From 0538a82c39e94d49fa6985c6a0101ca819be11ee Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 13 Oct 2022 15:31:13 -0400 Subject: mm: vmscan: make rotations a secondary factor in balancing anon vs file We noticed a 2% webserver throughput regression after upgrading from 5.6. This could be tracked down to a shift in the anon/file reclaim balance (confirmed with swappiness) that resulted in worse reclaim efficiency and thus more kswapd activity for the same outcome. The change that exposed the problem is aae466b0052e ("mm/swap: implement workingset detection for anonymous LRU"). By qualifying swapins based on their refault distance, it lowered the cost of anon reclaim in this workload, in turn causing (much) more anon scanning than before. Scanning the anon list is more expensive due to the higher ratio of mmapped pages that may rotate during reclaim, and so the result was an increase in %sys time. Right now, rotations aren't considered a cost when balancing scan pressure between LRUs. We can end up with very few file refaults putting all the scan pressure on hot anon pages that are rotated en masse, don't get reclaimed, and never push back on the file LRU again. We still only reclaim file cache in that case, but we burn a lot CPU rotating anon pages. It's "fair" from an LRU age POV, but doesn't reflect the real cost it imposes on the system. Consider rotations as a secondary factor in balancing the LRUs. This doesn't attempt to make a precise comparison between IO cost and CPU cost, it just says: if reloads are about comparable between the lists, or rotations are overwhelmingly different, adjust for CPU work. This fixed the regression on our webservers. It has since been deployed to the entire Meta fleet and hasn't caused any problems. Link: https://lkml.kernel.org/r/20221013193113.726425-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Cc: Rik van Riel Signed-off-by: Andrew Morton --- include/linux/swap.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index a18cf4b7c724..369d7799205d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -384,8 +384,9 @@ extern unsigned long totalreserve_pages; /* linux/mm/swap.c */ -void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); -void lru_note_cost_folio(struct folio *); +void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_io, unsigned int nr_rotated); +void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void lru_cache_add(struct page *); -- cgit v1.2.3 From ca92ea3dc5a2b01f98e9f02b7a6bc03be06fe124 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Sun, 30 Oct 2022 17:41:50 -0400 Subject: mm: always compile in pte markers Patch series "mm: Use pte marker for swapin errors". This series uses the pte marker to replace the swapin error swap entry, then we save one more swap entry slot for swap devices. A new pte marker bit is defined. This patch (of 2): The PTE markers code is tiny and now it's enabled for most of the distributions. It's fine to keep it as-is, but to make a broader use of it (e.g. replacing read error swap entry) it needs to be there always otherwise we need special code path to take care of !PTE_MARKER case. It'll be easier just make pte marker always exist. Use this chance to extend its usage to anonymous too by simply touching up some of the old comments, because it'll be used for anonymous pages in the follow up patches. Link: https://lkml.kernel.org/r/20221030214151.402274-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20221030214151.402274-2-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Huang Ying Reviewed-by: Miaohe Lin Acked-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Naoya Horiguchi Cc: Peter Xu Signed-off-by: Andrew Morton --- include/linux/swap.h | 10 +++------- include/linux/swapops.h | 31 ------------------------------- mm/Kconfig | 7 ------- mm/memory.c | 7 +++---- 4 files changed, 6 insertions(+), 49 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index 369d7799205d..211aeca9bfa7 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -60,17 +60,13 @@ static inline int current_is_kswapd(void) SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \ SWP_PTE_MARKER_NUM) /* - * PTE markers are used to persist information onto PTEs that are mapped with - * file-backed memories. As its name "PTE" hints, it should only be applied to - * the leaves of pgtables. + * PTE markers are used to persist information onto PTEs that otherwise + * should be a none pte. As its name "PTE" hints, it should only be + * applied to the leaves of pgtables. */ -#ifdef CONFIG_PTE_MARKER #define SWP_PTE_MARKER_NUM 1 #define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM) -#else -#define SWP_PTE_MARKER_NUM 0 -#endif /* * Unaddressable device memory support. See include/linux/hmm.h and diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 3ba9bf56899d..35c1fe62d2e1 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -412,8 +412,6 @@ typedef unsigned long pte_marker; #define PTE_MARKER_UFFD_WP BIT(0) #define PTE_MARKER_MASK (PTE_MARKER_UFFD_WP) -#ifdef CONFIG_PTE_MARKER - static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { return swp_entry(SWP_PTE_MARKER, marker); @@ -434,32 +432,6 @@ static inline bool is_pte_marker(pte_t pte) return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); } -#else /* CONFIG_PTE_MARKER */ - -static inline swp_entry_t make_pte_marker_entry(pte_marker marker) -{ - /* This should never be called if !CONFIG_PTE_MARKER */ - WARN_ON_ONCE(1); - return swp_entry(0, 0); -} - -static inline bool is_pte_marker_entry(swp_entry_t entry) -{ - return false; -} - -static inline pte_marker pte_marker_get(swp_entry_t entry) -{ - return 0; -} - -static inline bool is_pte_marker(pte_t pte) -{ - return false; -} - -#endif /* CONFIG_PTE_MARKER */ - static inline pte_t make_pte_marker(pte_marker marker) { return swp_entry_to_pte(make_pte_marker_entry(marker)); @@ -477,9 +449,6 @@ static inline pte_t make_pte_marker(pte_marker marker) * memory, kernel-only memory (including when the system is during-boot), * non-ram based generic file-system. It's fine to be used even there, but the * extra pte marker check will be pure overhead. - * - * For systems configured with !CONFIG_PTE_MARKER this will be automatically - * optimized to pte_none(). */ static inline int pte_none_mostly(pte_t pte) { diff --git a/mm/Kconfig b/mm/Kconfig index 57e1d8c5b505..4b28800d9be1 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1107,17 +1107,10 @@ config HAVE_ARCH_USERFAULTFD_MINOR help Arch has userfaultfd minor fault support -config PTE_MARKER - bool - - help - Allows to create marker PTEs for file-backed memory. - config PTE_MARKER_UFFD_WP bool "Userfaultfd write protection support for shmem/hugetlbfs" default y depends on HAVE_ARCH_USERFAULTFD_WP - select PTE_MARKER help Allows to create marker PTEs for userfaultfd write protection diff --git a/mm/memory.c b/mm/memory.c index 659620b6770f..b79d27533722 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3662,11 +3662,10 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf) unsigned long marker = pte_marker_get(entry); /* - * PTE markers should always be with file-backed memories, and the - * marker should never be empty. If anything weird happened, the best - * thing to do is to kill the process along with its mm. + * PTE markers should never be empty. If anything weird happened, + * the best thing to do is to kill the process along with its mm. */ - if (WARN_ON_ONCE(vma_is_anonymous(vmf->vma) || !marker)) + if (WARN_ON_ONCE(!marker)) return VM_FAULT_SIGBUS; if (pte_marker_entry_uffd_wp(entry)) -- cgit v1.2.3 From 15520a3f046998e3f57e695743e99b0875e2dae7 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Sun, 30 Oct 2022 17:41:51 -0400 Subject: mm: use pte markers for swap errors PTE markers are ideal mechanism for things like SWP_SWAPIN_ERROR. Using a whole swap entry type for this purpose can be an overkill, especially if we already have PTE markers. Define a new bit for swapin error and replace it with pte markers. Then we can safely drop SWP_SWAPIN_ERROR and give one device slot back to swap. We used to have SWP_SWAPIN_ERROR taking the page pfn as part of the swap entry, but it's never used. Neither do I see how it can be useful because normally the swapin failure should not be caused by a bad page but bad swap device. Drop it alongside. Link: https://lkml.kernel.org/r/20221030214151.402274-3-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Huang Ying Reviewed-by: Miaohe Lin Acked-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Naoya Horiguchi Signed-off-by: Andrew Morton --- include/linux/swap.h | 6 +----- include/linux/swapops.h | 26 ++++++++++++++------------ mm/memory.c | 6 ++++-- mm/shmem.c | 2 +- mm/swapfile.c | 2 +- 5 files changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index 211aeca9bfa7..fec6647a289a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -55,10 +55,6 @@ static inline int current_is_kswapd(void) * actions on faults. */ -#define SWP_SWAPIN_ERROR_NUM 1 -#define SWP_SWAPIN_ERROR (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ - SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \ - SWP_PTE_MARKER_NUM) /* * PTE markers are used to persist information onto PTEs that otherwise * should be a none pte. As its name "PTE" hints, it should only be @@ -121,7 +117,7 @@ static inline int current_is_kswapd(void) #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ - SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM) + SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 35c1fe62d2e1..27ade4f22abb 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -162,16 +162,6 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) return xa_mk_value(entry.val); } -static inline swp_entry_t make_swapin_error_entry(struct page *page) -{ - return swp_entry(SWP_SWAPIN_ERROR, page_to_pfn(page)); -} - -static inline int is_swapin_error_entry(swp_entry_t entry) -{ - return swp_type(entry) == SWP_SWAPIN_ERROR; -} - #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { @@ -409,8 +399,9 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) typedef unsigned long pte_marker; -#define PTE_MARKER_UFFD_WP BIT(0) -#define PTE_MARKER_MASK (PTE_MARKER_UFFD_WP) +#define PTE_MARKER_UFFD_WP BIT(0) +#define PTE_MARKER_SWAPIN_ERROR BIT(1) +#define PTE_MARKER_MASK (BIT(2) - 1) static inline swp_entry_t make_pte_marker_entry(pte_marker marker) { @@ -437,6 +428,17 @@ static inline pte_t make_pte_marker(pte_marker marker) return swp_entry_to_pte(make_pte_marker_entry(marker)); } +static inline swp_entry_t make_swapin_error_entry(void) +{ + return make_pte_marker_entry(PTE_MARKER_SWAPIN_ERROR); +} + +static inline int is_swapin_error_entry(swp_entry_t entry) +{ + return is_pte_marker_entry(entry) && + (pte_marker_get(entry) & PTE_MARKER_SWAPIN_ERROR); +} + /* * This is a special version to check pte_none() just to cover the case when * the pte is a pte marker. It existed because in many cases the pte marker diff --git a/mm/memory.c b/mm/memory.c index b79d27533722..142c4229549b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3668,6 +3668,10 @@ static vm_fault_t handle_pte_marker(struct vm_fault *vmf) if (WARN_ON_ONCE(!marker)) return VM_FAULT_SIGBUS; + /* Higher priority than uffd-wp when data corrupted */ + if (marker & PTE_MARKER_SWAPIN_ERROR) + return VM_FAULT_SIGBUS; + if (pte_marker_entry_uffd_wp(entry)) return pte_marker_handle_uffd_wp(vmf); @@ -3727,8 +3731,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; - } else if (is_swapin_error_entry(entry)) { - ret = VM_FAULT_SIGBUS; } else if (is_pte_marker_entry(entry)) { ret = handle_pte_marker(vmf); } else { diff --git a/mm/shmem.c b/mm/shmem.c index 0a7c4a748811..7428ae3fa4b9 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1682,7 +1682,7 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, swp_entry_t swapin_error; void *old; - swapin_error = make_swapin_error_entry(&folio->page); + swapin_error = make_swapin_error_entry(); old = xa_cmpxchg_irq(&mapping->i_pages, index, swp_to_radix_entry(swap), swp_to_radix_entry(swapin_error), 0); diff --git a/mm/swapfile.c b/mm/swapfile.c index 72e481aacd5d..03fe0949f6b2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1781,7 +1781,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte_t pteval; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); - pteval = swp_entry_to_pte(make_swapin_error_entry(page)); + pteval = swp_entry_to_pte(make_swapin_error_entry()); set_pte_at(vma->vm_mm, addr, pte, pteval); swap_free(entry); ret = 0; -- cgit v1.2.3 From 7cc8f9c7146a5c2dad6e71653c4f69972e73df6b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 9 Nov 2022 12:30:50 -0800 Subject: mm: mmu_gather: prepare to gather encoded page pointers with flags This is purely a preparatory patch that makes all the data structures ready for encoding flags with the mmu_gather page pointers. The code currently always sets the flag to zero and doesn't use it yet, but now it's tracking the type state along. The next step will be to actually start using it. Link: https://lkml.kernel.org/r/20221109203051.1835763-3-torvalds@linux-foundation.org Signed-off-by: Linus Torvalds Acked-by: Johannes Weiner Acked-by: Hugh Dickins Signed-off-by: Andrew Morton --- arch/s390/include/asm/tlb.h | 8 +++++--- include/asm-generic/tlb.h | 9 +++++---- include/linux/swap.h | 2 +- mm/mmu_gather.c | 8 ++++---- mm/swap_state.c | 11 ++++------- 5 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux/swap.h') diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 3a5c8fb590e5..05142226d65d 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -25,7 +25,8 @@ void __tlb_remove_table(void *_table); static inline void tlb_flush(struct mmu_gather *tlb); static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size); + struct encoded_page *page, + int page_size); #define tlb_flush tlb_flush #define pte_free_tlb pte_free_tlb @@ -42,9 +43,10 @@ static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, * has already been freed, so just do free_page_and_swap_cache. */ static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, - struct page *page, int page_size) + struct encoded_page *page, + int page_size) { - free_page_and_swap_cache(page); + free_page_and_swap_cache(encoded_page_ptr(page)); return false; } diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index cab7cfebf40b..54d03d1e712e 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -246,7 +246,7 @@ struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; - struct page *pages[]; + struct encoded_page *encoded_pages[]; }; #define MAX_GATHER_BATCH \ @@ -260,7 +260,8 @@ struct mmu_gather_batch { */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) -extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, +extern bool __tlb_remove_page_size(struct mmu_gather *tlb, + struct encoded_page *page, int page_size); #endif @@ -435,13 +436,13 @@ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) static inline void tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { - if (__tlb_remove_page_size(tlb, page, page_size)) + if (__tlb_remove_page_size(tlb, encode_page(page, 0), page_size)) tlb_flush_mmu(tlb); } static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { - return __tlb_remove_page_size(tlb, page, PAGE_SIZE); + return __tlb_remove_page_size(tlb, encode_page(page, 0), PAGE_SIZE); } /* tlb_remove_page diff --git a/include/linux/swap.h b/include/linux/swap.h index fec6647a289a..b61e2007d156 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -463,7 +463,7 @@ static inline unsigned long total_swapcache_pages(void) extern void free_swap_cache(struct page *page); extern void free_page_and_swap_cache(struct page *); -extern void free_pages_and_swap_cache(struct page **, int); +extern void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 3a2c3f8cad2f..382581c4a9f6 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -48,7 +48,7 @@ static void tlb_batch_pages_flush(struct mmu_gather *tlb) struct mmu_gather_batch *batch; for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { - struct page **pages = batch->pages; + struct encoded_page **pages = batch->encoded_pages; do { /* @@ -77,7 +77,7 @@ static void tlb_batch_list_free(struct mmu_gather *tlb) tlb->local.next = NULL; } -bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) +bool __tlb_remove_page_size(struct mmu_gather *tlb, struct encoded_page *page, int page_size) { struct mmu_gather_batch *batch; @@ -92,13 +92,13 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_ * Add the page and check if we are full. If so * force a flush. */ - batch->pages[batch->nr++] = page; + batch->encoded_pages[batch->nr++] = page; if (batch->nr == batch->max) { if (!tlb_next_batch(tlb)) return true; batch = tlb->active; } - VM_BUG_ON_PAGE(batch->nr > batch->max, page); + VM_BUG_ON_PAGE(batch->nr > batch->max, encoded_page_ptr(page)); return false; } diff --git a/mm/swap_state.c b/mm/swap_state.c index 40fe6f23e105..2927507b43d8 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -303,15 +303,12 @@ void free_page_and_swap_cache(struct page *page) * Passed an array of pages, drop them all from swapcache and then release * them. They are removed from the LRU and freed if this is their last use. */ -void free_pages_and_swap_cache(struct page **pages, int nr) +void free_pages_and_swap_cache(struct encoded_page **pages, int nr) { - struct page **pagep = pages; - int i; - lru_add_drain(); - for (i = 0; i < nr; i++) - free_swap_cache(pagep[i]); - release_pages(pagep, nr); + for (int i = 0; i < nr; i++) + free_swap_cache(encoded_page_ptr(pages[i])); + release_pages(pages, nr); } static inline bool swap_use_vma_readahead(void) -- cgit v1.2.3 From 6e1ca48d0669b0f5efcbaa051b23cd8e651a1614 Mon Sep 17 00:00:00 2001 From: "Vishal Moola (Oracle)" Date: Tue, 1 Nov 2022 10:53:26 -0700 Subject: folio-compat: remove lru_cache_add() There are no longer any callers of lru_cache_add(), so remove it. This saves 79 bytes of kernel text. Also cleanup some comments such that they reference the new folio_add_lru() instead. Link: https://lkml.kernel.org/r/20221101175326.13265-6-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) Reviewed-by: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Miklos Szeredi Signed-off-by: Andrew Morton --- include/linux/swap.h | 1 - mm/folio-compat.c | 6 ------ mm/truncate.c | 2 +- mm/workingset.c | 5 ++++- 4 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index b61e2007d156..0ceed49516ad 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -381,7 +381,6 @@ void lru_note_cost(struct lruvec *lruvec, bool file, void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); -void lru_cache_add(struct page *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 86933fa8f3e1..69ed25790c68 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -76,12 +76,6 @@ bool redirty_page_for_writepage(struct writeback_control *wbc, } EXPORT_SYMBOL(redirty_page_for_writepage); -void lru_cache_add(struct page *page) -{ - folio_add_lru(page_folio(page)); -} -EXPORT_SYMBOL(lru_cache_add); - void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma) { diff --git a/mm/truncate.c b/mm/truncate.c index c7bfd247a651..7b4ea4c4a46b 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -565,7 +565,7 @@ EXPORT_SYMBOL(invalidate_mapping_pages); * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave pages behind because * shrink_page_list() has a temp ref on them, or because they're transiently - * sitting in the lru_cache_add() pagevecs. + * sitting in the folio_add_lru() pagevecs. */ static int invalidate_complete_folio2(struct address_space *mapping, struct folio *folio) diff --git a/mm/workingset.c b/mm/workingset.c index d2d02978588c..1a86645b7b3c 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -492,7 +492,10 @@ void workingset_refault(struct folio *folio, void *shadow) /* Folio was active prior to eviction */ if (workingset) { folio_set_workingset(folio); - /* XXX: Move to lru_cache_add() when it supports new vs putback */ + /* + * XXX: Move to folio_add_lru() when it supports new vs + * putback + */ lru_note_cost_refault(folio); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr); } -- cgit v1.2.3 From 12a5d3955227b0d7e04fb793ccceeb2a1dd275c5 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Fri, 2 Dec 2022 14:35:31 -0800 Subject: mm: add nodes= arg to memory.reclaim The nodes= arg instructs the kernel to only scan the given nodes for proactive reclaim. For example use cases, consider a 2 tier memory system: nodes 0,1 -> top tier nodes 2,3 -> second tier $ echo "1m nodes=0" > memory.reclaim This instructs the kernel to attempt to reclaim 1m memory from node 0. Since node 0 is a top tier node, demotion will be attempted first. This is useful to direct proactive reclaim to specific nodes that are under pressure. $ echo "1m nodes=2,3" > memory.reclaim This instructs the kernel to attempt to reclaim 1m memory in the second tier, since this tier of memory has no demotion targets the memory will be reclaimed. $ echo "1m nodes=0,1" > memory.reclaim Instructs the kernel to reclaim memory from the top tier nodes, which can be desirable according to the userspace policy if there is pressure on the top tiers. Since these nodes have demotion targets, the kernel will attempt demotion first. Since commit 3f1509c57b1b ("Revert "mm/vmscan: never demote for memcg reclaim""), the proactive reclaim interface memory.reclaim does both reclaim and demotion. Reclaim and demotion incur different latency costs to the jobs in the cgroup. Demoted memory would still be addressable by the userspace at a higher latency, but reclaimed memory would need to incur a pagefault. The 'nodes' arg is useful to allow the userspace to control demotion and reclaim independently according to its policy: if the memory.reclaim is called on a node with demotion targets, it will attempt demotion first; if it is called on a node without demotion targets, it will only attempt reclaim. Link: https://lkml.kernel.org/r/20221202223533.1785418-1-almasrymina@google.com Signed-off-by: Mina Almasry Acked-by: Michal Hocko Acked-by: Shakeel Butt Acked-by: Muchun Song Cc: Bagas Sanjaya Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Roman Gushchin Cc: Tejun Heo Cc: Wei Xu Cc: Yang Shi Cc: Yosry Ahmed Cc: zefan li Signed-off-by: Andrew Morton --- Documentation/admin-guide/cgroup-v2.rst | 15 +++++--- include/linux/swap.h | 3 +- mm/memcontrol.c | 67 ++++++++++++++++++++++++++------- mm/vmscan.c | 4 +- 4 files changed, 68 insertions(+), 21 deletions(-) (limited to 'include/linux/swap.h') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 74cec76be9f2..c8ae7c897f14 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1245,17 +1245,13 @@ PAGE_SIZE multiple when read back. This is a simple interface to trigger memory reclaim in the target cgroup. - This file accepts a single key, the number of bytes to reclaim. - No nested keys are currently supported. + This file accepts a string which contains the number of bytes to + reclaim. Example:: echo "1G" > memory.reclaim - The interface can be later extended with nested keys to - configure the reclaim behavior. For example, specify the - type of memory to reclaim from (anon, file, ..). - Please note that the kernel can over or under reclaim from the target cgroup. If less bytes are reclaimed than the specified amount, -EAGAIN is returned. @@ -1267,6 +1263,13 @@ PAGE_SIZE multiple when read back. This means that the networking layer will not adapt based on reclaim induced by memory.reclaim. + This file also allows the user to specify the nodes to reclaim from, + via the 'nodes=' key, for example:: + + echo "1G nodes=0,1" > memory.reclaim + + The above instructs the kernel to reclaim memory from nodes 0,1. + memory.peak A read-only single value file which exists on non-root cgroups. diff --git a/include/linux/swap.h b/include/linux/swap.h index 0ceed49516ad..2787b84eaf12 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -418,7 +418,8 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options); + unsigned int reclaim_options, + nodemask_t *nodemask); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2c7a91689fef..ff65bc23be13 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -63,6 +63,7 @@ #include #include #include +#include #include "internal.h" #include #include @@ -2392,7 +2393,8 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg, psi_memstall_enter(&pflags); nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, - MEMCG_RECLAIM_MAY_SWAP); + MEMCG_RECLAIM_MAY_SWAP, + NULL); psi_memstall_leave(&pflags); } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); @@ -2683,7 +2685,8 @@ retry: psi_memstall_enter(&pflags); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, - gfp_mask, reclaim_options); + gfp_mask, reclaim_options, + NULL); psi_memstall_leave(&pflags); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) @@ -3503,7 +3506,8 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg, } if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) { + memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, + NULL)) { ret = -EBUSY; break; } @@ -3614,7 +3618,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) return -EINTR; if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - MEMCG_RECLAIM_MAY_SWAP)) + MEMCG_RECLAIM_MAY_SWAP, + NULL)) nr_retries--; } @@ -6418,7 +6423,8 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, } reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP); + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, + NULL); if (!reclaimed && !nr_retries--) break; @@ -6467,7 +6473,8 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (nr_reclaims) { if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP)) + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, + NULL)) nr_reclaims--; continue; } @@ -6590,21 +6597,54 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of, return nbytes; } +enum { + MEMORY_RECLAIM_NODES = 0, + MEMORY_RECLAIM_NULL, +}; + +static const match_table_t if_tokens = { + { MEMORY_RECLAIM_NODES, "nodes=%s" }, + { MEMORY_RECLAIM_NULL, NULL }, +}; + static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); unsigned int nr_retries = MAX_RECLAIM_RETRIES; unsigned long nr_to_reclaim, nr_reclaimed = 0; - unsigned int reclaim_options; - int err; + unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP | + MEMCG_RECLAIM_PROACTIVE; + char *old_buf, *start; + substring_t args[MAX_OPT_ARGS]; + int token; + char value[256]; + nodemask_t nodemask = NODE_MASK_ALL; buf = strstrip(buf); - err = page_counter_memparse(buf, "", &nr_to_reclaim); - if (err) - return err; - reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE; + old_buf = buf; + nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE; + if (buf == old_buf) + return -EINVAL; + + buf = strstrip(buf); + + while ((start = strsep(&buf, " ")) != NULL) { + if (!strlen(start)) + continue; + token = match_token(start, if_tokens, args); + match_strlcpy(value, args, sizeof(value)); + switch (token) { + case MEMORY_RECLAIM_NODES: + if (nodelist_parse(value, nodemask) < 0) + return -EINVAL; + break; + default: + return -EINVAL; + } + } + while (nr_reclaimed < nr_to_reclaim) { unsigned long reclaimed; @@ -6621,7 +6661,8 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_to_reclaim - nr_reclaimed, - GFP_KERNEL, reclaim_options); + GFP_KERNEL, reclaim_options, + &nodemask); if (!reclaimed && !nr_retries--) return -EAGAIN; diff --git a/mm/vmscan.c b/mm/vmscan.c index 1a59171c6695..2b42ac9ad755 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -6758,7 +6758,8 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options) + unsigned int reclaim_options, + nodemask_t *nodemask) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; @@ -6773,6 +6774,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), + .nodemask = nodemask, }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put -- cgit v1.2.3