From b1f202060afeb7fcb98473929d26fd3d2093b067 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Fri, 30 Aug 2024 11:03:36 +0100 Subject: [PATCH] mm: remap unused subpages to shared zeropage when splitting isolated thp Patch series "mm: split underused THPs", v5. The current upstream default policy for THP is always. However, Meta uses madvise in production as the current THP=always policy vastly overprovisions THPs in sparsely accessed memory areas, resulting in excessive memory pressure and premature OOM killing. Using madvise + relying on khugepaged has certain drawbacks over THP=always. Using madvise hints mean THPs aren't "transparent" and require userspace changes. Waiting for khugepaged to scan memory and collapse pages into THP can be slow and unpredictable in terms of performance (i.e. you dont know when the collapse will happen), while production environments require predictable performance. If there is enough memory available, its better for both performance and predictability to have a THP from fault time, i.e. THP=always rather than wait for khugepaged to collapse it, and deal with sparsely populated THPs when the system is running out of memory. This patch series is an attempt to mitigate the issue of running out of memory when THP is always enabled. During runtime whenever a THP is being faulted in or collapsed by khugepaged, the THP is added to a list. Whenever memory reclaim happens, the kernel runs the deferred_split shrinker which goes through the list and checks if the THP was underused, i.e. how many of the base 4K pages of the entire THP were zero-filled. If this number goes above a certain threshold, the shrinker will attempt to split that THP. Then at remap time, the pages that were zero-filled are mapped to the shared zeropage, hence saving memory. This method avoids the downside of wasting memory in areas where THP is sparsely filled when THP is always enabled, while still providing the upside THPs like reduced TLB misses without having to use madvise. Meta production workloads that were CPU bound (>99% CPU utilzation) were tested with THP shrinker. The results after 2 hours are as follows: | THP=madvise | THP=always | THP=always | | | + shrinker series | | | + max_ptes_none=409 ----------------------------------------------------------------------------- Performance improvement | - | +1.8% | +1.7% (over THP=madvise) | | | ----------------------------------------------------------------------------- Memory usage | 54.6G | 58.8G (+7.7%) | 55.9G (+2.4%) ----------------------------------------------------------------------------- max_ptes_none=409 means that any THP that has more than 409 out of 512 (80%) zero filled filled pages will be split. To test out the patches, the below commands without the shrinker will invoke OOM killer immediately and kill stress, but will not fail with the shrinker: echo 450 > /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_none mkdir /sys/fs/cgroup/test echo $$ > /sys/fs/cgroup/test/cgroup.procs echo 20M > /sys/fs/cgroup/test/memory.max echo 0 > /sys/fs/cgroup/test/memory.swap.max # allocate twice memory.max for each stress worker and touch 40/512 of # each THP, i.e. vm-stride 50K. # With the shrinker, max_ptes_none of 470 and below won't invoke OOM # killer. # Without the shrinker, OOM killer is invoked immediately irrespective # of max_ptes_none value and kills stress. stress --vm 1 --vm-bytes 40M --vm-stride 50K This patch (of 5): Here being unused means containing only zeros and inaccessible to userspace. When splitting an isolated thp under reclaim or migration, the unused subpages can be mapped to the shared zeropage, hence saving memory. This is particularly helpful when the internal fragmentation of a thp is high, i.e. it has many untouched subpages. This is also a prerequisite for THP low utilization shrinker which will be introduced in later patches, where underutilized THPs are split, and the zero-filled pages are freed saving memory. Link: https://lkml.kernel.org/r/20240830100438.3623486-1-usamaarif642@gmail.com Link: https://lkml.kernel.org/r/20240830100438.3623486-3-usamaarif642@gmail.com Signed-off-by: Yu Zhao Signed-off-by: Usama Arif Tested-by: Shuang Zhai Cc: Alexander Zhu Cc: Barry Song Cc: David Hildenbrand Cc: Domenico Cerasuolo Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Kairui Song Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Nico Pache Cc: Rik van Riel Cc: Roman Gushchin Cc: Ryan Roberts Cc: Shakeel Butt Cc: Shuang Zhai Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/rmap.h | 7 +++- mm/huge_memory.c | 8 ++--- mm/migrate.c | 76 +++++++++++++++++++++++++++++++++++++------- mm/migrate_device.c | 4 +-- 4 files changed, 77 insertions(+), 18 deletions(-) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 91b5935e8485..d5e93e44322e 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -745,7 +745,12 @@ int folio_mkclean(struct folio *); int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma); -void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); +enum rmp_flags { + RMP_LOCKED = 1 << 0, + RMP_USE_SHARED_ZEROPAGE = 1 << 1, +}; + +void remove_migration_ptes(struct folio *src, struct folio *dst, int flags); /* * rmap_walk_control: To control rmap traversing for specific needs diff --git a/mm/huge_memory.c b/mm/huge_memory.c index efc625086dc7..6b69309e002f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3004,7 +3004,7 @@ bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, return false; } -static void remap_page(struct folio *folio, unsigned long nr) +static void remap_page(struct folio *folio, unsigned long nr, int flags) { int i = 0; @@ -3012,7 +3012,7 @@ static void remap_page(struct folio *folio, unsigned long nr) if (!folio_test_anon(folio)) return; for (;;) { - remove_migration_ptes(folio, folio, true); + remove_migration_ptes(folio, folio, RMP_LOCKED | flags); i += folio_nr_pages(folio); if (i >= nr) break; @@ -3222,7 +3222,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, if (nr_dropped) shmem_uncharge(folio->mapping->host, nr_dropped); - remap_page(folio, nr); + remap_page(folio, nr, PageAnon(head) ? RMP_USE_SHARED_ZEROPAGE : 0); /* * set page to its compound_head when split to non order-0 pages, so @@ -3498,7 +3498,7 @@ fail: if (mapping) xas_unlock(&xas); local_irq_enable(); - remap_page(folio, folio_nr_pages(folio)); + remap_page(folio, folio_nr_pages(folio), 0); ret = -EAGAIN; } diff --git a/mm/migrate.c b/mm/migrate.c index 6f9c62c746be..d039863e014b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -204,13 +204,57 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list) return true; } +static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, + struct folio *folio, + unsigned long idx) +{ + struct page *page = folio_page(folio, idx); + bool contains_data; + pte_t newpte; + void *addr; + + VM_BUG_ON_PAGE(PageCompound(page), page); + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(pte_present(*pvmw->pte), page); + + if (folio_test_mlocked(folio) || (pvmw->vma->vm_flags & VM_LOCKED) || + mm_forbids_zeropage(pvmw->vma->vm_mm)) + return false; + + /* + * The pmd entry mapping the old thp was flushed and the pte mapping + * this subpage has been non present. If the subpage is only zero-filled + * then map it to the shared zeropage. + */ + addr = kmap_local_page(page); + contains_data = memchr_inv(addr, 0, PAGE_SIZE); + kunmap_local(addr); + + if (contains_data) + return false; + + newpte = pte_mkspecial(pfn_pte(my_zero_pfn(pvmw->address), + pvmw->vma->vm_page_prot)); + set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte); + + dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio)); + return true; +} + +struct rmap_walk_arg { + struct folio *folio; + bool map_unused_to_zeropage; +}; + /* * Restore a potential migration pte to a working pte entry */ static bool remove_migration_pte(struct folio *folio, - struct vm_area_struct *vma, unsigned long addr, void *old) + struct vm_area_struct *vma, unsigned long addr, void *arg) { - DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION); + struct rmap_walk_arg *rmap_walk_arg = arg; + DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION); while (page_vma_mapped_walk(&pvmw)) { rmap_t rmap_flags = RMAP_NONE; @@ -234,6 +278,9 @@ static bool remove_migration_pte(struct folio *folio, continue; } #endif + if (rmap_walk_arg->map_unused_to_zeropage && + try_to_map_unused_to_zeropage(&pvmw, folio, idx)) + continue; folio_get(folio); pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); @@ -312,14 +359,21 @@ static bool remove_migration_pte(struct folio *folio, * Get rid of all migration entries and replace them by * references to the indicated page. */ -void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked) +void remove_migration_ptes(struct folio *src, struct folio *dst, int flags) { - struct rmap_walk_control rwc = { - .rmap_one = remove_migration_pte, - .arg = src, + struct rmap_walk_arg rmap_walk_arg = { + .folio = src, + .map_unused_to_zeropage = flags & RMP_USE_SHARED_ZEROPAGE, }; - if (locked) + struct rmap_walk_control rwc = { + .rmap_one = remove_migration_pte, + .arg = &rmap_walk_arg, + }; + + VM_BUG_ON_FOLIO((flags & RMP_USE_SHARED_ZEROPAGE) && (src != dst), src); + + if (flags & RMP_LOCKED) rmap_walk_locked(dst, &rwc); else rmap_walk(dst, &rwc); @@ -934,7 +988,7 @@ static int writeout(struct address_space *mapping, struct folio *folio) * At this point we know that the migration attempt cannot * be successful. */ - remove_migration_ptes(folio, folio, false); + remove_migration_ptes(folio, folio, 0); rc = mapping->a_ops->writepage(&folio->page, &wbc); @@ -1098,7 +1152,7 @@ static void migrate_folio_undo_src(struct folio *src, struct list_head *ret) { if (page_was_mapped) - remove_migration_ptes(src, src, false); + remove_migration_ptes(src, src, 0); /* Drop an anon_vma reference if we took one */ if (anon_vma) put_anon_vma(anon_vma); @@ -1336,7 +1390,7 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private, lru_add_drain(); if (old_page_state & PAGE_WAS_MAPPED) - remove_migration_ptes(src, dst, false); + remove_migration_ptes(src, dst, 0); out_unlock_both: folio_unlock(dst); @@ -1474,7 +1528,7 @@ static int unmap_and_move_huge_page(new_folio_t get_new_folio, if (page_was_mapped) remove_migration_ptes(src, - rc == MIGRATEPAGE_SUCCESS ? dst : src, false); + rc == MIGRATEPAGE_SUCCESS ? dst : src, 0); unlock_put_anon: folio_unlock(dst); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 8d687de88a03..9cf26592ac93 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -424,7 +424,7 @@ static unsigned long migrate_device_unmap(unsigned long *src_pfns, continue; folio = page_folio(page); - remove_migration_ptes(folio, folio, false); + remove_migration_ptes(folio, folio, 0); src_pfns[i] = 0; folio_unlock(folio); @@ -840,7 +840,7 @@ void migrate_device_finalize(unsigned long *src_pfns, dst = src; } - remove_migration_ptes(src, dst, false); + remove_migration_ptes(src, dst, 0); folio_unlock(src); if (folio_is_zone_device(src))