diff options
323 files changed, 7350 insertions, 4391 deletions
diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst index 678d70d6e1c3..714a5171bfc0 100644 --- a/Documentation/admin-guide/blockdev/zram.rst +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -47,6 +47,8 @@ The list of possible return codes: -ENOMEM zram was not able to allocate enough memory to fulfil your needs. -EINVAL invalid input has been provided. +-EAGAIN re-try operation later (e.g. when attempting to run recompress + and writeback simultaneously). ======== ============================================================= If you use 'echo', the returned value is set by the 'echo' utility, diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index 270501db9f4e..286d16fc22eb 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -90,9 +90,7 @@ Brief summary of control files. used. memory.swappiness set/show swappiness parameter of vmscan (See sysctl's vm.swappiness) - memory.move_charge_at_immigrate set/show controls of moving charges - This knob is deprecated and shouldn't be - used. + memory.move_charge_at_immigrate This knob is deprecated. memory.oom_control set/show oom controls. This knob is deprecated and shouldn't be used. @@ -243,10 +241,6 @@ behind this approach is that a cgroup that aggressively uses a shared page will eventually get charged for it (once it is uncharged from the cgroup that brought it in -- this will happen on memory pressure). -But see :ref:`section 8.2 <cgroup-v1-memory-movable-charges>` when moving a -task to another cgroup, its pages may be recharged to the new cgroup, if -move_charge_at_immigrate has been chosen. - 2.4 Swap Extension -------------------------------------- @@ -756,78 +750,8 @@ If we want to change this to 1G, we can at any time use:: THIS IS DEPRECATED! -It's expensive and unreliable! It's better practice to launch workload -tasks directly from inside their target cgroup. Use dedicated workload -cgroups to allow fine-grained policy adjustments without having to -move physical pages between control domains. - -Users can move charges associated with a task along with task migration, that -is, uncharge task's pages from the old cgroup and charge them to the new cgroup. -This feature is not supported in !CONFIG_MMU environments because of lack of -page tables. - -8.1 Interface -------------- - -This feature is disabled by default. It can be enabled (and disabled again) by -writing to memory.move_charge_at_immigrate of the destination cgroup. - -If you want to enable it:: - - # echo (some positive value) > memory.move_charge_at_immigrate - -.. note:: - Each bits of move_charge_at_immigrate has its own meaning about what type - of charges should be moved. See :ref:`section 8.2 - <cgroup-v1-memory-movable-charges>` for details. - -.. note:: - Charges are moved only when you move mm->owner, in other words, - a leader of a thread group. - -.. note:: - If we cannot find enough space for the task in the destination cgroup, we - try to make space by reclaiming memory. Task migration may fail if we - cannot make enough space. - -.. note:: - It can take several seconds if you move charges much. - -And if you want disable it again:: - - # echo 0 > memory.move_charge_at_immigrate - -.. _cgroup-v1-memory-movable-charges: - -8.2 Type of charges which can be moved --------------------------------------- - -Each bit in move_charge_at_immigrate has its own meaning about what type of -charges should be moved. But in any case, it must be noted that an account of -a page or a swap can be moved only when it is charged to the task's current -(old) memory cgroup. - -+---+--------------------------------------------------------------------------+ -|bit| what type of charges would be moved ? | -+===+==========================================================================+ -| 0 | A charge of an anonymous page (or swap of it) used by the target task. | -| | You must enable Swap Extension (see 2.4) to enable move of swap charges. | -+---+--------------------------------------------------------------------------+ -| 1 | A charge of file pages (normal file, tmpfs file (e.g. ipc shared memory) | -| | and swaps of tmpfs file) mmapped by the target task. Unlike the case of | -| | anonymous pages, file pages (and swaps) in the range mmapped by the task | -| | will be moved even if the task hasn't done page fault, i.e. they might | -| | not be the task's "RSS", but other task's "RSS" that maps the same file. | -| | The mapcount of the page is ignored (the page can be moved independent | -| | of the mapcount). You must enable Swap Extension (see 2.4) to | -| | enable move of swap charges. | -+---+--------------------------------------------------------------------------+ - -8.3 TODO --------- - -- All of moving charge operations are done under cgroup_mutex. It's not good - behavior to hold the mutex too long, so we may need some trick. +Reading memory.move_charge_at_immigrate will always return 0 and writing +to it will always return -EINVAL. 9. Memory thresholds ==================== diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 2cb58daf3089..315ede811c9d 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1655,6 +1655,11 @@ The following nested keys are defined. pgdemote_khugepaged Number of pages demoted by khugepaged. + hugetlb + Amount of memory used by hugetlb pages. This metric only shows + up if hugetlb usage is accounted for in memory.current (i.e. + cgroup is mounted with the memory_hugetlb_accounting option). + memory.numa_stat A read-only nested-keyed file which exists on non-root cgroups. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9cd9cd06538b..a4736ee87b1a 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6711,6 +6711,16 @@ Force threading of all interrupt handlers except those marked explicitly IRQF_NO_THREAD. + thp_shmem= [KNL] + Format: <size>[KMG],<size>[KMG]:<policy>;<size>[KMG]-<size>[KMG]:<policy> + Control the default policy of each hugepage size for the + internal shmem mount. <policy> is one of policies available + for the shmem mount ("always", "inherit", "never", "within_size", + and "advise"). + It can be used multiple times for multiple shmem THP sizes. + See Documentation/admin-guide/mm/transhuge.rst for more + details. + topology= [S390,EARLY] Format: {off | on} Specify if the kernel should make use of the cpu @@ -6952,6 +6962,13 @@ See Documentation/admin-guide/mm/transhuge.rst for more details. + transparent_hugepage_shmem= [KNL] + Format: [always|within_size|advise|never|deny|force] + Can be used to control the hugepage allocation policy for + the internal shmem mount. + See Documentation/admin-guide/mm/transhuge.rst + for more details. + trusted.source= [KEYS] Format: <string> This parameter identifies the trust source as a backend diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index a1bb495eab59..5034915f4e8e 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -326,6 +326,29 @@ PMD_ORDER THP policy will be overridden. If the policy for PMD_ORDER is not defined within a valid ``thp_anon``, its policy will default to ``never``. +Similarly to ``transparent_hugepage``, you can control the hugepage +allocation policy for the internal shmem mount by using the kernel parameter +``transparent_hugepage_shmem=<policy>``, where ``<policy>`` is one of the +seven valid policies for shmem (``always``, ``within_size``, ``advise``, +``never``, ``deny``, and ``force``). + +In the same manner as ``thp_anon`` controls each supported anonymous THP +size, ``thp_shmem`` controls each supported shmem THP size. ``thp_shmem`` +has the same format as ``thp_anon``, but also supports the policy +``within_size``. + +``thp_shmem=`` may be specified multiple times to configure all THP sizes +as required. If ``thp_shmem=`` is specified at least once, any shmem THP +sizes not explicitly configured on the command line are implicitly set to +``never``. + +``transparent_hugepage_shmem`` setting only affects the global toggle. If +``thp_shmem`` is not specified, PMD_ORDER hugepage will default to +``inherit``. However, if a valid ``thp_shmem`` setting is provided by the +user, the PMD_ORDER hugepage policy will be overridden. If the policy for +PMD_ORDER is not defined within a valid ``thp_shmem``, its policy will +default to ``never``. + Hugepages in tmpfs/shmem ======================== @@ -530,10 +553,18 @@ anon_fault_fallback_charge instead falls back to using huge pages with lower orders or small pages even though the allocation was successful. -swpout - is incremented every time a huge page is swapped out in one +zswpout + is incremented every time a huge page is swapped out to zswap in one piece without splitting. +swpin + is incremented every time a huge page is swapped in from a non-zswap + swap device in one piece. + +swpout + is incremented every time a huge page is swapped out to a non-zswap + swap device in one piece without splitting. + swpout_fallback is incremented if a huge page has to be split before swapout. Usually because failed to allocate some continuous swap space diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index d7de44f5339d..0a1418ab72fd 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -511,19 +511,14 @@ Tests ~~~~~ There are KASAN tests that allow verifying that KASAN works and can detect -certain types of memory corruptions. The tests consist of two parts: +certain types of memory corruptions. -1. Tests that are integrated with the KUnit Test Framework. Enabled with -``CONFIG_KASAN_KUNIT_TEST``. These tests can be run and partially verified +All KASAN tests are integrated with the KUnit Test Framework and can be enabled +via ``CONFIG_KASAN_KUNIT_TEST``. The tests can be run and partially verified automatically in a few different ways; see the instructions below. -2. Tests that are currently incompatible with KUnit. Enabled with -``CONFIG_KASAN_MODULE_TEST`` and can only be run as a module. These tests can -only be verified manually by loading the kernel module and inspecting the -kernel log for KASAN reports. - -Each KUnit-compatible KASAN test prints one of multiple KASAN reports if an -error is detected. Then the test prints its number and status. +Each KASAN test prints one of multiple KASAN reports if an error is detected. +Then the test prints its number and status. When a test passes:: @@ -550,16 +545,16 @@ Or, if one of the tests failed:: not ok 1 - kasan -There are a few ways to run KUnit-compatible KASAN tests. +There are a few ways to run the KASAN tests. 1. Loadable module - With ``CONFIG_KUNIT`` enabled, KASAN-KUnit tests can be built as a loadable - module and run by loading ``kasan_test.ko`` with ``insmod`` or ``modprobe``. + With ``CONFIG_KUNIT`` enabled, the tests can be built as a loadable module + and run by loading ``kasan_test.ko`` with ``insmod`` or ``modprobe``. 2. Built-In - With ``CONFIG_KUNIT`` built-in, KASAN-KUnit tests can be built-in as well. + With ``CONFIG_KUNIT`` built-in, the tests can be built-in as well. In this case, the tests will run at boot as a late-init call. 3. Using kunit_tool diff --git a/Documentation/dev-tools/kmemleak.rst b/Documentation/dev-tools/kmemleak.rst index 2cb00b53339f..7d784e03f3f9 100644 --- a/Documentation/dev-tools/kmemleak.rst +++ b/Documentation/dev-tools/kmemleak.rst @@ -161,6 +161,7 @@ See the include/linux/kmemleak.h header for the functions prototype. - ``kmemleak_free_percpu`` - notify of a percpu memory block freeing - ``kmemleak_update_trace`` - update object allocation stack trace - ``kmemleak_not_leak`` - mark an object as not a leak +- ``kmemleak_transient_leak`` - mark an object as a transient leak - ``kmemleak_ignore`` - do not scan or report an object as leak - ``kmemleak_scan_area`` - add scan areas inside a memory block - ``kmemleak_no_scan`` - do not scan a memory block diff --git a/Documentation/mm/allocation-profiling.rst b/Documentation/mm/allocation-profiling.rst index ffd6655b7be2..316311240e6a 100644 --- a/Documentation/mm/allocation-profiling.rst +++ b/Documentation/mm/allocation-profiling.rst @@ -18,12 +18,17 @@ kconfig options: missing annotation Boot parameter: - sysctl.vm.mem_profiling=0|1|never + sysctl.vm.mem_profiling={0|1|never}[,compressed] When set to "never", memory allocation profiling overhead is minimized and it cannot be enabled at runtime (sysctl becomes read-only). When CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=y, default value is "1". When CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT=n, default value is "never". + "compressed" optional parameter will try to store page tag references in a + compact format, avoiding page extensions. This results in improved performance + and memory consumption, however it might fail depending on system configuration. + If compression fails, a warning is issued and memory allocation profiling gets + disabled. sysctl: /proc/sys/vm/mem_profiling diff --git a/Documentation/mm/damon/index.rst b/Documentation/mm/damon/index.rst index dafd6d028924..5a3359704cce 100644 --- a/Documentation/mm/damon/index.rst +++ b/Documentation/mm/damon/index.rst @@ -37,3 +37,9 @@ with no code but simple configurations. To utilize and control DAMON from the user-space, please refer to the administration :doc:`guide </admin-guide/mm/damon/index>`. + +If you prefer academic papers for reading and citations, please use the papers +from `HPDC'22 <https://dl.acm.org/doi/abs/10.1145/3502181.3531466>`_ and +`Middleware19 Industry <https://dl.acm.org/doi/abs/10.1145/3366626.3368125>`_ . +Note that those cover DAMON implementations in Linux v5.16 and v5.15, +respectively. diff --git a/Documentation/mm/split_page_table_lock.rst b/Documentation/mm/split_page_table_lock.rst index e4f6972eb6c0..581446d4a4eb 100644 --- a/Documentation/mm/split_page_table_lock.rst +++ b/Documentation/mm/split_page_table_lock.rst @@ -16,9 +16,13 @@ There are helpers to lock/unlock a table and other accessor functions: - pte_offset_map_lock() maps PTE and takes PTE table lock, returns pointer to PTE with pointer to its PTE table lock, or returns NULL if no PTE table; - - pte_offset_map_nolock() + - pte_offset_map_ro_nolock() maps PTE, returns pointer to PTE with pointer to its PTE table lock (not taken), or returns NULL if no PTE table; + - pte_offset_map_rw_nolock() + maps PTE, returns pointer to PTE with pointer to its PTE table + lock (not taken) and the value of its pmd entry, or returns NULL + if no PTE table; - pte_offset_map() maps PTE, returns pointer to PTE, or returns NULL if no PTE table; - pte_unmap() diff --git a/Documentation/translations/zh_CN/dev-tools/kasan.rst b/Documentation/translations/zh_CN/dev-tools/kasan.rst index 4491ad2830ed..fd2e3afbdfad 100644 --- a/Documentation/translations/zh_CN/dev-tools/kasan.rst +++ b/Documentation/translations/zh_CN/dev-tools/kasan.rst @@ -422,16 +422,12 @@ KASAN连接到vmap基础架构以懒清理未使用的影子内存。 ~~~~ 有一些KASAN测试可以验证KASAN是否正常工作并可以检测某些类型的内存损坏。 -测试由两部分组成: -1. 与KUnit测试框架集成的测试。使用 ``CONFIG_KASAN_KUNIT_TEST`` 启用。 -这些测试可以通过几种不同的方式自动运行和部分验证；请参阅下面的说明。 +所有 KASAN 测试都与 KUnit 测试框架集成，可通过 ``CONFIG_KASAN_KUNIT_TEST`` 启用。 +测试可以通过几种不同的方式自动运行和部分验证；请参阅以下说明。 -2. 与KUnit不兼容的测试。使用 ``CONFIG_KASAN_MODULE_TEST`` 启用并且只能作为模块 -运行。这些测试只能通过加载内核模块并检查内核日志以获取KASAN报告来手动验证。 - -如果检测到错误，每个KUnit兼容的KASAN测试都会打印多个KASAN报告之一，然后测试打印 -其编号和状态。 +如果检测到错误，每个 KASAN 测试都会打印多份 KASAN 报告中的一份。 +然后测试会打印其编号和状态。 当测试通过:: @@ -458,16 +454,16 @@ KASAN连接到vmap基础架构以懒清理未使用的影子内存。 not ok 1 - kasan -有几种方法可以运行与KUnit兼容的KASAN测试。 +有几种方法可以运行 KASAN 测试。 1. 可加载模块 - 启用 ``CONFIG_KUNIT`` 后，KASAN-KUnit测试可以构建为可加载模块，并通过使用 - ``insmod`` 或 ``modprobe`` 加载 ``kasan_test.ko`` 来运行。 + 启用 ``CONFIG_KUNIT`` 后，可以将测试构建为可加载模块 + 并通过使用 ``insmod`` 或 ``modprobe`` 加载 ``kasan_test.ko`` 来运行。 2. 内置 - 通过内置 ``CONFIG_KUNIT`` ，也可以内置KASAN-KUnit测试。在这种情况下， + 通过内置 ``CONFIG_KUNIT``，测试也可以内置。 测试将在启动时作为后期初始化调用运行。 3. 使用kunit_tool diff --git a/Documentation/translations/zh_TW/dev-tools/kasan.rst b/Documentation/translations/zh_TW/dev-tools/kasan.rst index ed342e67d8ed..27fb7645174d 100644 --- a/Documentation/translations/zh_TW/dev-tools/kasan.rst +++ b/Documentation/translations/zh_TW/dev-tools/kasan.rst @@ -404,16 +404,13 @@ KASAN連接到vmap基礎架構以懶清理未使用的影子內存。 ~~~~ 有一些KASAN測試可以驗證KASAN是否正常工作並可以檢測某些類型的內存損壞。 -測試由兩部分組成: -1. 與KUnit測試框架集成的測試。使用 ``CONFIG_KASAN_KUNIT_TEST`` 啓用。 -這些測試可以通過幾種不同的方式自動運行和部分驗證；請參閱下面的說明。 +所有 KASAN 測試均與 KUnit 測試框架集成，並且可以啟用 +透過 ``CONFIG_KASAN_KUNIT_TEST``。可以運行測試並進行部分驗證 +以幾種不同的方式自動進行；請參閱下面的說明。 -2. 與KUnit不兼容的測試。使用 ``CONFIG_KASAN_MODULE_TEST`` 啓用並且只能作爲模塊 -運行。這些測試只能通過加載內核模塊並檢查內核日誌以獲取KASAN報告來手動驗證。 - -如果檢測到錯誤，每個KUnit兼容的KASAN測試都會打印多個KASAN報告之一，然後測試打印 -其編號和狀態。 +如果偵測到錯誤，每個 KASAN 測試都會列印多個 KASAN 報告之一。 +然後測試列印其編號和狀態。 當測試通過:: @@ -440,16 +437,16 @@ KASAN連接到vmap基礎架構以懶清理未使用的影子內存。 not ok 1 - kasan -有幾種方法可以運行與KUnit兼容的KASAN測試。 +有幾種方法可以執行 KASAN 測試。 1. 可加載模塊 - 啓用 ``CONFIG_KUNIT`` 後，KASAN-KUnit測試可以構建爲可加載模塊，並通過使用 - ``insmod`` 或 ``modprobe`` 加載 ``kasan_test.ko`` 來運行。 + 啟用 ``CONFIG_KUNIT`` 後，測試可以建置為可載入模組 + 並且透過使用 ``insmod`` 或 ``modprobe`` 來載入 ``kasan_test.ko`` 來運作。 2. 內置 - 通過內置 ``CONFIG_KUNIT`` ，也可以內置KASAN-KUnit測試。在這種情況下， + 透過內建 ``CONFIG_KUNIT``，測試也可以內建。 測試將在啓動時作爲後期初始化調用運行。 3. 使用kunit_tool diff --git a/MAINTAINERS b/MAINTAINERS index e40e1220c733..50f7b27a86f4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14957,6 +14957,8 @@ S: Maintained W: http://www.linux-mm.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm T: quilt git://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new +F: Documentation/admin-guide/mm/ +F: Documentation/mm/ F: include/linux/gfp.h F: include/linux/gfp_types.h F: include/linux/memfd.h diff --git a/arch/Kconfig b/arch/Kconfig index de5200eb55d1..9446aad5d605 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1025,6 +1025,14 @@ config ARCH_WANTS_EXECMEM_LATE enough entropy for module space randomization, for instance arm64. +config ARCH_HAS_EXECMEM_ROX + bool + depends on MMU && !HIGHMEM + help + For architectures that support allocations of executable memory + with read-only execute permissions. Architecture must implement + execmem_fill_trapping_insns() callback to enable this. + config HAVE_IRQ_EXIT_ON_IRQ_STACK bool help diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index 396caece6d6d..483965c5a4de 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -5,3 +5,4 @@ generic-y += agp.h generic-y += asm-offsets.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += text-patching.h diff --git a/arch/alpha/include/asm/page.h b/arch/alpha/include/asm/page.h index 261af54fd601..5ec4c77e432e 100644 --- a/arch/alpha/include/asm/page.h +++ b/arch/alpha/include/asm/page.h @@ -14,7 +14,7 @@ extern void clear_page(void *page); #define clear_user_page(page, vaddr, pg) clear_page(page) #define vma_alloc_zeroed_movable_folio(vma, vaddr) \ - vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr) extern void copy_page(void * _to, void * _from); #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index 763929e814e9..1e700468a685 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -78,6 +78,9 @@ #define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ +#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */ +#define MADV_GUARD_REMOVE 103 /* unguard range */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 49285a3ce239..4c69522e0328 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -6,3 +6,4 @@ generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += user.h +generic-y += text-patching.h diff --git a/arch/arm/include/asm/patch.h b/arch/arm/include/asm/text-patching.h index 0b48247c4600..0b48247c4600 100644 --- a/arch/arm/include/asm/patch.h +++ b/arch/arm/include/asm/text-patching.h diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index e61591f33a6c..845acf9ce21e 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -23,7 +23,7 @@ #include <asm/insn.h> #include <asm/set_memory.h> #include <asm/stacktrace.h> -#include <asm/patch.h> +#include <asm/text-patching.h> /* * The compiler emitted profiling hook consists of diff --git a/arch/arm/kernel/jump_label.c b/arch/arm/kernel/jump_label.c index eb9c24b6e8e2..a06a92d0f550 100644 --- a/arch/arm/kernel/jump_label.c +++ b/arch/arm/kernel/jump_label.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/jump_label.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/insn.h> static void __arch_jump_label_transform(struct jump_entry *entry, diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index 22f937e6f3ff..ab76c55fd610 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -15,7 +15,7 @@ #include <linux/kgdb.h> #include <linux/uaccess.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/traps.h> struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c index e9e828b6bb30..4d45e60cd46d 100644 --- a/arch/arm/kernel/patch.c +++ b/arch/arm/kernel/patch.c @@ -9,7 +9,7 @@ #include <asm/fixmap.h> #include <asm/smp_plat.h> #include <asm/opcodes.h> -#include <asm/patch.h> +#include <asm/text-patching.h> struct patch { void *addr; diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c index 831793cd6ff9..2bec87c3327d 100644 --- a/arch/arm/mm/fault-armv.c +++ b/arch/arm/mm/fault-armv.c @@ -61,32 +61,8 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address, return ret; } -#if defined(CONFIG_SPLIT_PTE_PTLOCKS) -/* - * If we are using split PTE locks, then we need to take the page - * lock here. Otherwise we are using shared mm->page_table_lock - * which is already locked, thus cannot take it. - */ -static inline void do_pte_lock(spinlock_t *ptl) -{ - /* - * Use nested version here to indicate that we are already - * holding one similar spinlock. - */ - spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); -} - -static inline void do_pte_unlock(spinlock_t *ptl) -{ - spin_unlock(ptl); -} -#else /* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline void do_pte_lock(spinlock_t *ptl) {} -static inline void do_pte_unlock(spinlock_t *ptl) {} -#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ - static int adjust_pte(struct vm_area_struct *vma, unsigned long address, - unsigned long pfn) + unsigned long pfn, struct vm_fault *vmf) { spinlock_t *ptl; pgd_t *pgd; @@ -94,6 +70,7 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, pud_t *pud; pmd_t *pmd; pte_t *pte; + pmd_t pmdval; int ret; pgd = pgd_offset(vma->vm_mm, address); @@ -112,20 +89,33 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, if (pmd_none_or_clear_bad(pmd)) return 0; +again: /* * This is called while another page table is mapped, so we * must use the nested version. This also means we need to * open-code the spin-locking. */ - pte = pte_offset_map_nolock(vma->vm_mm, pmd, address, &ptl); + pte = pte_offset_map_rw_nolock(vma->vm_mm, pmd, address, &pmdval, &ptl); if (!pte) return 0; - do_pte_lock(ptl); + /* + * If we are using split PTE locks, then we need to take the page + * lock here. Otherwise we are using shared mm->page_table_lock + * which is already locked, thus cannot take it. + */ + if (ptl != vmf->ptl) { + spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); + if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) { + pte_unmap_unlock(pte, ptl); + goto again; + } + } ret = do_adjust_pte(vma, address, pfn, pte); - do_pte_unlock(ptl); + if (ptl != vmf->ptl) + spin_unlock(ptl); pte_unmap(pte); return ret; @@ -133,7 +123,8 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address, static void make_coherent(struct address_space *mapping, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, unsigned long pfn) + unsigned long addr, pte_t *ptep, unsigned long pfn, + struct vm_fault *vmf) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *mpnt; @@ -160,7 +151,7 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma, if (!(mpnt->vm_flags & VM_MAYSHARE)) continue; offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; - aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn); + aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf); } flush_dcache_mmap_unlock(mapping); if (aliases) @@ -203,7 +194,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, __flush_dcache_folio(mapping, folio); if (mapping) { if (cache_is_vivt()) - make_coherent(mapping, vma, addr, ptep, pfn); + make_coherent(mapping, vma, addr, ptep, pfn, vmf); else if (vma->vm_flags & VM_EXEC) __flush_icache_all(); } diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index d8238da095df..9fd877c87a38 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -25,7 +25,7 @@ #include <asm/cacheflush.h> #include <linux/percpu.h> #include <linux/bug.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/sections.h> #include "../decode-arm.h" diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index 7f65048380ca..966c6042c5ad 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -14,7 +14,7 @@ /* for arm_gen_branch */ #include <asm/insn.h> /* for patch_text */ -#include <asm/patch.h> +#include <asm/text-patching.h> #include "core.h" diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b9b992908a56..8b9f33cf561b 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -110,7 +110,7 @@ #define PAGE_END (_PAGE_END(VA_BITS_MIN)) #endif /* CONFIG_KASAN */ -#define PHYSMEM_END __pa(PAGE_END - 1) +#define DIRECT_MAP_PHYSMEM_END __pa(PAGE_END - 1) #define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) diff --git a/arch/arm64/include/asm/set_memory.h b/arch/arm64/include/asm/set_memory.h index 37774c793006..90f61b17275e 100644 --- a/arch/arm64/include/asm/set_memory.h +++ b/arch/arm64/include/asm/set_memory.h @@ -13,6 +13,7 @@ int set_memory_valid(unsigned long addr, int numpages, int enable); int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid); bool kernel_page_present(struct page *page); int set_memory_encrypted(unsigned long addr, int numpages); diff --git a/arch/arm64/include/asm/patching.h b/arch/arm64/include/asm/text-patching.h index 587bdb91ab7a..587bdb91ab7a 100644 --- a/arch/arm64/include/asm/patching.h +++ b/arch/arm64/include/asm/text-patching.h diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index b2d947175cbe..245cb419ca24 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -15,7 +15,7 @@ #include <asm/debug-monitors.h> #include <asm/ftrace.h> #include <asm/insn.h> -#include <asm/patching.h> +#include <asm/text-patching.h> #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS struct fregs_offset { diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c index f63ea915d6ad..b345425193d2 100644 --- a/arch/arm64/kernel/jump_label.c +++ b/arch/arm64/kernel/jump_label.c @@ -9,7 +9,7 @@ #include <linux/jump_label.h> #include <linux/smp.h> #include <asm/insn.h> -#include <asm/patching.h> +#include <asm/text-patching.h> bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index 4e1f983df3d1..f3c4d3a8a20f 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -17,7 +17,7 @@ #include <asm/debug-monitors.h> #include <asm/insn.h> -#include <asm/patching.h> +#include <asm/text-patching.h> #include <asm/traps.h> struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 945df74005c7..7f99723fbb8c 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -10,7 +10,7 @@ #include <asm/fixmap.h> #include <asm/insn.h> #include <asm/kprobes.h> -#include <asm/patching.h> +#include <asm/text-patching.h> #include <asm/sections.h> static DEFINE_RAW_SPINLOCK(patch_lock); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 48d88e07611d..d9e462eafb95 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -27,7 +27,7 @@ #include <asm/debug-monitors.h> #include <asm/insn.h> #include <asm/irq.h> -#include <asm/patching.h> +#include <asm/text-patching.h> #include <asm/ptrace.h> #include <asm/sections.h> #include <asm/system_misc.h> diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index ee318f6df647..4e26bd356a48 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -41,7 +41,7 @@ #include <asm/extable.h> #include <asm/insn.h> #include <asm/kprobes.h> -#include <asm/patching.h> +#include <asm/text-patching.h> #include <asm/traps.h> #include <asm/smp.h> #include <asm/stack_pointer.h> diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index c2f89a678ac0..ef63651099a9 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -1023,7 +1023,7 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, if (vma->vm_flags & VM_MTE) flags |= __GFP_ZEROTAGS; - return vma_alloc_folio(flags, 0, vma, vaddr, false); + return vma_alloc_folio(flags, 0, vma, vaddr); } void tag_clear_highpage(struct page *page) diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 6ae6ae806454..39fd1f7ff02a 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -282,7 +282,23 @@ int realm_register_memory_enc_ops(void) return arm64_mem_crypt_ops_register(&realm_crypt_ops); } +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) +{ + unsigned long addr = (unsigned long)page_address(page); + + if (!can_set_direct_map()) + return 0; + + return set_memory_valid(addr, nr, valid); +} + #ifdef CONFIG_DEBUG_PAGEALLOC +/* + * This is - apart from the return value - doing the same + * thing as the new set_direct_map_valid_noflush() function. + * + * Unify? Explain the conceptual differences? + */ void __kernel_map_pages(struct page *page, int numpages, int enable) { if (!can_set_direct_map()) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 27ef366363e4..66708b95493a 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -19,7 +19,7 @@ #include <asm/cacheflush.h> #include <asm/debug-monitors.h> #include <asm/insn.h> -#include <asm/patching.h> +#include <asm/text-patching.h> #include <asm/set_memory.h> #include "bpf_jit.h" diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index 9a9bc65b57a9..3a5c7f6e5aac 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -11,3 +11,4 @@ generic-y += qspinlock.h generic-y += parport.h generic-y += user.h generic-y += vmlinux.lds.h +generic-y += text-patching.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 8c1a78c8f527..1efa1e993d4b 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -5,3 +5,4 @@ generic-y += extable.h generic-y += iomap.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += text-patching.h diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 5b5a6c90e6e2..80ddb5edb845 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -11,3 +11,4 @@ generic-y += ioctl.h generic-y += mmzone.h generic-y += statfs.h generic-y += param.h +generic-y += text-patching.h diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h index 5da32c00d483..b837c65a4894 100644 --- a/arch/loongarch/include/asm/hugetlb.h +++ b/arch/loongarch/include/asm/hugetlb.h @@ -16,12 +16,7 @@ static inline int prepare_hugepage_range(struct file *file, unsigned long len) { unsigned long task_size = STACK_TOP; - struct hstate *h = hstate_file(file); - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (addr & ~huge_page_mask(h)) - return -EINVAL; if (len > task_size) return -ENOMEM; if (task_size - len < addr) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 20714b73f14c..da346733a1da 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -268,8 +268,11 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pm */ extern void pgd_init(void *addr); extern void pud_init(void *addr); +#define pud_init pud_init extern void pmd_init(void *addr); +#define pmd_init pmd_init extern void kernel_pte_init(void *addr); +#define kernel_pte_init kernel_pte_init /* * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that diff --git a/arch/loongarch/include/asm/set_memory.h b/arch/loongarch/include/asm/set_memory.h index d70505b6676c..55dfaefd02c8 100644 --- a/arch/loongarch/include/asm/set_memory.h +++ b/arch/loongarch/include/asm/set_memory.h @@ -17,5 +17,6 @@ int set_memory_rw(unsigned long addr, int numpages); bool kernel_page_present(struct page *page); int set_direct_map_default_noflush(struct page *page); int set_direct_map_invalid_noflush(struct page *page); +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid); #endif /* _ASM_LOONGARCH_SET_MEMORY_H */ diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c index ffd8d76021d4..bf8678248444 100644 --- a/arch/loongarch/mm/pageattr.c +++ b/arch/loongarch/mm/pageattr.c @@ -216,3 +216,22 @@ int set_direct_map_invalid_noflush(struct page *page) return __set_memory(addr, 1, __pgprot(0), __pgprot(_PAGE_PRESENT | _PAGE_VALID)); } + +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) +{ + unsigned long addr = (unsigned long)page_address(page); + pgprot_t set, clear; + + if (addr < vm_map_base) + return 0; + + if (valid) { + set = PAGE_KERNEL; + clear = __pgprot(0); + } else { + set = __pgprot(0); + clear = __pgprot(_PAGE_PRESENT | _PAGE_VALID); + } + + return __set_memory(addr, 1, set, clear); +} diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 0dbf9c5c6fae..b282e0dd8dc1 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -4,3 +4,4 @@ generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += spinlock.h +generic-y += text-patching.h diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h index af3a10973233..63c0e706084b 100644 --- a/arch/m68k/include/asm/page_no.h +++ b/arch/m68k/include/asm/page_no.h @@ -14,7 +14,7 @@ extern unsigned long memory_end; #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) #define vma_alloc_zeroed_movable_folio(vma, vaddr) \ - vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr) #define __pa(vaddr) ((unsigned long)(vaddr)) #define __va(paddr) ((void *)((unsigned long)(paddr))) diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index a055f5dbe00a..7178f990e8b3 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -8,3 +8,4 @@ generic-y += parport.h generic-y += syscalls.h generic-y += tlb.h generic-y += user.h +generic-y += text-patching.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 7ba67a0d6c97..684569b2ecd6 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -13,3 +13,4 @@ generic-y += parport.h generic-y += qrwlock.h generic-y += qspinlock.h generic-y += user.h +generic-y += text-patching.h diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h index fd69c8808554..d0a86ce83de9 100644 --- a/arch/mips/include/asm/hugetlb.h +++ b/arch/mips/include/asm/hugetlb.h @@ -17,12 +17,7 @@ static inline int prepare_hugepage_range(struct file *file, unsigned long len) { unsigned long task_size = STACK_TOP; - struct hstate *h = hstate_file(file); - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (addr & ~huge_page_mask(h)) - return -EINVAL; if (len > task_size) return -ENOMEM; if (task_size - len < addr) diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 401c1d9e4409..6e854bb11f37 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -317,7 +317,9 @@ static inline pmd_t *pud_pgtable(pud_t pud) */ extern void pgd_init(void *addr); extern void pud_init(void *addr); +#define pud_init pud_init extern void pmd_init(void *addr); +#define pmd_init pmd_init /* * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 9c48d9a21aa0..b700dae28c48 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -105,6 +105,9 @@ #define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ +#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */ +#define MADV_GUARD_REMOVE 103 /* unguard range */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 0d09829ed144..28004301c236 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -7,3 +7,4 @@ generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += spinlock.h generic-y += user.h +generic-y += text-patching.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index cef49d60d74c..2b1a6b00cdac 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -9,3 +9,4 @@ generic-y += spinlock.h generic-y += qrwlock_types.h generic-y += qrwlock.h generic-y += user.h +generic-y += text-patching.h diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index 72daacc472a0..5b3a5429f71b 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -12,21 +12,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); -/* - * If the arch doesn't supply something else, assume that hugepage - * size aligned regions are ok without further preparation. - */ -#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE -static inline int prepare_hugepage_range(struct file *file, - unsigned long addr, unsigned long len) -{ - if (len & ~HPAGE_MASK) - return -EINVAL; - if (addr & ~HPAGE_MASK) - return -EINVAL; - return 0; -} - #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) diff --git a/arch/parisc/include/asm/patch.h b/arch/parisc/include/asm/text-patching.h index 400d84c6e504..400d84c6e504 100644 --- a/arch/parisc/include/asm/patch.h +++ b/arch/parisc/include/asm/text-patching.h diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index 68c44f99bc93..b6a709506987 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -75,6 +75,9 @@ #define MADV_HWPOISON 100 /* poison a page for testing */ #define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */ +#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */ +#define MADV_GUARD_REMOVE 103 /* unguard range */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index c91f9c2e61ed..3e34b4473d3a 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -20,7 +20,7 @@ #include <asm/assembly.h> #include <asm/sections.h> #include <asm/ftrace.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #define __hot __section(".text.hot") diff --git a/arch/parisc/kernel/jump_label.c b/arch/parisc/kernel/jump_label.c index e253b134500d..ea51f15bf0e6 100644 --- a/arch/parisc/kernel/jump_label.c +++ b/arch/parisc/kernel/jump_label.c @@ -8,7 +8,7 @@ #include <linux/jump_label.h> #include <linux/bug.h> #include <asm/alternative.h> -#include <asm/patch.h> +#include <asm/text-patching.h> static inline int reassemble_17(int as17) { diff --git a/arch/parisc/kernel/kgdb.c b/arch/parisc/kernel/kgdb.c index b16fa9bac5f4..fee81f877525 100644 --- a/arch/parisc/kernel/kgdb.c +++ b/arch/parisc/kernel/kgdb.c @@ -16,7 +16,7 @@ #include <asm/ptrace.h> #include <asm/traps.h> #include <asm/processor.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/cacheflush.h> const struct kgdb_arch arch_kgdb_ops = { diff --git a/arch/parisc/kernel/kprobes.c b/arch/parisc/kernel/kprobes.c index 6e0b86652f30..9255adba67a3 100644 --- a/arch/parisc/kernel/kprobes.c +++ b/arch/parisc/kernel/kprobes.c @@ -12,7 +12,7 @@ #include <linux/kprobes.h> #include <linux/slab.h> #include <asm/cacheflush.h> -#include <asm/patch.h> +#include <asm/text-patching.h> DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); diff --git a/arch/parisc/kernel/patch.c b/arch/parisc/kernel/patch.c index e59574f65e64..35dd764b871e 100644 --- a/arch/parisc/kernel/patch.c +++ b/arch/parisc/kernel/patch.c @@ -13,7 +13,7 @@ #include <asm/cacheflush.h> #include <asm/fixmap.h> -#include <asm/patch.h> +#include <asm/text-patching.h> struct patch { void *addr; diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index aa664f7ddb63..e9d18cf25b79 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -21,27 +21,6 @@ #include <asm/mmu_context.h> -unsigned long -hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (len > TASK_SIZE) - return -ENOMEM; - - if (flags & MAP_FIXED) - if (prepare_hugepage_range(file, addr, len)) - return -EINVAL; - - if (addr) - addr = ALIGN(addr, huge_page_size(h)); - - /* we need to make sure the colouring is OK */ - return arch_get_unmapped_area(file, addr, len, pgoff, flags, 0); -} pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 4525a9c68260..dfe2e5ad3b21 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -21,7 +21,7 @@ #include <linux/percpu.h> #include <linux/module.h> #include <asm/probes.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #ifdef CONFIG_KPROBES #define __ARCH_WANT_KPROBES_INSN_SLOT diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/text-patching.h index e7f14720f630..e7f14720f630 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/text-patching.h diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 2086fa6cdc25..103b6605dd68 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -13,7 +13,7 @@ #include <linux/io.h> #include <linux/memblock.h> #include <linux/of.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/kdump.h> #include <asm/firmware.h> #include <linux/uio.h> diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c index d4b8aff20815..247ab2acaccc 100644 --- a/arch/powerpc/kernel/epapr_paravirt.c +++ b/arch/powerpc/kernel/epapr_paravirt.c @@ -9,7 +9,7 @@ #include <linux/of_fdt.h> #include <asm/epapr_hcalls.h> #include <asm/cacheflush.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/machdep.h> #include <asm/inst.h> diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c index 5277cf582c16..2659e1ac8604 100644 --- a/arch/powerpc/kernel/jump_label.c +++ b/arch/powerpc/kernel/jump_label.c @@ -5,7 +5,7 @@ #include <linux/kernel.h> #include <linux/jump_label.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/inst.h> void arch_jump_label_transform(struct jump_entry *entry, diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 7a8bc03a00af..5081334b7bd2 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -21,7 +21,7 @@ #include <asm/processor.h> #include <asm/machdep.h> #include <asm/debug.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <linux/slab.h> #include <asm/inst.h> diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index f8aa91bc3b17..9c85bbcc5201 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -21,7 +21,7 @@ #include <linux/slab.h> #include <linux/set_memory.h> #include <linux/execmem.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/cacheflush.h> #include <asm/sstep.h> #include <asm/sections.h> diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 816a63fd71fb..f930e3395a7f 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -18,7 +18,7 @@ #include <linux/bug.h> #include <linux/sort.h> #include <asm/setup.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> /* Count how many different relocations (different symbol, different addend) */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index e9bab599d0c2..135960918d14 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -17,7 +17,7 @@ #include <linux/kernel.h> #include <asm/module.h> #include <asm/firmware.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <linux/sort.h> #include <asm/setup.h> #include <asm/sections.h> diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c index c0b351d61058..2e83702bf9ba 100644 --- a/arch/powerpc/kernel/optprobes.c +++ b/arch/powerpc/kernel/optprobes.c @@ -13,7 +13,7 @@ #include <asm/kprobes.h> #include <asm/ptrace.h> #include <asm/cacheflush.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/sstep.h> #include <asm/ppc-opcode.h> #include <asm/inst.h> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ff61a3e7984c..7b739b9a91ab 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -54,7 +54,7 @@ #include <asm/firmware.h> #include <asm/hw_irq.h> #endif -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/exec.h> #include <asm/livepatch.h> #include <asm/cpu_has_feature.h> diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 4856e1a5161c..fbb7ebd8aa08 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -14,7 +14,7 @@ #include <linux/debugfs.h> #include <asm/asm-prototypes.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/security_features.h> #include <asm/sections.h> #include <asm/setup.h> diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index e515c1f7d8d3..75dbf3e0d9c4 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -40,7 +40,7 @@ #include <asm/time.h> #include <asm/serial.h> #include <asm/udbg.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/cpu_has_feature.h> #include <asm/asm-prototypes.h> #include <asm/kdump.h> diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 22f83fbbc762..3ebf5b9fbe98 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -60,7 +60,7 @@ #include <asm/xmon.h> #include <asm/udbg.h> #include <asm/kexec.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/ftrace.h> #include <asm/opal.h> #include <asm/cputhreads.h> diff --git a/arch/powerpc/kernel/static_call.c b/arch/powerpc/kernel/static_call.c index 1502b7e439ca..7cfd0710e757 100644 --- a/arch/powerpc/kernel/static_call.c +++ b/arch/powerpc/kernel/static_call.c @@ -2,7 +2,7 @@ #include <linux/memory.h> #include <linux/static_call.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) { diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index df41f4a7c738..afb7dcd47587 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -23,7 +23,7 @@ #include <linux/list.h> #include <asm/cacheflush.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/ftrace.h> #include <asm/syscall.h> #include <asm/inst.h> diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index d3c5552e4984..b3e0987ec7b0 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -23,7 +23,7 @@ #include <linux/list.h> #include <asm/cacheflush.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/ftrace.h> #include <asm/syscall.h> #include <asm/inst.h> diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index acdab294b340..af97fbb3c257 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -17,7 +17,7 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/page.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/inst.h> static int __patch_mem(void *exec_addr, unsigned long val, void *patch_addr, bool is_dword) diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index b7201ba50b2e..587c8cf1230f 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -16,7 +16,7 @@ #include <linux/sched/mm.h> #include <linux/stop_machine.h> #include <asm/cputable.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/interrupt.h> #include <asm/page.h> #include <asm/sections.h> diff --git a/arch/powerpc/lib/test-code-patching.c b/arch/powerpc/lib/test-code-patching.c index 8cd3b32f805b..1440d99630b3 100644 --- a/arch/powerpc/lib/test-code-patching.c +++ b/arch/powerpc/lib/test-code-patching.c @@ -6,7 +6,7 @@ #include <linux/vmalloc.h> #include <linux/init.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> static int __init instr_is_branch_to_addr(const u32 *instr, unsigned long addr) { diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c index 23c7805fb7b3..66b5b4fa1686 100644 --- a/arch/powerpc/lib/test_emulate_step.c +++ b/arch/powerpc/lib/test_emulate_step.c @@ -11,7 +11,7 @@ #include <asm/cpu_has_feature.h> #include <asm/sstep.h> #include <asm/ppc-opcode.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/inst.h> #define MAX_SUBTESTS 16 diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 2db167f4233f..6978344edcb4 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -25,7 +25,7 @@ #include <asm/mmu.h> #include <asm/machdep.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/sections.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index e1eadd03f133..47b22282269c 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -57,7 +57,7 @@ #include <asm/sections.h> #include <asm/copro.h> #include <asm/udbg.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/fadump.h> #include <asm/firmware.h> #include <asm/tm.h> diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index f2708c8629a5..6b783552403c 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -24,7 +24,7 @@ #include <linux/pgtable.h> #include <asm/udbg.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include "internal.h" diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c index 87307d0fc3b8..bc9a39821d1c 100644 --- a/arch/powerpc/mm/book3s64/slice.c +++ b/arch/powerpc/mm/book3s64/slice.c @@ -633,6 +633,20 @@ return_addr: } EXPORT_SYMBOL_GPL(slice_get_unmapped_area); +#ifdef CONFIG_HUGETLB_PAGE +static int file_to_psize(struct file *file) +{ + struct hstate *hstate = hstate_file(file); + + return shift_to_mmu_psize(huge_page_shift(hstate)); +} +#else +static int file_to_psize(struct file *file) +{ + return 0; +} +#endif + unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, @@ -640,11 +654,17 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long flags, vm_flags_t vm_flags) { + unsigned int psize; + if (radix_enabled()) return generic_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags); - return slice_get_unmapped_area(addr, len, flags, - mm_ctx_user_psize(¤t->mm->context), 0); + if (filp && is_file_hugepages(filp)) + psize = file_to_psize(filp); + else + psize = mm_ctx_user_psize(¤t->mm->context); + + return slice_get_unmapped_area(addr, len, flags, psize, 0); } unsigned long arch_get_unmapped_area_topdown(struct file *filp, @@ -654,11 +674,17 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, const unsigned long flags, vm_flags_t vm_flags) { + unsigned int psize; + if (radix_enabled()) return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags, vm_flags); - return slice_get_unmapped_area(addr0, len, flags, - mm_ctx_user_psize(¤t->mm->context), 1); + if (filp && is_file_hugepages(filp)) + psize = file_to_psize(filp); + else + psize = mm_ctx_user_psize(¤t->mm->context); + + return slice_get_unmapped_area(addr0, len, flags, psize, 1); } unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr) @@ -788,20 +814,4 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) return 1UL << mmu_psize_to_shift(get_slice_psize(vma->vm_mm, vma->vm_start)); } - -static int file_to_psize(struct file *file) -{ - struct hstate *hstate = hstate_file(file); - return shift_to_mmu_psize(huge_page_shift(hstate)); -} - -unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags) -{ - if (radix_enabled()) - return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags); - - return slice_get_unmapped_area(addr, len, flags, file_to_psize(file), 1); -} #endif diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c index aa9aa11927b2..03666d790a53 100644 --- a/arch/powerpc/mm/kasan/init_32.c +++ b/arch/powerpc/mm/kasan/init_32.c @@ -7,7 +7,7 @@ #include <linux/memblock.h> #include <linux/sched/task.h> #include <asm/pgalloc.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <mm/mmu_decl.h> static pgprot_t __init kasan_prot_ro(void) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 1221c561b43a..c7708c8fad29 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -26,7 +26,7 @@ #include <asm/svm.h> #include <asm/mmzone.h> #include <asm/ftrace.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/setup.h> #include <asm/fixmap.h> diff --git a/arch/powerpc/mm/nohash/44x.c b/arch/powerpc/mm/nohash/44x.c index 1beae802bb1c..6d10c6d8be71 100644 --- a/arch/powerpc/mm/nohash/44x.c +++ b/arch/powerpc/mm/nohash/44x.c @@ -24,7 +24,7 @@ #include <asm/mmu.h> #include <asm/page.h> #include <asm/cacheflush.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/smp.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/nohash/book3e_pgtable.c b/arch/powerpc/mm/nohash/book3e_pgtable.c index ad2a7c26f2a0..062e8785c1bb 100644 --- a/arch/powerpc/mm/nohash/book3e_pgtable.c +++ b/arch/powerpc/mm/nohash/book3e_pgtable.c @@ -10,7 +10,7 @@ #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/dma.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index b653a7be4cb1..0a650742f3a0 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -37,7 +37,7 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/tlb.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/cputhreads.h> #include <asm/hugetlb.h> #include <asm/paca.h> diff --git a/arch/powerpc/mm/nohash/tlb_64e.c b/arch/powerpc/mm/nohash/tlb_64e.c index d26656b07b72..4f925adf2695 100644 --- a/arch/powerpc/mm/nohash/tlb_64e.c +++ b/arch/powerpc/mm/nohash/tlb_64e.c @@ -24,7 +24,7 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/tlb.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/cputhreads.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 7316396e452d..61df5aed7989 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -398,7 +398,7 @@ void assert_pte_locked(struct mm_struct *mm, unsigned long addr) */ if (pmd_none(*pmd)) return; - pte = pte_offset_map_nolock(mm, pmd, addr, &ptl); + pte = pte_offset_map_ro_nolock(mm, pmd, addr, &ptl); BUG_ON(!pte); assert_spin_locked(ptl); pte_unmap(pte); diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 2a36cc2e7e9e..68c6a13e6acb 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -18,7 +18,7 @@ #include <linux/bpf.h> #include <asm/kprobes.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include "bpf_jit.h" diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c index 308a2e40d7be..1d2972229e3a 100644 --- a/arch/powerpc/perf/8xx-pmu.c +++ b/arch/powerpc/perf/8xx-pmu.c @@ -14,7 +14,7 @@ #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/ptrace.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/inst.h> #define PERF_8xx_ID_CPU_CYCLES 1 diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index dc01aa604cc1..2b79171ee185 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -16,7 +16,7 @@ #include <asm/machdep.h> #include <asm/firmware.h> #include <asm/ptrace.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/hw_irq.h> #include <asm/interrupt.h> diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index e52b848b64b7..32fa5fb557c0 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -23,7 +23,7 @@ #include <asm/mpic.h> #include <asm/cacheflush.h> #include <asm/dbell.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/cputhreads.h> #include <asm/fsl_pm.h> diff --git a/arch/powerpc/platforms/86xx/mpc86xx_smp.c b/arch/powerpc/platforms/86xx/mpc86xx_smp.c index 8a7e55acf090..9be33e41af6d 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_smp.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_smp.c @@ -12,7 +12,7 @@ #include <linux/delay.h> #include <linux/pgtable.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/page.h> #include <asm/pci-bridge.h> #include <asm/mpic.h> diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index fee638fd8970..0e8f20ecca08 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -35,7 +35,7 @@ #include <asm/firmware.h> #include <asm/rtas.h> #include <asm/cputhreads.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include "interrupt.h" #include <asm/udbg.h> diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index d21b681f52fb..09e7fe24fac1 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -35,7 +35,7 @@ #include <asm/ptrace.h> #include <linux/atomic.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/irq.h> #include <asm/page.h> #include <asm/sections.h> diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index ad41dffe4d92..d98b933e4984 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -18,7 +18,7 @@ #include <asm/opal.h> #include <asm/cputhreads.h> #include <asm/cpuidle.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/smp.h> #include <asm/runlatch.h> #include <asm/dbell.h> diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 2e9da58195f5..8f41ef364fc6 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -28,7 +28,7 @@ #include <asm/xive.h> #include <asm/opal.h> #include <asm/runlatch.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/dbell.h> #include <asm/kvm_ppc.h> #include <asm/ppc-opcode.h> diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index c597711ef20a..db99725e752b 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -39,7 +39,7 @@ #include <asm/xive.h> #include <asm/dbell.h> #include <asm/plpar_wrappers.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/svm.h> #include <asm/kvm_guest.h> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index e6cddbb2305f..e76e1d5d0611 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -50,7 +50,7 @@ #include <asm/xive.h> #include <asm/opal.h> #include <asm/firmware.h> -#include <asm/code-patching.h> +#include <asm/text-patching.h> #include <asm/sections.h> #include <asm/inst.h> #include <asm/interrupt.h> diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c index fc1a34faa5f3..dcc9d1ee5ffd 100644 --- a/arch/riscv/errata/andes/errata.c +++ b/arch/riscv/errata/andes/errata.c @@ -13,7 +13,7 @@ #include <asm/alternative.h> #include <asm/cacheflush.h> #include <asm/errata_list.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/processor.h> #include <asm/sbi.h> #include <asm/vendorid_list.h> diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c index cea3b96ade11..38aac2c47845 100644 --- a/arch/riscv/errata/sifive/errata.c +++ b/arch/riscv/errata/sifive/errata.c @@ -8,7 +8,7 @@ #include <linux/module.h> #include <linux/string.h> #include <linux/bug.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/vendorid_list.h> #include <asm/errata_list.h> diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index f5120e07c318..e24770a77932 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -16,7 +16,7 @@ #include <asm/errata_list.h> #include <asm/hwprobe.h> #include <asm/io.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/vendorid_list.h> #include <asm/vendor_extensions.h> diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index e79f15293492..5d7f3e8c2e50 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -963,6 +963,25 @@ void misc_mem_init(void); extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) +/* + * Use set_p*_safe(), and elide TLB flushing, when confident that *no* + * TLB flush will be required as a result of the "set". For example, use + * in scenarios where it is known ahead of time that the routine is + * setting non-present entries, or re-setting an existing entry to the + * same value. Otherwise, use the typical "set" helpers and flush the + * TLB. + */ +#define set_p4d_safe(p4dp, p4d) \ +({ \ + WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ + set_p4d(p4dp, p4d); \ +}) + +#define set_pgd_safe(pgdp, pgd) \ +({ \ + WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ + set_pgd(pgdp, pgd); \ +}) #endif /* !__ASSEMBLY__ */ #endif /* _ASM_RISCV_PGTABLE_H */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index ab92fc84e1fc..ea263d3683ef 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -42,6 +42,7 @@ static inline int set_kernel_memory(char *startp, char *endp, int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid); bool kernel_page_present(struct page *page); #endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/include/asm/patch.h b/arch/riscv/include/asm/text-patching.h index 7228e266b9a1..7228e266b9a1 100644 --- a/arch/riscv/include/asm/patch.h +++ b/arch/riscv/include/asm/text-patching.h diff --git a/arch/riscv/include/asm/uprobes.h b/arch/riscv/include/asm/uprobes.h index 3fc7deda9190..5008f76cdc27 100644 --- a/arch/riscv/include/asm/uprobes.h +++ b/arch/riscv/include/asm/uprobes.h @@ -4,7 +4,7 @@ #define _ASM_RISCV_UPROBES_H #include <asm/probes.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/bug.h> #define MAX_UINSN_BYTES 8 diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c index 0128b161bfda..7eb3cb1215c6 100644 --- a/arch/riscv/kernel/alternative.c +++ b/arch/riscv/kernel/alternative.c @@ -18,7 +18,7 @@ #include <asm/sbi.h> #include <asm/csr.h> #include <asm/insn.h> -#include <asm/patch.h> +#include <asm/text-patching.h> struct cpu_manufacturer_info_t { unsigned long vendor_id; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 3a8eeaa9310c..826f46b21f2e 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -20,7 +20,8 @@ #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwcap.h> -#include <asm/patch.h> +#include <asm/text-patching.h> +#include <asm/hwprobe.h> #include <asm/processor.h> #include <asm/sbi.h> #include <asm/vector.h> diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 5081ad886841..8cb9b211611d 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -10,7 +10,7 @@ #include <linux/memory.h> #include <linux/stop_machine.h> #include <asm/cacheflush.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #ifdef CONFIG_DYNAMIC_FTRACE void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c index 11ad789c60c6..6eee6f736f68 100644 --- a/arch/riscv/kernel/jump_label.c +++ b/arch/riscv/kernel/jump_label.c @@ -10,7 +10,7 @@ #include <linux/mutex.h> #include <asm/bug.h> #include <asm/cacheflush.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #define RISCV_INSN_NOP 0x00000013U #define RISCV_INSN_JAL 0x0000006fU diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index 34ef522f07a8..db13c9ddf9e3 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -13,7 +13,7 @@ #include <asm/cacheflush.h> #include <asm/fixmap.h> #include <asm/ftrace.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/sections.h> struct patch_insn { diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 474a65213657..380a0e8cecc0 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -12,7 +12,7 @@ #include <asm/sections.h> #include <asm/cacheflush.h> #include <asm/bug.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include "decode-insn.h" diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index 271d01a5ba4d..d815448758a1 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -386,6 +386,21 @@ int set_direct_map_default_noflush(struct page *page) PAGE_KERNEL, __pgprot(_PAGE_EXEC)); } +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) +{ + pgprot_t set, clear; + + if (valid) { + set = PAGE_KERNEL; + clear = __pgprot(_PAGE_EXEC); + } else { + set = __pgprot(0); + clear = __pgprot(_PAGE_PRESENT); + } + + return __set_memory((unsigned long)page_address(page), nr, set, clear); +} + #ifdef CONFIG_DEBUG_PAGEALLOC static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data) { diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 4cc631fa7039..ca60db75199d 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -10,7 +10,7 @@ #include <linux/filter.h> #include <linux/memory.h> #include <linux/stop_machine.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/cfi.h> #include <asm/percpu.h> #include "bpf_jit.h" diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index 6de753c667f4..f8cd2f70a7fb 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -9,7 +9,7 @@ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/memory.h> -#include <asm/patch.h> +#include <asm/text-patching.h> #include <asm/cfi.h> #include "bpf_jit.h" diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index cf1b5d6fb1a6..6f815d4ba0ca 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -12,39 +12,26 @@ #include <linux/pgtable.h> #include <asm/page.h> -#define hugetlb_free_pgd_range free_pgd_range #define hugepages_supported() (MACHINE_HAS_EDAT1) +#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz); void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); -pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep); -pte_t huge_ptep_get_and_clear(struct mm_struct *mm, +#define __HAVE_ARCH_HUGE_PTEP_GET +extern pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR +extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); -/* - * If the arch doesn't supply something else, assume that hugepage - * size aligned regions are ok without further preparation. - */ -static inline int prepare_hugepage_range(struct file *file, - unsigned long addr, unsigned long len) -{ - struct hstate *h = hstate_file(file); - - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (addr & ~huge_page_mask(h)) - return -EINVAL; - return 0; -} - static inline void arch_clear_hugetlb_flags(struct folio *folio) { clear_bit(PG_arch_1, &folio->flags); } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags +#define __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) { @@ -54,12 +41,14 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, set_pte(ptep, __pte(_SEGMENT_ENTRY_EMPTY)); } +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { return huge_ptep_get_and_clear(vma->vm_mm, address, ptep); } +#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) @@ -72,6 +61,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, return changed; } +#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -79,69 +69,36 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); } -static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) -{ - return mk_pte(page, pgprot); -} - +#define __HAVE_ARCH_HUGE_PTE_NONE static inline int huge_pte_none(pte_t pte) { return pte_none(pte); } +#define __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY 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); -} - -static inline int huge_pte_dirty(pte_t pte) -{ - return pte_dirty(pte); -} - -static inline pte_t huge_pte_mkwrite(pte_t pte) -{ - return pte_mkwrite_novma(pte); -} - -static inline pte_t huge_pte_mkdirty(pte_t pte) -{ - return pte_mkdirty(pte); -} - -static inline pte_t huge_pte_wrprotect(pte_t pte) -{ - return pte_wrprotect(pte); -} - -static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) -{ - return pte_modify(pte, newprot); -} - +#define __HAVE_ARCH_HUGE_PTE_MKUFFD_WP static inline pte_t huge_pte_mkuffd_wp(pte_t pte) { return pte; } +#define __HAVE_ARCH_HUGE_PTE_CLEAR_UFFD_WP static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) { return pte; } +#define __HAVE_ARCH_HUGE_PTE_UFFD_WP static inline int huge_pte_uffd_wp(pte_t pte) { return 0; } -static inline bool gigantic_page_runtime_supported(void) -{ - return true; -} +#include <asm-generic/hugetlb.h> #endif /* _ASM_S390_HUGETLB_H */ diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index b13a46e2e931..4f43cdd9835b 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -69,7 +69,7 @@ static inline void copy_page(void *to, void *from) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) #define vma_alloc_zeroed_movable_folio(vma, vaddr) \ - vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr) /* * These are used to make use of C type-checking.. diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h index cb4cc0f59012..94092f4ae764 100644 --- a/arch/s390/include/asm/set_memory.h +++ b/arch/s390/include/asm/set_memory.h @@ -62,6 +62,7 @@ __SET_MEMORY_FUNC(set_memory_4k, SET_MEMORY_4K) int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid); bool kernel_page_present(struct page *page); #endif diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index ded0eff58a19..7c79cf1bc7d7 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -242,88 +242,3 @@ bool __init arch_hugetlb_valid_size(unsigned long size) else return false; } - -static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info = {}; - - info.length = len; - info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - return vm_unmapped_area(&info); -} - -static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, - unsigned long addr0, unsigned long len, - unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info = {}; - unsigned long addr; - - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.low_limit = PAGE_SIZE; - info.high_limit = current->mm->mmap_base; - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - addr = vm_unmapped_area(&info); - - /* - * A failed mmap() very likely causes application failure, - * so fall back to the bottom-up function here. This scenario - * can happen with large stack limits and large mmap() - * allocations. - */ - if (addr & ~PAGE_MASK) { - VM_BUG_ON(addr != -ENOMEM); - info.flags = 0; - info.low_limit = TASK_UNMAPPED_BASE; - info.high_limit = TASK_SIZE; - addr = vm_unmapped_area(&info); - } - - return addr; -} - -unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (len > TASK_SIZE - mmap_min_addr) - return -ENOMEM; - - if (flags & MAP_FIXED) { - if (prepare_hugepage_range(file, addr, len)) - return -EINVAL; - goto check_asce_limit; - } - - if (addr) { - addr = ALIGN(addr, huge_page_size(h)); - vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vm_start_gap(vma))) - goto check_asce_limit; - } - - if (!test_bit(MMF_TOPDOWN, &mm->flags)) - addr = hugetlb_get_unmapped_area_bottomup(file, addr, len, - pgoff, flags); - else - addr = hugetlb_get_unmapped_area_topdown(file, addr, len, - pgoff, flags); - if (offset_in_page(addr)) - return addr; - -check_asce_limit: - return check_asce_limit(mm, addr, len); -} diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 96efa061ce01..33f3504be90b 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -17,6 +17,7 @@ #include <linux/random.h> #include <linux/compat.h> #include <linux/security.h> +#include <linux/hugetlb.h> #include <asm/elf.h> static unsigned long stack_maxrandom_size(void) @@ -73,6 +74,8 @@ static inline unsigned long mmap_base(unsigned long rnd, static int get_align_mask(struct file *filp, unsigned long flags) { + if (filp && is_file_hugepages(filp)) + return huge_page_mask_align(filp); if (!(current->flags & PF_RANDOMIZE)) return 0; if (filp || (flags & MAP_SHARED)) @@ -106,7 +109,8 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; info.align_mask = get_align_mask(filp, flags); - info.align_offset = pgoff << PAGE_SHIFT; + if (!(filp && is_file_hugepages(filp))) + info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); if (offset_in_page(addr)) return addr; @@ -144,7 +148,8 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; info.align_mask = get_align_mask(filp, flags); - info.align_offset = pgoff << PAGE_SHIFT; + if (!(filp && is_file_hugepages(filp))) + info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); /* diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 4a0f422cfeb6..8f56a21a077f 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -407,6 +407,18 @@ int set_direct_map_default_noflush(struct page *page) return __set_memory((unsigned long)page_to_virt(page), 1, SET_MEMORY_DEF); } +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) +{ + unsigned long flags; + + if (valid) + flags = SET_MEMORY_DEF; + else + flags = SET_MEMORY_INV; + + return __set_memory((unsigned long)page_to_virt(page), nr, flags); +} + bool kernel_page_present(struct page *page) { unsigned long addr; diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index fc44d9c88b41..4d3f10ed8275 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -3,3 +3,4 @@ generated-y += syscall_table.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += parport.h +generic-y += text-patching.h diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h index 75028bd568ba..4a92e6e4d627 100644 --- a/arch/sh/include/asm/hugetlb.h +++ b/arch/sh/include/asm/hugetlb.h @@ -5,21 +5,6 @@ #include <asm/cacheflush.h> #include <asm/page.h> -/* - * If the arch doesn't supply something else, assume that hugepage - * size aligned regions are ok without further preparation. - */ -#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE -static inline int prepare_hugepage_range(struct file *file, - unsigned long addr, unsigned long len) -{ - if (len & ~HPAGE_MASK) - return -EINVAL; - if (addr & ~HPAGE_MASK) - return -EINVAL; - return 0; -} - #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 43b0ae4c2c21..17ee8a273aa6 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -4,3 +4,4 @@ generated-y += syscall_table_64.h generic-y += agp.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += text-patching.h diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 80822f922e76..fb31bc0c5b48 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -23,6 +23,7 @@ #include <linux/utsname.h> #include <linux/smp.h> #include <linux/ipc.h> +#include <linux/hugetlb.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -42,12 +43,16 @@ SYSCALL_DEFINE0(getpagesize) unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct vm_unmapped_area_info info = {}; + bool file_hugepage = false; + + if (filp && is_file_hugepages(filp)) + file_hugepage = true; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate * cache aliasing constraints. */ - if ((flags & MAP_SHARED) && + if (!file_hugepage && (flags & MAP_SHARED) && ((addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))) return -EINVAL; return addr; @@ -62,9 +67,13 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi info.length = len; info.low_limit = addr; info.high_limit = TASK_SIZE; - info.align_mask = (flags & MAP_SHARED) ? - (PAGE_MASK & (SHMLBA - 1)) : 0; - info.align_offset = pgoff << PAGE_SHIFT; + if (!file_hugepage) { + info.align_mask = (flags & MAP_SHARED) ? + (PAGE_MASK & (SHMLBA - 1)) : 0; + info.align_offset = pgoff << PAGE_SHIFT; + } else { + info.align_mask = huge_page_mask_align(filp); + } return vm_unmapped_area(&info); } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index acade309dc2f..c5a284df7b41 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -30,6 +30,7 @@ #include <linux/context_tracking.h> #include <linux/timex.h> #include <linux/uaccess.h> +#include <linux/hugetlb.h> #include <asm/utrap.h> #include <asm/unistd.h> @@ -87,6 +88,16 @@ static inline unsigned long COLOR_ALIGN(unsigned long addr, return base + off; } +static unsigned long get_align_mask(struct file *filp, unsigned long flags) +{ + if (filp && is_file_hugepages(filp)) + return huge_page_mask_align(filp); + if (filp || (flags & MAP_SHARED)) + return PAGE_MASK & (SHMLBA - 1); + + return 0; +} + unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { struct mm_struct *mm = current->mm; @@ -94,12 +105,16 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi unsigned long task_size = TASK_SIZE; int do_color_align; struct vm_unmapped_area_info info = {}; + bool file_hugepage = false; + + if (filp && is_file_hugepages(filp)) + file_hugepage = true; if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate * cache aliasing constraints. */ - if ((flags & MAP_SHARED) && + if (!file_hugepage && (flags & MAP_SHARED) && ((addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))) return -EINVAL; return addr; @@ -111,7 +126,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi return -ENOMEM; do_color_align = 0; - if (filp || (flags & MAP_SHARED)) + if ((filp || (flags & MAP_SHARED)) && !file_hugepage) do_color_align = 1; if (addr) { @@ -129,8 +144,9 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi info.length = len; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = min(task_size, VA_EXCLUDE_START); - info.align_mask = do_color_align ? (PAGE_MASK & (SHMLBA - 1)) : 0; - info.align_offset = pgoff << PAGE_SHIFT; + info.align_mask = get_align_mask(filp, flags); + if (!file_hugepage) + info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) { @@ -154,15 +170,19 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, unsigned long addr = addr0; int do_color_align; struct vm_unmapped_area_info info = {}; + bool file_hugepage = false; /* This should only ever run for 32-bit processes. */ BUG_ON(!test_thread_flag(TIF_32BIT)); + if (filp && is_file_hugepages(filp)) + file_hugepage = true; + if (flags & MAP_FIXED) { /* We do not accept a shared mapping if it would violate * cache aliasing constraints. */ - if ((flags & MAP_SHARED) && + if (!file_hugepage && (flags & MAP_SHARED) && ((addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))) return -EINVAL; return addr; @@ -172,7 +192,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return -ENOMEM; do_color_align = 0; - if (filp || (flags & MAP_SHARED)) + if ((filp || (flags & MAP_SHARED)) && !file_hugepage) do_color_align = 1; /* requesting a specific address */ @@ -192,8 +212,9 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; - info.align_mask = do_color_align ? (PAGE_MASK & (SHMLBA - 1)) : 0; - info.align_offset = pgoff << PAGE_SHIFT; + info.align_mask = get_align_mask(filp, flags); + if (!file_hugepage) + info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); /* diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index cc91ca7a1e18..eee601a0d2cf 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -19,114 +19,6 @@ #include <asm/cacheflush.h> #include <asm/mmu_context.h> -/* Slightly simplified from the non-hugepage variant because by - * definition we don't have to worry about any page coloring stuff - */ - -static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp, - unsigned long addr, - unsigned long len, - unsigned long pgoff, - unsigned long flags) -{ - struct hstate *h = hstate_file(filp); - unsigned long task_size = TASK_SIZE; - struct vm_unmapped_area_info info = {}; - - if (test_thread_flag(TIF_32BIT)) - task_size = STACK_TOP32; - - info.length = len; - info.low_limit = TASK_UNMAPPED_BASE; - info.high_limit = min(task_size, VA_EXCLUDE_START); - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - addr = vm_unmapped_area(&info); - - if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) { - VM_BUG_ON(addr != -ENOMEM); - info.low_limit = VA_EXCLUDE_END; - info.high_limit = task_size; - addr = vm_unmapped_area(&info); - } - - return addr; -} - -static unsigned long -hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - const unsigned long len, - const unsigned long pgoff, - const unsigned long flags) -{ - struct hstate *h = hstate_file(filp); - struct mm_struct *mm = current->mm; - unsigned long addr = addr0; - struct vm_unmapped_area_info info = {}; - - /* This should only ever run for 32-bit processes. */ - BUG_ON(!test_thread_flag(TIF_32BIT)); - - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.low_limit = PAGE_SIZE; - info.high_limit = mm->mmap_base; - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - addr = vm_unmapped_area(&info); - - /* - * A failed mmap() very likely causes application failure, - * so fall back to the bottom-up function here. This scenario - * can happen with large stack limits and large mmap() - * allocations. - */ - if (addr & ~PAGE_MASK) { - VM_BUG_ON(addr != -ENOMEM); - info.flags = 0; - info.low_limit = TASK_UNMAPPED_BASE; - info.high_limit = STACK_TOP32; - addr = vm_unmapped_area(&info); - } - - return addr; -} - -unsigned long -hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - unsigned long task_size = TASK_SIZE; - - if (test_thread_flag(TIF_32BIT)) - task_size = STACK_TOP32; - - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (len > task_size) - return -ENOMEM; - - if (flags & MAP_FIXED) { - if (prepare_hugepage_range(file, addr, len)) - return -EINVAL; - return addr; - } - - if (addr) { - addr = ALIGN(addr, huge_page_size(h)); - vma = find_vma(mm, addr); - if (task_size - len >= addr && - (!vma || addr + len <= vm_start_gap(vma))) - return addr; - } - if (!test_bit(MMF_TOPDOWN, &mm->flags)) - return hugetlb_get_unmapped_area_bottomup(file, addr, len, - pgoff, flags); - else - return hugetlb_get_unmapped_area_topdown(file, addr, len, - pgoff, flags); -} static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift) { diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 8e594cda6d77..e8e8b54b3037 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -435,24 +435,25 @@ void __init arch_cpu_finalize_init(void) os_check_bugs(); } -void apply_seal_endbr(s32 *start, s32 *end) +void apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { } -void apply_retpolines(s32 *start, s32 *end) +void apply_retpolines(s32 *start, s32 *end, struct module *mod) { } -void apply_returns(s32 *start, s32 *end) +void apply_returns(s32 *start, s32 *end, struct module *mod) { } void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, - s32 *start_cfi, s32 *end_cfi) + s32 *start_cfi, s32 *end_cfi, struct module *mod) { } -void apply_alternatives(struct alt_instr *start, struct alt_instr *end) +void apply_alternatives(struct alt_instr *start, struct alt_instr *end, + struct module *mod) { } @@ -468,6 +469,11 @@ void *text_poke(void *addr, const void *opcode, size_t len) return memcpy(addr, opcode, len); } +void *text_poke_copy(void *addr, const void *opcode, size_t len) +{ + return text_poke(addr, opcode, len); +} + void text_poke_sync(void) { } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 948707a3615e..6c633d93c639 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -83,6 +83,7 @@ config X86 select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN select ARCH_HAS_EARLY_DEBUG if KGDB select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_EXECMEM_ROX if X86_64 select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index bfc7cabf4017..39e6efc1a9ca 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -48,7 +48,8 @@ int __init init_vdso_image(const struct vdso_image *image) apply_alternatives((struct alt_instr *)(image->data + image->alt), (struct alt_instr *)(image->data + image->alt + - image->alt_len)); + image->alt_len), + NULL); return 0; } diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index ca9ae606aab9..dc03a647776d 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -96,16 +96,16 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; * instructions were patched in already: */ extern int alternatives_patched; +struct module; extern void alternative_instructions(void); -extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); -extern void apply_retpolines(s32 *start, s32 *end); -extern void apply_returns(s32 *start, s32 *end); -extern void apply_seal_endbr(s32 *start, s32 *end); +extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end, + struct module *mod); +extern void apply_retpolines(s32 *start, s32 *end, struct module *mod); +extern void apply_returns(s32 *start, s32 *end, struct module *mod); +extern void apply_seal_endbr(s32 *start, s32 *end, struct module *mod); extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine, - s32 *start_cfi, s32 *end_cfi); - -struct module; + s32 *start_cfi, s32 *end_cfi, struct module *mod); struct callthunk_sites { s32 *call_start, *call_end; diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index 1b93ff80b43b..c9fe207916f4 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -35,7 +35,7 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, } #define vma_alloc_zeroed_movable_folio(vma, vaddr) \ - vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr, false) + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr) #ifndef __pa #define __pa(x) __phys_addr((unsigned long)(x)) diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index f3d257c45225..d63576608ce7 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -17,7 +17,7 @@ extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; -extern unsigned long physmem_end; +extern unsigned long direct_map_physmem_end; static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index c55a79d5feae..e525cd85f999 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -234,9 +234,10 @@ do { \ */ #define percpu_add_op(size, qual, var, val) \ do { \ - const int pao_ID__ = (__builtin_constant_p(val) && \ - ((val) == 1 || (val) == -1)) ? \ - (int)(val) : 0; \ + const int pao_ID__ = \ + (__builtin_constant_p(val) && \ + ((val) == 1 || \ + (val) == (typeof(val))-1)) ? (int)(val) : 0; \ \ if (0) { \ typeof(var) pao_tmp__; \ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 4c2d080d26b4..593f10aabd45 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1775,6 +1775,43 @@ bool arch_is_platform_page(u64 paddr); #define arch_is_platform_page arch_is_platform_page #endif +/* + * Use set_p*_safe(), and elide TLB flushing, when confident that *no* + * TLB flush will be required as a result of the "set". For example, use + * in scenarios where it is known ahead of time that the routine is + * setting non-present entries, or re-setting an existing entry to the + * same value. Otherwise, use the typical "set" helpers and flush the + * TLB. + */ +#define set_pte_safe(ptep, pte) \ +({ \ + WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ + set_pte(ptep, pte); \ +}) + +#define set_pmd_safe(pmdp, pmd) \ +({ \ + WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ + set_pmd(pmdp, pmd); \ +}) + +#define set_pud_safe(pudp, pud) \ +({ \ + WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ + set_pud(pudp, pud); \ +}) + +#define set_p4d_safe(p4dp, p4d) \ +({ \ + WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ + set_p4d(p4dp, p4d); \ +}) + +#define set_pgd_safe(pgdp, pgd) \ +({ \ + WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ + set_pgd(pgdp, pgd); \ +}) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index a98e53491a4e..ec68f8369bdc 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -141,7 +141,7 @@ extern unsigned int ptrs_per_p4d; #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ #ifdef CONFIG_RANDOMIZE_MEMORY -# define PHYSMEM_END physmem_end +# define DIRECT_MAP_PHYSMEM_END direct_map_physmem_end #endif /* diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 4b2abce2e3e7..cc62ef70ccc0 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -89,6 +89,7 @@ int set_pages_rw(struct page *page, int numpages); int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid); bool kernel_page_present(struct page *page); extern int kernel_set_to_readonly; diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 6259f1937fe7..ab9e143ec9fe 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -35,6 +35,7 @@ extern void *text_poke(void *addr, const void *opcode, size_t len); extern void text_poke_sync(void); extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); extern void *text_poke_copy(void *addr, const void *opcode, size_t len); +#define text_poke_copy text_poke_copy extern void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, bool core_ok); extern void *text_poke_set(void *addr, int c, size_t len); extern int poke_int3_handler(struct pt_regs *regs); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index d17518ca19b8..243843e44e89 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -392,8 +392,10 @@ EXPORT_SYMBOL(BUG_func); * Rewrite the "call BUG_func" replacement to point to the target of the * indirect pv_ops call "call *disp(%ip)". */ -static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a) +static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a, + struct module *mod) { + u8 *wr_instr = module_writable_address(mod, instr); void *target, *bug = &BUG_func; s32 disp; @@ -403,14 +405,14 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a) } if (a->instrlen != 6 || - instr[0] != CALL_RIP_REL_OPCODE || - instr[1] != CALL_RIP_REL_MODRM) { + wr_instr[0] != CALL_RIP_REL_OPCODE || + wr_instr[1] != CALL_RIP_REL_MODRM) { pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n"); BUG(); } /* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */ - disp = *(s32 *)(instr + 2); + disp = *(s32 *)(wr_instr + 2); #ifdef CONFIG_X86_64 /* ff 15 00 00 00 00 call *0x0(%rip) */ /* target address is stored at "next instruction + disp". */ @@ -448,7 +450,8 @@ static inline u8 * instr_va(struct alt_instr *i) * to refetch changed I$ lines. */ void __init_or_module noinline apply_alternatives(struct alt_instr *start, - struct alt_instr *end) + struct alt_instr *end, + struct module *mod) { u8 insn_buff[MAX_PATCH_LEN]; u8 *instr, *replacement; @@ -477,6 +480,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, */ for (a = start; a < end; a++) { int insn_buff_sz = 0; + u8 *wr_instr, *wr_replacement; /* * In case of nested ALTERNATIVE()s the outer alternative might @@ -490,7 +494,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, } instr = instr_va(a); + wr_instr = module_writable_address(mod, instr); + replacement = (u8 *)&a->repl_offset + a->repl_offset; + wr_replacement = module_writable_address(mod, replacement); + BUG_ON(a->instrlen > sizeof(insn_buff)); BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); @@ -501,9 +509,9 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, * patch if feature is *NOT* present. */ if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) { - memcpy(insn_buff, instr, a->instrlen); + memcpy(insn_buff, wr_instr, a->instrlen); optimize_nops(instr, insn_buff, a->instrlen); - text_poke_early(instr, insn_buff, a->instrlen); + text_poke_early(wr_instr, insn_buff, a->instrlen); continue; } @@ -513,11 +521,12 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, instr, instr, a->instrlen, replacement, a->replacementlen, a->flags); - memcpy(insn_buff, replacement, a->replacementlen); + memcpy(insn_buff, wr_replacement, a->replacementlen); insn_buff_sz = a->replacementlen; if (a->flags & ALT_FLAG_DIRECT_CALL) { - insn_buff_sz = alt_replace_call(instr, insn_buff, a); + insn_buff_sz = alt_replace_call(instr, insn_buff, a, + mod); if (insn_buff_sz < 0) continue; } @@ -527,11 +536,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen); - DUMP_BYTES(ALT, instr, a->instrlen, "%px: old_insn: ", instr); + DUMP_BYTES(ALT, wr_instr, a->instrlen, "%px: old_insn: ", instr); DUMP_BYTES(ALT, replacement, a->replacementlen, "%px: rpl_insn: ", replacement); DUMP_BYTES(ALT, insn_buff, insn_buff_sz, "%px: final_insn: ", instr); - text_poke_early(instr, insn_buff, insn_buff_sz); + text_poke_early(wr_instr, insn_buff, insn_buff_sz); } kasan_enable_current(); @@ -722,18 +731,20 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) /* * Generated by 'objtool --retpoline'. */ -void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) +void __init_or_module noinline apply_retpolines(s32 *start, s32 *end, + struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); struct insn insn; int len, ret; u8 bytes[16]; u8 op1, op2; - ret = insn_decode_kernel(&insn, addr); + ret = insn_decode_kernel(&insn, wr_addr); if (WARN_ON_ONCE(ret < 0)) continue; @@ -761,9 +772,9 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) len = patch_retpoline(addr, &insn, bytes); if (len == insn.length) { optimize_nops(addr, bytes, len); - DUMP_BYTES(RETPOLINE, ((u8*)addr), len, "%px: orig: ", addr); + DUMP_BYTES(RETPOLINE, ((u8*)wr_addr), len, "%px: orig: ", addr); DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr); - text_poke_early(addr, bytes, len); + text_poke_early(wr_addr, bytes, len); } } } @@ -799,7 +810,8 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) return i; } -void __init_or_module noinline apply_returns(s32 *start, s32 *end) +void __init_or_module noinline apply_returns(s32 *start, s32 *end, + struct module *mod) { s32 *s; @@ -808,12 +820,13 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) for (s = start; s < end; s++) { void *dest = NULL, *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); struct insn insn; int len, ret; u8 bytes[16]; u8 op; - ret = insn_decode_kernel(&insn, addr); + ret = insn_decode_kernel(&insn, wr_addr); if (WARN_ON_ONCE(ret < 0)) continue; @@ -833,32 +846,35 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) len = patch_return(addr, &insn, bytes); if (len == insn.length) { - DUMP_BYTES(RET, ((u8*)addr), len, "%px: orig: ", addr); + DUMP_BYTES(RET, ((u8*)wr_addr), len, "%px: orig: ", addr); DUMP_BYTES(RET, ((u8*)bytes), len, "%px: repl: ", addr); - text_poke_early(addr, bytes, len); + text_poke_early(wr_addr, bytes, len); } } } #else -void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } +void __init_or_module noinline apply_returns(s32 *start, s32 *end, + struct module *mod) { } #endif /* CONFIG_MITIGATION_RETHUNK */ #else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */ -void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } -void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } +void __init_or_module noinline apply_retpolines(s32 *start, s32 *end, + struct module *mod) { } +void __init_or_module noinline apply_returns(s32 *start, s32 *end, + struct module *mod) { } #endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */ #ifdef CONFIG_X86_KERNEL_IBT -static void poison_cfi(void *addr); +static void poison_cfi(void *addr, void *wr_addr); -static void __init_or_module poison_endbr(void *addr, bool warn) +static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn) { u32 endbr, poison = gen_endbr_poison(); - if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr))) + if (WARN_ON_ONCE(get_kernel_nofault(endbr, wr_addr))) return; if (!is_endbr(endbr)) { @@ -873,7 +889,7 @@ static void __init_or_module poison_endbr(void *addr, bool warn) */ DUMP_BYTES(ENDBR, ((u8*)addr), 4, "%px: orig: ", addr); DUMP_BYTES(ENDBR, ((u8*)&poison), 4, "%px: repl: ", addr); - text_poke_early(addr, &poison, 4); + text_poke_early(wr_addr, &poison, 4); } /* @@ -882,22 +898,23 @@ static void __init_or_module poison_endbr(void *addr, bool warn) * Seal the functions for indirect calls by clobbering the ENDBR instructions * and the kCFI hash value. */ -void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end) +void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); - poison_endbr(addr, true); + poison_endbr(addr, wr_addr, true); if (IS_ENABLED(CONFIG_FINEIBT)) - poison_cfi(addr - 16); + poison_cfi(addr - 16, wr_addr - 16); } } #else -void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { } +void __init_or_module apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { } #endif /* CONFIG_X86_KERNEL_IBT */ @@ -1119,7 +1136,7 @@ static u32 decode_caller_hash(void *addr) } /* .retpoline_sites */ -static int cfi_disable_callers(s32 *start, s32 *end) +static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod) { /* * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate @@ -1131,20 +1148,23 @@ static int cfi_disable_callers(s32 *start, s32 *end) for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr; u32 hash; addr -= fineibt_caller_size; - hash = decode_caller_hash(addr); + wr_addr = module_writable_address(mod, addr); + hash = decode_caller_hash(wr_addr); + if (!hash) /* nocfi callers */ continue; - text_poke_early(addr, jmp, 2); + text_poke_early(wr_addr, jmp, 2); } return 0; } -static int cfi_enable_callers(s32 *start, s32 *end) +static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod) { /* * Re-enable kCFI, undo what cfi_disable_callers() did. @@ -1154,106 +1174,115 @@ static int cfi_enable_callers(s32 *start, s32 *end) for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr; u32 hash; addr -= fineibt_caller_size; - hash = decode_caller_hash(addr); + wr_addr = module_writable_address(mod, addr); + hash = decode_caller_hash(wr_addr); if (!hash) /* nocfi callers */ continue; - text_poke_early(addr, mov, 2); + text_poke_early(wr_addr, mov, 2); } return 0; } /* .cfi_sites */ -static int cfi_rand_preamble(s32 *start, s32 *end) +static int cfi_rand_preamble(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); u32 hash; - hash = decode_preamble_hash(addr); + hash = decode_preamble_hash(wr_addr); if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n", addr, addr, 5, addr)) return -EINVAL; hash = cfi_rehash(hash); - text_poke_early(addr + 1, &hash, 4); + text_poke_early(wr_addr + 1, &hash, 4); } return 0; } -static int cfi_rewrite_preamble(s32 *start, s32 *end) +static int cfi_rewrite_preamble(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); u32 hash; - hash = decode_preamble_hash(addr); + hash = decode_preamble_hash(wr_addr); if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n", addr, addr, 5, addr)) return -EINVAL; - text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size); - WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678); - text_poke_early(addr + fineibt_preamble_hash, &hash, 4); + text_poke_early(wr_addr, fineibt_preamble_start, fineibt_preamble_size); + WARN_ON(*(u32 *)(wr_addr + fineibt_preamble_hash) != 0x12345678); + text_poke_early(wr_addr + fineibt_preamble_hash, &hash, 4); } return 0; } -static void cfi_rewrite_endbr(s32 *start, s32 *end) +static void cfi_rewrite_endbr(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr = module_writable_address(mod, addr); - poison_endbr(addr+16, false); + poison_endbr(addr + 16, wr_addr + 16, false); } } /* .retpoline_sites */ -static int cfi_rand_callers(s32 *start, s32 *end) +static int cfi_rand_callers(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr; u32 hash; addr -= fineibt_caller_size; - hash = decode_caller_hash(addr); + wr_addr = module_writable_address(mod, addr); + hash = decode_caller_hash(wr_addr); if (hash) { hash = -cfi_rehash(hash); - text_poke_early(addr + 2, &hash, 4); + text_poke_early(wr_addr + 2, &hash, 4); } } return 0; } -static int cfi_rewrite_callers(s32 *start, s32 *end) +static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod) { s32 *s; for (s = start; s < end; s++) { void *addr = (void *)s + *s; + void *wr_addr; u32 hash; addr -= fineibt_caller_size; - hash = decode_caller_hash(addr); + wr_addr = module_writable_address(mod, addr); + hash = decode_caller_hash(wr_addr); if (hash) { - text_poke_early(addr, fineibt_caller_start, fineibt_caller_size); - WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678); - text_poke_early(addr + fineibt_caller_hash, &hash, 4); + text_poke_early(wr_addr, fineibt_caller_start, fineibt_caller_size); + WARN_ON(*(u32 *)(wr_addr + fineibt_caller_hash) != 0x12345678); + text_poke_early(wr_addr + fineibt_caller_hash, &hash, 4); } /* rely on apply_retpolines() */ } @@ -1262,8 +1291,9 @@ static int cfi_rewrite_callers(s32 *start, s32 *end) } static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, - s32 *start_cfi, s32 *end_cfi, bool builtin) + s32 *start_cfi, s32 *end_cfi, struct module *mod) { + bool builtin = mod ? false : true; int ret; if (WARN_ONCE(fineibt_preamble_size != 16, @@ -1281,7 +1311,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, * rewrite them. This disables all CFI. If this succeeds but any of the * later stages fails, we're without CFI. */ - ret = cfi_disable_callers(start_retpoline, end_retpoline); + ret = cfi_disable_callers(start_retpoline, end_retpoline, mod); if (ret) goto err; @@ -1292,11 +1322,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash); } - ret = cfi_rand_preamble(start_cfi, end_cfi); + ret = cfi_rand_preamble(start_cfi, end_cfi, mod); if (ret) goto err; - ret = cfi_rand_callers(start_retpoline, end_retpoline); + ret = cfi_rand_callers(start_retpoline, end_retpoline, mod); if (ret) goto err; } @@ -1308,7 +1338,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, return; case CFI_KCFI: - ret = cfi_enable_callers(start_retpoline, end_retpoline); + ret = cfi_enable_callers(start_retpoline, end_retpoline, mod); if (ret) goto err; @@ -1318,17 +1348,17 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, case CFI_FINEIBT: /* place the FineIBT preamble at func()-16 */ - ret = cfi_rewrite_preamble(start_cfi, end_cfi); + ret = cfi_rewrite_preamble(start_cfi, end_cfi, mod); if (ret) goto err; /* rewrite the callers to target func()-16 */ - ret = cfi_rewrite_callers(start_retpoline, end_retpoline); + ret = cfi_rewrite_callers(start_retpoline, end_retpoline, mod); if (ret) goto err; /* now that nobody targets func()+0, remove ENDBR there */ - cfi_rewrite_endbr(start_cfi, end_cfi); + cfi_rewrite_endbr(start_cfi, end_cfi, mod); if (builtin) pr_info("Using FineIBT CFI\n"); @@ -1347,7 +1377,7 @@ static inline void poison_hash(void *addr) *(u32 *)addr = 0; } -static void poison_cfi(void *addr) +static void poison_cfi(void *addr, void *wr_addr) { switch (cfi_mode) { case CFI_FINEIBT: @@ -1359,8 +1389,8 @@ static void poison_cfi(void *addr) * ud2 * 1: nop */ - poison_endbr(addr, false); - poison_hash(addr + fineibt_preamble_hash); + poison_endbr(addr, wr_addr, false); + poison_hash(wr_addr + fineibt_preamble_hash); break; case CFI_KCFI: @@ -1369,7 +1399,7 @@ static void poison_cfi(void *addr) * movl $0, %eax * .skip 11, 0x90 */ - poison_hash(addr + 1); + poison_hash(wr_addr + 1); break; default: @@ -1380,22 +1410,21 @@ static void poison_cfi(void *addr) #else static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, - s32 *start_cfi, s32 *end_cfi, bool builtin) + s32 *start_cfi, s32 *end_cfi, struct module *mod) { } #ifdef CONFIG_X86_KERNEL_IBT -static void poison_cfi(void *addr) { } +static void poison_cfi(void *addr, void *wr_addr) { } #endif #endif void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, - s32 *start_cfi, s32 *end_cfi) + s32 *start_cfi, s32 *end_cfi, struct module *mod) { return __apply_fineibt(start_retpoline, end_retpoline, - start_cfi, end_cfi, - /* .builtin = */ false); + start_cfi, end_cfi, mod); } #ifdef CONFIG_SMP @@ -1692,16 +1721,16 @@ void __init alternative_instructions(void) paravirt_set_cap(); __apply_fineibt(__retpoline_sites, __retpoline_sites_end, - __cfi_sites, __cfi_sites_end, true); + __cfi_sites, __cfi_sites_end, NULL); /* * Rewrite the retpolines, must be done before alternatives since * those can rewrite the retpoline thunks. */ - apply_retpolines(__retpoline_sites, __retpoline_sites_end); - apply_returns(__return_sites, __return_sites_end); + apply_retpolines(__retpoline_sites, __retpoline_sites_end, NULL); + apply_returns(__return_sites, __return_sites_end, NULL); - apply_alternatives(__alt_instructions, __alt_instructions_end); + apply_alternatives(__alt_instructions, __alt_instructions_end, NULL); /* * Now all calls are established. Apply the call thunks if @@ -1712,7 +1741,7 @@ void __init alternative_instructions(void) /* * Seal all functions that do not have their address taken. */ - apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); + apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end, NULL); #ifdef CONFIG_SMP /* Patch to UP if other cpus not imminent. */ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index adb09f78edb2..4dd0ad6c94d6 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -118,10 +118,13 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code, return ret; /* replace the text with the new text */ - if (ftrace_poke_late) + if (ftrace_poke_late) { text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL); - else - text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE); + } else { + mutex_lock(&text_mutex); + text_poke((void *)ip, new_code, MCOUNT_INSN_SIZE); + mutex_unlock(&text_mutex); + } return 0; } @@ -318,7 +321,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 }; unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE }; union ftrace_op_code_union op_ptr; - int ret; + void *ret; if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { start_offset = (unsigned long)ftrace_regs_caller; @@ -349,15 +352,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE); /* Copy ftrace_caller onto the trampoline memory */ - ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size); - if (WARN_ON(ret < 0)) + ret = text_poke_copy(trampoline, (void *)start_offset, size); + if (WARN_ON(!ret)) goto fail; ip = trampoline + size; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else - memcpy(ip, retq, sizeof(retq)); + text_poke_copy(ip, retq, sizeof(retq)); /* No need to test direct calls on created trampolines */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { @@ -365,8 +368,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) ip = trampoline + (jmp_offset - start_offset); if (WARN_ON(*(char *)ip != 0x75)) goto fail; - ret = copy_from_kernel_nofault(ip, x86_nops[2], 2); - if (ret < 0) + if (!text_poke_copy(ip, x86_nops[2], 2)) goto fail; } @@ -379,7 +381,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) */ ptr = (unsigned long *)(trampoline + size + RET_SIZE); - *ptr = (unsigned long)ops; + text_poke_copy(ptr, &ops, sizeof(unsigned long)); op_offset -= start_offset; memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE); @@ -395,7 +397,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) op_ptr.offset = offset; /* put in the new offset to the ftrace_ops */ - memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE); + text_poke_copy(trampoline + op_offset, &op_ptr, OP_REF_SIZE); /* put in the call to the function */ mutex_lock(&text_mutex); @@ -405,9 +407,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) * the depth accounting before the call already. */ dest = ftrace_ops_get_func(ops); - memcpy(trampoline + call_offset, - text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest), - CALL_INSN_SIZE); + text_poke_copy_locked(trampoline + call_offset, + text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest), + CALL_INSN_SIZE, false); mutex_unlock(&text_mutex); /* ALLOC_TRAMP flags lets us know we created it */ diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 837450b6e882..8984abd91c00 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -146,18 +146,21 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs, } if (apply) { - if (memcmp(loc, &zero, size)) { + void *wr_loc = module_writable_address(me, loc); + + if (memcmp(wr_loc, &zero, size)) { pr_err("x86/modules: Invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n", (int)ELF64_R_TYPE(rel[i].r_info), loc, val); return -ENOEXEC; } - write(loc, &val, size); + write(wr_loc, &val, size); } else { if (memcmp(loc, &val, size)) { pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n", (int)ELF64_R_TYPE(rel[i].r_info), loc, val); return -ENOEXEC; } + /* FIXME: needs care for ROX module allocations */ write(loc, &zero, size); } } @@ -224,7 +227,7 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { - const Elf_Shdr *s, *alt = NULL, *locks = NULL, + const Elf_Shdr *s, *alt = NULL, *orc = NULL, *orc_ip = NULL, *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL, *calls = NULL, *cfi = NULL; @@ -233,8 +236,6 @@ int module_finalize(const Elf_Ehdr *hdr, for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { if (!strcmp(".altinstructions", secstrings + s->sh_name)) alt = s; - if (!strcmp(".smp_locks", secstrings + s->sh_name)) - locks = s; if (!strcmp(".orc_unwind", secstrings + s->sh_name)) orc = s; if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name)) @@ -265,20 +266,20 @@ int module_finalize(const Elf_Ehdr *hdr, csize = cfi->sh_size; } - apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize); + apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize, me); } if (retpolines) { void *rseg = (void *)retpolines->sh_addr; - apply_retpolines(rseg, rseg + retpolines->sh_size); + apply_retpolines(rseg, rseg + retpolines->sh_size, me); } if (returns) { void *rseg = (void *)returns->sh_addr; - apply_returns(rseg, rseg + returns->sh_size); + apply_returns(rseg, rseg + returns->sh_size, me); } if (alt) { /* patch .altinstructions */ void *aseg = (void *)alt->sh_addr; - apply_alternatives(aseg, aseg + alt->sh_size); + apply_alternatives(aseg, aseg + alt->sh_size, me); } if (calls || alt) { struct callthunk_sites cs = {}; @@ -297,8 +298,28 @@ int module_finalize(const Elf_Ehdr *hdr, } if (ibt_endbr) { void *iseg = (void *)ibt_endbr->sh_addr; - apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size); + apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size, me); } + + if (orc && orc_ip) + unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size, + (void *)orc->sh_addr, orc->sh_size); + + return 0; +} + +int module_post_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s, *locks = NULL; + char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { + if (!strcmp(".smp_locks", secstrings + s->sh_name)) + locks = s; + } + if (locks) { void *lseg = (void *)locks->sh_addr; void *text = me->mem[MOD_TEXT].base; @@ -308,10 +329,6 @@ int module_finalize(const Elf_Ehdr *hdr, text, text_end); } - if (orc && orc_ip) - unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size, - (void *)orc->sh_addr, orc->sh_size); - return 0; } diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 87f8c9a71c49..776ae6fa7f2d 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -18,6 +18,7 @@ #include <linux/random.h> #include <linux/uaccess.h> #include <linux/elf.h> +#include <linux/hugetlb.h> #include <asm/elf.h> #include <asm/ia32.h> @@ -25,8 +26,10 @@ /* * Align a virtual address to avoid aliasing in the I$ on AMD F15h. */ -static unsigned long get_align_mask(void) +static unsigned long get_align_mask(struct file *filp) { + if (filp && is_file_hugepages(filp)) + return huge_page_mask_align(filp); /* handle 32- and 64-bit case with a single conditional */ if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32()))) return 0; @@ -49,7 +52,7 @@ static unsigned long get_align_mask(void) */ static unsigned long get_align_bits(void) { - return va_align.bits & get_align_mask(); + return va_align.bits & get_align_mask(NULL); } static int __init control_va_addr_alignment(char *str) @@ -148,12 +151,15 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, info.length = len; info.low_limit = begin; info.high_limit = end; - info.align_offset = pgoff << PAGE_SHIFT; - info.start_gap = stack_guard_placement(vm_flags); + if (!(filp && is_file_hugepages(filp))) { + info.align_offset = pgoff << PAGE_SHIFT; + info.start_gap = stack_guard_placement(vm_flags); + } if (filp) { - info.align_mask = get_align_mask(); + info.align_mask = get_align_mask(filp); info.align_offset += get_align_bits(); } + return vm_unmapped_area(&info); } @@ -199,7 +205,10 @@ get_unmapped_area: info.low_limit = PAGE_SIZE; info.high_limit = get_mmap_base(0); - info.start_gap = stack_guard_placement(vm_flags); + if (!(filp && is_file_hugepages(filp))) { + info.start_gap = stack_guard_placement(vm_flags); + info.align_offset = pgoff << PAGE_SHIFT; + } /* * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area @@ -211,9 +220,8 @@ get_unmapped_area: if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall()) info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; - info.align_offset = pgoff << PAGE_SHIFT; if (filp) { - info.align_mask = get_align_mask(); + info.align_mask = get_align_mask(filp); info.align_offset += get_align_bits(); } addr = vm_unmapped_area(&info); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 807a5859a3c4..58f7f2bd535d 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -19,107 +19,6 @@ #include <asm/tlbflush.h> #include <asm/elf.h> -#ifdef CONFIG_HUGETLB_PAGE -static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info = {}; - - info.length = len; - info.low_limit = get_mmap_base(1); - - /* - * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area - * in the full address space. - */ - info.high_limit = in_32bit_syscall() ? - task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW); - - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - return vm_unmapped_area(&info); -} - -static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info = {}; - - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.low_limit = PAGE_SIZE; - info.high_limit = get_mmap_base(0); - - /* - * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area - * in the full address space. - */ - if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall()) - info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; - - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - addr = vm_unmapped_area(&info); - - /* - * A failed mmap() very likely causes application failure, - * so fall back to the bottom-up function here. This scenario - * can happen with large stack limits and large mmap() - * allocations. - */ - if (addr & ~PAGE_MASK) { - VM_BUG_ON(addr != -ENOMEM); - info.flags = 0; - info.low_limit = TASK_UNMAPPED_BASE; - info.high_limit = TASK_SIZE_LOW; - addr = vm_unmapped_area(&info); - } - - return addr; -} - -unsigned long -hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - - if (len & ~huge_page_mask(h)) - return -EINVAL; - - if (len > TASK_SIZE) - return -ENOMEM; - - /* No address checking. See comment at mmap_address_hint_valid() */ - if (flags & MAP_FIXED) { - if (prepare_hugepage_range(file, addr, len)) - return -EINVAL; - return addr; - } - - if (addr) { - addr &= huge_page_mask(h); - if (!mmap_address_hint_valid(addr, len)) - goto get_unmapped_area; - - vma = find_vma(mm, addr); - if (!vma || addr + len <= vm_start_gap(vma)) - return addr; - } - -get_unmapped_area: - if (!test_bit(MMF_TOPDOWN, &mm->flags)) - return hugetlb_get_unmapped_area_bottomup(file, addr, len, - pgoff, flags); - else - return hugetlb_get_unmapped_area_topdown(file, addr, len, - pgoff, flags); -} -#endif /* CONFIG_HUGETLB_PAGE */ #ifdef CONFIG_X86_64 bool __init arch_hugetlb_valid_size(unsigned long size) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 101725c149c4..c6d29f283001 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1058,18 +1058,53 @@ unsigned long arch_max_swapfile_size(void) #ifdef CONFIG_EXECMEM static struct execmem_info execmem_info __ro_after_init; +#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX +void execmem_fill_trapping_insns(void *ptr, size_t size, bool writeable) +{ + /* fill memory with INT3 instructions */ + if (writeable) + memset(ptr, INT3_INSN_OPCODE, size); + else + text_poke_set(ptr, INT3_INSN_OPCODE, size); +} +#endif + struct execmem_info __init *execmem_arch_setup(void) { unsigned long start, offset = 0; + enum execmem_range_flags flags; + pgprot_t pgprot; if (kaslr_enabled()) offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE; start = MODULES_VADDR + offset; + if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX)) { + pgprot = PAGE_KERNEL_ROX; + flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE; + } else { + pgprot = PAGE_KERNEL; + flags = EXECMEM_KASAN_SHADOW; + } + execmem_info = (struct execmem_info){ .ranges = { - [EXECMEM_DEFAULT] = { + [EXECMEM_MODULE_TEXT] = { + .flags = flags, + .start = start, + .end = MODULES_END, + .pgprot = pgprot, + .alignment = MODULE_ALIGN, + }, + [EXECMEM_KPROBES ... EXECMEM_BPF] = { + .flags = EXECMEM_KASAN_SHADOW, + .start = start, + .end = MODULES_END, + .pgprot = PAGE_KERNEL, + .alignment = MODULE_ALIGN, + }, + [EXECMEM_MODULE_DATA] = { .flags = EXECMEM_KASAN_SHADOW, .start = start, .end = MODULES_END, diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ff253648706f..01ea7c6df303 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -961,7 +961,7 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1; int ret; - if (WARN_ON_ONCE(end > PHYSMEM_END)) + if (WARN_ON_ONCE(end > DIRECT_MAP_PHYSMEM_END)) return -ERANGE; ret = __add_pages(nid, start_pfn, nr_pages, params); @@ -985,22 +985,32 @@ int arch_add_memory(int nid, u64 start, u64 size, return add_pages(nid, start_pfn, nr_pages, params); } -static void __meminit free_pagetable(struct page *page, int order) +static void free_reserved_pages(struct page *page, unsigned long nr_pages) { - unsigned long magic; - unsigned int nr_pages = 1 << order; + while (nr_pages--) + free_reserved_page(page++); +} +static void __meminit free_pagetable(struct page *page, int order) +{ /* bootmem page has reserved flag */ if (PageReserved(page)) { - magic = page->index; - if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) { + unsigned long nr_pages = 1 << order; +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE + enum bootmem_type type = bootmem_type(page); + + if (type == SECTION_INFO || type == MIX_SECTION_INFO) { while (nr_pages--) put_page_bootmem(page++); - } else - while (nr_pages--) - free_reserved_page(page++); - } else + } else { + free_reserved_pages(page, nr_pages); + } +#else + free_reserved_pages(page, nr_pages); +#endif + } else { free_pages((unsigned long)page_address(page), order); + } } static void __meminit free_hugepage_table(struct page *page, diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index e17e6e27b7ec..11a93542d198 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -52,7 +52,7 @@ static __initdata struct kaslr_memory_region { } kaslr_regions[] = { { .base = &page_offset_base, - .end = &physmem_end, + .end = &direct_map_physmem_end, }, { .base = &vmalloc_base, @@ -62,8 +62,12 @@ static __initdata struct kaslr_memory_region { }, }; -/* The end of the possible address space for physical memory */ -unsigned long physmem_end __ro_after_init; +/* + * The end of the physical address space that can be mapped directly by the + * kernel. This starts out at (1<<MAX_PHYSMEM_BITS) - 1), but KASLR may reduce + * that in order to increase the available entropy for mapping other regions. + */ +unsigned long direct_map_physmem_end __ro_after_init; /* Get size in bytes used by the memory region */ static inline unsigned long get_padding(struct kaslr_memory_region *region) @@ -94,7 +98,7 @@ void __init kernel_randomize_memory(void) BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); /* Preset the end of the possible address space for physical memory */ - physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1); + direct_map_physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1); if (!kaslr_memory_enabled()) return; @@ -145,7 +149,7 @@ void __init kernel_randomize_memory(void) vaddr += get_padding(&kaslr_regions[i]); /* * KASLR trims the maximum possible size of the - * direct-map. Update the physmem_end boundary. + * direct-map. Update the direct_map_physmem_end boundary. * No rounding required as the region starts * PUD aligned and size is in units of TB. */ diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 44f7b2ea6a07..069e421c2247 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -2444,6 +2444,14 @@ int set_direct_map_default_noflush(struct page *page) return __set_pages_p(page, 1); } +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) +{ + if (valid) + return __set_pages_p(page, nr); + + return __set_pages_np(page, nr); +} + #ifdef CONFIG_DEBUG_PAGEALLOC void __kernel_map_pages(struct page *page, int numpages, int enable) { diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index fa07c686cbcc..cc5dba738389 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -8,3 +8,4 @@ generic-y += parport.h generic-y += qrwlock.h generic-y += qspinlock.h generic-y += user.h +generic-y += text-patching.h diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 1ff0c858544f..99d4ccee7f6e 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -113,6 +113,9 @@ #define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ +#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */ +#define MADV_GUARD_REMOVE 103 /* unguard range */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index b3acbc4174fb..a738e7745865 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -1047,7 +1047,7 @@ void binder_alloc_vma_close(struct binder_alloc *alloc) /** * binder_alloc_free_page() - shrinker callback to free pages * @item: item to free - * @lock: lock protecting the item + * @lru: list_lru instance of the item * @cb_arg: callback argument * * Called from list_lru_walk() in binder_shrink_scan() to free @@ -1055,9 +1055,8 @@ void binder_alloc_vma_close(struct binder_alloc *alloc) */ enum lru_status binder_alloc_free_page(struct list_head *item, struct list_lru_one *lru, - spinlock_t *lock, void *cb_arg) - __must_hold(lock) + __must_hold(&lru->lock) { struct binder_lru_page *page = container_of(item, typeof(*page), lru); struct binder_alloc *alloc = page->alloc; @@ -1092,7 +1091,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, list_lru_isolate(lru, item); spin_unlock(&alloc->lock); - spin_unlock(lock); + spin_unlock(&lru->lock); if (vma) { trace_binder_unmap_user_start(alloc, index); @@ -1106,7 +1105,6 @@ enum lru_status binder_alloc_free_page(struct list_head *item, mmput_async(mm); __free_page(page_to_free); - spin_lock(lock); return LRU_REMOVED_RETRY; err_invalid_vma: diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 70387234477e..c02c8ebcb466 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -118,7 +118,7 @@ static inline void binder_selftest_alloc(struct binder_alloc *alloc) {} #endif enum lru_status binder_alloc_free_page(struct list_head *item, struct list_lru_one *lru, - spinlock_t *lock, void *cb_arg); + void *cb_arg); struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, size_t data_size, size_t offsets_size, diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index 6aea609b795c..402b7b175863 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -94,6 +94,7 @@ endchoice config ZRAM_DEF_COMP string + depends on ZRAM default "lzo-rle" if ZRAM_DEF_COMP_LZORLE default "lzo" if ZRAM_DEF_COMP_LZO default "lz4" if ZRAM_DEF_COMP_LZ4 diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index ad9c9bc3ccfc..3dee026988dc 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -178,11 +178,105 @@ static inline u32 zram_get_priority(struct zram *zram, u32 index) static void zram_accessed(struct zram *zram, u32 index) { zram_clear_flag(zram, index, ZRAM_IDLE); + zram_clear_flag(zram, index, ZRAM_PP_SLOT); #ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME zram->table[index].ac_time = ktime_get_boottime(); #endif } +#if defined CONFIG_ZRAM_WRITEBACK || defined CONFIG_ZRAM_MULTI_COMP +struct zram_pp_slot { + unsigned long index; + struct list_head entry; +}; + +/* + * A post-processing bucket is, essentially, a size class, this defines + * the range (in bytes) of pp-slots sizes in particular bucket. + */ +#define PP_BUCKET_SIZE_RANGE 64 +#define NUM_PP_BUCKETS ((PAGE_SIZE / PP_BUCKET_SIZE_RANGE) + 1) + +struct zram_pp_ctl { + struct list_head pp_buckets[NUM_PP_BUCKETS]; +}; + +static struct zram_pp_ctl *init_pp_ctl(void) +{ + struct zram_pp_ctl *ctl; + u32 idx; + + ctl = kmalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return NULL; + + for (idx = 0; idx < NUM_PP_BUCKETS; idx++) + INIT_LIST_HEAD(&ctl->pp_buckets[idx]); + return ctl; +} + +static void release_pp_slot(struct zram *zram, struct zram_pp_slot *pps) +{ + list_del_init(&pps->entry); + + zram_slot_lock(zram, pps->index); + zram_clear_flag(zram, pps->index, ZRAM_PP_SLOT); + zram_slot_unlock(zram, pps->index); + + kfree(pps); +} + +static void release_pp_ctl(struct zram *zram, struct zram_pp_ctl *ctl) +{ + u32 idx; + + if (!ctl) + return; + + for (idx = 0; idx < NUM_PP_BUCKETS; idx++) { + while (!list_empty(&ctl->pp_buckets[idx])) { + struct zram_pp_slot *pps; + + pps = list_first_entry(&ctl->pp_buckets[idx], + struct zram_pp_slot, + entry); + release_pp_slot(zram, pps); + } + } + + kfree(ctl); +} + +static void place_pp_slot(struct zram *zram, struct zram_pp_ctl *ctl, + struct zram_pp_slot *pps) +{ + u32 idx; + + idx = zram_get_obj_size(zram, pps->index) / PP_BUCKET_SIZE_RANGE; + list_add(&pps->entry, &ctl->pp_buckets[idx]); + + zram_set_flag(zram, pps->index, ZRAM_PP_SLOT); +} + +static struct zram_pp_slot *select_pp_slot(struct zram_pp_ctl *ctl) +{ + struct zram_pp_slot *pps = NULL; + s32 idx = NUM_PP_BUCKETS - 1; + + /* The higher the bucket id the more optimal slot post-processing is */ + while (idx >= 0) { + pps = list_first_entry_or_null(&ctl->pp_buckets[idx], + struct zram_pp_slot, + entry); + if (pps) + break; + + idx--; + } + return pps; +} +#endif + static inline void update_used_max(struct zram *zram, const unsigned long pages) { @@ -296,19 +390,28 @@ static void mark_idle(struct zram *zram, ktime_t cutoff) for (index = 0; index < nr_pages; index++) { /* - * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race. - * See the comment in writeback_store. + * Do not mark ZRAM_SAME slots as ZRAM_IDLE, because no + * post-processing (recompress, writeback) happens to the + * ZRAM_SAME slot. + * + * And ZRAM_WB slots simply cannot be ZRAM_IDLE. */ zram_slot_lock(zram, index); - if (zram_allocated(zram, index) && - !zram_test_flag(zram, index, ZRAM_UNDER_WB)) { + if (!zram_allocated(zram, index) || + zram_test_flag(zram, index, ZRAM_WB) || + zram_test_flag(zram, index, ZRAM_SAME)) { + zram_slot_unlock(zram, index); + continue; + } + #ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME - is_idle = !cutoff || ktime_after(cutoff, - zram->table[index].ac_time); + is_idle = !cutoff || + ktime_after(cutoff, zram->table[index].ac_time); #endif - if (is_idle) - zram_set_flag(zram, index, ZRAM_IDLE); - } + if (is_idle) + zram_set_flag(zram, index, ZRAM_IDLE); + else + zram_clear_flag(zram, index, ZRAM_IDLE); zram_slot_unlock(zram, index); } } @@ -587,11 +690,57 @@ static void read_from_bdev_async(struct zram *zram, struct page *page, #define IDLE_WRITEBACK (1<<1) #define INCOMPRESSIBLE_WRITEBACK (1<<2) +static int scan_slots_for_writeback(struct zram *zram, u32 mode, + unsigned long nr_pages, + unsigned long index, + struct zram_pp_ctl *ctl) +{ + struct zram_pp_slot *pps = NULL; + + for (; nr_pages != 0; index++, nr_pages--) { + if (!pps) + pps = kmalloc(sizeof(*pps), GFP_KERNEL); + if (!pps) + return -ENOMEM; + + INIT_LIST_HEAD(&pps->entry); + + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index)) + goto next; + + if (zram_test_flag(zram, index, ZRAM_WB) || + zram_test_flag(zram, index, ZRAM_SAME)) + goto next; + + if (mode & IDLE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_IDLE)) + goto next; + if (mode & HUGE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_HUGE)) + goto next; + if (mode & INCOMPRESSIBLE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE)) + goto next; + + pps->index = index; + place_pp_slot(zram, ctl, pps); + pps = NULL; +next: + zram_slot_unlock(zram, index); + } + + kfree(pps); + return 0; +} + static ssize_t writeback_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct zram *zram = dev_to_zram(dev); unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + struct zram_pp_ctl *ctl = NULL; + struct zram_pp_slot *pps; unsigned long index = 0; struct bio bio; struct bio_vec bio_vec; @@ -626,6 +775,12 @@ static ssize_t writeback_store(struct device *dev, goto release_init_lock; } + /* Do not permit concurrent post-processing actions. */ + if (atomic_xchg(&zram->pp_in_progress, 1)) { + up_read(&zram->init_lock); + return -EAGAIN; + } + if (!zram->backing_dev) { ret = -ENODEV; goto release_init_lock; @@ -637,7 +792,15 @@ static ssize_t writeback_store(struct device *dev, goto release_init_lock; } - for (; nr_pages != 0; index++, nr_pages--) { + ctl = init_pp_ctl(); + if (!ctl) { + ret = -ENOMEM; + goto release_init_lock; + } + + scan_slots_for_writeback(zram, mode, nr_pages, index, ctl); + + while ((pps = select_pp_slot(ctl))) { spin_lock(&zram->wb_limit_lock); if (zram->wb_limit_enable && !zram->bd_wb_limit) { spin_unlock(&zram->wb_limit_lock); @@ -654,38 +817,20 @@ static ssize_t writeback_store(struct device *dev, } } + index = pps->index; zram_slot_lock(zram, index); - if (!zram_allocated(zram, index)) - goto next; - - if (zram_test_flag(zram, index, ZRAM_WB) || - zram_test_flag(zram, index, ZRAM_SAME) || - zram_test_flag(zram, index, ZRAM_UNDER_WB)) - goto next; - - if (mode & IDLE_WRITEBACK && - !zram_test_flag(zram, index, ZRAM_IDLE)) - goto next; - if (mode & HUGE_WRITEBACK && - !zram_test_flag(zram, index, ZRAM_HUGE)) - goto next; - if (mode & INCOMPRESSIBLE_WRITEBACK && - !zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE)) - goto next; - /* - * Clearing ZRAM_UNDER_WB is duty of caller. - * IOW, zram_free_page never clear it. + * scan_slots() sets ZRAM_PP_SLOT and relases slot lock, so + * slots can change in the meantime. If slots are accessed or + * freed they lose ZRAM_PP_SLOT flag and hence we don't + * post-process them. */ - zram_set_flag(zram, index, ZRAM_UNDER_WB); - /* Need for hugepage writeback racing */ - zram_set_flag(zram, index, ZRAM_IDLE); + if (!zram_test_flag(zram, index, ZRAM_PP_SLOT)) + goto next; zram_slot_unlock(zram, index); + if (zram_read_page(zram, page, index, NULL)) { - zram_slot_lock(zram, index); - zram_clear_flag(zram, index, ZRAM_UNDER_WB); - zram_clear_flag(zram, index, ZRAM_IDLE); - zram_slot_unlock(zram, index); + release_pp_slot(zram, pps); continue; } @@ -700,10 +845,7 @@ static ssize_t writeback_store(struct device *dev, */ err = submit_bio_wait(&bio); if (err) { - zram_slot_lock(zram, index); - zram_clear_flag(zram, index, ZRAM_UNDER_WB); - zram_clear_flag(zram, index, ZRAM_IDLE); - zram_slot_unlock(zram, index); + release_pp_slot(zram, pps); /* * BIO errors are not fatal, we continue and simply * attempt to writeback the remaining objects (pages). @@ -717,25 +859,19 @@ static ssize_t writeback_store(struct device *dev, } atomic64_inc(&zram->stats.bd_writes); + zram_slot_lock(zram, index); /* - * We released zram_slot_lock so need to check if the slot was - * changed. If there is freeing for the slot, we can catch it - * easily by zram_allocated. - * A subtle case is the slot is freed/reallocated/marked as - * ZRAM_IDLE again. To close the race, idle_store doesn't - * mark ZRAM_IDLE once it found the slot was ZRAM_UNDER_WB. - * Thus, we could close the race by checking ZRAM_IDLE bit. + * Same as above, we release slot lock during writeback so + * slot can change under us: slot_free() or slot_free() and + * reallocation (zram_write_page()). In both cases slot loses + * ZRAM_PP_SLOT flag. No concurrent post-processing can set + * ZRAM_PP_SLOT on such slots until current post-processing + * finishes. */ - zram_slot_lock(zram, index); - if (!zram_allocated(zram, index) || - !zram_test_flag(zram, index, ZRAM_IDLE)) { - zram_clear_flag(zram, index, ZRAM_UNDER_WB); - zram_clear_flag(zram, index, ZRAM_IDLE); + if (!zram_test_flag(zram, index, ZRAM_PP_SLOT)) goto next; - } zram_free_page(zram, index); - zram_clear_flag(zram, index, ZRAM_UNDER_WB); zram_set_flag(zram, index, ZRAM_WB); zram_set_element(zram, index, blk_idx); blk_idx = 0; @@ -746,12 +882,15 @@ static ssize_t writeback_store(struct device *dev, spin_unlock(&zram->wb_limit_lock); next: zram_slot_unlock(zram, index); + release_pp_slot(zram, pps); } if (blk_idx) free_block_bdev(zram, blk_idx); __free_page(page); release_init_lock: + release_pp_ctl(zram, ctl); + atomic_set(&zram->pp_in_progress, 0); up_read(&zram->init_lock); return ret; @@ -1342,19 +1481,17 @@ static void zram_free_page(struct zram *zram, size_t index) #ifdef CONFIG_ZRAM_TRACK_ENTRY_ACTIME zram->table[index].ac_time = 0; #endif - if (zram_test_flag(zram, index, ZRAM_IDLE)) - zram_clear_flag(zram, index, ZRAM_IDLE); + + zram_clear_flag(zram, index, ZRAM_IDLE); + zram_clear_flag(zram, index, ZRAM_INCOMPRESSIBLE); + zram_clear_flag(zram, index, ZRAM_PP_SLOT); + zram_set_priority(zram, index, 0); if (zram_test_flag(zram, index, ZRAM_HUGE)) { zram_clear_flag(zram, index, ZRAM_HUGE); atomic64_dec(&zram->stats.huge_pages); } - if (zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE)) - zram_clear_flag(zram, index, ZRAM_INCOMPRESSIBLE); - - zram_set_priority(zram, index, 0); - if (zram_test_flag(zram, index, ZRAM_WB)) { zram_clear_flag(zram, index, ZRAM_WB); free_block_bdev(zram, zram_get_element(zram, index)); @@ -1378,13 +1515,11 @@ static void zram_free_page(struct zram *zram, size_t index) zs_free(zram->mem_pool, handle); atomic64_sub(zram_get_obj_size(zram, index), - &zram->stats.compr_data_size); + &zram->stats.compr_data_size); out: atomic64_dec(&zram->stats.pages_stored); zram_set_handle(zram, index, 0); zram_set_obj_size(zram, index, 0); - WARN_ON_ONCE(zram->table[index].flags & - ~(1UL << ZRAM_UNDER_WB)); } /* @@ -1648,6 +1783,52 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, } #ifdef CONFIG_ZRAM_MULTI_COMP +#define RECOMPRESS_IDLE (1 << 0) +#define RECOMPRESS_HUGE (1 << 1) + +static int scan_slots_for_recompress(struct zram *zram, u32 mode, + struct zram_pp_ctl *ctl) +{ + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + struct zram_pp_slot *pps = NULL; + unsigned long index; + + for (index = 0; index < nr_pages; index++) { + if (!pps) + pps = kmalloc(sizeof(*pps), GFP_KERNEL); + if (!pps) + return -ENOMEM; + + INIT_LIST_HEAD(&pps->entry); + + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index)) + goto next; + + if (mode & RECOMPRESS_IDLE && + !zram_test_flag(zram, index, ZRAM_IDLE)) + goto next; + + if (mode & RECOMPRESS_HUGE && + !zram_test_flag(zram, index, ZRAM_HUGE)) + goto next; + + if (zram_test_flag(zram, index, ZRAM_WB) || + zram_test_flag(zram, index, ZRAM_SAME) || + zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE)) + goto next; + + pps->index = index; + place_pp_slot(zram, ctl, pps); + pps = NULL; +next: + zram_slot_unlock(zram, index); + } + + kfree(pps); + return 0; +} + /* * This function will decompress (unless it's ZRAM_HUGE) the page and then * attempt to compress it using provided compression algorithm priority @@ -1655,7 +1836,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, * * Corresponding ZRAM slot should be locked. */ -static int zram_recompress(struct zram *zram, u32 index, struct page *page, +static int recompress_slot(struct zram *zram, u32 index, struct page *page, u64 *num_recomp_pages, u32 threshold, u32 prio, u32 prio_max) { @@ -1685,6 +1866,13 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, if (ret) return ret; + /* + * We touched this entry so mark it as non-IDLE. This makes sure that + * we don't preserve IDLE flag and don't incorrectly pick this entry + * for different post-processing type (e.g. writeback). + */ + zram_clear_flag(zram, index, ZRAM_IDLE); + class_index_old = zs_lookup_class_index(zram->mem_pool, comp_len_old); /* * Iterate the secondary comp algorithms list (in order of priority) @@ -1798,20 +1986,17 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, return 0; } -#define RECOMPRESS_IDLE (1 << 0) -#define RECOMPRESS_HUGE (1 << 1) - static ssize_t recompress_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { u32 prio = ZRAM_SECONDARY_COMP, prio_max = ZRAM_MAX_COMPS; struct zram *zram = dev_to_zram(dev); - unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; char *args, *param, *val, *algo = NULL; u64 num_recomp_pages = ULLONG_MAX; + struct zram_pp_ctl *ctl = NULL; + struct zram_pp_slot *pps; u32 mode = 0, threshold = 0; - unsigned long index; struct page *page; ssize_t ret; @@ -1881,6 +2066,12 @@ static ssize_t recompress_store(struct device *dev, goto release_init_lock; } + /* Do not permit concurrent post-processing actions. */ + if (atomic_xchg(&zram->pp_in_progress, 1)) { + up_read(&zram->init_lock); + return -EAGAIN; + } + if (algo) { bool found = false; @@ -1907,36 +2098,32 @@ static ssize_t recompress_store(struct device *dev, goto release_init_lock; } + ctl = init_pp_ctl(); + if (!ctl) { + ret = -ENOMEM; + goto release_init_lock; + } + + scan_slots_for_recompress(zram, mode, ctl); + ret = len; - for (index = 0; index < nr_pages; index++) { + while ((pps = select_pp_slot(ctl))) { int err = 0; if (!num_recomp_pages) break; - zram_slot_lock(zram, index); - - if (!zram_allocated(zram, index)) - goto next; - - if (mode & RECOMPRESS_IDLE && - !zram_test_flag(zram, index, ZRAM_IDLE)) - goto next; - - if (mode & RECOMPRESS_HUGE && - !zram_test_flag(zram, index, ZRAM_HUGE)) - goto next; - - if (zram_test_flag(zram, index, ZRAM_WB) || - zram_test_flag(zram, index, ZRAM_UNDER_WB) || - zram_test_flag(zram, index, ZRAM_SAME) || - zram_test_flag(zram, index, ZRAM_INCOMPRESSIBLE)) + zram_slot_lock(zram, pps->index); + if (!zram_test_flag(zram, pps->index, ZRAM_PP_SLOT)) goto next; - err = zram_recompress(zram, index, page, &num_recomp_pages, - threshold, prio, prio_max); + err = recompress_slot(zram, pps->index, page, + &num_recomp_pages, threshold, + prio, prio_max); next: - zram_slot_unlock(zram, index); + zram_slot_unlock(zram, pps->index); + release_pp_slot(zram, pps); + if (err) { ret = err; break; @@ -1948,6 +2135,8 @@ next: __free_page(page); release_init_lock: + release_pp_ctl(zram, ctl); + atomic_set(&zram->pp_in_progress, 0); up_read(&zram->init_lock); return ret; } @@ -2105,7 +2294,7 @@ static void zram_destroy_comps(struct zram *zram) { u32 prio; - for (prio = 0; prio < ZRAM_MAX_COMPS; prio++) { + for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { struct zcomp *comp = zram->comps[prio]; zram->comps[prio] = NULL; @@ -2144,6 +2333,7 @@ static void zram_reset_device(struct zram *zram) zram->disksize = 0; zram_destroy_comps(zram); memset(&zram->stats, 0, sizeof(zram->stats)); + atomic_set(&zram->pp_in_progress, 0); reset_bdev(zram); comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor); @@ -2176,7 +2366,7 @@ static ssize_t disksize_store(struct device *dev, goto out_unlock; } - for (prio = 0; prio < ZRAM_MAX_COMPS; prio++) { + for (prio = ZRAM_PRIMARY_COMP; prio < ZRAM_MAX_COMPS; prio++) { if (!zram->comp_algs[prio]) continue; @@ -2381,6 +2571,9 @@ static int zram_add(void) zram->disk->fops = &zram_devops; zram->disk->private_data = zram; snprintf(zram->disk->disk_name, 16, "zram%d", device_id); + atomic_set(&zram->pp_in_progress, 0); + zram_comp_params_reset(zram); + comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor); /* Actual capacity set using sysfs (/sys/block/zram<id>/disksize */ set_capacity(zram->disk, 0); @@ -2388,9 +2581,6 @@ static int zram_add(void) if (ret) goto out_cleanup_disk; - zram_comp_params_reset(zram); - comp_algorithm_set(zram, ZRAM_PRIMARY_COMP, default_compressor); - zram_debugfs_register(zram); pr_info("Added device: %s\n", zram->disk->disk_name); return device_id; diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index cfc8c059db63..134be414e210 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -47,7 +47,7 @@ enum zram_pageflags { ZRAM_SAME = ZRAM_FLAG_SHIFT, /* Page consists the same element */ ZRAM_WB, /* page is stored on backing_device */ - ZRAM_UNDER_WB, /* page is under writeback */ + ZRAM_PP_SLOT, /* Selected for post-processing */ ZRAM_HUGE, /* Incompressible page */ ZRAM_IDLE, /* not accessed page since last idle marking */ ZRAM_INCOMPRESSIBLE, /* none of the algorithms could compress it */ @@ -139,5 +139,6 @@ struct zram { #ifdef CONFIG_ZRAM_MEMORY_TRACKING struct dentry *debugfs_dir; #endif + atomic_t pp_in_progress; }; #endif diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index a28197b88c92..18f839721813 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -6,6 +6,7 @@ */ #include <linux/iova.h> +#include <linux/kmemleak.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/smp.h> @@ -673,6 +674,11 @@ static struct iova_magazine *iova_depot_pop(struct iova_rcache *rcache) { struct iova_magazine *mag = rcache->depot; + /* + * As the mag->next pointer is moved to rcache->depot and reset via + * the mag->size assignment, mark it as a transient false positive. + */ + kmemleak_transient_leak(mag->next); rcache->depot = mag->next; mag->size = IOVA_MAG_SIZE; rcache->depot_size--; diff --git a/fs/buffer.c b/fs/buffer.c index b158cb7a5038..cc8452f60251 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -736,15 +736,12 @@ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ - folio_memcg_lock(folio); newly_dirty = !folio_test_set_dirty(folio); spin_unlock(&mapping->i_private_lock); if (newly_dirty) __folio_mark_dirty(folio, mapping, 1); - folio_memcg_unlock(folio); - if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); @@ -1193,13 +1190,11 @@ void mark_buffer_dirty(struct buffer_head *bh) struct folio *folio = bh->b_folio; struct address_space *mapping = NULL; - folio_memcg_lock(folio); if (!folio_test_set_dirty(folio)) { mapping = folio->mapping; if (mapping) __folio_mark_dirty(folio, mapping, 0); } - folio_memcg_unlock(folio); if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } diff --git a/fs/dcache.c b/fs/dcache.c index 0099077a2982..b4d5e9e1e43d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1099,7 +1099,7 @@ void shrink_dentry_list(struct list_head *list) } static enum lru_status dentry_lru_isolate(struct list_head *item, - struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) + struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); @@ -1180,7 +1180,7 @@ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, - struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) + struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 2e6bc77f4f81..72b48f6f5561 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -149,7 +149,7 @@ static void gfs2_qd_list_dispose(struct list_head *list) static enum lru_status gfs2_qd_isolate(struct list_head *item, - struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) + struct list_lru_one *lru, void *arg) { struct list_head *dispose = arg; struct gfs2_quota_data *qd = diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 1bbf783b244a..a4441fb77f7c 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -174,103 +174,29 @@ out: * Called under mmap_write_lock(mm). */ -static unsigned long -hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info = {}; - - info.length = len; - info.low_limit = current->mm->mmap_base; - info.high_limit = arch_get_mmap_end(addr, len, flags); - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - return vm_unmapped_area(&info); -} - -static unsigned long -hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) -{ - struct hstate *h = hstate_file(file); - struct vm_unmapped_area_info info = {}; - - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.low_limit = PAGE_SIZE; - info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); - info.align_mask = PAGE_MASK & ~huge_page_mask(h); - addr = vm_unmapped_area(&info); - - /* - * A failed mmap() very likely causes application failure, - * so fall back to the bottom-up function here. This scenario - * can happen with large stack limits and large mmap() - * allocations. - */ - if (unlikely(offset_in_page(addr))) { - VM_BUG_ON(addr != -ENOMEM); - info.flags = 0; - info.low_limit = current->mm->mmap_base; - info.high_limit = arch_get_mmap_end(addr, len, flags); - addr = vm_unmapped_area(&info); - } - - return addr; -} - unsigned long -generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags) +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) { - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma, *prev; + unsigned long addr0 = 0; struct hstate *h = hstate_file(file); - const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len & ~huge_page_mask(h)) return -EINVAL; - if (len > mmap_end - mmap_min_addr) - return -ENOMEM; - if (flags & MAP_FIXED) { + if (addr & ~huge_page_mask(h)) + return -EINVAL; if (prepare_hugepage_range(file, addr, len)) return -EINVAL; - return addr; - } - - if (addr) { - addr = ALIGN(addr, huge_page_size(h)); - vma = find_vma_prev(mm, addr, &prev); - if (mmap_end - len >= addr && addr >= mmap_min_addr && - (!vma || addr + len <= vm_start_gap(vma)) && - (!prev || addr >= vm_end_gap(prev))) - return addr; } + if (addr) + addr0 = ALIGN(addr, huge_page_size(h)); - /* - * Use MMF_TOPDOWN flag as a hint to use topdown routine. - * If architectures have special needs, they should define their own - * version of hugetlb_get_unmapped_area. - */ - if (test_bit(MMF_TOPDOWN, &mm->flags)) - return hugetlb_get_unmapped_area_topdown(file, addr, len, - pgoff, flags); - return hugetlb_get_unmapped_area_bottomup(file, addr, len, - pgoff, flags); + return mm_get_unmapped_area_vmflags(current->mm, file, addr0, len, pgoff, + flags, 0); } -#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA -static unsigned long -hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags) -{ - return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags); -} -#endif - /* * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset. * Returns the maximum number of bytes one can read without touching the 1st raw diff --git a/fs/inode.c b/fs/inode.c index b13b778257ae..6b4c77268fc0 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -952,7 +952,7 @@ again: * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_lru_isolate(struct list_head *item, - struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) + struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct inode *inode = container_of(item, struct inode, i_lru); @@ -994,7 +994,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); - spin_unlock(lru_lock); + spin_unlock(&lru->lock); if (remove_inode_buffers(inode)) { unsigned long reap; reap = invalidate_mapping_pages(&inode->i_data, 0, -1); @@ -1005,7 +1005,6 @@ static enum lru_status inode_lru_isolate(struct list_head *item, mm_account_reclaimed_pages(reap); } inode_unpin_lru_isolating(inode); - spin_lock(lru_lock); return LRU_RETRY; } diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index b6e3d8f77b91..37d79400e5f4 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -802,7 +802,7 @@ static struct shrinker *nfs4_xattr_large_entry_shrinker; static enum lru_status cache_lru_isolate(struct list_head *item, - struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) + struct list_lru_one *lru, void *arg) { struct list_head *dispose = arg; struct inode *inode; @@ -867,7 +867,7 @@ nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc) static enum lru_status entry_lru_isolate(struct list_head *item, - struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) + struct list_lru_one *lru, void *arg) { struct list_head *dispose = arg; struct nfs4_xattr_bucket *bucket; diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 2e6783f63712..09c444eb944f 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -487,7 +487,6 @@ void nfsd_file_net_dispose(struct nfsd_net *nn) * nfsd_file_lru_cb - Examine an entry on the LRU list * @item: LRU entry to examine * @lru: controlling LRU - * @lock: LRU list lock (unused) * @arg: dispose list * * Return values: @@ -497,9 +496,7 @@ void nfsd_file_net_dispose(struct nfsd_net *nn) */ static enum lru_status nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru, - spinlock_t *lock, void *arg) - __releases(lock) - __acquires(lock) + void *arg) { struct list_head *head = arg; struct nfsd_file *nf = list_entry(item, struct nfsd_file, nf_lru); diff --git a/fs/proc/base.c b/fs/proc/base.c index 3e31a4805427..0edf14a9840e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -831,19 +831,21 @@ static const struct file_operations proc_single_file_operations = { struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode) { struct task_struct *task = get_proc_task(inode); - struct mm_struct *mm = ERR_PTR(-ESRCH); + struct mm_struct *mm; - if (task) { - mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); - put_task_struct(task); + if (!task) + return ERR_PTR(-ESRCH); - if (!IS_ERR_OR_NULL(mm)) { - /* ensure this mm_struct can't be freed */ - mmgrab(mm); - /* but do not pin its memory */ - mmput(mm); - } - } + mm = mm_access(task, mode | PTRACE_MODE_FSCREDS); + put_task_struct(task); + + if (IS_ERR(mm)) + return mm == ERR_PTR(-ESRCH) ? NULL : mm; + + /* ensure this mm_struct can't be freed */ + mmgrab(mm); + /* but do not pin its memory */ + mmput(mm); return mm; } @@ -2207,7 +2209,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) goto out_notask; mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); - if (IS_ERR_OR_NULL(mm)) + if (IS_ERR(mm)) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 245171d9164b..8ba9b1472390 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -91,7 +91,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #ifdef CONFIG_ZSWAP show_val_kb(m, "Zswap: ", zswap_total_pages()); seq_printf(m, "Zswapped: %8lu kB\n", - (unsigned long)atomic_read(&zswap_stored_pages) << + (unsigned long)atomic_long_read(&zswap_stored_pages) << (PAGE_SHIFT - 10)); #endif show_val_kb(m, "Dirty: ", diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index e8196f5778e2..aa63b8efd782 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1857,7 +1857,6 @@ static enum lru_status xfs_buftarg_drain_rele( struct list_head *item, struct list_lru_one *lru, - spinlock_t *lru_lock, void *arg) { @@ -1956,7 +1955,6 @@ static enum lru_status xfs_buftarg_isolate( struct list_head *item, struct list_lru_one *lru, - spinlock_t *lru_lock, void *arg) { struct xfs_buf *bp = container_of(item, struct xfs_buf, b_lru); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index b928b036990b..61ee110b47d7 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -441,9 +441,8 @@ static enum lru_status xfs_qm_dquot_isolate( struct list_head *item, struct list_lru_one *lru, - spinlock_t *lru_lock, void *arg) - __releases(lru_lock) __acquires(lru_lock) + __releases(&lru->lock) __acquires(&lru->lock) { struct xfs_dquot *dqp = container_of(item, struct xfs_dquot, q_lru); @@ -489,7 +488,7 @@ xfs_qm_dquot_isolate( trace_xfs_dqreclaim_dirty(dqp); /* we have to drop the LRU lock to flush the dquot */ - spin_unlock(lru_lock); + spin_unlock(&lru->lock); error = xfs_qm_dqflush(dqp, &bp); if (error) @@ -525,7 +524,6 @@ out_unlock_dirty: trace_xfs_dqreclaim_busy(dqp); XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses); xfs_dqunlock(dqp); - spin_lock(lru_lock); return LRU_RETRY; } diff --git a/include/asm-generic/codetag.lds.h b/include/asm-generic/codetag.lds.h index 64f536b80380..372c320c5043 100644 --- a/include/asm-generic/codetag.lds.h +++ b/include/asm-generic/codetag.lds.h @@ -11,4 +11,23 @@ #define CODETAG_SECTIONS() \ SECTION_WITH_BOUNDARIES(alloc_tags) +/* + * Module codetags which aren't used after module unload, therefore have the + * same lifespan as the module and can be safely unloaded with the module. + */ +#define MOD_CODETAG_SECTIONS() + +#define MOD_SEPARATE_CODETAG_SECTION(_name) \ + .codetag.##_name : { \ + SECTION_WITH_BOUNDARIES(_name) \ + } + +/* + * For codetags which might be used after module unload, therefore might stay + * longer in memory. Each such codetag type has its own section so that we can + * unload them individually once unused. + */ +#define MOD_SEPARATE_CODETAG_SECTIONS() \ + MOD_SEPARATE_CODETAG_SECTION(alloc_tags) + #endif /* __ASM_GENERIC_CODETAG_LDS_H */ diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 594d5905f615..f42133dae68e 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -42,20 +42,26 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) return pte_modify(pte, newprot); } +#ifndef __HAVE_ARCH_HUGE_PTE_MKUFFD_WP static inline pte_t huge_pte_mkuffd_wp(pte_t pte) { return huge_pte_wrprotect(pte_mkuffd_wp(pte)); } +#endif +#ifndef __HAVE_ARCH_HUGE_PTE_CLEAR_UFFD_WP static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) { return pte_clear_uffd_wp(pte); } +#endif +#ifndef __HAVE_ARCH_HUGE_PTE_UFFD_WP static inline int huge_pte_uffd_wp(pte_t pte) { return pte_uffd_wp(pte); } +#endif #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, @@ -106,22 +112,17 @@ static inline int huge_pte_none(pte_t pte) #endif /* Please refer to comments above pte_none_mostly() for the usage */ +#ifndef __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY static inline int huge_pte_none_mostly(pte_t pte) { return huge_pte_none(pte) || is_pte_marker(pte); } +#endif #ifndef __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { - struct hstate *h = hstate_file(file); - - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (addr & ~huge_page_mask(h)) - return -EINVAL; - return 0; } #endif diff --git a/include/asm-generic/text-patching.h b/include/asm-generic/text-patching.h new file mode 100644 index 000000000000..2245c641b741 --- /dev/null +++ b/include/asm-generic/text-patching.h @@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_GENERIC_TEXT_PATCHING_H +#define _ASM_GENERIC_TEXT_PATCHING_H + +#endif /* _ASM_GENERIC_TEXT_PATCHING_H */ diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 941deffc590d..7c0786bdf9af 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -30,6 +30,21 @@ struct alloc_tag { struct alloc_tag_counters __percpu *counters; } __aligned(8); +struct alloc_tag_kernel_section { + struct alloc_tag *first_tag; + unsigned long count; +}; + +struct alloc_tag_module_section { + union { + unsigned long start_addr; + struct alloc_tag *first_tag; + }; + unsigned long end_addr; + /* used size */ + unsigned long size; +}; + #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG #define CODETAG_EMPTY ((void *)1) @@ -54,6 +69,8 @@ static inline void set_codetag_empty(union codetag_ref *ref) {} #ifdef CONFIG_MEM_ALLOC_PROFILING +#define ALLOC_TAG_SECTION_NAME "alloc_tags" + struct codetag_bytes { struct codetag *ct; s64 bytes; @@ -76,7 +93,7 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); #define DEFINE_ALLOC_TAG(_alloc_tag) \ static struct alloc_tag _alloc_tag __used __aligned(8) \ - __section("alloc_tags") = { \ + __section(ALLOC_TAG_SECTION_NAME) = { \ .ct = CODE_TAG_INIT, \ .counters = &_shared_alloc_tag }; @@ -85,7 +102,7 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); #define DEFINE_ALLOC_TAG(_alloc_tag) \ static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr); \ static struct alloc_tag _alloc_tag __used __aligned(8) \ - __section("alloc_tags") = { \ + __section(ALLOC_TAG_SECTION_NAME) = { \ .ct = CODE_TAG_INIT, \ .counters = &_alloc_tag_cntr }; diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h index cffa38a73618..d8a8d245824a 100644 --- a/include/linux/bootmem_info.h +++ b/include/linux/bootmem_info.h @@ -6,11 +6,10 @@ #include <linux/kmemleak.h> /* - * Types for free bootmem stored in page->lru.next. These have to be in - * some random range in unsigned long space for debugging purposes. + * Types for free bootmem stored in the low bits of page->private. */ -enum { - MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, +enum bootmem_type { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 1, SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, MIX_SECTION_INFO, NODE_INFO, @@ -21,9 +20,19 @@ enum { void __init register_page_bootmem_info_node(struct pglist_data *pgdat); void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type); + enum bootmem_type type); void put_page_bootmem(struct page *page); +static inline enum bootmem_type bootmem_type(const struct page *page) +{ + return (unsigned long)page->private & 0xf; +} + +static inline unsigned long bootmem_info(const struct page *page) +{ + return (unsigned long)page->private >> 4; +} + /* * Any memory allocated via the memblock allocator and not via the * buddy will be marked reserved already in the memmap. For those @@ -31,7 +40,7 @@ void put_page_bootmem(struct page *page); */ static inline void free_bootmem_page(struct page *page) { - unsigned long magic = page->index; + enum bootmem_type type = bootmem_type(page); /* * The reserve_bootmem_region sets the reserved flag on bootmem @@ -39,7 +48,7 @@ static inline void free_bootmem_page(struct page *page) */ VM_BUG_ON_PAGE(page_ref_count(page) != 2, page); - if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) + if (type == SECTION_INFO || type == MIX_SECTION_INFO) put_page_bootmem(page); else VM_BUG_ON_PAGE(1, page); @@ -53,8 +62,18 @@ static inline void put_page_bootmem(struct page *page) { } +static inline enum bootmem_type bootmem_type(const struct page *page) +{ + return SECTION_INFO; +} + +static inline unsigned long bootmem_info(const struct page *page) +{ + return 0; +} + static inline void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type) + enum bootmem_type type) { } diff --git a/include/linux/codetag.h b/include/linux/codetag.h index c2a579ccd455..d14dbd26b370 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -13,6 +13,9 @@ struct codetag_module; struct seq_buf; struct module; +#define CODETAG_SECTION_START_PREFIX "__start_" +#define CODETAG_SECTION_STOP_PREFIX "__stop_" + /* * An instance of this structure is created in a special ELF section at every * code location being tagged. At runtime, the special section is treated as @@ -35,8 +38,15 @@ struct codetag_type_desc { size_t tag_size; void (*module_load)(struct codetag_type *cttype, struct codetag_module *cmod); - bool (*module_unload)(struct codetag_type *cttype, + void (*module_unload)(struct codetag_type *cttype, struct codetag_module *cmod); +#ifdef CONFIG_MODULES + void (*module_replaced)(struct module *mod, struct module *new_mod); + bool (*needs_section_mem)(struct module *mod, unsigned long size); + void *(*alloc_section_mem)(struct module *mod, unsigned long size, + unsigned int prepend, unsigned long align); + void (*free_section_mem)(struct module *mod, bool used); +#endif }; struct codetag_iterator { @@ -71,11 +81,31 @@ struct codetag_type * codetag_register_type(const struct codetag_type_desc *desc); #if defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) + +bool codetag_needs_module_section(struct module *mod, const char *name, + unsigned long size); +void *codetag_alloc_module_section(struct module *mod, const char *name, + unsigned long size, unsigned int prepend, + unsigned long align); +void codetag_free_module_sections(struct module *mod); +void codetag_module_replaced(struct module *mod, struct module *new_mod); void codetag_load_module(struct module *mod); -bool codetag_unload_module(struct module *mod); -#else +void codetag_unload_module(struct module *mod); + +#else /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */ + +static inline bool +codetag_needs_module_section(struct module *mod, const char *name, + unsigned long size) { return false; } +static inline void * +codetag_alloc_module_section(struct module *mod, const char *name, + unsigned long size, unsigned int prepend, + unsigned long align) { return NULL; } +static inline void codetag_free_module_sections(struct module *mod) {} +static inline void codetag_module_replaced(struct module *mod, struct module *new_mod) {} static inline void codetag_load_module(struct module *mod) {} -static inline bool codetag_unload_module(struct module *mod) { return true; } -#endif +static inline void codetag_unload_module(struct module *mod) {} + +#endif /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */ #endif /* _LINUX_CODETAG_H */ diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 32cef1144117..64130ae19690 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -46,11 +46,27 @@ enum execmem_type { /** * enum execmem_range_flags - options for executable memory allocations * @EXECMEM_KASAN_SHADOW: allocate kasan shadow + * @EXECMEM_ROX_CACHE: allocations should use ROX cache of huge pages */ enum execmem_range_flags { EXECMEM_KASAN_SHADOW = (1 << 0), + EXECMEM_ROX_CACHE = (1 << 1), }; +#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX +/** + * execmem_fill_trapping_insns - set memory to contain instructions that + * will trap + * @ptr: pointer to memory to fill + * @size: size of the range to fill + * @writable: is the memory poited by @ptr is writable or ROX + * + * A hook for architecures to fill execmem ranges with invalid instructions. + * Architectures that use EXECMEM_ROX_CACHE must implement this. + */ +void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable); +#endif + /** * struct execmem_range - definition of an address space suitable for code and * related data allocations @@ -123,6 +139,39 @@ void *execmem_alloc(enum execmem_type type, size_t size); */ void execmem_free(void *ptr); +#ifdef CONFIG_MMU +/** + * execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory + * @size: size of the virtual mapping in bytes + * + * Maps virtually contiguous area in the range suitable for EXECMEM_MODULE_DATA. + * + * Return: the area descriptor on success or %NULL on failure. + */ +struct vm_struct *execmem_vmap(size_t size); +#endif + +/** + * execmem_update_copy - copy an update to executable memory + * @dst: destination address to update + * @src: source address containing the data + * @size: how many bytes of memory shold be copied + * + * Copy @size bytes from @src to @dst using text poking if the memory at + * @dst is read-only. + * + * Return: a pointer to @dst or NULL on error + */ +void *execmem_update_copy(void *dst, const void *src, size_t size); + +/** + * execmem_is_rox - check if execmem is read-only + * @type - the execmem type to check + * + * Return: %true if the @type is read-only, %false if it's writable + */ +bool execmem_is_rox(enum execmem_type type); + #if defined(CONFIG_EXECMEM) && !defined(CONFIG_ARCH_WANTS_EXECMEM_LATE) void execmem_init(void); #else diff --git a/include/linux/gfp.h b/include/linux/gfp.h index a0a6d25f883f..b0fe9f62d15b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -306,7 +306,7 @@ struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, bool hugepage); + unsigned long addr); #else static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { @@ -326,7 +326,7 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde { return folio_alloc_noprof(gfp, order); } -#define vma_alloc_folio_noprof(gfp, order, vma, addr, hugepage) \ +#define vma_alloc_folio_noprof(gfp, order, vma, addr) \ folio_alloc_noprof(gfp, order) #endif @@ -341,7 +341,7 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { - struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr, false); + struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr); return &folio->page; } diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 930a591b9b61..6e452bd8e7e3 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -224,13 +224,7 @@ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { - struct folio *folio; - - folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr, false); - if (folio) - clear_user_highpage(&folio->page, vaddr); - - return folio; + return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr); } #endif diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ef5b80e48599..b94c2e8ee918 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -2,7 +2,6 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H -#include <linux/sched/coredump.h> #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ @@ -120,6 +119,8 @@ enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, + MTHP_STAT_ZSWPOUT, + MTHP_STAT_SWPIN, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, MTHP_STAT_SHMEM_ALLOC, @@ -253,19 +254,6 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, return orders; } -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)) && - !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); -} - unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long vm_flags, unsigned long tva_flags, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e4697539b665..ae4fe8615bb6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -546,16 +546,10 @@ static inline struct hstate *hstate_inode(struct inode *i) } #endif /* !CONFIG_HUGETLBFS */ -#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA -unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); -#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */ - unsigned long -generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, - unsigned long len, unsigned long pgoff, - unsigned long flags); +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private @@ -1035,9 +1029,19 @@ void hugetlb_unregister_node(struct node *node); */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); +static inline unsigned long huge_page_mask_align(struct file *file) +{ + return PAGE_MASK & ~huge_page_mask(hstate_file(file)); +} + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline unsigned long huge_page_mask_align(struct file *file) +{ + return 0; +} + static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 00a3bf7c0d8f..6bbfc8aa42e8 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -29,6 +29,9 @@ typedef unsigned int __bitwise kasan_vmalloc_flags_t; #define KASAN_VMALLOC_VM_ALLOC ((__force kasan_vmalloc_flags_t)0x02u) #define KASAN_VMALLOC_PROT_NORMAL ((__force kasan_vmalloc_flags_t)0x04u) +#define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */ +#define KASAN_VMALLOC_TLB_FLUSH 0x2 /* TLB flush */ + #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #include <linux/pgtable.h> @@ -564,7 +567,8 @@ void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end); + unsigned long free_region_end, + unsigned long flags); #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ @@ -579,7 +583,8 @@ static inline int kasan_populate_vmalloc(unsigned long start, static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) { } + unsigned long free_region_end, + unsigned long flags) { } #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ @@ -614,7 +619,8 @@ static inline int kasan_populate_vmalloc(unsigned long start, static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) { } + unsigned long free_region_end, + unsigned long flags) { } static inline void *kasan_unpoison_vmalloc(const void *start, unsigned long size, diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 30baae91b225..1f46046080f5 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -2,8 +2,6 @@ #ifndef _LINUX_KHUGEPAGED_H #define _LINUX_KHUGEPAGED_H -#include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */ - extern unsigned int khugepaged_max_ptes_none __read_mostly; #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern struct attribute_group khugepaged_attr_group; diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 6a3cd1bf4680..93a73c076d16 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -26,6 +26,7 @@ extern void kmemleak_free_part(const void *ptr, size_t size) __ref; extern void kmemleak_free_percpu(const void __percpu *ptr) __ref; extern void kmemleak_update_trace(const void *ptr) __ref; extern void kmemleak_not_leak(const void *ptr) __ref; +extern void kmemleak_transient_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; extern void kmemleak_no_scan(const void *ptr) __ref; @@ -93,6 +94,9 @@ static inline void kmemleak_update_trace(const void *ptr) static inline void kmemleak_not_leak(const void *ptr) { } +static inline void kmemleak_transient_leak(const void *ptr) +{ +} static inline void kmemleak_ignore(const void *ptr) { } diff --git a/include/linux/ksm.h b/include/linux/ksm.h index ec9c05044d4f..6a53ac4885bb 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -13,7 +13,6 @@ #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> -#include <linux/sched/coredump.h> #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, @@ -91,7 +90,7 @@ struct folio *ksm_might_need_to_copy(struct folio *folio, void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); -void collect_procs_ksm(struct folio *folio, struct page *page, +void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); @@ -123,8 +122,9 @@ static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } -static inline void collect_procs_ksm(struct folio *folio, struct page *page, - struct list_head *to_kill, int force_early) +static inline void collect_procs_ksm(const struct folio *folio, + const struct page *page, struct list_head *to_kill, + int force_early) { } diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 5099a8ccd5f4..05c166811f6b 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -32,6 +32,8 @@ struct list_lru_one { struct list_head list; /* may become negative during memcg reparenting */ long nr_items; + /* protects all fields above */ + spinlock_t lock; }; struct list_lru_memcg { @@ -41,11 +43,9 @@ struct list_lru_memcg { }; struct list_lru_node { - /* protects all lists on the node, including per cgroup */ - spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; - long nr_items; + atomic_long_t nr_items; } ____cacheline_aligned_in_smp; struct list_lru { @@ -56,16 +56,28 @@ struct list_lru { bool memcg_aware; struct xarray xa; #endif +#ifdef CONFIG_LOCKDEP + struct lock_class_key *key; +#endif }; void list_lru_destroy(struct list_lru *lru); int __list_lru_init(struct list_lru *lru, bool memcg_aware, - struct lock_class_key *key, struct shrinker *shrinker); + struct shrinker *shrinker); #define list_lru_init(lru) \ - __list_lru_init((lru), false, NULL, NULL) + __list_lru_init((lru), false, NULL) #define list_lru_init_memcg(lru, shrinker) \ - __list_lru_init((lru), true, NULL, shrinker) + __list_lru_init((lru), true, shrinker) + +static inline int list_lru_init_memcg_key(struct list_lru *lru, struct shrinker *shrinker, + struct lock_class_key *key) +{ +#ifdef CONFIG_LOCKDEP + lru->key = key; +#endif + return list_lru_init_memcg(lru, shrinker); +} int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); @@ -172,7 +184,7 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, - struct list_lru_one *list, spinlock_t *lock, void *cb_arg); + struct list_lru_one *list, void *cb_arg); /** * list_lru_walk_one: walk a @lru, isolating and disposing freeable items. diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h index c2c11004085e..cbbcd18d4186 100644 --- a/include/linux/maple_tree.h +++ b/include/linux/maple_tree.h @@ -224,7 +224,7 @@ typedef struct { /* nothing */ } lockdep_map_p; * (set at tree creation time) and dynamic information set under the spinlock. * * Another use of flags are to indicate global states of the tree. This is the - * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in + * case with the MT_FLAGS_USE_RCU flag, which indicates the tree is currently in * RCU mode. This mode was added to allow the tree to reuse nodes instead of * re-allocating and RCU freeing nodes when there is a single user. */ @@ -592,6 +592,20 @@ static __always_inline void mas_reset(struct ma_state *mas) #define mas_for_each(__mas, __entry, __max) \ while (((__entry) = mas_find((__mas), (__max))) != NULL) +/** + * mas_for_each_rev() - Iterate over a range of the maple tree in reverse order. + * @__mas: Maple Tree operation state (maple_state) + * @__entry: Entry retrieved from the tree + * @__min: minimum index to retrieve from the tree + * + * When returned, mas->index and mas->last will hold the entire range for the + * entry. + * + * Note: may return the zero entry. + */ +#define mas_for_each_rev(__mas, __entry, __min) \ + while (((__entry) = mas_find_rev((__mas), (__min))) != NULL) + #ifdef CONFIG_DEBUG_MAPLE_TREE enum mt_dump_format { mt_dump_dec, diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e1b41554a5fb..5502aa8e138e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -299,25 +299,10 @@ struct mem_cgroup { /* For oom notifier event fd */ struct list_head oom_notify; - /* - * Should we move charges of a task when a task is moved into this - * mem_cgroup ? And what type of charges should we move ? - */ - unsigned long move_charge_at_immigrate; - /* taken only while moving_account > 0 */ - spinlock_t move_lock; - unsigned long move_lock_flags; - /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - struct task_struct *move_lock_task; - /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; @@ -433,9 +418,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) * * - the folio lock * - LRU isolation - * - folio_memcg_lock() * - exclusive reference - * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -460,35 +443,6 @@ static inline bool folio_memcg_charged(struct folio *folio) return __folio_memcg(folio) != NULL; } -/** - * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. - * @folio: Pointer to the folio. - * - * This function assumes that the folio is known to have a - * proper memory cgroup pointer. It's not safe to call this function - * against some type of folios, e.g. slab folios or ex-slab folios. - * - * Return: A pointer to the memory cgroup associated with the folio, - * or NULL. - */ -static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) -{ - unsigned long memcg_data = READ_ONCE(folio->memcg_data); - - VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - - if (memcg_data & MEMCG_DATA_KMEM) { - struct obj_cgroup *objcg; - - objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); - return obj_cgroup_memcg(objcg); - } - - WARN_ON_ONCE(!rcu_read_lock_held()); - - return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); -} - /* * folio_memcg_check - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. @@ -504,9 +458,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) * * - the folio lock * - LRU isolation - * - lock_folio_memcg() * - exclusive reference - * - mem_cgroup_trylock_pages() * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. @@ -1103,10 +1055,9 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return NULL; } -static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) +static inline bool folio_memcg_charged(struct folio *folio) { - WARN_ON_ONCE(!rcu_read_lock_held()); - return NULL; + return false; } static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) @@ -1282,6 +1233,10 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) return NULL; } +static inline void obj_cgroup_get(struct obj_cgroup *objcg) +{ +} + static inline void obj_cgroup_put(struct obj_cgroup *objcg) { } @@ -1874,26 +1829,6 @@ static inline bool task_in_memcg_oom(struct task_struct *p) return p->memcg_in_oom; } -void folio_memcg_lock(struct folio *folio); -void folio_memcg_unlock(struct folio *folio); - -/* try to stablize folio_memcg() for all the pages in a memcg */ -static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) -{ - rcu_read_lock(); - - if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) - return true; - - rcu_read_unlock(); - return false; -} - -static inline void mem_cgroup_unlock_pages(void) -{ - rcu_read_unlock(); -} - static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); @@ -1915,26 +1850,6 @@ unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, return 0; } -static inline void folio_memcg_lock(struct folio *folio) -{ -} - -static inline void folio_memcg_unlock(struct folio *folio) -{ -} - -static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) -{ - /* to match folio_memcg_rcu() */ - rcu_read_lock(); - return true; -} - -static inline void mem_cgroup_unlock_pages(void) -{ - rcu_read_unlock(); -} - static inline bool task_in_memcg_oom(struct task_struct *p) { return false; diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 1add16f21612..ce9885e0178a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -47,7 +47,7 @@ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ - nodemask_t nodes; /* interleave/bind/perfer */ + nodemask_t nodes; /* interleave/bind/preferred/etc */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { diff --git a/include/linux/mm.h b/include/linux/mm.h index 673771f34674..2bbf73eb53e7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -97,11 +97,11 @@ extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif -#ifndef PHYSMEM_END +#ifndef DIRECT_MAP_PHYSMEM_END # ifdef MAX_PHYSMEM_BITS -# define PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) +# define DIRECT_MAP_PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1) # else -# define PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63)) +# define DIRECT_MAP_PHYSMEM_END (((phys_addr_t)-1)&~(1ULL<<63)) # endif #endif @@ -1298,8 +1298,6 @@ static inline struct folio *virt_to_folio(const void *x) void __folio_put(struct folio *folio); -void put_pages_list(struct list_head *pages); - void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); int folio_mc_copy(struct folio *dst, struct folio *src); @@ -1907,7 +1905,7 @@ static inline unsigned long page_to_section(const struct page *page) * * Return: The Page Frame Number of the first page in the folio. */ -static inline unsigned long folio_pfn(struct folio *folio) +static inline unsigned long folio_pfn(const struct folio *folio) { return page_to_pfn(&folio->page); } @@ -3028,8 +3026,11 @@ static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd, return pte; } -pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr, spinlock_t **ptlp); +pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, spinlock_t **ptlp); +pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, pmd_t *pmdvalp, + spinlock_t **ptlp); #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ @@ -3831,9 +3832,6 @@ 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, struct dev_pagemap *pgmap); -void pud_init(void *addr); -void pmd_init(void *addr); -void kernel_pte_init(void *addr); 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); @@ -4176,63 +4174,6 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla } #endif -#ifdef CONFIG_MEM_ALLOC_PROFILING -static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) -{ - int i; - struct alloc_tag *tag; - unsigned int nr_pages = 1 << new_order; - - if (!mem_alloc_profiling_enabled()) - return; - - tag = pgalloc_tag_get(&folio->page); - if (!tag) - return; - - for (i = nr_pages; i < (1 << old_order); i += nr_pages) { - union codetag_ref *ref = get_page_tag_ref(folio_page(folio, i)); - - if (ref) { - /* Set new reference to point to the original tag */ - alloc_tag_ref_set(ref, tag); - put_page_tag_ref(ref); - } - } -} - -static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) -{ - struct alloc_tag *tag; - union codetag_ref *ref; - - tag = pgalloc_tag_get(&old->page); - if (!tag) - return; - - ref = get_page_tag_ref(&new->page); - if (!ref) - return; - - /* Clear the old ref to the original allocation tag. */ - clear_page_tag_ref(&old->page); - /* Decrement the counters of the tag on get_new_folio. */ - alloc_tag_sub(ref, folio_nr_pages(new)); - - __alloc_tag_ref_set(ref, tag); - - put_page_tag_ref(ref); -} -#else /* !CONFIG_MEM_ALLOC_PROFILING */ -static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) -{ -} - -static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) -{ -} -#endif /* CONFIG_MEM_ALLOC_PROFILING */ - int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status); int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status); int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index f4fe593c1400..1b6a917fffa4 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -155,6 +155,11 @@ static inline int folio_lru_refs(struct folio *folio) return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; } +static inline void folio_clear_lru_refs(struct folio *folio) +{ + set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); +} + static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); @@ -222,6 +227,7 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, { unsigned long seq; unsigned long flags; + unsigned long mask; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); @@ -257,7 +263,14 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ - set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); + mask = LRU_GEN_MASK; + /* + * Don't clear PG_workingset here because it can affect PSI accounting + * if the activation is due to workingset refault. + */ + if (folio_test_active(folio)) + mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active); + set_mask_bits(&folio->flags, mask, flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ @@ -291,6 +304,12 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return true; } +static inline void folio_migrate_refs(struct folio *new, struct folio *old) +{ + unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; + + set_mask_bits(&new->flags, LRU_REFS_MASK, refs); +} #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) @@ -313,6 +332,10 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, return false; } +static inline void folio_migrate_refs(struct folio *new, struct folio *old) +{ + +} #endif /* CONFIG_LRU_GEN */ static __always_inline @@ -521,7 +544,7 @@ static inline pte_marker copy_pte_marker( { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ - pte_marker dstm = srcm & PTE_MARKER_POISONED; + pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e85beea1206e..7361a8f3ab68 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1535,4 +1535,88 @@ enum { /* See also internal only FOLL flags in mm/internal.h */ }; +/* mm flags */ + +/* + * The first two bits represent core dump modes for set-user-ID, + * the modes are SUID_DUMP_* defined in linux/sched/coredump.h + */ +#define MMF_DUMPABLE_BITS 2 +#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) +/* coredump filter bits */ +#define MMF_DUMP_ANON_PRIVATE 2 +#define MMF_DUMP_ANON_SHARED 3 +#define MMF_DUMP_MAPPED_PRIVATE 4 +#define MMF_DUMP_MAPPED_SHARED 5 +#define MMF_DUMP_ELF_HEADERS 6 +#define MMF_DUMP_HUGETLB_PRIVATE 7 +#define MMF_DUMP_HUGETLB_SHARED 8 +#define MMF_DUMP_DAX_PRIVATE 9 +#define MMF_DUMP_DAX_SHARED 10 + +#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS +#define MMF_DUMP_FILTER_BITS 9 +#define MMF_DUMP_FILTER_MASK \ + (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) +#define MMF_DUMP_FILTER_DEFAULT \ + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ + (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) + +#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS +# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) +#else +# define MMF_DUMP_MASK_DEFAULT_ELF 0 +#endif + /* leave room for more dump flags */ +#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ +#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 + */ +//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ + +#define MMF_HAS_UPROBES 19 /* has uprobes */ +#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ +#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ +#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ +#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ +#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) +#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ +#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ +/* + * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either + * replaced in the future by mm.pinned_vm when it becomes stable, or grow into + * a counter on its own. We're aggresive on this bit for now: even if the + * pinned pages were unpinned later on, we'll still keep this bit set for the + * lifecycle of this mm, just for simplicity. + */ +#define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ + +#define MMF_HAS_MDWE 28 +#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) + + +#define MMF_HAS_MDWE_NO_INHERIT 29 + +#define MMF_VM_MERGE_ANY 30 +#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) + +#define MMF_TOPDOWN 31 /* mm searches top down by default */ +#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) + +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ + MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ + MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) + +static inline unsigned long mmf_init_flags(unsigned long flags) +{ + if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) + flags &= ~((1UL << MMF_HAS_MDWE) | + (1UL << MMF_HAS_MDWE_NO_INHERIT)); + return flags & MMF_INIT_MASK; +} + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index d39ebb10caeb..e2dd57ca368b 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -606,6 +606,13 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline int mmu_notifier_clear_young(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + return 0; +} + static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 80bc5640bb60..b36124145a16 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -220,6 +220,9 @@ enum node_stat_item { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, +#ifdef CONFIG_HUGETLB_PAGE + NR_HUGETLB, +#endif NR_VM_NODE_STAT_ITEMS }; @@ -403,6 +406,8 @@ enum { NR_LRU_GEN_CAPS }; +#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) + #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) diff --git a/include/linux/module.h b/include/linux/module.h index 88ecc5e9f523..2a9386cbdf85 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -367,6 +367,8 @@ enum mod_mem_type { struct module_memory { void *base; + void *rw_copy; + bool is_rox; unsigned int size; #ifdef CONFIG_MODULES_TREE_LOOKUP @@ -767,6 +769,15 @@ static inline bool is_livepatch_module(struct module *mod) void set_module_sig_enforced(void); +void *__module_writable_address(struct module *mod, void *loc); + +static inline void *module_writable_address(struct module *mod, void *loc) +{ + if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod) + return loc; + return __module_writable_address(mod, loc); +} + #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) @@ -874,6 +885,11 @@ static inline bool module_is_coming(struct module *mod) { return false; } + +static inline void *module_writable_address(struct module *mod, void *loc) +{ + return loc; +} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index e395461d59e5..1f5507ba5a12 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -108,6 +108,10 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod); +int module_post_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod); + #ifdef CONFIG_MODULES void flush_module_init_free_work(void); #else diff --git a/include/linux/oom.h b/include/linux/oom.h index 7d0c9c48a0c5..1e0fc6931ce9 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -7,7 +7,6 @@ #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> -#include <linux/sched/coredump.h> /* MMF_* */ #include <linux/mm.h> /* VM_FAULT* */ struct zonelist; diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 7d79818dc065..4f5c9e979bb9 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -111,5 +111,12 @@ ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \ NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH) +#define NR_NON_PAGEFLAG_BITS (SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH + \ + LAST_CPUPID_SHIFT + KASAN_TAG_WIDTH + \ + LRU_GEN_WIDTH + LRU_REFS_WIDTH) + +#define NR_UNUSED_PAGEFLAG_BITS (BITS_PER_LONG - \ + (NR_NON_PAGEFLAG_BITS + NR_PAGEFLAGS)) + #endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 908ee0aad554..2220bfec278e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -689,6 +689,13 @@ static __always_inline bool folio_test_anon(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; } +static __always_inline bool PageAnonNotKsm(const struct page *page) +{ + unsigned long flags = (unsigned long)page_folio(page)->mapping; + + return (flags & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_ANON; +} + static __always_inline bool PageAnon(const struct page *page) { return folio_test_anon(page_folio(page)); @@ -718,13 +725,8 @@ static __always_inline bool folio_test_ksm(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } - -static __always_inline bool PageKsm(const struct page *page) -{ - return folio_test_ksm(page_folio(page)); -} #else -TESTPAGEFLAG_FALSE(Ksm, ksm) +FOLIO_TEST_FLAG_FALSE(ksm) #endif u64 stable_page_flags(const struct page *page); @@ -1137,14 +1139,14 @@ static __always_inline int PageAnonExclusive(const struct page *page) static __always_inline void SetPageAnonExclusive(struct page *page) { - VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page); + VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(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(!PageAnonNotKsm(page), page); VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index c16db0067090..73dc2c1841ec 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -3,10 +3,6 @@ #define __LINUX_PAGEISOLATION_H #ifdef CONFIG_MEMORY_ISOLATION -static inline bool has_isolate_pageblock(struct zone *zone) -{ - return zone->nr_isolate_pageblock; -} static inline bool is_migrate_isolate_page(struct page *page) { return get_pageblock_migratetype(page) == MIGRATE_ISOLATE; @@ -16,10 +12,6 @@ static inline bool is_migrate_isolate(int migratetype) return migratetype == MIGRATE_ISOLATE; } #else -static inline bool has_isolate_pageblock(struct zone *zone) -{ - return false; -} static inline bool is_migrate_isolate_page(struct page *page) { return false; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 68a5f1ff3301..bcf0865a38ae 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1011,22 +1011,25 @@ static inline struct folio *read_mapping_folio(struct address_space *mapping, return read_cache_folio(mapping, index, NULL, file); } -/* - * Get the offset in PAGE_SIZE (even for hugetlb pages). +/** + * page_pgoff - Calculate the logical page offset of this page. + * @folio: The folio containing this page. + * @page: The page which we need the offset of. + * + * For file pages, this is the offset from the beginning of the file + * in units of PAGE_SIZE. For anonymous pages, this is the offset from + * the beginning of the anon_vma in units of PAGE_SIZE. This will + * return nonsense for KSM pages. + * + * Context: Caller must have a reference on the folio or otherwise + * prevent it from being split or freed. + * + * Return: The offset in units of PAGE_SIZE. */ -static inline pgoff_t page_to_pgoff(struct page *page) +static inline pgoff_t page_pgoff(const struct folio *folio, + const struct page *page) { - struct page *head; - - if (likely(!PageTransTail(page))) - return page->index; - - head = compound_head(page); - /* - * We don't initialize ->index for tail pages: calculate based on - * head page - */ - return head->index + page - head; + return folio->index + folio_page_idx(folio, page); } /* diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index f5eb5a32aeed..9700a29f8afb 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -25,12 +25,15 @@ enum page_walk_lock { * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each PTE (lowest-level) entry, - * including empty ones + * @pte_entry: if set, called for each PTE (lowest-level) entry + * including empty ones, except if @install_pte is set. + * If @install_pte is set, @pte_entry is called only for + * existing PTEs. * @pte_hole: if set, called for each hole at all levels, * depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD. * Any folded depths (where PTRS_PER_P?D is equal to 1) - * are skipped. + * are skipped. If @install_pte is specified, this will + * not trigger for any populated ranges. * @hugetlb_entry: if set, called for each hugetlb entry. This hook * function is called with the vma lock held, in order to * protect against a concurrent freeing of the pte_t* or @@ -51,6 +54,13 @@ enum page_walk_lock { * @pre_vma: if set, called before starting walk on a non-null vma. * @post_vma: if set, called after a walk on a non-null vma, provided * that @pre_vma and the vma walk succeeded. + * @install_pte: if set, missing page table entries are installed and + * thus all levels are always walked in the specified + * range. This callback is then invoked at the PTE level + * (having split any THP pages prior), providing the PTE to + * install. If allocations fail, the walk is aborted. This + * operation is only available for userland memory. Not + * usable for hugetlb ranges. * * p?d_entry callbacks are called even if those levels are folded on a * particular architecture/configuration. @@ -76,6 +86,8 @@ struct mm_walk_ops { int (*pre_vma)(unsigned long start, unsigned long end, struct mm_walk *walk); void (*post_vma)(struct mm_walk *walk); + int (*install_pte)(unsigned long addr, unsigned long next, + pte_t *ptep, struct mm_walk *walk); enum page_walk_lock walk_lock; }; diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 59a3deb792a8..0e43ab653ab6 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -12,45 +12,166 @@ #include <linux/page_ext.h> extern struct page_ext_operations page_alloc_tagging_ops; +extern unsigned long alloc_tag_ref_mask; +extern int alloc_tag_ref_offs; +extern struct alloc_tag_kernel_section kernel_tags; -static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext) +DECLARE_STATIC_KEY_FALSE(mem_profiling_compressed); + +typedef u16 pgalloc_tag_idx; + +union pgtag_ref_handle { + union codetag_ref *ref; /* reference in page extension */ + struct page *page; /* reference in page flags */ +}; + +/* Reserved indexes */ +#define CODETAG_ID_NULL 0 +#define CODETAG_ID_EMPTY 1 +#define CODETAG_ID_FIRST 2 + +#ifdef CONFIG_MODULES + +extern struct alloc_tag_module_section module_tags; + +static inline struct alloc_tag *module_idx_to_tag(pgalloc_tag_idx idx) { - return (union codetag_ref *)page_ext_data(page_ext, &page_alloc_tagging_ops); + return &module_tags.first_tag[idx - kernel_tags.count]; } -static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref) +static inline pgalloc_tag_idx module_tag_to_idx(struct alloc_tag *tag) { - return (void *)ref - page_alloc_tagging_ops.offset; + return CODETAG_ID_FIRST + kernel_tags.count + (tag - module_tags.first_tag); } -/* Should be called only if mem_alloc_profiling_enabled() */ -static inline union codetag_ref *get_page_tag_ref(struct page *page) +#else /* CONFIG_MODULES */ + +static inline struct alloc_tag *module_idx_to_tag(pgalloc_tag_idx idx) { - if (page) { - struct page_ext *page_ext = page_ext_get(page); + pr_warn("invalid page tag reference %lu\n", (unsigned long)idx); + return NULL; +} - if (page_ext) - return codetag_ref_from_page_ext(page_ext); +static inline pgalloc_tag_idx module_tag_to_idx(struct alloc_tag *tag) +{ + pr_warn("invalid page tag 0x%lx\n", (unsigned long)tag); + return CODETAG_ID_NULL; +} + +#endif /* CONFIG_MODULES */ + +static inline void idx_to_ref(pgalloc_tag_idx idx, union codetag_ref *ref) +{ + switch (idx) { + case (CODETAG_ID_NULL): + ref->ct = NULL; + break; + case (CODETAG_ID_EMPTY): + set_codetag_empty(ref); + break; + default: + idx -= CODETAG_ID_FIRST; + ref->ct = idx < kernel_tags.count ? + &kernel_tags.first_tag[idx].ct : + &module_idx_to_tag(idx)->ct; + break; } - return NULL; } -static inline void put_page_tag_ref(union codetag_ref *ref) +static inline pgalloc_tag_idx ref_to_idx(union codetag_ref *ref) +{ + struct alloc_tag *tag; + + if (!ref->ct) + return CODETAG_ID_NULL; + + if (is_codetag_empty(ref)) + return CODETAG_ID_EMPTY; + + tag = ct_to_alloc_tag(ref->ct); + if (tag >= kernel_tags.first_tag && tag < kernel_tags.first_tag + kernel_tags.count) + return CODETAG_ID_FIRST + (tag - kernel_tags.first_tag); + + return module_tag_to_idx(tag); +} + + + +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline bool get_page_tag_ref(struct page *page, union codetag_ref *ref, + union pgtag_ref_handle *handle) { - if (WARN_ON(!ref)) + if (!page) + return false; + + if (static_key_enabled(&mem_profiling_compressed)) { + pgalloc_tag_idx idx; + + idx = (page->flags >> alloc_tag_ref_offs) & alloc_tag_ref_mask; + idx_to_ref(idx, ref); + handle->page = page; + } else { + struct page_ext *page_ext; + union codetag_ref *tmp; + + page_ext = page_ext_get(page); + if (!page_ext) + return false; + + tmp = (union codetag_ref *)page_ext_data(page_ext, &page_alloc_tagging_ops); + ref->ct = tmp->ct; + handle->ref = tmp; + } + + return true; +} + +static inline void put_page_tag_ref(union pgtag_ref_handle handle) +{ + if (WARN_ON(!handle.ref)) return; - page_ext_put(page_ext_from_codetag_ref(ref)); + if (!static_key_enabled(&mem_profiling_compressed)) + page_ext_put((void *)handle.ref - page_alloc_tagging_ops.offset); +} + +static inline void update_page_tag_ref(union pgtag_ref_handle handle, union codetag_ref *ref) +{ + if (static_key_enabled(&mem_profiling_compressed)) { + struct page *page = handle.page; + unsigned long old_flags; + unsigned long flags; + unsigned long idx; + + if (WARN_ON(!page || !ref)) + return; + + idx = (unsigned long)ref_to_idx(ref); + idx = (idx & alloc_tag_ref_mask) << alloc_tag_ref_offs; + do { + old_flags = READ_ONCE(page->flags); + flags = old_flags; + flags &= ~(alloc_tag_ref_mask << alloc_tag_ref_offs); + flags |= idx; + } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); + } else { + if (WARN_ON(!handle.ref || !ref)) + return; + + handle.ref->ct = ref->ct; + } } static inline void clear_page_tag_ref(struct page *page) { if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); + union pgtag_ref_handle handle; + union codetag_ref ref; - if (ref) { - set_codetag_empty(ref); - put_page_tag_ref(ref); + if (get_page_tag_ref(page, &ref, &handle)) { + set_codetag_empty(&ref); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); } } } @@ -59,11 +180,13 @@ static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) { if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); + union pgtag_ref_handle handle; + union codetag_ref ref; - if (ref) { - alloc_tag_add(ref, task->alloc_tag, PAGE_SIZE * nr); - put_page_tag_ref(ref); + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_add(&ref, task->alloc_tag, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); } } } @@ -71,11 +194,13 @@ static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) { if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); + union pgtag_ref_handle handle; + union codetag_ref ref; - if (ref) { - alloc_tag_sub(ref, PAGE_SIZE * nr); - put_page_tag_ref(ref); + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub(&ref, PAGE_SIZE * nr); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); } } } @@ -85,13 +210,14 @@ static inline struct alloc_tag *pgalloc_tag_get(struct page *page) struct alloc_tag *tag = NULL; if (mem_alloc_profiling_enabled()) { - union codetag_ref *ref = get_page_tag_ref(page); - - alloc_tag_sub_check(ref); - if (ref) { - if (ref->ct) - tag = ct_to_alloc_tag(ref->ct); - put_page_tag_ref(ref); + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(page, &ref, &handle)) { + alloc_tag_sub_check(&ref); + if (ref.ct) + tag = ct_to_alloc_tag(ref.ct); + put_page_tag_ref(handle); } } @@ -104,16 +230,22 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); } +void pgalloc_tag_split(struct folio *folio, int old_order, int new_order); +void pgalloc_tag_copy(struct folio *new, struct folio *old); + +void __init alloc_tag_sec_init(void); + #else /* CONFIG_MEM_ALLOC_PROFILING */ -static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } -static inline void put_page_tag_ref(union codetag_ref *ref) {} static inline void clear_page_tag_ref(struct page *page) {} static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, unsigned int nr) {} static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} +static inline void alloc_tag_sec_init(void) {} +static inline void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) {} +static inline void pgalloc_tag_copy(struct folio *new, struct folio *old) {} #endif /* CONFIG_MEM_ALLOC_PROFILING */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e8b2ac6bd2ae..adef9d6e9b1b 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -90,6 +90,27 @@ static inline unsigned long pud_index(unsigned long address) #define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #endif +#ifndef kernel_pte_init +static inline void kernel_pte_init(void *addr) +{ +} +#define kernel_pte_init kernel_pte_init +#endif + +#ifndef pmd_init +static inline void pmd_init(void *addr) +{ +} +#define pmd_init pmd_init +#endif + +#ifndef pud_init +static inline void pud_init(void *addr) +{ +} +#define pud_init pud_init +#endif + #ifndef pte_offset_kernel static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) { @@ -1056,44 +1077,6 @@ static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) } #endif -/* - * Use set_p*_safe(), and elide TLB flushing, when confident that *no* - * TLB flush will be required as a result of the "set". For example, use - * in scenarios where it is known ahead of time that the routine is - * setting non-present entries, or re-setting an existing entry to the - * same value. Otherwise, use the typical "set" helpers and flush the - * TLB. - */ -#define set_pte_safe(ptep, pte) \ -({ \ - WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ - set_pte(ptep, pte); \ -}) - -#define set_pmd_safe(pmdp, pmd) \ -({ \ - WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ - set_pmd(pmdp, pmd); \ -}) - -#define set_pud_safe(pudp, pud) \ -({ \ - WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ - set_pud(pudp, pud); \ -}) - -#define set_p4d_safe(p4dp, p4d) \ -({ \ - WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ - set_p4d(p4dp, p4d); \ -}) - -#define set_pgd_safe(pgdp, pgd) \ -({ \ - WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ - set_pgd(pgdp, pgd); \ -}) - #ifndef __HAVE_ARCH_DO_SWAP_PAGE static inline void arch_do_swap_page_nr(struct mm_struct *mm, struct vm_area_struct *vma, diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d5e93e44322e..683a04088f3f 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -171,7 +171,7 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, unlink_anon_vmas(next); } -struct anon_vma *folio_get_anon_vma(struct folio *folio); +struct anon_vma *folio_get_anon_vma(const struct folio *folio); /* RMAP flags, currently only relevant for some anon rmap operations. */ typedef int __bitwise rmap_t; @@ -194,8 +194,8 @@ enum rmap_level { RMAP_LEVEL_PMD, }; -static inline void __folio_rmap_sanity_checks(struct folio *folio, - struct page *page, int nr_pages, enum rmap_level level) +static inline void __folio_rmap_sanity_checks(const struct folio *folio, + const struct page *page, int nr_pages, enum rmap_level level) { /* hugetlb folios are handled separately. */ VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); @@ -728,11 +728,8 @@ page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw) } bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); - -/* - * Used by swapoff to help locate where page is expected in vma. - */ -unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); +unsigned long page_address_in_vma(const struct folio *folio, + const struct page *, const struct vm_area_struct *); /* * Cleans the PTEs of shared mappings. @@ -774,14 +771,14 @@ 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)(const struct folio *folio, struct rmap_walk_control *rwc); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc); void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc); -struct anon_vma *folio_lock_anon_vma_read(struct folio *folio, +struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index e62ff805cfc9..6eb65ceed213 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -8,12 +8,6 @@ #define SUID_DUMP_USER 1 /* Dump as user of process */ #define SUID_DUMP_ROOT 2 /* Dump as root */ -/* mm flags */ - -/* for SUID_DUMP_* above */ -#define MMF_DUMPABLE_BITS 2 -#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) - extern void set_dumpable(struct mm_struct *mm, int value); /* * This returns the actual value of the suid_dumpable flag. For things @@ -31,80 +25,4 @@ static inline int get_dumpable(struct mm_struct *mm) return __get_dumpable(mm->flags); } -/* coredump filter bits */ -#define MMF_DUMP_ANON_PRIVATE 2 -#define MMF_DUMP_ANON_SHARED 3 -#define MMF_DUMP_MAPPED_PRIVATE 4 -#define MMF_DUMP_MAPPED_SHARED 5 -#define MMF_DUMP_ELF_HEADERS 6 -#define MMF_DUMP_HUGETLB_PRIVATE 7 -#define MMF_DUMP_HUGETLB_SHARED 8 -#define MMF_DUMP_DAX_PRIVATE 9 -#define MMF_DUMP_DAX_SHARED 10 - -#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS -#define MMF_DUMP_FILTER_BITS 9 -#define MMF_DUMP_FILTER_MASK \ - (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) -#define MMF_DUMP_FILTER_DEFAULT \ - ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ - (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) - -#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS -# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) -#else -# define MMF_DUMP_MASK_DEFAULT_ELF 0 -#endif - /* leave room for more dump flags */ -#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ -#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 - */ -//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ - -#define MMF_HAS_UPROBES 19 /* has uprobes */ -#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ -#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ -#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ -#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ -#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ -#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) -#define MMF_OOM_REAP_QUEUED 25 /* mm was queued for oom_reaper */ -#define MMF_MULTIPROCESS 26 /* mm is shared between processes */ -/* - * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either - * replaced in the future by mm.pinned_vm when it becomes stable, or grow into - * a counter on its own. We're aggresive on this bit for now: even if the - * pinned pages were unpinned later on, we'll still keep this bit set for the - * lifecycle of this mm, just for simplicity. - */ -#define MMF_HAS_PINNED 27 /* FOLL_PIN has run, never cleared */ - -#define MMF_HAS_MDWE 28 -#define MMF_HAS_MDWE_MASK (1 << MMF_HAS_MDWE) - - -#define MMF_HAS_MDWE_NO_INHERIT 29 - -#define MMF_VM_MERGE_ANY 30 -#define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) - -#define MMF_TOPDOWN 31 /* mm searches top down by default */ -#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) - -#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ - MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ - MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) - -static inline unsigned long mmf_init_flags(unsigned long flags) -{ - if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) - flags &= ~((1UL << MMF_HAS_MDWE) | - (1UL << MMF_HAS_MDWE_NO_INHERIT)); - return flags & MMF_INIT_MASK; -} - #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index e7aec20fb44f..3030d9245f5a 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -34,6 +34,12 @@ static inline int set_direct_map_default_noflush(struct page *page) return 0; } +static inline int set_direct_map_valid_noflush(struct page *page, + unsigned nr, bool valid) +{ + return 0; +} + static inline bool kernel_page_present(struct page *page) { return true; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 018da28c01e7..0b273a7b9f01 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -114,6 +114,7 @@ int shmem_unuse(unsigned int type); unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force); +bool shmem_hpage_pmd_enabled(void); #else static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, @@ -121,6 +122,11 @@ static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, { return 0; } + +static inline bool shmem_hpage_pmd_enabled(void) +{ + return false; +} #endif #ifdef CONFIG_SHMEM diff --git a/include/linux/swapops.h b/include/linux/swapops.h index cb468e418ea1..96f26e29fefe 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -426,9 +426,19 @@ typedef unsigned long pte_marker; * "Poisoned" here is meant in the very general sense of "future accesses are * invalid", instead of referring very specifically to hardware memory errors. * This marker is meant to represent any of various different causes of this. + * + * Note that, when encountered by the faulting logic, PTEs with this marker will + * result in VM_FAULT_HWPOISON and thus regardless trigger hardware memory error + * logic. */ #define PTE_MARKER_POISONED BIT(1) -#define PTE_MARKER_MASK (BIT(2) - 1) +/* + * Indicates that, on fault, this PTE will case a SIGSEGV signal to be + * sent. This means guard markers behave in effect as if the region were mapped + * PROT_NONE, rather than if they were a memory hole or equivalent. + */ +#define PTE_MARKER_GUARD BIT(2) +#define PTE_MARKER_MASK (BIT(3) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { @@ -464,6 +474,18 @@ static inline int is_poisoned_swp_entry(swp_entry_t entry) { return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_POISONED); + +} + +static inline swp_entry_t make_guard_swp_entry(void) +{ + return make_pte_marker_entry(PTE_MARKER_GUARD); +} + +static inline int is_guard_swp_entry(swp_entry_t entry) +{ + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_GUARD); } /* diff --git a/include/linux/text-patching.h b/include/linux/text-patching.h new file mode 100644 index 000000000000..ad5877ab0855 --- /dev/null +++ b/include/linux/text-patching.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TEXT_PATCHING_H +#define _LINUX_TEXT_PATCHING_H + +#include <asm/text-patching.h> + +#ifndef text_poke_copy +static inline void *text_poke_copy(void *dst, const void *src, size_t len) +{ + return memcpy(dst, src, len); +} +#define text_poke_copy text_poke_copy +#endif + +#endif /* _LINUX_TEXT_PATCHING_H */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ad2ce7a6ab7a..31e9ffd936e3 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -134,12 +134,6 @@ extern void vm_unmap_ram(const void *mem, unsigned int count); extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); -#ifdef CONFIG_MMU -extern unsigned long vmalloc_nr_pages(void); -#else -static inline unsigned long vmalloc_nr_pages(void) { return 0; } -#endif - extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); #define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) @@ -208,6 +202,9 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); +int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, + struct page **pages, unsigned int page_shift); + /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() @@ -266,12 +263,29 @@ static inline bool is_vm_area_hugepages(const void *addr) #endif } +/* for /proc/kcore */ +long vread_iter(struct iov_iter *iter, const char *addr, size_t count); + +/* + * Internals. Don't use.. + */ +__init void vm_area_add_early(struct vm_struct *vm); +__init void vm_area_register_early(struct vm_struct *vm, size_t align); + +int register_vmap_purge_notifier(struct notifier_block *nb); +int unregister_vmap_purge_notifier(struct notifier_block *nb); + #ifdef CONFIG_MMU +#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) + +unsigned long vmalloc_nr_pages(void); + int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages); void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end); void vunmap_range(unsigned long addr, unsigned long end); + static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); @@ -279,24 +293,14 @@ static inline void set_vm_flush_reset_perms(void *addr) if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } +#else /* !CONFIG_MMU */ +#define VMALLOC_TOTAL 0UL -#else -static inline void set_vm_flush_reset_perms(void *addr) -{ -} -#endif - -/* for /proc/kcore */ -extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); - -/* - * Internals. Don't use.. - */ -extern __init void vm_area_add_early(struct vm_struct *vm); -extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); +static inline unsigned long vmalloc_nr_pages(void) { return 0; } +static inline void set_vm_flush_reset_perms(void *addr) {} +#endif /* CONFIG_MMU */ -#ifdef CONFIG_SMP -# ifdef CONFIG_MMU +#if defined(CONFIG_MMU) && defined(CONFIG_SMP) struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align); @@ -311,22 +315,9 @@ pcpu_get_vm_areas(const unsigned long *offsets, return NULL; } -static inline void -pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) -{ -} -# endif -#endif - -#ifdef CONFIG_MMU -#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) -#else -#define VMALLOC_TOTAL 0UL +static inline void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) {} #endif -int register_vmap_purge_notifier(struct notifier_block *nb); -int unregister_vmap_purge_notifier(struct notifier_block *nb); - #if defined(CONFIG_MMU) && defined(CONFIG_PRINTK) bool vmalloc_dump_obj(void *object); #else diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 9cd1beef0654..d961ead91bf1 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -7,7 +7,7 @@ struct lruvec; -extern atomic_t zswap_stored_pages; +extern atomic_long_t zswap_stored_pages; #ifdef CONFIG_ZSWAP diff --git a/include/trace/events/memcg.h b/include/trace/events/memcg.h new file mode 100644 index 000000000000..dfe2f51019b4 --- /dev/null +++ b/include/trace/events/memcg.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM memcg + +#if !defined(_TRACE_MEMCG_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MEMCG_H + +#include <linux/memcontrol.h> +#include <linux/tracepoint.h> + + +DECLARE_EVENT_CLASS(memcg_rstat_stats, + + TP_PROTO(struct mem_cgroup *memcg, int item, int val), + + TP_ARGS(memcg, item, val), + + TP_STRUCT__entry( + __field(u64, id) + __field(int, item) + __field(int, val) + ), + + TP_fast_assign( + __entry->id = cgroup_id(memcg->css.cgroup); + __entry->item = item; + __entry->val = val; + ), + + TP_printk("memcg_id=%llu item=%d val=%d", + __entry->id, __entry->item, __entry->val) +); + +DEFINE_EVENT(memcg_rstat_stats, mod_memcg_state, + + TP_PROTO(struct mem_cgroup *memcg, int item, int val), + + TP_ARGS(memcg, item, val) +); + +DEFINE_EVENT(memcg_rstat_stats, mod_memcg_lruvec_state, + + TP_PROTO(struct mem_cgroup *memcg, int item, int val), + + TP_ARGS(memcg, item, val) +); + +DECLARE_EVENT_CLASS(memcg_rstat_events, + + TP_PROTO(struct mem_cgroup *memcg, int item, unsigned long val), + + TP_ARGS(memcg, item, val), + + TP_STRUCT__entry( + __field(u64, id) + __field(int, item) + __field(unsigned long, val) + ), + + TP_fast_assign( + __entry->id = cgroup_id(memcg->css.cgroup); + __entry->item = item; + __entry->val = val; + ), + + TP_printk("memcg_id=%llu item=%d val=%lu", + __entry->id, __entry->item, __entry->val) +); + +DEFINE_EVENT(memcg_rstat_events, count_memcg_events, + + TP_PROTO(struct mem_cgroup *memcg, int item, unsigned long val), + + TP_ARGS(memcg, item, val) +); + +TRACE_EVENT(memcg_flush_stats, + + TP_PROTO(struct mem_cgroup *memcg, s64 stats_updates, + bool force, bool needs_flush), + + TP_ARGS(memcg, stats_updates, force, needs_flush), + + TP_STRUCT__entry( + __field(u64, id) + __field(s64, stats_updates) + __field(bool, force) + __field(bool, needs_flush) + ), + + TP_fast_assign( + __entry->id = cgroup_id(memcg->css.cgroup); + __entry->stats_updates = stats_updates; + __entry->force = force; + __entry->needs_flush = needs_flush; + ), + + TP_printk("memcg_id=%llu stats_updates=%lld force=%d needs_flush=%d", + __entry->id, __entry->stats_updates, + __entry->force, __entry->needs_flush) +); + +#endif /* _TRACE_MEMCG_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/mmap_lock.h b/include/trace/events/mmap_lock.h index f2827f98a44f..bc2e3ad787b3 100644 --- a/include/trace/events/mmap_lock.h +++ b/include/trace/events/mmap_lock.h @@ -10,9 +10,6 @@ struct mm_struct; -extern int trace_mmap_lock_reg(void); -extern void trace_mmap_lock_unreg(void); - DECLARE_EVENT_CLASS(mmap_lock, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write), @@ -40,16 +37,15 @@ DECLARE_EVENT_CLASS(mmap_lock, ); #define DEFINE_MMAP_LOCK_EVENT(name) \ - DEFINE_EVENT_FN(mmap_lock, name, \ + DEFINE_EVENT(mmap_lock, name, \ TP_PROTO(struct mm_struct *mm, const char *memcg_path, \ bool write), \ - TP_ARGS(mm, memcg_path, write), \ - trace_mmap_lock_reg, trace_mmap_lock_unreg) + TP_ARGS(mm, memcg_path, write)) DEFINE_MMAP_LOCK_EVENT(mmap_lock_start_locking); DEFINE_MMAP_LOCK_EVENT(mmap_lock_released); -TRACE_EVENT_FN(mmap_lock_acquire_returned, +TRACE_EVENT(mmap_lock_acquire_returned, TP_PROTO(struct mm_struct *mm, const char *memcg_path, bool write, bool success), @@ -76,9 +72,7 @@ TRACE_EVENT_FN(mmap_lock_acquire_returned, __get_str(memcg_path), __entry->write ? "true" : "false", __entry->success ? "true" : "false" - ), - - trace_mmap_lock_reg, trace_mmap_lock_unreg + ) ); #endif /* _TRACE_MMAP_LOCK_H */ diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 1a488c30afa5..490958fa10de 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -346,6 +346,51 @@ TRACE_EVENT(mm_vmscan_write_folio, show_reclaim_flags(__entry->reclaim_flags)) ); +TRACE_EVENT(mm_vmscan_reclaim_pages, + + TP_PROTO(int nid, + unsigned long nr_scanned, unsigned long nr_reclaimed, + struct reclaim_stat *stat), + + TP_ARGS(nid, nr_scanned, nr_reclaimed, stat), + + TP_STRUCT__entry( + __field(int, nid) + __field(unsigned long, nr_scanned) + __field(unsigned long, nr_reclaimed) + __field(unsigned long, nr_dirty) + __field(unsigned long, nr_writeback) + __field(unsigned long, nr_congested) + __field(unsigned long, nr_immediate) + __field(unsigned int, nr_activate0) + __field(unsigned int, nr_activate1) + __field(unsigned long, nr_ref_keep) + __field(unsigned long, nr_unmap_fail) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->nr_scanned = nr_scanned; + __entry->nr_reclaimed = nr_reclaimed; + __entry->nr_dirty = stat->nr_dirty; + __entry->nr_writeback = stat->nr_writeback; + __entry->nr_congested = stat->nr_congested; + __entry->nr_immediate = stat->nr_immediate; + __entry->nr_activate0 = stat->nr_activate[0]; + __entry->nr_activate1 = stat->nr_activate[1]; + __entry->nr_ref_keep = stat->nr_ref_keep; + __entry->nr_unmap_fail = stat->nr_unmap_fail; + ), + + TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld", + __entry->nid, + __entry->nr_scanned, __entry->nr_reclaimed, + __entry->nr_dirty, __entry->nr_writeback, + __entry->nr_congested, __entry->nr_immediate, + __entry->nr_activate0, __entry->nr_activate1, + __entry->nr_ref_keep, __entry->nr_unmap_fail) +); + TRACE_EVENT(mm_vmscan_lru_shrink_inactive, TP_PROTO(int nid, diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 6ce1f1ceb432..1ea2c4c33b86 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -79,6 +79,9 @@ #define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ +#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */ +#define MADV_GUARD_REMOVE 103 /* unguard range */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index a76ddc5fc982..fa04b14a7d72 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -15,7 +15,6 @@ #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> #include <linux/export.h> #include <linux/rmap.h> /* anon_vma_prepare */ #include <linux/mmu_notifier.h> diff --git a/kernel/fork.c b/kernel/fork.c index e58d27c05788..f253e81d0c28 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -16,7 +16,6 @@ #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> @@ -1546,8 +1545,9 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) return ERR_PTR(err); mm = get_task_mm(task); - if (mm && mm != current->mm && - !ptrace_may_access(task, mode)) { + if (!mm) { + mm = ERR_PTR(-ESRCH); + } else if (mm != current->mm && !ptrace_may_access(task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 326bfe6549d7..6de57246760e 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -399,7 +399,7 @@ again: key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); - key->shared.pgoff = folio->index + folio_page_idx(folio, page); + key->shared.pgoff = page_pgoff(folio, page); rcu_read_unlock(); } diff --git a/kernel/module/debug_kmemleak.c b/kernel/module/debug_kmemleak.c index b4cc03842d70..df873dad049d 100644 --- a/kernel/module/debug_kmemleak.c +++ b/kernel/module/debug_kmemleak.c @@ -14,7 +14,8 @@ void kmemleak_load_module(const struct module *mod, { /* only scan writable, non-executable sections */ for_each_mod_mem_type(type) { - if (type != MOD_DATA && type != MOD_INIT_DATA) + if (type != MOD_DATA && type != MOD_INIT_DATA && + !mod->mem[type].is_rox) kmemleak_no_scan(mod->mem[type].base); } } diff --git a/kernel/module/main.c b/kernel/module/main.c index 4490924fe24e..d2e1b8976c7b 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1189,6 +1189,18 @@ void __weak module_arch_freeing_init(struct module *mod) { } +void *__module_writable_address(struct module *mod, void *loc) +{ + for_class_mod_mem_type(type, text) { + struct module_memory *mem = &mod->mem[type]; + + if (loc >= mem->base && loc < mem->base + mem->size) + return loc + (mem->rw_copy - mem->base); + } + + return loc; +} + static int module_memory_alloc(struct module *mod, enum mod_mem_type type) { unsigned int size = PAGE_ALIGN(mod->mem[type].size); @@ -1206,6 +1218,23 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type) if (!ptr) return -ENOMEM; + mod->mem[type].base = ptr; + + if (execmem_is_rox(execmem_type)) { + ptr = vzalloc(size); + + if (!ptr) { + execmem_free(mod->mem[type].base); + return -ENOMEM; + } + + mod->mem[type].rw_copy = ptr; + mod->mem[type].is_rox = true; + } else { + mod->mem[type].rw_copy = mod->mem[type].base; + memset(mod->mem[type].base, 0, size); + } + /* * The pointer to these blocks of memory are stored on the module * structure and we keep that around so long as the module is @@ -1219,24 +1248,20 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type) */ kmemleak_not_leak(ptr); - memset(ptr, 0, size); - mod->mem[type].base = ptr; - return 0; } -static void module_memory_free(struct module *mod, enum mod_mem_type type, - bool unload_codetags) +static void module_memory_free(struct module *mod, enum mod_mem_type type) { - void *ptr = mod->mem[type].base; + struct module_memory *mem = &mod->mem[type]; - if (!unload_codetags && mod_mem_type_is_core_data(type)) - return; + if (mem->is_rox) + vfree(mem->rw_copy); - execmem_free(ptr); + execmem_free(mem->base); } -static void free_mod_mem(struct module *mod, bool unload_codetags) +static void free_mod_mem(struct module *mod) { for_each_mod_mem_type(type) { struct module_memory *mod_mem = &mod->mem[type]; @@ -1247,25 +1272,20 @@ static void free_mod_mem(struct module *mod, bool unload_codetags) /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod_mem->base, mod_mem->size); if (mod_mem->size) - module_memory_free(mod, type, unload_codetags); + module_memory_free(mod, type); } /* MOD_DATA hosts mod, so free it at last */ lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size); - module_memory_free(mod, MOD_DATA, unload_codetags); + module_memory_free(mod, MOD_DATA); } /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { - bool unload_codetags; - trace_module_free(mod); - unload_codetags = codetag_unload_module(mod); - if (!unload_codetags) - pr_warn("%s: memory allocation(s) from the module still alive, cannot unload cleanly\n", - mod->name); + codetag_unload_module(mod); mod_sysfs_teardown(mod); @@ -1308,7 +1328,7 @@ static void free_module(struct module *mod) kfree(mod->args); percpu_modfree(mod); - free_mod_mem(mod, unload_codetags); + free_mod_mem(mod); } void *__symbol_get(const char *symbol) @@ -1573,6 +1593,20 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i if (WARN_ON_ONCE(type == MOD_INVALID)) continue; + /* + * Do not allocate codetag memory as we load it into + * preallocated contiguous memory. + */ + if (codetag_needs_module_section(mod, sname, s->sh_size)) { + /* + * s->sh_entsize won't be used but populate the + * type field to avoid confusion. + */ + s->sh_entsize = ((unsigned long)(type) & SH_ENTSIZE_TYPE_MASK) + << SH_ENTSIZE_TYPE_SHIFT; + continue; + } + s->sh_entsize = module_get_offset_and_type(mod, type, s, i); pr_debug("\t%s\n", sname); } @@ -2247,17 +2281,19 @@ static int move_module(struct module *mod, struct load_info *info) int i; enum mod_mem_type t = 0; int ret = -ENOMEM; + bool codetag_section_found = false; for_each_mod_mem_type(type) { if (!mod->mem[type].size) { mod->mem[type].base = NULL; + mod->mem[type].rw_copy = NULL; continue; } ret = module_memory_alloc(mod, type); if (ret) { t = type; - goto out_enomem; + goto out_err; } } @@ -2266,12 +2302,37 @@ static int move_module(struct module *mod, struct load_info *info) for (i = 0; i < info->hdr->e_shnum; i++) { void *dest; Elf_Shdr *shdr = &info->sechdrs[i]; - enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; + const char *sname; + unsigned long addr; if (!(shdr->sh_flags & SHF_ALLOC)) continue; - dest = mod->mem[type].base + (shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK); + sname = info->secstrings + shdr->sh_name; + /* + * Load codetag sections separately as they might still be used + * after module unload. + */ + if (codetag_needs_module_section(mod, sname, shdr->sh_size)) { + dest = codetag_alloc_module_section(mod, sname, shdr->sh_size, + arch_mod_section_prepend(mod, i), shdr->sh_addralign); + if (WARN_ON(!dest)) { + ret = -EINVAL; + goto out_err; + } + if (IS_ERR(dest)) { + ret = PTR_ERR(dest); + goto out_err; + } + addr = (unsigned long)dest; + codetag_section_found = true; + } else { + enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; + unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK; + + addr = (unsigned long)mod->mem[type].base + offset; + dest = mod->mem[type].rw_copy + offset; + } if (shdr->sh_type != SHT_NOBITS) { /* @@ -2283,7 +2344,7 @@ static int move_module(struct module *mod, struct load_info *info) if (i == info->index.mod && (WARN_ON_ONCE(shdr->sh_size != sizeof(struct module)))) { ret = -ENOEXEC; - goto out_enomem; + goto out_err; } memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); } @@ -2293,15 +2354,18 @@ static int move_module(struct module *mod, struct load_info *info) * users of info can keep taking advantage and using the newly * minted official memory area. */ - shdr->sh_addr = (unsigned long)dest; + shdr->sh_addr = addr; pr_debug("\t0x%lx 0x%.8lx %s\n", (long)shdr->sh_addr, (long)shdr->sh_size, info->secstrings + shdr->sh_name); } return 0; -out_enomem: +out_err: for (t--; t >= 0; t--) - module_memory_free(mod, t, true); + module_memory_free(mod, t); + if (codetag_section_found) + codetag_free_module_sections(mod); + return ret; } @@ -2422,6 +2486,8 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) /* Module has been copied to its final place now: return it. */ mod = (void *)info->sechdrs[info->index.mod].sh_addr; kmemleak_load_module(mod, info); + codetag_module_replaced(info->mod, mod); + return mod; } @@ -2431,7 +2497,7 @@ static void module_deallocate(struct module *mod, struct load_info *info) percpu_modfree(mod); module_arch_freeing_init(mod); - free_mod_mem(mod, true); + free_mod_mem(mod); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -2441,8 +2507,17 @@ int __weak module_finalize(const Elf_Ehdr *hdr, return 0; } +int __weak module_post_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + return 0; +} + static int post_relocation(struct module *mod, const struct load_info *info) { + int ret; + /* Sort exception table now relocations are done. */ sort_extable(mod->extable, mod->extable + mod->num_exentries); @@ -2454,7 +2529,24 @@ static int post_relocation(struct module *mod, const struct load_info *info) add_kallsyms(mod, info); /* Arch-specific module finalizing. */ - return module_finalize(info->hdr, info->sechdrs, mod); + ret = module_finalize(info->hdr, info->sechdrs, mod); + if (ret) + return ret; + + for_each_mod_mem_type(type) { + struct module_memory *mem = &mod->mem[type]; + + if (mem->is_rox) { + if (!execmem_update_copy(mem->base, mem->rw_copy, + mem->size)) + return -ENOMEM; + + vfree(mem->rw_copy); + mem->rw_copy = NULL; + } + } + + return module_post_finalize(info->hdr, info->sechdrs, mod); } /* Call module constructors. */ diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c index c45caa4690e5..239e5013359d 100644 --- a/kernel/module/strict_rwx.c +++ b/kernel/module/strict_rwx.c @@ -34,6 +34,9 @@ int module_enable_text_rox(const struct module *mod) for_class_mod_mem_type(type, text) { int ret; + if (mod->mem[type].is_rox) + continue; + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) ret = module_set_memory(mod, type, set_memory_rox); else diff --git a/kernel/resource.c b/kernel/resource.c index 4101016e8b20..d2c8143ae4ff 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1869,7 +1869,7 @@ static resource_size_t gfr_start(struct resource *base, resource_size_t size, if (flags & GFR_DESCENDING) { resource_size_t end; - end = min_t(resource_size_t, base->end, PHYSMEM_END); + end = min_t(resource_size_t, base->end, DIRECT_MAP_PHYSMEM_END); return end - size + 1; } @@ -1886,7 +1886,7 @@ static bool gfr_continue(struct resource *base, resource_size_t addr, * @size did not wrap 0. */ return addr > addr - size && - addr <= min_t(resource_size_t, base->end, PHYSMEM_END); + addr <= min_t(resource_size_t, base->end, DIRECT_MAP_PHYSMEM_END); } static resource_size_t gfr_next(resource_size_t addr, resource_size_t size, diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a2fe6d5cfbd2..5d9eca035d47 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -993,6 +993,7 @@ config CODE_TAGGING config MEM_ALLOC_PROFILING bool "Enable memory allocation profiling" default n + depends on MMU depends on PROC_FS depends on !DEBUG_FORCE_WEAK_PER_CPU select CODE_TAGGING diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 98016e137b7f..f82889a830fa 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -195,13 +195,6 @@ config KASAN_KUNIT_TEST For more information on KUnit and unit tests in general, please refer 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 - A part of the KASAN test suite that is not integrated with KUnit. - Incompatible with Hardware Tag-Based KASAN. - config KASAN_EXTRA_INFO bool "Record and report more information" depends on KASAN diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 81e5f9a70f22..2414a7ee7ec7 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -1,12 +1,26 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/alloc_tag.h> +#include <linux/execmem.h> #include <linux/fs.h> #include <linux/gfp.h> +#include <linux/kallsyms.h> #include <linux/module.h> #include <linux/page_ext.h> #include <linux/proc_fs.h> #include <linux/seq_buf.h> #include <linux/seq_file.h> +#include <linux/vmalloc.h> + +#define ALLOCINFO_FILE_NAME "allocinfo" +#define MODULE_ALLOC_TAG_VMAP_SIZE (100000UL * sizeof(struct alloc_tag)) +#define SECTION_START(NAME) (CODETAG_SECTION_START_PREFIX NAME) +#define SECTION_STOP(NAME) (CODETAG_SECTION_STOP_PREFIX NAME) + +#ifdef CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT +static bool mem_profiling_support = true; +#else +static bool mem_profiling_support; +#endif static struct codetag_type *alloc_tag_cttype; @@ -15,6 +29,11 @@ EXPORT_SYMBOL(_shared_alloc_tag); DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, mem_alloc_profiling_key); +DEFINE_STATIC_KEY_FALSE(mem_profiling_compressed); + +struct alloc_tag_kernel_section kernel_tags = { NULL, 0 }; +unsigned long alloc_tag_ref_mask; +int alloc_tag_ref_offs; struct allocinfo_private { struct codetag_iterator iter; @@ -144,44 +163,450 @@ size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sl return nr; } +void pgalloc_tag_split(struct folio *folio, int old_order, int new_order) +{ + int i; + struct alloc_tag *tag; + unsigned int nr_pages = 1 << new_order; + + if (!mem_alloc_profiling_enabled()) + return; + + tag = pgalloc_tag_get(&folio->page); + if (!tag) + return; + + for (i = nr_pages; i < (1 << old_order); i += nr_pages) { + union pgtag_ref_handle handle; + union codetag_ref ref; + + if (get_page_tag_ref(folio_page(folio, i), &ref, &handle)) { + /* Set new reference to point to the original tag */ + alloc_tag_ref_set(&ref, tag); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); + } + } +} + +void pgalloc_tag_copy(struct folio *new, struct folio *old) +{ + union pgtag_ref_handle handle; + union codetag_ref ref; + struct alloc_tag *tag; + + tag = pgalloc_tag_get(&old->page); + if (!tag) + return; + + if (!get_page_tag_ref(&new->page, &ref, &handle)) + return; + + /* Clear the old ref to the original allocation tag. */ + clear_page_tag_ref(&old->page); + /* Decrement the counters of the tag on get_new_folio. */ + alloc_tag_sub(&ref, folio_size(new)); + __alloc_tag_ref_set(&ref, tag); + update_page_tag_ref(handle, &ref); + put_page_tag_ref(handle); +} + +static void shutdown_mem_profiling(bool remove_file) +{ + if (mem_alloc_profiling_enabled()) + static_branch_disable(&mem_alloc_profiling_key); + + if (!mem_profiling_support) + return; + + if (remove_file) + remove_proc_entry(ALLOCINFO_FILE_NAME, NULL); + mem_profiling_support = false; +} + static void __init procfs_init(void) { - proc_create_seq("allocinfo", 0400, NULL, &allocinfo_seq_op); + if (!mem_profiling_support) + return; + + if (!proc_create_seq(ALLOCINFO_FILE_NAME, 0400, NULL, &allocinfo_seq_op)) { + pr_err("Failed to create %s file\n", ALLOCINFO_FILE_NAME); + shutdown_mem_profiling(false); + } +} + +void __init alloc_tag_sec_init(void) +{ + struct alloc_tag *last_codetag; + + if (!mem_profiling_support) + return; + + if (!static_key_enabled(&mem_profiling_compressed)) + return; + + kernel_tags.first_tag = (struct alloc_tag *)kallsyms_lookup_name( + SECTION_START(ALLOC_TAG_SECTION_NAME)); + last_codetag = (struct alloc_tag *)kallsyms_lookup_name( + SECTION_STOP(ALLOC_TAG_SECTION_NAME)); + kernel_tags.count = last_codetag - kernel_tags.first_tag; + + /* Check if kernel tags fit into page flags */ + if (kernel_tags.count > (1UL << NR_UNUSED_PAGEFLAG_BITS)) { + shutdown_mem_profiling(false); /* allocinfo file does not exist yet */ + pr_err("%lu allocation tags cannot be references using %d available page flag bits. Memory allocation profiling is disabled!\n", + kernel_tags.count, NR_UNUSED_PAGEFLAG_BITS); + return; + } + + alloc_tag_ref_offs = (LRU_REFS_PGOFF - NR_UNUSED_PAGEFLAG_BITS); + alloc_tag_ref_mask = ((1UL << NR_UNUSED_PAGEFLAG_BITS) - 1); + pr_debug("Memory allocation profiling compression is using %d page flag bits!\n", + NR_UNUSED_PAGEFLAG_BITS); +} + +#ifdef CONFIG_MODULES + +static struct maple_tree mod_area_mt = MTREE_INIT(mod_area_mt, MT_FLAGS_ALLOC_RANGE); +static struct vm_struct *vm_module_tags; +/* A dummy object used to indicate an unloaded module */ +static struct module unloaded_mod; +/* A dummy object used to indicate a module prepended area */ +static struct module prepend_mod; + +struct alloc_tag_module_section module_tags; + +static inline unsigned long alloc_tag_align(unsigned long val) +{ + if (!static_key_enabled(&mem_profiling_compressed)) { + /* No alignment requirements when we are not indexing the tags */ + return val; + } + + if (val % sizeof(struct alloc_tag) == 0) + return val; + return ((val / sizeof(struct alloc_tag)) + 1) * sizeof(struct alloc_tag); } -static bool alloc_tag_module_unload(struct codetag_type *cttype, - struct codetag_module *cmod) +static bool ensure_alignment(unsigned long align, unsigned int *prepend) { - struct codetag_iterator iter = codetag_get_ct_iter(cttype); - struct alloc_tag_counters counter; - bool module_unused = true; + if (!static_key_enabled(&mem_profiling_compressed)) { + /* No alignment requirements when we are not indexing the tags */ + return true; + } + + /* + * If alloc_tag size is not a multiple of required alignment, tag + * indexing does not work. + */ + if (!IS_ALIGNED(sizeof(struct alloc_tag), align)) + return false; + + /* Ensure prepend consumes multiple of alloc_tag-sized blocks */ + if (*prepend) + *prepend = alloc_tag_align(*prepend); + + return true; +} + +static inline bool tags_addressable(void) +{ + unsigned long tag_idx_count; + + if (!static_key_enabled(&mem_profiling_compressed)) + return true; /* with page_ext tags are always addressable */ + + tag_idx_count = CODETAG_ID_FIRST + kernel_tags.count + + module_tags.size / sizeof(struct alloc_tag); + + return tag_idx_count < (1UL << NR_UNUSED_PAGEFLAG_BITS); +} + +static bool needs_section_mem(struct module *mod, unsigned long size) +{ + if (!mem_profiling_support) + return false; + + return size >= sizeof(struct alloc_tag); +} + +static struct alloc_tag *find_used_tag(struct alloc_tag *from, struct alloc_tag *to) +{ + while (from <= to) { + struct alloc_tag_counters counter; + + counter = alloc_tag_read(from); + if (counter.bytes) + return from; + from++; + } + + return NULL; +} + +/* Called with mod_area_mt locked */ +static void clean_unused_module_areas_locked(void) +{ + MA_STATE(mas, &mod_area_mt, 0, module_tags.size); + struct module *val; + + mas_for_each(&mas, val, module_tags.size) { + if (val != &unloaded_mod) + continue; + + /* Release area if all tags are unused */ + if (!find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index), + (struct alloc_tag *)(module_tags.start_addr + mas.last))) + mas_erase(&mas); + } +} + +/* Called with mod_area_mt locked */ +static bool find_aligned_area(struct ma_state *mas, unsigned long section_size, + unsigned long size, unsigned int prepend, unsigned long align) +{ + bool cleanup_done = false; + +repeat: + /* Try finding exact size and hope the start is aligned */ + if (!mas_empty_area(mas, 0, section_size - 1, prepend + size)) { + if (IS_ALIGNED(mas->index + prepend, align)) + return true; + + /* Try finding larger area to align later */ + mas_reset(mas); + if (!mas_empty_area(mas, 0, section_size - 1, + size + prepend + align - 1)) + return true; + } + + /* No free area, try cleanup stale data and repeat the search once */ + if (!cleanup_done) { + clean_unused_module_areas_locked(); + cleanup_done = true; + mas_reset(mas); + goto repeat; + } + + return false; +} + +static int vm_module_tags_populate(void) +{ + unsigned long phys_size = vm_module_tags->nr_pages << PAGE_SHIFT; + + if (phys_size < module_tags.size) { + struct page **next_page = vm_module_tags->pages + vm_module_tags->nr_pages; + unsigned long addr = module_tags.start_addr + phys_size; + unsigned long more_pages; + unsigned long nr; + + more_pages = ALIGN(module_tags.size - phys_size, PAGE_SIZE) >> PAGE_SHIFT; + nr = alloc_pages_bulk_array_node(GFP_KERNEL | __GFP_NOWARN, + NUMA_NO_NODE, more_pages, next_page); + if (nr < more_pages || + vmap_pages_range(addr, addr + (nr << PAGE_SHIFT), PAGE_KERNEL, + next_page, PAGE_SHIFT) < 0) { + /* Clean up and error out */ + for (int i = 0; i < nr; i++) + __free_page(next_page[i]); + return -ENOMEM; + } + vm_module_tags->nr_pages += nr; + } + + return 0; +} + +static void *reserve_module_tags(struct module *mod, unsigned long size, + unsigned int prepend, unsigned long align) +{ + unsigned long section_size = module_tags.end_addr - module_tags.start_addr; + MA_STATE(mas, &mod_area_mt, 0, section_size - 1); + unsigned long offset; + void *ret = NULL; + + /* If no tags return error */ + if (size < sizeof(struct alloc_tag)) + return ERR_PTR(-EINVAL); + + /* + * align is always power of 2, so we can use IS_ALIGNED and ALIGN. + * align 0 or 1 means no alignment, to simplify set to 1. + */ + if (!align) + align = 1; + + if (!ensure_alignment(align, &prepend)) { + shutdown_mem_profiling(true); + pr_err("%s: alignment %lu is incompatible with allocation tag indexing. Memory allocation profiling is disabled!\n", + mod->name, align); + return ERR_PTR(-EINVAL); + } + + mas_lock(&mas); + if (!find_aligned_area(&mas, section_size, size, prepend, align)) { + ret = ERR_PTR(-ENOMEM); + goto unlock; + } + + /* Mark found area as reserved */ + offset = mas.index; + offset += prepend; + offset = ALIGN(offset, align); + if (offset != mas.index) { + unsigned long pad_start = mas.index; + + mas.last = offset - 1; + mas_store(&mas, &prepend_mod); + if (mas_is_err(&mas)) { + ret = ERR_PTR(xa_err(mas.node)); + goto unlock; + } + mas.index = offset; + mas.last = offset + size - 1; + mas_store(&mas, mod); + if (mas_is_err(&mas)) { + mas.index = pad_start; + mas_erase(&mas); + ret = ERR_PTR(xa_err(mas.node)); + } + } else { + mas.last = offset + size - 1; + mas_store(&mas, mod); + if (mas_is_err(&mas)) + ret = ERR_PTR(xa_err(mas.node)); + } +unlock: + mas_unlock(&mas); + + if (IS_ERR(ret)) + return ret; + + if (module_tags.size < offset + size) { + int grow_res; + + module_tags.size = offset + size; + if (mem_alloc_profiling_enabled() && !tags_addressable()) { + shutdown_mem_profiling(true); + pr_warn("With module %s there are too many tags to fit in %d page flag bits. Memory allocation profiling is disabled!\n", + mod->name, NR_UNUSED_PAGEFLAG_BITS); + } + + grow_res = vm_module_tags_populate(); + if (grow_res) { + shutdown_mem_profiling(true); + pr_err("Failed to allocate memory for allocation tags in the module %s. Memory allocation profiling is disabled!\n", + mod->name); + return ERR_PTR(grow_res); + } + } + + return (struct alloc_tag *)(module_tags.start_addr + offset); +} + +static void release_module_tags(struct module *mod, bool used) +{ + MA_STATE(mas, &mod_area_mt, module_tags.size, module_tags.size); struct alloc_tag *tag; - struct codetag *ct; + struct module *val; + + mas_lock(&mas); + mas_for_each_rev(&mas, val, 0) + if (val == mod) + break; + + if (!val) /* module not found */ + goto out; + + if (!used) + goto release_area; + + /* Find out if the area is used */ + tag = find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index), + (struct alloc_tag *)(module_tags.start_addr + mas.last)); + if (tag) { + struct alloc_tag_counters counter = alloc_tag_read(tag); + + pr_info("%s:%u module %s func:%s has %llu allocated at module unload\n", + tag->ct.filename, tag->ct.lineno, tag->ct.modname, + tag->ct.function, counter.bytes); + } else { + used = false; + } +release_area: + mas_store(&mas, used ? &unloaded_mod : NULL); + val = mas_prev_range(&mas, 0); + if (val == &prepend_mod) + mas_store(&mas, NULL); +out: + mas_unlock(&mas); +} - for (ct = codetag_next_ct(&iter); ct; ct = codetag_next_ct(&iter)) { - if (iter.cmod != cmod) +static void replace_module(struct module *mod, struct module *new_mod) +{ + MA_STATE(mas, &mod_area_mt, 0, module_tags.size); + struct module *val; + + mas_lock(&mas); + mas_for_each(&mas, val, module_tags.size) { + if (val != mod) continue; - tag = ct_to_alloc_tag(ct); - counter = alloc_tag_read(tag); + mas_store_gfp(&mas, new_mod, GFP_KERNEL); + break; + } + mas_unlock(&mas); +} - if (WARN(counter.bytes, - "%s:%u module %s func:%s has %llu allocated at module unload", - ct->filename, ct->lineno, ct->modname, ct->function, counter.bytes)) - module_unused = false; +static int __init alloc_mod_tags_mem(void) +{ + /* Map space to copy allocation tags */ + vm_module_tags = execmem_vmap(MODULE_ALLOC_TAG_VMAP_SIZE); + if (!vm_module_tags) { + pr_err("Failed to map %lu bytes for module allocation tags\n", + MODULE_ALLOC_TAG_VMAP_SIZE); + module_tags.start_addr = 0; + return -ENOMEM; } - return module_unused; + vm_module_tags->pages = kmalloc_array(get_vm_area_size(vm_module_tags) >> PAGE_SHIFT, + sizeof(struct page *), GFP_KERNEL | __GFP_ZERO); + if (!vm_module_tags->pages) { + free_vm_area(vm_module_tags); + return -ENOMEM; + } + + module_tags.start_addr = (unsigned long)vm_module_tags->addr; + module_tags.end_addr = module_tags.start_addr + MODULE_ALLOC_TAG_VMAP_SIZE; + /* Ensure the base is alloc_tag aligned when required for indexing */ + module_tags.start_addr = alloc_tag_align(module_tags.start_addr); + + return 0; +} + +static void __init free_mod_tags_mem(void) +{ + int i; + + module_tags.start_addr = 0; + for (i = 0; i < vm_module_tags->nr_pages; i++) + __free_page(vm_module_tags->pages[i]); + kfree(vm_module_tags->pages); + free_vm_area(vm_module_tags); } -#ifdef CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT -static bool mem_profiling_support __meminitdata = true; -#else -static bool mem_profiling_support __meminitdata; -#endif +#else /* CONFIG_MODULES */ + +static inline int alloc_mod_tags_mem(void) { return 0; } +static inline void free_mod_tags_mem(void) {} + +#endif /* CONFIG_MODULES */ +/* See: Documentation/mm/allocation-profiling.rst */ static int __init setup_early_mem_profiling(char *str) { + bool compressed = false; bool enable; if (!str || !str[0]) @@ -190,22 +615,37 @@ static int __init setup_early_mem_profiling(char *str) if (!strncmp(str, "never", 5)) { enable = false; mem_profiling_support = false; + pr_info("Memory allocation profiling is disabled!\n"); } else { - int res; + char *token = strsep(&str, ","); - res = kstrtobool(str, &enable); - if (res) - return res; + if (kstrtobool(token, &enable)) + return -EINVAL; + if (str) { + + if (strcmp(str, "compressed")) + return -EINVAL; + + compressed = true; + } mem_profiling_support = true; + pr_info("Memory allocation profiling is enabled %s compression and is turned %s!\n", + compressed ? "with" : "without", enable ? "on" : "off"); } - if (enable != static_key_enabled(&mem_alloc_profiling_key)) { + if (enable != mem_alloc_profiling_enabled()) { if (enable) static_branch_enable(&mem_alloc_profiling_key); else static_branch_disable(&mem_alloc_profiling_key); } + if (compressed != static_key_enabled(&mem_profiling_compressed)) { + if (compressed) + static_branch_enable(&mem_profiling_compressed); + else + static_branch_disable(&mem_profiling_compressed); + } return 0; } @@ -213,6 +653,9 @@ early_param("sysctl.vm.mem_profiling", setup_early_mem_profiling); static __init bool need_page_alloc_tagging(void) { + if (static_key_enabled(&mem_profiling_compressed)) + return false; + return mem_profiling_support; } @@ -255,14 +698,26 @@ static inline void sysctl_init(void) {} static int __init alloc_tag_init(void) { const struct codetag_type_desc desc = { - .section = "alloc_tags", - .tag_size = sizeof(struct alloc_tag), - .module_unload = alloc_tag_module_unload, + .section = ALLOC_TAG_SECTION_NAME, + .tag_size = sizeof(struct alloc_tag), +#ifdef CONFIG_MODULES + .needs_section_mem = needs_section_mem, + .alloc_section_mem = reserve_module_tags, + .free_section_mem = release_module_tags, + .module_replaced = replace_module, +#endif }; + int res; + + res = alloc_mod_tags_mem(); + if (res) + return res; alloc_tag_cttype = codetag_register_type(&desc); - if (IS_ERR(alloc_tag_cttype)) + if (IS_ERR(alloc_tag_cttype)) { + free_mod_tags_mem(); return PTR_ERR(alloc_tag_cttype); + } sysctl_init(); procfs_init(); diff --git a/lib/codetag.c b/lib/codetag.c index d1fbbb7c2ec3..42aadd6c1454 100644 --- a/lib/codetag.c +++ b/lib/codetag.c @@ -149,8 +149,8 @@ static struct codetag_range get_section_range(struct module *mod, const char *section) { return (struct codetag_range) { - get_symbol(mod, "__start_", section), - get_symbol(mod, "__stop_", section), + get_symbol(mod, CODETAG_SECTION_START_PREFIX, section), + get_symbol(mod, CODETAG_SECTION_STOP_PREFIX, section), }; } @@ -207,6 +207,94 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod) } #ifdef CONFIG_MODULES +#define CODETAG_SECTION_PREFIX ".codetag." + +/* Some codetag types need a separate module section */ +bool codetag_needs_module_section(struct module *mod, const char *name, + unsigned long size) +{ + const char *type_name; + struct codetag_type *cttype; + bool ret = false; + + if (strncmp(name, CODETAG_SECTION_PREFIX, strlen(CODETAG_SECTION_PREFIX))) + return false; + + type_name = name + strlen(CODETAG_SECTION_PREFIX); + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + if (strcmp(type_name, cttype->desc.section) == 0) { + if (!cttype->desc.needs_section_mem) + break; + + down_write(&cttype->mod_lock); + ret = cttype->desc.needs_section_mem(mod, size); + up_write(&cttype->mod_lock); + break; + } + } + mutex_unlock(&codetag_lock); + + return ret; +} + +void *codetag_alloc_module_section(struct module *mod, const char *name, + unsigned long size, unsigned int prepend, + unsigned long align) +{ + const char *type_name = name + strlen(CODETAG_SECTION_PREFIX); + struct codetag_type *cttype; + void *ret = ERR_PTR(-EINVAL); + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + if (strcmp(type_name, cttype->desc.section) == 0) { + if (WARN_ON(!cttype->desc.alloc_section_mem)) + break; + + down_write(&cttype->mod_lock); + ret = cttype->desc.alloc_section_mem(mod, size, prepend, align); + up_write(&cttype->mod_lock); + break; + } + } + mutex_unlock(&codetag_lock); + + return ret; +} + +void codetag_free_module_sections(struct module *mod) +{ + struct codetag_type *cttype; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + if (!cttype->desc.free_section_mem) + continue; + + down_write(&cttype->mod_lock); + cttype->desc.free_section_mem(mod, false); + up_write(&cttype->mod_lock); + } + mutex_unlock(&codetag_lock); +} + +void codetag_module_replaced(struct module *mod, struct module *new_mod) +{ + struct codetag_type *cttype; + + mutex_lock(&codetag_lock); + list_for_each_entry(cttype, &codetag_types, link) { + if (!cttype->desc.module_replaced) + continue; + + down_write(&cttype->mod_lock); + cttype->desc.module_replaced(mod, new_mod); + up_write(&cttype->mod_lock); + } + mutex_unlock(&codetag_lock); +} + void codetag_load_module(struct module *mod) { struct codetag_type *cttype; @@ -220,13 +308,12 @@ void codetag_load_module(struct module *mod) mutex_unlock(&codetag_lock); } -bool codetag_unload_module(struct module *mod) +void codetag_unload_module(struct module *mod) { struct codetag_type *cttype; - bool unload_ok = true; if (!mod) - return true; + return; /* await any module's kfree_rcu() operations to complete */ kvfree_rcu_barrier(); @@ -246,18 +333,17 @@ bool codetag_unload_module(struct module *mod) } if (found) { if (cttype->desc.module_unload) - if (!cttype->desc.module_unload(cttype, cmod)) - unload_ok = false; + cttype->desc.module_unload(cttype, cmod); cttype->count -= range_size(cttype, &cmod->range); idr_remove(&cttype->mod_idr, mod_id); kfree(cmod); } up_write(&cttype->mod_lock); + if (found && cttype->desc.free_section_mem) + cttype->desc.free_section_mem(mod, true); } mutex_unlock(&codetag_lock); - - return unload_ok; } #endif /* CONFIG_MODULES */ diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 3619301dda2e..d0ae808f3a14 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -64,6 +64,21 @@ #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> +/* + * Kernel pointer hashing renders much of the maple tree dump useless as tagged + * pointers get hashed to arbitrary values. + * + * If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is + * permissible to bypass this. Otherwise remain cautious and retain the hashing. + * + * Userland doesn't know about %px so also use %p there. + */ +#if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE) +#define PTR_FMT "%px" +#else +#define PTR_FMT "%p" +#endif + #define MA_ROOT_PARENT 1 /* @@ -120,7 +135,6 @@ static const unsigned char mt_min_slots[] = { #define MAPLE_BIG_NODE_GAPS (MAPLE_ARANGE64_SLOTS * 2 + 1) struct maple_big_node { - struct maple_pnode *parent; unsigned long pivot[MAPLE_BIG_NODE_SLOTS - 1]; union { struct maple_enode *slot[MAPLE_BIG_NODE_SLOTS]; @@ -1193,19 +1207,17 @@ static inline void mas_push_node(struct ma_state *mas, struct maple_node *used) reuse->request_count = 0; reuse->node_count = 0; - if (count && (head->node_count < MAPLE_ALLOC_SLOTS)) { - head->slot[head->node_count++] = reuse; - head->total++; - goto done; - } - - reuse->total = 1; - if ((head) && !((unsigned long)head & 0x1)) { + if (count) { + if (head->node_count < MAPLE_ALLOC_SLOTS) { + head->slot[head->node_count++] = reuse; + head->total++; + goto done; + } reuse->slot[0] = head; reuse->node_count = 1; - reuse->total += head->total; } + reuse->total = count + 1; mas->alloc = reuse; done: if (requested > 1) @@ -1251,11 +1263,11 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) mas->alloc = node; node->total = ++allocated; + node->request_count = 0; requested--; } node = mas->alloc; - node->request_count = 0; while (requested) { max_req = MAPLE_ALLOC_SLOTS - node->node_count; slots = (void **)&node->slot[node->node_count]; @@ -1271,7 +1283,10 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) node->node_count += count; allocated += count; - node = node->slot[0]; + /* find a non-full node*/ + do { + node = node->slot[0]; + } while (unlikely(node->node_count == MAPLE_ALLOC_SLOTS)); requested -= count; } mas->alloc->total = allocated; @@ -1280,10 +1295,9 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) nomem_bulk: /* Clean up potential freed allocations on bulk failure */ memset(slots, 0, max_req * sizeof(unsigned long)); + mas->alloc->total = allocated; nomem_one: mas_set_alloc_req(mas, requested); - if (mas->alloc && !(((unsigned long)mas->alloc & 0x1))) - mas->alloc->total = allocated; mas_set_err(mas, -ENOMEM); } @@ -1943,14 +1957,13 @@ static inline void mas_mab_cp(struct ma_state *mas, unsigned char mas_start, for (; i < piv_end; i++, j++) { b_node->pivot[j] = pivots[i]; if (unlikely(!b_node->pivot[j])) - break; + goto complete; if (unlikely(mas->max == b_node->pivot[j])) goto complete; } - if (likely(i <= mas_end)) - b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt); + b_node->pivot[j] = mas_safe_pivot(mas, pivots, i, mt); complete: b_node->b_end = ++j; @@ -2139,9 +2152,7 @@ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); - if (mte_is_root(mas->node)) - return false; - + /* For root node, p_slot is set to 0 by mte_parent_slot(). */ if (!p_slot) return false; @@ -3159,10 +3170,7 @@ static inline void mast_fill_bnode(struct maple_subtree_state *mast, bool cp = true; unsigned char split; - memset(mast->bn->gap, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->gap)); - memset(mast->bn->slot, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->slot)); - memset(mast->bn->pivot, 0, sizeof(unsigned long) * ARRAY_SIZE(mast->bn->pivot)); - mast->bn->b_end = 0; + memset(mast->bn, 0, sizeof(struct maple_big_node)); if (mte_is_root(mas->node)) { cp = false; @@ -3400,7 +3408,7 @@ static noinline_for_kasan void mas_commit_b_node(struct ma_wr_state *wr_mas, * @mas: The maple state * @entry: The entry to store into the tree */ -static inline int mas_root_expand(struct ma_state *mas, void *entry) +static inline void mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; @@ -3436,12 +3444,23 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry) ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); - return slot; + return; } +/* + * mas_store_root() - Storing value into root. + * @mas: The maple state + * @entry: The entry to store. + * + * There is no root node now and we are storing a value into the root - this + * function either assigns the pointer or expands into a node. + */ static inline void mas_store_root(struct ma_state *mas, void *entry) { - if (likely((mas->last != 0) || (mas->index != 0))) + if (!entry) { + if (!mas->index) + rcu_assign_pointer(mas->tree->ma_root, NULL); + } else if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); @@ -3662,7 +3681,9 @@ static inline void mas_new_root(struct ma_state *mas, void *entry) void __rcu **slots; unsigned long *pivots; - if (!entry && !mas->index && mas->last == ULONG_MAX) { + WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX); + + if (!entry) { mas->depth = 0; mas_set_height(mas); rcu_assign_pointer(mas->tree->ma_root, entry); @@ -3889,7 +3910,8 @@ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } - } else if (!mt_in_rcu(mas->tree)) { + } else { + WARN_ON_ONCE(mt_in_rcu(mas->tree)); /* * Expand the range, only partially overwriting the previous and * next ranges @@ -3899,8 +3921,6 @@ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ - } else { - return; } trace_ma_write(__func__, mas, 0, wr_mas->entry); @@ -4181,75 +4201,53 @@ static inline int mas_prealloc_calc(struct ma_state *mas, void *entry) } /* - * mas_wr_store_type() - Set the store type for a given + * mas_wr_store_type() - Determine the store type for a given * store operation. * @wr_mas: The maple write state + * + * Return: the type of store needed for the operation */ -static inline void mas_wr_store_type(struct ma_wr_state *wr_mas) +static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end; - if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) { - mas->store_type = wr_store_root; - return; - } + if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) + return wr_store_root; - if (unlikely(!mas_wr_walk(wr_mas))) { - mas->store_type = wr_spanning_store; - return; - } + if (unlikely(!mas_wr_walk(wr_mas))) + return wr_spanning_store; /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); if (!wr_mas->entry) mas_wr_extend_null(wr_mas); - new_end = mas_wr_new_end(wr_mas); - if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) { - mas->store_type = wr_exact_fit; - return; - } + if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) + return wr_exact_fit; - if (unlikely(!mas->index && mas->last == ULONG_MAX)) { - mas->store_type = wr_new_root; - return; - } + if (unlikely(!mas->index && mas->last == ULONG_MAX)) + return wr_new_root; + new_end = mas_wr_new_end(wr_mas); /* Potential spanning rebalance collapsing a node */ if (new_end < mt_min_slots[wr_mas->type]) { - if (!mte_is_root(mas->node) && !(mas->mas_flags & MA_STATE_BULK)) { - mas->store_type = wr_rebalance; - return; - } - mas->store_type = wr_node_store; - return; + if (!mte_is_root(mas->node) && !(mas->mas_flags & MA_STATE_BULK)) + return wr_rebalance; + return wr_node_store; } - if (new_end >= mt_slots[wr_mas->type]) { - mas->store_type = wr_split_store; - return; - } + if (new_end >= mt_slots[wr_mas->type]) + return wr_split_store; - if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) { - mas->store_type = wr_append; - return; - } + if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) + return wr_append; if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) || - (wr_mas->offset_end - mas->offset == 1))) { - mas->store_type = wr_slot_store; - return; - } - - if (mte_is_root(mas->node) || (new_end >= mt_min_slots[wr_mas->type]) || - (mas->mas_flags & MA_STATE_BULK)) { - mas->store_type = wr_node_store; - return; - } + (wr_mas->offset_end - mas->offset == 1))) + return wr_slot_store; - mas->store_type = wr_invalid; - MAS_WARN_ON(mas, 1); + return wr_node_store; } /** @@ -4264,7 +4262,7 @@ static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry) int request; mas_wr_prealloc_setup(wr_mas); - mas_wr_store_type(wr_mas); + mas->store_type = mas_wr_store_type(wr_mas); request = mas_prealloc_calc(mas, entry); if (!request) return; @@ -5419,7 +5417,8 @@ void *mas_store(struct ma_state *mas, void *entry) trace_ma_write(__func__, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) - pr_err("Error %lX > %lX %p\n", mas->index, mas->last, entry); + pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, + entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); @@ -5435,7 +5434,7 @@ void *mas_store(struct ma_state *mas, void *entry) * overwrite multiple entries within a self-balancing B-Tree. */ mas_wr_prealloc_setup(&wr_mas); - mas_wr_store_type(&wr_mas); + mas->store_type = mas_wr_store_type(&wr_mas); if (mas->mas_flags & MA_STATE_PREALLOC) { mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); @@ -5538,7 +5537,7 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) int request; mas_wr_prealloc_setup(&wr_mas); - mas_wr_store_type(&wr_mas); + mas->store_type = mas_wr_store_type(&wr_mas); request = mas_prealloc_calc(mas, entry); if (!request) return ret; @@ -7124,14 +7123,14 @@ static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) - pr_cont("value %ld (0x%lx) [%p]\n", xa_to_value(entry), - xa_to_value(entry), entry); + pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry), + xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) - pr_cont("UNKNOWN ENTRY (%p)\n", entry); + pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry); else - pr_cont("%p\n", entry); + pr_cont(PTR_FMT "\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, @@ -7147,13 +7146,13 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry, for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: - pr_cont("%p %lX ", node->slot[i], node->pivot[i]); + pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: - pr_cont("%p %lu ", node->slot[i], node->pivot[i]); + pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } - pr_cont("%p\n", node->slot[i]); + pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; @@ -7175,11 +7174,11 @@ static void mt_dump_range64(const struct maple_tree *mt, void *entry, if (last > max) { switch(format) { case mt_dump_hex: - pr_err("node %p last (%lx) > max (%lx) at pivot %d!\n", + pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: - pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n", + pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } @@ -7209,13 +7208,13 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: - pr_cont("%p %lX ", node->slot[i], node->pivot[i]); + pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: - pr_cont("%p %lu ", node->slot[i], node->pivot[i]); + pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } - pr_cont("%p\n", node->slot[i]); + pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; @@ -7234,11 +7233,11 @@ static void mt_dump_arange64(const struct maple_tree *mt, void *entry, if (last > max) { switch(format) { case mt_dump_hex: - pr_err("node %p last (%lx) > max (%lx) at pivot %d!\n", + pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: - pr_err("node %p last (%lu) > max (%lu) at pivot %d!\n", + pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } @@ -7256,8 +7255,8 @@ static void mt_dump_node(const struct maple_tree *mt, void *entry, mt_dump_range(min, max, depth, format); - pr_cont("node %p depth %d type %d parent %p", node, depth, type, - node ? node->parent : NULL); + pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node, + depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); @@ -7285,12 +7284,14 @@ void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); - pr_info("maple_tree(%p) flags %X, height %u root %p\n", + pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n", mt, mt->ma_flags, mt_height(mt), entry); - if (!xa_is_node(entry)) - mt_dump_entry(entry, 0, 0, 0, format); - else if (entry) + if (xa_is_node(entry)) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); + else if (entry) + mt_dump_entry(entry, 0, 0, 0, format); + else + pr_info("(empty)\n"); } EXPORT_SYMBOL_GPL(mt_dump); @@ -7337,7 +7338,7 @@ static void mas_validate_gaps(struct ma_state *mas) MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { - pr_err("%p[%u] %lu >= %lu - %lu + 1 (%lu)\n", + pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); @@ -7357,19 +7358,19 @@ counted: MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { - pr_err("gap offset %p[%u] is invalid\n", node, offset); + pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { - pr_err("gap %p[%u] is not the largest gap %lu\n", + pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { - pr_err("gap %p[%u] beyond node limit != 0\n", + pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } @@ -7383,7 +7384,7 @@ counted: p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { - pr_err("gap %p[%u] != %lu\n", p_mn, p_slot, max_gap); + pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } @@ -7413,11 +7414,11 @@ static void mas_validate_parent_slot(struct ma_state *mas) node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) - pr_err("parent %p[%u] does not have %p\n", + pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { - pr_err("Invalid child %p at parent %p[%u] p_slot %u\n", + pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } @@ -7439,20 +7440,20 @@ static void mas_validate_child_slot(struct ma_state *mas) child = mas_slot(mas, slots, i); if (!child) { - pr_err("Non-leaf node lacks child at %p[%u]\n", + pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { - pr_err("Slot error at %p[%u]: child %p has pslot %u\n", + pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { - pr_err("child %p has parent %p not %p\n", + pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); @@ -7482,24 +7483,24 @@ static void mas_validate_limits(struct ma_state *mas) piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { - pr_err("Missing node limit pivot at %p[%u]", + pr_err("Missing node limit pivot at " PTR_FMT "[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { - pr_err("%p[%u] piv %lu < prev_piv %lu\n", + pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { - pr_err("%p[%u] %lu < %lu\n", mas_mn(mas), i, + pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { - pr_err("%p[%u] %lu > %lu\n", mas_mn(mas), i, + pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } @@ -7509,7 +7510,7 @@ static void mas_validate_limits(struct ma_state *mas) } if (mas_data_end(mas) != i) { - pr_err("node%p: data_end %u != the last slot offset %u\n", + pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } @@ -7518,8 +7519,8 @@ static void mas_validate_limits(struct ma_state *mas) void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { - pr_err("%p[%u] should not have entry %p\n", mas_mn(mas), - i, entry); + pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n", + mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } @@ -7529,7 +7530,7 @@ static void mas_validate_limits(struct ma_state *mas) if (!piv) continue; - pr_err("%p[%u] should not have piv %lu\n", + pr_err(PTR_FMT "[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } @@ -7554,7 +7555,7 @@ static void mt_validate_nulls(struct maple_tree *mt) do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { - pr_err("Sequential nulls end at %p[%u]\n", + pr_err("Sequential nulls end at " PTR_FMT "[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); @@ -7596,7 +7597,8 @@ void mt_validate(struct maple_tree *mt) end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && (mas.max != ULONG_MAX))) { - pr_err("Invalid size %u of %p\n", end, mas_mn(&mas)); + pr_err("Invalid size %u of " PTR_FMT "\n", + end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); @@ -7612,7 +7614,8 @@ EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { - pr_err("MAS: tree=%p enode=%p ", mas->tree, mas->node); + pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ", + mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); @@ -7676,7 +7679,7 @@ void mas_dump(const struct ma_state *mas) pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); - pr_err(" min=%lx max=%lx alloc=%p, depth=%u, flags=%x\n", + pr_err(" min=%lx max=%lx alloc=" PTR_FMT ", depth=%u, flags=%x\n", mas->min, mas->max, mas->alloc, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); @@ -7685,7 +7688,7 @@ EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { - pr_err("WR_MAS: node=%p r_min=%lx r_max=%lx\n", + pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, diff --git a/lib/percpu_test.c b/lib/percpu_test.c index 4a3d70bbc1a0..ce7124b16dab 100644 --- a/lib/percpu_test.c +++ b/lib/percpu_test.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/limits.h> #include <linux/module.h> /* validate @native and @pcp counter values match @expected */ @@ -24,8 +25,9 @@ static int __init percpu_test_init(void) * +ul_one/-ul_one below would replace with inc/dec instructions. */ volatile unsigned int ui_one = 1; - long l = 0; + unsigned long long ull = 0; unsigned long ul = 0; + long l = 0; pr_info("percpu test start\n"); @@ -112,6 +114,13 @@ static int __init percpu_test_init(void) CHECK(ul, ulong_counter, -1); CHECK(ul, ulong_counter, ULONG_MAX); + ul = ull = 0; + __this_cpu_write(ulong_counter, 0); + + ul = ull += UINT_MAX; + __this_cpu_add(ulong_counter, ull); + CHECK(ul, ulong_counter, UINT_MAX); + ul = 3; __this_cpu_write(ulong_counter, 3); diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 989a12a67872..6dc234913dd5 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -120,6 +120,9 @@ long strncpy_from_user(char *dst, const char __user *src, long count) if (unlikely(count <= 0)) return 0; + kasan_check_write(dst, count); + check_object_size(dst, count, false); + if (can_do_masked_user_access()) { long retval; @@ -142,8 +145,6 @@ long strncpy_from_user(char *dst, const char __user *src, long count) if (max > count) max = count; - kasan_check_write(dst, count); - check_object_size(dst, count, false); if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 31561e0e1a0d..704cb1093ae8 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -1387,6 +1387,92 @@ static noinline void __init check_prev_entry(struct maple_tree *mt) mas_unlock(&mas); } +static noinline void __init check_store_null(struct maple_tree *mt) +{ + MA_STATE(mas, mt, 0, ULONG_MAX); + + /* + * Store NULL at range [0, ULONG_MAX] to an empty tree should result + * in an empty tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at any range to an empty tree should result in an empty + * tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set_range(&mas, 3, 10); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at range [0, ULONG_MAX] to a single entry tree should + * result in an empty tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set(&mas, 0); + mas_store_gfp(&mas, &mas, GFP_KERNEL); + mas_set_range(&mas, 0, ULONG_MAX); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at range [0, n] to a single entry tree should + * result in an empty tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set(&mas, 0); + mas_store_gfp(&mas, &mas, GFP_KERNEL); + mas_set_range(&mas, 0, 5); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at range [m, n] where m > 0 to a single entry tree + * should still be a single entry tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set(&mas, 0); + mas_store_gfp(&mas, &mas, GFP_KERNEL); + mas_set_range(&mas, 2, 5); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, mtree_empty(mt)); +// MT_BUG_ON(mt, xa_is_node(mas_root(&mas))); + mas_unlock(&mas); + mtree_destroy(mt); + + /* + * Store NULL at range [0, ULONG_MAX] to a tree with node should + * result in an empty tree + */ + mt_init_flags(mt, MT_FLAGS_ALLOC_RANGE); + mas_lock(&mas); + mas_set_range(&mas, 1, 3); + mas_store_gfp(&mas, &mas, GFP_KERNEL); +// MT_BUG_ON(mt, !xa_is_node(mas_root(&mas))); + mas_set_range(&mas, 0, ULONG_MAX); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + MT_BUG_ON(mt, !mtree_empty(mt)); + mas_unlock(&mas); + mtree_destroy(mt); +} + static noinline void __init check_root_expand(struct maple_tree *mt) { MA_STATE(mas, mt, 0, 0); @@ -3711,6 +3797,10 @@ static int __init maple_tree_seed(void) #endif mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); + check_store_null(&tree); + mtree_destroy(&tree); + + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); check_root_expand(&tree); mtree_destroy(&tree); diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c index fa7cb0c87c03..95f288169a38 100644 --- a/mm/bootmem_info.c +++ b/mm/bootmem_info.c @@ -14,23 +14,24 @@ #include <linux/memory_hotplug.h> #include <linux/kmemleak.h> -void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) +void get_page_bootmem(unsigned long info, struct page *page, + enum bootmem_type type) { - page->index = type; + BUG_ON(type > 0xf); + BUG_ON(info > (ULONG_MAX >> 4)); SetPagePrivate(page); - set_page_private(page, info); + set_page_private(page, info << 4 | type); page_ref_inc(page); } void put_page_bootmem(struct page *page) { - unsigned long type = page->index; + enum bootmem_type type = bootmem_type(page); BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); if (page_ref_dec_return(page) == 1) { - page->index = 0; ClearPagePrivate(page); set_page_private(page, 0); INIT_LIST_HEAD(&page->lru); @@ -32,7 +32,7 @@ #include "cma.h" struct cma cma_areas[MAX_CMA_AREAS]; -unsigned cma_area_count; +unsigned int cma_area_count; static DEFINE_MUTEX(cma_mutex); phys_addr_t cma_get_base(const struct cma *cma) @@ -135,7 +135,6 @@ out_error: totalcma_pages -= cma->count; cma->count = 0; pr_err("CMA area %s could not be activated\n", cma->name); - return; } static int __init cma_init_reserved_areas(void) @@ -182,6 +181,15 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, if (!size || !memblock_is_region_reserved(base, size)) return -EINVAL; + /* + * CMA uses CMA_MIN_ALIGNMENT_BYTES as alignment requirement which + * needs pageblock_order to be initialized. Let's enforce it. + */ + if (!pageblock_order) { + pr_err("pageblock_order not yet initialized. Called during early boot?\n"); + return -EINVAL; + } + /* ensure minimal alignment required by mm core */ if (!IS_ALIGNED(base | size, CMA_MIN_ALIGNMENT_BYTES)) return -EINVAL; diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 35b72f88983a..d0357f3e9372 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -60,7 +60,7 @@ config DAMON_SYSFS the interface for arbitrary data access monitoring. config DAMON_SYSFS_KUNIT_TEST - bool "Test for damon debugfs interface" if !KUNIT_ALL_TESTS + bool "Test for damon sysfs interface" if !KUNIT_ALL_TESTS depends on DAMON_SYSFS && KUNIT=y default KUNIT_ALL_TESTS help diff --git a/mm/damon/tests/dbgfs-kunit.h b/mm/damon/tests/dbgfs-kunit.h index d2ecfcc8db86..087e53f641a8 100644 --- a/mm/damon/tests/dbgfs-kunit.h +++ b/mm/damon/tests/dbgfs-kunit.h @@ -168,6 +168,6 @@ static struct kunit_suite damon_test_suite = { }; kunit_test_suite(damon_test_suite); -#endif /* _DAMON_TEST_H */ +#endif /* _DAMON_DBGFS_TEST_H */ #endif /* CONFIG_DAMON_KUNIT_TEST */ diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h index a339d117150f..b9fe3bc8472b 100644 --- a/mm/damon/tests/vaddr-kunit.h +++ b/mm/damon/tests/vaddr-kunit.h @@ -66,7 +66,7 @@ failed: static void damon_test_three_regions_in_vmas(struct kunit *test) { static struct mm_struct mm; - struct damon_addr_range regions[3] = {0,}; + struct damon_addr_range regions[3] = {0}; /* 10-20-25, 200-210-220, 300-305, 307-330 */ struct vm_area_struct vmas[] = { (struct vm_area_struct) {.vm_start = 10, .vm_end = 20}, @@ -300,6 +300,8 @@ static void damon_test_split_evenly(struct kunit *test) damon_test_split_evenly_fail(test, 0, 100, 0); damon_test_split_evenly_succ(test, 0, 100, 10); damon_test_split_evenly_succ(test, 5, 59, 5); + damon_test_split_evenly_succ(test, 4, 6, 1); + damon_test_split_evenly_succ(test, 0, 3, 2); damon_test_split_evenly_fail(test, 5, 6, 2); } diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 08cfd22b5249..b9eaa20b73b9 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -67,10 +67,14 @@ static int damon_va_evenly_split_region(struct damon_target *t, unsigned long sz_orig, sz_piece, orig_end; struct damon_region *n = NULL, *next; unsigned long start; + unsigned int i; if (!r || !nr_pieces) return -EINVAL; + if (nr_pieces == 1) + return 0; + orig_end = r->ar.end; sz_orig = damon_sz_region(r); sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION); @@ -80,8 +84,7 @@ static int damon_va_evenly_split_region(struct damon_target *t, r->ar.end = r->ar.start + sz_piece; next = damon_next_region(r); - for (start = r->ar.end; start + sz_piece <= orig_end; - start += sz_piece) { + for (start = r->ar.end, i = 1; i < nr_pieces; start += sz_piece, i++) { n = damon_new_region(start, start + sz_piece); if (!n) return -ENOMEM; @@ -353,11 +356,9 @@ static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm, set_huge_pte_at(mm, addr, pte, entry, psize); } -#ifdef CONFIG_MMU_NOTIFIER if (mmu_notifier_clear_young(mm, addr, addr + huge_page_size(hstate_vma(vma)))) referenced = true; -#endif /* CONFIG_MMU_NOTIFIER */ if (referenced) folio_set_young(folio); diff --git a/mm/execmem.c b/mm/execmem.c index 0c4b36bc6d10..317b6a8d35be 100644 --- a/mm/execmem.c +++ b/mm/execmem.c @@ -6,28 +6,41 @@ * Copyright (C) 2024 Mike Rapoport IBM. */ +#define pr_fmt(fmt) "execmem: " fmt + #include <linux/mm.h> +#include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/execmem.h> +#include <linux/maple_tree.h> +#include <linux/set_memory.h> #include <linux/moduleloader.h> +#include <linux/text-patching.h> + +#include <asm/tlbflush.h> + +#include "internal.h" static struct execmem_info *execmem_info __ro_after_init; static struct execmem_info default_execmem_info __ro_after_init; -static void *__execmem_alloc(struct execmem_range *range, size_t size) +#ifdef CONFIG_MMU +static void *execmem_vmalloc(struct execmem_range *range, size_t size, + pgprot_t pgprot, unsigned long vm_flags) { bool kasan = range->flags & EXECMEM_KASAN_SHADOW; - unsigned long vm_flags = VM_FLUSH_RESET_PERMS; gfp_t gfp_flags = GFP_KERNEL | __GFP_NOWARN; + unsigned int align = range->alignment; unsigned long start = range->start; unsigned long end = range->end; - unsigned int align = range->alignment; - pgprot_t pgprot = range->pgprot; void *p; if (kasan) vm_flags |= VM_DEFER_KMEMLEAK; + if (vm_flags & VM_ALLOW_HUGE_VMAP) + align = PMD_SIZE; + p = __vmalloc_node_range(size, align, start, end, gfp_flags, pgprot, vm_flags, NUMA_NO_NODE, __builtin_return_address(0)); @@ -40,7 +53,7 @@ static void *__execmem_alloc(struct execmem_range *range, size_t size) } if (!p) { - pr_warn_ratelimited("execmem: unable to allocate memory\n"); + pr_warn_ratelimited("unable to allocate memory\n"); return NULL; } @@ -49,14 +62,314 @@ static void *__execmem_alloc(struct execmem_range *range, size_t size) return NULL; } - return kasan_reset_tag(p); + return p; +} + +struct vm_struct *execmem_vmap(size_t size) +{ + struct execmem_range *range = &execmem_info->ranges[EXECMEM_MODULE_DATA]; + struct vm_struct *area; + + area = __get_vm_area_node(size, range->alignment, PAGE_SHIFT, VM_ALLOC, + range->start, range->end, NUMA_NO_NODE, + GFP_KERNEL, __builtin_return_address(0)); + if (!area && range->fallback_start) + area = __get_vm_area_node(size, range->alignment, PAGE_SHIFT, VM_ALLOC, + range->fallback_start, range->fallback_end, + NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); + + return area; +} +#else +static void *execmem_vmalloc(struct execmem_range *range, size_t size, + pgprot_t pgprot, unsigned long vm_flags) +{ + return vmalloc(size); +} +#endif /* CONFIG_MMU */ + +#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX +struct execmem_cache { + struct mutex mutex; + struct maple_tree busy_areas; + struct maple_tree free_areas; +}; + +static struct execmem_cache execmem_cache = { + .mutex = __MUTEX_INITIALIZER(execmem_cache.mutex), + .busy_areas = MTREE_INIT_EXT(busy_areas, MT_FLAGS_LOCK_EXTERN, + execmem_cache.mutex), + .free_areas = MTREE_INIT_EXT(free_areas, MT_FLAGS_LOCK_EXTERN, + execmem_cache.mutex), +}; + +static inline unsigned long mas_range_len(struct ma_state *mas) +{ + return mas->last - mas->index + 1; +} + +static int execmem_set_direct_map_valid(struct vm_struct *vm, bool valid) +{ + unsigned int nr = (1 << get_vm_area_page_order(vm)); + unsigned int updated = 0; + int err = 0; + + for (int i = 0; i < vm->nr_pages; i += nr) { + err = set_direct_map_valid_noflush(vm->pages[i], nr, valid); + if (err) + goto err_restore; + updated += nr; + } + + return 0; + +err_restore: + for (int i = 0; i < updated; i += nr) + set_direct_map_valid_noflush(vm->pages[i], nr, !valid); + + return err; +} + +static void execmem_cache_clean(struct work_struct *work) +{ + struct maple_tree *free_areas = &execmem_cache.free_areas; + struct mutex *mutex = &execmem_cache.mutex; + MA_STATE(mas, free_areas, 0, ULONG_MAX); + void *area; + + mutex_lock(mutex); + mas_for_each(&mas, area, ULONG_MAX) { + size_t size = mas_range_len(&mas); + + if (IS_ALIGNED(size, PMD_SIZE) && + IS_ALIGNED(mas.index, PMD_SIZE)) { + struct vm_struct *vm = find_vm_area(area); + + execmem_set_direct_map_valid(vm, true); + mas_store_gfp(&mas, NULL, GFP_KERNEL); + vfree(area); + } + } + mutex_unlock(mutex); +} + +static DECLARE_WORK(execmem_cache_clean_work, execmem_cache_clean); + +static int execmem_cache_add(void *ptr, size_t size) +{ + struct maple_tree *free_areas = &execmem_cache.free_areas; + struct mutex *mutex = &execmem_cache.mutex; + unsigned long addr = (unsigned long)ptr; + MA_STATE(mas, free_areas, addr - 1, addr + 1); + unsigned long lower, upper; + void *area = NULL; + int err; + + lower = addr; + upper = addr + size - 1; + + mutex_lock(mutex); + area = mas_walk(&mas); + if (area && mas.last == addr - 1) + lower = mas.index; + + area = mas_next(&mas, ULONG_MAX); + if (area && mas.index == addr + size) + upper = mas.last; + + mas_set_range(&mas, lower, upper); + err = mas_store_gfp(&mas, (void *)lower, GFP_KERNEL); + mutex_unlock(mutex); + if (err) + return err; + + return 0; +} + +static bool within_range(struct execmem_range *range, struct ma_state *mas, + size_t size) +{ + unsigned long addr = mas->index; + + if (addr >= range->start && addr + size < range->end) + return true; + + if (range->fallback_start && + addr >= range->fallback_start && addr + size < range->fallback_end) + return true; + + return false; +} + +static void *__execmem_cache_alloc(struct execmem_range *range, size_t size) +{ + struct maple_tree *free_areas = &execmem_cache.free_areas; + struct maple_tree *busy_areas = &execmem_cache.busy_areas; + MA_STATE(mas_free, free_areas, 0, ULONG_MAX); + MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX); + struct mutex *mutex = &execmem_cache.mutex; + unsigned long addr, last, area_size = 0; + void *area, *ptr = NULL; + int err; + + mutex_lock(mutex); + mas_for_each(&mas_free, area, ULONG_MAX) { + area_size = mas_range_len(&mas_free); + + if (area_size >= size && within_range(range, &mas_free, size)) + break; + } + + if (area_size < size) + goto out_unlock; + + addr = mas_free.index; + last = mas_free.last; + + /* insert allocated size to busy_areas at range [addr, addr + size) */ + mas_set_range(&mas_busy, addr, addr + size - 1); + err = mas_store_gfp(&mas_busy, (void *)addr, GFP_KERNEL); + if (err) + goto out_unlock; + + mas_store_gfp(&mas_free, NULL, GFP_KERNEL); + if (area_size > size) { + void *ptr = (void *)(addr + size); + + /* + * re-insert remaining free size to free_areas at range + * [addr + size, last] + */ + mas_set_range(&mas_free, addr + size, last); + err = mas_store_gfp(&mas_free, ptr, GFP_KERNEL); + if (err) { + mas_store_gfp(&mas_busy, NULL, GFP_KERNEL); + goto out_unlock; + } + } + ptr = (void *)addr; + +out_unlock: + mutex_unlock(mutex); + return ptr; +} + +static int execmem_cache_populate(struct execmem_range *range, size_t size) +{ + unsigned long vm_flags = VM_ALLOW_HUGE_VMAP; + unsigned long start, end; + struct vm_struct *vm; + size_t alloc_size; + int err = -ENOMEM; + void *p; + + alloc_size = round_up(size, PMD_SIZE); + p = execmem_vmalloc(range, alloc_size, PAGE_KERNEL, vm_flags); + if (!p) + return err; + + vm = find_vm_area(p); + if (!vm) + goto err_free_mem; + + /* fill memory with instructions that will trap */ + execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true); + + start = (unsigned long)p; + end = start + alloc_size; + + vunmap_range(start, end); + + err = execmem_set_direct_map_valid(vm, false); + if (err) + goto err_free_mem; + + err = vmap_pages_range_noflush(start, end, range->pgprot, vm->pages, + PMD_SHIFT); + if (err) + goto err_free_mem; + + err = execmem_cache_add(p, alloc_size); + if (err) + goto err_free_mem; + + return 0; + +err_free_mem: + vfree(p); + return err; +} + +static void *execmem_cache_alloc(struct execmem_range *range, size_t size) +{ + void *p; + int err; + + p = __execmem_cache_alloc(range, size); + if (p) + return p; + + err = execmem_cache_populate(range, size); + if (err) + return NULL; + + return __execmem_cache_alloc(range, size); +} + +static bool execmem_cache_free(void *ptr) +{ + struct maple_tree *busy_areas = &execmem_cache.busy_areas; + struct mutex *mutex = &execmem_cache.mutex; + unsigned long addr = (unsigned long)ptr; + MA_STATE(mas, busy_areas, addr, addr); + size_t size; + void *area; + + mutex_lock(mutex); + area = mas_walk(&mas); + if (!area) { + mutex_unlock(mutex); + return false; + } + size = mas_range_len(&mas); + + mas_store_gfp(&mas, NULL, GFP_KERNEL); + mutex_unlock(mutex); + + execmem_fill_trapping_insns(ptr, size, /* writable = */ false); + + execmem_cache_add(ptr, size); + + schedule_work(&execmem_cache_clean_work); + + return true; +} +#else /* CONFIG_ARCH_HAS_EXECMEM_ROX */ +static void *execmem_cache_alloc(struct execmem_range *range, size_t size) +{ + return NULL; +} + +static bool execmem_cache_free(void *ptr) +{ + return false; } +#endif /* CONFIG_ARCH_HAS_EXECMEM_ROX */ void *execmem_alloc(enum execmem_type type, size_t size) { struct execmem_range *range = &execmem_info->ranges[type]; + bool use_cache = range->flags & EXECMEM_ROX_CACHE; + unsigned long vm_flags = VM_FLUSH_RESET_PERMS; + pgprot_t pgprot = range->pgprot; + void *p; - return __execmem_alloc(range, size); + if (use_cache) + p = execmem_cache_alloc(range, size); + else + p = execmem_vmalloc(range, size, pgprot, vm_flags); + + return kasan_reset_tag(p); } void execmem_free(void *ptr) @@ -66,7 +379,19 @@ void execmem_free(void *ptr) * supported by vmalloc. */ WARN_ON(in_interrupt()); - vfree(ptr); + + if (!execmem_cache_free(ptr)) + vfree(ptr); +} + +void *execmem_update_copy(void *dst, const void *src, size_t size) +{ + return text_poke_copy(dst, src, size); +} + +bool execmem_is_rox(enum execmem_type type) +{ + return !!(execmem_info->ranges[type].flags & EXECMEM_ROX_CACHE); } static bool execmem_validate(struct execmem_info *info) @@ -78,6 +403,17 @@ static bool execmem_validate(struct execmem_info *info) return false; } + if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX)) { + for (int i = EXECMEM_DEFAULT; i < EXECMEM_TYPE_MAX; i++) { + r = &info->ranges[i]; + + if (r->flags & EXECMEM_ROX_CACHE) { + pr_warn_once("ROX cache is not supported\n"); + r->flags &= ~EXECMEM_ROX_CACHE; + } + } + } + return true; } diff --git a/mm/filemap.c b/mm/filemap.c index 196779e8e396..7c76a123ba18 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -119,7 +119,6 @@ * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) - * ->memcg->move_lock (folio_remove_rmap_pte->folio_memcg_lock) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) @@ -3260,8 +3259,8 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; - ptep = pte_offset_map_nolock(vma->vm_mm, vmf->pmd, vmf->address, - &vmf->ptl); + ptep = pte_offset_map_ro_nolock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; @@ -922,14 +922,14 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && - !pte_dirty(pte) && !PageDirty(page)) - set_page_dirty(page); + !pte_dirty(pte) && !folio_test_dirty(folio)) + folio_mark_dirty(folio); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use - * mark_page_accessed(). + * folio_mark_accessed(). */ - mark_page_accessed(page); + folio_mark_accessed(folio); } out: pte_unmap_unlock(ptep, ptl); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5734d5d5060f..ee335d96fc39 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -8,7 +8,6 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> #include <linux/hugetlb.h> @@ -84,6 +83,21 @@ unsigned long huge_anon_orders_madvise __read_mostly; unsigned long huge_anon_orders_inherit __read_mostly; static bool anon_orders_configured __initdata; +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + struct inode *inode; + + if (!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) + return false; + + if (!vma->vm_file) + return false; + + inode = file_inode(vma->vm_file); + + return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); +} + unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long vm_flags, unsigned long tva_flags, @@ -601,6 +615,8 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); +DEFINE_MTHP_STAT_ATTR(zswpout, MTHP_STAT_ZSWPOUT); +DEFINE_MTHP_STAT_ATTR(swpin, MTHP_STAT_SWPIN); DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); #ifdef CONFIG_SHMEM @@ -619,6 +635,8 @@ static struct attribute *anon_stats_attrs[] = { &anon_fault_fallback_attr.attr, &anon_fault_fallback_charge_attr.attr, #ifndef CONFIG_SHMEM + &zswpout_attr.attr, + &swpin_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif @@ -649,6 +667,8 @@ static struct attribute_group file_stats_attr_grp = { static struct attribute *any_stats_attrs[] = { #ifdef CONFIG_SHMEM + &zswpout_attr.attr, + &swpin_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, #endif @@ -938,26 +958,6 @@ out: } __setup("transparent_hugepage=", setup_transparent_hugepage); -static inline int get_order_from_str(const char *size_str) -{ - unsigned long size; - char *endptr; - int order; - - size = memparse(size_str, &endptr); - - if (!is_power_of_2(size)) - goto err; - order = get_order(size); - if (BIT(order) & ~THP_ORDERS_ALL_ANON) - goto err; - - return order; -err: - pr_err("invalid size %s in thp_anon boot parameter\n", size_str); - return -EINVAL; -} - static char str_dup[PAGE_SIZE] __initdata; static int __init setup_thp_anon(char *str) { @@ -969,7 +969,7 @@ static int __init setup_thp_anon(char *str) if (!str || strlen(str) + 1 > PAGE_SIZE) goto err; - strcpy(str_dup, str); + strscpy(str_dup, str); always = huge_anon_orders_always; madvise = huge_anon_orders_madvise; @@ -987,10 +987,22 @@ static int __init setup_thp_anon(char *str) start_size = strsep(&subtoken, "-"); end_size = subtoken; - start = get_order_from_str(start_size); - end = get_order_from_str(end_size); + start = get_order_from_str(start_size, THP_ORDERS_ALL_ANON); + end = get_order_from_str(end_size, THP_ORDERS_ALL_ANON); } else { - start = end = get_order_from_str(subtoken); + start_size = end_size = subtoken; + start = end = get_order_from_str(subtoken, + THP_ORDERS_ALL_ANON); + } + + if (start == -EINVAL) { + pr_err("invalid size %s in thp_anon boot parameter\n", start_size); + goto err; + } + + if (end == -EINVAL) { + pr_err("invalid size %s in thp_anon boot parameter\n", end_size); + goto err; } if (start < 0 || end < 0 || start > end) @@ -1137,47 +1149,87 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, } EXPORT_SYMBOL_GPL(thp_get_unmapped_area); -static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, - struct page *page, gfp_t gfp) +static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma, + unsigned long addr) { - struct vm_area_struct *vma = vmf->vma; - struct folio *folio = page_folio(page); - pgtable_t pgtable; - unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - vm_fault_t ret = 0; + gfp_t gfp = vma_thp_gfp_mask(vma); + const int order = HPAGE_PMD_ORDER; + struct folio *folio; - VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + folio = vma_alloc_folio(gfp, order, vma, addr & HPAGE_PMD_MASK); + if (unlikely(!folio)) { + count_vm_event(THP_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + return NULL; + } + + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { folio_put(folio); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); - return VM_FAULT_FALLBACK; + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK); + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); + return NULL; } folio_throttle_swaprate(folio, gfp); - pgtable = pte_alloc_one(vma->vm_mm); - if (unlikely(!pgtable)) { - ret = VM_FAULT_OOM; - goto release; - } - - folio_zero_user(folio, vmf->address); + /* + * When a folio is not zeroed during allocation (__GFP_ZERO not used), + * folio_zero_user() is used to make sure that the page corresponding + * to the faulting address will be hot in the cache after zeroing. + */ + if (!alloc_zeroed()) + folio_zero_user(folio, addr); /* * The memory barrier inside __folio_mark_uptodate makes sure that * folio_zero_user writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); + return folio; +} + +static void map_anon_folio_pmd(struct folio *folio, pmd_t *pmd, + struct vm_area_struct *vma, unsigned long haddr) +{ + pmd_t entry; + + entry = mk_huge_pmd(&folio->page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE); + folio_add_lru_vma(folio, vma); + set_pmd_at(vma->vm_mm, haddr, pmd, entry); + update_mmu_cache_pmd(vma, haddr, pmd); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + count_vm_event(THP_FAULT_ALLOC); + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); +} + +static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf) +{ + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + struct folio *folio; + pgtable_t pgtable; + vm_fault_t ret = 0; + + folio = vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + pgtable = pte_alloc_one(vma->vm_mm); + if (unlikely(!pgtable)) { + ret = VM_FAULT_OOM; + goto release; + } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { goto unlock_release; } else { - pmd_t entry; - ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock_release; @@ -1191,21 +1243,11 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON(ret & VM_FAULT_FALLBACK); return ret; } - - entry = mk_huge_pmd(page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE); - folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); - set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); - update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); - add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); mm_inc_nr_ptes(vma->vm_mm); deferred_split_folio(folio, false); spin_unlock(vmf->ptl); - count_vm_event(THP_FAULT_ALLOC); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); - count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } return 0; @@ -1272,8 +1314,6 @@ static void set_huge_zero_folio(pgtable_t pgtable, struct mm_struct *mm, vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - gfp_t gfp; - struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret; @@ -1324,14 +1364,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } return ret; } - gfp = vma_thp_gfp_mask(vma); - folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true); - if (unlikely(!folio)) { - count_vm_event(THP_FAULT_FALLBACK); - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); - return VM_FAULT_FALLBACK; - } - return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp); + + return __do_huge_pmd_anonymous_page(vmf); } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1763,6 +1797,38 @@ unlock: spin_unlock(vmf->ptl); } +static vm_fault_t do_huge_zero_wp_pmd(struct vm_fault *vmf) +{ + unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + struct vm_area_struct *vma = vmf->vma; + struct mmu_notifier_range range; + struct folio *folio; + vm_fault_t ret = 0; + + folio = vma_alloc_anon_folio_pmd(vma, vmf->address); + if (unlikely(!folio)) + return VM_FAULT_FALLBACK; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, haddr, + haddr + HPAGE_PMD_SIZE); + mmu_notifier_invalidate_range_start(&range); + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) + goto release; + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto release; + (void)pmdp_huge_clear_flush(vma, haddr, vmf->pmd); + map_anon_folio_pmd(folio, vmf->pmd, vma, haddr); + goto unlock; +release: + folio_put(folio); +unlock: + spin_unlock(vmf->ptl); + mmu_notifier_invalidate_range_end(&range); + return ret; +} + vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; @@ -1775,8 +1841,15 @@ 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); - if (is_huge_zero_pmd(orig_pmd)) + if (is_huge_zero_pmd(orig_pmd)) { + vm_fault_t ret = do_huge_zero_wp_pmd(vmf); + + if (!(ret & VM_FAULT_FALLBACK)) + return ret; + + /* Fallback to splitting PMD if THP cannot be allocated */ goto fallback; + } spin_lock(vmf->ptl); @@ -3124,8 +3197,8 @@ static void __split_huge_page_tail(struct folio *folio, int tail, /* ->mapping in first and second tail page is replaced by other uses */ VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, page_tail); - page_tail->mapping = head->mapping; - page_tail->index = head->index + tail; + new_folio->mapping = folio->mapping; + new_folio->index = folio->index + tail; /* * page->private should not be set in tail pages. Fix up and warn once @@ -3201,11 +3274,11 @@ static void __split_huge_page(struct page *page, struct list_head *list, ClearPageHasHWPoisoned(head); for (i = nr - new_nr; i >= new_nr; i -= new_nr) { + struct folio *tail; __split_huge_page_tail(folio, i, lruvec, list, new_order); + tail = page_folio(head + i); /* Some pages can be beyond EOF: drop them from page cache */ - if (head[i].index >= end) { - struct folio *tail = page_folio(head + i); - + if (tail->index >= end) { if (shmem_mapping(folio->mapping)) nr_dropped++; else if (folio_test_clear_dirty(tail)) @@ -3213,12 +3286,12 @@ static void __split_huge_page(struct page *page, struct list_head *list, inode_to_wb(folio->mapping->host)); __filemap_remove_folio(tail, NULL); folio_put(tail); - } else if (!PageAnon(page)) { - __xa_store(&folio->mapping->i_pages, head[i].index, - head + i, 0); + } else if (!folio_test_anon(folio)) { + __xa_store(&folio->mapping->i_pages, tail->index, + tail, 0); } else if (swap_cache) { __xa_store(&swap_cache->i_pages, offset + i, - head + i, 0); + tail, 0); } } @@ -4096,7 +4169,7 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, tok = strsep(&buf, ","); if (tok) { - strcpy(file_path, tok); + strscpy(file_path, tok); } else { ret = -EINVAL; goto out; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 190fa05635f4..ea2ed8e301ef 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1925,6 +1925,7 @@ void free_huge_folio(struct folio *folio) pages_per_huge_page(h), folio); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); + lruvec_stat_mod_folio(folio, NR_HUGETLB, -pages_per_huge_page(h)); mem_cgroup_uncharge(folio); if (restore_reserve) h->resv_huge_pages++; @@ -3093,6 +3094,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, if (!memcg_charge_ret) mem_cgroup_commit_charge(folio, memcg); + lruvec_stat_mod_folio(folio, NR_HUGETLB, pages_per_huge_page(h)); mem_cgroup_put(memcg); return folio; @@ -3301,6 +3303,7 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; char buf[32]; + LIST_HEAD(folio_list); for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { if (hstate_is_gigantic(h)) { @@ -3310,14 +3313,18 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; - folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, - &node_states[N_MEMORY]); + folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, + &node_states[N_MEMORY], NULL); if (!folio) break; - free_huge_folio(folio); /* free it into the hugepage allocator */ + list_add(&folio->lru, &folio_list); } cond_resched(); } + + if (!list_empty(&folio_list)) + prep_and_add_allocated_folios(h, &folio_list); + if (i == h->max_huge_pages_node[nid]) return; @@ -6348,6 +6355,10 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; + } else if (WARN_ON_ONCE(marker & PTE_MARKER_GUARD)) { + /* This isn't supported in hugetlb. */ + ret = VM_FAULT_SIGSEGV; + goto out_mutex; } } diff --git a/mm/internal.h b/mm/internal.h index 64c2eb0b160e..5a7302baeed7 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/pagemap.h> +#include <linux/pagewalk.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -841,7 +842,7 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) } /* mm/util.c */ -struct anon_vma *folio_anon_vma(struct folio *folio); +struct anon_vma *folio_anon_vma(const struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); @@ -959,7 +960,7 @@ extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ -static inline unsigned long vma_address(struct vm_area_struct *vma, +static inline unsigned long vma_address(const struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; @@ -1117,10 +1118,11 @@ void ClearPageHWPoisonTakenOff(struct page *page); bool take_page_off_buddy(struct page *page); bool put_page_back_buddy(struct page *page); struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); -void add_to_kill_ksm(struct task_struct *tsk, struct page *p, +void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long ksm_addr); -unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); +unsigned long page_mapped_in_vma(const struct page *page, + struct vm_area_struct *vma); #else static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu) @@ -1234,6 +1236,7 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); +unsigned int get_vm_area_page_order(struct vm_struct *vm); #else static inline void vmalloc_init(void) { @@ -1262,6 +1265,12 @@ int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_folio(struct folio *folio); +struct vm_struct *__get_vm_area_node(unsigned long size, + unsigned long align, unsigned long shift, + unsigned long flags, unsigned long start, + unsigned long end, int node, gfp_t gfp_mask, + const void *caller); + /* * mm/gup.c */ @@ -1276,6 +1285,34 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr, void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); +static inline bool alloc_zeroed(void) +{ + return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, + &init_on_alloc); +} + +/* + * Parses a string with mem suffixes into its order. Useful to parse kernel + * parameters. + */ +static inline int get_order_from_str(const char *size_str, + unsigned long valid_orders) +{ + unsigned long size; + char *endptr; + int order; + + size = memparse(size_str, &endptr); + + if (!is_power_of_2(size)) + return -EINVAL; + order = get_order(size); + if (BIT(order) & ~valid_orders) + return -EINVAL; + + return order; +} + enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, @@ -1356,7 +1393,7 @@ static inline bool gup_must_unshare(struct vm_area_struct *vma, smp_rmb(); /* - * Note that PageKsm() pages cannot be exclusive, and consequently, + * Note that KSM pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); @@ -1488,4 +1525,9 @@ static inline void accept_page(struct page *page) } #endif /* CONFIG_UNACCEPTED_MEMORY */ +/* pagewalk.c */ +int walk_page_range_mm(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private); + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index b88543e5c0cc..1a958e7c8a46 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -46,7 +46,6 @@ endif CFLAGS_kasan_test_c.o := $(CFLAGS_KASAN_TEST) RUSTFLAGS_kasan_test_rust.o := $(RUSTFLAGS_KASAN) -CFLAGS_kasan_test_module.o := $(CFLAGS_KASAN_TEST) obj-y := common.o report.o obj-$(CONFIG_KASAN_GENERIC) += init.o generic.o report_generic.o shadow.o quarantine.o @@ -59,4 +58,3 @@ ifdef CONFIG_RUST endif obj-$(CONFIG_KASAN_KUNIT_TEST) += kasan_test.o -obj-$(CONFIG_KASAN_MODULE_TEST) += kasan_test_module.o diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index 9958ebc15d38..ccd66c7a4081 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -8,6 +8,7 @@ #define pr_fmt(fmt) "kasan: " fmt +#include <kunit/visibility.h> #include <linux/init.h> #include <linux/kasan.h> #include <linux/kernel.h> @@ -394,12 +395,12 @@ void kasan_enable_hw_tags(void) #if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) -EXPORT_SYMBOL_GPL(kasan_enable_hw_tags); +EXPORT_SYMBOL_IF_KUNIT(kasan_enable_hw_tags); -void kasan_force_async_fault(void) +VISIBLE_IF_KUNIT void kasan_force_async_fault(void) { hw_force_async_tag_fault(); } -EXPORT_SYMBOL_GPL(kasan_force_async_fault); +EXPORT_SYMBOL_IF_KUNIT(kasan_force_async_fault); #endif diff --git a/mm/kasan/init.c b/mm/kasan/init.c index ac607c306292..ced6b29fcf76 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -106,10 +106,6 @@ static void __ref zero_pte_populate(pmd_t *pmd, unsigned long addr, } } -void __weak __meminit kernel_pte_init(void *addr) -{ -} - static int __ref zero_pmd_populate(pud_t *pud, unsigned long addr, unsigned long end) { @@ -145,10 +141,6 @@ static int __ref zero_pmd_populate(pud_t *pud, unsigned long addr, return 0; } -void __weak __meminit pmd_init(void *addr) -{ -} - static int __ref zero_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end) { @@ -187,10 +179,6 @@ static int __ref zero_pud_populate(p4d_t *p4d, unsigned long addr, return 0; } -void __weak __meminit pud_init(void *addr) -{ -} - static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, unsigned long end) { diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index f438a6cdc964..b7e4b81421b3 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -568,7 +568,7 @@ static inline void kasan_kunit_test_suite_end(void) { } #endif /* CONFIG_KASAN_KUNIT_TEST */ -#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) || IS_ENABLED(CONFIG_KASAN_MODULE_TEST) +#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) bool kasan_save_enable_multi_shot(void); void kasan_restore_multi_shot(bool enabled); diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index d8fb281e439d..e0ec5a6d15be 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -33,6 +33,8 @@ #define OOB_TAG_OFF (IS_ENABLED(CONFIG_KASAN_GENERIC) ? 0 : KASAN_GRANULE_SIZE) +MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING); + static bool multishot; /* Fields set based on lines observed in the console. */ @@ -213,6 +215,36 @@ static void kmalloc_node_oob_right(struct kunit *test) kfree(ptr); } +static void kmalloc_track_caller_oob_right(struct kunit *test) +{ + char *ptr; + size_t size = 128 - KASAN_GRANULE_SIZE; + + /* + * Check that KASAN detects out-of-bounds access for object allocated via + * kmalloc_track_caller(). + */ + ptr = kmalloc_track_caller(size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + + OPTIMIZER_HIDE_VAR(ptr); + KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 'y'); + + kfree(ptr); + + /* + * Check that KASAN detects out-of-bounds access for object allocated via + * kmalloc_node_track_caller(). + */ + ptr = kmalloc_node_track_caller(size, GFP_KERNEL, 0); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + + OPTIMIZER_HIDE_VAR(ptr); + KUNIT_EXPECT_KASAN_FAIL(test, ptr[size] = 'y'); + + kfree(ptr); +} + /* * Check that KASAN detects an out-of-bounds access for a big object allocated * via kmalloc(). But not as big as to trigger the page_alloc fallback. @@ -1928,10 +1960,92 @@ static void rust_uaf(struct kunit *test) KUNIT_EXPECT_KASAN_FAIL(test, kasan_test_rust_uaf()); } +static void copy_to_kernel_nofault_oob(struct kunit *test) +{ + char *ptr; + char buf[128]; + size_t size = sizeof(buf); + + /* + * This test currently fails with the HW_TAGS mode. The reason is + * unknown and needs to be investigated. + */ + KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_KASAN_HW_TAGS); + + ptr = kmalloc(size - KASAN_GRANULE_SIZE, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); + + /* + * We test copy_to_kernel_nofault() to detect corrupted memory that is + * being written into the kernel. In contrast, + * copy_from_kernel_nofault() is primarily used in kernel helper + * functions where the source address might be random or uninitialized. + * Applying KASAN instrumentation to copy_from_kernel_nofault() could + * lead to false positives. By focusing KASAN checks only on + * copy_to_kernel_nofault(), we ensure that only valid memory is + * written to the kernel, minimizing the risk of kernel corruption + * while avoiding false positives in the reverse case. + */ + KUNIT_EXPECT_KASAN_FAIL(test, + copy_to_kernel_nofault(&buf[0], ptr, size)); + KUNIT_EXPECT_KASAN_FAIL(test, + copy_to_kernel_nofault(ptr, &buf[0], size)); + + kfree(ptr); +} + +static void copy_user_test_oob(struct kunit *test) +{ + char *kmem; + char __user *usermem; + unsigned long useraddr; + size_t size = 128 - KASAN_GRANULE_SIZE; + int __maybe_unused unused; + + kmem = kunit_kmalloc(test, size, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, kmem); + + useraddr = kunit_vm_mmap(test, NULL, 0, PAGE_SIZE, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANONYMOUS | MAP_PRIVATE, 0); + KUNIT_ASSERT_NE_MSG(test, useraddr, 0, + "Could not create userspace mm"); + KUNIT_ASSERT_LT_MSG(test, useraddr, (unsigned long)TASK_SIZE, + "Failed to allocate user memory"); + + OPTIMIZER_HIDE_VAR(size); + usermem = (char __user *)useraddr; + + KUNIT_EXPECT_KASAN_FAIL(test, + unused = copy_from_user(kmem, usermem, size + 1)); + KUNIT_EXPECT_KASAN_FAIL(test, + unused = copy_to_user(usermem, kmem, size + 1)); + KUNIT_EXPECT_KASAN_FAIL(test, + unused = __copy_from_user(kmem, usermem, size + 1)); + KUNIT_EXPECT_KASAN_FAIL(test, + unused = __copy_to_user(usermem, kmem, size + 1)); + KUNIT_EXPECT_KASAN_FAIL(test, + unused = __copy_from_user_inatomic(kmem, usermem, size + 1)); + KUNIT_EXPECT_KASAN_FAIL(test, + unused = __copy_to_user_inatomic(usermem, kmem, size + 1)); + + /* + * Prepare a long string in usermem to avoid the strncpy_from_user test + * bailing out on '\0' before it reaches out-of-bounds. + */ + memset(kmem, 'a', size); + KUNIT_EXPECT_EQ(test, copy_to_user(usermem, kmem, size), 0); + + KUNIT_EXPECT_KASAN_FAIL(test, + unused = strncpy_from_user(kmem, usermem, size + 1)); +} + static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kmalloc_oob_right), KUNIT_CASE(kmalloc_oob_left), KUNIT_CASE(kmalloc_node_oob_right), + KUNIT_CASE(kmalloc_track_caller_oob_right), KUNIT_CASE(kmalloc_big_oob_right), KUNIT_CASE(kmalloc_large_oob_right), KUNIT_CASE(kmalloc_large_uaf), @@ -1992,7 +2106,7 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(kasan_strings), KUNIT_CASE(kasan_bitops_generic), KUNIT_CASE(kasan_bitops_tags), - KUNIT_CASE(kasan_atomics), + KUNIT_CASE_SLOW(kasan_atomics), KUNIT_CASE(vmalloc_helpers_tags), KUNIT_CASE(vmalloc_oob), KUNIT_CASE(vmap_tags), @@ -2000,7 +2114,9 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(match_all_not_assigned), KUNIT_CASE(match_all_ptr_tag), KUNIT_CASE(match_all_mem_tag), + KUNIT_CASE(copy_to_kernel_nofault_oob), KUNIT_CASE(rust_uaf), + KUNIT_CASE(copy_user_test_oob), {} }; diff --git a/mm/kasan/kasan_test_module.c b/mm/kasan/kasan_test_module.c deleted file mode 100644 index 27ec22767e42..000000000000 --- a/mm/kasan/kasan_test_module.c +++ /dev/null @@ -1,81 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * - * Copyright (c) 2014 Samsung Electronics Co., Ltd. - * Author: Andrey Ryabinin <a.ryabinin@samsung.com> - */ - -#define pr_fmt(fmt) "kasan: test: " fmt - -#include <linux/mman.h> -#include <linux/module.h> -#include <linux/printk.h> -#include <linux/slab.h> -#include <linux/uaccess.h> - -#include "kasan.h" - -static noinline void __init copy_user_test(void) -{ - char *kmem; - char __user *usermem; - size_t size = 128 - KASAN_GRANULE_SIZE; - int __maybe_unused unused; - - kmem = kmalloc(size, GFP_KERNEL); - if (!kmem) - return; - - usermem = (char __user *)vm_mmap(NULL, 0, PAGE_SIZE, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_ANONYMOUS | MAP_PRIVATE, 0); - if (IS_ERR(usermem)) { - pr_err("Failed to allocate user memory\n"); - kfree(kmem); - return; - } - - OPTIMIZER_HIDE_VAR(size); - - pr_info("out-of-bounds in copy_from_user()\n"); - unused = copy_from_user(kmem, usermem, size + 1); - - pr_info("out-of-bounds in copy_to_user()\n"); - unused = copy_to_user(usermem, kmem, size + 1); - - pr_info("out-of-bounds in __copy_from_user()\n"); - unused = __copy_from_user(kmem, usermem, size + 1); - - pr_info("out-of-bounds in __copy_to_user()\n"); - unused = __copy_to_user(usermem, kmem, size + 1); - - pr_info("out-of-bounds in __copy_from_user_inatomic()\n"); - unused = __copy_from_user_inatomic(kmem, usermem, size + 1); - - pr_info("out-of-bounds in __copy_to_user_inatomic()\n"); - unused = __copy_to_user_inatomic(usermem, kmem, size + 1); - - pr_info("out-of-bounds in strncpy_from_user()\n"); - unused = strncpy_from_user(kmem, usermem, size + 1); - - vm_munmap((unsigned long)usermem, PAGE_SIZE); - kfree(kmem); -} - -static int __init kasan_test_module_init(void) -{ - /* - * Temporarily enable multi-shot mode. Otherwise, KASAN would only - * report the first detected bug and panic the kernel if panic_on_warn - * is enabled. - */ - bool multishot = kasan_save_enable_multi_shot(); - - copy_user_test(); - - kasan_restore_multi_shot(multishot); - return -EAGAIN; -} - -module_init(kasan_test_module_init); -MODULE_LICENSE("GPL"); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index b48c768acc84..50fb19ad4388 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -10,6 +10,7 @@ */ #include <kunit/test.h> +#include <kunit/visibility.h> #include <linux/bitops.h> #include <linux/ftrace.h> #include <linux/init.h> @@ -132,20 +133,20 @@ static bool report_enabled(void) return !test_and_set_bit(KASAN_BIT_REPORTED, &kasan_flags); } -#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) || IS_ENABLED(CONFIG_KASAN_MODULE_TEST) +#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) -bool kasan_save_enable_multi_shot(void) +VISIBLE_IF_KUNIT bool kasan_save_enable_multi_shot(void) { return test_and_set_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); } -EXPORT_SYMBOL_GPL(kasan_save_enable_multi_shot); +EXPORT_SYMBOL_IF_KUNIT(kasan_save_enable_multi_shot); -void kasan_restore_multi_shot(bool enabled) +VISIBLE_IF_KUNIT void kasan_restore_multi_shot(bool enabled) { if (!enabled) clear_bit(KASAN_BIT_MULTI_SHOT, &kasan_flags); } -EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); +EXPORT_SYMBOL_IF_KUNIT(kasan_restore_multi_shot); #endif @@ -157,17 +158,17 @@ EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); */ static bool kasan_kunit_executing; -void kasan_kunit_test_suite_start(void) +VISIBLE_IF_KUNIT void kasan_kunit_test_suite_start(void) { WRITE_ONCE(kasan_kunit_executing, true); } -EXPORT_SYMBOL_GPL(kasan_kunit_test_suite_start); +EXPORT_SYMBOL_IF_KUNIT(kasan_kunit_test_suite_start); -void kasan_kunit_test_suite_end(void) +VISIBLE_IF_KUNIT void kasan_kunit_test_suite_end(void) { WRITE_ONCE(kasan_kunit_executing, false); } -EXPORT_SYMBOL_GPL(kasan_kunit_test_suite_end); +EXPORT_SYMBOL_IF_KUNIT(kasan_kunit_test_suite_end); static bool kasan_kunit_test_suite_executing(void) { diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index d6210ca48dda..88d1c9dcb507 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -489,7 +489,8 @@ static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr, */ void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) + unsigned long free_region_end, + unsigned long flags) { void *shadow_start, *shadow_end; unsigned long region_start, region_end; @@ -522,12 +523,17 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, __memset(shadow_start, KASAN_SHADOW_INIT, shadow_end - shadow_start); return; } - apply_to_existing_page_range(&init_mm, + + + if (flags & KASAN_VMALLOC_PAGE_RANGE) + apply_to_existing_page_range(&init_mm, (unsigned long)shadow_start, size, kasan_depopulate_vmalloc_pte, NULL); - flush_tlb_kernel_range((unsigned long)shadow_start, - (unsigned long)shadow_end); + + if (flags & KASAN_VMALLOC_TLB_FLUSH) + flush_tlb_kernel_range((unsigned long)shadow_start, + (unsigned long)shadow_end); } } diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index 00fd17285285..f65fb182466d 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -383,6 +383,22 @@ static void test_use_after_free_read(struct kunit *test) KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } +static void test_use_after_free_read_nofault(struct kunit *test) +{ + const size_t size = 32; + char *addr; + char dst; + int ret; + + setup_test_cache(test, size, 0, NULL); + addr = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); + test_free(addr); + /* Use after free with *_nofault() */ + ret = copy_from_kernel_nofault(&dst, addr, 1); + KUNIT_EXPECT_EQ(test, ret, -EFAULT); + KUNIT_EXPECT_FALSE(test, report_available()); +} + static void test_double_free(struct kunit *test) { const size_t size = 32; @@ -780,6 +796,7 @@ static struct kunit_case kfence_test_cases[] = { KFENCE_KUNIT_CASE(test_out_of_bounds_read), KFENCE_KUNIT_CASE(test_out_of_bounds_write), KFENCE_KUNIT_CASE(test_use_after_free_read), + KFENCE_KUNIT_CASE(test_use_after_free_read_nofault), KFENCE_KUNIT_CASE(test_double_free), KFENCE_KUNIT_CASE(test_invalid_addr_free), KFENCE_KUNIT_CASE(test_corruption), diff --git a/mm/khugepaged.c b/mm/khugepaged.c index b538c3d48386..6f8d46d107b4 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -4,7 +4,6 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> @@ -416,9 +415,11 @@ static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) static bool hugepage_pmd_enabled(void) { /* - * We cover both the anon and the file-backed case here; file-backed + * We cover the anon, shmem and the file-backed case here; file-backed * hugepages, when configured in, are determined by the global control. * Anon pmd-sized hugepages are determined by the pmd-size control. + * Shmem pmd-sized hugepages are also determined by its pmd-size control, + * except when the global shmem_huge is set to SHMEM_HUGE_DENY. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && hugepage_global_enabled()) @@ -430,6 +431,8 @@ static bool hugepage_pmd_enabled(void) if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) && hugepage_global_enabled()) return true; + if (IS_ENABLED(CONFIG_SHMEM) && shmem_hpage_pmd_enabled()) + return true; return false; } @@ -1011,7 +1014,11 @@ static int __collapse_huge_page_swapin(struct mm_struct *mm, }; if (!pte++) { - pte = pte_offset_map_nolock(mm, pmd, address, &ptl); + /* + * Here the ptl is only used to check pte_same() in + * do_swap_page(), so readonly version is enough. + */ + pte = pte_offset_map_ro_nolock(mm, pmd, address, &ptl); if (!pte) { mmap_read_unlock(mm); result = SCAN_PMD_NULL; @@ -1601,7 +1608,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) pml = pmd_lock(mm, pmd); - start_pte = pte_offset_map_nolock(mm, pmd, haddr, &ptl); + start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto abort; if (!pml) @@ -1609,6 +1616,9 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, else if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); + if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) + goto abort; + /* step 2: clear page table and adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { @@ -1641,7 +1651,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, nr_ptes++; } - pte_unmap(start_pte); if (!pml) spin_unlock(ptl); @@ -1654,14 +1663,19 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, /* step 4: remove empty page table */ if (!pml) { pml = pmd_lock(mm, pmd); - if (ptl != pml) + if (ptl != pml) { spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); + if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) { + flush_tlb_mm(mm); + goto unlock; + } + } } pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd); pmdp_get_lockless_sync(); + pte_unmap_unlock(start_pte, ptl); if (ptl != pml) - spin_unlock(ptl); - spin_unlock(pml); + spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); @@ -1681,6 +1695,7 @@ abort: folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } +unlock: if (start_pte) pte_unmap_unlock(start_pte, ptl); if (pml && pml != ptl) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 0400f5e8ac60..2a945c07ae99 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -935,6 +935,28 @@ static void make_black_object(unsigned long ptr, unsigned int objflags) } /* + * Reset the checksum of an object. The immediate effect is that it will not + * be reported as a leak during the next scan until its checksum is updated. + */ +static void reset_checksum(unsigned long ptr) +{ + unsigned long flags; + struct kmemleak_object *object; + + object = find_and_get_object(ptr, 0); + if (!object) { + kmemleak_warn("Not resetting the checksum of an unknown object at 0x%08lx\n", + ptr); + return; + } + + raw_spin_lock_irqsave(&object->lock, flags); + object->checksum = 0; + raw_spin_unlock_irqrestore(&object->lock, flags); + put_object(object); +} + +/* * Add a scanning area to the object. If at least one such area is added, * kmemleak will only scan these ranges rather than the whole memory block. */ @@ -1011,7 +1033,7 @@ static void object_set_excess_ref(unsigned long ptr, unsigned long excess_ref) } /* - * Set the OBJECT_NO_SCAN flag for the object corresponding to the give + * Set the OBJECT_NO_SCAN flag for the object corresponding to the given * pointer. Such object will not be scanned by kmemleak but references to it * are searched. */ @@ -1203,6 +1225,23 @@ void __ref kmemleak_not_leak(const void *ptr) EXPORT_SYMBOL(kmemleak_not_leak); /** + * kmemleak_transient_leak - mark an allocated object as transient false positive + * @ptr: pointer to beginning of the object + * + * Calling this function on an object will cause the memory block to not be + * reported as a leak temporarily. This may happen, for example, if the object + * is part of a singly linked list and the ->next reference to it is changed. + */ +void __ref kmemleak_transient_leak(const void *ptr) +{ + pr_debug("%s(0x%px)\n", __func__, ptr); + + if (kmemleak_enabled && ptr && !IS_ERR(ptr)) + reset_checksum((unsigned long)ptr); +} +EXPORT_SYMBOL(kmemleak_transient_leak); + +/** * kmemleak_ignore - ignore an allocated object * @ptr: pointer to beginning of the object * diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c index 13236d579eba..9733a22c46c1 100644 --- a/mm/kmsan/kmsan_test.c +++ b/mm/kmsan/kmsan_test.c @@ -640,6 +640,22 @@ static void test_unpoison_memory(struct kunit *test) KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } +static void test_copy_from_kernel_nofault(struct kunit *test) +{ + long ret; + char buf[4], src[4]; + size_t size = sizeof(buf); + + EXPECTATION_UNINIT_VALUE_FN(expect, "copy_from_kernel_nofault"); + kunit_info( + test, + "testing copy_from_kernel_nofault with uninitialized memory\n"); + + ret = copy_from_kernel_nofault((char *)&buf[0], (char *)&src[0], size); + USE(ret); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + static struct kunit_case kmsan_test_cases[] = { KUNIT_CASE(test_uninit_kmalloc), KUNIT_CASE(test_init_kmalloc), @@ -664,6 +680,7 @@ static struct kunit_case kmsan_test_cases[] = { KUNIT_CASE(test_long_origin_chain), KUNIT_CASE(test_stackdepot_roundtrip), KUNIT_CASE(test_unpoison_memory), + KUNIT_CASE(test_copy_from_kernel_nofault), {}, }; @@ -20,7 +20,6 @@ #include <linux/mman.h> #include <linux/sched.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> #include <linux/sched/cputime.h> #include <linux/rwsem.h> #include <linux/pagemap.h> @@ -657,7 +656,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_v * * VM_FAULT_SIGBUS could occur if we race with truncation of the * backing file, which also invalidates anonymous pages: that's - * okay, that truncation will have unmapped the PageKsm for us. + * okay, that truncation will have unmapped the KSM page for us. * * VM_FAULT_OOM: at the time of writing (late July 2009), setting * aside mem_cgroup limits, VM_FAULT_OOM would only be set if the @@ -1052,7 +1051,8 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma, return err; } -static inline struct ksm_stable_node *folio_stable_node(struct folio *folio) +static inline +struct ksm_stable_node *folio_stable_node(const struct folio *folio) { return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL; } @@ -1257,7 +1257,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct folio *folio, if (WARN_ON_ONCE(folio_test_large(folio))) return err; - pvmw.address = page_address_in_vma(&folio->page, vma); + pvmw.address = page_address_in_vma(folio, folio_page(folio, 0), vma); if (pvmw.address == -EFAULT) goto out; @@ -1341,7 +1341,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, { struct folio *kfolio = page_folio(kpage); struct mm_struct *mm = vma->vm_mm; - struct folio *folio; + struct folio *folio = page_folio(page); pmd_t *pmd; pmd_t pmde; pte_t *ptep; @@ -1351,7 +1351,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, int err = -EFAULT; struct mmu_notifier_range range; - addr = page_address_in_vma(page, vma); + addr = page_address_in_vma(folio, page, vma); if (addr == -EFAULT) goto out; @@ -1417,7 +1417,6 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, ptep_clear_flush(vma, addr, ptep); set_pte_at(mm, addr, ptep, newpte); - folio = page_folio(page); folio_remove_rmap_pte(folio, page, vma); if (!folio_mapped(folio)) folio_free_swap(folio); @@ -1435,7 +1434,7 @@ out: * try_to_merge_one_page - take two pages and merge them into one * @vma: the vma that holds the pte pointing to page * @page: the PageAnon page that we want to replace with kpage - * @kpage: the PageKsm page that we want to map instead of page, + * @kpage: the KSM page that we want to map instead of page, * or NULL the first time when we want to use page as kpage. * * This function returns 0 if the pages were merged, -EFAULT otherwise. @@ -1443,28 +1442,29 @@ out: static int try_to_merge_one_page(struct vm_area_struct *vma, struct page *page, struct page *kpage) { + struct folio *folio = page_folio(page); pte_t orig_pte = __pte(0); int err = -EFAULT; if (page == kpage) /* ksm page forked */ return 0; - if (!PageAnon(page)) + if (!folio_test_anon(folio)) goto out; /* * We need the folio lock to read a stable swapcache flag in - * write_protect_page(). We use trylock_page() instead of - * lock_page() because we don't want to wait here - we - * prefer to continue scanning and merging different pages, - * then come back to this page when it is unlocked. + * write_protect_page(). We trylock because we don't want to wait + * here - we prefer to continue scanning and merging different + * pages, then come back to this page when it is unlocked. */ - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto out; - if (PageTransCompound(page)) { + if (folio_test_large(folio)) { if (split_huge_page(page)) goto out_unlock; + folio = page_folio(page); } /* @@ -1473,28 +1473,28 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, * ptes are necessarily already write-protected. But in either * case, we need to lock and check page_count is not raised. */ - if (write_protect_page(vma, page_folio(page), &orig_pte) == 0) { + if (write_protect_page(vma, folio, &orig_pte) == 0) { if (!kpage) { /* - * While we hold page lock, upgrade page from - * PageAnon+anon_vma to PageKsm+NULL stable_node: + * While we hold folio lock, upgrade folio from + * anon to a NULL stable_node with the KSM flag set: * stable_tree_insert() will update stable_node. */ - folio_set_stable_node(page_folio(page), NULL); - mark_page_accessed(page); + folio_set_stable_node(folio, NULL); + folio_mark_accessed(folio); /* - * Page reclaim just frees a clean page with no dirty + * Page reclaim just frees a clean folio with no dirty * ptes: make sure that the ksm page would be swapped. */ - if (!PageDirty(page)) - SetPageDirty(page); + if (!folio_test_dirty(folio)) + folio_mark_dirty(folio); err = 0; } else if (pages_identical(page, kpage)) err = replace_page(vma, page, kpage, orig_pte); } out_unlock: - unlock_page(page); + folio_unlock(folio); out: return err; } @@ -1582,7 +1582,7 @@ out: * Note that this function upgrades page to ksm page: if one of the pages * is already a ksm page, try_to_merge_with_ksm_page should be used. */ -static struct page *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, +static struct folio *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, struct page *page, struct ksm_rmap_item *tree_rmap_item, struct page *tree_page) @@ -1600,7 +1600,7 @@ static struct page *try_to_merge_two_pages(struct ksm_rmap_item *rmap_item, if (err) break_cow(rmap_item); } - return err ? NULL : page; + return err ? NULL : page_folio(page); } static __always_inline @@ -1787,9 +1787,9 @@ static __always_inline struct folio *chain(struct ksm_stable_node **s_n_d, * with identical content to the page that we are scanning right now. * * This function returns the stable tree node of identical content if found, - * NULL otherwise. + * -EBUSY if the stable node's page is being migrated, NULL otherwise. */ -static struct page *stable_tree_search(struct page *page) +static struct folio *stable_tree_search(struct page *page) { int nid; struct rb_root *root; @@ -1804,7 +1804,7 @@ static struct page *stable_tree_search(struct page *page) if (page_node && page_node->head != &migrate_nodes) { /* ksm page forked */ folio_get(folio); - return &folio->page; + return folio; } nid = get_kpfn_nid(folio_pfn(folio)); @@ -1899,7 +1899,7 @@ again: folio_put(tree_folio); goto replace; } - return &tree_folio->page; + return tree_folio; } } @@ -1913,7 +1913,7 @@ again: out: if (is_page_sharing_candidate(page_node)) { folio_get(folio); - return &folio->page; + return folio; } else return NULL; @@ -1963,7 +1963,7 @@ replace: } stable_node_dup->head = &migrate_nodes; list_add(&stable_node_dup->list, stable_node_dup->head); - return &folio->page; + return folio; chain_append: /* @@ -2217,7 +2217,7 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite struct ksm_rmap_item *tree_rmap_item; struct page *tree_page = NULL; struct ksm_stable_node *stable_node; - struct page *kpage; + struct folio *kfolio; unsigned int checksum; int err; bool max_page_sharing_bypass = false; @@ -2259,31 +2259,31 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite return; } - /* We first start with searching the page inside the stable tree */ - kpage = stable_tree_search(page); - if (kpage == page && rmap_item->head == stable_node) { - put_page(kpage); + /* Start by searching for the folio in the stable tree */ + kfolio = stable_tree_search(page); + if (&kfolio->page == page && rmap_item->head == stable_node) { + folio_put(kfolio); return; } remove_rmap_item_from_tree(rmap_item); - if (kpage) { - if (PTR_ERR(kpage) == -EBUSY) + if (kfolio) { + if (kfolio == ERR_PTR(-EBUSY)) return; - err = try_to_merge_with_ksm_page(rmap_item, page, kpage); + err = try_to_merge_with_ksm_page(rmap_item, page, &kfolio->page); if (!err) { /* * The page was successfully merged: * add its rmap_item to the stable tree. */ - lock_page(kpage); - stable_tree_append(rmap_item, page_stable_node(kpage), + folio_lock(kfolio); + stable_tree_append(rmap_item, folio_stable_node(kfolio), max_page_sharing_bypass); - unlock_page(kpage); + folio_unlock(kfolio); } - put_page(kpage); + folio_put(kfolio); return; } @@ -2292,7 +2292,7 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite if (tree_rmap_item) { bool split; - kpage = try_to_merge_two_pages(rmap_item, page, + kfolio = try_to_merge_two_pages(rmap_item, page, tree_rmap_item, tree_page); /* * If both pages we tried to merge belong to the same compound @@ -2307,20 +2307,20 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite split = PageTransCompound(page) && compound_head(page) == compound_head(tree_page); put_page(tree_page); - if (kpage) { + if (kfolio) { /* * The pages were successfully merged: insert new * node in the stable tree and add both rmap_items. */ - lock_page(kpage); - stable_node = stable_tree_insert(page_folio(kpage)); + folio_lock(kfolio); + stable_node = stable_tree_insert(kfolio); if (stable_node) { stable_tree_append(tree_rmap_item, stable_node, false); stable_tree_append(rmap_item, stable_node, false); } - unlock_page(kpage); + folio_unlock(kfolio); /* * If we fail to insert the page into the stable tree, @@ -2401,10 +2401,10 @@ static unsigned int skip_age(rmap_age_t age) /* * Determines if a page should be skipped for the current scan. * - * @page: page to check + * @folio: folio containing the page to check * @rmap_item: associated rmap_item of page */ -static bool should_skip_rmap_item(struct page *page, +static bool should_skip_rmap_item(struct folio *folio, struct ksm_rmap_item *rmap_item) { rmap_age_t age; @@ -2417,7 +2417,7 @@ static bool should_skip_rmap_item(struct page *page, * will essentially ignore them, but we still have to process them * properly. */ - if (PageKsm(page)) + if (folio_test_ksm(folio)) return false; age = rmap_item->age; @@ -2560,7 +2560,7 @@ next_mm: ksm_scan.rmap_list = &rmap_item->rmap_list; - if (should_skip_rmap_item(tmp_page, rmap_item)) { + if (should_skip_rmap_item(folio, rmap_item)) { folio_put(folio); goto next_page; } @@ -2970,7 +2970,7 @@ struct folio *ksm_might_need_to_copy(struct folio *folio, if (!folio_test_uptodate(folio)) return folio; /* let do_swap_page report the error */ - new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr, false); + new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); if (new_folio && mem_cgroup_charge(new_folio, vma->vm_mm, GFP_KERNEL)) { folio_put(new_folio); @@ -3067,7 +3067,7 @@ again: /* * Collect processes when the error hit an ksm page. */ -void collect_procs_ksm(struct folio *folio, struct page *page, +void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early) { struct ksm_stable_node *stable_node; diff --git a/mm/list_lru.c b/mm/list_lru.c index 9b7ff06e9d32..f93ada6a207b 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -59,6 +59,53 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) } return &lru->node[nid].lru; } + +static inline struct list_lru_one * +lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, + bool irq, bool skip_empty) +{ + struct list_lru_one *l; + long nr_items; + + rcu_read_lock(); +again: + l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); + if (likely(l)) { + if (irq) + spin_lock_irq(&l->lock); + else + spin_lock(&l->lock); + nr_items = READ_ONCE(l->nr_items); + if (likely(nr_items != LONG_MIN)) { + WARN_ON(nr_items < 0); + rcu_read_unlock(); + return l; + } + if (irq) + spin_unlock_irq(&l->lock); + else + spin_unlock(&l->lock); + } + /* + * Caller may simply bail out if raced with reparenting or + * may iterate through the list_lru and expect empty slots. + */ + if (skip_empty) { + rcu_read_unlock(); + return NULL; + } + VM_WARN_ON(!css_is_dying(&memcg->css)); + memcg = parent_mem_cgroup(memcg); + goto again; +} + +static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) +{ + if (irq_off) + spin_unlock_irq(&l->lock); + else + spin_unlock(&l->lock); +} #else static void list_lru_register(struct list_lru *lru) { @@ -83,30 +130,52 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { return &lru->node[nid].lru; } + +static inline struct list_lru_one * +lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, + bool irq, bool skip_empty) +{ + struct list_lru_one *l = &lru->node[nid].lru; + + if (irq) + spin_lock_irq(&l->lock); + else + spin_lock(&l->lock); + + return l; +} + +static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) +{ + if (irq_off) + spin_unlock_irq(&l->lock); + else + spin_unlock(&l->lock); +} #endif /* CONFIG_MEMCG */ /* The caller must ensure the memcg lifetime. */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, - struct mem_cgroup *memcg) + struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; - spin_lock(&nlru->lock); + l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); + if (!l) + return false; if (list_empty(item)) { - l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); - nlru->nr_items++; - spin_unlock(&nlru->lock); + unlock_list_lru(l, false); + atomic_long_inc(&nlru->nr_items); return true; } - spin_unlock(&nlru->lock); + unlock_list_lru(l, false); return false; } -EXPORT_SYMBOL_GPL(list_lru_add); bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { @@ -127,24 +196,23 @@ EXPORT_SYMBOL_GPL(list_lru_add_obj); /* The caller must ensure the memcg lifetime. */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, - struct mem_cgroup *memcg) + struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; - - spin_lock(&nlru->lock); + l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); + if (!l) + return false; if (!list_empty(item)) { - l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); list_del_init(item); l->nr_items--; - nlru->nr_items--; - spin_unlock(&nlru->lock); + unlock_list_lru(l, false); + atomic_long_dec(&nlru->nr_items); return true; } - spin_unlock(&nlru->lock); + unlock_list_lru(l, false); return false; } -EXPORT_SYMBOL_GPL(list_lru_del); bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) { @@ -201,25 +269,24 @@ unsigned long list_lru_count_node(struct list_lru *lru, int nid) struct list_lru_node *nlru; nlru = &lru->node[nid]; - return nlru->nr_items; + return atomic_long_read(&nlru->nr_items); } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long -__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx, +__list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, - unsigned long *nr_to_walk) + unsigned long *nr_to_walk, bool irq_off) { struct list_lru_node *nlru = &lru->node[nid]; - struct list_lru_one *l; + struct list_lru_one *l = NULL; struct list_head *item, *n; unsigned long isolated = 0; restart: - l = list_lru_from_memcg_idx(lru, nid, memcg_idx); + l = lock_list_lru_of_memcg(lru, nid, memcg, irq_off, true); if (!l) - goto out; - + return isolated; list_for_each_safe(item, n, &l->list) { enum lru_status ret; @@ -231,19 +298,19 @@ restart: break; --*nr_to_walk; - ret = isolate(item, l, &nlru->lock, cb_arg); + ret = isolate(item, l, cb_arg); switch (ret) { + /* + * LRU_RETRY, LRU_REMOVED_RETRY and LRU_STOP will drop the lru + * lock. List traversal will have to restart from scratch. + */ + case LRU_RETRY: + goto restart; case LRU_REMOVED_RETRY: - assert_spin_locked(&nlru->lock); fallthrough; case LRU_REMOVED: isolated++; - nlru->nr_items--; - /* - * If the lru lock has been dropped, our list - * traversal is now invalid and so we have to - * restart from scratch. - */ + atomic_long_dec(&nlru->nr_items); if (ret == LRU_REMOVED_RETRY) goto restart; break; @@ -252,20 +319,13 @@ restart: break; case LRU_SKIP: break; - case LRU_RETRY: - /* - * The lru lock has been dropped, our list traversal is - * now invalid and so we have to restart from scratch. - */ - assert_spin_locked(&nlru->lock); - goto restart; case LRU_STOP: - assert_spin_locked(&nlru->lock); goto out; default: BUG(); } } + unlock_list_lru(l, irq_off); out: return isolated; } @@ -275,14 +335,8 @@ list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { - struct list_lru_node *nlru = &lru->node[nid]; - unsigned long ret; - - spin_lock(&nlru->lock); - ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate, - cb_arg, nr_to_walk); - spin_unlock(&nlru->lock); - return ret; + return __list_lru_walk_one(lru, nid, memcg, isolate, + cb_arg, nr_to_walk, false); } EXPORT_SYMBOL_GPL(list_lru_walk_one); @@ -291,14 +345,8 @@ list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { - struct list_lru_node *nlru = &lru->node[nid]; - unsigned long ret; - - spin_lock_irq(&nlru->lock); - ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate, - cb_arg, nr_to_walk); - spin_unlock_irq(&nlru->lock); - return ret; + return __list_lru_walk_one(lru, nid, memcg, isolate, + cb_arg, nr_to_walk, true); } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, @@ -313,16 +361,21 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid, #ifdef CONFIG_MEMCG if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { struct list_lru_memcg *mlru; + struct mem_cgroup *memcg; unsigned long index; xa_for_each(&lru->xa, index, mlru) { - struct list_lru_node *nlru = &lru->node[nid]; - - spin_lock(&nlru->lock); - isolated += __list_lru_walk_one(lru, nid, index, + rcu_read_lock(); + memcg = mem_cgroup_from_id(index); + if (!mem_cgroup_tryget(memcg)) { + rcu_read_unlock(); + continue; + } + rcu_read_unlock(); + isolated += __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, - nr_to_walk); - spin_unlock(&nlru->lock); + nr_to_walk, false); + mem_cgroup_put(memcg); if (*nr_to_walk <= 0) break; @@ -334,14 +387,19 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid, } EXPORT_SYMBOL_GPL(list_lru_walk_node); -static void init_one_lru(struct list_lru_one *l) +static void init_one_lru(struct list_lru *lru, struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); + spin_lock_init(&l->lock); l->nr_items = 0; +#ifdef CONFIG_LOCKDEP + if (lru->key) + lockdep_set_class(&l->lock, lru->key); +#endif } #ifdef CONFIG_MEMCG -static struct list_lru_memcg *memcg_init_list_lru_one(gfp_t gfp) +static struct list_lru_memcg *memcg_init_list_lru_one(struct list_lru *lru, gfp_t gfp) { int nid; struct list_lru_memcg *mlru; @@ -351,25 +409,11 @@ static struct list_lru_memcg *memcg_init_list_lru_one(gfp_t gfp) return NULL; for_each_node(nid) - init_one_lru(&mlru->node[nid]); + init_one_lru(lru, &mlru->node[nid]); return mlru; } -static void memcg_list_lru_free(struct list_lru *lru, int src_idx) -{ - struct list_lru_memcg *mlru = xa_erase_irq(&lru->xa, src_idx); - - /* - * The __list_lru_walk_one() can walk the list of this node. - * We need kvfree_rcu() here. And the walking of the list - * is under lru->node[nid]->lock, which can serve as a RCU - * read-side critical section. - */ - if (mlru) - kvfree_rcu(mlru, rcu); -} - static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { if (memcg_aware) @@ -393,77 +437,64 @@ static void memcg_destroy_list_lru(struct list_lru *lru) xas_unlock_irq(&xas); } -static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, - int src_idx, struct mem_cgroup *dst_memcg) +static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid, + struct list_lru_one *src, + struct mem_cgroup *dst_memcg) { - struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; - struct list_lru_one *src, *dst; - - /* - * Since list_lru_{add,del} may be called under an IRQ-safe lock, - * we have to use IRQ-safe primitives here to avoid deadlock. - */ - spin_lock_irq(&nlru->lock); + struct list_lru_one *dst; - src = list_lru_from_memcg_idx(lru, nid, src_idx); - if (!src) - goto out; + spin_lock_irq(&src->lock); dst = list_lru_from_memcg_idx(lru, nid, dst_idx); + spin_lock_nested(&dst->lock, SINGLE_DEPTH_NESTING); list_splice_init(&src->list, &dst->list); - if (src->nr_items) { dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); - src->nr_items = 0; } -out: - spin_unlock_irq(&nlru->lock); -} - -static void memcg_reparent_list_lru(struct list_lru *lru, - int src_idx, struct mem_cgroup *dst_memcg) -{ - int i; + /* Mark the list_lru_one dead */ + src->nr_items = LONG_MIN; - for_each_node(i) - memcg_reparent_list_lru_node(lru, i, src_idx, dst_memcg); - - memcg_list_lru_free(lru, src_idx); + spin_unlock(&dst->lock); + spin_unlock_irq(&src->lock); } void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) { - struct cgroup_subsys_state *css; struct list_lru *lru; - int src_idx = memcg->kmemcg_id; + int i; - /* - * Change kmemcg_id of this cgroup and all its descendants to the - * parent's id, and then move all entries from this cgroup's list_lrus - * to ones of the parent. - * - * After we have finished, all list_lrus corresponding to this cgroup - * are guaranteed to remain empty. So we can safely free this cgroup's - * list lrus in memcg_list_lru_free(). - * - * Changing ->kmemcg_id to the parent can prevent memcg_list_lru_alloc() - * from allocating list lrus for this cgroup after memcg_list_lru_free() - * call. - */ - rcu_read_lock(); - css_for_each_descendant_pre(css, &memcg->css) { - struct mem_cgroup *child; + mutex_lock(&list_lrus_mutex); + list_for_each_entry(lru, &memcg_list_lrus, list) { + struct list_lru_memcg *mlru; + XA_STATE(xas, &lru->xa, memcg->kmemcg_id); - child = mem_cgroup_from_css(css); - WRITE_ONCE(child->kmemcg_id, parent->kmemcg_id); - } - rcu_read_unlock(); + /* + * Lock the Xarray to ensure no on going list_lru_memcg + * allocation and further allocation will see css_is_dying(). + */ + xas_lock_irq(&xas); + mlru = xas_store(&xas, NULL); + xas_unlock_irq(&xas); + if (!mlru) + continue; - mutex_lock(&list_lrus_mutex); - list_for_each_entry(lru, &memcg_list_lrus, list) - memcg_reparent_list_lru(lru, src_idx, parent); + /* + * With Xarray value set to NULL, holding the lru lock below + * prevents list_lru_{add,del,isolate} from touching the lru, + * safe to reparent. + */ + for_each_node(i) + memcg_reparent_list_lru_one(lru, i, &mlru->node[i], parent); + + /* + * Here all list_lrus corresponding to the cgroup are guaranteed + * to remain empty, we can safely free this lru, any further + * memcg_list_lru_alloc() call will simply bail out. + */ + kvfree_rcu(mlru, rcu); + } mutex_unlock(&list_lrus_mutex); } @@ -478,77 +509,48 @@ static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp) { - int i; unsigned long flags; - struct list_lru_memcg_table { - struct list_lru_memcg *mlru; - struct mem_cgroup *memcg; - } *table; + struct list_lru_memcg *mlru; + struct mem_cgroup *pos, *parent; XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; gfp &= GFP_RECLAIM_MASK; - table = kmalloc_array(memcg->css.cgroup->level, sizeof(*table), gfp); - if (!table) - return -ENOMEM; - /* * Because the list_lru can be reparented to the parent cgroup's * list_lru, we should make sure that this cgroup and all its * ancestors have allocated list_lru_memcg. */ - for (i = 0; memcg; memcg = parent_mem_cgroup(memcg), i++) { - if (memcg_list_lru_allocated(memcg, lru)) - break; - - table[i].memcg = memcg; - table[i].mlru = memcg_init_list_lru_one(gfp); - if (!table[i].mlru) { - while (i--) - kfree(table[i].mlru); - kfree(table); - return -ENOMEM; + do { + /* + * Keep finding the farest parent that wasn't populated + * until found memcg itself. + */ + pos = memcg; + parent = parent_mem_cgroup(pos); + while (!memcg_list_lru_allocated(parent, lru)) { + pos = parent; + parent = parent_mem_cgroup(pos); } - } - - xas_lock_irqsave(&xas, flags); - while (i--) { - int index = READ_ONCE(table[i].memcg->kmemcg_id); - struct list_lru_memcg *mlru = table[i].mlru; - xas_set(&xas, index); -retry: - if (unlikely(index < 0 || xas_error(&xas) || xas_load(&xas))) { - kfree(mlru); - } else { - xas_store(&xas, mlru); - if (xas_error(&xas) == -ENOMEM) { - xas_unlock_irqrestore(&xas, flags); - if (xas_nomem(&xas, gfp)) - xas_set_err(&xas, 0); - xas_lock_irqsave(&xas, flags); - /* - * The xas lock has been released, this memcg - * can be reparented before us. So reload - * memcg id. More details see the comments - * in memcg_reparent_list_lrus(). - */ - index = READ_ONCE(table[i].memcg->kmemcg_id); - if (index < 0) - xas_set_err(&xas, 0); - else if (!xas_error(&xas) && index != xas.xa_index) - xas_set(&xas, index); - goto retry; + mlru = memcg_init_list_lru_one(lru, gfp); + if (!mlru) + return -ENOMEM; + xas_set(&xas, pos->kmemcg_id); + do { + xas_lock_irqsave(&xas, flags); + if (!xas_load(&xas) && !css_is_dying(&pos->css)) { + xas_store(&xas, mlru); + if (!xas_error(&xas)) + mlru = NULL; } - } - } - /* xas_nomem() is used to free memory instead of memory allocation. */ - if (xas.xa_alloc) - xas_nomem(&xas, gfp); - xas_unlock_irqrestore(&xas, flags); - kfree(table); + xas_unlock_irqrestore(&xas, flags); + } while (xas_nomem(&xas, gfp)); + if (mlru) + kfree(mlru); + } while (pos != memcg && !css_is_dying(&pos->css)); return xas_error(&xas); } @@ -562,8 +564,7 @@ static void memcg_destroy_list_lru(struct list_lru *lru) } #endif /* CONFIG_MEMCG */ -int __list_lru_init(struct list_lru *lru, bool memcg_aware, - struct lock_class_key *key, struct shrinker *shrinker) +int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker) { int i; @@ -581,12 +582,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, if (!lru->node) return -ENOMEM; - for_each_node(i) { - spin_lock_init(&lru->node[i].lock); - if (key) - lockdep_set_class(&lru->node[i].lock, key); - init_one_lru(&lru->node[i].lru); - } + for_each_node(i) + init_one_lru(lru, &lru->node[i].lru); memcg_init_list_lru(lru, memcg_aware); list_lru_register(lru); diff --git a/mm/maccess.c b/mm/maccess.c index 518a25667323..8f0906180a94 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -13,9 +13,14 @@ bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src, return true; } +/* + * The below only uses kmsan_check_memory() to ensure uninitialized kernel + * memory isn't leaked. + */ #define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ - __get_kernel_nofault(dst, src, type, err_label); \ + __get_kernel_nofault(dst, src, type, err_label); \ + kmsan_check_memory(src, sizeof(type)); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ @@ -49,7 +54,8 @@ EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); #define copy_to_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ - __put_kernel_nofault(dst, src, type, err_label); \ + __put_kernel_nofault(dst, src, type, err_label); \ + instrument_write(dst, sizeof(type)); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ @@ -76,6 +82,7 @@ Efault: pagefault_enable(); return -EFAULT; } +EXPORT_SYMBOL_GPL(copy_to_kernel_nofault); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) { diff --git a/mm/madvise.c b/mm/madvise.c index ff139e57cca2..0ceae57da7da 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -37,6 +37,12 @@ #include "internal.h" #include "swap.h" +/* + * Maximum number of attempts we make to install guard pages before we give up + * and return -ERESTARTNOINTR to have userspace try again. + */ +#define MAX_MADVISE_GUARD_RETRIES 3 + struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; @@ -60,6 +66,8 @@ static int madvise_need_mmap_write(int behavior) case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: case MADV_COLLAPSE: + case MADV_GUARD_INSTALL: + case MADV_GUARD_REMOVE: return 0; default: /* be safe, default to 1. list exceptions explicitly */ @@ -1017,6 +1025,214 @@ static long madvise_remove(struct vm_area_struct *vma, return error; } +static bool is_valid_guard_vma(struct vm_area_struct *vma, bool allow_locked) +{ + vm_flags_t disallowed = VM_SPECIAL | VM_HUGETLB; + + /* + * A user could lock after setting a guard range but that's fine, as + * they'd not be able to fault in. The issue arises when we try to zap + * existing locked VMAs. We don't want to do that. + */ + if (!allow_locked) + disallowed |= VM_LOCKED; + + if (!vma_is_anonymous(vma)) + return false; + + if ((vma->vm_flags & (VM_MAYWRITE | disallowed)) != VM_MAYWRITE) + return false; + + return true; +} + +static bool is_guard_pte_marker(pte_t ptent) +{ + return is_pte_marker(ptent) && + is_guard_swp_entry(pte_to_swp_entry(ptent)); +} + +static int guard_install_pud_entry(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pud_t pudval = pudp_get(pud); + + /* If huge return >0 so we abort the operation + zap. */ + return pud_trans_huge(pudval) || pud_devmap(pudval); +} + +static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pmd_t pmdval = pmdp_get(pmd); + + /* If huge return >0 so we abort the operation + zap. */ + return pmd_trans_huge(pmdval) || pmd_devmap(pmdval); +} + +static int guard_install_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t pteval = ptep_get(pte); + unsigned long *nr_pages = (unsigned long *)walk->private; + + /* If there is already a guard page marker, we have nothing to do. */ + if (is_guard_pte_marker(pteval)) { + (*nr_pages)++; + + return 0; + } + + /* If populated return >0 so we abort the operation + zap. */ + return 1; +} + +static int guard_install_set_pte(unsigned long addr, unsigned long next, + pte_t *ptep, struct mm_walk *walk) +{ + unsigned long *nr_pages = (unsigned long *)walk->private; + + /* Simply install a PTE marker, this causes segfault on access. */ + *ptep = make_pte_marker(PTE_MARKER_GUARD); + (*nr_pages)++; + + return 0; +} + +static const struct mm_walk_ops guard_install_walk_ops = { + .pud_entry = guard_install_pud_entry, + .pmd_entry = guard_install_pmd_entry, + .pte_entry = guard_install_pte_entry, + .install_pte = guard_install_set_pte, + .walk_lock = PGWALK_RDLOCK, +}; + +static long madvise_guard_install(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + long err; + int i; + + *prev = vma; + if (!is_valid_guard_vma(vma, /* allow_locked = */false)) + return -EINVAL; + + /* + * If we install guard markers, then the range is no longer + * empty from a page table perspective and therefore it's + * appropriate to have an anon_vma. + * + * This ensures that on fork, we copy page tables correctly. + */ + err = anon_vma_prepare(vma); + if (err) + return err; + + /* + * Optimistically try to install the guard marker pages first. If any + * non-guard pages are encountered, give up and zap the range before + * trying again. + * + * We try a few times before giving up and releasing back to userland to + * loop around, releasing locks in the process to avoid contention. This + * would only happen if there was a great many racing page faults. + * + * In most cases we should simply install the guard markers immediately + * with no zap or looping. + */ + for (i = 0; i < MAX_MADVISE_GUARD_RETRIES; i++) { + unsigned long nr_pages = 0; + + /* Returns < 0 on error, == 0 if success, > 0 if zap needed. */ + err = walk_page_range_mm(vma->vm_mm, start, end, + &guard_install_walk_ops, &nr_pages); + if (err < 0) + return err; + + if (err == 0) { + unsigned long nr_expected_pages = PHYS_PFN(end - start); + + VM_WARN_ON(nr_pages != nr_expected_pages); + return 0; + } + + /* + * OK some of the range have non-guard pages mapped, zap + * them. This leaves existing guard pages in place. + */ + zap_page_range_single(vma, start, end - start, NULL); + } + + /* + * We were unable to install the guard pages due to being raced by page + * faults. This should not happen ordinarily. We return to userspace and + * immediately retry, relieving lock contention. + */ + return restart_syscall(); +} + +static int guard_remove_pud_entry(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pud_t pudval = pudp_get(pud); + + /* If huge, cannot have guard pages present, so no-op - skip. */ + if (pud_trans_huge(pudval) || pud_devmap(pudval)) + walk->action = ACTION_CONTINUE; + + return 0; +} + +static int guard_remove_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pmd_t pmdval = pmdp_get(pmd); + + /* If huge, cannot have guard pages present, so no-op - skip. */ + if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval)) + walk->action = ACTION_CONTINUE; + + return 0; +} + +static int guard_remove_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t ptent = ptep_get(pte); + + if (is_guard_pte_marker(ptent)) { + /* Simply clear the PTE marker. */ + pte_clear_not_present_full(walk->mm, addr, pte, false); + update_mmu_cache(walk->vma, addr, pte); + } + + return 0; +} + +static const struct mm_walk_ops guard_remove_walk_ops = { + .pud_entry = guard_remove_pud_entry, + .pmd_entry = guard_remove_pmd_entry, + .pte_entry = guard_remove_pte_entry, + .walk_lock = PGWALK_RDLOCK, +}; + +static long madvise_guard_remove(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + *prev = vma; + /* + * We're ok with removing guards in mlock()'d ranges, as this is a + * non-destructive action. + */ + if (!is_valid_guard_vma(vma, /* allow_locked = */true)) + return -EINVAL; + + return walk_page_range(vma->vm_mm, start, end, + &guard_remove_walk_ops, NULL); +} + /* * Apply an madvise behavior to a region of a vma. madvise_update_vma * will handle splitting a vm area into separate areas, each area with its own @@ -1098,6 +1314,10 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, break; case MADV_COLLAPSE: return madvise_collapse(vma, prev, start, end); + case MADV_GUARD_INSTALL: + return madvise_guard_install(vma, prev, start, end); + case MADV_GUARD_REMOVE: + return madvise_guard_remove(vma, prev, start, end); } anon_name = anon_vma_name(vma); @@ -1197,6 +1417,8 @@ madvise_behavior_valid(int behavior) case MADV_DODUMP: case MADV_WIPEONFORK: case MADV_KEEPONFORK: + case MADV_GUARD_INSTALL: + case MADV_GUARD_REMOVE: #ifdef CONFIG_MEMORY_FAILURE case MADV_SOFT_OFFLINE: case MADV_HWPOISON: @@ -1208,7 +1430,8 @@ madvise_behavior_valid(int behavior) } } -static bool process_madvise_behavior_valid(int behavior) +/* Can we invoke process_madvise() on a remote mm for the specified behavior? */ +static bool process_madvise_remote_valid(int behavior) { switch (behavior) { case MADV_COLD: @@ -1477,6 +1700,45 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) return do_madvise(current->mm, start, len_in, behavior); } +/* Perform an madvise operation over a vector of addresses and lengths. */ +static ssize_t vector_madvise(struct mm_struct *mm, struct iov_iter *iter, + int behavior) +{ + ssize_t ret = 0; + size_t total_len; + + total_len = iov_iter_count(iter); + + while (iov_iter_count(iter)) { + ret = do_madvise(mm, (unsigned long)iter_iov_addr(iter), + iter_iov_len(iter), behavior); + /* + * An madvise operation is attempting to restart the syscall, + * but we cannot proceed as it would not be correct to repeat + * the operation in aggregate, and would be surprising to the + * user. + * + * As we have already dropped locks, it is safe to just loop and + * try again. We check for fatal signals in case we need exit + * early anyway. + */ + if (ret == -ERESTARTNOINTR) { + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + continue; + } + if (ret < 0) + break; + iov_iter_advance(iter, iter_iov_len(iter)); + } + + ret = (total_len - iov_iter_count(iter)) ? : ret; + + return ret; +} + SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, size_t, vlen, int, behavior, unsigned int, flags) { @@ -1486,7 +1748,6 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, struct iov_iter iter; struct task_struct *task; struct mm_struct *mm; - size_t total_len; unsigned int f_flags; if (flags != 0) { @@ -1504,38 +1765,33 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, goto free_iov; } - if (!process_madvise_behavior_valid(behavior)) { - ret = -EINVAL; - goto release_task; - } - /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); - if (IS_ERR_OR_NULL(mm)) { - ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; + if (IS_ERR(mm)) { + ret = PTR_ERR(mm); goto release_task; } /* + * We need only perform this check if we are attempting to manipulate a + * remote process's address space. + */ + if (mm != current->mm && !process_madvise_remote_valid(behavior)) { + ret = -EINVAL; + goto release_mm; + } + + /* * Require CAP_SYS_NICE for influencing process performance. Note that - * only non-destructive hints are currently supported. + * only non-destructive hints are currently supported for remote + * processes. */ if (mm != current->mm && !capable(CAP_SYS_NICE)) { ret = -EPERM; goto release_mm; } - total_len = iov_iter_count(&iter); - - while (iov_iter_count(&iter)) { - ret = do_madvise(mm, (unsigned long)iter_iov_addr(&iter), - iter_iov_len(&iter), behavior); - if (ret < 0) - break; - iov_iter_advance(&iter, iter_iov_len(&iter)); - } - - ret = (total_len - iov_iter_count(&iter)) ? : ret; + ret = vector_madvise(mm, &iter, behavior); release_mm: mmput(mm); diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 86527d8fa7b9..a071fa43d479 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -40,31 +40,6 @@ static struct mem_cgroup_tree soft_limit_tree __read_mostly; #define MEM_CGROUP_MAX_RECLAIM_LOOPS 100 #define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2 -/* Stuffs for move charges at task migration. */ -/* - * Types of charges to be moved. - */ -#define MOVE_ANON 0x1ULL -#define MOVE_FILE 0x2ULL -#define MOVE_MASK (MOVE_ANON | MOVE_FILE) - -/* "mc" and its members are protected by cgroup_mutex */ -static struct move_charge_struct { - spinlock_t lock; /* for from, to */ - struct mm_struct *mm; - struct mem_cgroup *from; - struct mem_cgroup *to; - unsigned long flags; - unsigned long precharge; - unsigned long moved_charge; - unsigned long moved_swap; - struct task_struct *moving_task; /* a task moving charges */ - wait_queue_head_t waitq; /* a waitq for other context */ -} mc = { - .lock = __SPIN_LOCK_UNLOCKED(mc.lock), - .waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq), -}; - /* for OOM */ struct mem_cgroup_eventfd_list { struct list_head list; @@ -426,196 +401,22 @@ unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, return nr_reclaimed; } -/* - * A routine for checking "mem" is under move_account() or not. - * - * Checking a cgroup is mc.from or mc.to or under hierarchy of - * moving cgroups. This is for waiting at high-memory pressure - * caused by "move". - */ -static bool mem_cgroup_under_move(struct mem_cgroup *memcg) -{ - struct mem_cgroup *from; - struct mem_cgroup *to; - bool ret = false; - /* - * Unlike task_move routines, we access mc.to, mc.from not under - * mutual exclusion by cgroup_mutex. Here, we take spinlock instead. - */ - spin_lock(&mc.lock); - from = mc.from; - to = mc.to; - if (!from) - goto unlock; - - ret = mem_cgroup_is_descendant(from, memcg) || - mem_cgroup_is_descendant(to, memcg); -unlock: - spin_unlock(&mc.lock); - return ret; -} - -bool memcg1_wait_acct_move(struct mem_cgroup *memcg) -{ - if (mc.moving_task && current != mc.moving_task) { - if (mem_cgroup_under_move(memcg)) { - DEFINE_WAIT(wait); - prepare_to_wait(&mc.waitq, &wait, TASK_INTERRUPTIBLE); - /* moving charge context might have finished. */ - if (mc.moving_task) - schedule(); - finish_wait(&mc.waitq, &wait); - return true; - } - } - return false; -} - -/** - * folio_memcg_lock - Bind a folio to its memcg. - * @folio: The folio. - * - * This function prevents unlocked LRU folios from being moved to - * another cgroup. - * - * It ensures lifetime of the bound memcg. The caller is responsible - * for the lifetime of the folio. - */ -void folio_memcg_lock(struct folio *folio) -{ - struct mem_cgroup *memcg; - unsigned long flags; - - /* - * The RCU lock is held throughout the transaction. The fast - * path can get away without acquiring the memcg->move_lock - * because page moving starts with an RCU grace period. - */ - rcu_read_lock(); - - if (mem_cgroup_disabled()) - return; -again: - memcg = folio_memcg(folio); - if (unlikely(!memcg)) - return; - -#ifdef CONFIG_PROVE_LOCKING - local_irq_save(flags); - might_lock(&memcg->move_lock); - local_irq_restore(flags); -#endif - - if (atomic_read(&memcg->moving_account) <= 0) - return; - - spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != folio_memcg(folio)) { - spin_unlock_irqrestore(&memcg->move_lock, flags); - goto again; - } - - /* - * When charge migration first begins, we can have multiple - * critical sections holding the fast-path RCU lock and one - * holding the slowpath move_lock. Track the task who has the - * move_lock for folio_memcg_unlock(). - */ - memcg->move_lock_task = current; - memcg->move_lock_flags = flags; -} - -static void __folio_memcg_unlock(struct mem_cgroup *memcg) -{ - if (memcg && memcg->move_lock_task == current) { - unsigned long flags = memcg->move_lock_flags; - - memcg->move_lock_task = NULL; - memcg->move_lock_flags = 0; - - spin_unlock_irqrestore(&memcg->move_lock, flags); - } - - rcu_read_unlock(); -} - -/** - * folio_memcg_unlock - Release the binding between a folio and its memcg. - * @folio: The folio. - * - * This releases the binding created by folio_memcg_lock(). This does - * not change the accounting of this folio to its memcg, but it does - * permit others to change it. - */ -void folio_memcg_unlock(struct folio *folio) -{ - __folio_memcg_unlock(folio_memcg(folio)); -} - -#ifdef CONFIG_SWAP -/** - * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record. - * @entry: swap entry to be moved - * @from: mem_cgroup which the entry is moved from - * @to: mem_cgroup which the entry is moved to - * - * It succeeds only when the swap_cgroup's record for this entry is the same - * as the mem_cgroup's id of @from. - * - * Returns 0 on success, -EINVAL on failure. - * - * The caller must have charged to @to, IOW, called page_counter_charge() about - * both res and memsw, and called css_get(). - */ -static int mem_cgroup_move_swap_account(swp_entry_t entry, - struct mem_cgroup *from, struct mem_cgroup *to) -{ - unsigned short old_id, new_id; - - old_id = mem_cgroup_id(from); - new_id = mem_cgroup_id(to); - - if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { - mod_memcg_state(from, MEMCG_SWAP, -1); - mod_memcg_state(to, MEMCG_SWAP, 1); - return 0; - } - return -EINVAL; -} -#else -static inline int mem_cgroup_move_swap_account(swp_entry_t entry, - struct mem_cgroup *from, struct mem_cgroup *to) -{ - return -EINVAL; -} -#endif - static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, struct cftype *cft) { - return mem_cgroup_from_css(css)->move_charge_at_immigrate; + return 0; } #ifdef CONFIG_MMU static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - pr_warn_once("Cgroup memory moving (move_charge_at_immigrate) is deprecated. " "Please report your usecase to linux-mm@kvack.org if you " "depend on this functionality.\n"); - if (val & ~MOVE_MASK) + if (val != 0) return -EINVAL; - - /* - * No kind of locking is needed in here, because ->can_attach() will - * check this value once in the beginning of the process, and then carry - * on with stale data. This means that changes to this value will only - * affect task migrations starting after the change. - */ - memcg->move_charge_at_immigrate = val; return 0; } #else @@ -626,785 +427,6 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, } #endif -#ifdef CONFIG_MMU -/* Handlers for move charge at task migration. */ -static int mem_cgroup_do_precharge(unsigned long count) -{ - int ret; - - /* Try a single bulk charge without reclaim first, kswapd may wake */ - ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count); - if (!ret) { - mc.precharge += count; - return ret; - } - - /* Try charges one by one with reclaim, but do not retry */ - while (count--) { - ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1); - if (ret) - return ret; - mc.precharge++; - cond_resched(); - } - return 0; -} - -union mc_target { - struct folio *folio; - swp_entry_t ent; -}; - -enum mc_target_type { - MC_TARGET_NONE = 0, - MC_TARGET_PAGE, - MC_TARGET_SWAP, - MC_TARGET_DEVICE, -}; - -static struct page *mc_handle_present_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent) -{ - struct page *page = vm_normal_page(vma, addr, ptent); - - if (!page) - return NULL; - if (PageAnon(page)) { - if (!(mc.flags & MOVE_ANON)) - return NULL; - } else { - if (!(mc.flags & MOVE_FILE)) - return NULL; - } - get_page(page); - - return page; -} - -#if defined(CONFIG_SWAP) || defined(CONFIG_DEVICE_PRIVATE) -static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, - pte_t ptent, swp_entry_t *entry) -{ - struct page *page = NULL; - swp_entry_t ent = pte_to_swp_entry(ptent); - - if (!(mc.flags & MOVE_ANON)) - return NULL; - - /* - * Handle device private pages that are not accessible by the CPU, but - * stored as special swap entries in the page table. - */ - if (is_device_private_entry(ent)) { - page = pfn_swap_entry_to_page(ent); - if (!get_page_unless_zero(page)) - return NULL; - return page; - } - - if (non_swap_entry(ent)) - return NULL; - - /* - * Because swap_cache_get_folio() updates some statistics counter, - * we call find_get_page() with swapper_space directly. - */ - page = find_get_page(swap_address_space(ent), swap_cache_index(ent)); - entry->val = ent.val; - - return page; -} -#else -static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, - pte_t ptent, swp_entry_t *entry) -{ - return NULL; -} -#endif - -static struct page *mc_handle_file_pte(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent) -{ - unsigned long index; - struct folio *folio; - - if (!vma->vm_file) /* anonymous vma */ - return NULL; - if (!(mc.flags & MOVE_FILE)) - return NULL; - - /* folio is moved even if it's not RSS of this task(page-faulted). */ - /* shmem/tmpfs may report page out on swap: account for that too. */ - index = linear_page_index(vma, addr); - folio = filemap_get_incore_folio(vma->vm_file->f_mapping, index); - if (IS_ERR(folio)) - return NULL; - return folio_file_page(folio, index); -} - -static void memcg1_check_events(struct mem_cgroup *memcg, int nid); -static void memcg1_charge_statistics(struct mem_cgroup *memcg, int nr_pages); - -/** - * mem_cgroup_move_account - move account of the folio - * @folio: The folio. - * @compound: charge the page as compound or small page - * @from: mem_cgroup which the folio is moved from. - * @to: mem_cgroup which the folio is moved to. @from != @to. - * - * The folio must be locked and not on the LRU. - * - * This function doesn't do "charge" to new cgroup and doesn't do "uncharge" - * from old cgroup. - */ -static int mem_cgroup_move_account(struct folio *folio, - bool compound, - struct mem_cgroup *from, - struct mem_cgroup *to) -{ - struct lruvec *from_vec, *to_vec; - struct pglist_data *pgdat; - unsigned int nr_pages = compound ? folio_nr_pages(folio) : 1; - int nid, ret; - - VM_BUG_ON(from == to); - VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - VM_BUG_ON(compound && !folio_test_large(folio)); - - ret = -EINVAL; - if (folio_memcg(folio) != from) - goto out; - - pgdat = folio_pgdat(folio); - from_vec = mem_cgroup_lruvec(from, pgdat); - to_vec = mem_cgroup_lruvec(to, pgdat); - - folio_memcg_lock(folio); - - if (folio_test_anon(folio)) { - if (folio_mapped(folio)) { - __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); - __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); - if (folio_test_pmd_mappable(folio)) { - __mod_lruvec_state(from_vec, NR_ANON_THPS, - -nr_pages); - __mod_lruvec_state(to_vec, NR_ANON_THPS, - nr_pages); - } - } - } else { - __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); - __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); - - if (folio_test_swapbacked(folio)) { - __mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages); - __mod_lruvec_state(to_vec, NR_SHMEM, nr_pages); - } - - if (folio_mapped(folio)) { - __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); - __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); - } - - if (folio_test_dirty(folio)) { - struct address_space *mapping = folio_mapping(folio); - - if (mapping_can_writeback(mapping)) { - __mod_lruvec_state(from_vec, NR_FILE_DIRTY, - -nr_pages); - __mod_lruvec_state(to_vec, NR_FILE_DIRTY, - nr_pages); - } - } - } - -#ifdef CONFIG_SWAP - if (folio_test_swapcache(folio)) { - __mod_lruvec_state(from_vec, NR_SWAPCACHE, -nr_pages); - __mod_lruvec_state(to_vec, NR_SWAPCACHE, nr_pages); - } -#endif - if (folio_test_writeback(folio)) { - __mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages); - __mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages); - } - - /* - * All state has been migrated, let's switch to the new memcg. - * - * It is safe to change page's memcg here because the page - * is referenced, charged, isolated, and locked: we can't race - * with (un)charging, migration, LRU putback, or anything else - * that would rely on a stable page's memory cgroup. - * - * Note that folio_memcg_lock is a memcg lock, not a page lock, - * to save space. As soon as we switch page's memory cgroup to a - * new memcg that isn't locked, the above state can change - * concurrently again. Make sure we're truly done with it. - */ - smp_mb(); - - css_get(&to->css); - css_put(&from->css); - - /* Warning should never happen, so don't worry about refcount non-0 */ - WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); - folio->memcg_data = (unsigned long)to; - - __folio_memcg_unlock(from); - - ret = 0; - nid = folio_nid(folio); - - local_irq_disable(); - memcg1_charge_statistics(to, nr_pages); - memcg1_check_events(to, nid); - memcg1_charge_statistics(from, -nr_pages); - memcg1_check_events(from, nid); - local_irq_enable(); -out: - return ret; -} - -/** - * get_mctgt_type - get target type of moving charge - * @vma: the vma the pte to be checked belongs - * @addr: the address corresponding to the pte to be checked - * @ptent: the pte to be checked - * @target: the pointer the target page or swap ent will be stored(can be NULL) - * - * Context: Called with pte lock held. - * Return: - * * MC_TARGET_NONE - If the pte is not a target for move charge. - * * MC_TARGET_PAGE - If the page corresponding to this pte is a target for - * move charge. If @target is not NULL, the folio is stored in target->folio - * with extra refcnt taken (Caller should release it). - * * MC_TARGET_SWAP - If the swap entry corresponding to this pte is a - * target for charge migration. If @target is not NULL, the entry is - * stored in target->ent. - * * MC_TARGET_DEVICE - Like MC_TARGET_PAGE but page is device memory and - * thus not on the lru. For now such page is charged like a regular page - * would be as it is just special memory taking the place of a regular page. - * See Documentations/vm/hmm.txt and include/linux/hmm.h - */ -static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, - unsigned long addr, pte_t ptent, union mc_target *target) -{ - struct page *page = NULL; - struct folio *folio; - enum mc_target_type ret = MC_TARGET_NONE; - swp_entry_t ent = { .val = 0 }; - - 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); - - if (page) - folio = page_folio(page); - if (target && page) { - if (!folio_trylock(folio)) { - folio_put(folio); - return ret; - } - /* - * page_mapped() must be stable during the move. This - * pte is locked, so if it's present, the page cannot - * become unmapped. If it isn't, we have only partial - * control over the mapped state: the page lock will - * prevent new faults against pagecache and swapcache, - * so an unmapped page cannot become mapped. However, - * if the page is already mapped elsewhere, it can - * unmap, and there is nothing we can do about it. - * Alas, skip moving the page in this case. - */ - if (!pte_present(ptent) && page_mapped(page)) { - folio_unlock(folio); - folio_put(folio); - return ret; - } - } - - if (!page && !ent.val) - return ret; - if (page) { - /* - * Do only loose check w/o serialization. - * mem_cgroup_move_account() checks the page is valid or - * not under LRU exclusion. - */ - if (folio_memcg(folio) == mc.from) { - ret = MC_TARGET_PAGE; - if (folio_is_device_private(folio) || - folio_is_device_coherent(folio)) - ret = MC_TARGET_DEVICE; - if (target) - target->folio = folio; - } - if (!ret || !target) { - if (target) - folio_unlock(folio); - folio_put(folio); - } - } - /* - * There is a swap entry and a page doesn't exist or isn't charged. - * But we cannot move a tail-page in a THP. - */ - if (ent.val && !ret && (!page || !PageTransCompound(page)) && - mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) { - ret = MC_TARGET_SWAP; - if (target) - target->ent = ent; - } - return ret; -} - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/* - * We don't consider PMD mapped swapping or file mapped pages because THP does - * not support them for now. - * Caller should make sure that pmd_trans_huge(pmd) is true. - */ -static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, union mc_target *target) -{ - struct page *page = NULL; - struct folio *folio; - enum mc_target_type ret = MC_TARGET_NONE; - - if (unlikely(is_swap_pmd(pmd))) { - VM_BUG_ON(thp_migration_supported() && - !is_pmd_migration_entry(pmd)); - return ret; - } - page = pmd_page(pmd); - VM_BUG_ON_PAGE(!page || !PageHead(page), page); - folio = page_folio(page); - if (!(mc.flags & MOVE_ANON)) - return ret; - if (folio_memcg(folio) == mc.from) { - ret = MC_TARGET_PAGE; - if (target) { - folio_get(folio); - if (!folio_trylock(folio)) { - folio_put(folio); - return MC_TARGET_NONE; - } - target->folio = folio; - } - } - return ret; -} -#else -static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, - unsigned long addr, pmd_t pmd, union mc_target *target) -{ - return MC_TARGET_NONE; -} -#endif - -static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, - unsigned long addr, unsigned long end, - struct mm_walk *walk) -{ - struct vm_area_struct *vma = walk->vma; - pte_t *pte; - spinlock_t *ptl; - - ptl = pmd_trans_huge_lock(pmd, vma); - if (ptl) { - /* - * Note their can not be MC_TARGET_DEVICE for now as we do not - * support transparent huge page with MEMORY_DEVICE_PRIVATE but - * this might change. - */ - if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) - mc.precharge += HPAGE_PMD_NR; - spin_unlock(ptl); - return 0; - } - - pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - if (!pte) - return 0; - for (; addr != end; pte++, addr += PAGE_SIZE) - if (get_mctgt_type(vma, addr, ptep_get(pte), NULL)) - mc.precharge++; /* increment precharge temporarily */ - pte_unmap_unlock(pte - 1, ptl); - cond_resched(); - - return 0; -} - -static const struct mm_walk_ops precharge_walk_ops = { - .pmd_entry = mem_cgroup_count_precharge_pte_range, - .walk_lock = PGWALK_RDLOCK, -}; - -static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) -{ - unsigned long precharge; - - mmap_read_lock(mm); - walk_page_range(mm, 0, ULONG_MAX, &precharge_walk_ops, NULL); - mmap_read_unlock(mm); - - precharge = mc.precharge; - mc.precharge = 0; - - return precharge; -} - -static int mem_cgroup_precharge_mc(struct mm_struct *mm) -{ - unsigned long precharge = mem_cgroup_count_precharge(mm); - - VM_BUG_ON(mc.moving_task); - mc.moving_task = current; - return mem_cgroup_do_precharge(precharge); -} - -/* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */ -static void __mem_cgroup_clear_mc(void) -{ - struct mem_cgroup *from = mc.from; - struct mem_cgroup *to = mc.to; - - /* we must uncharge all the leftover precharges from mc.to */ - if (mc.precharge) { - mem_cgroup_cancel_charge(mc.to, mc.precharge); - mc.precharge = 0; - } - /* - * we didn't uncharge from mc.from at mem_cgroup_move_account(), so - * we must uncharge here. - */ - if (mc.moved_charge) { - mem_cgroup_cancel_charge(mc.from, mc.moved_charge); - mc.moved_charge = 0; - } - /* we must fixup refcnts and charges */ - if (mc.moved_swap) { - /* uncharge swap account from the old cgroup */ - if (!mem_cgroup_is_root(mc.from)) - page_counter_uncharge(&mc.from->memsw, mc.moved_swap); - - mem_cgroup_id_put_many(mc.from, mc.moved_swap); - - /* - * we charged both to->memory and to->memsw, so we - * should uncharge to->memory. - */ - if (!mem_cgroup_is_root(mc.to)) - page_counter_uncharge(&mc.to->memory, mc.moved_swap); - - mc.moved_swap = 0; - } - memcg1_oom_recover(from); - memcg1_oom_recover(to); - wake_up_all(&mc.waitq); -} - -static void mem_cgroup_clear_mc(void) -{ - struct mm_struct *mm = mc.mm; - - /* - * we must clear moving_task before waking up waiters at the end of - * task migration. - */ - mc.moving_task = NULL; - __mem_cgroup_clear_mc(); - spin_lock(&mc.lock); - mc.from = NULL; - mc.to = NULL; - mc.mm = NULL; - spin_unlock(&mc.lock); - - mmput(mm); -} - -int memcg1_can_attach(struct cgroup_taskset *tset) -{ - struct cgroup_subsys_state *css; - struct mem_cgroup *memcg = NULL; /* unneeded init to make gcc happy */ - struct mem_cgroup *from; - struct task_struct *leader, *p; - struct mm_struct *mm; - unsigned long move_flags; - int ret = 0; - - /* charge immigration isn't supported on the default hierarchy */ - if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return 0; - - /* - * Multi-process migrations only happen on the default hierarchy - * where charge immigration is not used. Perform charge - * immigration if @tset contains a leader and whine if there are - * multiple. - */ - p = NULL; - cgroup_taskset_for_each_leader(leader, css, tset) { - WARN_ON_ONCE(p); - p = leader; - memcg = mem_cgroup_from_css(css); - } - if (!p) - return 0; - - /* - * We are now committed to this value whatever it is. Changes in this - * tunable will only affect upcoming migrations, not the current one. - * So we need to save it, and keep it going. - */ - move_flags = READ_ONCE(memcg->move_charge_at_immigrate); - if (!move_flags) - return 0; - - from = mem_cgroup_from_task(p); - - VM_BUG_ON(from == memcg); - - mm = get_task_mm(p); - if (!mm) - return 0; - /* We move charges only when we move a owner of the mm */ - if (mm->owner == p) { - VM_BUG_ON(mc.from); - VM_BUG_ON(mc.to); - VM_BUG_ON(mc.precharge); - VM_BUG_ON(mc.moved_charge); - VM_BUG_ON(mc.moved_swap); - - spin_lock(&mc.lock); - mc.mm = mm; - mc.from = from; - mc.to = memcg; - mc.flags = move_flags; - spin_unlock(&mc.lock); - /* We set mc.moving_task later */ - - ret = mem_cgroup_precharge_mc(mm); - if (ret) - mem_cgroup_clear_mc(); - } else { - mmput(mm); - } - return ret; -} - -void memcg1_cancel_attach(struct cgroup_taskset *tset) -{ - if (mc.to) - mem_cgroup_clear_mc(); -} - -static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, - unsigned long addr, unsigned long end, - struct mm_walk *walk) -{ - int ret = 0; - struct vm_area_struct *vma = walk->vma; - pte_t *pte; - spinlock_t *ptl; - enum mc_target_type target_type; - union mc_target target; - struct folio *folio; - bool tried_split_before = false; - -retry_pmd: - ptl = pmd_trans_huge_lock(pmd, vma); - if (ptl) { - if (mc.precharge < HPAGE_PMD_NR) { - spin_unlock(ptl); - return 0; - } - target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); - if (target_type == MC_TARGET_PAGE) { - folio = target.folio; - /* - * Deferred split queue locking depends on memcg, - * and unqueue is unsafe unless folio refcount is 0: - * split or skip if on the queue? first try to split. - */ - if (!list_empty(&folio->_deferred_list)) { - spin_unlock(ptl); - if (!tried_split_before) - split_folio(folio); - folio_unlock(folio); - folio_put(folio); - if (tried_split_before) - return 0; - tried_split_before = true; - goto retry_pmd; - } - /* - * So long as that pmd lock is held, the folio cannot - * be racily added to the _deferred_list, because - * __folio_remove_rmap() will find !partially_mapped. - */ - if (folio_isolate_lru(folio)) { - if (!mem_cgroup_move_account(folio, true, - mc.from, mc.to)) { - mc.precharge -= HPAGE_PMD_NR; - mc.moved_charge += HPAGE_PMD_NR; - } - folio_putback_lru(folio); - } - folio_unlock(folio); - folio_put(folio); - } else if (target_type == MC_TARGET_DEVICE) { - folio = target.folio; - if (!mem_cgroup_move_account(folio, true, - mc.from, mc.to)) { - mc.precharge -= HPAGE_PMD_NR; - mc.moved_charge += HPAGE_PMD_NR; - } - folio_unlock(folio); - folio_put(folio); - } - spin_unlock(ptl); - return 0; - } - -retry: - pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - if (!pte) - return 0; - for (; addr != end; addr += PAGE_SIZE) { - pte_t ptent = ptep_get(pte++); - bool device = false; - swp_entry_t ent; - - if (!mc.precharge) - break; - - switch (get_mctgt_type(vma, addr, ptent, &target)) { - case MC_TARGET_DEVICE: - device = true; - fallthrough; - case MC_TARGET_PAGE: - folio = target.folio; - /* - * We can have a part of the split pmd here. Moving it - * can be done but it would be too convoluted so simply - * ignore such a partial THP and keep it in original - * memcg. There should be somebody mapping the head. - */ - if (folio_test_large(folio)) - goto put; - if (!device && !folio_isolate_lru(folio)) - goto put; - if (!mem_cgroup_move_account(folio, false, - mc.from, mc.to)) { - mc.precharge--; - /* we uncharge from mc.from later. */ - mc.moved_charge++; - } - if (!device) - folio_putback_lru(folio); -put: /* get_mctgt_type() gets & locks the page */ - folio_unlock(folio); - folio_put(folio); - break; - case MC_TARGET_SWAP: - ent = target.ent; - if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) { - mc.precharge--; - mem_cgroup_id_get_many(mc.to, 1); - /* we fixup other refcnts and charges later. */ - mc.moved_swap++; - } - break; - default: - break; - } - } - pte_unmap_unlock(pte - 1, ptl); - cond_resched(); - - if (addr != end) { - /* - * We have consumed all precharges we got in can_attach(). - * We try charge one by one, but don't do any additional - * charges to mc.to if we have failed in charge once in attach() - * phase. - */ - ret = mem_cgroup_do_precharge(1); - if (!ret) - goto retry; - } - - return ret; -} - -static const struct mm_walk_ops charge_walk_ops = { - .pmd_entry = mem_cgroup_move_charge_pte_range, - .walk_lock = PGWALK_RDLOCK, -}; - -static void mem_cgroup_move_charge(void) -{ - lru_add_drain_all(); - /* - * Signal folio_memcg_lock() to take the memcg's move_lock - * while we're moving its pages to another memcg. Then wait - * for already started RCU-only updates to finish. - */ - atomic_inc(&mc.from->moving_account); - synchronize_rcu(); -retry: - if (unlikely(!mmap_read_trylock(mc.mm))) { - /* - * Someone who are holding the mmap_lock might be waiting in - * waitq. So we cancel all extra charges, wake up all waiters, - * and retry. Because we cancel precharges, we might not be able - * to move enough charges, but moving charge is a best-effort - * feature anyway, so it wouldn't be a big problem. - */ - __mem_cgroup_clear_mc(); - cond_resched(); - goto retry; - } - /* - * When we have consumed all precharges and failed in doing - * additional charge, the page walk just aborts. - */ - walk_page_range(mc.mm, 0, ULONG_MAX, &charge_walk_ops, NULL); - mmap_read_unlock(mc.mm); - atomic_dec(&mc.from->moving_account); -} - -void memcg1_move_task(void) -{ - if (mc.to) { - mem_cgroup_move_charge(); - mem_cgroup_clear_mc(); - } -} - -#else /* !CONFIG_MMU */ -int memcg1_can_attach(struct cgroup_taskset *tset) -{ - return 0; -} -void memcg1_cancel_attach(struct cgroup_taskset *tset) -{ -} -void memcg1_move_task(void) -{ -} -#endif - static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap) { struct mem_cgroup_threshold_ary *t; @@ -2072,7 +1094,6 @@ void memcg1_memcg_init(struct mem_cgroup *memcg) { INIT_LIST_HEAD(&memcg->oom_notify); mutex_init(&memcg->thresholds_lock); - spin_lock_init(&memcg->move_lock); INIT_LIST_HEAD(&memcg->event_list); spin_lock_init(&memcg->event_list_lock); } diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h index c0672e25bcdb..0e3b82951d91 100644 --- a/mm/memcontrol-v1.h +++ b/mm/memcontrol-v1.h @@ -80,12 +80,7 @@ static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg) WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX); } -bool memcg1_wait_acct_move(struct mem_cgroup *memcg); - struct cgroup_taskset; -int memcg1_can_attach(struct cgroup_taskset *tset); -void memcg1_cancel_attach(struct cgroup_taskset *tset); -void memcg1_move_task(void); void memcg1_css_offline(struct mem_cgroup *memcg); /* for encoding cft->private value on file */ @@ -130,7 +125,6 @@ static inline void memcg1_free_events(struct mem_cgroup *memcg) {} static inline void memcg1_memcg_init(struct mem_cgroup *memcg) {} static inline void memcg1_remove_from_trees(struct mem_cgroup *memcg) {} static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg) {} -static inline bool memcg1_wait_acct_move(struct mem_cgroup *memcg) { return false; } static inline void memcg1_css_offline(struct mem_cgroup *memcg) {} static inline bool memcg1_oom_prepare(struct mem_cgroup *memcg, bool *locked) { return true; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 53db98d2c4a1..7b3503d12aaf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -71,6 +71,10 @@ #include <linux/uaccess.h> +#define CREATE_TRACE_POINTS +#include <trace/events/memcg.h> +#undef CREATE_TRACE_POINTS + #include <trace/events/vmscan.h> struct cgroup_subsys memory_cgrp_subsys __read_mostly; @@ -114,6 +118,7 @@ struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr) return container_of(vmpr, struct mem_cgroup, vmpressure); } +#define SEQ_BUF_SIZE SZ_4K #define CURRENT_OBJCG_UPDATE_BIT 0 #define CURRENT_OBJCG_UPDATE_FLAG (1UL << CURRENT_OBJCG_UPDATE_BIT) @@ -310,6 +315,9 @@ static const unsigned int memcg_node_stat_items[] = { PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, +#ifdef CONFIG_HUGETLB_PAGE + NR_HUGETLB, +#endif }; static const unsigned int memcg_stat_items[] = { @@ -418,6 +426,8 @@ static const unsigned int memcg_vm_event_stat[] = { PGPGIN, PGPGOUT, #endif + PSWPIN, + PSWPOUT, PGSCAN_KSWAPD, PGSCAN_DIRECT, PGSCAN_KHUGEPAGED, @@ -588,8 +598,16 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) } } -static void do_flush_stats(struct mem_cgroup *memcg) +static void __mem_cgroup_flush_stats(struct mem_cgroup *memcg, bool force) { + bool needs_flush = memcg_vmstats_needs_flush(memcg->vmstats); + + trace_memcg_flush_stats(memcg, atomic64_read(&memcg->vmstats->stats_updates), + force, needs_flush); + + if (!force && !needs_flush) + return; + if (mem_cgroup_is_root(memcg)) WRITE_ONCE(flush_last_time, jiffies_64); @@ -613,8 +631,7 @@ void mem_cgroup_flush_stats(struct mem_cgroup *memcg) if (!memcg) memcg = root_mem_cgroup; - if (memcg_vmstats_needs_flush(memcg->vmstats)) - do_flush_stats(memcg); + __mem_cgroup_flush_stats(memcg, false); } void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) @@ -630,7 +647,7 @@ static void flush_memcg_stats_dwork(struct work_struct *w) * Deliberately ignore memcg_vmstats_needs_flush() here so that flushing * in latency-sensitive paths is as cheap as possible. */ - do_flush_stats(root_mem_cgroup); + __mem_cgroup_flush_stats(root_mem_cgroup, true); queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME); } @@ -684,7 +701,9 @@ void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, return; __this_cpu_add(memcg->vmstats_percpu->state[i], val); - memcg_rstat_updated(memcg, memcg_state_val_in_pages(idx, val)); + val = memcg_state_val_in_pages(idx, val); + memcg_rstat_updated(memcg, val); + trace_mod_memcg_state(memcg, idx, val); } /* idx can be of type enum memcg_stat_item or node_stat_item. */ @@ -743,7 +762,9 @@ static void __mod_memcg_lruvec_state(struct lruvec *lruvec, /* Update lruvec */ __this_cpu_add(pn->lruvec_stats_percpu->state[i], val); - memcg_rstat_updated(memcg, memcg_state_val_in_pages(idx, val)); + val = memcg_state_val_in_pages(idx, val); + memcg_rstat_updated(memcg, val); + trace_mod_memcg_lruvec_state(memcg, idx, val); memcg_stats_unlock(); } @@ -834,6 +855,7 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, memcg_stats_lock(); __this_cpu_add(memcg->vmstats_percpu->events[i], count); memcg_rstat_updated(memcg, count); + trace_count_memcg_events(memcg, idx, count); memcg_stats_unlock(); } @@ -1181,7 +1203,6 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) * These functions are safe to use under any of the following conditions: * - folio locked * - folio_test_lru false - * - folio_memcg_lock() * - folio frozen (refcount of 0) * * Return: The lruvec this folio is on with its lock held. @@ -1203,7 +1224,6 @@ struct lruvec *folio_lruvec_lock(struct folio *folio) * These functions are safe to use under any of the following conditions: * - folio locked * - folio_test_lru false - * - folio_memcg_lock() * - folio frozen (refcount of 0) * * Return: The lruvec this folio is on with its lock held and interrupts @@ -1227,7 +1247,6 @@ struct lruvec *folio_lruvec_lock_irq(struct folio *folio) * These functions are safe to use under any of the following conditions: * - folio locked * - folio_test_lru false - * - folio_memcg_lock() * - folio frozen (refcount of 0) * * Return: The lruvec this folio is on with its lock held and interrupts @@ -1350,6 +1369,9 @@ static const struct memory_stat memory_stats[] = { { "unevictable", NR_UNEVICTABLE }, { "slab_reclaimable", NR_SLAB_RECLAIMABLE_B }, { "slab_unreclaimable", NR_SLAB_UNRECLAIMABLE_B }, +#ifdef CONFIG_HUGETLB_PAGE + { "hugetlb", NR_HUGETLB }, +#endif /* The memory events */ { "workingset_refault_anon", WORKINGSET_REFAULT_ANON }, @@ -1445,6 +1467,11 @@ static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s) for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { u64 size; +#ifdef CONFIG_HUGETLB_PAGE + if (unlikely(memory_stats[i].idx == NR_HUGETLB) && + !(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING)) + continue; +#endif size = memcg_page_state_output(memcg, memory_stats[i].idx); seq_buf_printf(s, "%s %llu\n", memory_stats[i].name, size); @@ -1520,7 +1547,7 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct * void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { /* Use static buffer, for the caller is holding oom_lock. */ - static char buf[PAGE_SIZE]; + static char buf[SEQ_BUF_SIZE]; struct seq_buf s; lockdep_assert_held(&oom_lock); @@ -1546,7 +1573,7 @@ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) pr_info("Memory cgroup stats for "); pr_cont_cgroup_path(memcg->css.cgroup); pr_cont(":"); - seq_buf_init(&s, buf, sizeof(buf)); + seq_buf_init(&s, buf, SEQ_BUF_SIZE); memory_stat_format(memcg, &s); seq_buf_do_printk(&s, KERN_INFO); } @@ -2234,12 +2261,6 @@ retry: */ if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER)) goto retry; - /* - * At task move, charge accounts can be doubly counted. So, it's - * better to wait until the end of task_move if something is going on. - */ - if (memcg1_wait_acct_move(mem_over_limit)) - goto retry; if (nr_retries--) goto retry; @@ -2373,9 +2394,7 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) * * - the page lock * - LRU isolation - * - folio_memcg_lock() * - exclusive reference - * - mem_cgroup_trylock_pages() */ folio->memcg_data = (unsigned long)memcg; } @@ -3102,15 +3121,13 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) if (!parent) parent = root_mem_cgroup; - memcg_reparent_objcgs(memcg, parent); + memcg_reparent_list_lrus(memcg, parent); /* - * After we have finished memcg_reparent_objcgs(), all list_lrus - * corresponding to this cgroup are guaranteed to remain empty. - * The ordering is imposed by list_lru_node->lock taken by - * memcg_reparent_list_lrus(). + * Objcg's reparenting must be after list_lru's, make sure list_lru + * helpers won't use parent's list_lru until child is drained. */ - memcg_reparent_list_lrus(memcg, parent); + memcg_reparent_objcgs(memcg, parent); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -3733,68 +3750,90 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) memcg_wb_domain_size_changed(memcg); } -static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) +struct aggregate_control { + /* pointer to the aggregated (CPU and subtree aggregated) counters */ + long *aggregate; + /* pointer to the non-hierarchichal (CPU aggregated) counters */ + long *local; + /* pointer to the pending child counters during tree propagation */ + long *pending; + /* pointer to the parent's pending counters, could be NULL */ + long *ppending; + /* pointer to the percpu counters to be aggregated */ + long *cstat; + /* pointer to the percpu counters of the last aggregation*/ + long *cstat_prev; + /* size of the above counters */ + int size; +}; + +static void mem_cgroup_stat_aggregate(struct aggregate_control *ac) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent = parent_mem_cgroup(memcg); - struct memcg_vmstats_percpu *statc; + int i; long delta, delta_cpu, v; - int i, nid; - - statc = per_cpu_ptr(memcg->vmstats_percpu, cpu); - for (i = 0; i < MEMCG_VMSTAT_SIZE; i++) { + for (i = 0; i < ac->size; i++) { /* * Collect the aggregated propagation counts of groups * below us. We're in a per-cpu loop here and this is * a global counter, so the first cycle will get them. */ - delta = memcg->vmstats->state_pending[i]; + delta = ac->pending[i]; if (delta) - memcg->vmstats->state_pending[i] = 0; + ac->pending[i] = 0; /* Add CPU changes on this level since the last flush */ delta_cpu = 0; - v = READ_ONCE(statc->state[i]); - if (v != statc->state_prev[i]) { - delta_cpu = v - statc->state_prev[i]; + v = READ_ONCE(ac->cstat[i]); + if (v != ac->cstat_prev[i]) { + delta_cpu = v - ac->cstat_prev[i]; delta += delta_cpu; - statc->state_prev[i] = v; + ac->cstat_prev[i] = v; } /* Aggregate counts on this level and propagate upwards */ if (delta_cpu) - memcg->vmstats->state_local[i] += delta_cpu; + ac->local[i] += delta_cpu; if (delta) { - memcg->vmstats->state[i] += delta; - if (parent) - parent->vmstats->state_pending[i] += delta; + ac->aggregate[i] += delta; + if (ac->ppending) + ac->ppending[i] += delta; } } +} - for (i = 0; i < NR_MEMCG_EVENTS; i++) { - delta = memcg->vmstats->events_pending[i]; - if (delta) - memcg->vmstats->events_pending[i] = 0; - - delta_cpu = 0; - v = READ_ONCE(statc->events[i]); - if (v != statc->events_prev[i]) { - delta_cpu = v - statc->events_prev[i]; - delta += delta_cpu; - statc->events_prev[i] = v; - } +static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct memcg_vmstats_percpu *statc; + struct aggregate_control ac; + int nid; - if (delta_cpu) - memcg->vmstats->events_local[i] += delta_cpu; + statc = per_cpu_ptr(memcg->vmstats_percpu, cpu); - if (delta) { - memcg->vmstats->events[i] += delta; - if (parent) - parent->vmstats->events_pending[i] += delta; - } - } + ac = (struct aggregate_control) { + .aggregate = memcg->vmstats->state, + .local = memcg->vmstats->state_local, + .pending = memcg->vmstats->state_pending, + .ppending = parent ? parent->vmstats->state_pending : NULL, + .cstat = statc->state, + .cstat_prev = statc->state_prev, + .size = MEMCG_VMSTAT_SIZE, + }; + mem_cgroup_stat_aggregate(&ac); + + ac = (struct aggregate_control) { + .aggregate = memcg->vmstats->events, + .local = memcg->vmstats->events_local, + .pending = memcg->vmstats->events_pending, + .ppending = parent ? parent->vmstats->events_pending : NULL, + .cstat = statc->events, + .cstat_prev = statc->events_prev, + .size = NR_MEMCG_EVENTS, + }; + mem_cgroup_stat_aggregate(&ac); for_each_node_state(nid, N_MEMORY) { struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid]; @@ -3807,28 +3846,17 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu); - for (i = 0; i < NR_MEMCG_NODE_STAT_ITEMS; i++) { - delta = lstats->state_pending[i]; - if (delta) - lstats->state_pending[i] = 0; - - delta_cpu = 0; - v = READ_ONCE(lstatc->state[i]); - if (v != lstatc->state_prev[i]) { - delta_cpu = v - lstatc->state_prev[i]; - delta += delta_cpu; - lstatc->state_prev[i] = v; - } - - if (delta_cpu) - lstats->state_local[i] += delta_cpu; + ac = (struct aggregate_control) { + .aggregate = lstats->state, + .local = lstats->state_local, + .pending = lstats->state_pending, + .ppending = plstats ? plstats->state_pending : NULL, + .cstat = lstatc->state, + .cstat_prev = lstatc->state_prev, + .size = NR_MEMCG_NODE_STAT_ITEMS, + }; + mem_cgroup_stat_aggregate(&ac); - if (delta) { - lstats->state[i] += delta; - if (plstats) - plstats->state_pending[i] += delta; - } - } } WRITE_ONCE(statc->stats_updates, 0); /* We are in a per-cpu loop here, only do the atomic write once */ @@ -4189,12 +4217,12 @@ static int memory_events_local_show(struct seq_file *m, void *v) int memory_stat_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + char *buf = kmalloc(SEQ_BUF_SIZE, GFP_KERNEL); struct seq_buf s; if (!buf) return -ENOMEM; - seq_buf_init(&s, buf, PAGE_SIZE); + seq_buf_init(&s, buf, SEQ_BUF_SIZE); memory_stat_format(memcg, &s); seq_puts(m, buf); kfree(buf); @@ -4433,9 +4461,6 @@ struct cgroup_subsys memory_cgrp_subsys = { .exit = mem_cgroup_exit, .dfl_cftypes = memory_files, #ifdef CONFIG_MEMCG_V1 - .can_attach = memcg1_can_attach, - .cancel_attach = memcg1_cancel_attach, - .post_attach = memcg1_move_task, .legacy_cftypes = mem_cgroup_legacy_files, #endif .early_init = 0, @@ -5277,11 +5302,8 @@ bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) break; } - /* - * mem_cgroup_flush_stats() ignores small changes. Use - * do_flush_stats() directly to get accurate stats for charging. - */ - do_flush_stats(memcg); + /* Force flush to get accurate stats for charging */ + __mem_cgroup_flush_stats(memcg, true); pages = memcg_page_state(memcg, MEMCG_ZSWAP_B) / PAGE_SIZE; if (pages < max) continue; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 96ce31e5a203..a7b8ccd29b6f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -100,7 +100,7 @@ static ssize_t _name##_show(struct device *dev, \ { \ struct memory_failure_stats *mf_stats = \ &NODE_DATA(dev->id)->mf_stats; \ - return sprintf(buf, "%lu\n", mf_stats->_name); \ + return sysfs_emit(buf, "%lu\n", mf_stats->_name); \ } \ static DEVICE_ATTR_RO(_name) @@ -445,7 +445,7 @@ static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma, * Schedule a process for later kill. * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. */ -static void __add_to_kill(struct task_struct *tsk, struct page *p, +static void __add_to_kill(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long addr) { @@ -461,7 +461,7 @@ static void __add_to_kill(struct task_struct *tsk, struct page *p, if (is_zone_device_page(p)) tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr); else - tk->size_shift = page_shift(compound_head(p)); + tk->size_shift = folio_shift(page_folio(p)); /* * Send SIGKILL if "tk->addr == -EFAULT". Also, as @@ -486,7 +486,7 @@ static void __add_to_kill(struct task_struct *tsk, struct page *p, list_add_tail(&tk->nd, to_kill); } -static void add_to_kill_anon_file(struct task_struct *tsk, struct page *p, +static void add_to_kill_anon_file(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long addr) { @@ -509,7 +509,7 @@ static bool task_in_to_kill_list(struct list_head *to_kill, return false; } -void add_to_kill_ksm(struct task_struct *tsk, struct page *p, +void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long addr) { @@ -606,8 +606,9 @@ struct task_struct *task_early_kill(struct task_struct *tsk, int force_early) /* * Collect processes when the error hit an anonymous page. */ -static void collect_procs_anon(struct folio *folio, struct page *page, - struct list_head *to_kill, int force_early) +static void collect_procs_anon(const struct folio *folio, + const struct page *page, struct list_head *to_kill, + int force_early) { struct task_struct *tsk; struct anon_vma *av; @@ -617,7 +618,7 @@ static void collect_procs_anon(struct folio *folio, struct page *page, if (av == NULL) /* Not actually mapped anymore */ return; - pgoff = page_to_pgoff(page); + pgoff = page_pgoff(folio, page); rcu_read_lock(); for_each_process(tsk) { struct vm_area_struct *vma; @@ -643,8 +644,9 @@ static void collect_procs_anon(struct folio *folio, struct page *page, /* * Collect processes when the error hit a file mapped page. */ -static void collect_procs_file(struct folio *folio, struct page *page, - struct list_head *to_kill, int force_early) +static void collect_procs_file(const struct folio *folio, + const struct page *page, struct list_head *to_kill, + int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -653,7 +655,7 @@ static void collect_procs_file(struct folio *folio, struct page *page, i_mmap_lock_read(mapping); rcu_read_lock(); - pgoff = page_to_pgoff(page); + pgoff = page_pgoff(folio, page); for_each_process(tsk) { struct task_struct *t = task_early_kill(tsk, force_early); unsigned long addr; @@ -671,7 +673,7 @@ static void collect_procs_file(struct folio *folio, struct page *page, */ if (vma->vm_mm != t->mm) continue; - addr = page_address_in_vma(page, vma); + addr = page_address_in_vma(folio, page, vma); add_to_kill_anon_file(t, page, vma, to_kill, addr); } } @@ -680,7 +682,7 @@ static void collect_procs_file(struct folio *folio, struct page *page, } #ifdef CONFIG_FS_DAX -static void add_to_kill_fsdax(struct task_struct *tsk, struct page *p, +static void add_to_kill_fsdax(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, pgoff_t pgoff) { @@ -691,7 +693,7 @@ static void add_to_kill_fsdax(struct task_struct *tsk, struct page *p, /* * Collect processes when the error hit a fsdax page. */ -static void collect_procs_fsdax(struct page *page, +static void collect_procs_fsdax(const struct page *page, struct address_space *mapping, pgoff_t pgoff, struct list_head *to_kill, bool pre_remove) { @@ -725,7 +727,7 @@ static void collect_procs_fsdax(struct page *page, /* * Collect the processes who have the corrupted page mapped to kill. */ -static void collect_procs(struct folio *folio, struct page *page, +static void collect_procs(const struct folio *folio, const struct page *page, struct list_head *tokill, int force_early) { if (!folio->mapping) diff --git a/mm/memory.c b/mm/memory.c index bdf77a3ec47b..75c2dfd04f72 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1,4 +1,3 @@ - // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c @@ -44,7 +43,6 @@ #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> @@ -1061,8 +1059,7 @@ static inline struct folio *folio_prealloc(struct mm_struct *src_mm, if (need_zero) new_folio = vma_alloc_zeroed_movable_folio(vma, addr); else - new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, - addr, false); + new_folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, addr); if (!new_folio) return NULL; @@ -1085,6 +1082,7 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; + pmd_t dummy_pmdval; pte_t ptent; spinlock_t *src_ptl, *dst_ptl; int progress, max_nr, ret = 0; @@ -1110,7 +1108,15 @@ again: ret = -ENOMEM; goto out; } - src_pte = pte_offset_map_nolock(src_mm, src_pmd, addr, &src_ptl); + + /* + * We already hold the exclusive mmap_lock, the copy_pte_range() and + * retract_page_tables() are using vma->anon_vma to be exclusive, so + * the PTE page is stable, and there is no need to get pmdval and do + * pmd_same() check. + */ + src_pte = pte_offset_map_rw_nolock(src_mm, src_pmd, addr, &dummy_pmdval, + &src_ptl); if (!src_pte) { pte_unmap_unlock(dst_pte, dst_ptl); /* ret == 0 */ @@ -1449,7 +1455,7 @@ static inline bool should_zap_folio(struct zap_details *details, return !folio_test_anon(folio); } -static inline bool zap_drop_file_uffd_wp(struct zap_details *details) +static inline bool zap_drop_markers(struct zap_details *details) { if (!details) return false; @@ -1470,7 +1476,7 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, if (vma_is_anonymous(vma)) return; - if (zap_drop_file_uffd_wp(details)) + if (zap_drop_markers(details)) return; for (;;) { @@ -1665,7 +1671,15 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, * drop the marker if explicitly requested. */ if (!vma_is_anonymous(vma) && - !zap_drop_file_uffd_wp(details)) + !zap_drop_markers(details)) + continue; + } else if (is_guard_swp_entry(entry)) { + /* + * Ordinary zapping should not remove guard PTE + * markers. Only do so if we should remove PTE markers + * in general. + */ + if (!zap_drop_markers(details)) continue; } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { @@ -3997,6 +4011,10 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf) if (marker & PTE_MARKER_POISONED) return VM_FAULT_HWPOISON; + /* Hitting a guard page is always a fatal condition. */ + if (marker & PTE_MARKER_GUARD) + return VM_FAULT_SIGSEGV; + if (pte_marker_entry_uffd_wp(entry)) return pte_marker_handle_uffd_wp(vmf); @@ -4010,8 +4028,7 @@ static struct folio *__alloc_swap_folio(struct vm_fault *vmf) struct folio *folio; swp_entry_t entry; - folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, - vmf->address, false); + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vmf->address); if (!folio) return NULL; @@ -4167,7 +4184,7 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf) gfp = vma_thp_gfp_mask(vma); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); - folio = vma_alloc_folio(gfp, order, vma, addr, true); + folio = vma_alloc_folio(gfp, order, vma, addr); if (folio) { if (!mem_cgroup_swapin_charge_folio(folio, vma->vm_mm, gfp, entry)) @@ -4706,7 +4723,7 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) gfp = vma_thp_gfp_mask(vma); while (orders) { addr = ALIGN_DOWN(vmf->address, PAGE_SIZE << order); - folio = vma_alloc_folio(gfp, order, vma, addr, true); + folio = vma_alloc_folio(gfp, order, vma, addr); if (folio) { if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); @@ -4714,7 +4731,15 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf) goto next; } folio_throttle_swaprate(folio, gfp); - folio_zero_user(folio, vmf->address); + /* + * When a folio is not zeroed during allocation + * (__GFP_ZERO not used), folio_zero_user() is used + * to make sure that the page corresponding to the + * faulting address will be hot in the cache after + * zeroing. + */ + if (!alloc_zeroed()) + folio_zero_user(folio, vmf->address); return folio; } next: @@ -5743,14 +5768,24 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) vmf->pte = NULL; vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID; } else { + pmd_t dummy_pmdval; + /* * A regular pmd is established and it can't morph into a huge * pmd by anon khugepaged, since that takes mmap_lock in write * mode; but shmem or file collapse to THP could still morph * it into a huge pmd: just retry later if so. + * + * Use the maywrite version to indicate that vmf->pte may be + * modified, but since we will use pte_same() to detect the + * change of the !pte_none() entry, there is no need to recheck + * the pmdval. Here we chooes to pass a dummy variable instead + * of NULL, which helps new user think about why this place is + * special. */ - vmf->pte = pte_offset_map_nolock(vmf->vma->vm_mm, vmf->pmd, - vmf->address, &vmf->ptl); + vmf->pte = pte_offset_map_rw_nolock(vmf->vma->vm_mm, vmf->pmd, + vmf->address, &dummy_pmdval, + &vmf->ptl); if (unlikely(!vmf->pte)) return 0; vmf->orig_pte = ptep_get_lockless(vmf->pte); @@ -6365,7 +6400,7 @@ static inline void pfnmap_lockdep_assert(struct vm_area_struct *vma) struct address_space *mapping = file ? file->f_mapping : NULL; if (mapping) - lockdep_assert(lockdep_is_held(&vma->vm_file->f_mapping->i_mmap_rwsem) || + lockdep_assert(lockdep_is_held(&mapping->i_mmap_rwsem) || lockdep_is_held(&vma->vm_mm->mmap_lock)); else lockdep_assert(lockdep_is_held(&vma->vm_mm->mmap_lock)); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 621ae1015106..c43b4e7fb298 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1681,7 +1681,7 @@ struct range __weak arch_get_mappable_range(void) struct range mhp_get_pluggable_range(bool need_mapping) { - const u64 max_phys = PHYSMEM_END; + const u64 max_phys = DIRECT_MAP_PHYSMEM_END; struct range mhp_range; if (need_mapping) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b646fab3e45e..bb37cd1a51d8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -8,7 +8,7 @@ * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * - * Support four policies per VMA and per process: + * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * @@ -1367,7 +1367,7 @@ static long do_mbind(unsigned long start, unsigned long len, if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { - addr = page_address_in_vma( + addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; @@ -2290,7 +2290,6 @@ struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. - * @hugepage: Unused (was: For hugepages try only preferred node if possible). * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the @@ -2301,7 +2300,7 @@ struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, bool hugepage) + unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; diff --git a/mm/migrate.c b/mm/migrate.c index 47a8d102ae7a..2ce6b4b814df 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -695,6 +695,7 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) if (folio_test_idle(folio)) folio_set_idle(newfolio); + folio_migrate_refs(newfolio, folio); /* * Copy NUMA information to the new page, to prevent over-eager * future migrations of this same page. @@ -1732,7 +1733,7 @@ static int migrate_pages_batch(struct list_head *from, list_for_each_entry_safe(folio, folio2, from, lru) { is_large = folio_test_large(folio); - is_thp = is_large && folio_test_pmd_mappable(folio); + is_thp = folio_test_pmd_mappable(folio); nr_pages = folio_nr_pages(folio); cond_resched(); diff --git a/mm/mm_init.c b/mm/mm_init.c index 4ba5607aaf19..1c205b0a86ed 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -83,8 +83,7 @@ void __init mminit_verify_pageflags_layout(void) unsigned long or_mask, add_mask; shift = BITS_PER_LONG; - width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH - - LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH - LRU_GEN_WIDTH - LRU_REFS_WIDTH; + width = shift - NR_NON_PAGEFLAG_BITS; mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths", "Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Gen %d Tier %d Flags %d\n", SECTIONS_WIDTH, @@ -2639,7 +2638,7 @@ void __init mm_core_init(void) BUILD_BUG_ON(MAX_ZONELISTS > 2); build_all_zonelists(NULL); page_alloc_init_cpuhp(); - + alloc_tag_sec_init(); /* * page_ext requires contiguous pages, * bigger than MAX_PAGE_ORDER unless SPARSEMEM. diff --git a/mm/mmap.c b/mm/mmap.c index 79d541f1502b..386429f7db5a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -577,22 +577,6 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ -/* - * We account for memory if it's a private writeable mapping, - * not hugepages and VM_NORESERVE wasn't set. - */ -static inline bool accountable_mapping(struct file *file, vm_flags_t vm_flags) -{ - /* - * hugetlb has its own accounting separate from the core VM - * VM_HUGETLB may not be set yet so we cannot check for that flag. - */ - if (file && is_file_hugepages(file)) - return false; - - return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; -} - /** * unmapped_area() - Find an area between the low_limit and the high_limit with * the correct alignment and offset, all from @info. Note: current->mm is used @@ -776,6 +760,8 @@ generic_get_unmapped_area(struct file *filp, unsigned long addr, info.low_limit = mm->mmap_base; info.high_limit = mmap_end; info.start_gap = stack_guard_placement(vm_flags); + if (filp && is_file_hugepages(filp)) + info.align_mask = huge_page_mask_align(filp); return vm_unmapped_area(&info); } @@ -826,6 +812,8 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.start_gap = stack_guard_placement(vm_flags); + if (filp && is_file_hugepages(filp)) + info.align_mask = huge_page_mask_align(filp); addr = vm_unmapped_area(&info); /* @@ -1051,6 +1039,8 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; + mmap_assert_write_locked(mm); + /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; if (address >= (TASK_SIZE & PAGE_MASK)) @@ -1086,11 +1076,7 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); - /* - * vma->vm_start/vm_end cannot change under us because the caller - * is required to hold the mmap_lock in read mode. We need the - * anon_vma lock to serialize against concurrent expand_stacks. - */ + /* We update the anon VMA tree. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ @@ -1104,16 +1090,6 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { - /* - * We only hold a shared mmap_lock lock here, so - * we need to protect against concurrent vma - * expansions. anon_vma_lock_write() doesn't - * help here, as we don't guarantee that all - * growable vmas in a mm share the same root - * anon vma. So, we reuse mm->page_table_lock - * to guard against concurrent vma expansions. - */ - spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); @@ -1122,7 +1098,6 @@ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) /* Overwrite old entry in mtree. */ vma_iter_store(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); - spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } @@ -1149,6 +1124,8 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) if (!(vma->vm_flags & VM_GROWSDOWN)) return -EFAULT; + mmap_assert_write_locked(mm); + address &= PAGE_MASK; if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) return -EPERM; @@ -1178,11 +1155,7 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); - /* - * vma->vm_start/vm_end cannot change under us because the caller - * is required to hold the mmap_lock in read mode. We need the - * anon_vma lock to serialize against concurrent expand_stacks. - */ + /* We update the anon VMA tree. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ @@ -1196,16 +1169,6 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { - /* - * We only hold a shared mmap_lock lock here, so - * we need to protect against concurrent vma - * expansions. anon_vma_lock_write() doesn't - * help here, as we don't guarantee that all - * growable vmas in a mm share the same root - * anon vma. So, we reuse mm->page_table_lock - * to guard against concurrent vma expansions. - */ - spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); @@ -1215,7 +1178,6 @@ int expand_downwards(struct vm_area_struct *vma, unsigned long address) /* Overwrite old entry in mtree. */ vma_iter_store(&vmi, vma); anon_vma_interval_tree_post_update_vma(vma); - spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } @@ -1358,224 +1320,6 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, return do_vmi_munmap(&vmi, mm, start, len, uf, false); } -static unsigned long __mmap_region(struct file *file, unsigned long addr, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, - struct list_head *uf) -{ - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma = NULL; - pgoff_t pglen = PHYS_PFN(len); - unsigned long charged = 0; - struct vma_munmap_struct vms; - struct ma_state mas_detach; - struct maple_tree mt_detach; - unsigned long end = addr + len; - int error; - VMA_ITERATOR(vmi, mm, addr); - VMG_STATE(vmg, mm, &vmi, addr, end, vm_flags, pgoff); - - vmg.file = file; - /* Find the first overlapping VMA */ - vma = vma_find(&vmi, end); - init_vma_munmap(&vms, &vmi, vma, addr, end, uf, /* unlock = */ false); - if (vma) { - mt_init_flags(&mt_detach, vmi.mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); - mt_on_stack(mt_detach); - mas_init(&mas_detach, &mt_detach, /* addr = */ 0); - /* Prepare to unmap any existing mapping in the area */ - error = vms_gather_munmap_vmas(&vms, &mas_detach); - if (error) - goto gather_failed; - - vmg.next = vms.next; - vmg.prev = vms.prev; - vma = NULL; - } else { - vmg.next = vma_iter_next_rewind(&vmi, &vmg.prev); - } - - /* Check against address space limit. */ - if (!may_expand_vm(mm, vm_flags, pglen - vms.nr_pages)) { - error = -ENOMEM; - goto abort_munmap; - } - - /* - * Private writable mapping: check memory availability - */ - if (accountable_mapping(file, vm_flags)) { - charged = pglen; - charged -= vms.nr_accounted; - if (charged) { - error = security_vm_enough_memory_mm(mm, charged); - if (error) - goto abort_munmap; - } - - vms.nr_accounted = 0; - vm_flags |= VM_ACCOUNT; - vmg.flags = vm_flags; - } - - /* - * clear PTEs while the vma is still in the tree so that rmap - * cannot race with the freeing later in the truncate scenario. - * This is also needed for mmap_file(), which is why vm_ops - * close function is called. - */ - vms_clean_up_area(&vms, &mas_detach); - vma = vma_merge_new_range(&vmg); - if (vma) - goto expanded; - /* - * Determine the object being mapped and call the appropriate - * specific mapper. the address has already been validated, but - * not unmapped, but the maps are removed from the list. - */ - vma = vm_area_alloc(mm); - if (!vma) { - error = -ENOMEM; - goto unacct_error; - } - - vma_iter_config(&vmi, addr, end); - vma_set_range(vma, addr, end, pgoff); - vm_flags_init(vma, vm_flags); - vma->vm_page_prot = vm_get_page_prot(vm_flags); - - if (vma_iter_prealloc(&vmi, vma)) { - error = -ENOMEM; - goto free_vma; - } - - if (file) { - vma->vm_file = get_file(file); - error = mmap_file(file, vma); - if (error) - goto unmap_and_free_file_vma; - - /* Drivers cannot alter the address of the VMA. */ - WARN_ON_ONCE(addr != vma->vm_start); - /* - * Drivers should not permit writability when previously it was - * disallowed. - */ - VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && - !(vm_flags & VM_MAYWRITE) && - (vma->vm_flags & VM_MAYWRITE)); - - vma_iter_config(&vmi, addr, end); - /* - * If vm_flags changed after mmap_file(), we should try merge - * vma again as we may succeed this time. - */ - if (unlikely(vm_flags != vma->vm_flags && vmg.prev)) { - struct vm_area_struct *merge; - - vmg.flags = vma->vm_flags; - /* If this fails, state is reset ready for a reattempt. */ - merge = vma_merge_new_range(&vmg); - - if (merge) { - /* - * ->mmap() can change vma->vm_file and fput - * the original file. So fput the vma->vm_file - * here or we would add an extra fput for file - * and cause general protection fault - * ultimately. - */ - fput(vma->vm_file); - vm_area_free(vma); - vma = merge; - /* Update vm_flags to pick up the change. */ - vm_flags = vma->vm_flags; - goto file_expanded; - } - vma_iter_config(&vmi, addr, end); - } - - vm_flags = vma->vm_flags; - } else if (vm_flags & VM_SHARED) { - error = shmem_zero_setup(vma); - if (error) - goto free_iter_vma; - } else { - vma_set_anonymous(vma); - } - -#ifdef CONFIG_SPARC64 - /* TODO: Fix SPARC ADI! */ - WARN_ON_ONCE(!arch_validate_flags(vm_flags)); -#endif - - /* Lock the VMA since it is modified after insertion into VMA tree */ - vma_start_write(vma); - vma_iter_store(&vmi, vma); - mm->map_count++; - vma_link_file(vma); - - /* - * vma_merge_new_range() calls khugepaged_enter_vma() too, the below - * call covers the non-merge case. - */ - khugepaged_enter_vma(vma, vma->vm_flags); - -file_expanded: - file = vma->vm_file; - ksm_add_vma(vma); -expanded: - perf_event_mmap(vma); - - /* Unmap any existing mapping in the area */ - vms_complete_munmap_vmas(&vms, &mas_detach); - - vm_stat_account(mm, vm_flags, pglen); - if (vm_flags & VM_LOCKED) { - if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || - is_vm_hugetlb_page(vma) || - vma == get_gate_vma(current->mm)) - vm_flags_clear(vma, VM_LOCKED_MASK); - else - mm->locked_vm += pglen; - } - - if (file) - uprobe_mmap(vma); - - /* - * New (or expanded) vma always get soft dirty status. - * Otherwise user-space soft-dirty page tracker won't - * be able to distinguish situation when vma area unmapped, - * then new mapped in-place (which must be aimed as - * a completely new data area). - */ - vm_flags_set(vma, VM_SOFTDIRTY); - - vma_set_page_prot(vma); - - return addr; - -unmap_and_free_file_vma: - fput(vma->vm_file); - vma->vm_file = NULL; - - vma_iter_set(&vmi, vma->vm_end); - /* Undo any partial mapping done by a device driver. */ - unmap_region(&vmi.mas, vma, vmg.prev, vmg.next); -free_iter_vma: - vma_iter_free(&vmi); -free_vma: - vm_area_free(vma); -unacct_error: - if (charged) - vm_unacct_memory(charged); - -abort_munmap: - vms_abort_munmap_vmas(&vms, &mas_detach); -gather_failed: - return error; -} - unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index 368b840e7508..f186d57df2c6 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -19,43 +19,23 @@ EXPORT_TRACEPOINT_SYMBOL(mmap_lock_released); #ifdef CONFIG_MEMCG -static atomic_t reg_refcount; - /* * Size of the buffer for memcg path names. Ignoring stack trace support, * trace_events_hist.c uses MAX_FILTER_STR_VAL for this, so we also use it. */ #define MEMCG_PATH_BUF_SIZE MAX_FILTER_STR_VAL -int trace_mmap_lock_reg(void) -{ - atomic_inc(®_refcount); - return 0; -} - -void trace_mmap_lock_unreg(void) -{ - atomic_dec(®_refcount); -} - -#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ - do { \ - char buf[MEMCG_PATH_BUF_SIZE]; \ - get_mm_memcg_path(mm, buf, sizeof(buf)); \ - trace_mmap_lock_##type(mm, buf, ##__VA_ARGS__); \ +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ + do { \ + if (trace_mmap_lock_##type##_enabled()) { \ + char buf[MEMCG_PATH_BUF_SIZE]; \ + get_mm_memcg_path(mm, buf, sizeof(buf)); \ + trace_mmap_lock_##type(mm, buf, ##__VA_ARGS__); \ + } \ } while (0) #else /* !CONFIG_MEMCG */ -int trace_mmap_lock_reg(void) -{ - return 0; -} - -void trace_mmap_lock_unreg(void) -{ -} - #define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ trace_mmap_lock_##type(mm, "", ##__VA_ARGS__) @@ -65,16 +45,13 @@ void trace_mmap_lock_unreg(void) #ifdef CONFIG_MEMCG /* * Write the given mm_struct's memcg path to a buffer. If the path cannot be - * determined or the trace event is being unregistered, empty string is written. + * determined, empty string is written. */ static void get_mm_memcg_path(struct mm_struct *mm, char *buf, size_t buflen) { struct mem_cgroup *memcg; buf[0] = '\0'; - /* No need to get path if no trace event is registered. */ - if (!atomic_read(®_refcount)) - return; memcg = get_mem_cgroup_from_mm(mm); if (memcg == NULL) return; diff --git a/mm/mprotect.c b/mm/mprotect.c index 6f450af3252e..516b1d847e2c 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -236,9 +236,11 @@ static long change_pte_range(struct mmu_gather *tlb, } else if (is_pte_marker_entry(entry)) { /* * Ignore error swap entries unconditionally, - * because any access should sigbus anyway. + * because any access should sigbus/sigsegv + * anyway. */ - if (is_poisoned_swp_entry(entry)) + if (is_poisoned_swp_entry(entry) || + is_guard_swp_entry(entry)) continue; /* * If this is uffd-wp pte marker and we'd like diff --git a/mm/mremap.c b/mm/mremap.c index dee98ff2bbd6..60473413836b 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -140,6 +140,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, { struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; + pmd_t dummy_pmdval; spinlock_t *old_ptl, *new_ptl; bool force_flush = false; unsigned long len = old_end - old_addr; @@ -175,7 +176,15 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, err = -EAGAIN; goto out; } - new_pte = pte_offset_map_nolock(mm, new_pmd, new_addr, &new_ptl); + /* + * Now new_pte is none, so hpage_collapse_scan_file() path can not find + * this by traversing file->f_mapping, so there is no concurrency with + * retract_page_tables(). In addition, we already hold the exclusive + * mmap_lock, so this new_pte page is stable, so there is no need to get + * pmdval and do pmd_same() check. + */ + new_pte = pte_offset_map_rw_nolock(mm, new_pmd, new_addr, &dummy_pmdval, + &new_ptl); if (!new_pte) { pte_unmap_unlock(old_pte, old_ptl); err = -EAGAIN; @@ -817,17 +826,24 @@ static unsigned long move_vma(struct vm_area_struct *vma, return new_addr; } -static struct vm_area_struct *vma_to_resize(unsigned long addr, +/* + * resize_is_valid() - Ensure the vma can be resized to the new length at the give + * address. + * + * @vma: The vma to resize + * @addr: The old address + * @old_len: The current size + * @new_len: The desired size + * @flags: The vma flags + * + * Return 0 on success, error otherwise. + */ +static int resize_is_valid(struct vm_area_struct *vma, unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; unsigned long pgoff; - vma = vma_lookup(mm, addr); - if (!vma) - return ERR_PTR(-EFAULT); - /* * !old_len is a special case where an attempt is made to 'duplicate' * a mapping. This makes no sense for private mappings as it will @@ -838,39 +854,53 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, */ if (!old_len && !(vma->vm_flags & (VM_SHARED | VM_MAYSHARE))) { pr_warn_once("%s (%d): attempted to duplicate a private mapping with mremap. This is not supported.\n", current->comm, current->pid); - return ERR_PTR(-EINVAL); + return -EINVAL; } if ((flags & MREMAP_DONTUNMAP) && (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))) - return ERR_PTR(-EINVAL); + return -EINVAL; /* We can't remap across vm area boundaries */ if (old_len > vma->vm_end - addr) - return ERR_PTR(-EFAULT); + return -EFAULT; if (new_len == old_len) - return vma; + return 0; /* Need to be careful about a growing mapping */ pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; if (pgoff + (new_len >> PAGE_SHIFT) < pgoff) - return ERR_PTR(-EINVAL); + return -EINVAL; if (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP)) - return ERR_PTR(-EFAULT); + return -EFAULT; if (!mlock_future_ok(mm, vma->vm_flags, new_len - old_len)) - return ERR_PTR(-EAGAIN); + return -EAGAIN; if (!may_expand_vm(mm, vma->vm_flags, (new_len - old_len) >> PAGE_SHIFT)) - return ERR_PTR(-ENOMEM); + return -ENOMEM; - return vma; + return 0; } +/* + * mremap_to() - remap a vma to a new location + * @addr: The old address + * @old_len: The old size + * @new_addr: The target address + * @new_len: The new size + * @locked: If the returned vma is locked (VM_LOCKED) + * @flags: the mremap flags + * @uf: The mremap userfaultfd context + * @uf_unmap_early: The userfaultfd unmap early context + * @uf_unmap: The userfaultfd unmap context + * + * Returns: The new address of the vma or an error. + */ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, unsigned long new_addr, unsigned long new_len, bool *locked, unsigned long flags, struct vm_userfaultfd_ctx *uf, @@ -879,18 +909,18 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - unsigned long ret = -EINVAL; + unsigned long ret; unsigned long map_flags = 0; if (offset_in_page(new_addr)) - goto out; + return -EINVAL; if (new_len > TASK_SIZE || new_addr > TASK_SIZE - new_len) - goto out; + return -EINVAL; /* Ensure the old/new locations do not overlap */ if (addr + old_len > new_addr && new_addr + new_len > addr) - goto out; + return -EINVAL; /* * move_vma() need us to stay 4 maps below the threshold, otherwise @@ -917,27 +947,28 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, */ ret = do_munmap(mm, new_addr, new_len, uf_unmap_early); if (ret) - goto out; + return ret; } if (old_len > new_len) { ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap); if (ret) - goto out; + return ret; old_len = new_len; } - vma = vma_to_resize(addr, old_len, new_len, flags); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto out; - } + vma = vma_lookup(mm, addr); + if (!vma) + return -EFAULT; + + ret = resize_is_valid(vma, addr, old_len, new_len, flags); + if (ret) + return ret; /* MREMAP_DONTUNMAP expands by old_len since old_len == new_len */ if (flags & MREMAP_DONTUNMAP && !may_expand_vm(mm, vma->vm_flags, old_len >> PAGE_SHIFT)) { - ret = -ENOMEM; - goto out; + return -ENOMEM; } if (flags & MREMAP_FIXED) @@ -950,17 +981,14 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, ((addr - vma->vm_start) >> PAGE_SHIFT), map_flags); if (IS_ERR_VALUE(ret)) - goto out; + return ret; /* We got a new mapping */ if (!(flags & MREMAP_FIXED)) new_addr = ret; - ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, flags, uf, - uf_unmap); - -out: - return ret; + return move_vma(vma, addr, old_len, new_len, new_addr, locked, flags, + uf, uf_unmap); } static int vma_expandable(struct vm_area_struct *vma, unsigned long delta) @@ -1105,11 +1133,9 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, /* * Ok, we need to grow.. */ - vma = vma_to_resize(addr, old_len, new_len, flags); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); + ret = resize_is_valid(vma, addr, old_len, new_len, flags); + if (ret) goto out; - } /* old_len exactly to the end of the area.. */ diff --git a/mm/mseal.c b/mm/mseal.c index ece977bd21e1..81d6e980e8a9 100644 --- a/mm/mseal.c +++ b/mm/mseal.c @@ -30,6 +30,7 @@ static bool is_madv_discard(int behavior) case MADV_REMOVE: case MADV_DONTFORK: case MADV_WIPEONFORK: + case MADV_GUARD_INSTALL: return true; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 4d7a0004df2c..1c485beb0b93 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -24,7 +24,6 @@ #include <linux/gfp.h> #include <linux/sched.h> #include <linux/sched/mm.h> -#include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/sched/debug.h> #include <linux/swap.h> diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 72a5d8836425..fdb89ce85fff 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -917,7 +917,9 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, unsigned long thresh) { struct wb_domain *dom = dtc_dom(dtc); + struct bdi_writeback *wb = dtc->wb; u64 wb_thresh; + u64 wb_max_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; @@ -931,11 +933,28 @@ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); - wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); + wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); - if (wb_thresh > (thresh * wb_max_ratio) / (100 * BDI_RATIO_SCALE)) - wb_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); + wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); + if (wb_thresh > wb_max_thresh) + wb_thresh = wb_max_thresh; + + /* + * With strictlimit flag, the wb_thresh is treated as + * a hard limit in balance_dirty_pages() and wb_position_ratio(). + * It's possible that wb_thresh is close to zero, not because + * the device is slow, but because it has been inactive. + * To prevent occasional writes from being blocked, we raise wb_thresh. + */ + if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { + unsigned long limit = hard_dirty_limit(dom, dtc->thresh); + u64 wb_scale_thresh = 0; + + if (limit > dtc->dirty) + wb_scale_thresh = (limit - dtc->dirty) / 100; + wb_thresh = max(wb_thresh, min(wb_scale_thresh, wb_max_thresh / 4)); + } return wb_thresh; } @@ -2724,8 +2743,6 @@ EXPORT_SYMBOL(noop_dirty_folio); /* * Helper function for set_page_dirty family. * - * Caller must hold folio_memcg_lock(). - * * NOTE: This relies on being atomic wrt interrupts. */ static void folio_account_dirtied(struct folio *folio, @@ -2758,7 +2775,6 @@ static void folio_account_dirtied(struct folio *folio, /* * Helper function for deaccounting dirty page without writeback. * - * Caller must hold folio_memcg_lock(). */ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) { @@ -2776,9 +2792,8 @@ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * - * The caller must hold folio_memcg_lock(). It is the caller's - * responsibility to prevent the folio from being truncated while - * this function is in progress, although it may have been truncated + * It is the caller's responsibility to prevent the folio from being truncated + * while this function is in progress, although it may have been truncated * before this function is called. Most callers have the folio locked. * A few have the folio blocked from truncation through other means (e.g. * zap_vma_pages() has it mapped and is holding the page table lock). @@ -2822,14 +2837,10 @@ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, */ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { - folio_memcg_lock(folio); - if (folio_test_set_dirty(folio)) { - folio_memcg_unlock(folio); + if (folio_test_set_dirty(folio)) return false; - } __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); - folio_memcg_unlock(folio); if (mapping->host) { /* !PageAnon && !swapper_space */ @@ -2956,14 +2967,12 @@ void __folio_cancel_dirty(struct folio *folio) struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; - folio_memcg_lock(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie); - folio_memcg_unlock(folio); } else { folio_clear_dirty(folio); } @@ -3074,7 +3083,6 @@ bool __folio_end_writeback(struct folio *folio) struct address_space *mapping = folio_mapping(folio); bool ret; - folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -3105,7 +3113,6 @@ bool __folio_end_writeback(struct folio *folio) lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); node_stat_mod_folio(folio, NR_WRITTEN, nr); - folio_memcg_unlock(folio); return ret; } @@ -3118,7 +3125,6 @@ void __folio_start_writeback(struct folio *folio, bool keep_write) VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); - folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; @@ -3159,7 +3165,6 @@ void __folio_start_writeback(struct folio *folio, bool keep_write) lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); - folio_memcg_unlock(folio); access_ret = arch_make_folio_accessible(folio); /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 119a3a52f96e..1cb4b8c8886d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5377,7 +5377,7 @@ void __ref build_all_zonelists(pg_data_t *pgdat) pr_info("Built %u zonelists, mobility grouping %s. Total pages: %ld\n", nr_online_nodes, - page_group_by_mobility_disabled ? "off" : "on", + str_off_on(page_group_by_mobility_disabled), vm_total_pages); #ifdef CONFIG_NUMA pr_info("Policy zone: %s\n", zone_names[policy_zone]); diff --git a/mm/page_io.c b/mm/page_io.c index 01749b99fb54..4b4ea8e49cf6 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -277,6 +277,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) swap_zeromap_folio_clear(folio); } if (zswap_store(folio)) { + count_mthp_stat(folio_order(folio), MTHP_STAT_ZSWPOUT); folio_unlock(folio); return 0; } @@ -296,8 +297,9 @@ static inline void count_swpout_vm_event(struct folio *folio) count_memcg_folio_events(folio, THP_SWPOUT, 1); count_vm_event(THP_SWPOUT); } - count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT); #endif + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT); + count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio)); count_vm_events(PSWPOUT, folio_nr_pages(folio)); } @@ -493,6 +495,8 @@ static void sio_read_complete(struct kiocb *iocb, long ret) for (p = 0; p < sio->pages; p++) { struct folio *folio = page_folio(sio->bvec[p].bv_page); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); + count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); folio_mark_uptodate(folio); folio_unlock(folio); } @@ -586,6 +590,8 @@ static void swap_read_folio_bdev_sync(struct folio *folio, * attempt to access it in the page fault retry time check. */ get_task_struct(current); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); + count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio_wait(&bio); __end_swap_bio_read(&bio); @@ -601,6 +607,8 @@ static void swap_read_folio_bdev_async(struct folio *folio, bio->bi_iter.bi_sector = swap_folio_sector(folio); bio->bi_end_io = end_swap_bio_read; bio_add_folio_nofail(bio, folio, folio_size(folio), 0); + count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN); + count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio)); count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio(bio); } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index ae5cc42aa208..81839a9e74f1 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -13,7 +13,8 @@ static inline bool not_found(struct page_vma_mapped_walk *pvmw) return false; } -static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp) +static bool map_pte(struct page_vma_mapped_walk *pvmw, pmd_t *pmdvalp, + spinlock_t **ptlp) { pte_t ptent; @@ -25,6 +26,7 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp) return !!pvmw->pte; } +again: /* * It is important to return the ptl corresponding to pte, * in case *pvmw->pmd changes underneath us; so we need to @@ -32,8 +34,8 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp) * proceeds to loop over next ptes, and finds a match later. * Though, in most cases, page lock already protects this. */ - pvmw->pte = pte_offset_map_nolock(pvmw->vma->vm_mm, pvmw->pmd, - pvmw->address, ptlp); + pvmw->pte = pte_offset_map_rw_nolock(pvmw->vma->vm_mm, pvmw->pmd, + pvmw->address, pmdvalp, ptlp); if (!pvmw->pte) return false; @@ -67,8 +69,13 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp) } else if (!pte_present(ptent)) { return false; } + spin_lock(*ptlp); + if (unlikely(!pmd_same(*pmdvalp, pmdp_get_lockless(pvmw->pmd)))) { + pte_unmap_unlock(pvmw->pte, *ptlp); + goto again; + } pvmw->ptl = *ptlp; - spin_lock(pvmw->ptl); + return true; } @@ -278,7 +285,7 @@ restart: step_forward(pvmw, PMD_SIZE); continue; } - if (!map_pte(pvmw, &ptl)) { + if (!map_pte(pvmw, &pmde, &ptl)) { if (!pvmw->pte) goto restart; goto next_pte; @@ -305,8 +312,13 @@ next_pte: } while (pte_none(ptep_get(pvmw->pte))); if (!pvmw->ptl) { + spin_lock(ptl); + if (unlikely(!pmd_same(pmde, pmdp_get_lockless(pvmw->pmd)))) { + pte_unmap_unlock(pvmw->pte, ptl); + pvmw->pte = NULL; + goto restart; + } pvmw->ptl = ptl; - spin_lock(pvmw->ptl); } goto this_pte; } while (pvmw->address < end); @@ -325,10 +337,10 @@ next_pte: * outside the VMA or not present, returns -EFAULT. * Only valid for normal file or anonymous VMAs. */ -unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) +unsigned long page_mapped_in_vma(const struct page *page, + struct vm_area_struct *vma) { - struct folio *folio = page_folio(page); - pgoff_t pgoff = folio->index + folio_page_idx(folio, page); + const struct folio *folio = page_folio(page); struct page_vma_mapped_walk pvmw = { .pfn = page_to_pfn(page), .nr_pages = 1, @@ -336,7 +348,7 @@ unsigned long page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) .flags = PVMW_SYNC, }; - pvmw.address = vma_address(vma, pgoff, 1); + pvmw.address = vma_address(vma, page_pgoff(folio, page), 1); if (pvmw.address == -EFAULT) goto out; if (!page_vma_mapped_walk(&pvmw)) diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 5f9f01532e67..e478777c86e1 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -3,9 +3,14 @@ #include <linux/highmem.h> #include <linux/sched.h> #include <linux/hugetlb.h> +#include <linux/mmu_context.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <asm/tlbflush.h> + +#include "internal.h" + /* * We want to know the real level where a entry is located ignoring any * folding of levels which may be happening. For example if p4d is folded then @@ -29,9 +34,23 @@ static int walk_pte_range_inner(pte_t *pte, unsigned long addr, int err = 0; for (;;) { - err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); - if (err) - break; + if (ops->install_pte && pte_none(ptep_get(pte))) { + pte_t new_pte; + + err = ops->install_pte(addr, addr + PAGE_SIZE, &new_pte, + walk); + if (err) + break; + + set_pte_at(walk->mm, addr, pte, new_pte); + /* Non-present before, so for arches that need it. */ + if (!WARN_ON_ONCE(walk->no_vma)) + update_mmu_cache(walk->vma, addr, pte); + } else { + err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); + if (err) + break; + } if (addr >= end - PAGE_SIZE) break; addr += PAGE_SIZE; @@ -81,6 +100,8 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pmd_t *pmd; unsigned long next; const struct mm_walk_ops *ops = walk->ops; + bool has_handler = ops->pte_entry; + bool has_install = ops->install_pte; int err = 0; int depth = real_depth(3); @@ -89,11 +110,14 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, again: next = pmd_addr_end(addr, end); if (pmd_none(*pmd)) { - if (ops->pte_hole) + if (has_install) + err = __pte_alloc(walk->mm, pmd); + else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; - continue; + if (!has_install) + continue; } walk->action = ACTION_SUBTREE; @@ -109,18 +133,25 @@ again: if (walk->action == ACTION_AGAIN) goto again; - - /* - * Check this here so we only break down trans_huge - * pages when we _need_ to - */ - if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) || - walk->action == ACTION_CONTINUE || - !(ops->pte_entry)) + if (walk->action == ACTION_CONTINUE) continue; + if (!has_handler) { /* No handlers for lower page tables. */ + if (!has_install) + continue; /* Nothing to do. */ + /* + * We are ONLY installing, so avoid unnecessarily + * splitting a present huge page. + */ + if (pmd_present(*pmd) && + (pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) + continue; + } + if (walk->vma) split_huge_pmd(walk->vma, pmd, addr); + else if (pmd_leaf(*pmd) || !pmd_present(*pmd)) + continue; /* Nothing to do. */ err = walk_pte_range(pmd, addr, next, walk); if (err) @@ -140,6 +171,8 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pud_t *pud; unsigned long next; const struct mm_walk_ops *ops = walk->ops; + bool has_handler = ops->pmd_entry || ops->pte_entry; + bool has_install = ops->install_pte; int err = 0; int depth = real_depth(2); @@ -148,11 +181,14 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, again: next = pud_addr_end(addr, end); if (pud_none(*pud)) { - if (ops->pte_hole) + if (has_install) + err = __pmd_alloc(walk->mm, pud, addr); + else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; - continue; + if (!has_install) + continue; } walk->action = ACTION_SUBTREE; @@ -164,14 +200,26 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (walk->action == ACTION_AGAIN) goto again; - - if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) || - walk->action == ACTION_CONTINUE || - !(ops->pmd_entry || ops->pte_entry)) + if (walk->action == ACTION_CONTINUE) continue; + if (!has_handler) { /* No handlers for lower page tables. */ + if (!has_install) + continue; /* Nothing to do. */ + /* + * We are ONLY installing, so avoid unnecessarily + * splitting a present huge page. + */ + if (pud_present(*pud) && + (pud_trans_huge(*pud) || pud_devmap(*pud))) + continue; + } + if (walk->vma) split_huge_pud(walk->vma, pud, addr); + else if (pud_leaf(*pud) || !pud_present(*pud)) + continue; /* Nothing to do. */ + if (pud_none(*pud)) goto again; @@ -189,6 +237,8 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, p4d_t *p4d; unsigned long next; const struct mm_walk_ops *ops = walk->ops; + bool has_handler = ops->pud_entry || ops->pmd_entry || ops->pte_entry; + bool has_install = ops->install_pte; int err = 0; int depth = real_depth(1); @@ -196,18 +246,21 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) { - if (ops->pte_hole) + if (has_install) + err = __pud_alloc(walk->mm, p4d, addr); + else if (ops->pte_hole) err = ops->pte_hole(addr, next, depth, walk); if (err) break; - continue; + if (!has_install) + continue; } if (ops->p4d_entry) { err = ops->p4d_entry(p4d, addr, next, walk); if (err) break; } - if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) + if (has_handler || has_install) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -222,6 +275,9 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, pgd_t *pgd; unsigned long next; const struct mm_walk_ops *ops = walk->ops; + bool has_handler = ops->p4d_entry || ops->pud_entry || ops->pmd_entry || + ops->pte_entry; + bool has_install = ops->install_pte; int err = 0; if (walk->pgd) @@ -231,18 +287,21 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) { - if (ops->pte_hole) + if (has_install) + err = __p4d_alloc(walk->mm, pgd, addr); + else if (ops->pte_hole) err = ops->pte_hole(addr, next, 0, walk); if (err) break; - continue; + if (!has_install) + continue; } if (ops->pgd_entry) { err = ops->pgd_entry(pgd, addr, next, walk); if (err) break; } - if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry) + if (has_handler || has_install) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; @@ -334,6 +393,11 @@ static int __walk_page_range(unsigned long start, unsigned long end, int err = 0; struct vm_area_struct *vma = walk->vma; const struct mm_walk_ops *ops = walk->ops; + bool is_hugetlb = is_vm_hugetlb_page(vma); + + /* We do not support hugetlb PTE installation. */ + if (ops->install_pte && is_hugetlb) + return -EINVAL; if (ops->pre_vma) { err = ops->pre_vma(start, end, walk); @@ -341,7 +405,7 @@ static int __walk_page_range(unsigned long start, unsigned long end, return err; } - if (is_vm_hugetlb_page(vma)) { + if (is_hugetlb) { if (ops->hugetlb_entry) err = walk_hugetlb_range(start, end, walk); } else @@ -380,47 +444,14 @@ static inline void process_vma_walk_lock(struct vm_area_struct *vma, #endif } -/** - * walk_page_range - walk page table with caller specific callbacks - * @mm: mm_struct representing the target process of page table walk - * @start: start address of the virtual address range - * @end: end address of the virtual address range - * @ops: operation to call during the walk - * @private: private data for callbacks' usage - * - * Recursively walk the page table tree of the process represented by @mm - * within the virtual address range [@start, @end). During walking, we can do - * some caller-specific works for each entry, by setting up pmd_entry(), - * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these - * callbacks, the associated entries/pages are just ignored. - * The return values of these callbacks are commonly defined like below: - * - * - 0 : succeeded to handle the current entry, and if you don't reach the - * end address yet, continue to walk. - * - >0 : succeeded to handle the current entry, and return to the caller - * with caller specific value. - * - <0 : failed to handle the current entry, and return to the caller - * with error code. - * - * Before starting to walk page table, some callers want to check whether - * they really want to walk over the current vma, typically by checking - * its vm_flags. walk_page_test() and @ops->test_walk() are used for this - * purpose. - * - * If operations need to be staged before and committed after a vma is walked, - * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(), - * since it is intended to handle commit-type operations, can't return any - * errors. - * - * struct mm_walk keeps current values of some common data like vma and pmd, - * which are useful for the access from callbacks. If you want to pass some - * caller-specific data to callbacks, @private should be helpful. +/* + * See the comment for walk_page_range(), this performs the heavy lifting of the + * operation, only sets no restrictions on how the walk proceeds. * - * Locking: - * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_lock, - * because these function traverse vma list and/or access to vma's data. + * We usually restrict the ability to install PTEs, but this functionality is + * available to internal memory management code and provided in mm/internal.h. */ -int walk_page_range(struct mm_struct *mm, unsigned long start, +int walk_page_range_mm(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private) { @@ -479,6 +510,80 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, return err; } +/* + * Determine if the walk operations specified are permitted to be used for a + * page table walk. + * + * This check is performed on all functions which are parameterised by walk + * operations and exposed in include/linux/pagewalk.h. + * + * Internal memory management code can use the walk_page_range_mm() function to + * be able to use all page walking operations. + */ +static bool check_ops_valid(const struct mm_walk_ops *ops) +{ + /* + * The installation of PTEs is solely under the control of memory + * management logic and subject to many subtle locking, security and + * cache considerations so we cannot permit other users to do so, and + * certainly not for exported symbols. + */ + if (ops->install_pte) + return false; + + return true; +} + +/** + * walk_page_range - walk page table with caller specific callbacks + * @mm: mm_struct representing the target process of page table walk + * @start: start address of the virtual address range + * @end: end address of the virtual address range + * @ops: operation to call during the walk + * @private: private data for callbacks' usage + * + * Recursively walk the page table tree of the process represented by @mm + * within the virtual address range [@start, @end). During walking, we can do + * some caller-specific works for each entry, by setting up pmd_entry(), + * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these + * callbacks, the associated entries/pages are just ignored. + * The return values of these callbacks are commonly defined like below: + * + * - 0 : succeeded to handle the current entry, and if you don't reach the + * end address yet, continue to walk. + * - >0 : succeeded to handle the current entry, and return to the caller + * with caller specific value. + * - <0 : failed to handle the current entry, and return to the caller + * with error code. + * + * Before starting to walk page table, some callers want to check whether + * they really want to walk over the current vma, typically by checking + * its vm_flags. walk_page_test() and @ops->test_walk() are used for this + * purpose. + * + * If operations need to be staged before and committed after a vma is walked, + * there are two callbacks, pre_vma() and post_vma(). Note that post_vma(), + * since it is intended to handle commit-type operations, can't return any + * errors. + * + * struct mm_walk keeps current values of some common data like vma and pmd, + * which are useful for the access from callbacks. If you want to pass some + * caller-specific data to callbacks, @private should be helpful. + * + * Locking: + * Callers of walk_page_range() and walk_page_vma() should hold @mm->mmap_lock, + * because these function traverse vma list and/or access to vma's data. + */ +int walk_page_range(struct mm_struct *mm, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private) +{ + if (!check_ops_valid(ops)) + return -EINVAL; + + return walk_page_range_mm(mm, start, end, ops, private); +} + /** * walk_page_range_novma - walk a range of pagetables not backed by a vma * @mm: mm_struct representing the target process of page table walk @@ -494,7 +599,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, * walking the kernel pages tables or page tables for firmware. * * Note: Be careful to walk the kernel pages tables, the caller may be need to - * take other effective approache (mmap lock may be insufficient) to prevent + * take other effective approaches (mmap lock may be insufficient) to prevent * the intermediate kernel page tables belonging to the specified address range * from being freed (e.g. memory hot-remove). */ @@ -513,6 +618,8 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, if (start >= end || !walk.mm) return -EINVAL; + if (!check_ops_valid(ops)) + return -EINVAL; /* * 1) For walking the user virtual address space: @@ -556,6 +663,8 @@ int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start, return -EINVAL; if (start < vma->vm_start || end > vma->vm_end) return -EINVAL; + if (!check_ops_valid(ops)) + return -EINVAL; process_mm_walk_lock(walk.mm, ops->walk_lock); process_vma_walk_lock(vma, ops->walk_lock); @@ -574,6 +683,8 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, if (!walk.mm) return -EINVAL; + if (!check_ops_valid(ops)) + return -EINVAL; process_mm_walk_lock(walk.mm, ops->walk_lock); process_vma_walk_lock(vma, ops->walk_lock); @@ -623,6 +734,9 @@ int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, unsigned long start_addr, end_addr; int err = 0; + if (!check_ops_valid(ops)) + return -EINVAL; + lockdep_assert_held(&mapping->i_mmap_rwsem); vma_interval_tree_foreach(vma, &mapping->i_mmap, first_index, first_index + nr - 1) { diff --git a/mm/percpu.c b/mm/percpu.c index da21680ff294..d8dd31a2e407 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -253,13 +253,13 @@ static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { - page->index = (unsigned long)pcpu; + page->private = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { - return (struct pcpu_chunk *)page->index; + return (struct pcpu_chunk *)page->private; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) @@ -1864,6 +1864,10 @@ restart: area_found: pcpu_stats_area_alloc(chunk, size); + + if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) + pcpu_schedule_balance_work(); + spin_unlock_irqrestore(&pcpu_lock, flags); /* populate if not all pages are already there */ @@ -1891,9 +1895,6 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); } - if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) - pcpu_schedule_balance_work(); - /* clear the areas and return address relative to base address */ for_each_possible_cpu(cpu) memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index a78a4adf711a..5297dcc38c37 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -305,8 +305,8 @@ nomap: return NULL; } -pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, - unsigned long addr, spinlock_t **ptlp) +pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, spinlock_t **ptlp) { pmd_t pmdval; pte_t *pte; @@ -317,6 +317,19 @@ pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, return pte; } +pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, pmd_t *pmdvalp, + spinlock_t **ptlp) +{ + pte_t *pte; + + VM_WARN_ON_ONCE(!pmdvalp); + pte = __pte_offset_map(pmd, addr, pmdvalp); + if (likely(pte)) + *ptlp = pte_lockptr(mm, pmdvalp); + return pte; +} + /* * pte_offset_map_lock(mm, pmd, addr, ptlp), and its internal implementation * __pte_offset_map_lock() below, is usually called with the pmd pointer for @@ -347,14 +360,28 @@ pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd, * and disconnected table. Until pte_unmap(pte) unmaps and rcu_read_unlock()s * afterwards. * - * pte_offset_map_nolock(mm, pmd, addr, ptlp), above, is like pte_offset_map(); + * pte_offset_map_ro_nolock(mm, pmd, addr, ptlp), above, is like pte_offset_map(); * but when successful, it also outputs a pointer to the spinlock in ptlp - as * pte_offset_map_lock() does, but in this case without locking it. This helps * the caller to avoid a later pte_lockptr(mm, *pmd), which might by that time - * act on a changed *pmd: pte_offset_map_nolock() provides the correct spinlock - * pointer for the page table that it returns. In principle, the caller should - * recheck *pmd once the lock is taken; in practice, no callsite needs that - - * either the mmap_lock for write, or pte_same() check on contents, is enough. + * act on a changed *pmd: pte_offset_map_ro_nolock() provides the correct spinlock + * pointer for the page table that it returns. Even after grabbing the spinlock, + * we might be looking either at a page table that is still mapped or one that + * was unmapped and is about to get freed. But for R/O access this is sufficient. + * So it is only applicable for read-only cases where any modification operations + * to the page table are not allowed even if the corresponding spinlock is held + * afterwards. + * + * pte_offset_map_rw_nolock(mm, pmd, addr, pmdvalp, ptlp), above, is like + * pte_offset_map_ro_nolock(); but when successful, it also outputs the pdmval. + * It is applicable for may-write cases where any modification operations to the + * page table may happen after the corresponding spinlock is held afterwards. + * But the users should make sure the page table is stable like checking pte_same() + * or checking pmd_same() by using the output pmdval before performing the write + * operations. + * + * Note: "RO" / "RW" expresses the intended semantics, not that the *kmap* will + * be read-only/read-write protected. * * Note that free_pgtables(), used after unmapping detached vmas, or when * exiting the whole mm, does not take page table lock before freeing a page diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index b308e96cd05a..656d3e88755b 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -201,8 +201,8 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, } mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS); - if (!mm || IS_ERR(mm)) { - rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; + if (IS_ERR(mm)) { + rc = PTR_ERR(mm); /* * Explicitly map EACCES to EPERM as EPERM is a more * appropriate error code for process_vw_readv/writev diff --git a/mm/readahead.c b/mm/readahead.c index 9a807727d809..8f1cf599b572 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -206,9 +206,9 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; - unsigned long ra_folio_index, index = readahead_index(ractl); + unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); - unsigned long mark, i = 0; + unsigned long mark = ULONG_MAX, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* @@ -232,9 +232,14 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, * index that only has lookahead or "async_region" to set the * readahead flag. */ - ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, - min_nrpages); - mark = ra_folio_index - index; + if (lookahead_size <= nr_to_read) { + unsigned long ra_folio_index; + + ra_folio_index = round_up(readahead_index(ractl) + + nr_to_read - lookahead_size, + min_nrpages); + mark = ra_folio_index - index; + } nr_to_read += readahead_index(ractl) - index; ractl->_index = index; diff --git a/mm/rmap.c b/mm/rmap.c index 73d5998677d4..c6c4d4ea29a7 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -32,7 +32,6 @@ * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) - * folio_lock_memcg move_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) @@ -497,7 +496,7 @@ void __init anon_vma_init(void) * concurrently without folio lock protection). See folio_lock_anon_vma_read() * which has already covered that, and comment above remap_pages(). */ -struct anon_vma *folio_get_anon_vma(struct folio *folio) +struct anon_vma *folio_get_anon_vma(const struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; @@ -541,7 +540,7 @@ out: * reference like with folio_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(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; @@ -768,15 +767,27 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ -/* - * At what user virtual address is page expected in vma? - * Caller should check the page is actually part of the vma. +/** + * page_address_in_vma - The virtual address of a page in this VMA. + * @folio: The folio containing the page. + * @page: The page within the folio. + * @vma: The VMA we need to know the address in. + * + * Calculates the user virtual address of this page in the specified VMA. + * It is the caller's responsibililty to check the page is actually + * within the VMA. There may not currently be a PTE pointing at this + * page, but if a page fault occurs at this address, this is the page + * which will be accessed. + * + * Context: Caller should hold a reference to the folio. Caller should + * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the + * VMA from being altered. + * + * Return: The virtual address corresponding to this page in the VMA. */ -unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) +unsigned long page_address_in_vma(const struct folio *folio, + const struct page *page, const struct vm_area_struct *vma) { - struct folio *folio = page_folio(page); - pgoff_t pgoff; - if (folio_test_anon(folio)) { struct anon_vma *page__anon_vma = folio_anon_vma(folio); /* @@ -792,9 +803,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) return -EFAULT; } - /* The !page__anon_vma above handles KSM folios */ - pgoff = folio->index + folio_page_idx(folio, page); - return vma_address(vma, pgoff, 1); + /* KSM folios don't reach here because of the !page__anon_vma check */ + return vma_address(vma, page_pgoff(folio, page), 1); } /* @@ -1261,8 +1271,9 @@ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ -static void __page_check_anon_rmap(struct folio *folio, struct page *page, - struct vm_area_struct *vma, unsigned long address) +static void __page_check_anon_rmap(const struct folio *folio, + const struct page *page, struct vm_area_struct *vma, + unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to @@ -1277,7 +1288,7 @@ static void __page_check_anon_rmap(struct folio *folio, struct page *page, */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); - VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address), + VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address), page); } @@ -2559,7 +2570,7 @@ void __put_anon_vma(struct anon_vma *anon_vma) anon_vma_free(root); } -static struct anon_vma *rmap_walk_anon_lock(struct folio *folio, +static struct anon_vma *rmap_walk_anon_lock(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; diff --git a/mm/shmem.c b/mm/shmem.c index c7881e16f4be..ccb9629a0f70 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -141,6 +141,7 @@ static unsigned long huge_shmem_orders_always __read_mostly; static unsigned long huge_shmem_orders_madvise __read_mostly; static unsigned long huge_shmem_orders_inherit __read_mostly; static unsigned long huge_shmem_orders_within_size __read_mostly; +static bool shmem_orders_configured __initdata; #endif #ifdef CONFIG_TMPFS @@ -553,17 +554,15 @@ static bool shmem_confirm_swap(struct address_space *mapping, static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; -static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - loff_t write_end, bool shmem_huge_force, - struct vm_area_struct *vma, - unsigned long vm_flags) +static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, + loff_t write_end, bool shmem_huge_force, + unsigned long vm_flags) { - struct mm_struct *mm = vma ? vma->vm_mm : NULL; loff_t i_size; - if (!S_ISREG(inode->i_mode)) + if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) return false; - if (mm && ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &mm->flags))) + if (!S_ISREG(inode->i_mode)) return false; if (shmem_huge == SHMEM_HUGE_DENY) return false; @@ -581,7 +580,7 @@ static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, return true; fallthrough; case SHMEM_HUGE_ADVISE: - if (mm && (vm_flags & VM_HUGEPAGE)) + if (vm_flags & VM_HUGEPAGE) return true; fallthrough; default: @@ -589,35 +588,39 @@ static bool __shmem_huge_global_enabled(struct inode *inode, pgoff_t index, } } -static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - loff_t write_end, bool shmem_huge_force, - struct vm_area_struct *vma, unsigned long vm_flags) +static int shmem_parse_huge(const char *str) { - if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER) - return false; + int huge; - return __shmem_huge_global_enabled(inode, index, write_end, - shmem_huge_force, vma, vm_flags); -} + if (!str) + return -EINVAL; -#if defined(CONFIG_SYSFS) -static int shmem_parse_huge(const char *str) -{ if (!strcmp(str, "never")) - return SHMEM_HUGE_NEVER; - if (!strcmp(str, "always")) - return SHMEM_HUGE_ALWAYS; - if (!strcmp(str, "within_size")) - return SHMEM_HUGE_WITHIN_SIZE; - if (!strcmp(str, "advise")) - return SHMEM_HUGE_ADVISE; - if (!strcmp(str, "deny")) - return SHMEM_HUGE_DENY; - if (!strcmp(str, "force")) - return SHMEM_HUGE_FORCE; - return -EINVAL; + huge = SHMEM_HUGE_NEVER; + else if (!strcmp(str, "always")) + huge = SHMEM_HUGE_ALWAYS; + else if (!strcmp(str, "within_size")) + huge = SHMEM_HUGE_WITHIN_SIZE; + else if (!strcmp(str, "advise")) + huge = SHMEM_HUGE_ADVISE; + else if (!strcmp(str, "deny")) + huge = SHMEM_HUGE_DENY; + else if (!strcmp(str, "force")) + huge = SHMEM_HUGE_FORCE; + else + return -EINVAL; + + if (!has_transparent_hugepage() && + huge != SHMEM_HUGE_NEVER && huge != SHMEM_HUGE_DENY) + return -EINVAL; + + /* Do not override huge allocation policy with non-PMD sized mTHP */ + if (huge == SHMEM_HUGE_FORCE && + huge_shmem_orders_inherit != BIT(HPAGE_PMD_ORDER)) + return -EINVAL; + + return huge; } -#endif #if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS) static const char *shmem_format_huge(int huge) @@ -777,8 +780,8 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, } static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, - loff_t write_end, bool shmem_huge_force, - struct vm_area_struct *vma, unsigned long vm_flags) + loff_t write_end, bool shmem_huge_force, + unsigned long vm_flags) { return false; } @@ -1173,7 +1176,7 @@ static int shmem_getattr(struct mnt_idmap *idmap, STATX_ATTR_NODUMP); generic_fillattr(idmap, request_mask, inode, stat); - if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0)) + if (shmem_huge_global_enabled(inode, 0, 0, false, 0)) stat->blksize = HPAGE_PMD_SIZE; if (request_mask & STATX_BTIME) { @@ -1658,6 +1661,23 @@ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE +bool shmem_hpage_pmd_enabled(void) +{ + if (shmem_huge == SHMEM_HUGE_DENY) + return false; + if (test_bit(HPAGE_PMD_ORDER, &huge_shmem_orders_always)) + return true; + if (test_bit(HPAGE_PMD_ORDER, &huge_shmem_orders_madvise)) + return true; + if (test_bit(HPAGE_PMD_ORDER, &huge_shmem_orders_within_size)) + return true; + if (test_bit(HPAGE_PMD_ORDER, &huge_shmem_orders_inherit) && + shmem_huge != SHMEM_HUGE_NEVER) + return true; + + return false; +} + unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force) @@ -1673,7 +1693,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, return 0; global_huge = shmem_huge_global_enabled(inode, index, write_end, - shmem_huge_force, vma, vm_flags); + shmem_huge_force, vm_flags); if (!vma || !vma_is_anon_shmem(vma)) { /* * For tmpfs, we now only support PMD sized THP if huge page @@ -2879,7 +2899,10 @@ static struct inode *__shmem_get_inode(struct mnt_idmap *idmap, cache_no_acl(inode); if (sbinfo->noswap) mapping_set_unevictable(inode->i_mapping); - mapping_set_large_folios(inode->i_mapping); + + /* Don't consider 'deny' for emergencies and 'force' for testing */ + if (sbinfo->huge) + mapping_set_large_folios(inode->i_mapping); switch (mode & S_IFMT) { default: @@ -3140,27 +3163,19 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) unsigned long offset; int error = 0; ssize_t retval = 0; - loff_t *ppos = &iocb->ki_pos; - - index = *ppos >> PAGE_SHIFT; - offset = *ppos & ~PAGE_MASK; for (;;) { struct folio *folio = NULL; struct page *page = NULL; - pgoff_t end_index; unsigned long nr, ret; - loff_t i_size = i_size_read(inode); + loff_t end_offset, i_size = i_size_read(inode); + bool fallback_page_copy = false; + size_t fsize; - end_index = i_size >> PAGE_SHIFT; - if (index > end_index) + if (unlikely(iocb->ki_pos >= i_size)) break; - if (index == end_index) { - nr = i_size & ~PAGE_MASK; - if (nr <= offset) - break; - } + index = iocb->ki_pos >> PAGE_SHIFT; error = shmem_get_folio(inode, index, 0, &folio, SGP_READ); if (error) { if (error == -EINVAL) @@ -3176,24 +3191,29 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) error = -EIO; break; } + + if (folio_test_large(folio) && + folio_test_has_hwpoisoned(folio)) + fallback_page_copy = true; } /* * We must evaluate after, since reads (unlike writes) * are called without i_rwsem protection against truncate */ - nr = PAGE_SIZE; i_size = i_size_read(inode); - end_index = i_size >> PAGE_SHIFT; - if (index == end_index) { - nr = i_size & ~PAGE_MASK; - if (nr <= offset) { - if (folio) - folio_put(folio); - break; - } + if (unlikely(iocb->ki_pos >= i_size)) { + if (folio) + folio_put(folio); + break; } - nr -= offset; + end_offset = min_t(loff_t, i_size, iocb->ki_pos + to->count); + if (folio && likely(!fallback_page_copy)) + fsize = folio_size(folio); + else + fsize = PAGE_SIZE; + offset = iocb->ki_pos & (fsize - 1); + nr = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); if (folio) { /* @@ -3201,10 +3221,15 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ - if (mapping_writably_mapped(mapping)) - flush_dcache_page(page); + if (mapping_writably_mapped(mapping)) { + if (likely(!fallback_page_copy)) + flush_dcache_folio(folio); + else + flush_dcache_page(page); + } + /* - * Mark the page accessed if we read the beginning. + * Mark the folio accessed if we read the beginning. */ if (!offset) folio_mark_accessed(folio); @@ -3212,9 +3237,11 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ - ret = copy_page_to_iter(page, offset, nr, to); + if (likely(!fallback_page_copy)) + ret = copy_folio_to_iter(folio, offset, nr, to); + else + ret = copy_page_to_iter(page, offset, nr, to); folio_put(folio); - } else if (user_backed_iter(to)) { /* * Copy to user tends to be so well optimized, but @@ -3232,9 +3259,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) } retval += ret; - offset += ret; - index += offset >> PAGE_SHIFT; - offset &= ~PAGE_MASK; + iocb->ki_pos += ret; if (!iov_iter_count(to)) break; @@ -3245,7 +3270,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) cond_resched(); } - *ppos = ((loff_t) index << PAGE_SHIFT) + offset; file_accessed(file); return retval ? retval : error; } @@ -3334,11 +3358,16 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, len = min_t(size_t, len, npages * PAGE_SIZE); do { + bool fallback_page_splice = false; + struct page *page = NULL; + pgoff_t index; + size_t size; + if (*ppos >= i_size_read(inode)) break; - error = shmem_get_folio(inode, *ppos / PAGE_SIZE, 0, &folio, - SGP_READ); + index = *ppos >> PAGE_SHIFT; + error = shmem_get_folio(inode, index, 0, &folio, SGP_READ); if (error) { if (error == -EINVAL) error = 0; @@ -3347,12 +3376,15 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (folio) { folio_unlock(folio); - if (folio_test_hwpoison(folio) || - (folio_test_large(folio) && - folio_test_has_hwpoisoned(folio))) { + page = folio_file_page(folio, index); + if (PageHWPoison(page)) { error = -EIO; break; } + + if (folio_test_large(folio) && + folio_test_has_hwpoisoned(folio)) + fallback_page_splice = true; } /* @@ -3366,7 +3398,17 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, isize = i_size_read(inode); if (unlikely(*ppos >= isize)) break; - part = min_t(loff_t, isize - *ppos, len); + /* + * Fallback to PAGE_SIZE splice if the large folio has hwpoisoned + * pages. + */ + size = len; + if (unlikely(fallback_page_splice)) { + size_t offset = *ppos & ~PAGE_MASK; + + size = umin(size, PAGE_SIZE - offset); + } + part = min_t(loff_t, isize - *ppos, size); if (folio) { /* @@ -3374,8 +3416,12 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ - if (mapping_writably_mapped(mapping)) - flush_dcache_folio(folio); + if (mapping_writably_mapped(mapping)) { + if (likely(!fallback_page_splice)) + flush_dcache_folio(folio); + else + flush_dcache_page(page); + } folio_mark_accessed(folio); /* * Ok, we have the page, and it's up-to-date, so we can @@ -5224,7 +5270,8 @@ void __init shmem_init(void) * Default to setting PMD-sized THP to inherit the global setting and * disable all other multi-size THPs. */ - huge_shmem_orders_inherit = BIT(HPAGE_PMD_ORDER); + if (!shmem_orders_configured) + huge_shmem_orders_inherit = BIT(HPAGE_PMD_ORDER); #endif return; @@ -5267,7 +5314,7 @@ static ssize_t shmem_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { char tmp[16]; - int huge; + int huge, err; if (count + 1 > sizeof(tmp)) return -EINVAL; @@ -5278,20 +5325,14 @@ static ssize_t shmem_enabled_store(struct kobject *kobj, huge = shmem_parse_huge(tmp); if (huge == -EINVAL) - return -EINVAL; - if (!has_transparent_hugepage() && - huge != SHMEM_HUGE_NEVER && huge != SHMEM_HUGE_DENY) - return -EINVAL; - - /* Do not override huge allocation policy with non-PMD sized mTHP */ - if (huge == SHMEM_HUGE_FORCE && - huge_shmem_orders_inherit != BIT(HPAGE_PMD_ORDER)) - return -EINVAL; + return huge; shmem_huge = huge; if (shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; - return count; + + err = start_stop_khugepaged(); + return err ? err : count; } struct kobj_attribute shmem_enabled_attr = __ATTR_RW(shmem_enabled); @@ -5368,6 +5409,12 @@ static ssize_t thpsize_shmem_enabled_store(struct kobject *kobj, ret = -EINVAL; } + if (ret > 0) { + int err = start_stop_khugepaged(); + + if (err) + ret = err; + } return ret; } @@ -5375,6 +5422,126 @@ struct kobj_attribute thpsize_shmem_enabled_attr = __ATTR(shmem_enabled, 0644, thpsize_shmem_enabled_show, thpsize_shmem_enabled_store); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */ +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) + +static int __init setup_transparent_hugepage_shmem(char *str) +{ + int huge; + + huge = shmem_parse_huge(str); + if (huge == -EINVAL) { + pr_warn("transparent_hugepage_shmem= cannot parse, ignored\n"); + return huge; + } + + shmem_huge = huge; + return 1; +} +__setup("transparent_hugepage_shmem=", setup_transparent_hugepage_shmem); + +static char str_dup[PAGE_SIZE] __initdata; +static int __init setup_thp_shmem(char *str) +{ + char *token, *range, *policy, *subtoken; + unsigned long always, inherit, madvise, within_size; + char *start_size, *end_size; + int start, end, nr; + char *p; + + if (!str || strlen(str) + 1 > PAGE_SIZE) + goto err; + strscpy(str_dup, str); + + always = huge_shmem_orders_always; + inherit = huge_shmem_orders_inherit; + madvise = huge_shmem_orders_madvise; + within_size = huge_shmem_orders_within_size; + p = str_dup; + while ((token = strsep(&p, ";")) != NULL) { + range = strsep(&token, ":"); + policy = token; + + if (!policy) + goto err; + + while ((subtoken = strsep(&range, ",")) != NULL) { + if (strchr(subtoken, '-')) { + start_size = strsep(&subtoken, "-"); + end_size = subtoken; + + start = get_order_from_str(start_size, + THP_ORDERS_ALL_FILE_DEFAULT); + end = get_order_from_str(end_size, + THP_ORDERS_ALL_FILE_DEFAULT); + } else { + start_size = end_size = subtoken; + start = end = get_order_from_str(subtoken, + THP_ORDERS_ALL_FILE_DEFAULT); + } + + if (start == -EINVAL) { + pr_err("invalid size %s in thp_shmem boot parameter\n", + start_size); + goto err; + } + + if (end == -EINVAL) { + pr_err("invalid size %s in thp_shmem boot parameter\n", + end_size); + goto err; + } + + if (start < 0 || end < 0 || start > end) + goto err; + + nr = end - start + 1; + if (!strcmp(policy, "always")) { + bitmap_set(&always, start, nr); + bitmap_clear(&inherit, start, nr); + bitmap_clear(&madvise, start, nr); + bitmap_clear(&within_size, start, nr); + } else if (!strcmp(policy, "advise")) { + bitmap_set(&madvise, start, nr); + bitmap_clear(&inherit, start, nr); + bitmap_clear(&always, start, nr); + bitmap_clear(&within_size, start, nr); + } else if (!strcmp(policy, "inherit")) { + bitmap_set(&inherit, start, nr); + bitmap_clear(&madvise, start, nr); + bitmap_clear(&always, start, nr); + bitmap_clear(&within_size, start, nr); + } else if (!strcmp(policy, "within_size")) { + bitmap_set(&within_size, start, nr); + bitmap_clear(&inherit, start, nr); + bitmap_clear(&madvise, start, nr); + bitmap_clear(&always, start, nr); + } else if (!strcmp(policy, "never")) { + bitmap_clear(&inherit, start, nr); + bitmap_clear(&madvise, start, nr); + bitmap_clear(&always, start, nr); + bitmap_clear(&within_size, start, nr); + } else { + pr_err("invalid policy %s in thp_shmem boot parameter\n", policy); + goto err; + } + } + } + + huge_shmem_orders_always = always; + huge_shmem_orders_madvise = madvise; + huge_shmem_orders_inherit = inherit; + huge_shmem_orders_within_size = within_size; + shmem_orders_configured = true; + return 1; + +err: + pr_warn("thp_shmem=%s: error parsing string, ignoring setting\n", str); + return 0; +} +__setup("thp_shmem=", setup_thp_shmem); + +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + #else /* !CONFIG_SHMEM */ /* diff --git a/mm/show_mem.c b/mm/show_mem.c index ec885a398fa0..43afb56abbd3 100644 --- a/mm/show_mem.c +++ b/mm/show_mem.c @@ -285,8 +285,7 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z #endif K(node_page_state(pgdat, NR_PAGETABLE)), K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)), - pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? - "yes" : "no"); + str_yes_no(pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)); } for_each_populated_zone(zone) { diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index c0388b2e959d..cec67c5f37d8 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -184,10 +184,6 @@ static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node) return p; } -void __weak __meminit kernel_pte_init(void *addr) -{ -} - pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) { pmd_t *pmd = pmd_offset(pud, addr); @@ -201,10 +197,6 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) return pmd; } -void __weak __meminit pmd_init(void *addr) -{ -} - pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) { pud_t *pud = pud_offset(p4d, addr); @@ -218,10 +210,6 @@ pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) return pud; } -void __weak __meminit pud_init(void *addr) -{ -} - p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) { p4d_t *p4d = p4d_offset(pgd, addr); diff --git a/mm/sparse.c b/mm/sparse.c index dc38539f8560..13b6624d3562 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -129,7 +129,7 @@ static inline int sparse_early_nid(struct mem_section *section) static void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn) { - unsigned long max_sparsemem_pfn = (PHYSMEM_END + 1) >> PAGE_SHIFT; + unsigned long max_sparsemem_pfn = (DIRECT_MAP_PHYSMEM_END + 1) >> PAGE_SHIFT; /* * Sanity checks - do not allow an architecture to pass @@ -720,19 +720,19 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages, static void free_map_bootmem(struct page *memmap) { unsigned long maps_section_nr, removing_section_nr, i; - unsigned long magic, nr_pages; + unsigned long type, nr_pages; struct page *page = virt_to_page(memmap); nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) >> PAGE_SHIFT; for (i = 0; i < nr_pages; i++, page++) { - magic = page->index; + type = bootmem_type(page); - BUG_ON(magic == NODE_INFO); + BUG_ON(type == NODE_INFO); maps_section_nr = pfn_to_section_nr(page_to_pfn(page)); - removing_section_nr = page_private(page); + removing_section_nr = bootmem_info(page); /* * When this function is called, the removing section is diff --git a/mm/swap.c b/mm/swap.c index 59f30a981c6f..10decd9dffa1 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -113,37 +113,6 @@ void __folio_put(struct folio *folio) } EXPORT_SYMBOL(__folio_put); -/** - * put_pages_list() - release a list of pages - * @pages: list of pages threaded on page->lru - * - * Release a list of pages which are strung together on page.lru. - */ -void put_pages_list(struct list_head *pages) -{ - struct folio_batch fbatch; - struct folio *folio, *next; - - folio_batch_init(&fbatch); - list_for_each_entry_safe(folio, next, pages, lru) { - if (!folio_put_testzero(folio)) - continue; - if (folio_test_hugetlb(folio)) { - free_huge_folio(folio); - continue; - } - /* LRU flag must be clear because it's passed using the lru */ - if (folio_batch_add(&fbatch, folio) > 0) - continue; - free_unref_folios(&fbatch); - } - - if (fbatch.nr) - free_unref_folios(&fbatch); - INIT_LIST_HEAD(pages); -} -EXPORT_SYMBOL(put_pages_list); - typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add(struct lruvec *lruvec, struct folio *folio) diff --git a/mm/swap_state.c b/mm/swap_state.c index 4669f29cf555..e0c0321b8ff7 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -889,8 +889,7 @@ struct folio *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, static ssize_t vma_ra_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sysfs_emit(buf, "%s\n", - enable_vma_readahead ? "true" : "false"); + return sysfs_emit(buf, "%s\n", str_true_false(enable_vma_readahead)); } static ssize_t vma_ra_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, diff --git a/mm/truncate.c b/mm/truncate.c index 09fa809f921d..7c304d2f0052 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -23,42 +23,28 @@ #include <linux/rmap.h> #include "internal.h" -/* - * Regular page slots are stabilized by the page lock even without the tree - * itself locked. These unlocked entries need verification under the tree - * lock. - */ -static inline void __clear_shadow_entry(struct address_space *mapping, - pgoff_t index, void *entry) -{ - XA_STATE(xas, &mapping->i_pages, index); - - xas_set_update(&xas, workingset_update_node); - if (xas_load(&xas) != entry) - return; - xas_store(&xas, NULL); -} - static void clear_shadow_entries(struct address_space *mapping, - struct folio_batch *fbatch, pgoff_t *indices) + unsigned long start, unsigned long max) { - int i; + XA_STATE(xas, &mapping->i_pages, start); + struct folio *folio; /* Handled by shmem itself, or for DAX we do nothing. */ if (shmem_mapping(mapping) || dax_mapping(mapping)) return; - spin_lock(&mapping->host->i_lock); - xa_lock_irq(&mapping->i_pages); + xas_set_update(&xas, workingset_update_node); - for (i = 0; i < folio_batch_count(fbatch); i++) { - struct folio *folio = fbatch->folios[i]; + spin_lock(&mapping->host->i_lock); + xas_lock_irq(&xas); + /* Clear all shadow entries from start to max */ + xas_for_each(&xas, folio, max) { if (xa_is_value(folio)) - __clear_shadow_entry(mapping, indices[i], folio); + xas_store(&xas, NULL); } - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); @@ -68,54 +54,53 @@ static void clear_shadow_entries(struct address_space *mapping, * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the folio_batch may be altered by this function by removing * exceptional entries similar to what folio_batch_remove_exceptionals() does. + * Please note that indices[] has entries in ascending order as guaranteed by + * either find_get_entries() or find_lock_entries(). */ static void truncate_folio_batch_exceptionals(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) { + XA_STATE(xas, &mapping->i_pages, indices[0]); + int nr = folio_batch_count(fbatch); + struct folio *folio; int i, j; - bool dax; /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; - for (j = 0; j < folio_batch_count(fbatch); j++) + for (j = 0; j < nr; j++) if (xa_is_value(fbatch->folios[j])) break; - if (j == folio_batch_count(fbatch)) + if (j == nr) return; - dax = dax_mapping(mapping); - if (!dax) { - spin_lock(&mapping->host->i_lock); - xa_lock_irq(&mapping->i_pages); + if (dax_mapping(mapping)) { + for (i = j; i < nr; i++) { + if (xa_is_value(fbatch->folios[i])) + dax_delete_mapping_entry(mapping, indices[i]); + } + goto out; } - for (i = j; i < folio_batch_count(fbatch); i++) { - struct folio *folio = fbatch->folios[i]; - pgoff_t index = indices[i]; - - if (!xa_is_value(folio)) { - fbatch->folios[j++] = folio; - continue; - } + xas_set(&xas, indices[j]); + xas_set_update(&xas, workingset_update_node); - if (unlikely(dax)) { - dax_delete_mapping_entry(mapping, index); - continue; - } + spin_lock(&mapping->host->i_lock); + xas_lock_irq(&xas); - __clear_shadow_entry(mapping, index, folio); + xas_for_each(&xas, folio, indices[nr-1]) { + if (xa_is_value(folio)) + xas_store(&xas, NULL); } - if (!dax) { - xa_unlock_irq(&mapping->i_pages); - if (mapping_shrinkable(mapping)) - inode_add_lru(mapping->host); - spin_unlock(&mapping->host->i_lock); - } - fbatch->nr = j; + xas_unlock_irq(&xas); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); +out: + folio_batch_remove_exceptionals(fbatch); } /** @@ -477,11 +462,13 @@ unsigned long mapping_try_invalidate(struct address_space *mapping, unsigned long ret; unsigned long count = 0; int i; - bool xa_has_values = false; folio_batch_init(&fbatch); while (find_lock_entries(mapping, &index, end, &fbatch, indices)) { - for (i = 0; i < folio_batch_count(&fbatch); i++) { + bool xa_has_values = false; + int nr = folio_batch_count(&fbatch); + + for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ @@ -508,7 +495,7 @@ unsigned long mapping_try_invalidate(struct address_space *mapping, } if (xa_has_values) - clear_shadow_entries(mapping, &fbatch, indices); + clear_shadow_entries(mapping, indices[0], indices[nr-1]); folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); @@ -604,7 +591,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping, int ret = 0; int ret2 = 0; int did_range_unmap = 0; - bool xa_has_values = false; if (mapping_empty(mapping)) return 0; @@ -612,7 +598,10 @@ int invalidate_inode_pages2_range(struct address_space *mapping, folio_batch_init(&fbatch); index = start; while (find_get_entries(mapping, &index, end, &fbatch, indices)) { - for (i = 0; i < folio_batch_count(&fbatch); i++) { + bool xa_has_values = false; + int nr = folio_batch_count(&fbatch); + + for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ @@ -658,7 +647,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } if (xa_has_values) - clear_shadow_entries(mapping, &fbatch, indices); + clear_shadow_entries(mapping, indices[0], indices[nr-1]); folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index ce13c4062647..60a0be33766f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -251,7 +251,7 @@ static int mfill_atomic_pte_copy(pmd_t *dst_pmd, if (!*foliop) { ret = -ENOMEM; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, dst_vma, - dst_addr, false); + dst_addr); if (!folio) goto out; @@ -1135,7 +1135,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, spinlock_t *src_ptl, *dst_ptl; pte_t *src_pte = NULL; pte_t *dst_pte = NULL; - + pmd_t dummy_pmdval; struct folio *src_folio = NULL; struct anon_vma *src_anon_vma = NULL; struct mmu_notifier_range range; @@ -1146,7 +1146,14 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, src_addr, src_addr + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); retry: - dst_pte = pte_offset_map_nolock(mm, dst_pmd, dst_addr, &dst_ptl); + /* + * Use the maywrite version to indicate that dst_pte will be modified, + * but since we will use pte_same() to detect the change of the pte + * entry, there is no need to get pmdval, so just pass a dummy variable + * to it. + */ + dst_pte = pte_offset_map_rw_nolock(mm, dst_pmd, dst_addr, &dummy_pmdval, + &dst_ptl); /* Retry if a huge pmd materialized from under us */ if (unlikely(!dst_pte)) { @@ -1154,7 +1161,9 @@ retry: goto out; } - src_pte = pte_offset_map_nolock(mm, src_pmd, src_addr, &src_ptl); + /* same as dst_pte */ + src_pte = pte_offset_map_rw_nolock(mm, src_pmd, src_addr, &dummy_pmdval, + &src_ptl); /* * We held the mmap_lock for reading so MADV_DONTNEED diff --git a/mm/util.c b/mm/util.c index 4f1275023eb7..60017d2a9e48 100644 --- a/mm/util.c +++ b/mm/util.c @@ -820,7 +820,7 @@ void *vcalloc_noprof(size_t n, size_t size) } EXPORT_SYMBOL(vcalloc_noprof); -struct anon_vma *folio_anon_vma(struct folio *folio) +struct anon_vma *folio_anon_vma(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; @@ -7,6 +7,57 @@ #include "vma_internal.h" #include "vma.h" +struct mmap_state { + struct mm_struct *mm; + struct vma_iterator *vmi; + + unsigned long addr; + unsigned long end; + pgoff_t pgoff; + unsigned long pglen; + unsigned long flags; + struct file *file; + + unsigned long charged; + bool retry_merge; + + struct vm_area_struct *prev; + struct vm_area_struct *next; + + /* Unmapping state. */ + struct vma_munmap_struct vms; + struct ma_state mas_detach; + struct maple_tree mt_detach; +}; + +#define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, flags_, file_) \ + struct mmap_state name = { \ + .mm = mm_, \ + .vmi = vmi_, \ + .addr = addr_, \ + .end = (addr_) + len, \ + .pgoff = pgoff_, \ + .pglen = PHYS_PFN(len_), \ + .flags = flags_, \ + .file = file_, \ + } + +#define VMG_MMAP_STATE(name, map_, vma_) \ + struct vma_merge_struct name = { \ + .mm = (map_)->mm, \ + .vmi = (map_)->vmi, \ + .start = (map_)->addr, \ + .end = (map_)->end, \ + .flags = (map_)->flags, \ + .pgoff = (map_)->pgoff, \ + .file = (map_)->file, \ + .prev = (map_)->prev, \ + .vma = vma_, \ + .next = (vma_) ? NULL : (map_)->next, \ + .state = VMA_MERGE_START, \ + .merge_flags = VMG_FLAG_DEFAULT, \ + } + static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_next) { struct vm_area_struct *vma = merge_next ? vmg->next : vmg->prev; @@ -564,7 +615,11 @@ void validate_mm(struct mm_struct *mm) anon_vma_unlock_read(anon_vma); } #endif - i++; + /* Check for a infinite loop */ + if (++i > mm->map_count + 10) { + i = -1; + break; + } } if (i != mm->map_count) { pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i); @@ -911,10 +966,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) { struct vm_area_struct *prev = vmg->prev; struct vm_area_struct *next = vmg->next; - unsigned long start = vmg->start; unsigned long end = vmg->end; - pgoff_t pgoff = vmg->pgoff; - pgoff_t pglen = PHYS_PFN(end - start); bool can_merge_left, can_merge_right; bool just_expand = vmg->merge_flags & VMG_FLAG_JUST_EXPAND; @@ -936,7 +988,6 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) if (can_merge_right) { vmg->end = next->vm_end; vmg->vma = next; - vmg->pgoff = next->vm_pgoff - pglen; } /* If we can merge with the previous VMA, adjust vmg accordingly. */ @@ -970,16 +1021,6 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) return vmg->vma; } - /* If expansion failed, reset state. Allows us to retry merge later. */ - if (!just_expand) { - vmg->vma = NULL; - vmg->start = start; - vmg->end = end; - vmg->pgoff = pgoff; - if (vmg->vma == prev) - vma_iter_set(vmg->vmi, start); - } - return NULL; } @@ -1103,7 +1144,7 @@ static inline void vms_clear_ptes(struct vma_munmap_struct *vms, vms->clear_ptes = false; } -void vms_clean_up_area(struct vma_munmap_struct *vms, +static void vms_clean_up_area(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *vma; @@ -1126,7 +1167,7 @@ void vms_clean_up_area(struct vma_munmap_struct *vms, * used for the munmap() and may downgrade the lock - if requested. Everything * needed to be done once the vma maple tree is updated. */ -void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, +static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *vma; @@ -1168,6 +1209,23 @@ void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, } /* + * reattach_vmas() - Undo any munmap work and free resources + * @mas_detach: The maple state with the detached maple tree + * + * Reattach any detached vmas and free up the maple tree used to track the vmas. + */ +static void reattach_vmas(struct ma_state *mas_detach) +{ + struct vm_area_struct *vma; + + mas_set(mas_detach, 0); + mas_for_each(mas_detach, vma, ULONG_MAX) + vma_mark_detached(vma, false); + + __mt_destroy(mas_detach->tree); +} + +/* * vms_gather_munmap_vmas() - Put all VMAs within a range into a maple tree * for removal at a later date. Handles splitting first and last if necessary * and marking the vmas as isolated. @@ -1177,7 +1235,7 @@ void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, * * Return: 0 on success, error otherwise */ -int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, +static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *next = NULL; @@ -1254,7 +1312,7 @@ int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, else if (is_data_mapping(next->vm_flags)) vms->data_vm += nrpages; - if (unlikely(vms->uf)) { + if (vms->uf) { /* * If userfaultfd_unmap_prep returns an error the vmas * will remain split, but userland will get a @@ -1316,6 +1374,39 @@ map_count_exceeded: } /* + * init_vma_munmap() - Initializer wrapper for vma_munmap_struct + * @vms: The vma munmap struct + * @vmi: The vma iterator + * @vma: The first vm_area_struct to munmap + * @start: The aligned start address to munmap + * @end: The aligned end address to munmap + * @uf: The userfaultfd list_head + * @unlock: Unlock after the operation. Only unlocked on success + */ +static void init_vma_munmap(struct vma_munmap_struct *vms, + struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, struct list_head *uf, + bool unlock) +{ + vms->vmi = vmi; + vms->vma = vma; + if (vma) { + vms->start = start; + vms->end = end; + } else { + vms->start = vms->end = 0; + } + vms->unlock = unlock; + vms->uf = uf; + vms->vma_count = 0; + vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0; + vms->exec_vm = vms->stack_vm = vms->data_vm = 0; + vms->unmap_start = FIRST_USER_ADDRESS; + vms->unmap_end = USER_PGTABLES_CEILING; + vms->clear_ptes = false; +} + +/* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator * @vma: The starting vm_area_struct @@ -2069,3 +2160,321 @@ void mm_drop_all_locks(struct mm_struct *mm) mutex_unlock(&mm_all_locks_mutex); } + +/* + * We account for memory if it's a private writeable mapping, + * not hugepages and VM_NORESERVE wasn't set. + */ +static bool accountable_mapping(struct file *file, vm_flags_t vm_flags) +{ + /* + * hugetlb has its own accounting separate from the core VM + * VM_HUGETLB may not be set yet so we cannot check for that flag. + */ + if (file && is_file_hugepages(file)) + return false; + + return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; +} + +/* + * vms_abort_munmap_vmas() - Undo as much as possible from an aborted munmap() + * operation. + * @vms: The vma unmap structure + * @mas_detach: The maple state with the detached maple tree + * + * Reattach any detached vmas, free up the maple tree used to track the vmas. + * If that's not possible because the ptes are cleared (and vm_ops->closed() may + * have been called), then a NULL is written over the vmas and the vmas are + * removed (munmap() completed). + */ +static void vms_abort_munmap_vmas(struct vma_munmap_struct *vms, + struct ma_state *mas_detach) +{ + struct ma_state *mas = &vms->vmi->mas; + + if (!vms->nr_pages) + return; + + if (vms->clear_ptes) + return reattach_vmas(mas_detach); + + /* + * Aborting cannot just call the vm_ops open() because they are often + * not symmetrical and state data has been lost. Resort to the old + * failure method of leaving a gap where the MAP_FIXED mapping failed. + */ + mas_set_range(mas, vms->start, vms->end - 1); + mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL); + /* Clean up the insertion of the unfortunate gap */ + vms_complete_munmap_vmas(vms, mas_detach); +} + +/* + * __mmap_prepare() - Prepare to gather any overlapping VMAs that need to be + * unmapped once the map operation is completed, check limits, account mapping + * and clean up any pre-existing VMAs. + * + * @map: Mapping state. + * @uf: Userfaultfd context list. + * + * Returns: 0 on success, error code otherwise. + */ +static int __mmap_prepare(struct mmap_state *map, struct list_head *uf) +{ + int error; + struct vma_iterator *vmi = map->vmi; + struct vma_munmap_struct *vms = &map->vms; + + /* Find the first overlapping VMA and initialise unmap state. */ + vms->vma = vma_find(vmi, map->end); + init_vma_munmap(vms, vmi, vms->vma, map->addr, map->end, uf, + /* unlock = */ false); + + /* OK, we have overlapping VMAs - prepare to unmap them. */ + if (vms->vma) { + mt_init_flags(&map->mt_detach, + vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); + mt_on_stack(map->mt_detach); + mas_init(&map->mas_detach, &map->mt_detach, /* addr = */ 0); + /* Prepare to unmap any existing mapping in the area */ + error = vms_gather_munmap_vmas(vms, &map->mas_detach); + if (error) { + /* On error VMAs will already have been reattached. */ + vms->nr_pages = 0; + return error; + } + + map->next = vms->next; + map->prev = vms->prev; + } else { + map->next = vma_iter_next_rewind(vmi, &map->prev); + } + + /* Check against address space limit. */ + if (!may_expand_vm(map->mm, map->flags, map->pglen - vms->nr_pages)) + return -ENOMEM; + + /* Private writable mapping: check memory availability. */ + if (accountable_mapping(map->file, map->flags)) { + map->charged = map->pglen; + map->charged -= vms->nr_accounted; + if (map->charged) { + error = security_vm_enough_memory_mm(map->mm, map->charged); + if (error) + return error; + } + + vms->nr_accounted = 0; + map->flags |= VM_ACCOUNT; + } + + /* + * Clear PTEs while the vma is still in the tree so that rmap + * cannot race with the freeing later in the truncate scenario. + * This is also needed for mmap_file(), which is why vm_ops + * close function is called. + */ + vms_clean_up_area(vms, &map->mas_detach); + + return 0; +} + + +static int __mmap_new_file_vma(struct mmap_state *map, + struct vm_area_struct *vma) +{ + struct vma_iterator *vmi = map->vmi; + int error; + + vma->vm_file = get_file(map->file); + error = mmap_file(vma->vm_file, vma); + if (error) { + fput(vma->vm_file); + vma->vm_file = NULL; + + vma_iter_set(vmi, vma->vm_end); + /* Undo any partial mapping done by a device driver. */ + unmap_region(&vmi->mas, vma, map->prev, map->next); + + return error; + } + + /* Drivers cannot alter the address of the VMA. */ + WARN_ON_ONCE(map->addr != vma->vm_start); + /* + * Drivers should not permit writability when previously it was + * disallowed. + */ + VM_WARN_ON_ONCE(map->flags != vma->vm_flags && + !(map->flags & VM_MAYWRITE) && + (vma->vm_flags & VM_MAYWRITE)); + + /* If the flags change (and are mergeable), let's retry later. */ + map->retry_merge = vma->vm_flags != map->flags && !(vma->vm_flags & VM_SPECIAL); + map->flags = vma->vm_flags; + + return 0; +} + +/* + * __mmap_new_vma() - Allocate a new VMA for the region, as merging was not + * possible. + * + * @map: Mapping state. + * @vmap: Output pointer for the new VMA. + * + * Returns: Zero on success, or an error. + */ +static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap) +{ + struct vma_iterator *vmi = map->vmi; + int error = 0; + struct vm_area_struct *vma; + + /* + * Determine the object being mapped and call the appropriate + * specific mapper. the address has already been validated, but + * not unmapped, but the maps are removed from the list. + */ + vma = vm_area_alloc(map->mm); + if (!vma) + return -ENOMEM; + + vma_iter_config(vmi, map->addr, map->end); + vma_set_range(vma, map->addr, map->end, map->pgoff); + vm_flags_init(vma, map->flags); + vma->vm_page_prot = vm_get_page_prot(map->flags); + + if (vma_iter_prealloc(vmi, vma)) { + error = -ENOMEM; + goto free_vma; + } + + if (map->file) + error = __mmap_new_file_vma(map, vma); + else if (map->flags & VM_SHARED) + error = shmem_zero_setup(vma); + else + vma_set_anonymous(vma); + + if (error) + goto free_iter_vma; + +#ifdef CONFIG_SPARC64 + /* TODO: Fix SPARC ADI! */ + WARN_ON_ONCE(!arch_validate_flags(map->flags)); +#endif + + /* Lock the VMA since it is modified after insertion into VMA tree */ + vma_start_write(vma); + vma_iter_store(vmi, vma); + map->mm->map_count++; + vma_link_file(vma); + + /* + * vma_merge_new_range() calls khugepaged_enter_vma() too, the below + * call covers the non-merge case. + */ + khugepaged_enter_vma(vma, map->flags); + ksm_add_vma(vma); + *vmap = vma; + return 0; + +free_iter_vma: + vma_iter_free(vmi); +free_vma: + vm_area_free(vma); + return error; +} + +/* + * __mmap_complete() - Unmap any VMAs we overlap, account memory mapping + * statistics, handle locking and finalise the VMA. + * + * @map: Mapping state. + * @vma: Merged or newly allocated VMA for the mmap()'d region. + */ +static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma) +{ + struct mm_struct *mm = map->mm; + unsigned long vm_flags = vma->vm_flags; + + perf_event_mmap(vma); + + /* Unmap any existing mapping in the area. */ + vms_complete_munmap_vmas(&map->vms, &map->mas_detach); + + vm_stat_account(mm, vma->vm_flags, map->pglen); + if (vm_flags & VM_LOCKED) { + if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || + is_vm_hugetlb_page(vma) || + vma == get_gate_vma(mm)) + vm_flags_clear(vma, VM_LOCKED_MASK); + else + mm->locked_vm += map->pglen; + } + + if (vma->vm_file) + uprobe_mmap(vma); + + /* + * New (or expanded) vma always get soft dirty status. + * Otherwise user-space soft-dirty page tracker won't + * be able to distinguish situation when vma area unmapped, + * then new mapped in-place (which must be aimed as + * a completely new data area). + */ + vm_flags_set(vma, VM_SOFTDIRTY); + + vma_set_page_prot(vma); +} + +unsigned long __mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma = NULL; + int error; + VMA_ITERATOR(vmi, mm, addr); + MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vm_flags, file); + + error = __mmap_prepare(&map, uf); + if (error) + goto abort_munmap; + + /* Attempt to merge with adjacent VMAs... */ + if (map.prev || map.next) { + VMG_MMAP_STATE(vmg, &map, /* vma = */ NULL); + + vma = vma_merge_new_range(&vmg); + } + + /* ...but if we can't, allocate a new VMA. */ + if (!vma) { + error = __mmap_new_vma(&map, &vma); + if (error) + goto unacct_error; + } + + /* If flags changed, we might be able to merge, so try again. */ + if (map.retry_merge) { + VMG_MMAP_STATE(vmg, &map, vma); + + vma_iter_config(map.vmi, map.addr, map.end); + vma_merge_existing_range(&vmg); + } + + __mmap_complete(&map, vma); + + return addr; + + /* Accounting was done by __mmap_prepare(). */ +unacct_error: + if (map.charged) + vm_unacct_memory(map.charged); +abort_munmap: + vms_abort_munmap_vmas(&map.vms, &map.mas_detach); + return error; +} @@ -165,99 +165,6 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi, return 0; } -#ifdef CONFIG_MMU -/* - * init_vma_munmap() - Initializer wrapper for vma_munmap_struct - * @vms: The vma munmap struct - * @vmi: The vma iterator - * @vma: The first vm_area_struct to munmap - * @start: The aligned start address to munmap - * @end: The aligned end address to munmap - * @uf: The userfaultfd list_head - * @unlock: Unlock after the operation. Only unlocked on success - */ -static inline void init_vma_munmap(struct vma_munmap_struct *vms, - struct vma_iterator *vmi, struct vm_area_struct *vma, - unsigned long start, unsigned long end, struct list_head *uf, - bool unlock) -{ - vms->vmi = vmi; - vms->vma = vma; - if (vma) { - vms->start = start; - vms->end = end; - } else { - vms->start = vms->end = 0; - } - vms->unlock = unlock; - vms->uf = uf; - vms->vma_count = 0; - vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0; - vms->exec_vm = vms->stack_vm = vms->data_vm = 0; - vms->unmap_start = FIRST_USER_ADDRESS; - vms->unmap_end = USER_PGTABLES_CEILING; - vms->clear_ptes = false; -} -#endif - -int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, - struct ma_state *mas_detach); - -void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, - struct ma_state *mas_detach); - -void vms_clean_up_area(struct vma_munmap_struct *vms, - struct ma_state *mas_detach); - -/* - * reattach_vmas() - Undo any munmap work and free resources - * @mas_detach: The maple state with the detached maple tree - * - * Reattach any detached vmas and free up the maple tree used to track the vmas. - */ -static inline void reattach_vmas(struct ma_state *mas_detach) -{ - struct vm_area_struct *vma; - - mas_set(mas_detach, 0); - mas_for_each(mas_detach, vma, ULONG_MAX) - vma_mark_detached(vma, false); - - __mt_destroy(mas_detach->tree); -} - -/* - * vms_abort_munmap_vmas() - Undo as much as possible from an aborted munmap() - * operation. - * @vms: The vma unmap structure - * @mas_detach: The maple state with the detached maple tree - * - * Reattach any detached vmas, free up the maple tree used to track the vmas. - * If that's not possible because the ptes are cleared (and vm_ops->closed() may - * have been called), then a NULL is written over the vmas and the vmas are - * removed (munmap() completed). - */ -static inline void vms_abort_munmap_vmas(struct vma_munmap_struct *vms, - struct ma_state *mas_detach) -{ - struct ma_state *mas = &vms->vmi->mas; - if (!vms->nr_pages) - return; - - if (vms->clear_ptes) - return reattach_vmas(mas_detach); - - /* - * Aborting cannot just call the vm_ops open() because they are often - * not symmetrical and state data has been lost. Resort to the old - * failure method of leaving a gap where the MAP_FIXED mapping failed. - */ - mas_set_range(mas, vms->start, vms->end - 1); - mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL); - /* Clean up the insertion of the unfortunate gap */ - vms_complete_munmap_vmas(vms, mas_detach); -} - int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, @@ -336,6 +243,10 @@ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); int mm_take_all_locks(struct mm_struct *mm); void mm_drop_all_locks(struct mm_struct *mm); +unsigned long __mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf); + static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { /* diff --git a/mm/vma_internal.h b/mm/vma_internal.h index b930ab12a587..fc5f172a36bd 100644 --- a/mm/vma_internal.h +++ b/mm/vma_internal.h @@ -17,8 +17,10 @@ #include <linux/file.h> #include <linux/fs.h> #include <linux/huge_mm.h> +#include <linux/hugetlb.h> #include <linux/hugetlb_inline.h> #include <linux/kernel.h> +#include <linux/ksm.h> #include <linux/khugepaged.h> #include <linux/list.h> #include <linux/maple_tree.h> @@ -32,11 +34,14 @@ #include <linux/mmu_context.h> #include <linux/mutex.h> #include <linux/pagemap.h> +#include <linux/perf_event.h> #include <linux/pfn.h> #include <linux/rcupdate.h> #include <linux/rmap.h> #include <linux/rwsem.h> #include <linux/sched/signal.h> +#include <linux/security.h> +#include <linux/shmem_fs.h> #include <linux/swap.h> #include <linux/uprobes.h> #include <linux/userfaultfd_k.h> diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 634162271c00..7ed39d104201 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -653,7 +653,7 @@ int vmap_pages_range_noflush(unsigned long addr, unsigned long end, * RETURNS: * 0 on success, -errno on failure. */ -static int vmap_pages_range(unsigned long addr, unsigned long end, +int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { int err; @@ -2182,6 +2182,25 @@ decay_va_pool_node(struct vmap_node *vn, bool full_decay) reclaim_list_global(&decay_list); } +static void +kasan_release_vmalloc_node(struct vmap_node *vn) +{ + struct vmap_area *va; + unsigned long start, end; + + start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start; + end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end; + + list_for_each_entry(va, &vn->purge_list, list) { + if (is_vmalloc_or_module_addr((void *) va->va_start)) + kasan_release_vmalloc(va->va_start, va->va_end, + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE); + } + + kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH); +} + static void purge_vmap_node(struct work_struct *work) { struct vmap_node *vn = container_of(work, @@ -2190,20 +2209,17 @@ static void purge_vmap_node(struct work_struct *work) struct vmap_area *va, *n_va; LIST_HEAD(local_list); + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_release_vmalloc_node(vn); + vn->nr_purged = 0; list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { unsigned long nr = va_size(va) >> PAGE_SHIFT; - unsigned long orig_start = va->va_start; - unsigned long orig_end = va->va_end; unsigned int vn_id = decode_vn_id(va->flags); list_del_init(&va->list); - if (is_vmalloc_or_module_addr((void *)orig_start)) - kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); - nr_purged_pages += nr; vn->nr_purged++; @@ -3007,6 +3023,11 @@ static inline unsigned int vm_area_page_order(struct vm_struct *vm) #endif } +unsigned int get_vm_area_page_order(struct vm_struct *vm) +{ + return vm_area_page_order(vm); +} + static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order) { #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC @@ -3085,7 +3106,7 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm) vm->flags &= ~VM_UNINITIALIZED; } -static struct vm_struct *__get_vm_area_node(unsigned long size, +struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller) @@ -3763,8 +3784,6 @@ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, } if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { - unsigned long size_per_node; - /* * Try huge pages. Only try for PAGE_KERNEL allocations, * others like modules don't yet expect huge pages in @@ -3772,13 +3791,10 @@ void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, * supporting them. */ - size_per_node = size; - if (node == NUMA_NO_NODE) - size_per_node /= num_online_nodes(); - if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE) + if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE) shift = PMD_SHIFT; else - shift = arch_vmap_pte_supported_shift(size_per_node); + shift = arch_vmap_pte_supported_shift(size); align = max(real_align, 1UL << shift); size = ALIGN(real_size, 1UL << shift); @@ -4784,7 +4800,8 @@ recovery: &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; } @@ -4834,7 +4851,8 @@ err_free_shadow: &free_vmap_area_list); if (va) kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; kfree(vms[area]); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 28ba2b06fc7d..76378bc257e3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1258,8 +1258,8 @@ retry: THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); } - count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); #endif + count_mthp_stat(order, MTHP_STAT_SWPOUT_FALLBACK); if (!add_to_swap(folio)) goto activate_locked_split; } @@ -2129,7 +2129,7 @@ static void shrink_active_list(unsigned long nr_to_scan, static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { - struct reclaim_stat dummy_stat; + struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { @@ -2140,12 +2140,13 @@ static unsigned int reclaim_folio_list(struct list_head *folio_list, .no_demotion = 1, }; - nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, true); + nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &stat, true); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } + trace_mm_vmscan_reclaim_pages(pgdat->node_id, sc.nr_scanned, nr_reclaimed, &stat); return nr_reclaimed; } @@ -2602,8 +2603,6 @@ static bool should_clear_pmd_young(void) * shorthand helpers ******************************************************************************/ -#define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) - #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) @@ -3138,7 +3137,6 @@ static int folio_update_gen(struct folio *folio, int gen) unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); - VM_WARN_ON_ONCE(!rcu_read_lock_held()); do { /* lru_gen_del_folio() has isolated this page? */ @@ -3354,7 +3352,7 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, if (folio_nid(folio) != pgdat->node_id) return NULL; - if (folio_memcg_rcu(folio) != memcg) + if (folio_memcg(folio) != memcg) return NULL; /* file VMAs can contain anon pages from COW */ @@ -3386,8 +3384,10 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); DEFINE_MAX_SEQ(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); + pmd_t pmdval; - pte = pte_offset_map_nolock(args->mm, pmd, start & PMD_MASK, &ptl); + pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, + &ptl); if (!pte) return false; if (!spin_trylock(ptl)) { @@ -3395,6 +3395,11 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, return false; } + if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) { + pte_unmap_unlock(pte, ptl); + return false; + } + arch_enter_lazy_mmu_mode(); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { @@ -3643,10 +3648,8 @@ static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) .p4d_entry = walk_pud_range, .walk_lock = PGWALK_RDLOCK, }; - int err; struct lruvec *lruvec = walk->lruvec; - struct mem_cgroup *memcg = lruvec_memcg(lruvec); walk->next_addr = FIRST_USER_ADDRESS; @@ -3659,10 +3662,6 @@ static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) if (walk->seq != max_seq) break; - /* folio_update_gen() requires stable folio_memcg() */ - if (!mem_cgroup_trylock_pages(memcg)) - break; - /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); @@ -3670,8 +3669,6 @@ static void walk_mm(struct mm_struct *mm, struct lru_gen_mm_walk *walk) mmap_read_unlock(mm); } - mem_cgroup_unlock_pages(); - if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(walk); @@ -4093,10 +4090,6 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) } } - /* folio_update_gen() requires stable folio_memcg() */ - if (!mem_cgroup_trylock_pages(memcg)) - return true; - arch_enter_lazy_mmu_mode(); pte -= (addr - start) / PAGE_SIZE; @@ -4134,12 +4127,13 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) old_gen = folio_lru_gen(folio); if (old_gen < 0) folio_set_referenced(folio); - else if (old_gen != new_gen) + else if (old_gen != new_gen) { + folio_clear_lru_refs(folio); folio_activate(folio); + } } arch_leave_lazy_mmu_mode(); - mem_cgroup_unlock_pages(); /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) @@ -4290,6 +4284,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c int tier_idx) { bool success; + bool dirty, writeback; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); @@ -4335,9 +4330,17 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c return true; } + dirty = folio_test_dirty(folio); + writeback = folio_test_writeback(folio); + if (type == LRU_GEN_FILE && dirty) { + sc->nr.file_taken += delta; + if (!writeback) + sc->nr.unqueued_dirty += delta; + } + /* waiting for writeback */ - if (folio_test_locked(folio) || folio_test_writeback(folio) || - (type == LRU_GEN_FILE && folio_test_dirty(folio))) { + if (folio_test_locked(folio) || writeback || + (type == LRU_GEN_FILE && dirty)) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; @@ -4368,7 +4371,7 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca /* see the comment on MAX_NR_TIERS */ if (!folio_test_referenced(folio)) - set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); + folio_clear_lru_refs(folio); /* for shrink_folio_list() */ folio_clear_reclaim(folio); @@ -4453,7 +4456,8 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); - + if (type == LRU_GEN_FILE) + sc->nr.file_taken += isolated; /* * There might not be eligible folios due to reclaim_idx. Check the * remaining to prevent livelock if it's not making progress. @@ -4587,6 +4591,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); + sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr_reclaimed += reclaimed; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, scanned, reclaimed, &stat, sc->priority, @@ -4795,6 +4800,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) cond_resched(); } + /* + * If too many file cache in the coldest generation can't be evicted + * due to being dirty, wake up the flusher. + */ + if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken) + wakeup_flusher_threads(WB_REASON_VMSCAN); + /* whether this lruvec should be rotated */ return nr_to_scan < 0; } @@ -5940,6 +5952,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) bool reclaimable = false; if (lru_gen_enabled() && root_reclaim(sc)) { + memset(&sc->nr, 0, sizeof(sc->nr)); lru_gen_shrink_node(pgdat, sc); return; } @@ -5990,7 +6003,8 @@ again: set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ - if (sc->nr.unqueued_dirty == sc->nr.file_taken) + if (sc->nr.unqueued_dirty && + sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* diff --git a/mm/vmstat.c b/mm/vmstat.c index ac6a5aa34eab..4d016314a56c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1273,6 +1273,9 @@ const char * const vmstat_text[] = { "pgdemote_kswapd", "pgdemote_direct", "pgdemote_khugepaged", +#ifdef CONFIG_HUGETLB_PAGE + "nr_hugetlb", +#endif /* system-wide enum vm_stat_item counters */ "nr_dirty_threshold", "nr_dirty_background_threshold", @@ -1780,6 +1783,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, zone_page_state(zone, i)); #ifdef CONFIG_NUMA + fold_vm_zone_numa_events(zone); for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) seq_printf(m, "\n %-12s %lu", numa_stat_name(i), zone_numa_event_state(zone, i)); @@ -1793,13 +1797,17 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, pcp = per_cpu_ptr(zone->per_cpu_pageset, i); seq_printf(m, "\n cpu: %i" - "\n count: %i" - "\n high: %i" - "\n batch: %i", + "\n count: %i" + "\n high: %i" + "\n batch: %i" + "\n high_min: %i" + "\n high_max: %i", i, pcp->count, pcp->high, - pcp->batch); + pcp->batch, + pcp->high_min, + pcp->high_max); #ifdef CONFIG_SMP pzstats = per_cpu_ptr(zone->per_cpu_zonestats, i); seq_printf(m, "\n vm stats threshold: %d", @@ -1931,6 +1939,7 @@ static const struct seq_operations vmstat_op = { #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct delayed_work, vmstat_work); int sysctl_stat_interval __read_mostly = HZ; +static int vmstat_late_init_done; #ifdef CONFIG_PROC_FS static void refresh_vm_stats(struct work_struct *work) @@ -2133,7 +2142,8 @@ static void __init init_cpu_node_state(void) static int vmstat_cpu_online(unsigned int cpu) { - refresh_zone_stat_thresholds(); + if (vmstat_late_init_done) + refresh_zone_stat_thresholds(); if (!node_state(cpu_to_node(cpu), N_CPU)) { node_set_state(cpu_to_node(cpu), N_CPU); @@ -2165,6 +2175,14 @@ static int vmstat_cpu_dead(unsigned int cpu) return 0; } +static int __init vmstat_late_init(void) +{ + refresh_zone_stat_thresholds(); + vmstat_late_init_done = 1; + + return 0; +} +late_initcall(vmstat_late_init); #endif struct workqueue_struct *mm_percpu_wq; diff --git a/mm/workingset.c b/mm/workingset.c index a2b28e356e68..a4705e196545 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -591,22 +591,12 @@ void workingset_refault(struct folio *folio, void *shadow) */ void workingset_activation(struct folio *folio) { - struct mem_cgroup *memcg; - - rcu_read_lock(); /* * Filter non-memcg pages here, e.g. unmap can call * mark_page_accessed() on VDSO pages. - * - * XXX: See workingset_refault() - this should return - * root_mem_cgroup even for !CONFIG_MEMCG. */ - memcg = folio_memcg_rcu(folio); - if (!mem_cgroup_disabled() && !memcg) - goto out; - workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio)); -out: - rcu_read_unlock(); + if (mem_cgroup_disabled() || folio_memcg_charged(folio)) + workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio)); } /* @@ -712,8 +702,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, static enum lru_status shadow_lru_isolate(struct list_head *item, struct list_lru_one *lru, - spinlock_t *lru_lock, - void *arg) __must_hold(lru_lock) + void *arg) __must_hold(lru->lock) { struct xa_node *node = container_of(item, struct xa_node, private_list); struct address_space *mapping; @@ -722,20 +711,20 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, /* * Page cache insertions and deletions synchronously maintain * the shadow node LRU under the i_pages lock and the - * lru_lock. Because the page cache tree is emptied before - * the inode can be destroyed, holding the lru_lock pins any + * &lru->lock. Because the page cache tree is emptied before + * the inode can be destroyed, holding the &lru->lock pins any * address_space that has nodes on the LRU. * * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want - * to reclaim, take the node off-LRU, and drop the lru_lock. + * to reclaim, take the node off-LRU, and drop the &lru->lock. */ mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ if (!xa_trylock(&mapping->i_pages)) { - spin_unlock_irq(lru_lock); + spin_unlock_irq(&lru->lock); ret = LRU_RETRY; goto out; } @@ -744,7 +733,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, if (mapping->host != NULL) { if (!spin_trylock(&mapping->host->i_lock)) { xa_unlock(&mapping->i_pages); - spin_unlock_irq(lru_lock); + spin_unlock_irq(&lru->lock); ret = LRU_RETRY; goto out; } @@ -753,7 +742,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, list_lru_isolate(lru, item); __dec_node_page_state(virt_to_page(node), WORKINGSET_NODES); - spin_unlock(lru_lock); + spin_unlock(&lru->lock); /* * The nodes should only contain one or more shadow entries, @@ -777,7 +766,6 @@ out_invalid: ret = LRU_REMOVED_RETRY; out: cond_resched(); - spin_lock_irq(lru_lock); return ret; } @@ -823,8 +811,8 @@ static int __init workingset_init(void) if (!workingset_shadow_shrinker) goto err; - ret = __list_lru_init(&shadow_nodes, true, &shadow_nodes_key, - workingset_shadow_shrinker); + ret = list_lru_init_memcg_key(&shadow_nodes, workingset_shadow_shrinker, + &shadow_nodes_key); if (ret) goto err_list_lru; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 16a07def09c9..64b66a4d3e6e 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + /* * zsmalloc memory allocator * @@ -261,7 +263,7 @@ struct zspage { struct mapping_area { local_lock_t lock; char *vm_buf; /* copy buffer for objects that span pages */ - char *vm_addr; /* address of kmap_atomic()'ed pages */ + char *vm_addr; /* address of kmap_local_page()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ }; @@ -898,7 +900,7 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) set_first_obj_offset(page, off); - vaddr = kmap_atomic(page); + vaddr = kmap_local_page(page); link = (struct link_free *)vaddr + off / sizeof(*link); while ((off += class->size) < PAGE_SIZE) { @@ -921,7 +923,7 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) */ link->next = -1UL << OBJ_TAG_BITS; } - kunmap_atomic(vaddr); + kunmap_local(vaddr); page = next_page; off %= PAGE_SIZE; } @@ -1044,11 +1046,10 @@ static inline void __zs_cpu_down(struct mapping_area *area) static void *__zs_map_object(struct mapping_area *area, struct page *pages[2], int off, int size) { - int sizes[2]; - void *addr; + size_t sizes[2]; char *buf = area->vm_buf; - /* disable page faults to match kmap_atomic() return conditions */ + /* disable page faults to match kmap_local_page() return conditions */ pagefault_disable(); /* no read fastpath */ @@ -1059,12 +1060,8 @@ static void *__zs_map_object(struct mapping_area *area, sizes[1] = size - sizes[0]; /* copy object to per-cpu buffer */ - addr = kmap_atomic(pages[0]); - memcpy(buf, addr + off, sizes[0]); - kunmap_atomic(addr); - addr = kmap_atomic(pages[1]); - memcpy(buf + sizes[0], addr, sizes[1]); - kunmap_atomic(addr); + memcpy_from_page(buf, pages[0], off, sizes[0]); + memcpy_from_page(buf + sizes[0], pages[1], 0, sizes[1]); out: return area->vm_buf; } @@ -1072,8 +1069,7 @@ out: static void __zs_unmap_object(struct mapping_area *area, struct page *pages[2], int off, int size) { - int sizes[2]; - void *addr; + size_t sizes[2]; char *buf; /* no write fastpath */ @@ -1089,15 +1085,11 @@ static void __zs_unmap_object(struct mapping_area *area, sizes[1] = size - sizes[0]; /* copy per-cpu buffer to object */ - addr = kmap_atomic(pages[0]); - memcpy(addr + off, buf, sizes[0]); - kunmap_atomic(addr); - addr = kmap_atomic(pages[1]); - memcpy(addr, buf + sizes[0], sizes[1]); - kunmap_atomic(addr); + memcpy_to_page(pages[0], off, buf, sizes[0]); + memcpy_to_page(pages[1], 0, buf + sizes[0], sizes[1]); out: - /* enable page faults to match kunmap_atomic() return conditions */ + /* enable page faults to match kunmap_local() return conditions */ pagefault_enable(); } @@ -1223,7 +1215,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, area->vm_mm = mm; if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ - area->vm_addr = kmap_atomic(page); + area->vm_addr = kmap_local_page(page); ret = area->vm_addr + off; goto out; } @@ -1260,7 +1252,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) area = this_cpu_ptr(&zs_map_area); if (off + class->size <= PAGE_SIZE) - kunmap_atomic(area->vm_addr); + kunmap_local(area->vm_addr); else { struct page *pages[2]; @@ -1318,7 +1310,7 @@ static unsigned long obj_malloc(struct zs_pool *pool, for (i = 0; i < nr_page; i++) m_page = get_next_page(m_page); - vaddr = kmap_atomic(m_page); + vaddr = kmap_local_page(m_page); link = (struct link_free *)vaddr + m_offset / sizeof(*link); set_freeobj(zspage, link->next >> OBJ_TAG_BITS); if (likely(!ZsHugePage(zspage))) @@ -1328,7 +1320,7 @@ static unsigned long obj_malloc(struct zs_pool *pool, /* record handle to page->index */ zspage->first_page->index = handle | OBJ_ALLOCATED_TAG; - kunmap_atomic(vaddr); + kunmap_local(vaddr); mod_zspage_inuse(zspage, 1); obj = location_to_obj(m_page, obj); @@ -1419,7 +1411,7 @@ static void obj_free(int class_size, unsigned long obj) f_offset = offset_in_page(class_size * f_objidx); zspage = get_zspage(f_page); - vaddr = kmap_atomic(f_page); + vaddr = kmap_local_page(f_page); link = (struct link_free *)(vaddr + f_offset); /* Insert this object in containing zspage's freelist */ @@ -1429,7 +1421,7 @@ static void obj_free(int class_size, unsigned long obj) f_page->index = 0; set_freeobj(zspage, f_objidx); - kunmap_atomic(vaddr); + kunmap_local(vaddr); mod_zspage_inuse(zspage, -1); } @@ -1492,8 +1484,8 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, if (d_off + class->size > PAGE_SIZE) d_size = PAGE_SIZE - d_off; - s_addr = kmap_atomic(s_page); - d_addr = kmap_atomic(d_page); + s_addr = kmap_local_page(s_page); + d_addr = kmap_local_page(d_page); while (1) { size = min(s_size, d_size); @@ -1509,33 +1501,33 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, d_size -= size; /* - * Calling kunmap_atomic(d_addr) is necessary. kunmap_atomic() - * calls must occurs in reverse order of calls to kmap_atomic(). - * So, to call kunmap_atomic(s_addr) we should first call - * kunmap_atomic(d_addr). For more details see + * Calling kunmap_local(d_addr) is necessary. kunmap_local() + * calls must occurs in reverse order of calls to kmap_local_page(). + * So, to call kunmap_local(s_addr) we should first call + * kunmap_local(d_addr). For more details see * Documentation/mm/highmem.rst. */ if (s_off >= PAGE_SIZE) { - kunmap_atomic(d_addr); - kunmap_atomic(s_addr); + kunmap_local(d_addr); + kunmap_local(s_addr); s_page = get_next_page(s_page); - s_addr = kmap_atomic(s_page); - d_addr = kmap_atomic(d_page); + s_addr = kmap_local_page(s_page); + d_addr = kmap_local_page(d_page); s_size = class->size - written; s_off = 0; } if (d_off >= PAGE_SIZE) { - kunmap_atomic(d_addr); + kunmap_local(d_addr); d_page = get_next_page(d_page); - d_addr = kmap_atomic(d_page); + d_addr = kmap_local_page(d_page); d_size = class->size - written; d_off = 0; } } - kunmap_atomic(d_addr); - kunmap_atomic(s_addr); + kunmap_local(d_addr); + kunmap_local(s_addr); } /* @@ -1548,7 +1540,7 @@ static unsigned long find_alloced_obj(struct size_class *class, unsigned int offset; int index = *obj_idx; unsigned long handle = 0; - void *addr = kmap_atomic(page); + void *addr = kmap_local_page(page); offset = get_first_obj_offset(page); offset += class->size * index; @@ -1561,7 +1553,7 @@ static unsigned long find_alloced_obj(struct size_class *class, index++; } - kunmap_atomic(addr); + kunmap_local(addr); *obj_idx = index; @@ -1798,14 +1790,14 @@ static int zs_page_migrate(struct page *newpage, struct page *page, migrate_write_lock(zspage); offset = get_first_obj_offset(page); - s_addr = kmap_atomic(page); + s_addr = kmap_local_page(page); /* * Here, any user cannot access all objects in the zspage so let's move. */ - d_addr = kmap_atomic(newpage); + d_addr = kmap_local_page(newpage); copy_page(d_addr, s_addr); - kunmap_atomic(d_addr); + kunmap_local(d_addr); for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE; addr += class->size) { @@ -1818,7 +1810,7 @@ static int zs_page_migrate(struct page *newpage, struct page *page, record_obj(handle, new_obj); } } - kunmap_atomic(s_addr); + kunmap_local(s_addr); replace_sub_page(class, zspage, newpage, page); /* diff --git a/mm/zswap.c b/mm/zswap.c index 0030ce8fecfc..f6316b66fb23 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -43,7 +43,7 @@ * statistics **********************************/ /* The number of compressed pages currently stored in zswap */ -atomic_t zswap_stored_pages = ATOMIC_INIT(0); +atomic_long_t zswap_stored_pages = ATOMIC_INIT(0); /* * The statistics below are not protected from concurrent access for @@ -402,7 +402,7 @@ static void __zswap_pool_empty(struct percpu_ref *ref) spin_unlock_bh(&zswap_pools_lock); } -static int __must_check zswap_pool_get(struct zswap_pool *pool) +static int __must_check zswap_pool_tryget(struct zswap_pool *pool) { if (!pool) return 0; @@ -410,6 +410,12 @@ static int __must_check zswap_pool_get(struct zswap_pool *pool) return percpu_ref_tryget(&pool->ref); } +/* The caller must already have a reference. */ +static void zswap_pool_get(struct zswap_pool *pool) +{ + percpu_ref_get(&pool->ref); +} + static void zswap_pool_put(struct zswap_pool *pool) { percpu_ref_put(&pool->ref); @@ -440,7 +446,7 @@ static struct zswap_pool *zswap_pool_current_get(void) rcu_read_lock(); pool = __zswap_pool_current(); - if (!zswap_pool_get(pool)) + if (!zswap_pool_tryget(pool)) pool = NULL; rcu_read_unlock(); @@ -461,7 +467,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) if (strcmp(zpool_get_type(pool->zpool), type)) continue; /* if we can't get it, it's about to be destroyed */ - if (!zswap_pool_get(pool)) + if (!zswap_pool_tryget(pool)) continue; return pool; } @@ -703,12 +709,11 @@ static void zswap_lru_add(struct list_lru *list_lru, struct zswap_entry *entry) /* * Note that it is safe to use rcu_read_lock() here, even in the face of - * concurrent memcg offlining. Thanks to the memcg->kmemcg_id indirection - * used in list_lru lookup, only two scenarios are possible: + * concurrent memcg offlining: * - * 1. list_lru_add() is called before memcg->kmemcg_id is updated. The + * 1. list_lru_add() is called before list_lru_one is dead. The * new entry will be reparented to memcg's parent's list_lru. - * 2. list_lru_add() is called after memcg->kmemcg_id is updated. The + * 2. list_lru_add() is called after list_lru_one is dead. The * new entry will be added directly to memcg's parent's list_lru. * * Similar reasoning holds for list_lru_del(). @@ -802,7 +807,7 @@ static void zswap_entry_free(struct zswap_entry *entry) obj_cgroup_put(entry->objcg); } zswap_entry_cache_free(entry); - atomic_dec(&zswap_stored_pages); + atomic_long_dec(&zswap_stored_pages); } /********************************* @@ -875,7 +880,8 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) return 0; } -static bool zswap_compress(struct folio *folio, struct zswap_entry *entry) +static bool zswap_compress(struct page *page, struct zswap_entry *entry, + struct zswap_pool *pool) { struct crypto_acomp_ctx *acomp_ctx; struct scatterlist input, output; @@ -887,13 +893,13 @@ static bool zswap_compress(struct folio *folio, struct zswap_entry *entry) gfp_t gfp; u8 *dst; - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); + acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); mutex_lock(&acomp_ctx->mutex); dst = acomp_ctx->buffer; sg_init_table(&input, 1); - sg_set_folio(&input, folio, PAGE_SIZE, 0); + sg_set_page(&input, page, PAGE_SIZE, 0); /* * We need PAGE_SIZE * 2 here since there maybe over-compression case, @@ -920,7 +926,7 @@ static bool zswap_compress(struct folio *folio, struct zswap_entry *entry) if (comp_ret) goto unlock; - zpool = entry->pool->zpool; + zpool = pool->zpool; gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; if (zpool_malloc_support_movable(zpool)) gfp |= __GFP_HIGHMEM | __GFP_MOVABLE; @@ -1096,7 +1102,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry, * for reclaim by this ratio. */ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_one *l, - spinlock_t *lock, void *arg) + void *arg) { struct zswap_entry *entry = container_of(item, struct zswap_entry, lru); bool *encountered_page_in_swapcache = (bool *)arg; @@ -1152,7 +1158,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o * It's safe to drop the lock here because we return either * LRU_REMOVED_RETRY or LRU_RETRY. */ - spin_unlock(lock); + spin_unlock(&l->lock); writeback_result = zswap_writeback_entry(entry, swpentry); @@ -1173,7 +1179,6 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o zswap_written_back_pages++; } - spin_lock(lock); return ret; } @@ -1233,7 +1238,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED); } else { nr_backing = zswap_total_pages(); - nr_stored = atomic_read(&zswap_stored_pages); + nr_stored = atomic_long_read(&zswap_stored_pages); } if (!nr_stored) @@ -1403,68 +1408,27 @@ resched: /********************************* * main API **********************************/ -bool zswap_store(struct folio *folio) + +static ssize_t zswap_store_page(struct page *page, + struct obj_cgroup *objcg, + struct zswap_pool *pool) { - swp_entry_t swp = folio->swap; - pgoff_t offset = swp_offset(swp); - struct xarray *tree = swap_zswap_tree(swp); + swp_entry_t page_swpentry = page_swap_entry(page); struct zswap_entry *entry, *old; - struct obj_cgroup *objcg = NULL; - struct mem_cgroup *memcg = NULL; - - VM_WARN_ON_ONCE(!folio_test_locked(folio)); - VM_WARN_ON_ONCE(!folio_test_swapcache(folio)); - - /* Large folios aren't supported */ - if (folio_test_large(folio)) - return false; - - if (!zswap_enabled) - goto check_old; - - /* Check cgroup limits */ - objcg = get_obj_cgroup_from_folio(folio); - if (objcg && !obj_cgroup_may_zswap(objcg)) { - memcg = get_mem_cgroup_from_objcg(objcg); - if (shrink_memcg(memcg)) { - mem_cgroup_put(memcg); - goto reject; - } - mem_cgroup_put(memcg); - } - - if (zswap_check_limits()) - goto reject; /* allocate entry */ - entry = zswap_entry_cache_alloc(GFP_KERNEL, folio_nid(folio)); + entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page)); if (!entry) { zswap_reject_kmemcache_fail++; - goto reject; - } - - /* if entry is successfully added, it keeps the reference */ - entry->pool = zswap_pool_current_get(); - if (!entry->pool) - goto freepage; - - if (objcg) { - memcg = get_mem_cgroup_from_objcg(objcg); - if (memcg_list_lru_alloc(memcg, &zswap_list_lru, GFP_KERNEL)) { - mem_cgroup_put(memcg); - goto put_pool; - } - mem_cgroup_put(memcg); + return -EINVAL; } - if (!zswap_compress(folio, entry)) - goto put_pool; - - entry->swpentry = swp; - entry->objcg = objcg; - entry->referenced = true; + if (!zswap_compress(page, entry, pool)) + goto compress_failed; - old = xa_store(tree, offset, entry, GFP_KERNEL); + old = xa_store(swap_zswap_tree(page_swpentry), + swp_offset(page_swpentry), + entry, GFP_KERNEL); if (xa_is_err(old)) { int err = xa_err(old); @@ -1481,10 +1445,15 @@ bool zswap_store(struct folio *folio) if (old) zswap_entry_free(old); - if (objcg) { - obj_cgroup_charge_zswap(objcg, entry->length); - count_objcg_events(objcg, ZSWPOUT, 1); - } + /* + * The entry is successfully compressed and stored in the tree, there is + * no further possibility of failure. Grab refs to the pool and objcg. + * These refs will be dropped by zswap_entry_free() when the entry is + * removed from the tree. + */ + zswap_pool_get(pool); + if (objcg) + obj_cgroup_get(objcg); /* * We finish initializing the entry while it's already in xarray. @@ -1496,37 +1465,115 @@ bool zswap_store(struct folio *folio) * The publishing order matters to prevent writeback from seeing * an incoherent entry. */ + entry->pool = pool; + entry->swpentry = page_swpentry; + entry->objcg = objcg; + entry->referenced = true; if (entry->length) { INIT_LIST_HEAD(&entry->lru); zswap_lru_add(&zswap_list_lru, entry); } - /* update stats */ - atomic_inc(&zswap_stored_pages); - count_vm_event(ZSWPOUT); - - return true; + return entry->length; store_failed: - zpool_free(entry->pool->zpool, entry->handle); -put_pool: - zswap_pool_put(entry->pool); -freepage: + zpool_free(pool->zpool, entry->handle); +compress_failed: zswap_entry_cache_free(entry); -reject: + return -EINVAL; +} + +bool zswap_store(struct folio *folio) +{ + long nr_pages = folio_nr_pages(folio); + swp_entry_t swp = folio->swap; + struct obj_cgroup *objcg = NULL; + struct mem_cgroup *memcg = NULL; + struct zswap_pool *pool; + size_t compressed_bytes = 0; + bool ret = false; + long index; + + VM_WARN_ON_ONCE(!folio_test_locked(folio)); + VM_WARN_ON_ONCE(!folio_test_swapcache(folio)); + + if (!zswap_enabled) + goto check_old; + + objcg = get_obj_cgroup_from_folio(folio); + if (objcg && !obj_cgroup_may_zswap(objcg)) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (shrink_memcg(memcg)) { + mem_cgroup_put(memcg); + goto put_objcg; + } + mem_cgroup_put(memcg); + } + + if (zswap_check_limits()) + goto put_objcg; + + pool = zswap_pool_current_get(); + if (!pool) + goto put_objcg; + + if (objcg) { + memcg = get_mem_cgroup_from_objcg(objcg); + if (memcg_list_lru_alloc(memcg, &zswap_list_lru, GFP_KERNEL)) { + mem_cgroup_put(memcg); + goto put_pool; + } + mem_cgroup_put(memcg); + } + + for (index = 0; index < nr_pages; ++index) { + struct page *page = folio_page(folio, index); + ssize_t bytes; + + bytes = zswap_store_page(page, objcg, pool); + if (bytes < 0) + goto put_pool; + compressed_bytes += bytes; + } + + if (objcg) { + obj_cgroup_charge_zswap(objcg, compressed_bytes); + count_objcg_events(objcg, ZSWPOUT, nr_pages); + } + + atomic_long_add(nr_pages, &zswap_stored_pages); + count_vm_events(ZSWPOUT, nr_pages); + + ret = true; + +put_pool: + zswap_pool_put(pool); +put_objcg: obj_cgroup_put(objcg); - if (zswap_pool_reached_full) + if (!ret && zswap_pool_reached_full) queue_work(shrink_wq, &zswap_shrink_work); check_old: /* - * If the zswap store fails or zswap is disabled, we must invalidate the - * possibly stale entry which was previously stored at this offset. - * Otherwise, writeback could overwrite the new data in the swapfile. + * If the zswap store fails or zswap is disabled, we must invalidate + * the possibly stale entries which were previously stored at the + * offsets corresponding to each page of the folio. Otherwise, + * writeback could overwrite the new data in the swapfile. */ - entry = xa_erase(tree, offset); - if (entry) - zswap_entry_free(entry); - return false; + if (!ret) { + unsigned type = swp_type(swp); + pgoff_t offset = swp_offset(swp); + struct zswap_entry *entry; + struct xarray *tree; + + for (index = 0; index < nr_pages; ++index) { + tree = swap_zswap_tree(swp_entry(type, offset + index)); + entry = xa_erase(tree, offset + index); + if (entry) + zswap_entry_free(entry); + } + } + + return ret; } bool zswap_load(struct folio *folio) @@ -1594,6 +1641,9 @@ void zswap_invalidate(swp_entry_t swp) struct xarray *tree = swap_zswap_tree(swp); struct zswap_entry *entry; + if (xa_empty(tree)) + return; + entry = xa_erase(tree, offset); if (entry) zswap_entry_free(entry); @@ -1651,6 +1701,13 @@ static int debugfs_get_total_size(void *data, u64 *val) } DEFINE_DEBUGFS_ATTRIBUTE(total_size_fops, debugfs_get_total_size, NULL, "%llu\n"); +static int debugfs_get_stored_pages(void *data, u64 *val) +{ + *val = atomic_long_read(&zswap_stored_pages); + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(stored_pages_fops, debugfs_get_stored_pages, NULL, "%llu\n"); + static int zswap_debugfs_init(void) { if (!debugfs_initialized()) @@ -1674,8 +1731,8 @@ static int zswap_debugfs_init(void) zswap_debugfs_root, &zswap_written_back_pages); debugfs_create_file("pool_total_size", 0444, zswap_debugfs_root, NULL, &total_size_fops); - debugfs_create_atomic_t("stored_pages", 0444, - zswap_debugfs_root, &zswap_stored_pages); + debugfs_create_file("stored_pages", 0444, + zswap_debugfs_root, NULL, &stored_pages_fops); return 0; } diff --git a/scripts/module.lds.S b/scripts/module.lds.S index 3f43edef813c..711c6e029936 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -50,7 +50,7 @@ SECTIONS { .data : { *(.data .data.[0-9a-zA-Z_]*) *(.data..L*) - CODETAG_SECTIONS() + MOD_CODETAG_SECTIONS() } .rodata : { @@ -59,9 +59,10 @@ SECTIONS { } #else .data : { - CODETAG_SECTIONS() + MOD_CODETAG_SECTIONS() } #endif + MOD_SEPARATE_CODETAG_SECTIONS() } /* bring in arch-specific sections */ diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index 6ce1f1ceb432..1ea2c4c33b86 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -79,6 +79,9 @@ #define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ +#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */ +#define MADV_GUARD_REMOVE 103 /* unguard range */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/tools/mm/page_owner_sort.c b/tools/mm/page_owner_sort.c index e1f264444342..880e36df0c11 100644 --- a/tools/mm/page_owner_sort.c +++ b/tools/mm/page_owner_sort.c @@ -377,6 +377,7 @@ static char *get_comm(char *buf) if (errno != 0) { if (debug_on) fprintf(stderr, "wrong comm in follow buf:\n%s\n", buf); + free(comm_str); return NULL; } diff --git a/tools/mm/slabinfo.c b/tools/mm/slabinfo.c index 04e9e6ba86ea..1433eff99feb 100644 --- a/tools/mm/slabinfo.c +++ b/tools/mm/slabinfo.c @@ -21,7 +21,7 @@ #include <regex.h> #include <errno.h> -#define MAX_SLABS 500 +#define MAX_SLABS 2000 #define MAX_ALIASES 500 #define MAX_NODES 1024 @@ -1228,6 +1228,8 @@ static void read_slab_dir(void) continue; switch (de->d_type) { case DT_LNK: + if (alias - aliasinfo == MAX_ALIASES) + fatal("Too many aliases\n"); alias->name = strdup(de->d_name); count = readlink(de->d_name, buffer, sizeof(buffer)-1); @@ -1242,6 +1244,8 @@ static void read_slab_dir(void) alias++; break; case DT_DIR: + if (slab - slabinfo == MAX_SLABS) + fatal("Too many slabs\n"); if (chdir(de->d_name)) fatal("Unable to access slab %s\n", slab->name); slab->name = strdup(de->d_name); @@ -1312,10 +1316,6 @@ static void read_slab_dir(void) slabs = slab - slabinfo; actual_slabs = slabs; aliases = alias - aliasinfo; - if (slabs > MAX_SLABS) - fatal("Too many slabs\n"); - if (aliases > MAX_ALIASES) - fatal("Too many aliases\n"); } static void output_slabs(void) diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 551ae6898c1d..bc30050227fd 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -462,6 +462,28 @@ static noinline void __init check_new_node(struct maple_tree *mt) MT_BUG_ON(mt, mas_allocated(&mas) != 10 + MAPLE_ALLOC_SLOTS - 1); mas_destroy(&mas); + mas.node = MA_ERROR(-ENOMEM); + mas_node_count(&mas, MAPLE_ALLOC_SLOTS + 1); /* Request */ + mas_nomem(&mas, GFP_KERNEL); /* Fill request */ + MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 1); + mas.node = MA_ERROR(-ENOMEM); + mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 2 + 2); /* Request */ + mas_nomem(&mas, GFP_KERNEL); /* Fill request */ + mas.status = ma_start; + MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 2 + 2); + mas_destroy(&mas); + + mas.node = MA_ERROR(-ENOMEM); + mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 2 + 1); /* Request */ + mas_nomem(&mas, GFP_KERNEL); /* Fill request */ + MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 2 + 1); + mas.node = MA_ERROR(-ENOMEM); + mas_node_count(&mas, MAPLE_ALLOC_SLOTS * 3 + 2); /* Request */ + mas_nomem(&mas, GFP_KERNEL); /* Fill request */ + mas.status = ma_start; + MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS * 3 + 2); + mas_destroy(&mas); + mtree_unlock(mt); } diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh index aa995516870b..54d45791b0d9 100644 --- a/tools/testing/selftests/damon/_debugfs_common.sh +++ b/tools/testing/selftests/damon/_debugfs_common.sh @@ -8,7 +8,12 @@ test_write_result() { expect_reason=$4 expected=$5 - echo "$content" > "$file" + if [ "$expected" = "0" ] + then + echo "$content" > "$file" + else + echo "$content" > "$file" 2> /dev/null + fi if [ $? -ne "$expected" ] then echo "writing $content to $file doesn't return $expected" diff --git a/tools/testing/selftests/damon/access_memory_even.c b/tools/testing/selftests/damon/access_memory_even.c index 3be121487432..a9f4e9aaf3a9 100644 --- a/tools/testing/selftests/damon/access_memory_even.c +++ b/tools/testing/selftests/damon/access_memory_even.c @@ -14,10 +14,8 @@ int main(int argc, char *argv[]) { char **regions; - clock_t start_clock; int nr_regions; int sz_region; - int access_time_ms; int i; if (argc != 3) { diff --git a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh index 4a76e37ef16b..bd6c22d96ead 100755 --- a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh +++ b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh @@ -12,7 +12,7 @@ then exit 1 fi -if echo foo > "$DBGFS/mk_contexts" +if echo foo > "$DBGFS/mk_contexts" 2> /dev/null then echo "duplicate context creation success" exit 1 diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c index a6fe0689f88d..53e69a669668 100644 --- a/tools/testing/selftests/damon/huge_count_read_write.c +++ b/tools/testing/selftests/damon/huge_count_read_write.c @@ -18,7 +18,7 @@ void write_read_with_huge_count(char *file) { int filedesc = open(file, O_RDWR); - char buf[25]; + char buf[256]; int ret; printf("%s %s\n", __func__, file); @@ -28,9 +28,7 @@ void write_read_with_huge_count(char *file) } write(filedesc, "", 0xfffffffful); - perror("after write: "); ret = read(filedesc, buf, 0xfffffffful); - perror("after read: "); close(filedesc); } diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index da030b43e43b..8f01f4da1c0d 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -51,3 +51,7 @@ hugetlb_madv_vs_map mseal_test seal_elf droppable +hugetlb_dio +pkey_sighandler_tests_32 +pkey_sighandler_tests_64 +guard-pages diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 321e63955272..3de23ea4663f 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -90,6 +90,7 @@ TEST_GEN_FILES += hugetlb_fault_after_madv TEST_GEN_FILES += hugetlb_madv_vs_map TEST_GEN_FILES += hugetlb_dio TEST_GEN_FILES += droppable +TEST_GEN_FILES += guard-pages ifneq ($(ARCH),arm64) TEST_GEN_FILES += soft-dirty @@ -126,7 +127,9 @@ endif ifneq (,$(filter $(ARCH),arm64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390)) TEST_GEN_FILES += va_high_addr_switch +ifneq ($(ARCH),riscv64) TEST_GEN_FILES += virtual_address_range +endif TEST_GEN_FILES += write_to_hugetlbfs endif diff --git a/tools/testing/selftests/mm/guard-pages.c b/tools/testing/selftests/mm/guard-pages.c new file mode 100644 index 000000000000..7cdf815d0d63 --- /dev/null +++ b/tools/testing/selftests/mm/guard-pages.c @@ -0,0 +1,1243 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "../kselftest_harness.h" +#include <asm-generic/mman.h> /* Force the import of the tools version. */ +#include <assert.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/userfaultfd.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <sys/uio.h> +#include <unistd.h> + +/* + * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: + * + * "If the signal occurs other than as the result of calling the abort or raise + * function, the behavior is undefined if the signal handler refers to any + * object with static storage duration other than by assigning a value to an + * object declared as volatile sig_atomic_t" + */ +static volatile sig_atomic_t signal_jump_set; +static sigjmp_buf signal_jmp_buf; + +/* + * Ignore the checkpatch warning, we must read from x but don't want to do + * anything with it in order to trigger a read page fault. We therefore must use + * volatile to stop the compiler from optimising this away. + */ +#define FORCE_READ(x) (*(volatile typeof(x) *)x) + +static int userfaultfd(int flags) +{ + return syscall(SYS_userfaultfd, flags); +} + +static void handle_fatal(int c) +{ + if (!signal_jump_set) + return; + + siglongjmp(signal_jmp_buf, c); +} + +static int pidfd_open(pid_t pid, unsigned int flags) +{ + return syscall(SYS_pidfd_open, pid, flags); +} + +/* + * Enable our signal catcher and try to read/write the specified buffer. The + * return value indicates whether the read/write succeeds without a fatal + * signal. + */ +static bool try_access_buf(char *ptr, bool write) +{ + bool failed; + + /* Tell signal handler to jump back here on fatal signal. */ + signal_jump_set = true; + /* If a fatal signal arose, we will jump back here and failed is set. */ + failed = sigsetjmp(signal_jmp_buf, 0) != 0; + + if (!failed) { + if (write) + *ptr = 'x'; + else + FORCE_READ(ptr); + } + + signal_jump_set = false; + return !failed; +} + +/* Try and read from a buffer, return true if no fatal signal. */ +static bool try_read_buf(char *ptr) +{ + return try_access_buf(ptr, false); +} + +/* Try and write to a buffer, return true if no fatal signal. */ +static bool try_write_buf(char *ptr) +{ + return try_access_buf(ptr, true); +} + +/* + * Try and BOTH read from AND write to a buffer, return true if BOTH operations + * succeed. + */ +static bool try_read_write_buf(char *ptr) +{ + return try_read_buf(ptr) && try_write_buf(ptr); +} + +FIXTURE(guard_pages) +{ + unsigned long page_size; +}; + +FIXTURE_SETUP(guard_pages) +{ + struct sigaction act = { + .sa_handler = &handle_fatal, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction"); + + self->page_size = (unsigned long)sysconf(_SC_PAGESIZE); +}; + +FIXTURE_TEARDOWN(guard_pages) +{ + struct sigaction act = { + .sa_handler = SIG_DFL, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + sigaction(SIGSEGV, &act, NULL); +} + +TEST_F(guard_pages, basic) +{ + const unsigned long NUM_PAGES = 10; + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + ptr = mmap(NULL, NUM_PAGES * page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANON, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Trivially assert we can touch the first page. */ + ASSERT_TRUE(try_read_write_buf(ptr)); + + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + + /* Establish that 1st page SIGSEGV's. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + + /* Ensure we can touch everything else.*/ + for (i = 1; i < NUM_PAGES; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Establish a guard page at the end of the mapping. */ + ASSERT_EQ(madvise(&ptr[(NUM_PAGES - 1) * page_size], page_size, + MADV_GUARD_INSTALL), 0); + + /* Check that both guard pages result in SIGSEGV. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[(NUM_PAGES - 1) * page_size])); + + /* Remove the first guard page. */ + ASSERT_FALSE(madvise(ptr, page_size, MADV_GUARD_REMOVE)); + + /* Make sure we can touch it. */ + ASSERT_TRUE(try_read_write_buf(ptr)); + + /* Remove the last guard page. */ + ASSERT_FALSE(madvise(&ptr[(NUM_PAGES - 1) * page_size], page_size, + MADV_GUARD_REMOVE)); + + /* Make sure we can touch it. */ + ASSERT_TRUE(try_read_write_buf(&ptr[(NUM_PAGES - 1) * page_size])); + + /* + * Test setting a _range_ of pages, namely the first 3. The first of + * these be faulted in, so this also tests that we can install guard + * pages over backed pages. + */ + ASSERT_EQ(madvise(ptr, 3 * page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure they are all guard pages. */ + for (i = 0; i < 3; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Make sure the rest are not. */ + for (i = 3; i < NUM_PAGES; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Remove guard pages. */ + ASSERT_EQ(madvise(ptr, NUM_PAGES * page_size, MADV_GUARD_REMOVE), 0); + + /* Now make sure we can touch everything. */ + for (i = 0; i < NUM_PAGES; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* + * Now remove all guard pages, make sure we don't remove existing + * entries. + */ + ASSERT_EQ(madvise(ptr, NUM_PAGES * page_size, MADV_GUARD_REMOVE), 0); + + for (i = 0; i < NUM_PAGES * page_size; i += page_size) { + char chr = ptr[i]; + + ASSERT_EQ(chr, 'x'); + } + + ASSERT_EQ(munmap(ptr, NUM_PAGES * page_size), 0); +} + +/* Assert that operations applied across multiple VMAs work as expected. */ +TEST_F(guard_pages, multi_vma) +{ + const unsigned long page_size = self->page_size; + char *ptr_region, *ptr, *ptr1, *ptr2, *ptr3; + int i; + + /* Reserve a 100 page region over which we can install VMAs. */ + ptr_region = mmap(NULL, 100 * page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr_region, MAP_FAILED); + + /* Place a VMA of 10 pages size at the start of the region. */ + ptr1 = mmap(ptr_region, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr1, MAP_FAILED); + + /* Place a VMA of 5 pages size 50 pages into the region. */ + ptr2 = mmap(&ptr_region[50 * page_size], 5 * page_size, + PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* Place a VMA of 20 pages size at the end of the region. */ + ptr3 = mmap(&ptr_region[80 * page_size], 20 * page_size, + PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr3, MAP_FAILED); + + /* Unmap gaps. */ + ASSERT_EQ(munmap(&ptr_region[10 * page_size], 40 * page_size), 0); + ASSERT_EQ(munmap(&ptr_region[55 * page_size], 25 * page_size), 0); + + /* + * We end up with VMAs like this: + * + * 0 10 .. 50 55 .. 80 100 + * [---] [---] [---] + */ + + /* + * Now mark the whole range as guard pages and make sure all VMAs are as + * such. + */ + + /* + * madvise() is certifiable and lets you perform operations over gaps, + * everything works, but it indicates an error and errno is set to + * -ENOMEM. Also if anything runs out of memory it is set to + * -ENOMEM. You are meant to guess which is which. + */ + ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_INSTALL), -1); + ASSERT_EQ(errno, ENOMEM); + + for (i = 0; i < 10; i++) { + char *curr = &ptr1[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + for (i = 0; i < 5; i++) { + char *curr = &ptr2[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + for (i = 0; i < 20; i++) { + char *curr = &ptr3[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now remove guar pages over range and assert the opposite. */ + + ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_REMOVE), -1); + ASSERT_EQ(errno, ENOMEM); + + for (i = 0; i < 10; i++) { + char *curr = &ptr1[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + for (i = 0; i < 5; i++) { + char *curr = &ptr2[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + for (i = 0; i < 20; i++) { + char *curr = &ptr3[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Now map incompatible VMAs in the gaps. */ + ptr = mmap(&ptr_region[10 * page_size], 40 * page_size, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr = mmap(&ptr_region[55 * page_size], 25 * page_size, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * We end up with VMAs like this: + * + * 0 10 .. 50 55 .. 80 100 + * [---][xxxx][---][xxxx][---] + * + * Where 'x' signifies VMAs that cannot be merged with those adjacent to + * them. + */ + + /* Multiple VMAs adjacent to one another should result in no error. */ + ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_INSTALL), 0); + for (i = 0; i < 100; i++) { + char *curr = &ptr_region[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + ASSERT_EQ(madvise(ptr_region, 100 * page_size, MADV_GUARD_REMOVE), 0); + for (i = 0; i < 100; i++) { + char *curr = &ptr_region[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr_region, 100 * page_size), 0); +} + +/* + * Assert that batched operations performed using process_madvise() work as + * expected. + */ +TEST_F(guard_pages, process_madvise) +{ + const unsigned long page_size = self->page_size; + pid_t pid = getpid(); + int pidfd = pidfd_open(pid, 0); + char *ptr_region, *ptr1, *ptr2, *ptr3; + ssize_t count; + struct iovec vec[6]; + + ASSERT_NE(pidfd, -1); + + /* Reserve region to map over. */ + ptr_region = mmap(NULL, 100 * page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr_region, MAP_FAILED); + + /* + * 10 pages offset 1 page into reserve region. We MAP_POPULATE so we + * overwrite existing entries and test this code path against + * overwriting existing entries. + */ + ptr1 = mmap(&ptr_region[page_size], 10 * page_size, + PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE | MAP_POPULATE, -1, 0); + ASSERT_NE(ptr1, MAP_FAILED); + /* We want guard markers at start/end of each VMA. */ + vec[0].iov_base = ptr1; + vec[0].iov_len = page_size; + vec[1].iov_base = &ptr1[9 * page_size]; + vec[1].iov_len = page_size; + + /* 5 pages offset 50 pages into reserve region. */ + ptr2 = mmap(&ptr_region[50 * page_size], 5 * page_size, + PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + vec[2].iov_base = ptr2; + vec[2].iov_len = page_size; + vec[3].iov_base = &ptr2[4 * page_size]; + vec[3].iov_len = page_size; + + /* 20 pages offset 79 pages into reserve region. */ + ptr3 = mmap(&ptr_region[79 * page_size], 20 * page_size, + PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr3, MAP_FAILED); + vec[4].iov_base = ptr3; + vec[4].iov_len = page_size; + vec[5].iov_base = &ptr3[19 * page_size]; + vec[5].iov_len = page_size; + + /* Free surrounding VMAs. */ + ASSERT_EQ(munmap(ptr_region, page_size), 0); + ASSERT_EQ(munmap(&ptr_region[11 * page_size], 39 * page_size), 0); + ASSERT_EQ(munmap(&ptr_region[55 * page_size], 24 * page_size), 0); + ASSERT_EQ(munmap(&ptr_region[99 * page_size], page_size), 0); + + /* Now guard in one step. */ + count = process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); + + /* OK we don't have permission to do this, skip. */ + if (count == -1 && errno == EPERM) + ksft_exit_skip("No process_madvise() permissions, try running as root.\n"); + + /* Returns the number of bytes advised. */ + ASSERT_EQ(count, 6 * page_size); + + /* Now make sure the guarding was applied. */ + + ASSERT_FALSE(try_read_write_buf(ptr1)); + ASSERT_FALSE(try_read_write_buf(&ptr1[9 * page_size])); + + ASSERT_FALSE(try_read_write_buf(ptr2)); + ASSERT_FALSE(try_read_write_buf(&ptr2[4 * page_size])); + + ASSERT_FALSE(try_read_write_buf(ptr3)); + ASSERT_FALSE(try_read_write_buf(&ptr3[19 * page_size])); + + /* Now do the same with unguard... */ + count = process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); + + /* ...and everything should now succeed. */ + + ASSERT_TRUE(try_read_write_buf(ptr1)); + ASSERT_TRUE(try_read_write_buf(&ptr1[9 * page_size])); + + ASSERT_TRUE(try_read_write_buf(ptr2)); + ASSERT_TRUE(try_read_write_buf(&ptr2[4 * page_size])); + + ASSERT_TRUE(try_read_write_buf(ptr3)); + ASSERT_TRUE(try_read_write_buf(&ptr3[19 * page_size])); + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr1, 10 * page_size), 0); + ASSERT_EQ(munmap(ptr2, 5 * page_size), 0); + ASSERT_EQ(munmap(ptr3, 20 * page_size), 0); + close(pidfd); +} + +/* Assert that unmapping ranges does not leave guard markers behind. */ +TEST_F(guard_pages, munmap) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr_new1, *ptr_new2; + + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard first and last pages. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + ASSERT_EQ(madvise(&ptr[9 * page_size], page_size, MADV_GUARD_INSTALL), 0); + + /* Assert that they are guarded. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[9 * page_size])); + + /* Unmap them. */ + ASSERT_EQ(munmap(ptr, page_size), 0); + ASSERT_EQ(munmap(&ptr[9 * page_size], page_size), 0); + + /* Map over them.*/ + ptr_new1 = mmap(ptr, page_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr_new1, MAP_FAILED); + ptr_new2 = mmap(&ptr[9 * page_size], page_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr_new2, MAP_FAILED); + + /* Assert that they are now not guarded. */ + ASSERT_TRUE(try_read_write_buf(ptr_new1)); + ASSERT_TRUE(try_read_write_buf(ptr_new2)); + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Assert that mprotect() operations have no bearing on guard markers. */ +TEST_F(guard_pages, mprotect) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard the middle of the range. */ + ASSERT_EQ(madvise(&ptr[5 * page_size], 2 * page_size, + MADV_GUARD_INSTALL), 0); + + /* Assert that it is indeed guarded. */ + ASSERT_FALSE(try_read_write_buf(&ptr[5 * page_size])); + ASSERT_FALSE(try_read_write_buf(&ptr[6 * page_size])); + + /* Now make these pages read-only. */ + ASSERT_EQ(mprotect(&ptr[5 * page_size], 2 * page_size, PROT_READ), 0); + + /* Make sure the range is still guarded. */ + ASSERT_FALSE(try_read_buf(&ptr[5 * page_size])); + ASSERT_FALSE(try_read_buf(&ptr[6 * page_size])); + + /* Make sure we can guard again without issue.*/ + ASSERT_EQ(madvise(&ptr[5 * page_size], 2 * page_size, + MADV_GUARD_INSTALL), 0); + + /* Make sure the range is, yet again, still guarded. */ + ASSERT_FALSE(try_read_buf(&ptr[5 * page_size])); + ASSERT_FALSE(try_read_buf(&ptr[6 * page_size])); + + /* Now unguard the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Make sure the whole range is readable. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Split and merge VMAs and make sure guard pages still behave. */ +TEST_F(guard_pages, split_merge) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr_new; + int i; + + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the whole range is guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now unmap some pages in the range so we split. */ + ASSERT_EQ(munmap(&ptr[2 * page_size], page_size), 0); + ASSERT_EQ(munmap(&ptr[5 * page_size], page_size), 0); + ASSERT_EQ(munmap(&ptr[8 * page_size], page_size), 0); + + /* Make sure the remaining ranges are guarded post-split. */ + for (i = 0; i < 2; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + for (i = 2; i < 5; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + for (i = 6; i < 8; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + for (i = 9; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now map them again - the unmap will have cleared the guards. */ + ptr_new = mmap(&ptr[2 * page_size], page_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + ptr_new = mmap(&ptr[5 * page_size], page_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + ptr_new = mmap(&ptr[8 * page_size], page_size, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + + /* Now make sure guard pages are established. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + bool expect_true = i == 2 || i == 5 || i == 8; + + ASSERT_TRUE(expect_true ? result : !result); + } + + /* Now guard everything again. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the whole range is guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now split the range into three. */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0); + ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, PROT_READ), 0); + + /* Make sure the whole range is guarded for read. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_buf(curr)); + } + + /* Now reset protection bits so we merge the whole thing. */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ | PROT_WRITE), 0); + ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE), 0); + + /* Make sure the whole range is still guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Split range into 3 again... */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ), 0); + ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, PROT_READ), 0); + + /* ...and unguard the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Make sure the whole range is remedied for read. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_buf(curr)); + } + + /* Merge them again. */ + ASSERT_EQ(mprotect(ptr, 3 * page_size, PROT_READ | PROT_WRITE), 0); + ASSERT_EQ(mprotect(&ptr[7 * page_size], 3 * page_size, + PROT_READ | PROT_WRITE), 0); + + /* Now ensure the merged range is remedied for read/write. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Assert that MADV_DONTNEED does not remove guard markers. */ +TEST_F(guard_pages, dontneed) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Back the whole range. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + *curr = 'y'; + } + + /* Guard every other page. */ + for (i = 0; i < 10; i += 2) { + char *curr = &ptr[i * page_size]; + int res = madvise(curr, page_size, MADV_GUARD_INSTALL); + + ASSERT_EQ(res, 0); + } + + /* Indicate that we don't need any of the range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_DONTNEED), 0); + + /* Check to ensure guard markers are still in place. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_buf(curr); + + if (i % 2 == 0) { + ASSERT_FALSE(result); + } else { + ASSERT_TRUE(result); + /* Make sure we really did get reset to zero page. */ + ASSERT_EQ(*curr, '\0'); + } + + /* Now write... */ + result = try_write_buf(&ptr[i * page_size]); + + /* ...and make sure same result. */ + ASSERT_TRUE(i % 2 != 0 ? result : !result); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Assert that mlock()'ed pages work correctly with guard markers. */ +TEST_F(guard_pages, mlock) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Populate. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + *curr = 'y'; + } + + /* Lock. */ + ASSERT_EQ(mlock(ptr, 10 * page_size), 0); + + /* Now try to guard, should fail with EINVAL. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), -1); + ASSERT_EQ(errno, EINVAL); + + /* OK unlock. */ + ASSERT_EQ(munlock(ptr, 10 * page_size), 0); + + /* Guard first half of range, should now succeed. */ + ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure guard works. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + + if (i < 5) { + ASSERT_FALSE(result); + } else { + ASSERT_TRUE(result); + ASSERT_EQ(*curr, 'x'); + } + } + + /* + * Now lock the latter part of the range. We can't lock the guard pages, + * as this would result in the pages being populated and the guarding + * would cause this to error out. + */ + ASSERT_EQ(mlock(&ptr[5 * page_size], 5 * page_size), 0); + + /* + * Now remove guard pages, we permit mlock()'d ranges to have guard + * pages removed as it is a non-destructive operation. + */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* Now check that no guard pages remain. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Assert that moving, extending and shrinking memory via mremap() retains + * guard markers where possible. + * + * - Moving a mapping alone should retain markers as they are. + */ +TEST_F(guard_pages, mremap_move) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr_new; + + /* Map 5 pages. */ + ptr = mmap(NULL, 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Place guard markers at both ends of the 5 page span. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the guard pages are in effect. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* Map a new region we will move this range into. Doing this ensures + * that we have reserved a range to map into. + */ + ptr_new = mmap(NULL, 5 * page_size, PROT_NONE, MAP_ANON | MAP_PRIVATE, + -1, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + + ASSERT_EQ(mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr_new), ptr_new); + + /* Make sure the guard markers are retained. */ + ASSERT_FALSE(try_read_write_buf(ptr_new)); + ASSERT_FALSE(try_read_write_buf(&ptr_new[4 * page_size])); + + /* + * Clean up - we only need reference the new pointer as we overwrote the + * PROT_NONE range and moved the existing one. + */ + munmap(ptr_new, 5 * page_size); +} + +/* + * Assert that moving, extending and shrinking memory via mremap() retains + * guard markers where possible. + * + * Expanding should retain guard pages, only now in different position. The user + * will have to remove guard pages manually to fix up (they'd have to do the + * same if it were a PROT_NONE mapping). + */ +TEST_F(guard_pages, mremap_expand) +{ + const unsigned long page_size = self->page_size; + char *ptr, *ptr_new; + + /* Map 10 pages... */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + /* ...But unmap the last 5 so we can ensure we can expand into them. */ + ASSERT_EQ(munmap(&ptr[5 * page_size], 5 * page_size), 0); + + /* Place guard markers at both ends of the 5 page span. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the guarding is in effect. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* Now expand to 10 pages. */ + ptr = mremap(ptr, 5 * page_size, 10 * page_size, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Make sure the guard markers are retained in their original positions. + */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* Reserve a region which we can move to and expand into. */ + ptr_new = mmap(NULL, 20 * page_size, PROT_NONE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr_new, MAP_FAILED); + + /* Now move and expand into it. */ + ptr = mremap(ptr, 10 * page_size, 20 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr_new); + ASSERT_EQ(ptr, ptr_new); + + /* + * Again, make sure the guard markers are retained in their original positions. + */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* + * A real user would have to remove guard markers, but would reasonably + * expect all characteristics of the mapping to be retained, including + * guard markers. + */ + + /* Cleanup. */ + munmap(ptr, 20 * page_size); +} +/* + * Assert that moving, extending and shrinking memory via mremap() retains + * guard markers where possible. + * + * Shrinking will result in markers that are shrunk over being removed. Again, + * if the user were using a PROT_NONE mapping they'd have to manually fix this + * up also so this is OK. + */ +TEST_F(guard_pages, mremap_shrink) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + /* Map 5 pages. */ + ptr = mmap(NULL, 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Place guard markers at both ends of the 5 page span. */ + ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0); + ASSERT_EQ(madvise(&ptr[4 * page_size], page_size, MADV_GUARD_INSTALL), 0); + + /* Make sure the guarding is in effect. */ + ASSERT_FALSE(try_read_write_buf(ptr)); + ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size])); + + /* Now shrink to 3 pages. */ + ptr = mremap(ptr, 5 * page_size, 3 * page_size, MREMAP_MAYMOVE); + ASSERT_NE(ptr, MAP_FAILED); + + /* We expect the guard marker at the start to be retained... */ + ASSERT_FALSE(try_read_write_buf(ptr)); + + /* ...But remaining pages will not have guard markers. */ + for (i = 1; i < 3; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* + * As with expansion, a real user would have to remove guard pages and + * fixup. But you'd have to do similar manual things with PROT_NONE + * mappings too. + */ + + /* + * If we expand back to the original size, the end marker will, of + * course, no longer be present. + */ + ptr = mremap(ptr, 3 * page_size, 5 * page_size, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Again, we expect the guard marker at the start to be retained... */ + ASSERT_FALSE(try_read_write_buf(ptr)); + + /* ...But remaining pages will not have guard markers. */ + for (i = 1; i < 5; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + munmap(ptr, 5 * page_size); +} + +/* + * Assert that forking a process with VMAs that do not have VM_WIPEONFORK set + * retain guard pages. + */ +TEST_F(guard_pages, fork) +{ + const unsigned long page_size = self->page_size; + char *ptr; + pid_t pid; + int i; + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Establish guard apges in the first 5 pages. */ + ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); + + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) { + /* This is the child process now. */ + + /* Assert that the guarding is in effect. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + + ASSERT_TRUE(i >= 5 ? result : !result); + } + + /* Now unguard the range.*/ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + exit(0); + } + + /* Parent process. */ + + /* Parent simply waits on child. */ + waitpid(pid, NULL, 0); + + /* Child unguard does not impact parent page table state. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + + ASSERT_TRUE(i >= 5 ? result : !result); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* + * Assert that forking a process with VMAs that do have VM_WIPEONFORK set + * behave as expected. + */ +TEST_F(guard_pages, fork_wipeonfork) +{ + const unsigned long page_size = self->page_size; + char *ptr; + pid_t pid; + int i; + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Mark wipe on fork. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_WIPEONFORK), 0); + + /* Guard the first 5 pages. */ + ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); + + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) { + /* This is the child process now. */ + + /* Guard will have been wiped. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_TRUE(try_read_write_buf(curr)); + } + + exit(0); + } + + /* Parent process. */ + + waitpid(pid, NULL, 0); + + /* Guard markers should be in effect.*/ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + bool result = try_read_write_buf(curr); + + ASSERT_TRUE(i >= 5 ? result : !result); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Ensure that MADV_FREE retains guard entries as expected. */ +TEST_F(guard_pages, lazyfree) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Ensure guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Lazyfree range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_FREE), 0); + + /* This should leave the guard markers in place. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Ensure that MADV_POPULATE_READ, MADV_POPULATE_WRITE behave as expected. */ +TEST_F(guard_pages, populate) +{ + const unsigned long page_size = self->page_size; + char *ptr; + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Populate read should error out... */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_POPULATE_READ), -1); + ASSERT_EQ(errno, EFAULT); + + /* ...as should populate write. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_POPULATE_WRITE), -1); + ASSERT_EQ(errno, EFAULT); + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Ensure that MADV_COLD, MADV_PAGEOUT do not remove guard markers. */ +TEST_F(guard_pages, cold_pageout) +{ + const unsigned long page_size = self->page_size; + char *ptr; + int i; + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Guard range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* Ensured guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Now mark cold. This should have no impact on guard markers. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_COLD), 0); + + /* Should remain guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* OK, now page out. This should equally, have no effect on markers. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_PAGEOUT), 0); + + /* Should remain guarded. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* Ensure that guard pages do not break userfaultd. */ +TEST_F(guard_pages, uffd) +{ + const unsigned long page_size = self->page_size; + int uffd; + char *ptr; + int i; + struct uffdio_api api = { + .api = UFFD_API, + .features = 0, + }; + struct uffdio_register reg; + struct uffdio_range range; + + /* Set up uffd. */ + uffd = userfaultfd(0); + if (uffd == -1 && errno == EPERM) + ksft_exit_skip("No userfaultfd permissions, try running as root.\n"); + ASSERT_NE(uffd, -1); + + ASSERT_EQ(ioctl(uffd, UFFDIO_API, &api), 0); + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Register the range with uffd. */ + range.start = (unsigned long)ptr; + range.len = 10 * page_size; + reg.range = range; + reg.mode = UFFDIO_REGISTER_MODE_MISSING; + ASSERT_EQ(ioctl(uffd, UFFDIO_REGISTER, ®), 0); + + /* Guard the range. This should not trigger the uffd. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + + /* The guarding should behave as usual with no uffd intervention. */ + for (i = 0; i < 10; i++) { + char *curr = &ptr[i * page_size]; + + ASSERT_FALSE(try_read_write_buf(curr)); + } + + /* Cleanup. */ + ASSERT_EQ(ioctl(uffd, UFFDIO_UNREGISTER, &range), 0); + close(uffd); + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/hugetlb_fault_after_madv.c b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c index 73b81c632366..e2640529dbb2 100644 --- a/tools/testing/selftests/mm/hugetlb_fault_after_madv.c +++ b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c @@ -5,20 +5,36 @@ #include <sys/mman.h> #include <sys/types.h> #include <unistd.h> +#include <setjmp.h> +#include <signal.h> #include "vm_util.h" #include "../kselftest.h" -#define MMAP_SIZE (1 << 21) #define INLOOP_ITER 100 -char *huge_ptr; +static char *huge_ptr; +static size_t huge_page_size; + +static sigjmp_buf sigbuf; +static bool sigbus_triggered; + +static void signal_handler(int signal) +{ + if (signal == SIGBUS) { + sigbus_triggered = true; + siglongjmp(sigbuf, 1); + } +} /* Touch the memory while it is being madvised() */ void *touch(void *unused) { char *ptr = (char *)huge_ptr; + if (sigsetjmp(sigbuf, 1)) + return NULL; + for (int i = 0; i < INLOOP_ITER; i++) ptr[0] = '.'; @@ -30,7 +46,7 @@ void *madv(void *unused) usleep(rand() % 10); for (int i = 0; i < INLOOP_ITER; i++) - madvise(huge_ptr, MMAP_SIZE, MADV_DONTNEED); + madvise(huge_ptr, huge_page_size, MADV_DONTNEED); return NULL; } @@ -44,9 +60,23 @@ int main(void) * interactions */ int max = 10000; + int err; + + ksft_print_header(); + ksft_set_plan(1); srand(getpid()); + if (signal(SIGBUS, signal_handler) == SIG_ERR) + ksft_exit_skip("Could not register signal handler."); + + huge_page_size = default_huge_page_size(); + if (!huge_page_size) + ksft_exit_skip("Could not detect default hugetlb page size."); + + ksft_print_msg("[INFO] detected default hugetlb page size: %zu KiB\n", + huge_page_size / 1024); + free_hugepages = get_free_hugepages(); if (free_hugepages != 1) { ksft_exit_skip("This test needs one and only one page to execute. Got %lu\n", @@ -54,7 +84,7 @@ int main(void) } while (max--) { - huge_ptr = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE, + huge_ptr = mmap(NULL, huge_page_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); @@ -66,8 +96,14 @@ int main(void) pthread_join(thread1, NULL); pthread_join(thread2, NULL); - munmap(huge_ptr, MMAP_SIZE); + munmap(huge_ptr, huge_page_size); } - return KSFT_PASS; + ksft_test_result(!sigbus_triggered, "SIGBUS behavior\n"); + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + ksft_exit_pass(); } diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 2c5394584af4..2fc290d9430c 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -349,10 +349,12 @@ if [ $VADDR64 -ne 0 ]; then # allows high virtual address allocation requests independent # of platform's physical memory. - prev_policy=$(cat /proc/sys/vm/overcommit_memory) - echo 1 > /proc/sys/vm/overcommit_memory - CATEGORY="hugevm" run_test ./virtual_address_range - echo $prev_policy > /proc/sys/vm/overcommit_memory + if [ -x ./virtual_address_range ]; then + prev_policy=$(cat /proc/sys/vm/overcommit_memory) + echo 1 > /proc/sys/vm/overcommit_memory + CATEGORY="hugevm" run_test ./virtual_address_range + echo $prev_policy > /proc/sys/vm/overcommit_memory + fi # va high address boundary switch test ARCH_ARM64="arm64" diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 4e4c1e311247..2a2b69e91950 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -64,7 +64,7 @@ #define NR_CHUNKS_HIGH NR_CHUNKS_384TB #endif -static char *hind_addr(void) +static char *hint_addr(void) { int bits = HIGH_ADDR_SHIFT + rand() % (63 - HIGH_ADDR_SHIFT); @@ -185,7 +185,7 @@ int main(int argc, char *argv[]) } for (i = 0; i < NR_CHUNKS_HIGH; i++) { - hint = hind_addr(); + hint = hint_addr(); hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); diff --git a/tools/testing/shared/shared.mk b/tools/testing/shared/shared.mk index a6bc51d0b0bf..923ee2492256 100644 --- a/tools/testing/shared/shared.mk +++ b/tools/testing/shared/shared.mk @@ -69,6 +69,7 @@ generated/bit-length.h: FORCE @if ! grep -qws CONFIG_$(LONG_BIT)BIT generated/bit-length.h; then \ echo "Generating $@"; \ echo "#define CONFIG_$(LONG_BIT)BIT 1" > $@; \ + echo "#define CONFIG_PHYS_ADDR_T_$(LONG_BIT)BIT 1" >> $@; \ fi FORCE: ; diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c index b33b47342d41..8fab5e13c7c3 100644 --- a/tools/testing/vma/vma.c +++ b/tools/testing/vma/vma.c @@ -4,6 +4,8 @@ #include <stdio.h> #include <stdlib.h> +#include "generated/bit-length.h" + #include "maple-shared.h" #include "vma_internal.h" diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index c5b9da034511..e76ff579e1fd 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -44,7 +44,9 @@ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 #define VM_DONTEXPAND 0x00040000 +#define VM_LOCKONFAULT 0x00080000 #define VM_ACCOUNT 0x00100000 +#define VM_NORESERVE 0x00200000 #define VM_MIXEDMAP 0x10000000 #define VM_STACK VM_GROWSDOWN #define VM_SHADOW_STACK VM_NONE @@ -53,6 +55,14 @@ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) +/* This mask represents all the VMA flag bits used by mlock */ +#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) + +#ifdef CONFIG_64BIT +/* VM is sealed, in vm_flags */ +#define VM_SEALED _BITUL(63) +#endif + #define FIRST_USER_ADDRESS 0UL #define USER_PGTABLES_CEILING 0UL @@ -698,8 +708,9 @@ static inline void tlb_finish_mmu(struct mmu_gather *) { } -static inline void get_file(struct file *) +static inline struct file *get_file(struct file *f) { + return f; } static inline int vma_dup_policy(struct vm_area_struct *, struct vm_area_struct *) @@ -920,4 +931,106 @@ static inline bool signal_pending(void *) return false; } +static inline bool is_file_hugepages(struct file *) +{ + return false; +} + +static inline int security_vm_enough_memory_mm(struct mm_struct *, long) +{ + return true; +} + +static inline bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long) +{ + return true; +} + +static inline void vm_flags_init(struct vm_area_struct *vma, + vm_flags_t flags) +{ + vma->__vm_flags = flags; +} + +static inline void vm_flags_set(struct vm_area_struct *vma, + vm_flags_t flags) +{ + vma_start_write(vma); + vma->__vm_flags |= flags; +} + +static inline void vm_flags_clear(struct vm_area_struct *vma, + vm_flags_t flags) +{ + vma_start_write(vma); + vma->__vm_flags &= ~flags; +} + +static inline int call_mmap(struct file *, struct vm_area_struct *) +{ + return 0; +} + +static inline int shmem_zero_setup(struct vm_area_struct *) +{ + return 0; +} + +static inline void vma_set_anonymous(struct vm_area_struct *vma) +{ + vma->vm_ops = NULL; +} + +static inline void ksm_add_vma(struct vm_area_struct *) +{ +} + +static inline void perf_event_mmap(struct vm_area_struct *) +{ +} + +static inline bool vma_is_dax(struct vm_area_struct *) +{ + return false; +} + +static inline struct vm_area_struct *get_gate_vma(struct mm_struct *) +{ + return NULL; +} + +bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); + +/* Update vma->vm_page_prot to reflect vma->vm_flags. */ +static inline void vma_set_page_prot(struct vm_area_struct *vma) +{ + unsigned long vm_flags = vma->vm_flags; + pgprot_t vm_page_prot; + + /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */ + vm_page_prot = pgprot_modify(vma->vm_page_prot, vm_get_page_prot(vm_flags)); + + if (vma_wants_writenotify(vma, vm_page_prot)) { + vm_flags &= ~VM_SHARED; + /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */ + vm_page_prot = pgprot_modify(vm_page_prot, vm_get_page_prot(vm_flags)); + } + /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ + WRITE_ONCE(vma->vm_page_prot, vm_page_prot); +} + +static inline bool arch_validate_flags(unsigned long) +{ + return true; +} + +static inline void vma_close(struct vm_area_struct *) +{ +} + +static inline int mmap_file(struct file *, struct vm_area_struct *) +{ + return 0; +} + #endif /* __MM_VMA_INTERNAL_H */ |