diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index f7b1c746299119..6988895d09a87a 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -60,6 +60,10 @@ HugePages_Surp the pool above the value in ``/proc/sys/vm/nr_hugepages``. The maximum number of surplus huge pages is controlled by ``/proc/sys/vm/nr_overcommit_hugepages``. + Note: When the feature of freeing unused vmemmap pages associated + with each hugetlb page is enabled, the number of surplus huge pages + may be temporarily larger than the maximum number of surplus huge + pages when the system is under memory pressure. Hugepagesize is the default hugepage size (in Kb). Hugetlb @@ -80,6 +84,10 @@ returned to the huge page pool when freed by a task. A user with root privileges can dynamically allocate more or free some persistent huge pages by increasing or decreasing the value of ``nr_hugepages``. +Note: When the feature of freeing unused vmemmap pages associated with each +hugetlb page is enabled, we can fail to free the huge pages triggered by +the user when ths system is under memory pressure. Please try again later. + Pages that are used as huge pages are reserved inside the kernel and cannot be used for other purposes. Huge pages cannot be swapped out under memory pressure. diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index 05d51d2d8beb73..c6bae2d7716096 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -357,6 +357,19 @@ creates ZONE_MOVABLE as following. Unfortunately, there is no information to show which memory block belongs to ZONE_MOVABLE. This is TBD. + Memory offlining can fail when dissolving a free huge page on ZONE_MOVABLE + and the feature of freeing unused vmemmap pages associated with each hugetlb + page is enabled. + + This can happen when we have plenty of ZONE_MOVABLE memory, but not enough + kernel memory to allocate vmemmmap pages. We may even be able to migrate + huge page contents, but will not be able to dissolve the source huge page. + This will prevent an offline operation and is unfortunate as memory offlining + is expected to succeed on movable zones. Users that depend on memory hotplug + to succeed for movable zones should carefully consider whether the memory + savings gained from this feature are worth the risk of possibly not being + able to offline memory in certain situations. + .. note:: Techniques that rely on long-term pinnings of memory (especially, RDMA and vfio) are fundamentally problematic with ZONE_MOVABLE and, therefore, memory diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0c8c96481259f8..3578d9d708feea 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -532,12 +532,14 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * modifications require hugetlb_lock. * 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. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, + HPG_vmemmap_optimized, __NR_HPAGEFLAGS, }; @@ -583,6 +585,7 @@ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) +HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) #ifdef CONFIG_HUGETLB_PAGE diff --git a/include/linux/mm.h b/include/linux/mm.h index 3437aa7c6c9105..706bee98d9657f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3078,6 +3078,8 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) void 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); void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e7eb1ab8c78a27..778db5de6232e4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1376,6 +1376,39 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, h->nr_huge_pages_node[nid]--; } +static void add_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + int zeroed; + int nid = page_to_nid(page); + + VM_BUG_ON_PAGE(!HPageVmemmapOptimized(page), page); + + lockdep_assert_held(&hugetlb_lock); + + INIT_LIST_HEAD(&page->lru); + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; + + if (adjust_surplus) { + h->surplus_huge_pages++; + h->surplus_huge_pages_node[nid]++; + } + + set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); + set_page_private(page, 0); + SetHPageVmemmapOptimized(page); + + /* + * This page is now managed by the hugetlb allocator and has + * no users -- drop the last reference. + */ + zeroed = put_page_testzero(page); + VM_BUG_ON_PAGE(!zeroed, page); + arch_clear_hugepage_flags(page); + enqueue_huge_page(h, page); +} + static void __update_and_free_page(struct hstate *h, struct page *page) { int i; @@ -1384,6 +1417,18 @@ static void __update_and_free_page(struct hstate *h, struct page *page) if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; + if (alloc_huge_page_vmemmap(h, page)) { + spin_lock_irq(&hugetlb_lock); + /* + * If we cannot allocate vmemmap pages, just refuse to free the + * page and put the page back on the hugetlb free list and treat + * as a surplus page. + */ + add_hugetlb_page(h, page, true); + spin_unlock_irq(&hugetlb_lock); + return; + } + 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 | @@ -1450,7 +1495,7 @@ static inline void flush_free_hpage_work(struct hstate *h) static void update_and_free_page(struct hstate *h, struct page *page, bool atomic) { - if (!free_vmemmap_pages_per_hpage(h) || !atomic) { + if (!HPageVmemmapOptimized(page) || !atomic) { __update_and_free_page(h, page); return; } @@ -1806,10 +1851,14 @@ static struct page *remove_pool_huge_page(struct hstate *h, * nothing for in-use hugepages and non-hugepages. * This function returns values like below: * - * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use - * (allocated or reserved.) - * 0: successfully dissolved free hugepages or the page is not a - * hugepage (considered as already dissolved) + * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages + * when the system is under memory pressure and the feature of + * freeing unused vmemmap pages associated with each hugetlb page + * is enabled. + * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use + * (allocated or reserved.) + * 0: successfully dissolved free hugepages or the page is not a + * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { @@ -1851,19 +1900,38 @@ int dissolve_free_huge_page(struct page *page) goto retry; } - /* - * 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); - } remove_hugetlb_page(h, head, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); - update_and_free_page(h, head, false); - return 0; + + /* + * Normally update_and_free_page will allocate required vmemmmap + * before freeing the page. update_and_free_page will fail to + * free the page if it can not allocate required vmemmap. We + * need to adjust max_huge_pages if the page is not freed. + * Attempt to allocate vmemmmap here so that we can take + * appropriate action on failure. + */ + rc = alloc_huge_page_vmemmap(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); + add_hugetlb_page(h, head, false); + h->max_huge_pages++; + spin_unlock_irq(&hugetlb_lock); + } + + return rc; } out: spin_unlock_irq(&hugetlb_lock); diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index cb28c5b6c9ff77..a897c77782469f 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -185,6 +185,38 @@ static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h) return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT; } +/* + * Previously discarded vmemmap pages will be allocated and remapping + * after this function returns zero. + */ +int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +{ + int ret; + unsigned long vmemmap_addr = (unsigned long)head; + unsigned long vmemmap_end, vmemmap_reuse; + + if (!HPageVmemmapOptimized(head)) + return 0; + + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + /* + * The pages which the vmemmap virtual address range [@vmemmap_addr, + * @vmemmap_end) are mapped to are freed to the buddy allocator, and + * the range is mapped to the page which @vmemmap_reuse is mapped to. + * When a HugeTLB page is freed to the buddy allocator, previously + * discarded vmemmap pages must be allocated and remapping. + */ + ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse, + GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE); + + if (!ret) + ClearHPageVmemmapOptimized(head); + + return ret; +} + void free_huge_page_vmemmap(struct hstate *h, struct page *head) { unsigned long vmemmap_addr = (unsigned long)head; @@ -203,4 +235,6 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head) * which the range [@vmemmap_addr, @vmemmap_end] is mapped to. */ vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse); + + SetHPageVmemmapOptimized(head); } diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h index 01f8637adbe0c7..a37771b0b82ac9 100644 --- a/mm/hugetlb_vmemmap.h +++ b/mm/hugetlb_vmemmap.h @@ -11,6 +11,7 @@ #include #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +int alloc_huge_page_vmemmap(struct hstate *h, struct page *head); void free_huge_page_vmemmap(struct hstate *h, struct page *head); /* @@ -25,6 +26,11 @@ static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h) return 0; } #else +static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +{ + return 0; +} + static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head) { } diff --git a/mm/migrate.c b/mm/migrate.c index 380ca57b903147..cc4d6af4168349 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -626,7 +626,10 @@ void migrate_page_states(struct page *newpage, struct page *page) if (PageSwapCache(page)) ClearPageSwapCache(page); ClearPagePrivate(page); - set_page_private(page, 0); + + /* page->private contains hugetlb specific flags */ + if (!PageHuge(page)) + set_page_private(page, 0); /* * If any waiters have accumulated on the new page then diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 3ec5488c815cd7..a3aa275e26686e 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -40,7 +40,8 @@ * @remap_pte: called for each lowest-level entry (PTE). * @reuse_page: the page which is reused for the tail vmemmap pages. * @reuse_addr: the virtual address of the @reuse_page page. - * @vmemmap_pages: the list head of the vmemmap pages that can be freed. + * @vmemmap_pages: the list head of the vmemmap pages that can be freed + * or is mapped from. */ struct vmemmap_remap_walk { void (*remap_pte)(pte_t *pte, unsigned long addr, @@ -224,6 +225,78 @@ void vmemmap_remap_free(unsigned long start, unsigned long end, free_vmemmap_page_list(&vmemmap_pages); } +static void vmemmap_restore_pte(pte_t *pte, unsigned long addr, + struct vmemmap_remap_walk *walk) +{ + pgprot_t pgprot = PAGE_KERNEL; + struct page *page; + void *to; + + BUG_ON(pte_page(*pte) != walk->reuse_page); + + page = list_first_entry(walk->vmemmap_pages, struct page, lru); + list_del(&page->lru); + to = page_to_virt(page); + copy_page(to, (void *)walk->reuse_addr); + + set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot)); +} + +static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, + gfp_t gfp_mask, struct list_head *list) +{ + unsigned long nr_pages = (end - start) >> PAGE_SHIFT; + int nid = page_to_nid((struct page *)start); + struct page *page, *next; + + while (nr_pages--) { + page = alloc_pages_node(nid, gfp_mask, 0); + if (!page) + goto out; + list_add_tail(&page->lru, list); + } + + return 0; +out: + list_for_each_entry_safe(page, next, list, lru) + __free_pages(page, 0); + return -ENOMEM; +} + +/** + * vmemmap_remap_alloc - remap the vmemmap virtual address range [@start, end) + * to the page which is from the @vmemmap_pages + * respectively. + * @start: start address of the vmemmap virtual address range that we want + * to remap. + * @end: end address of the vmemmap virtual address range that we want to + * remap. + * @reuse: reuse address. + * @gfp_mask: GFP flag for allocating vmemmap pages. + */ +int vmemmap_remap_alloc(unsigned long start, unsigned long end, + unsigned long reuse, gfp_t gfp_mask) +{ + LIST_HEAD(vmemmap_pages); + struct vmemmap_remap_walk walk = { + .remap_pte = vmemmap_restore_pte, + .reuse_addr = reuse, + .vmemmap_pages = &vmemmap_pages, + }; + + /* See the comment in the vmemmap_remap_free(). */ + BUG_ON(start - reuse != PAGE_SIZE); + + might_sleep_if(gfpflags_allow_blocking(gfp_mask)); + + if (alloc_vmemmap_page_list(start, end, gfp_mask, &vmemmap_pages)) + return -ENOMEM; + + vmemmap_remap_range(reuse, end, &walk); + + return 0; +} + /* * Allocate a block of memory to be used to back the virtual memory map * or to back the page tables that are used to create the mapping.