From 74d609585d8bd6083bd9d75bc1fd2c0d3851bcc5 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 10:01:45 -0500 Subject: page cache: Add and replace pages using the XArray Use the XArray APIs to add and replace pages in the page cache. This removes two uses of the radix tree preload API and is significantly shorter code. It also removes the last user of __radix_tree_create() outside radix-tree.c itself, so make it static. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..6ea50cf41b4c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -299,8 +299,12 @@ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); void workingset_activation(struct page *page); -/* Do not use directly, use workingset_lookup_update */ -void workingset_update_node(struct radix_tree_node *node); +/* Only track the nodes of mappings with shadow entries */ +void workingset_update_node(struct xa_node *node); +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ + xas_set_update(xas, workingset_update_node); \ +} while (0) /* Returns workingset_update_node() if the mapping has shadow entries. */ #define workingset_lookup_update(mapping) \ -- cgit v1.2.3 From a97e7904c0806309fd77103005bb7820c3f1c5e4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 24 Nov 2017 14:24:59 -0500 Subject: mm: Convert workingset to XArray We construct an XA_STATE and use it to delete the node with xas_store() rather than adding a special function for this unique use case. Includes a test that simulates this usage for the test suite. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 9 -------- lib/test_xarray.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/workingset.c | 51 +++++++++++++++++------------------------ 3 files changed, 86 insertions(+), 39 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6ea50cf41b4c..112cebcf0402 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -306,15 +306,6 @@ void workingset_update_node(struct xa_node *node); xas_set_update(xas, workingset_update_node); \ } while (0) -/* Returns workingset_update_node() if the mapping has shadow entries. */ -#define workingset_lookup_update(mapping) \ -({ \ - radix_tree_update_node_t __helper = workingset_update_node; \ - if (dax_mapping(mapping) || shmem_mapping(mapping)) \ - __helper = NULL; \ - __helper; \ -}) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index a752e6a37e6f..128c6489082f 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -863,6 +863,67 @@ static noinline void check_create_range(struct xarray *xa) check_create_range_3(); } +static LIST_HEAD(shadow_nodes); + +static void test_update_node(struct xa_node *node) +{ + if (node->count && node->count == node->nr_values) { + if (list_empty(&node->private_list)) + list_add(&shadow_nodes, &node->private_list); + } else { + if (!list_empty(&node->private_list)) + list_del_init(&node->private_list); + } +} + +static noinline void shadow_remove(struct xarray *xa) +{ + struct xa_node *node; + + xa_lock(xa); + while ((node = list_first_entry_or_null(&shadow_nodes, + struct xa_node, private_list))) { + XA_STATE(xas, node->array, 0); + XA_BUG_ON(xa, node->array != xa); + list_del_init(&node->private_list); + xas.xa_node = xa_parent_locked(node->array, node); + xas.xa_offset = node->offset; + xas.xa_shift = node->shift + XA_CHUNK_SHIFT; + xas_set_update(&xas, test_update_node); + xas_store(&xas, NULL); + } + xa_unlock(xa); +} + +static noinline void check_workingset(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + xas_set_update(&xas, test_update_node); + + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(0)); + xas_next(&xas); + xas_store(&xas, xa_mk_value(1)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + XA_BUG_ON(xa, list_empty(&shadow_nodes)); + + xas_lock(&xas); + xas_next(&xas); + xas_store(&xas, &xas); + XA_BUG_ON(xa, !list_empty(&shadow_nodes)); + + xas_store(&xas, xa_mk_value(2)); + xas_unlock(&xas); + XA_BUG_ON(xa, list_empty(&shadow_nodes)); + + shadow_remove(xa); + XA_BUG_ON(xa, !list_empty(&shadow_nodes)); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -916,6 +977,10 @@ static int xarray_checks(void) check_create_range(&array); check_store_iter(&array); + check_workingset(&array, 0); + check_workingset(&array, 64); + check_workingset(&array, 4096); + printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; } diff --git a/mm/workingset.c b/mm/workingset.c index c201cbb8c00f..5cfb29ec3fd9 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -148,7 +148,7 @@ * and activations is maintained (node->inactive_age). * * On eviction, a snapshot of this counter (along with some bits to - * identify the node) is stored in the now empty page cache radix tree + * identify the node) is stored in the now empty page cache * slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible @@ -162,7 +162,7 @@ /* * Eviction timestamps need to be able to cover the full range of - * actionable refaults. However, bits are tight in the radix tree + * actionable refaults. However, bits are tight in the xarray * entry, and after storing the identifier for the lruvec there might * not be enough left to represent every single actionable refault. In * that case, we have to sacrifice granularity for distance, and group @@ -339,7 +339,7 @@ out: static struct list_lru shadow_nodes; -void workingset_update_node(struct radix_tree_node *node) +void workingset_update_node(struct xa_node *node) { /* * Track non-empty nodes that contain only shadow entries; @@ -368,7 +368,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, nodes = list_lru_shrink_count(&shadow_nodes, sc); /* - * Approximate a reasonable limit for the radix tree nodes + * Approximate a reasonable limit for the nodes * containing shadow entries. We don't need to keep more * shadow entries than possible pages on the active list, * since refault distances bigger than that are dismissed. @@ -383,11 +383,11 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, * worst-case density of 1/8th. Below that, not all eligible * refaults can be detected anymore. * - * On 64-bit with 7 radix_tree_nodes per page and 64 slots + * On 64-bit with 7 xa_nodes per page and 64 slots * each, this will reclaim shadow entries when they consume * ~1.8% of available memory: * - * PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE + * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE */ if (sc->memcg) { cache = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, @@ -396,7 +396,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, cache = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) + node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE); } - max_nodes = cache >> (RADIX_TREE_MAP_SHIFT - 3); + max_nodes = cache >> (XA_CHUNK_SHIFT - 3); if (!nodes) return SHRINK_EMPTY; @@ -409,11 +409,11 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, static enum lru_status shadow_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, - void *arg) + void *arg) __must_hold(lru_lock) { + struct xa_node *node = container_of(item, struct xa_node, private_list); + XA_STATE(xas, node->array, 0); struct address_space *mapping; - struct radix_tree_node *node; - unsigned int i; int ret; /* @@ -421,14 +421,13 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * the shadow node LRU under the i_pages lock and the * lru_lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the lru_lock pins any - * address_space that has radix tree nodes on the LRU. + * address_space that has nodes on the LRU. * * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the lru_lock. */ - node = container_of(item, struct xa_node, private_list); mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ @@ -450,25 +449,17 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; - for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { - if (node->slots[i]) { - if (WARN_ON_ONCE(!xa_is_value(node->slots[i]))) - goto out_invalid; - if (WARN_ON_ONCE(!node->nr_values)) - goto out_invalid; - if (WARN_ON_ONCE(!mapping->nrexceptional)) - goto out_invalid; - node->slots[i] = NULL; - node->nr_values--; - node->count--; - mapping->nrexceptional--; - } - } - if (WARN_ON_ONCE(node->nr_values)) - goto out_invalid; + mapping->nrexceptional -= node->nr_values; + xas.xa_node = xa_parent_locked(&mapping->i_pages, node); + xas.xa_offset = node->offset; + xas.xa_shift = node->shift + XA_CHUNK_SHIFT; + xas_set_update(&xas, workingset_update_node); + /* + * We could store a shadow entry here which was the minimum of the + * shadow entries we were tracking ... + */ + xas_store(&xas, NULL); inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); - __radix_tree_delete_node(&mapping->i_pages, node, - workingset_lookup_update(mapping)); out_invalid: xa_unlock_irq(&mapping->i_pages); -- cgit v1.2.3 From 4e17ec250fce0eba9b70a91c9622da2748a3ec50 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 29 Nov 2017 08:32:39 -0500 Subject: mm: Convert delete_from_swap_cache to XArray Both callers of __delete_from_swap_cache have the swp_entry_t already, so pass that in to make constructing the XA_STATE easier. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 5 +++-- mm/swap_state.c | 24 ++++++++++-------------- mm/vmscan.c | 2 +- 3 files changed, 14 insertions(+), 17 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index 112cebcf0402..cb479bf5842e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -403,7 +403,7 @@ extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); -extern void __delete_from_swap_cache(struct page *); +extern void __delete_from_swap_cache(struct page *, swp_entry_t entry); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); @@ -557,7 +557,8 @@ static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, return -1; } -static inline void __delete_from_swap_cache(struct page *page) +static inline void __delete_from_swap_cache(struct page *page, + swp_entry_t entry) { } diff --git a/mm/swap_state.c b/mm/swap_state.c index 850314c2c3ab..f393c994cc60 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -154,23 +154,22 @@ unlock: * This must be called only on pages that have * been verified to be in the swap cache. */ -void __delete_from_swap_cache(struct page *page) +void __delete_from_swap_cache(struct page *page, swp_entry_t entry) { - struct address_space *address_space; + struct address_space *address_space = swap_address_space(entry); int i, nr = hpage_nr_pages(page); - swp_entry_t entry; - pgoff_t idx; + pgoff_t idx = swp_offset(entry); + XA_STATE(xas, &address_space->i_pages, idx); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); VM_BUG_ON_PAGE(PageWriteback(page), page); - entry.val = page_private(page); - address_space = swap_address_space(entry); - idx = swp_offset(entry); for (i = 0; i < nr; i++) { - radix_tree_delete(&address_space->i_pages, idx + i); + void *entry = xas_store(&xas, NULL); + VM_BUG_ON_PAGE(entry != page + i, entry); set_page_private(page + i, 0); + xas_next(&xas); } ClearPageSwapCache(page); address_space->nrpages -= nr; @@ -243,14 +242,11 @@ fail: */ void delete_from_swap_cache(struct page *page) { - swp_entry_t entry; - struct address_space *address_space; - - entry.val = page_private(page); + swp_entry_t entry = { .val = page_private(page) }; + struct address_space *address_space = swap_address_space(entry); - address_space = swap_address_space(entry); xa_lock_irq(&address_space->i_pages); - __delete_from_swap_cache(page); + __delete_from_swap_cache(page, entry); xa_unlock_irq(&address_space->i_pages); put_swap_page(page, entry); diff --git a/mm/vmscan.c b/mm/vmscan.c index c7ce2c161225..80f731cf974e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -923,7 +923,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); - __delete_from_swap_cache(page); + __delete_from_swap_cache(page, swap); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); } else { -- cgit v1.2.3 From 1899ad18c6072d689896badafb81267b0a1092a4 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:04 -0700 Subject: mm: workingset: tell cache transitions from workingset thrashing Refaults happen during transitions between workingsets as well as in-place thrashing. Knowing the difference between the two has a range of applications, including measuring the impact of memory shortage on the system performance, as well as the ability to smarter balance pressure between the filesystem cache and the swap-backed workingset. During workingset transitions, inactive cache refaults and pushes out established active cache. When that active cache isn't stale, however, and also ends up refaulting, that's bonafide thrashing. Introduce a new page flag that tells on eviction whether the page has been active or not in its lifetime. This bit is then stored in the shadow entry, to classify refaults as transitioning or thrashing. How many page->flags does this leave us with on 32-bit? 20 bits are always page flags 21 if you have an MMU 23 with the zone bits for DMA, Normal, HighMem, Movable 29 with the sparsemem section bits 30 if PAE is enabled 31 with this patch. So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If that's not enough, the system can switch to discontigmem and re-gain the 6 or 7 sparsemem section bits. Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/linux/page-flags.h | 5 ++- include/linux/swap.h | 2 +- include/trace/events/mmflags.h | 1 + mm/filemap.c | 9 ++-- mm/huge_memory.c | 1 + mm/migrate.c | 2 + mm/swap_state.c | 1 + mm/vmscan.c | 1 + mm/vmstat.c | 1 + mm/workingset.c | 95 +++++++++++++++++++++++++++--------------- 11 files changed, 77 insertions(+), 42 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bbeba21f6a3..ba51d5bf7af1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74bee8cecf4c..4d99504f6496 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -69,13 +69,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -280,6 +281,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..b93740d72e78 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -296,7 +296,7 @@ struct vma_swap_readahead { /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); /* Do not use directly, use workingset_lookup_update */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index a81cffb76d89..a1675d43777e 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -88,6 +88,7 @@ {1UL << PG_dirty, "dirty" }, \ {1UL << PG_lru, "lru" }, \ {1UL << PG_active, "active" }, \ + {1UL << PG_workingset, "workingset" }, \ {1UL << PG_slab, "slab" }, \ {1UL << PG_owner_priv_1, "owner_priv_1" }, \ {1UL << PG_arch_1, "arch_1" }, \ diff --git a/mm/filemap.c b/mm/filemap.c index de6fed2a0815..7997adce5a29 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -915,12 +915,9 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - if (!(gfp_mask & __GFP_WRITE) && - shadow && workingset_refault(shadow)) { - SetPageActive(page); - workingset_activation(page); - } else - ClearPageActive(page); + WARN_ON_ONCE(PageActive(page)); + if (!(gfp_mask & __GFP_WRITE) && shadow) + workingset_refault(page, shadow); lru_cache_add(page); } return ret; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index deed97fba979..8ea1b36bd452 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2369,6 +2369,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | + (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | (1L << PG_dirty))); diff --git a/mm/migrate.c b/mm/migrate.c index 84381b55b2bd..1ea27b343ccd 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -685,6 +685,8 @@ void migrate_page_states(struct page *newpage, struct page *page) SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); + if (PageWorkingset(page)) + SetPageWorkingset(newpage); if (PageChecked(page)) SetPageChecked(newpage); if (PageMappedToDisk(page)) diff --git a/mm/swap_state.c b/mm/swap_state.c index ecee9c6c4cc1..0d6a7f268d2e 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -448,6 +448,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * Initiate read into locked page and return. */ + SetPageWorkingset(new_page); lru_cache_add_anon(new_page); *new_page_allocated = true; return new_page; diff --git a/mm/vmscan.c b/mm/vmscan.c index 961401c46334..87e9fef341d2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2145,6 +2145,7 @@ static void shrink_active_list(unsigned long nr_to_scan, } ClearPageActive(page); /* we are de-activating */ + SetPageWorkingset(page); list_add(&page->lru, &l_inactive); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 2cec2fa4c8ae..d918f6192d15 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1145,6 +1145,7 @@ const char * const vmstat_text[] = { "nr_isolated_file", "workingset_refault", "workingset_activate", + "workingset_restore", "workingset_nodereclaim", "nr_anon_pages", "nr_mapped", diff --git a/mm/workingset.c b/mm/workingset.c index 7d5fa0dd2b38..99b7f7c09b13 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -121,7 +121,7 @@ * the only thing eating into inactive list space is active pages. * * - * Activating refaulting pages + * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given @@ -134,6 +134,10 @@ * used less frequently than the refaulting page - or even not used at * all anymore. * + * That means if inactive cache is refaulting with a suitable refault + * distance, we assume the cache workingset is transitioning and put + * pressure on the current active list. + * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. @@ -141,6 +145,14 @@ * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * + * Refaulting active pages + * + * If on the other hand the refaulting pages have recently been + * deactivated, it means that the active list is no longer protecting + * actively used cache from reclaim. The cache is NOT transitioning to + * a different workingset; the existing workingset is thrashing in the + * space allocated to the page cache. + * * * Implementation * @@ -156,8 +168,7 @@ */ #define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - NODES_SHIFT + \ - MEM_CGROUP_ID_SHIFT) + 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* @@ -170,23 +181,28 @@ */ static unsigned int bucket_order __read_mostly; -static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) +static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, + bool workingset) { eviction >>= bucket_order; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; + eviction = (eviction << 1) | workingset; eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, - unsigned long *evictionp) + unsigned long *evictionp, bool *workingsetp) { unsigned long entry = (unsigned long)shadow; int memcgid, nid; + bool workingset; entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + workingset = entry & 1; + entry >>= 1; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -195,6 +211,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; + *workingsetp = workingset; } /** @@ -207,8 +224,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, */ void *workingset_eviction(struct address_space *mapping, struct page *page) { - struct mem_cgroup *memcg = page_memcg(page); struct pglist_data *pgdat = page_pgdat(page); + struct mem_cgroup *memcg = page_memcg(page); int memcgid = mem_cgroup_id(memcg); unsigned long eviction; struct lruvec *lruvec; @@ -220,30 +237,30 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) lruvec = mem_cgroup_lruvec(pgdat, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); - return pack_shadow(memcgid, pgdat, eviction); + return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } /** * workingset_refault - evaluate the refault of a previously evicted page + * @page: the freshly allocated replacement page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously * evicted page in the context of the node it was allocated in. - * - * Returns %true if the page should be activated, %false otherwise. */ -bool workingset_refault(void *shadow) +void workingset_refault(struct page *page, void *shadow) { unsigned long refault_distance; + struct pglist_data *pgdat; unsigned long active_file; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; - struct pglist_data *pgdat; + bool workingset; int memcgid; - unpack_shadow(shadow, &memcgid, &pgdat, &eviction); + unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* @@ -263,41 +280,51 @@ bool workingset_refault(void *shadow) * configurations instead. */ memcg = mem_cgroup_from_id(memcgid); - if (!mem_cgroup_disabled() && !memcg) { - rcu_read_unlock(); - return false; - } + if (!mem_cgroup_disabled() && !memcg) + goto out; lruvec = mem_cgroup_lruvec(pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); /* - * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. + * Calculate the refault distance * - * There is a special case: usually, shadow entries have a - * short lifetime and are either refaulted or reclaimed along - * with the inode before they get too old. But it is not - * impossible for the inactive_age to lap a shadow entry in - * the field, which can then can result in a false small - * refault distance, leading to a false activation should this - * old entry actually refault again. However, earlier kernels - * used to deactivate unconditionally with *every* reclaim - * invocation for the longest time, so the occasional - * inappropriate activation leading to pressure on the active - * list is not a problem. + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. There is a + * special case: usually, shadow entries have a short lifetime + * and are either refaulted or reclaimed along with the inode + * before they get too old. But it is not impossible for the + * inactive_age to lap a shadow entry in the field, which can + * then result in a false small refault distance, leading to a + * false activation should this old entry actually refault + * again. However, earlier kernels used to deactivate + * unconditionally with *every* reclaim invocation for the + * longest time, so the occasional inappropriate activation + * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; inc_lruvec_state(lruvec, WORKINGSET_REFAULT); - if (refault_distance <= active_file) { - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); - rcu_read_unlock(); - return true; + /* + * Compare the distance to the existing workingset size. We + * don't act on pages that couldn't stay resident even if all + * the memory was available to the page cache. + */ + if (refault_distance > active_file) + goto out; + + SetPageActive(page); + atomic_long_inc(&lruvec->inactive_age); + inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); + + /* Page was active prior to eviction */ + if (workingset) { + SetPageWorkingset(page); + inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } +out: rcu_read_unlock(); - return false; } /** -- cgit v1.2.3 From bc4ae27d817a4e92071ef67cb6368120cfabe7ec Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 26 Oct 2018 15:10:51 -0700 Subject: mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS The SWP_FILE flag serves two purposes: to make swap_{read,write}page() go through the filesystem, and to make swapoff() call ->swap_deactivate(). For Btrfs, we want the latter but not the former, so split this flag into two. This makes us always call ->swap_deactivate() if ->swap_activate() succeeded, not just if it didn't add any swap extents itself. This also resolves the issue of the very misleading name of SWP_FILE, which is only used for swap files over NFS. Link: http://lkml.kernel.org/r/6d63d8668c4287a4f6d203d65696e96f80abdfc7.1536704650.git.osandov@fb.com Signed-off-by: Omar Sandoval Reviewed-by: Nikolay Borisov Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: David Sterba Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 13 +++++++------ mm/page_io.c | 6 +++--- mm/swapfile.c | 13 ++++++++----- 3 files changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux/swap.h') diff --git a/include/linux/swap.h b/include/linux/swap.h index b93740d72e78..38195f5c96b1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -167,13 +167,14 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ - SWP_FILE = (1 << 7), /* set after swap_activate success */ - SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ - SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ - SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ - SWP_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */ + SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ + SWP_FS = (1 << 8), /* swap file goes through fs */ + SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ + SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ + SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 13), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL diff --git a/mm/page_io.c b/mm/page_io.c index 573d3663d846..a451ffa9491c 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -283,7 +283,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct kiocb kiocb; struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -365,7 +365,7 @@ int swap_readpage(struct page *page, bool synchronous) goto out; } - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -423,7 +423,7 @@ int swap_set_page_dirty(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct address_space *mapping = sis->swap_file->f_mapping; VM_BUG_ON_PAGE(!PageSwapCache(page), page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2681e50592c5..f0c7e4c11bab 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1003,7 +1003,7 @@ start_over: goto nextsi; } if (size == SWAPFILE_CLUSTER) { - if (!(si->flags & SWP_FILE)) + if (!(si->flags & SWP_FS)) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, @@ -2299,12 +2299,13 @@ static void destroy_swap_extents(struct swap_info_struct *sis) kfree(se); } - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; - sis->flags &= ~SWP_FILE; - mapping->a_ops->swap_deactivate(swap_file); + sis->flags &= ~SWP_ACTIVATED; + if (mapping->a_ops->swap_deactivate) + mapping->a_ops->swap_deactivate(swap_file); } } @@ -2400,8 +2401,10 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); + if (ret >= 0) + sis->flags |= SWP_ACTIVATED; if (!ret) { - sis->flags |= SWP_FILE; + sis->flags |= SWP_FS; ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; } -- cgit v1.2.3