From d883544515aae54842c21730b880172e7894fde9 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 13 Aug 2019 15:37:15 -0700 Subject: mm: mempolicy: make the behavior consistent when MPOL_MF_MOVE* and MPOL_MF_STRICT were specified When both MPOL_MF_MOVE* and MPOL_MF_STRICT was specified, mbind() should try best to migrate misplaced pages, if some of the pages could not be migrated, then return -EIO. There are three different sub-cases: 1. vma is not migratable 2. vma is migratable, but there are unmovable pages 3. vma is migratable, pages are movable, but migrate_pages() fails If #1 happens, kernel would just abort immediately, then return -EIO, after a7f40cfe3b7a ("mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified"). If #3 happens, kernel would set policy and migrate pages with best-effort, but won't rollback the migrated pages and reset the policy back. Before that commit, they behaves in the same way. It'd better to keep their behavior consistent. But, rolling back the migrated pages and resetting the policy back sounds not feasible, so just make #1 behave as same as #3. Userspace will know that not everything was successfully migrated (via -EIO), and can take whatever steps it deems necessary - attempt rollback, determine which exact page(s) are violating the policy, etc. Make queue_pages_range() return 1 to indicate there are unmovable pages or vma is not migratable. The #2 is not handled correctly in the current kernel, the following patch will fix it. [yang.shi@linux.alibaba.com: fix review comments from Vlastimil] Link: http://lkml.kernel.org/r/1563556862-54056-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1561162809-59140-2-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Reviewed-by: Vlastimil Babka Cc: Michal Hocko Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 68 +++++++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 48 insertions(+), 20 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f48693f75b37..932c26845e3e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -429,11 +429,14 @@ static inline bool queue_pages_required(struct page *page, } /* - * queue_pages_pmd() has three possible return values: - * 1 - pages are placed on the right node or queued successfully. - * 0 - THP was split. - * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing - * page was already on a node that does not follow the policy. + * queue_pages_pmd() has four possible return values: + * 0 - pages are placed on the right node or queued successfully. + * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * 2 - THP was split. + * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an + * existing page was already on a node that does not follow the + * policy. */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -451,19 +454,17 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, if (is_huge_zero_page(page)) { spin_unlock(ptl); __split_huge_pmd(walk->vma, pmd, addr, false, NULL); + ret = 2; goto out; } - if (!queue_pages_required(page, qp)) { - ret = 1; + if (!queue_pages_required(page, qp)) goto unlock; - } - ret = 1; flags = qp->flags; /* go to thp migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma)) { - ret = -EIO; + ret = 1; goto unlock; } @@ -479,6 +480,13 @@ out: /* * Scan through pages checking if pages follow certain conditions, * and move them to the pagelist if they do. + * + * queue_pages_pte_range() has three possible return values: + * 0 - pages are placed on the right node or queued successfully. + * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * -EIO - only MPOL_MF_STRICT was specified and an existing page was already + * on a node that does not follow the policy. */ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -488,17 +496,17 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; int ret; + bool has_unmovable = false; pte_t *pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); - if (ret > 0) - return 0; - else if (ret < 0) + if (ret != 2) return ret; } + /* THP was split, fall through to pte walk */ if (pmd_trans_unstable(pmd)) return 0; @@ -519,14 +527,21 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (!queue_pages_required(page, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - if (!vma_migratable(vma)) + /* MPOL_MF_STRICT must be specified if we get here */ + if (!vma_migratable(vma)) { + has_unmovable = true; break; + } migrate_page_add(page, qp->pagelist, flags); } else break; } pte_unmap_unlock(pte - 1, ptl); cond_resched(); + + if (has_unmovable) + return 1; + return addr != end ? -EIO : 0; } @@ -639,7 +654,13 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, * * If pages found in a given range are on a set of nodes (determined by * @nodes and @flags,) it's isolated and queued to the pagelist which is - * passed via @private.) + * passed via @private. + * + * queue_pages_range() has three possible return values: + * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were + * specified. + * 0 - queue pages successfully or no misplaced page. + * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified. */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, @@ -1182,6 +1203,7 @@ static long do_mbind(unsigned long start, unsigned long len, struct mempolicy *new; unsigned long end; int err; + int ret; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) @@ -1243,10 +1265,15 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) goto mpol_out; - err = queue_pages_range(mm, start, end, nmask, + ret = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); - if (!err) - err = mbind_range(mm, start, end, new); + + if (ret < 0) { + err = -EIO; + goto up_out; + } + + err = mbind_range(mm, start, end, new); if (!err) { int nr_failed = 0; @@ -1259,13 +1286,14 @@ static long do_mbind(unsigned long start, unsigned long len, putback_movable_pages(&pagelist); } - if (nr_failed && (flags & MPOL_MF_STRICT)) + if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; } else putback_movable_pages(&pagelist); +up_out: up_write(&mm->mmap_sem); - mpol_out: +mpol_out: mpol_put(new); return err; } -- cgit v1.2.3 From a53190a4aaa36494f4d7209fd1fcc6f2ee08e0e0 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 13 Aug 2019 15:37:18 -0700 Subject: mm: mempolicy: handle vma with unmovable pages mapped correctly in mbind When running syzkaller internally, we ran into the below bug on 4.9.x kernel: kernel BUG at mm/huge_memory.c:2124! invalid opcode: 0000 [#1] SMP KASAN CPU: 0 PID: 1518 Comm: syz-executor107 Not tainted 4.9.168+ #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.5.1 01/01/2011 task: ffff880067b34900 task.stack: ffff880068998000 RIP: split_huge_page_to_list+0x8fb/0x1030 mm/huge_memory.c:2124 Call Trace: split_huge_page include/linux/huge_mm.h:100 [inline] queue_pages_pte_range+0x7e1/0x1480 mm/mempolicy.c:538 walk_pmd_range mm/pagewalk.c:50 [inline] walk_pud_range mm/pagewalk.c:90 [inline] walk_pgd_range mm/pagewalk.c:116 [inline] __walk_page_range+0x44a/0xdb0 mm/pagewalk.c:208 walk_page_range+0x154/0x370 mm/pagewalk.c:285 queue_pages_range+0x115/0x150 mm/mempolicy.c:694 do_mbind mm/mempolicy.c:1241 [inline] SYSC_mbind+0x3c3/0x1030 mm/mempolicy.c:1370 SyS_mbind+0x46/0x60 mm/mempolicy.c:1352 do_syscall_64+0x1d2/0x600 arch/x86/entry/common.c:282 entry_SYSCALL_64_after_swapgs+0x5d/0xdb Code: c7 80 1c 02 00 e8 26 0a 76 01 <0f> 0b 48 c7 c7 40 46 45 84 e8 4c RIP [] split_huge_page_to_list+0x8fb/0x1030 mm/huge_memory.c:2124 RSP with the below test: uint64_t r[1] = {0xffffffffffffffff}; int main(void) { syscall(__NR_mmap, 0x20000000, 0x1000000, 3, 0x32, -1, 0); intptr_t res = 0; res = syscall(__NR_socket, 0x11, 3, 0x300); if (res != -1) r[0] = res; *(uint32_t*)0x20000040 = 0x10000; *(uint32_t*)0x20000044 = 1; *(uint32_t*)0x20000048 = 0xc520; *(uint32_t*)0x2000004c = 1; syscall(__NR_setsockopt, r[0], 0x107, 0xd, 0x20000040, 0x10); syscall(__NR_mmap, 0x20fed000, 0x10000, 0, 0x8811, r[0], 0); *(uint64_t*)0x20000340 = 2; syscall(__NR_mbind, 0x20ff9000, 0x4000, 0x4002, 0x20000340, 0x45d4, 3); return 0; } Actually the test does: mmap(0x20000000, 16777216, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x20000000 socket(AF_PACKET, SOCK_RAW, 768) = 3 setsockopt(3, SOL_PACKET, PACKET_TX_RING, {block_size=65536, block_nr=1, frame_size=50464, frame_nr=1}, 16) = 0 mmap(0x20fed000, 65536, PROT_NONE, MAP_SHARED|MAP_FIXED|MAP_POPULATE|MAP_DENYWRITE, 3, 0) = 0x20fed000 mbind(..., MPOL_MF_STRICT|MPOL_MF_MOVE) = 0 The setsockopt() would allocate compound pages (16 pages in this test) for packet tx ring, then the mmap() would call packet_mmap() to map the pages into the user address space specified by the mmap() call. When calling mbind(), it would scan the vma to queue the pages for migration to the new node. It would split any huge page since 4.9 doesn't support THP migration, however, the packet tx ring compound pages are not THP and even not movable. So, the above bug is triggered. However, the later kernel is not hit by this issue due to commit d44d363f6578 ("mm: don't assume anonymous pages have SwapBacked flag"), which just removes the PageSwapBacked check for a different reason. But, there is a deeper issue. According to the semantic of mbind(), it should return -EIO if MPOL_MF_MOVE or MPOL_MF_MOVE_ALL was specified and MPOL_MF_STRICT was also specified, but the kernel was unable to move all existing pages in the range. The tx ring of the packet socket is definitely not movable, however, mbind() returns success for this case. Although the most socket file associates with non-movable pages, but XDP may have movable pages from gup. So, it sounds not fine to just check the underlying file type of vma in vma_migratable(). Change migrate_page_add() to check if the page is movable or not, if it is unmovable, just return -EIO. But do not abort pte walk immediately, since there may be pages off LRU temporarily. We should migrate other pages if MPOL_MF_MOVE* is specified. Set has_unmovable flag if some paged could not be not moved, then return -EIO for mbind() eventually. With this change the above test would return -EIO as expected. [yang.shi@linux.alibaba.com: fix review comments from Vlastimil] Link: http://lkml.kernel.org/r/1563556862-54056-3-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1561162809-59140-3-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Reviewed-by: Vlastimil Babka Cc: Michal Hocko Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 932c26845e3e..547cd403ed02 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -403,7 +403,7 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { }, }; -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); struct queue_pages { @@ -463,12 +463,11 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, flags = qp->flags; /* go to thp migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - if (!vma_migratable(walk->vma)) { + if (!vma_migratable(walk->vma) || + migrate_page_add(page, qp->pagelist, flags)) { ret = 1; goto unlock; } - - migrate_page_add(page, qp->pagelist, flags); } else ret = -EIO; unlock: @@ -532,7 +531,14 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, has_unmovable = true; break; } - migrate_page_add(page, qp->pagelist, flags); + + /* + * Do not abort immediately since there may be + * temporary off LRU pages in the range. Still + * need migrate other LRU pages. + */ + if (migrate_page_add(page, qp->pagelist, flags)) + has_unmovable = true; } else break; } @@ -961,7 +967,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, /* * page migration, thp tail pages can be passed. */ -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { struct page *head = compound_head(page); @@ -974,8 +980,19 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_cache(head), hpage_nr_pages(head)); + } else if (flags & MPOL_MF_STRICT) { + /* + * Non-movable page may reach here. And, there may be + * temporary off LRU pages or non-LRU movable pages. + * Treat them as unmovable pages since they can't be + * isolated, so they can't be moved at the moment. It + * should return -EIO for this case too. + */ + return -EIO; } } + + return 0; } /* page allocation callback for NUMA node migration */ @@ -1178,9 +1195,10 @@ static struct page *new_page(struct page *page, unsigned long start) } #else -static void migrate_page_add(struct page *page, struct list_head *pagelist, +static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { + return -EIO; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, -- cgit v1.2.3 From 92717d429b38e4f9f934eed7e605cc42858f1839 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 13 Aug 2019 15:37:50 -0700 Subject: Revert "Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"" Patch series "reapply: relax __GFP_THISNODE for MADV_HUGEPAGE mappings". The fixes for what was originally reported as "pathological THP behavior" we rightfully reverted to be sure not to introduced regressions at end of a merge window after a severe regression report from the kernel bot. We can safely re-apply them now that we had time to analyze the problem. The mm process worked fine, because the good fixes were eventually committed upstream without excessive delay. The regression reported by the kernel bot however forced us to revert the good fixes to be sure not to introduce regressions and to give us the time to analyze the issue further. The silver lining is that this extra time allowed to think more at this issue and also plan for a future direction to improve things further in terms of THP NUMA locality. This patch (of 2): This reverts commit 356ff8a9a78fb35d ("Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"). So it reapplies 89c83fb539f954 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"). Consolidation of the THP allocation flags at the same place was meant to be a clean up to easier handle otherwise scattered code which is imposing a maintenance burden. There were no real problems observed with the gfp mask consolidation but the reversion was rushed through without a larger consensus regardless. This patch brings the consolidation back because this should make the long term maintainability easier as well as it should allow future changes to be less error prone. [mhocko@kernel.org: changelog additions] Link: http://lkml.kernel.org/r/20190503223146.2312-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Acked-by: Michal Hocko Cc: Mel Gorman Cc: Vlastimil Babka Cc: David Rientjes Cc: Zi Yan Cc: Stefan Priebe - Profihost AG Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++-------- mm/huge_memory.c | 27 ++++++++++++++------------- mm/mempolicy.c | 32 +++----------------------------- mm/shmem.c | 2 +- 4 files changed, 22 insertions(+), 51 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fb07b503dc45..f33881688f42 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1334ede667a8..f7e388b8662d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -644,30 +644,30 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + const gfp_t gfp_mask = GFP_TRANSHUGE_LIGHT | __GFP_THISNODE; /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); + return GFP_TRANSHUGE | __GFP_THISNODE | + (vma_madvised ? 0 : __GFP_NORETRY); /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + return gfp_mask | __GFP_KSWAPD_RECLAIM; /* Synchronous compaction if madvised, otherwise kick kcompactd */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | - (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); + return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM); /* Only do synchronous compaction if madvised */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | - (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); + return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); - return GFP_TRANSHUGE_LIGHT; + return gfp_mask; } /* Caller must hold page table lock. */ @@ -739,8 +739,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) pte_free(vma->vm_mm, pgtable); return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma); - page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1347,8 +1347,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) alloc: if (__transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - huge_gfp = alloc_hugepage_direct_gfpmask(vma); - new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, + haddr, numa_node_id()); } else new_page = NULL; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 547cd403ed02..9c9877a43d58 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1180,8 +1180,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); + thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, + address, numa_node_id()); if (!thp) return NULL; prep_transhuge_page(thp); @@ -2083,7 +2083,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). - * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2094,7 +2093,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, int node) { struct mempolicy *pol; struct page *page; @@ -2112,31 +2111,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { - int hpage_node = node; - - /* - * For hugepage allocation and non-interleave policy which - * allows the current node (or other explicitly preferred - * node) we only try to allocate from the current/preferred - * node and don't fall back to other nodes, as the cost of - * remote accesses would likely offset THP benefits. - * - * If the policy is interleave, or does not allow the current - * node in its nodemask, we allocate the standard way. - */ - if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; - - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(hpage_node, *nmask)) { - mpol_cond_put(pol); - page = __alloc_pages_node(hpage_node, - gfp | __GFP_THISNODE, order); - goto out; - } - } - nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); diff --git a/mm/shmem.c b/mm/shmem.c index 626d8c74b973..2bed4761f279 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1466,7 +1466,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); -- cgit v1.2.3 From a8282608c88e08b1782141026eab61204c1e533f Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Tue, 13 Aug 2019 15:37:53 -0700 Subject: Revert "mm, thp: restore node-local hugepage allocations" This reverts commit 2f0799a0ffc033b ("mm, thp: restore node-local hugepage allocations"). commit 2f0799a0ffc033b was rightfully applied to avoid the risk of a severe regression that was reported by the kernel test robot at the end of the merge window. Now we understood the regression was a false positive and was caused by a significant increase in fairness during a swap trashing benchmark. So it's safe to re-apply the fix and continue improving the code from there. The benchmark that reported the regression is very useful, but it provides a meaningful result only when there is no significant alteration in fairness during the workload. The removal of __GFP_THISNODE increased fairness. __GFP_THISNODE cannot be used in the generic page faults path for new memory allocations under the MPOL_DEFAULT mempolicy, or the allocation behavior significantly deviates from what the MPOL_DEFAULT semantics are supposed to be for THP and 4k allocations alike. Setting THP defrag to "always" or using MADV_HUGEPAGE (with THP defrag set to "madvise") has never meant to provide an implicit MPOL_BIND on the "current" node the task is running on, causing swap storms and providing a much more aggressive behavior than even zone_reclaim_node = 3. Any workload who could have benefited from __GFP_THISNODE has now to enable zone_reclaim_mode=1||2||3. __GFP_THISNODE implicitly provided the zone_reclaim_mode behavior, but it only did so if THP was enabled: if THP was disabled, there would have been no chance to get any 4k page from the current node if the current node was full of pagecache, which further shows how this __GFP_THISNODE was misplaced in MADV_HUGEPAGE. MADV_HUGEPAGE has never been intended to provide any zone_reclaim_mode semantics, in fact the two are orthogonal, zone_reclaim_mode = 1|2|3 must work exactly the same with MADV_HUGEPAGE set or not. The performance characteristic of memory depends on the hardware details. The numbers below are obtained on Naples/EPYC architecture and the N/A projection extends them to show what we should aim for in the future as a good THP NUMA locality default. The benchmark used exercises random memory seeks (note: the cost of the page faults is not part of the measurement). D0 THP | D0 4k | D1 THP | D1 4k | D2 THP | D2 4k | D3 THP | D3 4k | ... 0% | +43% | +45% | +106% | +131% | +224% | N/A | N/A D0 means distance zero (i.e. local memory), D1 means distance one (i.e. intra socket memory), D2 means distance two (i.e. inter socket memory), etc... For the guest physical memory allocated by qemu and for guest mode kernel the performance characteristic of RAM is more complex and an ideal default could be: D0 THP | D1 THP | D0 4k | D2 THP | D1 4k | D3 THP | D2 4k | D3 4k | ... 0% | +58% | +101% | N/A | +222% | N/A | N/A | N/A NOTE: the N/A are projections and haven't been measured yet, the measurement in this case is done on a 1950x with only two NUMA nodes. The THP case here means THP was used both in the host and in the guest. After applying this commit the THP NUMA locality order that we'll get out of MADV_HUGEPAGE is this: D0 THP | D1 THP | D2 THP | D3 THP | ... | D0 4k | D1 4k | D2 4k | D3 4k | ... Before this commit it was: D0 THP | D0 4k | D1 4k | D2 4k | D3 4k | ... Even if we ignore the breakage of large workloads that can't fit in a single node that the __GFP_THISNODE implicit "current node" mbind caused, the THP NUMA locality order provided by __GFP_THISNODE was still not the one we shall aim for in the long term (i.e. the first one at the top). After this commit is applied, we can introduce a new allocator multi order API and to replace those two alloc_pages_vmas calls in the page fault path, with a single multi order call: unsigned int order = (1 << HPAGE_PMD_ORDER) | (1 << 0); page = alloc_pages_multi_order(..., &order); if (!page) goto out; if (!(order & (1 << 0))) { VM_WARN_ON(order != 1 << HPAGE_PMD_ORDER); /* THP fault */ } else { VM_WARN_ON(order != 1 << 0); /* 4k fallback */ } The page allocator logic has to be altered so that when it fails on any zone with order 9, it has to try again with a order 0 before falling back to the next zone in the zonelist. After that we need to do more measurements and evaluate if adding an opt-in feature for guest mode is worth it, to swap "DN 4k | DN+1 THP" with "DN+1 THP | DN 4k" at every NUMA distance crossing. Link: http://lkml.kernel.org/r/20190503223146.2312-3-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Acked-by: Michal Hocko Acked-by: Mel Gorman Cc: Vlastimil Babka Cc: David Rientjes Cc: Zi Yan Cc: Stefan Priebe - Profihost AG Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 ++ mm/huge_memory.c | 42 ++++++++++++++++++++++++++---------------- mm/mempolicy.c | 2 +- 3 files changed, 29 insertions(+), 17 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5228c62af416..bac395f1d00a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f7e388b8662d..738065f765ab 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -647,27 +647,37 @@ release: static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); - const gfp_t gfp_mask = GFP_TRANSHUGE_LIGHT | __GFP_THISNODE; + gfp_t this_node = 0; - /* Always do synchronous compaction */ - if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE | __GFP_THISNODE | - (vma_madvised ? 0 : __GFP_NORETRY); +#ifdef CONFIG_NUMA + struct mempolicy *pol; + /* + * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not + * specified, to express a general desire to stay on the current + * node for optimistic allocation attempts. If the defrag mode + * and/or madvise hint requires the direct reclaim then we prefer + * to fallback to other node rather than node reclaim because that + * can lead to excessive reclaim even though there is free memory + * on other nodes. We expect that NUMA preferences are specified + * by memory policies. + */ + pol = get_vma_policy(vma, addr); + if (pol->mode != MPOL_BIND) + this_node = __GFP_THISNODE; + mpol_cond_put(pol); +#endif - /* Kick kcompactd and fail quickly */ + if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) + return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return gfp_mask | __GFP_KSWAPD_RECLAIM; - - /* Synchronous compaction if madvised, otherwise kick kcompactd */ + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) - return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); - - /* Only do synchronous compaction if madvised */ + return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : + __GFP_KSWAPD_RECLAIM | this_node); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) - return gfp_mask | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); - - return gfp_mask; + return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : + this_node); + return GFP_TRANSHUGE_LIGHT | this_node; } /* Caller must hold page table lock. */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9c9877a43d58..65e0874fce17 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1734,7 +1734,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); -- cgit v1.2.3