diff options
| -rw-r--r-- | Documentation/admin-guide/kernel-parameters.txt | 7 | ||||
| -rw-r--r-- | Documentation/admin-guide/mm/hugetlbpage.rst | 4 | ||||
| -rw-r--r-- | Documentation/admin-guide/mm/memory-hotplug.rst | 4 | ||||
| -rw-r--r-- | Documentation/admin-guide/sysctl/vm.rst | 3 | ||||
| -rw-r--r-- | Documentation/mm/highmem.rst | 31 | ||||
| -rw-r--r-- | Documentation/mm/vmemmap_dedup.rst | 72 | ||||
| -rw-r--r-- | arch/arm64/mm/flush.c | 13 | ||||
| -rw-r--r-- | arch/x86/mm/hugetlbpage.c | 8 | ||||
| -rw-r--r-- | fs/Kconfig | 12 | ||||
| -rw-r--r-- | include/linux/highmem.h | 7 | ||||
| -rw-r--r-- | include/linux/hugetlb.h | 24 | ||||
| -rw-r--r-- | include/linux/mm.h | 9 | ||||
| -rw-r--r-- | include/linux/page-flags.h | 32 | ||||
| -rw-r--r-- | include/linux/swapops.h | 9 | ||||
| -rw-r--r-- | include/linux/sysctl.h | 4 | ||||
| -rw-r--r-- | include/ras/ras_event.h | 1 | ||||
| -rw-r--r-- | mm/hugetlb.c | 73 | ||||
| -rw-r--r-- | mm/hugetlb_vmemmap.c | 589 | ||||
| -rw-r--r-- | mm/hugetlb_vmemmap.h | 45 | ||||
| -rw-r--r-- | mm/memory-failure.c | 179 | ||||
| -rw-r--r-- | mm/sparse-vmemmap.c | 399 |
21 files changed, 823 insertions, 702 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 54a9756f2dad..db5de5f0b9d3 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1735,12 +1735,13 @@ hugetlb_free_vmemmap= [KNL] Reguires CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP enabled. + Control if HugeTLB Vmemmap Optimization (HVO) is enabled. Allows heavy hugetlb users to free up some more memory (7 * PAGE_SIZE for each 2MB hugetlb page). - Format: { [oO][Nn]/Y/y/1 | [oO][Ff]/N/n/0 (default) } + Format: { on | off (default) } - [oO][Nn]/Y/y/1: enable the feature - [oO][Ff]/N/n/0: disable the feature + on: enable HVO + off: disable HVO Built with CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y, the default is on. diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index a90330d0a837..8e2727dc18d4 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -164,8 +164,8 @@ default_hugepagesz will all result in 256 2M huge pages being allocated. Valid default huge page size is architecture dependent. hugetlb_free_vmemmap - When CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is set, this enables optimizing - unused vmemmap pages associated with each HugeTLB page. + When CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is set, this enables HugeTLB + Vmemmap Optimization (HVO). When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages`` indicates the current number of pre-allocated huge pages of the default size. diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index 0f56ecd8ac05..a3c9e8ad8fa0 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -653,8 +653,8 @@ block might fail: - Concurrent activity that operates on the same physical memory area, such as allocating gigantic pages, can result in temporary offlining failures. -- Out of memory when dissolving huge pages, especially when freeing unused - vmemmap pages associated with each hugetlb page is enabled. +- Out of memory when dissolving huge pages, especially when HugeTLB Vmemmap + Optimization (HVO) is enabled. Offlining code may be able to migrate huge page contents, but may not be able to dissolve the source huge page because it fails allocating (unmovable) pages diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index f74f722ad702..9b833e439f09 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -569,8 +569,7 @@ This knob is not available when the size of 'struct page' (a structure defined in include/linux/mm_types.h) is not power of two (an unusual system config could result in this). -Enable (set to 1) or disable (set to 0) the feature of optimizing vmemmap pages -associated with each HugeTLB page. +Enable (set to 1) or disable (set to 0) HugeTLB Vmemmap Optimization (HVO). Once enabled, the vmemmap pages of subsequent allocation of HugeTLB pages from buddy allocator will be optimized (7 pages per 2MB HugeTLB page and 4095 pages diff --git a/Documentation/mm/highmem.rst b/Documentation/mm/highmem.rst index c9887f241c6c..0f731d9196b0 100644 --- a/Documentation/mm/highmem.rst +++ b/Documentation/mm/highmem.rst @@ -60,17 +60,40 @@ list shows them in order of preference of use. This function should be preferred, where feasible, over all the others. These mappings are thread-local and CPU-local, meaning that the mapping - can only be accessed from within this thread and the thread is bound the - CPU while the mapping is active. Even if the thread is preempted (since - preemption is never disabled by the function) the CPU can not be - unplugged from the system via CPU-hotplug until the mapping is disposed. + can only be accessed from within this thread and the thread is bound to the + CPU while the mapping is active. Although preemption is never disabled by + this function, the CPU can not be unplugged from the system via + CPU-hotplug until the mapping is disposed. It's valid to take pagefaults in a local kmap region, unless the context in which the local mapping is acquired does not allow it for other reasons. + As said, pagefaults and preemption are never disabled. There is no need to + disable preemption because, when context switches to a different task, the + maps of the outgoing task are saved and those of the incoming one are + restored. + kmap_local_page() always returns a valid virtual address and it is assumed that kunmap_local() will never fail. + On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the + virtual address of the direct mapping. Only real highmem pages are + temporarily mapped. Therefore, users may call a plain page_address() + for pages which are known to not come from ZONE_HIGHMEM. However, it is + always safe to use kmap_local_page() / kunmap_local(). + + While it is significantly faster than kmap(), for the higmem case it + comes with restrictions about the pointers validity. Contrary to kmap() + mappings, the local mappings are only valid in the context of the caller + and cannot be handed to other contexts. This implies that users must + be absolutely sure to keep the use of the return address local to the + thread which mapped it. + + Most code can be designed to use thread local mappings. User should + therefore try to design their code to avoid the use of kmap() by mapping + pages in the same thread the address will be used and prefer + kmap_local_page(). + Nesting kmap_local_page() and kmap_atomic() mappings is allowed to a certain extent (up to KMAP_TYPE_NR) but their invocations have to be strictly ordered because the map implementation is stack based. See kmap_local_page() kdocs diff --git a/Documentation/mm/vmemmap_dedup.rst b/Documentation/mm/vmemmap_dedup.rst index c9c495f62d12..a4b12ff906c4 100644 --- a/Documentation/mm/vmemmap_dedup.rst +++ b/Documentation/mm/vmemmap_dedup.rst @@ -7,23 +7,25 @@ A vmemmap diet for HugeTLB and Device DAX HugeTLB ======= -The struct page structures (page structs) are used to describe a physical -page frame. By default, there is a one-to-one mapping from a page frame to -it's corresponding page struct. +This section is to explain how HugeTLB Vmemmap Optimization (HVO) works. + +The ``struct page`` structures are used to describe a physical page frame. By +default, there is a one-to-one mapping from a page frame to it's corresponding +``struct page``. HugeTLB pages consist of multiple base page size pages and is supported by many architectures. See Documentation/admin-guide/mm/hugetlbpage.rst for more details. On the x86-64 architecture, HugeTLB pages of size 2MB and 1GB are currently supported. Since the base page size on x86 is 4KB, a 2MB HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of 4096 base pages. -For each base page, there is a corresponding page struct. +For each base page, there is a corresponding ``struct page``. -Within the HugeTLB subsystem, only the first 4 page structs are used to -contain unique information about a HugeTLB page. __NR_USED_SUBPAGE provides -this upper limit. The only 'useful' information in the remaining page structs +Within the HugeTLB subsystem, only the first 4 ``struct page`` are used to +contain unique information about a HugeTLB page. ``__NR_USED_SUBPAGE`` provides +this upper limit. The only 'useful' information in the remaining ``struct page`` is the compound_head field, and this field is the same for all tail pages. -By removing redundant page structs for HugeTLB pages, memory can be returned +By removing redundant ``struct page`` for HugeTLB pages, memory can be returned to the buddy allocator for other uses. Different architectures support different HugeTLB pages. For example, the @@ -44,7 +46,7 @@ page. | | 64KB | 2MB | 512MB | 16GB | | +--------------+-----------+-----------+-----------+-----------+-----------+ -When the system boot up, every HugeTLB page has more than one struct page +When the system boot up, every HugeTLB page has more than one ``struct page`` structs which size is (unit: pages):: struct_size = HugeTLB_Size / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE @@ -74,10 +76,10 @@ Where n is how many pte entries which one page can contains. So the value of n is (PAGE_SIZE / sizeof(pte_t)). This optimization only supports 64-bit system, so the value of sizeof(pte_t) -is 8. And this optimization also applicable only when the size of struct page -is a power of two. In most cases, the size of struct page is 64 bytes (e.g. +is 8. And this optimization also applicable only when the size of ``struct page`` +is a power of two. In most cases, the size of ``struct page`` is 64 bytes (e.g. x86-64 and arm64). So if we use pmd level mapping for a HugeTLB page, the -size of struct page structs of it is 8 page frames which size depends on the +size of ``struct page`` structs of it is 8 page frames which size depends on the size of the base page. For the HugeTLB page of the pud level mapping, then:: @@ -86,7 +88,7 @@ For the HugeTLB page of the pud level mapping, then:: = PAGE_SIZE / 8 * 8 (pages) = PAGE_SIZE (pages) -Where the struct_size(pmd) is the size of the struct page structs of a +Where the struct_size(pmd) is the size of the ``struct page`` structs of a HugeTLB page of the pmd level mapping. E.g.: A 2MB HugeTLB page on x86_64 consists in 8 page frames while 1GB @@ -94,7 +96,7 @@ HugeTLB page consists in 4096. Next, we take the pmd level mapping of the HugeTLB page as an example to show the internal implementation of this optimization. There are 8 pages -struct page structs associated with a HugeTLB page which is pmd mapped. +``struct page`` structs associated with a HugeTLB page which is pmd mapped. Here is how things look before optimization:: @@ -122,10 +124,10 @@ Here is how things look before optimization:: +-----------+ The value of page->compound_head is the same for all tail pages. The first -page of page structs (page 0) associated with the HugeTLB page contains the 4 -page structs necessary to describe the HugeTLB. The only use of the remaining -pages of page structs (page 1 to page 7) is to point to page->compound_head. -Therefore, we can remap pages 1 to 7 to page 0. Only 1 page of page structs +page of ``struct page`` (page 0) associated with the HugeTLB page contains the 4 +``struct page`` necessary to describe the HugeTLB. The only use of the remaining +pages of ``struct page`` (page 1 to page 7) is to point to page->compound_head. +Therefore, we can remap pages 1 to 7 to page 0. Only 1 page of ``struct page`` will be used for each HugeTLB page. This will allow us to free the remaining 7 pages to the buddy allocator. @@ -167,13 +169,37 @@ entries that can be cached in a single TLB entry. The contiguous bit is used to increase the mapping size at the pmd and pte (last) level. So this type of HugeTLB page can be optimized only when its -size of the struct page structs is greater than 1 page. +size of the ``struct page`` structs is greater than **1** page. Notice: The head vmemmap page is not freed to the buddy allocator and all tail vmemmap pages are mapped to the head vmemmap page frame. So we can see -more than one struct page struct with PG_head (e.g. 8 per 2 MB HugeTLB page) -associated with each HugeTLB page. The compound_head() can handle this -correctly (more details refer to the comment above compound_head()). +more than one ``struct page`` struct with ``PG_head`` (e.g. 8 per 2 MB HugeTLB +page) associated with each HugeTLB page. The ``compound_head()`` can handle +this correctly. There is only **one** head ``struct page``, the tail +``struct page`` with ``PG_head`` are fake head ``struct page``. We need an +approach to distinguish between those two different types of ``struct page`` so +that ``compound_head()`` can return the real head ``struct page`` when the +parameter is the tail ``struct page`` but with ``PG_head``. The following code +snippet describes how to distinguish between real and fake head ``struct page``. + +.. code-block:: c + + if (test_bit(PG_head, &page->flags)) { + unsigned long head = READ_ONCE(page[1].compound_head); + + if (head & 1) { + if (head == (unsigned long)page + 1) + /* head struct page */ + else + /* tail struct page */ + } else { + /* head struct page */ + } + } + +We can safely access the field of the **page[1]** with ``PG_head`` because the +page is a compound page composed with at least two contiguous pages. +The implementation refers to ``page_fixed_fake_head()``. Device DAX ========== @@ -187,7 +213,7 @@ PMD_SIZE (2M on x86_64) and PUD_SIZE (1G on x86_64). The differences with HugeTLB are relatively minor. -It only use 3 page structs for storing all information as opposed +It only use 3 ``struct page`` for storing all information as opposed to 4 on HugeTLB pages. There's no remapping of vmemmap given that device-dax memory is not part of diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index fc4f710e9820..5f9379b3c8c8 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -76,17 +76,10 @@ EXPORT_SYMBOL_GPL(__sync_icache_dcache); void flush_dcache_page(struct page *page) { /* - * Only the head page's flags of HugeTLB can be cleared since the tail - * vmemmap pages associated with each HugeTLB page are mapped with - * read-only when CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP is enabled (more - * details can refer to vmemmap_remap_pte()). Although - * __sync_icache_dcache() only set PG_dcache_clean flag on the head - * page struct, there is more than one page struct with PG_dcache_clean - * associated with the HugeTLB page since the head vmemmap page frame - * is reused (more details can refer to the comments above - * page_fixed_fake_head()). + * HugeTLB pages are always fully mapped and only head page will be + * set PG_dcache_clean (see comments in __sync_icache_dcache()). */ - if (hugetlb_optimize_vmemmap_enabled() && PageHuge(page)) + if (PageHuge(page)) page = compound_head(page); if (test_bit(PG_dcache_clean, &page->flags)) diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 509408da0da1..6b3033845c6d 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -30,9 +30,15 @@ int pmd_huge(pmd_t pmd) (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; } +/* + * pud_huge() returns 1 if @pud is hugetlb related entry, that is normal + * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. + * Otherwise, returns 0. + */ int pud_huge(pud_t pud) { - return !!(pud_val(pud) & _PAGE_PSE); + return !pud_none(pud) && + (pud_val(pud) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; } #ifdef CONFIG_HUGETLB_PAGE diff --git a/fs/Kconfig b/fs/Kconfig index 5976eb33535f..a547307c1ae8 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -247,8 +247,7 @@ config HUGETLB_PAGE # # Select this config option from the architecture Kconfig, if it is preferred -# to enable the feature of minimizing overhead of struct page associated with -# each HugeTLB page. +# to enable the feature of HugeTLB Vmemmap Optimization (HVO). # config ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP bool @@ -259,14 +258,13 @@ config HUGETLB_PAGE_OPTIMIZE_VMEMMAP depends on SPARSEMEM_VMEMMAP config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON - bool "Default optimizing vmemmap pages of HugeTLB to on" + bool "HugeTLB Vmemmap Optimization (HVO) defaults to on" default n depends on HUGETLB_PAGE_OPTIMIZE_VMEMMAP help - When using HUGETLB_PAGE_OPTIMIZE_VMEMMAP, the optimizing unused vmemmap - pages associated with each HugeTLB page is default off. Say Y here - to enable optimizing vmemmap pages of HugeTLB by default. It can then - be disabled on the command line via hugetlb_free_vmemmap=off. + The HugeTLB VmemmapvOptimization (HVO) defaults to off. Say Y here to + enable HVO by default. It can be disabled via hugetlb_free_vmemmap=off + (boot command line) or hugetlb_optimize_vmemmap (sysctl). config MEMFD_CREATE def_bool TMPFS || HUGETLBFS diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 177b07944640..25679035ca28 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -60,11 +60,11 @@ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage - * @page: Pointer to the page to be mapped + * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * - * Can be invoked from any context. + * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of @@ -86,8 +86,7 @@ static inline void kmap_flush_unused(void); * temporarily mapped. * * While it is significantly faster than kmap() for the higmem case it - * comes with restrictions about the pointer validity. Only use when really - * necessary. + * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 4cdfce976644..3ec981a0d8b3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -43,6 +43,9 @@ enum { SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */ __MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD, #endif +#ifdef CONFIG_MEMORY_FAILURE + SUBPAGE_INDEX_HWPOISON, +#endif __NR_USED_SUBPAGE, }; @@ -551,7 +554,7 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. - * HPG_temporary - - Set on a page that is temporarily allocated from the buddy + * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. @@ -561,6 +564,8 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. + * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page + * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, @@ -568,6 +573,7 @@ enum hugetlb_page_flags { HPG_temporary, HPG_freed, HPG_vmemmap_optimized, + HPG_raw_hwp_unreliable, __NR_HPAGEFLAGS, }; @@ -614,6 +620,7 @@ HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) +HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) #ifdef CONFIG_HUGETLB_PAGE @@ -638,9 +645,6 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP - unsigned int optimize_vmemmap_pages; -#endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ struct cftype cgroup_files_dfl[8]; @@ -716,7 +720,7 @@ static inline struct hstate *hstate_vma(struct vm_area_struct *vma) return hstate_file(vma->vm_file); } -static inline unsigned long huge_page_size(struct hstate *h) +static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } @@ -745,7 +749,7 @@ static inline bool hstate_is_gigantic(struct hstate *h) return huge_page_order(h) >= MAX_ORDER; } -static inline unsigned int pages_per_huge_page(struct hstate *h) +static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } @@ -799,6 +803,14 @@ extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); +#ifdef CONFIG_MEMORY_FAILURE +extern void hugetlb_clear_page_hwpoison(struct page *hpage); +#else +static inline void hugetlb_clear_page_hwpoison(struct page *hpage) +{ +} +#endif + #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) diff --git a/include/linux/mm.h b/include/linux/mm.h index 18e01474cf6b..3bedc449c14d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3142,13 +3142,6 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP -int vmemmap_remap_free(unsigned long start, unsigned long end, - unsigned long reuse); -int vmemmap_remap_alloc(unsigned long start, unsigned long end, - unsigned long reuse, gfp_t gfp_mask); -#endif - 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, @@ -3183,6 +3176,7 @@ enum mf_flags { MF_SOFT_OFFLINE = 1 << 3, MF_UNPOISON = 1 << 4, MF_SW_SIMULATED = 1 << 5, + MF_NO_RETRY = 1 << 6, }; int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); @@ -3235,7 +3229,6 @@ enum mf_action_page_type { MF_MSG_DIFFERENT_COMPOUND, MF_MSG_HUGE, MF_MSG_FREE_HUGE, - MF_MSG_NON_PMD_HUGE, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index ea19528564d1..465ff35a8c00 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -205,34 +205,15 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP -DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, - hugetlb_optimize_vmemmap_key); - -static __always_inline bool hugetlb_optimize_vmemmap_enabled(void) -{ - return static_branch_maybe(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, - &hugetlb_optimize_vmemmap_key); -} +DECLARE_STATIC_KEY_FALSE(hugetlb_optimize_vmemmap_key); /* - * If the feature of optimizing vmemmap pages associated with each HugeTLB - * page is enabled, the head vmemmap page frame is reused and all of the tail - * vmemmap addresses map to the head vmemmap page frame (furture details can - * refer to the figure at the head of the mm/hugetlb_vmemmap.c). In other - * words, there are more than one page struct with PG_head associated with each - * HugeTLB page. We __know__ that there is only one head page struct, the tail - * page structs with PG_head are fake head page structs. We need an approach - * to distinguish between those two different types of page structs so that - * compound_head() can return the real head page struct when the parameter is - * the tail page struct but with PG_head. - * - * The page_fixed_fake_head() returns the real head page struct if the @page is - * fake page head, otherwise, returns @page which can either be a true page - * head or tail. + * Return the real head page struct iff the @page is a fake head page, otherwise + * return the @page itself. See Documentation/mm/vmemmap_dedup.rst. */ static __always_inline const struct page *page_fixed_fake_head(const struct page *page) { - if (!hugetlb_optimize_vmemmap_enabled()) + if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key)) return page; /* @@ -260,11 +241,6 @@ static inline const struct page *page_fixed_fake_head(const struct page *page) { return page; } - -static inline bool hugetlb_optimize_vmemmap_enabled(void) -{ - return false; -} #endif static __always_inline int page_is_fake_head(struct page *page) diff --git a/include/linux/swapops.h b/include/linux/swapops.h index bb7afd03a324..a3d435bf9f97 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -490,6 +490,11 @@ static inline void num_poisoned_pages_dec(void) atomic_long_dec(&num_poisoned_pages); } +static inline void num_poisoned_pages_sub(long i) +{ + atomic_long_sub(i, &num_poisoned_pages); +} + #else static inline swp_entry_t make_hwpoison_entry(struct page *page) @@ -505,6 +510,10 @@ static inline int is_hwpoison_entry(swp_entry_t swp) static inline void num_poisoned_pages_inc(void) { } + +static inline void num_poisoned_pages_sub(long i) +{ +} #endif static inline int non_swap_entry(swp_entry_t entry) diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 17b42ce89d3e..780690dc08cd 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -268,6 +268,10 @@ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * return NULL; } +static inline void register_sysctl_init(const char *path, struct ctl_table *table) +{ +} + static inline struct ctl_table_header *register_sysctl_mount_point(const char *path) { return NULL; diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index d0337a41141c..cbd3ddd7c33d 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -360,7 +360,6 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_DIFFERENT_COMPOUND, "different compound page after locking" ) \ EM ( MF_MSG_HUGE, "huge page" ) \ EM ( MF_MSG_FREE_HUGE, "free huge page" ) \ - EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" ) \ EM ( MF_MSG_UNMAP_FAILED, "unmapping failed page" ) \ EM ( MF_MSG_DIRTY_SWAPCACHE, "dirty swapcache page" ) \ EM ( MF_MSG_CLEAN_SWAPCACHE, "clean swapcache page" ) \ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f044962ad9df..0aee2f3ae15c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1535,7 +1535,14 @@ static void __update_and_free_page(struct hstate *h, struct page *page) if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; - if (hugetlb_vmemmap_alloc(h, page)) { + /* + * If we don't know which subpages are hwpoisoned, we can't free + * the hugepage, so it's leaked intentionally. + */ + if (HPageRawHwpUnreliable(page)) + return; + + if (hugetlb_vmemmap_restore(h, page)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the @@ -1547,6 +1554,13 @@ static void __update_and_free_page(struct hstate *h, struct page *page) return; } + /* + * Move PageHWPoison flag from head page to the raw error pages, + * which makes any healthy subpages reusable. + */ + if (unlikely(PageHWPoison(page))) + hugetlb_clear_page_hwpoison(page); + for (i = 0; i < pages_per_huge_page(h); i++, subpage = mem_map_next(subpage, page, i)) { subpage->flags &= ~(1 << PG_locked | 1 << PG_error | @@ -1612,7 +1626,7 @@ static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { - if (hugetlb_optimize_vmemmap_pages(h)) + if (hugetlb_vmemmap_optimizable(h)) flush_work(&free_hpage_work); } @@ -1734,7 +1748,7 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) static void __prep_new_huge_page(struct hstate *h, struct page *page) { - hugetlb_vmemmap_free(h, page); + hugetlb_vmemmap_optimize(h, page); INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); hugetlb_set_page_subpool(page, NULL); @@ -2107,17 +2121,8 @@ retry: * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. */ - rc = hugetlb_vmemmap_alloc(h, head); + rc = hugetlb_vmemmap_restore(h, head); if (!rc) { - /* - * Move PageHWPoison flag from head page to the raw - * error page, which makes any subpages rather than - * the error page reusable. - */ - if (PageHWPoison(head) && page != head) { - SetPageHWPoison(page); - ClearPageHWPoison(head); - } update_and_free_page(h, head, false); } else { spin_lock_irq(&hugetlb_lock); @@ -2432,8 +2437,7 @@ static void return_unused_surplus_pages(struct hstate *h, /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; - /* Cannot return gigantic pages currently */ - if (hstate_is_gigantic(h)) + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) goto out; /* @@ -3182,8 +3186,10 @@ static void __init report_hugepages(void) char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); - pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n", + pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n", buf, h->free_huge_pages); + pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n", + hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf); } } @@ -3421,7 +3427,7 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) remove_hugetlb_page_for_demote(h, page, false); spin_unlock_irq(&hugetlb_lock); - rc = hugetlb_vmemmap_alloc(h, page); + rc = hugetlb_vmemmap_restore(h, page); if (rc) { /* Allocation of vmemmmap failed, we can not demote page */ spin_lock_irq(&hugetlb_lock); @@ -4111,7 +4117,6 @@ void __init hugetlb_add_hstate(unsigned int order) h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); - hugetlb_vmemmap_init(h); parsed_hstate = h; } @@ -6985,10 +6990,38 @@ struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags) { - if (flags & (FOLL_GET | FOLL_PIN)) + struct page *page = NULL; + spinlock_t *ptl; + pte_t pte; + + if (WARN_ON_ONCE(flags & FOLL_PIN)) return NULL; - return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); +retry: + ptl = huge_pte_lock(hstate_sizelog(PUD_SHIFT), mm, (pte_t *)pud); + if (!pud_huge(*pud)) + goto out; + pte = huge_ptep_get((pte_t *)pud); + if (pte_present(pte)) { + page = pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(!try_grab_page(page, flags))) { + page = NULL; + goto out; + } + } else { + if (is_hugetlb_entry_migration(pte)) { + spin_unlock(ptl); + __migration_entry_wait(mm, (pte_t *)pud, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } +out: + spin_unlock(ptl); + return page; } struct page * __weak diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 1362feb3c6c9..20f414c0379f 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Optimize vmemmap pages associated with HugeTLB + * HugeTLB Vmemmap Optimization (HVO) * - * Copyright (c) 2020, Bytedance. All rights reserved. + * Copyright (c) 2020, ByteDance. All rights reserved. * * Author: Muchun Song <songmuchun@bytedance.com> * @@ -10,84 +10,443 @@ */ #define |