, "memory.reclaim", buf); + if (!err) { + /* + * If writing succeeds, then the written amount should have been + * fully reclaimed (and maybe more). + */ + current = cg_read_long(memcg, "memory.current"); + if (!values_close(current, MB(30), 3) && current > MB(30)) + goto cleanup; + break; + } + + /* The kernel could not reclaim the full amount, try again. */ + if (err == -EAGAIN && retries--) + continue; + + /* We got an unexpected error or ran out of retries. */ + goto cleanup; + } + + ret = KSFT_PASS; +cleanup: + cg_destroy(memcg); + free(memcg); + close(fd); + + return ret; +} + static int alloc_anon_50M_check_swap(const char *cgroup, void *arg) { long mem_max = (long)arg; @@ -987,9 +1107,6 @@ static int tcp_client(const char *cgroup, unsigned short port) if (current < 0 || sock < 0) goto close_sk; - if (current < sock) - goto close_sk; - if (values_close(current, sock, 10)) { ret = KSFT_PASS; break; @@ -1079,12 +1196,14 @@ cleanup: /* * This test disables swapping and tries to allocate anonymous memory * up to OOM with memory.group.oom set. Then it checks that all - * processes in the leaf (but not the parent) were killed. + * processes in the leaf were killed. It also checks that oom_events + * were propagated to the parent level. */ static int test_memcg_oom_group_leaf_events(const char *root) { int ret = KSFT_FAIL; char *parent, *child; + long parent_oom_events; parent = cg_name(root, "memcg_test_0"); child = cg_name(root, "memcg_test_0/memcg_test_1"); @@ -1122,7 +1241,7 @@ static int test_memcg_oom_group_leaf_events(const char *root) if (cg_read_key_long(child, "memory.events", "oom_kill ") <= 0) goto cleanup; - if (cg_read_key_long(parent, "memory.events", "oom_kill ") != 0) + if (cg_read_key_long(parent, "memory.events", "oom_kill ") <= 0) goto cleanup; ret = KSFT_PASS; @@ -1230,14 +1349,20 @@ static int test_memcg_oom_group_score_events(const char *root) if (!cg_run(memcg, alloc_anon, (void *)MB(100))) goto cleanup; - if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 3) - goto cleanup; + parent_oom_events = cg_read_key_long( + parent, "memory.events", "oom_kill "); + /* + * If memory_localevents is not enabled (the default), the parent should + * count OOM events in its children groups. Otherwise, it should not + * have observed any events. + */ + if ((has_localevents && parent_oom_events == 0) || + parent_oom_events > 0) + ret = KSFT_PASS; if (kill(safe_pid, SIGKILL)) goto cleanup; - ret = KSFT_PASS; - cleanup: if (memcg) cg_destroy(memcg); @@ -1246,7 +1371,6 @@ cleanup: return ret; } - #define T(x) { x, #x } struct memcg_test { int (*fn)(const char *root); @@ -1259,6 +1383,7 @@ struct memcg_test { T(test_memcg_high), T(test_memcg_high_sync), T(test_memcg_max), + T(test_memcg_reclaim), T(test_memcg_oom_events), T(test_memcg_swap_max), T(test_memcg_sock), @@ -1271,7 +1396,7 @@ struct memcg_test { int main(int argc, char **argv) { char root[PATH_MAX]; - int i, ret = EXIT_SUCCESS; + int i, proc_status, ret = EXIT_SUCCESS; if (cg_find_unified_root(root, sizeof(root))) ksft_exit_skip("cgroup v2 isn't mounted\n"); @@ -1287,6 +1412,16 @@ int main(int argc, char **argv) if (cg_write(root, "cgroup.subtree_control", "+memory")) ksft_exit_skip("Failed to set memory controller\n"); + proc_status = proc_mount_contains("memory_recursiveprot"); + if (proc_status < 0) + ksft_exit_skip("Failed to query cgroup mount option\n"); + has_recursiveprot = proc_status; + + proc_status = proc_mount_contains("memory_localevents"); + if (proc_status < 0) + ksft_exit_skip("Failed to query cgroup mount option\n"); + has_localevents = proc_status; + for (i = 0; i < ARRAY_SIZE(tests); i++) { switch (tests[i].fn(root)) { case KSFT_PASS: diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh index 2e3ae77cb6db..89592c64462f 100644 --- a/tools/testing/selftests/damon/sysfs.sh +++ b/tools/testing/selftests/damon/sysfs.sh @@ -231,6 +231,7 @@ test_context() { context_dir=$1 ensure_dir "$context_dir" "exist" + ensure_file "$context_dir/avail_operations" "exit" 400 ensure_file "$context_dir/operations" "exist" 600 test_monitoring_attrs "$context_dir/monitoring_attrs" test_targets "$context_dir/targets" diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index d7507f3c7c76..31e5eea2a9b9 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -9,7 +9,9 @@ map_hugetlb map_populate thuge-gen compaction_test +migration mlock2-tests +mrelease_test mremap_dontunmap mremap_test on-fault-limit @@ -29,5 +31,6 @@ write_to_hugetlbfs hmm-tests memfd_secret local_config.* +soft-dirty split_huge_page_test ksm_tests diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 5b1ecd00695b..44f25acfbeca 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -36,20 +36,23 @@ TEST_GEN_FILES += hugepage-mremap TEST_GEN_FILES += hugepage-shm TEST_GEN_FILES += hugepage-vmemmap TEST_GEN_FILES += khugepaged -TEST_GEN_FILES += madv_populate +TEST_GEN_PROGS = madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate TEST_GEN_FILES += memfd_secret +TEST_GEN_FILES += migration TEST_GEN_FILES += mlock-random-test TEST_GEN_FILES += mlock2-tests +TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd -TEST_GEN_FILES += split_huge_page_test +TEST_GEN_PROGS += soft-dirty +TEST_GEN_PROGS += split_huge_page_test TEST_GEN_FILES += ksm_tests ifeq ($(MACHINE),x86_64) @@ -89,10 +92,15 @@ endif TEST_PROGS := run_vmtests.sh TEST_FILES := test_vmalloc.sh +TEST_FILES += test_hmm.sh KSFT_KHDR_INSTALL := 1 include ../lib.mk +$(OUTPUT)/madv_populate: vm_util.c +$(OUTPUT)/soft-dirty: vm_util.c +$(OUTPUT)/split_huge_page_test: vm_util.c + ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) @@ -149,6 +157,8 @@ $(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS) $(OUTPUT)/ksm_tests: LDLIBS += -lnuma +$(OUTPUT)/migration: LDLIBS += -lnuma + local_config.mk local_config.h: check_config.sh /bin/sh ./check_config.sh $(CC) diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config index 60e82da0de85..be087c4bc396 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/vm/config @@ -4,3 +4,5 @@ CONFIG_TEST_VMALLOC=m CONFIG_DEVICE_PRIVATE=y CONFIG_TEST_HMM=m CONFIG_GUP_TEST=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_MEM_SOFT_DIRTY=y diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c index cda837a14736..6bb36ca71cb5 100644 --- a/tools/testing/selftests/vm/gup_test.c +++ b/tools/testing/selftests/vm/gup_test.c @@ -1,7 +1,9 @@ #include <fcntl.h> +#include <errno.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> +#include <dirent.h> #include <sys/ioctl.h> #include <sys/mman.h> #include <sys/stat.h> @@ -9,6 +11,7 @@ #include <pthread.h> #include <assert.h> #include "../../../../mm/gup_test.h" +#include "../kselftest.h" #include "util.h" @@ -18,6 +21,8 @@ #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ +#define GUP_TEST_FILE "/sys/kernel/debug/gup_test" + static unsigned long cmd = GUP_FAST_BENCHMARK; static int gup_fd, repeats = 1; static unsigned long size = 128 * MB; @@ -206,8 +211,23 @@ int main(int argc, char **argv) gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); if (gup_fd == -1) { - perror("open"); - exit(1); + switch (errno) { + case EACCES: + if (getuid()) + printf("Please run this test as root\n"); + break; + case ENOENT: + if (opendir("/sys/kernel/debug") == NULL) { + printf("mount debugfs at /sys/kernel/debug\n"); + break; + } + printf("check if CONFIG_GUP_TEST is enabled in kernel config\n"); + break; + default: + perror("failed to open /sys/kernel/debug/gup_test"); + break; + } + exit(KSFT_SKIP); } p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0); diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 1d689084a54b..585978f181ed 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -178,6 +178,12 @@ int main(int argc, char *argv[]) munmap(addr, length); + addr = mremap(addr, length, length, 0); + if (addr != MAP_FAILED) { + printf("mremap: Expected failure, but call succeeded\n"); + exit(1); + } + close(fd); unlink(argv[argc-1]); diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index fd85f15869d1..2fcf24312da8 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -221,7 +221,8 @@ static bool assert_ksm_pages_count(long dupl_page_count) static int ksm_save_def(struct ksm_sysfs *ksm_sysfs) { if (ksm_read_sysfs(KSM_FP("max_page_sharing"), &ksm_sysfs->max_page_sharing) || - ksm_read_sysfs(KSM_FP("merge_across_nodes"), &ksm_sysfs->merge_across_nodes) || + numa_available() ? 0 : + ksm_read_sysfs(KSM_FP("merge_across_nodes"), &ksm_sysfs->merge_across_nodes) || ksm_read_sysfs(KSM_FP("sleep_millisecs"), &ksm_sysfs->sleep_millisecs) || ksm_read_sysfs(KSM_FP("pages_to_scan"), &ksm_sysfs->pages_to_scan) || ksm_read_sysfs(KSM_FP("run"), &ksm_sysfs->run) || @@ -236,7 +237,8 @@ static int ksm_save_def(struct ksm_sysfs *ksm_sysfs) static int ksm_restore(struct ksm_sysfs *ksm_sysfs) { if (ksm_write_sysfs(KSM_FP("max_page_sharing"), ksm_sysfs->max_page_sharing) || - ksm_write_sysfs(KSM_FP("merge_across_nodes"), ksm_sysfs->merge_across_nodes) || + numa_available() ? 0 : + ksm_write_sysfs(KSM_FP("merge_across_nodes"), ksm_sysfs->merge_across_nodes) || ksm_write_sysfs(KSM_FP("pages_to_scan"), ksm_sysfs->pages_to_scan) || ksm_write_sysfs(KSM_FP("run"), ksm_sysfs->run) || ksm_write_sysfs(KSM_FP("sleep_millisecs"), ksm_sysfs->sleep_millisecs) || @@ -720,7 +722,8 @@ int main(int argc, char *argv[]) if (ksm_write_sysfs(KSM_FP("run"), 2) || ksm_write_sysfs(KSM_FP("sleep_millisecs"), 0) || - ksm_write_sysfs(KSM_FP("merge_across_nodes"), 1) || + numa_available() ? 0 : + ksm_write_sysfs(KSM_FP("merge_across_nodes"), 1) || ksm_write_sysfs(KSM_FP("pages_to_scan"), page_count)) return KSFT_FAIL; diff --git a/tools/testing/selftests/vm/madv_populate.c b/tools/testing/selftests/vm/madv_populate.c index 3ee0e8275600..715a42e8e2cd 100644 --- a/tools/testing/selftests/vm/madv_populate.c +++ b/tools/testing/selftests/vm/madv_populate.c @@ -18,6 +18,7 @@ #include <sys/mman.h> #include "../kselftest.h" +#include "vm_util.h" /* * For now, we're using 2 MiB of private anonymous memory for all tests. @@ -26,18 +27,6 @@ static size_t pagesize; -static uint64_t pagemap_get_entry(int fd, char *start) -{ - const unsigned long pfn = (unsigned long)start / pagesize; - uint64_t entry; - int ret; - - ret = pread(fd, &entry, sizeof(entry), pfn * sizeof(entry)); - if (ret != sizeof(entry)) - ksft_exit_fail_msg("reading pagemap failed\n"); - return entry; -} - static bool pagemap_is_populated(int fd, char *start) { uint64_t entry = pagemap_get_entry(fd, start); @@ -46,13 +35,6 @@ static bool pagemap_is_populated(int fd, char *start) return entry & 0xc000000000000000ull; } -static bool pagemap_is_softdirty(int fd, char *start) -{ - uint64_t entry = pagemap_get_entry(fd, start); - - return entry & 0x0080000000000000ull; -} - static void sense_support(void) { char *addr; @@ -258,20 +240,6 @@ static bool range_is_not_softdirty(char *start, ssize_t size) return ret; } -static void clear_softdirty(void) -{ - int fd = open("/proc/self/clear_refs", O_WRONLY); - const char *ctrl = "4"; - int ret; - - if (fd < 0) - ksft_exit_fail_msg("opening clear_refs failed\n"); - ret = write(fd, ctrl, strlen(ctrl)); - if (ret != strlen(ctrl)) - ksft_exit_fail_msg("writing clear_refs failed\n"); - close(fd); -} - static void test_softdirty(void) { char *addr; diff --git a/tools/testing/selftests/vm/migration.c b/tools/testing/selftests/vm/migration.c new file mode 100644 index 000000000000..1cec8425e3ca --- /dev/null +++ b/tools/testing/selftests/vm/migration.c @@ -0,0 +1,193 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * The main purpose of the tests here is to exercise the migration entry code + * paths in the kernel. + */ + +#include "../kselftest_harness.h" +#include <strings.h> +#include <pthread.h> +#include <numa.h> +#include <numaif.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <signal.h> +#include <time.h> + +#define TWOMEG (2<<20) +#define RUNTIME (60) + +#define ALIGN(x, a) (((x) + (a - 1)) & (~((a) - 1))) + +FIXTURE(migration) +{ + pthread_t *threads; + pid_t *pids; + int nthreads; + int n1; + int n2; +}; + +FIXTURE_SETUP(migration) +{ + int n; + + ASSERT_EQ(numa_available(), 0); + self->nthreads = numa_num_task_cpus() - 1; + self->n1 = -1; + self->n2 = -1; + + for (n = 0; n < numa_max_possible_node(); n++) + if (numa_bitmask_isbitset(numa_all_nodes_ptr, n)) { + if (self->n1 == -1) { + self->n1 = n; + } else { + self->n2 = n; + break; + } + } + + self->threads = malloc(self->nthreads * sizeof(*self->threads)); + ASSERT_NE(self->threads, NULL); + self->pids = malloc(self->nthreads * sizeof(*self->pids)); + ASSERT_NE(self->pids, NULL); +}; + +FIXTURE_TEARDOWN(migration) +{ + free(self->threads); + free(self->pids); +} + +int migrate(uint64_t *ptr, int n1, int n2) +{ + int ret, tmp; + int status = 0; + struct timespec ts1, ts2; + + if (clock_gettime(CLOCK_MONOTONIC, &ts1)) + return -1; + + while (1) { + if (clock_gettime(CLOCK_MONOTONIC, &ts2)) + return -1; + + if (ts2.tv_sec - ts1.tv_sec >= RUNTIME) + return 0; + + ret = move_pages(0, 1, (void **) &ptr, &n2, &status, + MPOL_MF_MOVE_ALL); + if (ret) { + if (ret > 0) + printf("Didn't migrate %d pages\n", ret); + else + perror("Couldn't migrate pages"); + return -2; + } + + tmp = n2; + n2 = n1; + n1 = tmp; + } + + return 0; +} + +void *access_mem(void *ptr) +{ + uint64_t y = 0; + volatile uint64_t *x = ptr; + + while (1) { + pthread_testcancel(); + y += *x; + } + + return NULL; +} + +/* + * Basic migration entry testing. One thread will move pages back and forth + * between nodes whilst other threads try and access them triggering the + * migration entry wait paths in the kernel. + */ +TEST_F_TIMEOUT(migration, private_anon, 2*RUNTIME) +{ + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) + if (pthread_create(&self->threads[i], NULL, access_mem, ptr)) + perror("Couldn't create thread"); + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(pthread_cancel(self->threads[i]), 0); +} + +/* + * Same as the previous test but with shared memory. + */ +TEST_F_TIMEOUT(migration, shared_anon, 2*RUNTIME) +{ + pid_t pid; + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) { + pid = fork(); + if (!pid) + access_mem(ptr); + else + self->pids[i] = pid; + } + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(kill(self->pids[i], SIGTERM), 0); +} + +/* + * Tests the pmd migration entry paths. + */ +TEST_F_TIMEOUT(migration, private_anon_thp, 2*RUNTIME) +{ + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, 2*TWOMEG, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + ptr = (uint64_t *) ALIGN((uintptr_t) ptr, TWOMEG); + ASSERT_EQ(madvise(ptr, TWOMEG, MADV_HUGEPAGE), 0); + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) + if (pthread_create(&self->threads[i], NULL, access_mem, ptr)) + perror("Couldn't create thread"); + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(pthread_cancel(self->threads[i]), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/mrelease_test.c b/tools/testing/selftests/vm/mrelease_test.c new file mode 100644 index 000000000000..96671c2f7d48 --- /dev/null +++ b/tools/testing/selftests/vm/mrelease_test.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2022 Google LLC + */ +#define _GNU_SOURCE +#include <errno.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "util.h" + +#include "../kselftest.h" + +#ifndef __NR_pidfd_open +#define __NR_pidfd_open -1 +#endif + +#ifndef __NR_process_mrelease +#define __NR_process_mrelease -1 +#endif + +#define MB(x) (x << 20) +#define MAX_SIZE_MB 1024 + +static int alloc_noexit(unsigned long nr_pages, int pipefd) +{ + int ppid = getppid(); + int timeout = 10; /* 10sec timeout to get killed */ + unsigned long i; + char *buf; + + buf = (char *)mmap(NULL, nr_pages * PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, 0, 0); + if (buf == MAP_FAILED) { + perror("mmap failed, halting the test"); + return KSFT_FAIL; + } + + for (i = 0; i < nr_pages; i++) + *((unsigned long *)(buf + (i * PAGE_SIZE))) = i; + + /* Signal the parent that the child is ready */ + if (write(pipefd, "", 1) < 0) { + perror("write"); + return KSFT_FAIL; + } + + /* Wait to be killed (when reparenting happens) */ + while (getppid() == ppid && timeout > 0) { + sleep(1); + timeout--; + } + + munmap(buf, nr_pages * PAGE_SIZE); + + return (timeout > 0) ? KSFT_PASS : KSFT_FAIL; +} + +/* The process_mrelease calls in this test are expected to fail */ +static void run_negative_tests(int pidfd) +{ + /* Test invalid flags. Expect to fail with EINVAL error code. */ + if (!syscall(__NR_process_mrelease, pidfd, (unsigned int)-1) || + errno != EINVAL) { + perror("process_mrelease with wrong flags"); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } + /* + * Test reaping while process is alive with no pending SIGKILL. + * Expect to fail with EINVAL error code. + */ + if (!syscall(__NR_process_mrelease, pidfd, 0) || errno != EINVAL) { + perror("process_mrelease on a live process"); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } +} + +static int child_main(int pipefd[], size_t size) +{ + int res; + + /* Allocate and fault-in memory and wait to be killed */ + close(pipefd[0]); + res = alloc_noexit(MB(size) / PAGE_SIZE, pipefd[1]); + close(pipefd[1]); + return res; +} + +int main(void) +{ + int pipefd[2], pidfd; + bool success, retry; + size_t size; + pid_t pid; + char byte; + int res; + + /* Test a wrong pidfd */ + if (!syscall(__NR_process_mrelease, -1, 0) || errno != EBADF) { + perror("process_mrelease with wrong pidfd"); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } + + /* Start the test with 1MB child memory allocation */ + size = 1; +retry: + /* + * Pipe for the child to signal when it's done allocating + * memory + */ + if (pipe(pipefd)) { + perror("pipe"); + exit(KSFT_FAIL); + } + pid = fork(); + if (pid < 0) { + perror("fork"); + close(pipefd[0]); + close(pipefd[1]); + exit(KSFT_FAIL); + } + + if (pid == 0) { + /* Child main routine */ + res = child_main(pipefd, size); + exit(res); + } + + /* + * Parent main routine: + * Wait for the child to finish allocations, then kill and reap + */ + close(pipefd[1]); + /* Block until the child is ready */ + res = read(pipefd[0], &byte, 1); + close(pipefd[0]); + if (res < 0) { + perror("read"); + if (!kill(pid, SIGKILL)) + waitpid(pid, NULL, 0); + exit(KSFT_FAIL); + } + + pidfd = syscall(__NR_pidfd_open, pid, 0); + if (pidfd < 0) { + perror("pidfd_open"); + if (!kill(pid, SIGKILL)) + waitpid(pid, NULL, 0); + exit(KSFT_FAIL); + } + + /* Run negative tests which require a live child */ + run_negative_tests(pidfd); + + if (kill(pid, SIGKILL)) { + perror("kill"); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } + + success = (syscall(__NR_process_mrelease, pidfd, 0) == 0); + if (!success) { + /* + * If we failed to reap because the child exited too soon, + * before we could call process_mrelease. Double child's memory + * which causes it to spend more time on cleanup and increases + * our chances of reaping its memory before it exits. + * Retry until we succeed or reach MAX_SIZE_MB. + */ + if (errno == ESRCH) { + retry = (size <= MAX_SIZE_MB); + } else { + perror("process_mrelease"); + waitpid(pid, NULL, 0); + exit(errno == ENOSYS ? KSFT_SKIP : KSFT_FAIL); + } + } + + /* Cleanup to prevent zombies */ + if (waitpid(pid, NULL, 0) < 0) { + perror("waitpid"); + exit(KSFT_FAIL); + } + close(pidfd); + + if (!success) { + if (retry) { + size *= 2; + goto retry; + } + printf("All process_mrelease attempts failed!\n"); + exit(KSFT_FAIL); + } + + printf("Success reaping a child with %zuMB of memory allocations\n", + size); + return KSFT_PASS; +} diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index 2d0ae88665db..291bc1e07842 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -1523,7 +1523,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) /* * Reset the shadow, assuming that the above mprotect() * correctly changed PKRU, but to an unknown value since - * the actual alllocated pkey is unknown. + * the actual allocated pkey is unknown. */ shadow_pkey_reg = __read_pkey_reg(); diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 352ba00cf26b..41fce8bea929 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -9,12 +9,12 @@ mnt=./huge exitcode=0 #get huge pagesize and freepages from /proc/meminfo -while read name size unit; do +while read -r name size unit; do if [ "$name" = "HugePages_Free:" ]; then - freepgs=$size + freepgs="$size" fi if [ "$name" = "Hugepagesize:" ]; then - hpgsize_KB=$size + hpgsize_KB="$size" fi done < /proc/meminfo @@ -30,27 +30,26 @@ needmem_KB=$((half_ufd_size_MB * 2 * 1024)) #set proper nr_hugepages if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then - nr_hugepgs=`cat /proc/sys/vm/nr_hugepages` + nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) needpgs=$((needmem_KB / hpgsize_KB)) tries=2 - while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do - lackpgs=$(( $needpgs - $freepgs )) + while [ "$tries" -gt 0 ] && [ "$freepgs" -lt "$needpgs" ]; do + lackpgs=$((needpgs - freepgs)) echo 3 > /proc/sys/vm/drop_caches - echo $(( $lackpgs + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages - if [ $? -ne 0 ]; then + if ! echo $((lackpgs + nr_hugepgs)) > /proc/sys/vm/nr_hugepages; then echo "Please run this test as root" exit $ksft_skip fi - while read name size unit; do + while read -r name size unit; do if [ "$name" = "HugePages_Free:" ]; then freepgs=$size fi done < /proc/meminfo tries=$((tries - 1)) done - if [ $freepgs -lt $needpgs ]; then + if [ "$freepgs" -lt "$needpgs" ]; then printf "Not enough huge pages available (%d < %d)\n" \ - $freepgs $needpgs + "$freepgs" "$needpgs" exit 1 fi else @@ -60,458 +59,124 @@ fi #filter 64bit architectures ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64" -if [ -z $ARCH ]; then - ARCH=`uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/'` +if [ -z "$ARCH" ]; then + ARCH=$(uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/') fi VADDR64=0 -echo "$ARCH64STR" | grep $ARCH && VADDR64=1 - -mkdir $mnt -mount -t hugetlbfs none $mnt - -echo "---------------------" -echo "running hugepage-mmap" -echo "---------------------" -./hugepage-mmap -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +echo "$ARCH64STR" | grep "$ARCH" && VADDR64=1 + +# Usage: run_test [test binary] [arbitrary test arguments...] +run_test() { + local title="running $*" + local sep=$(echo -n "$title" | tr "[:graph:][:space:]" -) + printf "%s\n%s\n%s\n" "$sep" "$title" "$sep" + + "$@" + local ret=$? + if [ $ret -eq 0 ]; then + echo "[PASS]" + elif [ $ret -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip + else + echo "[FAIL]" + exitcode=1 + fi +} -shmmax=`cat /proc/sys/kernel/shmmax` -shmall=`cat /proc/sys/kernel/shmall` +mkdir "$mnt" +mount -t hugetlbfs none "$mnt" + +run_test ./hugepage-mmap + +shmmax=$(cat /proc/sys/kernel/shmmax) +shmall=$(cat /proc/sys/kernel/shmall) echo 268435456 > /proc/sys/kernel/shmmax echo 4194304 > /proc/sys/kernel/shmall -echo "--------------------" -echo "running hugepage-shm" -echo "--------------------" -./hugepage-shm -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi -echo $shmmax > /proc/sys/kernel/shmmax -echo $shmall > /proc/sys/kernel/shmall - -echo "-------------------" -echo "running map_hugetlb" -echo "-------------------" -./map_hugetlb -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./hugepage-shm +echo "$shmmax" > /proc/sys/kernel/shmmax +echo "$shmall" > /proc/sys/kernel/shmall -echo "-----------------------" -echo "running hugepage-mremap" -echo "-----------------------" -./hugepage-mremap $mnt/huge_mremap -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi -rm -f $mnt/huge_mremap - -echo "------------------------" -echo "running hugepage-vmemmap" -echo "------------------------" -./hugepage-vmemmap -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./map_hugetlb -echo "-----------------------" -echo "running hugetlb-madvise" -echo "-----------------------" -./hugetlb-madvise $mnt/madvise-test -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi -rm -f $mnt/madvise-test +run_test ./hugepage-mremap "$mnt"/huge_mremap +rm -f "$mnt"/huge_mremap + +run_test ./hugepage-vmemmap + +run_test ./hugetlb-madvise "$mnt"/madvise-test +rm -f "$mnt"/madvise-test echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" echo " hugetlb regression testing." -echo "---------------------------" -echo "running map_fixed_noreplace" -echo "---------------------------" -./map_fixed_noreplace -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./map_fixed_noreplace -echo "------------------------------------------------------" -echo "running: gup_test -u # get_user_pages_fast() benchmark" -echo "------------------------------------------------------" -./gup_test -u -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +# get_user_pages_fast() benchmark +run_test ./gup_test -u +# pin_user_pages_fast() benchmark +run_test ./gup_test -a +# Dump pages 0, 19, and 4096, using pin_user_pages: +run_test ./gup_test -ct -F 0x1 0 19 0x1000 -echo "------------------------------------------------------" -echo "running: gup_test -a # pin_user_pages_fast() benchmark" -echo "------------------------------------------------------" -./gup_test -a -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "------------------------------------------------------------" -echo "# Dump pages 0, 19, and 4096, using pin_user_pages:" -echo "running: gup_test -ct -F 0x1 0 19 0x1000 # dump_page() test" -echo "------------------------------------------------------------" -./gup_test -ct -F 0x1 0 19 0x1000 -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "-------------------" -echo "running userfaultfd" -echo "-------------------" -./userfaultfd anon 20 16 -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "---------------------------" -echo "running userfaultfd_hugetlb" -echo "---------------------------" +run_test ./userfaultfd anon 20 16 # Test requires source and destination huge pages. Size of source # (half_ufd_size_MB) is passed as argument to test. -./userfaultfd hugetlb $half_ufd_size_MB 32 -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "-------------------------" -echo "running userfaultfd_shmem" -echo "-------------------------" -./userfaultfd shmem 20 16 -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./userfaultfd hugetlb "$half_ufd_size_MB" 32 +run_test ./userfaultfd shmem 20 16 #cleanup -umount $mnt -rm -rf $mnt -echo $nr_hugepgs > /proc/sys/vm/nr_hugepages - -echo "-----------------------" -echo "running compaction_test" -echo "-----------------------" -./compaction_test -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "----------------------" -echo "running on-fault-limit" -echo "----------------------" -sudo -u nobody ./on-fault-limit -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -echo "--------------------" -echo "running map_populate" -echo "--------------------" -./map_populate -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +umount "$mnt" +rm -rf "$mnt" +echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages -echo "-------------------------" -echo "running mlock-random-test" -echo "-------------------------" -./mlock-random-test -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./compaction_test -echo "--------------------" -echo "running mlock2-tests" -echo "--------------------" -./mlock2-tests -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test sudo -u nobody ./on-fault-limit -echo "-------------------" -echo "running mremap_test" -echo "-------------------" -./mremap_test -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi - -echo "-----------------" -echo "running thuge-gen" -echo "-----------------" -./thuge-gen -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi - -if [ $VADDR64 -ne 0 ]; then -echo "-----------------------------" -echo "running virtual_address_range" -echo "-----------------------------" -./virtual_address_range -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi +run_test ./map_populate -echo "-----------------------------" -echo "running virtual address 128TB switch test" -echo "-----------------------------" -./va_128TBswitch -if [ $? -ne 0 ]; then - echo "[FAIL]" - exitcode=1 -else - echo "[PASS]" -fi -fi # VADDR64 +run_test ./mlock-random-test -echo "------------------------------------" -echo "running vmalloc stability smoke test" -echo "------------------------------------" -./test_vmalloc.sh smoke -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +run_test ./mlock2-tests -echo "------------------------------------" -echo "running MREMAP_DONTUNMAP smoke test" -echo "------------------------------------" -./mremap_dontunmap -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +run_test ./mrelease_test -echo "running HMM smoke test" -echo "------------------------------------" -./test_hmm.sh smoke -ret_val=$? +run_test ./mremap_test -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +run_test ./thuge-gen -echo "--------------------------------------------------------" -echo "running MADV_POPULATE_READ and MADV_POPULATE_WRITE tests" -echo "--------------------------------------------------------" -./madv_populate -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +if [ $VADDR64 -ne 0 ]; then + run_test ./virtual_address_range -echo "running memfd_secret test" -echo "------------------------------------" -./memfd_secret -ret_val=$? + # virtual address 128TB switch test + run_test ./va_128TBswitch +fi # VADDR64 -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +# vmalloc stability smoke test +run_test ./test_vmalloc.sh smoke -echo "-------------------------------------------------------" -echo "running KSM MADV_MERGEABLE test with 10 identical pages" -echo "-------------------------------------------------------" -./ksm_tests -M -p 10 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +run_test ./mremap_dontunmap -echo "------------------------" -echo "running KSM unmerge test" -echo "------------------------" -./ksm_tests -U -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +run_test ./test_hmm.sh smoke -echo "----------------------------------------------------------" -echo "running KSM test with 10 zero pages and use_zero_pages = 0" -echo "----------------------------------------------------------" -./ksm_tests -Z -p 10 -z 0 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi - -echo "----------------------------------------------------------" -echo "running KSM test with 10 zero pages and use_zero_pages = 1" -echo "----------------------------------------------------------" -./ksm_tests -Z -p 10 -z 1 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi - -echo "-------------------------------------------------------------" -echo "running KSM test with 2 NUMA nodes and merge_across_nodes = 1" -echo "-------------------------------------------------------------" -./ksm_tests -N -m 1 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +# MADV_POPULATE_READ and MADV_POPULATE_WRITE tests +run_test ./madv_populate -echo "-------------------------------------------------------------" -echo "running KSM test with 2 NUMA nodes and merge_across_nodes = 0" -echo "-------------------------------------------------------------" -./ksm_tests -N -m 0 -ret_val=$? - -if [ $ret_val -eq 0 ]; then - echo "[PASS]" -elif [ $ret_val -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip -else - echo "[FAIL]" - exitcode=1 -fi +run_test ./memfd_secret -exit $exitcode +# KSM MADV_MERGEABLE test with 10 identical pages +run_test ./ksm_tests -M -p 10 +# KSM unmerge test +run_test ./ksm_tests -U +# KSM test with 10 zero pages and use_zero_pages = 0 +run_test ./ksm_tests -Z -p 10 -z 0 +# KSM test with 10 zero pages and use_zero_pages = 1 +run_test ./ksm_tests -Z -p 10 -z 1 +# KSM test with 2 NUMA nodes and merge_across_nodes = 1 +run_test ./ksm_tests -N -m 1 +# KSM test with 2 NUMA nodes and merge_across_nodes = 0 +run_test ./ksm_tests -N -m 0 exit $exitcode diff --git a/tools/testing/selftests/vm/settings b/tools/testing/selftests/vm/settings new file mode 100644 index 000000000000..9abfc60e9e6f --- /dev/null +++ b/tools/testing/selftests/vm/settings @@ -0,0 +1 @@ +timeout=45 diff --git a/tools/testing/selftests/vm/soft-dirty.c b/tools/testing/selftests/vm/soft-dirty.c new file mode 100644 index 000000000000..08ab62a4a9d0 --- /dev/null +++ b/tools/testing/selftests/vm/soft-dirty.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> +#include <stdbool.h> +#include <fcntl.h> +#include <stdint.h> +#include <malloc.h> +#include <sys/mman.h> +#include "../kselftest.h" +#include "vm_util.h" + +#define PAGEMAP_FILE_PATH "/proc/self/pagemap" +#define TEST_ITERATIONS 10000 + +static void test_simple(int pagemap_fd, int pagesize) +{ + int i; + char *map; + + map = aligned_alloc(pagesize, pagesize); + if (!map) + ksft_exit_fail_msg("mmap failed\n"); + + clear_softdirty(); + + for (i = 0 ; i < TEST_ITERATIONS; i++) { + if (pagemap_is_softdirty(pagemap_fd, map) == 1) { + ksft_print_msg("dirty bit was 1, but should be 0 (i=%d)\n", i); + break; + } + + clear_softdirty(); + // Write something to the page to get the dirty bit enabled on the page + map[0]++; + + if (pagemap_is_softdirty(pagemap_fd, map) == 0) { + ksft_print_msg("dirty bit was 0, but should be 1 (i=%d)\n", i); + break; + } + + clear_softdirty(); + } + free(map); + + ksft_test_result(i == TEST_ITERATIONS, "Test %s\n", __func__); +} + +static void test_vma_reuse(int pagemap_fd, int pagesize) +{ + char *map, *map2; + + map = mmap(NULL, pagesize, (PROT_READ | PROT_WRITE), (MAP_PRIVATE | MAP_ANON), -1, 0); + if (map == MAP_FAILED) + ksft_exit_fail_msg("mmap failed"); + + // The kernel always marks new regions as soft dirty + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map) == 1, + "Test %s dirty bit of allocated page\n", __func__); + + clear_softdirty(); + munmap(map, pagesize); + + map2 = mmap(NULL, pagesize, (PROT_READ | PROT_WRITE), (MAP_PRIVATE | MAP_ANON), -1, 0); + if (map2 == MAP_FAILED) + ksft_exit_fail_msg("mmap failed"); + + // Dirty bit is set for new regions even if they are reused + if (map == map2) + ksft_test_result(pagemap_is_softdirty(pagemap_fd, map2) == 1, + "Test %s dirty bit of reused address page\n", __func__); + else + ksft_test_result_skip("Test %s dirty bit of reused address page\n", __func__); + + munmap(map2, pagesize); +} + +static void test_hugepage(int pagemap_fd, int pagesize) +{ + char *map; + int i, ret; + size_t hpage_len = read_pmd_pagesize(); + + map = memalign(hpage_len, hpage_len); + if (!map) + ksft_exit_fail_msg("memalign failed\n"); + + ret = madvise(map, hpage_len, MADV_HUGEPAGE); + if (ret) + ksft_exit_fail_msg("madvise failed %d\n", ret); + + for (i = 0; i < hpage_len; i++) + map[i] = (char)i; + + if (check_huge(map)) { + ksft_test_result_pass("Test %s huge page allocation\n", __func__); + + clear_softdirty(); + for (i = 0 ; i < TEST_ITERATIONS ; i++) { + if (pagemap_is_softdirty(pagemap_fd, map) == 1) { + ksft_print_msg("dirty bit was 1, but should be 0 (i=%d)\n", i); + break; + } + + clear_softdirty(); + // Write something to the page to get the dirty bit enabled on the page + map[0]++; + + if (pagemap_is_softdirty(pagemap_fd, map) == 0) { + ksft_print_msg("dirty bit was 0, but should be 1 (i=%d)\n", i); + break; + } + clear_softdirty(); + } + + ksft_test_result(i == TEST_ITERATIONS, "Test %s huge page dirty bit\n", __func__); + } else { + // hugepage allocation failed. skip these tests + ksft_test_result_skip("Test %s huge page allocation\n", __func__); + ksft_test_result_skip("Test %s huge page dirty bit\n", __func__); + } + free(map); +} + +int main(int argc, char **argv) +{ + int pagemap_fd; + int pagesize; + + ksft_print_header(); + ksft_set_plan(5); + + pagemap_fd = open(PAGEMAP_FILE_PATH, O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_fail_msg("Failed to open %s\n", PAGEMAP_FILE_PATH); + + pagesize = getpagesize(); + + test_simple(pagemap_fd, pagesize); + test_vma_reuse(pagemap_fd, pagesize); + test_hugepage(pagemap_fd, pagesize); + + close(pagemap_fd); + + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c index 52497b7b9f1d..6aa2b8253aed 100644 --- a/tools/testing/selftests/vm/split_huge_page_test.c +++ b/tools/testing/selftests/vm/split_huge_page_test.c @@ -16,14 +16,13 @@ #include <sys/mount.h> #include <malloc.h> #include <stdbool.h> +#include "vm_util.h" uint64_t pagesize; unsigned int pageshift; uint64_t pmd_pagesize; -#define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages" -#define SMAP_PATH "/proc/self/smaps" #define INPUT_MAX 80 #define PID_FMT "%d,0x%lx,0x%lx" @@ -51,30 +50,6 @@ int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file) return 0; } - -static uint64_t read_pmd_pagesize(void) -{ - int fd; - char buf[20]; - ssize_t num_read; - - fd = open(PMD_SIZE_PATH, O_RDONLY); - if (fd == -1) { - perror("Open hpage_pmd_size failed"); - exit(EXIT_FAILURE); - } - num_read = read(fd, buf, 19); - if (num_read < 1) { - close(fd); - perror("Read hpage_pmd_size failed"); - exit(EXIT_FAILURE); - } - buf[num_read] = '\0'; - close(fd); - - return strtoul(buf, NULL, 10); -} - static int write_file(const char *path, const char *buf, size_t buflen) { int fd; @@ -113,58 +88,6 @@ static void write_debugfs(const char *fmt, ...) } } -#define MAX_LINE_LENGTH 500 - -static bool check_for_pattern(FILE *fp, const char *pattern, char *buf) -{ - while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { - if (!strncmp(buf, pattern, strlen(pattern))) - return true; - } - return false; -} - -static uint64_t check_huge(void *addr) -{ - uint64_t thp = 0; - int ret; - FILE *fp; - char buffer[MAX_LINE_LENGTH]; - char addr_pattern[MAX_LINE_LENGTH]; - - ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", - (unsigned long) addr); - if (ret >= MAX_LINE_LENGTH) { - printf("%s: Pattern is too long\n", __func__); - exit(EXIT_FAILURE); - } - - - fp = fopen(SMAP_PATH, "r"); - if (!fp) { - printf("%s: Failed to open file %s\n", __func__, SMAP_PATH); - exit(EXIT_FAILURE); - } - if (!check_for_pattern(fp, addr_pattern, buffer)) - goto err_out; - - /* - * Fetch the AnonHugePages: in the same block and check the number of - * hugepages. - */ - if (!check_for_pattern(fp, "AnonHugePages:", buffer)) - goto err_out; - - if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) { - printf("Reading smap error\n"); - exit(EXIT_FAILURE); - } - -err_out: - fclose(fp); - return thp; -} - void split_pmd_thp(void) { char *one_page; diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 92a4516f8f0d..0bdfc1955229 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -82,7 +82,7 @@ static int test_type; static volatile bool test_uffdio_copy_eexist = true; static volatile bool test_uffdio_zeropage_eexist = true; /* Whether to test uffd write-protection */ -static bool test_uffdio_wp = false; +static bool test_uffdio_wp = true; /* Whether to test uffd minor faults */ static bool test_uffdio_minor = false; @@ -1422,7 +1422,6 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) static int userfaultfd_stress(void) { void *area; - char *tmp_area; unsigned long nr; struct uffdio_register uffdio_register; struct uffd_stats uffd_stats[nr_cpus]; @@ -1533,13 +1532,9 @@ static int userfaultfd_stress(void) count_verify[nr], nr); /* prepare next bounce */ - tmp_area = area_src; - area_src = area_dst; - area_dst = tmp_area; + swap(area_src, area_dst); - tmp_area = area_src_alias; - area_src_alias = area_dst_alias; - area_dst_alias = tmp_area; + swap(area_src_alias, area_dst_alias); uffd_stats_report(uffd_stats, nr_cpus); } @@ -1594,8 +1589,6 @@ static void set_test_type(const char *type) if (!strcmp(type, "anon")) { test_type = TEST_ANON; uffd_test_ops = &anon_uffd_test_ops; - /* Only enable write-protect test for anonymous test */ - test_uffdio_wp = true; } else if (!strcmp(type, "hugetlb")) { test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; diff --git a/tools/testing/selftests/vm/vm_util.c b/tools/testing/selftests/vm/vm_util.c new file mode 100644 index 000000000000..b58ab11a7a30 --- /dev/null +++ b/tools/testing/selftests/vm/vm_util.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <string.h> +#include <fcntl.h> +#include "../kselftest.h" +#include "vm_util.h" + +#define PMD_SIZE_FILE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" +#define SMAP_FILE_PATH "/proc/self/smaps" +#define MAX_LINE_LENGTH 500 + +uint64_t pagemap_get_entry(int fd, char *start) +{ + const unsigned long pfn = (unsigned long)start / getpagesize(); + uint64_t entry; + int ret; + + ret = pread(fd, &entry, sizeof(entry), pfn * sizeof(entry)); + if (ret != sizeof(entry)) + ksft_exit_fail_msg("reading pagemap failed\n"); + return entry; +} + +bool pagemap_is_softdirty(int fd, char *start) +{ + uint64_t entry = pagemap_get_entry(fd, start); + + // Check if dirty bit (55th bit) is set + return entry & 0x0080000000000000ull; +} + +void clear_softdirty(void) +{ + int ret; + const char *ctrl = "4"; + int fd = open("/proc/self/clear_refs", O_WRONLY); + + if (fd < 0) + ksft_exit_fail_msg("opening clear_refs failed\n"); + ret = write(fd, ctrl, strlen(ctrl)); + close(fd); + if (ret != strlen(ctrl)) + ksft_exit_fail_msg("writing clear_refs failed\n"); +} + +static bool check_for_pattern(FILE *fp, const char *pattern, char *buf) +{ + while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) { + if (!strncmp(buf, pattern, strlen(pattern))) + return true; + } + return false; +} + +uint64_t read_pmd_pagesize(void) +{ + int fd; + char buf[20]; + ssize_t num_read; + + fd = open(PMD_SIZE_FILE_PATH, O_RDONLY); + if (fd == -1) + ksft_exit_fail_msg("Open hpage_pmd_size failed\n"); + + num_read = read(fd, buf, 19); + if (num_read < 1) { + close(fd); + ksft_exit_fail_msg("Read hpage_pmd_size failed\n"); + } + buf[num_read] = '\0'; + close(fd); + + return strtoul(buf, NULL, 10); +} + +uint64_t check_huge(void *addr) +{ + uint64_t thp = 0; + int ret; + FILE *fp; + char buffer[MAX_LINE_LENGTH]; + char addr_pattern[MAX_LINE_LENGTH]; + + ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", + (unsigned long) addr); + if (ret >= MAX_LINE_LENGTH) + ksft_exit_fail_msg("%s: Pattern is too long\n", __func__); + + fp = fopen(SMAP_FILE_PATH, "r"); + if (!fp) + ksft_exit_fail_msg("%s: Failed to open file %s\n", __func__, SMAP_FILE_PATH); + + if (!check_for_pattern(fp, addr_pattern, buffer)) + goto err_out; + + /* + * Fetch the AnonHugePages: in the same block and check the number of + * hugepages. + */ + if (!check_for_pattern(fp, "AnonHugePages:", buffer)) + goto err_out; + + if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) + ksft_exit_fail_msg("Reading smap error\n"); + +err_out: + fclose(fp); + return thp; +} diff --git a/tools/testing/selftests/vm/vm_util.h b/tools/testing/selftests/vm/vm_util.h new file mode 100644 index 000000000000..2e512bd57ae1 --- /dev/null +++ b/tools/testing/selftests/vm/vm_util.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <stdint.h> +#include <stdbool.h> + +uint64_t pagemap_get_entry(int fd, char *start); +bool pagemap_is_softdirty(int fd, char *start); +void clear_softdirty(void); +uint64_t read_pmd_pagesize(void); +uint64_t check_huge(void *addr); diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index b1ed76d9a979..381dcc00cb62 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -80,9 +80,10 @@ #define KPF_SOFTDIRTY 40 #define KPF_ARCH_2 41 -/* [48-] take some arbitrary free slots for expanding overloaded flags +/* [47-] take some arbitrary free slots for expanding overloaded flags * not part of kernel API */ +#define KPF_ANON_EXCLUSIVE 47 #define KPF_READAHEAD 48 #define KPF_SLOB_FREE 49 #define KPF_SLUB_FROZEN 50 @@ -138,6 +139,7 @@ static const char * const page_flag_names[] = { [KPF_SOFTDIRTY] = "f:softdirty", [KPF_ARCH_2] = "H:arch_2", + [KPF_ANON_EXCLUSIVE] = "d:anon_exclusive", [KPF_READAHEAD] = "I:readahead", [KPF_SLOB_FREE] = "P:slob_free", [KPF_SLUB_FROZEN] = "A:slub_frozen", @@ -472,6 +474,10 @@ static int bit_mask_ok(uint64_t flags) static uint64_t expand_overloaded_flags(uint64_t flags, uint64_t pme) { + /* Anonymous pages overload PG_mappedtodisk */ + if ((flags & BIT(ANON)) && (flags & BIT(MAPPEDTODISK))) + flags ^= BIT(MAPPEDTODISK) | BIT(ANON_EXCLUSIVE); + /* SLOB/SLUB overload several page flags */ if (flags & BIT(SLAB)) { if (flags & BIT(PRIVATE)) diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c index 7d98e76c2291..c149427eb1c9 100644 --- a/tools/vm/page_owner_sort.c +++ b/tools/vm/page_owner_sort.c @@ -39,6 +39,7 @@ struct block_list { int page_num; pid_t pid; pid_t tgid; + int allocator; }; enum FILTER_BIT { FILTER_UNRELEASE = 1<<1, @@ -51,14 +52,39 @@ enum CULL_BIT { CULL_PID = 1<<2, CULL_TGID = 1<<3, CULL_COMM = 1<<4, - CULL_STACKTRACE = 1<<5 + CULL_STACKTRACE = 1<<5, + CULL_ALLOCATOR = 1<<6 +}; +enum ALLOCATOR_BIT { + ALLOCATOR_CMA = 1<<1, + ALLOCATOR_SLAB = 1<<2, + ALLOCATOR_VMALLOC = 1<<3, + ALLOCATOR_OTHERS = 1<<4 +}; +enum ARG_TYPE { + ARG_TXT, ARG_COMM, ARG_STACKTRACE, ARG_ALLOC_TS, ARG_FREE_TS, + ARG_CULL_TIME, ARG_PAGE_NUM, ARG_PID, ARG_TGID, ARG_UNKNOWN, ARG_FREE, + ARG_ALLOCATOR +}; +enum SORT_ORDER { + SORT_ASC = 1, + SORT_DESC = -1, }; struct filter_condition { - pid_t tgid; - pid_t pid; - char comm[TASK_COMM_LEN]; + pid_t *pids; + pid_t *tgids; + char **comms; + int pids_size; + int tgids_size; + int comms_size; +}; +struct sort_condition { + int (**cmps)(const void *, const void *); + int *signs; + int size; }; static struct filter_condition fc; +static struct sort_condition sc; static regex_t order_pattern; static regex_t pid_pattern; static regex_t tgid_pattern; @@ -70,16 +96,22 @@ static int list_size; static int max_size; static int cull; static int filter; +static bool debug_on; -int read_block(char *buf, int buf_size, FILE *fin) +static void set_single_cmp(int (*cmp)(const void *, const void *), int sign); + +int read_block(char *buf, char *ext_buf, int buf_size, FILE *fin) { char *curr = buf, *const buf_end = buf + buf_size; while (buf_end - curr > 1 && fgets(curr, buf_end - curr, fin)) { - if (*curr == '\n') /* empty line */ + if (*curr == '\n') { /* empty line */ return curr - buf; - if (!strncmp(curr, "PFN", 3)) + } + if (!strncmp(curr, "PFN", 3)) { + strcpy(ext_buf, curr); continue; + } curr += strlen(curr); } @@ -104,14 +136,14 @@ static int compare_num(const void *p1, const void *p2) { const struct block_list *l1 = p1, *l2 = p2; - return l2->num - l1->num; + return l1->num - l2->num; } static int compare_page_num(const void *p1, const void *p2) { const struct block_list *l1 = p1, *l2 = p2; - return l2->page_num - l1->page_num; + return l1->page_num - l2->page_num; } static int compare_pid(const void *p1, const void *p2) @@ -128,6 +160,13 @@ static int compare_tgid(const void *p1, const void *p2) return l1->tgid - l2->tgid; } +static int compare_allocator(const void *p1, const void *p2) +{ + const struct block_list *l1 = p1, *l2 = p2; + + return l1->allocator - l2->allocator; +} + static int compare_comm(const void *p1, const void *p2) { const struct block_list *l1 = p1, *l2 = p2; @@ -149,7 +188,6 @@ static int compare_free_ts(const void *p1, const void *p2) return l1->free_ts_nsec < l2->free_ts_nsec ? -1 : 1; } - static int compare_release(const void *p1, const void *p2) { const struct block_list *l1 = p1, *l2 = p2; @@ -161,7 +199,6 @@ static int compare_release(const void *p1, const void *p2) return l1->free_ts_nsec ? 1 : -1; } - static int compare_cull_condition(const void *p1, const void *p2) { if (cull == 0) @@ -176,9 +213,21 @@ static int compare_cull_condition(const void *p1, const void *p2) return compare_comm(p1, p2); if ((cull & CULL_UNRELEASE) && compare_release(p1, p2)) return compare_release(p1, p2); + if ((cull & CULL_ALLOCATOR) && compare_allocator(p1, p2)) + return compare_allocator(p1, p2); return 0; } +static int compare_sort_condition(const void *p1, const void *p2) +{ + int cmp = 0; + + for (int i = 0; i < sc.size; ++i) + if (cmp == 0) + cmp = sc.signs[i] * sc.cmps[i](p1, p2); + return cmp; +} + static int search_pattern(regex_t *pattern, char *pattern_str, char *buf) { int err, val_len; @@ -186,7 +235,8 @@ static int search_pattern(regex_t *pattern, char *pattern_str, char *buf) err = regexec(pattern, buf, 2, pmatch, REG_NOTBOL); if (err != 0 || pmatch[1].rm_so == -1) { - printf("no matching pattern in %s\n", buf); + if (debug_on) + fprintf(stderr, "no matching pattern in %s\n", buf); return -1; } val_len = pmatch[1].rm_eo - pmatch[1].rm_so; @@ -202,7 +252,7 @@ static void check_regcomp(regex_t *pattern, const char *regex) err = regcomp(pattern, regex, REG_EXTENDED | REG_NEWLINE); if (err != 0 || pattern->re_nsub != 1) { - printf("Invalid pattern %s code %d\n", regex, err); + fprintf(stderr, "Invalid pattern %s code %d\n", regex, err); exit(1); } } @@ -251,7 +301,8 @@ static int get_page_num(char *buf) errno = 0; order_val = strtol(order_str, &endptr, 10); if (order_val > 64 || errno != 0 || endptr == order_str || *endptr != '\0') { - printf("wrong order in follow buf:\n%s\n", buf); + if (debug_on) + fprintf(stderr, "wrong order in follow buf:\n%s\n", buf); return 0; } @@ -268,7 +319,8 @@ static pid_t get_pid(char *buf) errno = 0; pid = strtol(pid_str, &endptr, 10); if (errno != 0 || endptr == pid_str || *endptr != '\0') { - printf("wrong/invalid pid in follow buf:\n%s\n", buf); + if (debug_on) + fprintf(stderr, "wrong/invalid pid in follow buf:\n%s\n", buf); return -1; } @@ -286,7 +338,8 @@ static pid_t get_tgid(char *buf) errno = 0; tgid = strtol(tgid_str, &endptr, 10); if (errno != 0 || endptr == tgid_str || *endptr != '\0') { - printf("wrong/invalid tgid in follow buf:\n%s\n", buf); + if (debug_on) + fprintf(stderr, "wrong/invalid tgid in follow buf:\n%s\n", buf); return -1; } @@ -304,7 +357,8 @@ static __u64 get_ts_nsec(char *buf) errno = 0; ts_nsec = strtoull(ts_nsec_str, &endptr, 10); if (errno != 0 || endptr == ts_nsec_str || *endptr != '\0') { - printf("wrong ts_nsec in follow buf:\n%s\n", buf); + if (debug_on) + fprintf(stderr, "wrong ts_nsec in follow buf:\n%s\n", buf); return -1; } @@ -321,7 +375,8 @@ static __u64 get_free_ts_nsec(char *buf) errno = 0; free_ts_nsec = strtoull(free_ts_nsec_str, &endptr, 10); if (errno != 0 || endptr == free_ts_nsec_str || *endptr != '\0') { - printf("wrong free_ts_nsec in follow buf:\n%s\n", buf); + if (debug_on) + fprintf(stderr, "wrong free_ts_nsec in follow buf:\n%s\n", buf); return -1; } @@ -337,33 +392,104 @@ static char *get_comm(char *buf) search_pattern(&comm_pattern, comm_str, buf); errno = 0; if (errno != 0) { - printf("wrong comm in follow buf:\n%s\n", buf); + if (debug_on) + fprintf(stderr, "wrong comm in follow buf:\n%s\n", buf); return NULL; } return comm_str; } +static int get_arg_type(const char *arg) +{ + if (!strcmp(arg, "pid") || !strcmp(arg, "p")) + return ARG_PID; + else if (!strcmp(arg, "tgid") || !strcmp(arg, "tg")) + return ARG_TGID; + else if (!strcmp(arg, "name") || !strcmp(arg, "n")) + return ARG_COMM; + else if (!strcmp(arg, "stacktrace") || !strcmp(arg, "st")) + return ARG_STACKTRACE; + else if (!strcmp(arg, "free") || !strcmp(arg, "f")) + return ARG_FREE; + else if (!strcmp(arg, "txt") || !strcmp(arg, "T")) + return ARG_TXT; + else if (!strcmp(arg, "free_ts") || !strcmp(arg, "ft")) + return ARG_FREE_TS; + else if (!strcmp(arg, "alloc_ts") || !strcmp(arg, "at")) + return ARG_ALLOC_TS; + else if (!strcmp(arg, "allocator") || !strcmp(arg, "ator")) + return ARG_ALLOCATOR; + else { + return ARG_UNKNOWN; + } +} + +static int get_allocator(const char *buf, const char *migrate_info) +{ + char *tmp, *first_line, *second_line; + int allocator = 0; + + if (strstr(migrate_info, "CMA")) + allocator |= ALLOCATOR_CMA; + if (strstr(migrate_info, "slab")) + allocator |= ALLOCATOR_SLAB; + tmp = strstr(buf, "__vmalloc_node_range"); + if (tmp) { + second_line = tmp; + while (*tmp != '\n') + tmp--; + tmp--; + while (*tmp != '\n') + tmp--; + first_line = ++tmp; + tmp = strstr(tmp, "alloc_pages"); + if (tmp && first_line <= tmp && tmp < second_line) + allocator |= ALLOCATOR_VMALLOC; + } + if (allocator == 0) + allocator = ALLOCATOR_OTHERS; + return allocator; +} + +static bool match_num_list(int num, int *list, int list_size) +{ + for (int i = 0; i < list_size; ++i) + if (list[i] == num) + return true; + return false; +} + +static bool match_str_list(const char *str, char **list, int list_size) +{ + for (int i = 0; i < list_size; ++i) + if (!strcmp(list[i], str)) + return true; + return false; +} + static bool is_need(char *buf) { if ((filter & FILTER_UNRELEASE) && get_free_ts_nsec(buf) != 0) return false; - if ((filter & FILTER_PID) && get_pid(buf) != fc.pid) + if ((filter & FILTER_PID) && !match_num_list(get_pid(buf), fc.pids, fc.pids_size)) return false; - if ((filter & FILTER_TGID) && get_tgid(buf) != fc.tgid) + if ((filter & FILTER_TGID) && + !match_num_list(get_tgid(buf), fc.tgids, fc.tgids_size)) return false; char *comm = get_comm(buf); if ((filter & FILTER_COMM) && - strncmp(comm, fc.comm, TASK_COMM_LEN) != 0) { + !match_str_list(comm, fc.comms, fc.comms_size)) { free(comm); return false; } + free(comm); return true; } -static void add_list(char *buf, int len) +static void add_list(char *buf, int len, char *ext_buf) { if (list_size != 0 && len == list[list_size-1].len && @@ -373,7 +499,7 @@ static void add_list(char *buf, int len) return; } if (list_size == max_size) { - printf("max_size too small??\n"); + fprintf(stderr, "max_size too small??\n"); exit(1); } if (!is_need(buf)) @@ -383,7 +509,7 @@ static void add_list(char *buf, int len) list[list_size].comm = get_comm(buf); list[list_size].txt = malloc(len+1); if (!list[list_size].txt) { - printf("Out of memory\n"); + fprintf(stderr, "Out of memory\n"); exit(1); } memcpy(list[list_size].txt, buf, len); @@ -397,6 +523,7 @@ static void add_list(char *buf, int len) list[list_size].stacktrace++; list[list_size].ts_nsec = get_ts_nsec(buf); list[list_size].free_ts_nsec = get_free_ts_nsec(buf); + list[list_size].allocator = get_allocator(buf, ext_buf); list_size++; if (list_size % 1000 == 0) { printf("loaded %d\r", list_size); @@ -409,25 +536,130 @@ static bool parse_cull_args(const char *arg_str) int size = 0; char **args = explode(',', arg_str, &size); - for (int i = 0; i < size; ++i) - if (!strcmp(args[i], "pid") || !strcmp(args[i], "p")) + for (int i = 0; i < size; ++i) { + int arg_type = get_arg_type(args[i]); + + if (arg_type == ARG_PID) cull |= CULL_PID; - else if (!strcmp(args[i], "tgid") || !strcmp(args[i], "tg")) + else if (arg_type == ARG_TGID) cull |= CULL_TGID; - else if (!strcmp(args[i], "name") || !strcmp(args[i], "n")) + else if (arg_type == ARG_COMM) cull |= CULL_COMM; - else if (!strcmp(args[i], "stacktrace") || !strcmp(args[i], "st")) + else if (arg_type == ARG_STACKTRACE) cull |= CULL_STACKTRACE; - else if (!strcmp(args[i], "free") || !strcmp(args[i], "f")) + else if (arg_type == ARG_FREE) cull |= CULL_UNRELEASE; + else if (arg_type == ARG_ALLOCATOR) + cull |= CULL_ALLOCATOR; else { free_explode(args, size); return false; } + } free_explode(args, size); + if (sc.size == 0) + set_single_cmp(compare_num, SORT_DESC); return true; } +static void set_single_cmp(int (*cmp)(const void *, const void *), int sign) +{ + if (sc.signs == NULL || sc.size < 1) + sc.signs = calloc(1, sizeof(int)); + sc.signs[0] = sign; + if (sc.cmps == NULL || sc.size < 1) + sc.cmps = calloc(1, sizeof(int *)); + sc.cmps[0] = cmp; + sc.size = 1; +} + +static bool parse_sort_args(const char *arg_str) +{ + int size = 0; + + if (sc.size != 0) { /* reset sort_condition */ + free(sc.signs); + free(sc.cmps); + size = 0; + } + + char **args = explode(',', arg_str, &size); + + sc.signs = calloc(size, sizeof(int)); + sc.cmps = calloc(size, sizeof(int *)); + for (int i = 0; i < size; ++i) { + int offset = 0; + + sc.signs[i] = SORT_ASC; + if (args[i][0] == '-' || args[i][0] == '+') { + if (args[i][0] == '-') + sc.signs[i] = SORT_DESC; + offset = 1; + } + + int arg_type = get_arg_type(args[i]+offset); + + if (arg_type == ARG_PID) + sc.cmps[i] = compare_pid; + else if (arg_type == ARG_TGID) + sc.cmps[i] = compare_tgid; + else if (arg_type == ARG_COMM) + sc.cmps[i] = compare_comm; + else if (arg_type == ARG_STACKTRACE) + sc.cmps[i] = compare_stacktrace; + else if (arg_type == ARG_ALLOC_TS) + sc.cmps[i] = compare_ts; + else if (arg_type == ARG_FREE_TS) + sc.cmps[i] = compare_free_ts; + else if (arg_type == ARG_TXT) + sc.cmps[i] = compare_txt; + else if (arg_type == ARG_ALLOCATOR) + sc.cmps[i] = compare_allocator; + else { + free_explode(args, size); + sc.size = 0; + return false; + } + } + sc.size = size; + free_explode(args, size); + return true; +} + +static int *parse_nums_list(char *arg_str, int *list_size) +{ + int size = 0; + char **args = explode(',', arg_str, &size); + int *list = calloc(size, sizeof(int)); + + errno = 0; + for (int i = 0; i < size; ++i) { + char *endptr = NULL; + + list[i] = strtol(args[i], &endptr, 10); + if (errno != 0 || endptr == args[i] || *endptr != '\0') { + free(list); + return NULL; + } + } + *list_size = size; + free_explode(args, size); + return list; +} + +static void print_allocator(FILE *out, int allocator) +{ + fprintf(out, "allocated by "); + if (allocator & ALLOCATOR_CMA) + fprintf(out, "CMA "); + if (allocator & ALLOCATOR_SLAB) + fprintf(out, "SLAB "); + if (allocator & ALLOCATOR_VMALLOC) + fprintf(out, "VMALLOC "); + if (allocator & ALLOCATOR_OTHERS) + fprintf(out, "OTHERS "); +} + #define BUF_SIZE (128 * 1024) static void usage(void) @@ -442,19 +674,20 @@ static void usage(void) "-a\t\tSort by memory allocate time.\n" "-r\t\tSort by memory release time.\n" "-f\t\tFilter out the information of blocks whose memory has been released.\n" - "--pid <PID>\tSelect by pid. This selects the information of blocks whose process ID number equals to <PID>.\n" - "--tgid <TGID>\tSelect by tgid. This selects the information of blocks whose Thread Group ID number equals to <TGID>.\n" - "--name <command>\n\t\tSelect by command name. This selects the information of blocks whose command name identical to <command>.\n" - "--cull <rules>\tCull by user-defined rules. <rules> is a single argument in the form of a comma-separated list with some common fields predefined\n" + "-d\t\tPrint debug information.\n" + "--pid <pidlist>\tSelect by pid. This selects the information of blocks whose process ID numbers appear in <pidlist>.\n" + "--tgid <tgidlist>\tSelect by tgid. This selects the information of blocks whose Thread Group ID numbers appear in <tgidlist>.\n" + "--name <cmdlist>\n\t\tSelect by command name. This selects the information of blocks whose command name appears in <cmdlist>.\n" + "--cull <rules>\tCull by user-defined rules.<rules> is a single argument in the form of a comma-separated list with some common fields predefined\n" + "--sort <order>\tSpecify sort order as: [+|-]key[,[+|-]key[,...]]\n" ); } int main(int argc, char **argv) { - int (*cmp)(const void *, const void *) = compare_num; FILE *fin, *fout; - char *buf, *endptr; - int ret, i, count; + char *buf, *ext_buf; + int i, count; struct stat st; int opt; struct option longopts[] = { @@ -462,64 +695,74 @@ int main(int argc, char **argv) { "tgid", required_argument, NULL, 2 }, { "name", required_argument, NULL, 3 }, { "cull", required_argument, NULL, 4 }, + { "sort", required_argument, NULL, 5 }, { 0, 0, 0, 0}, }; - while ((opt = getopt_long(argc, argv, "afmnprstP", longopts, NULL)) != -1) + while ((opt = getopt_long(argc, argv, "adfmnprstP", longopts, NULL)) != -1) switch (opt) { case 'a': - cmp = compare_ts; + set_single_cmp(compare_ts, SORT_ASC); + break; + case 'd': + debug_on = true; break; case 'f': filter = filter | FILTER_UNRELEASE; break; case 'm': - cmp = compare_page_num; + set_single_cmp(compare_page_num, SORT_DESC); break; case 'p': - cmp = compare_pid; + set_single_cmp(compare_pid, SORT_ASC); break; case 'r': - cmp = compare_free_ts; + set_single_cmp(compare_free_ts, SORT_ASC); break; case 's': - cmp = compare_stacktrace; + set_single_cmp(compare_stacktrace, SORT_ASC); break; case 't': - cmp = compare_num; + set_single_cmp(compare_num, SORT_DESC); break; case 'P': - cmp = compare_tgid; + set_single_cmp(compare_tgid, SORT_ASC); break; case 'n': - cmp = compare_comm; + set_single_cmp(compare_comm, SORT_ASC); break; case 1: filter = filter | FILTER_PID; - errno = 0; - fc.pid = strtol(optarg, &endptr, 10); - if (errno != 0 || endptr == optarg || *endptr != '\0') { - printf("wrong/invalid pid in from the command line:%s\n", optarg); + fc.pids = parse_nums_list(optarg, &fc.pids_size); + if (fc.pids == NULL) { + fprintf(stderr, "wrong/invalid pid in from the command line:%s\n", + optarg); exit(1); } break; case 2: filter = filter | FILTER_TGID; - errno = 0; - fc.tgid = strtol(optarg, &endptr, 10); - if (errno != 0 || endptr == optarg || *endptr != '\0') { - printf("wrong/invalid tgid in from the command line:%s\n", optarg); + fc.tgids = parse_nums_list(optarg, &fc.tgids_size); + if (fc.tgids == NULL) { + fprintf(stderr, "wrong/invalid tgid in from the command line:%s\n", + optarg); exit(1); } break; case 3: filter = filter | FILTER_COMM; - strncpy(fc.comm, optarg, TASK_COMM_LEN); - fc.comm[TASK_COMM_LEN-1] = '\0'; + fc.comms = explode(',', optarg, &fc.comms_size); break; case 4: if (!parse_cull_args(optarg)) { - printf("wrong argument after --cull in from the command line:%s\n", + fprintf(stderr, "wrong argument after --cull option:%s\n", + optarg); + exit(1); + } + break; + case 5: + if (!parse_sort_args(optarg)) { + fprintf(stderr, "wrong argument after --sort option:%s\n", optarg); exit(1); } @@ -553,17 +796,18 @@ int main(int argc, char **argv) list = malloc(max_size * sizeof(*list)); buf = malloc(BUF_SIZE); - if (!list || !buf) { - printf("Out of memory\n"); + ext_buf = malloc(BUF_SIZE); + if (!list || !buf || !ext_buf) { + fprintf(stderr, "Out of memory\n"); exit(1); } for ( ; ; ) { - ret = read_block(buf, BUF_SIZE, fin); - if (ret < 0) - break; + int buf_len = read_block(buf, ext_buf, BUF_SIZE, fin); - add_list(buf, ret); + if (buf_len < 0) + break; + add_list(buf, buf_len, ext_buf); } printf("loaded %d\n", list_size); @@ -584,12 +828,14 @@ int main(int argc, char **argv) } } - qsort(list, count, sizeof(list[0]), cmp); + qsort(list, count, sizeof(list[0]), compare_sort_condition); for (i = 0; i < count; i++) { - if (cull == 0) - fprintf(fout, "%d times, %d pages:\n%s\n", - list[i].num, list[i].page_num, list[i].txt); + if (cull == 0) { + fprintf(fout, "%d times, %d pages, ", list[i].num, list[i].page_num); + print_allocator(fout, list[i].allocator); + fprintf(fout, ":\n%s\n", list[i].txt); + } else { fprintf(fout, "%d times, %d pages", list[i].num, list[i].page_num); @@ -599,6 +845,10 @@ int main(int argc, char **argv) fprintf(fout, ", TGID %d", list[i].pid); if (cull & CULL_COMM || filter & FILTER_COMM) fprintf(fout, ", task_comm_name: %s", list[i].comm); + if (cull & CULL_ALLOCATOR) { + fprintf(fout, ", "); + print_allocator(fout, list[i].allocator); + } if (cull & CULL_UNRELEASE) fprintf(fout, " (%s)", list[i].free_ts_nsec ? "UNRELEASED" : "RELEASED"); |